System

Abstract

An object of the system according to the embodiment is to inquire about the results of players and games in detail and analyze the results based on conditions.SOLUTION: A system includes a result inquiry part, a game result confirmation part, and a condition result inquiry part. The result inquiry unit inquires about various results such as the batting average and the number of home runs of a player, and the number of wins and the earned run average of a pitcher. A game result confirmation part confirms the game result of the previous day and the present result table based on the result inquired by the result inquiry part. The condition record inquiry section searches for the attendance of spectators and weather information of the day from the game schedule confirmed by the game result confirmation section, and obtains the game record under the conditions.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] Conventional technology has the problem that it is difficult to query the performance of players and games in detail and analyze the performance based on conditions.

[0005] The system according to the embodiment aims to inquire into the performance of players and games in detail and to analyze the performance based on conditions. [Means for solving the problem]

[0006] The system according to the embodiment includes a results inquiry unit, a game result confirmation unit, and a condition results inquiry unit. The results inquiry unit inquires about various results, such as a player's batting average and number of home runs, and a pitcher's number of wins and earned run average. The game result confirmation unit checks the previous day's game results and the current score sheet based on the results inquired by the results inquiry unit. The condition results inquiry unit searches for the number of spectators and weather information for that day from the game schedule confirmed by the game result confirmation unit, and obtains the game results under those conditions. [Effects of the Invention]

[0007] The system according to the embodiment can query the performance of players and games in detail and analyze the performance based on conditions. [Brief explanation of the drawings]

[0008] [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. DETAILED DESCRIPTION OF THE INVENTION

[0009] 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.

[0010] First, the terms used in the following description will be explained.

[0011] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] 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.

[0013] 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.

[0014] 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), and Bluetooth (registered trademark).

[0015] 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."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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).

[0019] 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.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. 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.

[0022] 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.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A performance inquiry system according to an embodiment of the present invention utilizes generative AI to inquire into and analyze the performance of baseball players and teams in detail. This performance inquiry system inquires into various performance data, such as a player's batting average and number of home runs, and a pitcher's number of wins and earned run average, checks the previous day's game results and the current score sheet, and searches the game schedule for attendance and weather information for that day to determine the game results under those conditions. This allows the user to quickly and accurately obtain detailed performance information.

[0029] A performance inquiry system according to an embodiment includes a performance inquiry unit, a game result confirmation unit, and a condition performance inquiry unit. The performance inquiry unit inquires about various performances, such as a player's batting average and number of home runs, and a pitcher's number of wins and earned run average. For example, when a user inputs a prompt such as "Tell me the top 10 batting averages this season," the performance inquiry unit uses a generation AI to analyze the instruction and display a list of the corresponding player's performance. Furthermore, when a user inputs a prompt such as "Tell me the number of home runs hit by player A," the performance inquiry unit uses a generation AI to analyze the instruction and display the corresponding performance. Furthermore, when a user inputs a prompt such as "Tell me the earned run average of pitcher B," the performance inquiry unit uses a generation AI to analyze the instruction and display the corresponding performance. The game result confirmation unit checks the previous day's game results and the current score sheet based on the performance inquired by the performance inquiry unit. For example, when a user inputs a prompt such as "Tell me the results of yesterday's game," the game result confirmation unit uses a generation AI to analyze the instruction and display the previous day's game results. Furthermore, when a user inputs a prompt such as "Tell me the current score sheet," the game result confirmation unit uses the generation AI to analyze the instruction and display the current score sheet. When a user inputs a prompt such as "Tell me the results of this week's games," the game result confirmation unit uses the generation AI to analyze the instruction and display the corresponding game results. The conditional score inquiry unit searches the game schedule confirmed by the game result confirmation unit for the number of spectators and weather information for that day, and obtains the game results under those conditions. For example, when a user inputs a prompt such as "Tell me the number of spectators and weather for the next game," the conditional score inquiry unit uses the generation AI to analyze the instruction and display the corresponding information. When a user inputs a prompt such as "Tell me the results of games played on rainy days," the conditional score inquiry unit uses the generation AI to analyze the instruction and display the corresponding results. When a user inputs a prompt such as "Tell me the results of games with high attendances," the conditional score inquiry unit uses the generation AI to analyze the instruction and display the corresponding results. As a result, the score inquiry system according to the embodiment allows users to quickly and accurately obtain detailed score information. For example, a user can use the generative AI to quickly query the performance of a particular player.Users can also use the AI ​​to easily check the previous day's game results and the current standings. Users can also use the AI ​​to search for attendance numbers and weather information from the game schedule and calculate game results under those conditions.

[0030] The performance inquiry unit can predict future performance based on performance data and provide the prediction to the user. The performance inquiry unit, for example, analyzes performance data such as a player's past batting average and number of home runs to predict future performance. For example, the performance inquiry unit predicts the batting average for the next season based on the player's data from the past five years. The performance inquiry unit also analyzes a pitcher's past number of wins and earned run average to predict his performance in the next game. For example, the performance inquiry unit predicts the earned run average for the next game based on the pitcher's past game data. The performance inquiry unit also predicts future performance by taking into account the player's training data and health condition. For example, the performance inquiry unit predicts the player's performance for the next season based on the player's training effects and injury history. In this way, future performance can be predicted and provided to the user, thereby providing more detailed information.

[0031] The performance inquiry unit can use performance data to analyze the training effects of a player and propose an optimal training plan. The performance inquiry unit, for example, analyzes a player's past performance data and training data to evaluate the training effects. For example, the performance inquiry unit analyzes the impact of a specific training menu on batting average. The performance inquiry unit also proposes an optimal training plan for a player based on the training effects. For example, the performance inquiry unit proposes a training menu to improve a pitcher's ERA. The performance inquiry unit also integrates the player's performance data and training data to visualize the training effects. For example, the performance inquiry unit displays a graph showing the effect of improving performance for each training menu. This helps improve the player's performance by analyzing the training effects of a player and proposing an optimal training plan.

[0032] The result inquiry unit can compare the performance data of other sports and analyze the correlation of performance between different sports. For example, the result inquiry unit compares the performance data of a baseball player with the performance data of players of other sports and analyzes the correlation of performance. For example, the result inquiry unit compares the performance of baseball and soccer players. The result inquiry unit also integrates the performance data of different sports to find common performance indicators. For example, the result inquiry unit analyzes the correlation between batting average and number of goals scored. The result inquiry unit also uses the performance data of other sports to build a model to predict the performance of a baseball player. For example, the result inquiry unit predicts the performance of a baseball player based on the performance data of basketball players. In this way, by analyzing the correlation of performance between different sports, it is possible to evaluate performance from a broader perspective.

[0033] The performance inquiry unit can predict a player's health condition and injury risk using performance data. The performance inquiry unit, for example, analyzes a player's performance data and health data to predict injury risk. For example, the performance inquiry unit predicts injury risk for the next season based on past performance and injury history. The performance inquiry unit also uses performance data to build a model for evaluating a player's health condition. For example, the performance inquiry unit evaluates a player's health condition based on fluctuations in batting average and earned run average. The performance inquiry unit also integrates health data and performance data to optimize a player's training plan. For example, the performance inquiry unit suggests a training menu to reduce injury risk. In this way, by predicting a player's health condition and injury risk, it becomes possible to maintain a player's performance and prevent injuries.

[0034] The game result confirmation unit can analyze game results in real time and suggest strategic changes during the game. The game result confirmation unit, for example, builds a system that analyzes game results in real time and suggests strategic changes during the game. For example, the game result confirmation unit suggests pitcher changes or defensive position changes. The game result confirmation unit also collects game data in real time and evaluates the timing of strategic changes. For example, the game result confirmation unit suggests batter changes in specific situations. The game result confirmation unit also suggests strategies for the next play in real time based on the game results. For example, the game result confirmation unit suggests the timing of bunting or stealing bases in the next at-bat. In this way, game performance can be optimized by suggesting strategic changes during the game in real time.

[0035] The game result confirmation unit can automatically generate a strategy for the next game based on the game result. The game result confirmation unit, for example, analyzes the game result and builds a system that automatically generates a strategy for the next game. For example, the game result confirmation unit suggests changes to pitcher rotations and batting orders. The game result confirmation unit also suggests an optimal strategy for the next game based on the results of past games. For example, the game result confirmation unit suggests the placement of batters against a specific pitcher. The game result confirmation unit also uses game result data to simulate a strategy for the next game. For example, the game result confirmation unit compares different strategy scenarios and selects the optimal strategy. In this way, game preparation can be made more efficient by automatically generating a strategy for the next game.

[0036] The game result confirmation unit can compare the results with those of other leagues and international games and conduct analysis from a global perspective. The game result confirmation unit, for example, collects result data from other leagues and international games and builds a system for comparative analysis. For example, the game result confirmation unit compares the results of MLB and NPB games. The game result confirmation unit also analyzes the results of games from different leagues from a global perspective and finds common performance indicators. For example, the game result confirmation unit makes international comparisons of batting averages and earned run averages. The game result confirmation unit also proposes global strategies based on the result data from other leagues and international games. For example, the game result confirmation unit proposes strategies for international tournaments. This makes it possible to analyze from a global perspective by comparing the results of other leagues and international games.

[0037] The game result confirmation unit can evaluate a player's performance using game results and propose compensation and contract terms. The game result confirmation unit, for example, analyzes game result data and builds a system for evaluating a player's performance. For example, the game result confirmation unit evaluates a player based on batting average and earned run average. The game result confirmation unit also proposes a player's compensation and contract terms based on the performance evaluation. For example, the game result confirmation unit proposes incentives according to performance. The game result confirmation unit also integrates the game result data and performance evaluation to optimize the player's contract terms. For example, the game result confirmation unit proposes contract renewal terms based on past performance. In this way, the player's performance is evaluated and compensation and contract terms are proposed, thereby improving the player's motivation.

[0038] The conditional performance reference unit can predict game performance based on the game schedule and weather information. The conditional performance reference unit, for example, analyzes the game schedule and weather information to build a system that predicts game performance. For example, the conditional performance reference unit predicts batting average and earned run average in rainy weather. The conditional performance reference unit also builds a model that predicts game performance based on past game schedules and weather information. For example, the conditional performance reference unit predicts performance under specific weather conditions. The conditional performance reference unit also collects game schedules and weather information in real time to predict game performance. For example, the conditional performance reference unit predicts performance based on the weather forecast for the day before the game. In this way, game preparations can be optimized by predicting game performance based on the game schedule and weather information.

[0039] The condition and performance reference unit can analyze the correlation between attendance numbers and performance and propose a marketing strategy. The condition and performance reference unit, for example, builds a system that analyzes game schedules and attendance data and analyzes the correlation with performance. For example, the condition and performance reference unit analyzes performance at games with high attendance numbers. The condition and performance reference unit also proposes a marketing strategy based on the correlation between attendance numbers and performance. For example, the condition and performance reference unit proposes a promotion for a specific game. The condition and performance reference unit also integrates attendance number data and performance data to optimize the marketing strategy. For example, the condition and performance reference unit proposes an advertising strategy for games with high attendance numbers. In this way, the correlation between attendance numbers and performance is analyzed and a marketing strategy is proposed, thereby increasing the number of spectators.

[0040] The condition result reference unit can compare the game schedules of other events and sports and perform competitive analysis. The condition result reference unit, for example, collects game schedule data of other events and sports and builds a system for comparative analysis. For example, the condition result reference unit compares it with soccer and basketball game schedules. The condition result reference unit also analyzes game schedules of different events and sports and performs competitive analysis. For example, the condition result reference unit evaluates competition with other sporting events held on the same day. The condition result reference unit also performs competitive analysis based on game schedule data of other events and sports and proposes the optimal game schedule. For example, the condition result reference unit selects a schedule with minimal competition. This makes it possible to perform competitive analysis by comparing it with game schedules of other events and sports.

[0041] The condition performance reference unit can optimize a player's rest and training schedule based on the game schedule. The condition performance reference unit, for example, analyzes game schedule data and builds a system that optimizes a player's rest and training schedule. For example, the condition performance reference unit proposes a training plan that takes into account rest days between games. The condition performance reference unit also proposes an optimal rest schedule based on a player's past performance data and the game schedule. For example, the condition performance reference unit sets rest days after consecutive games. The condition performance reference unit also integrates game schedule data and player health data to optimize the training schedule. For example, the condition performance reference unit proposes a training plan to reduce the risk of injury. In this way, a player's performance can be maintained by optimizing a player's rest and training schedule based on the game schedule.

[0042] The performance trend analysis unit can predict future match results based on performance trends. The performance trend analysis unit, for example, analyzes past performance trend data between players and builds a system that predicts future match results. For example, the performance trend analysis unit predicts the result of the next match based on the match results between a specific pitcher and batter. The performance trend analysis unit also evaluates the compatibility between players based on the performance trend data and predicts future match results. For example, the performance trend analysis unit predicts performance in the next match based on past match results. The performance trend analysis unit also collects performance trend data between players in real time and predicts future match results. For example, the performance trend analysis unit predicts the result of the next match based on performance data from the day before the game. In this way, preparations for the match can be optimized by predicting future match results based on the performance trends between players.

[0043] The performance trend analysis unit can analyze a player's growth or decline using performance trends and propose a career plan. The performance trend analysis unit, for example, analyzes a player's performance trend data and builds a system to evaluate growth or decline. For example, the performance trend analysis unit evaluates a player's growth based on fluctuations in batting average and earned run average. The performance trend analysis unit also proposes a player's career plan based on the performance trend data. For example, the performance trend analysis unit proposes a specific training menu or position change. The performance trend analysis unit also integrates the player's performance trend data and training data to optimize the career plan. For example, the performance trend analysis unit proposes a training plan to improve performance. In this way, the player's growth or decline is analyzed and a career plan is proposed, thereby improving the player's long-term performance.

[0044] The performance trend analysis unit can compare the performance trends of baseball players with those of other sports or competitions to analyze compatibility between different sports. The performance trend analysis unit, for example, compares performance trend data of baseball players with performance trend data of other sports players to build a system for analyzing compatibility. For example, the performance trend analysis unit compares the performance trends of baseball and soccer players. The performance trend analysis unit also integrates performance trend data from different sports to find common performance indicators. For example, the performance trend analysis unit analyzes the correlation between batting average and number of goals scored. The performance trend analysis unit also builds a model to predict the performance of baseball players using performance trend data from other sports. For example, the performance trend analysis unit predicts the performance of baseball players based on performance trend data of basketball players. This makes it possible to analyze compatibility between different sports by comparing performance trends with those of other sports or competitions.

[0045] The performance trend analysis unit can evaluate the possibility of a player being traded or transferred based on the performance trend. The performance trend analysis unit, for example, analyzes player performance trend data and builds a system that evaluates the possibility of a trade or transfer. For example, the performance trend analysis unit evaluates the trade value of a player whose performance is improving. The performance trend analysis unit also suggests a player's transfer destination based on the performance trend data. For example, the performance trend analysis unit suggests a player who is expected to improve his performance on a specific team. The performance trend analysis unit also integrates the player's performance trend data with the team's needs and suggests the optimal timing for a trade or transfer. For example, the performance trend analysis unit suggests a trade for a player whose performance is declining. In this way, team composition can be optimized by evaluating the possibility of a player being traded or transferred based on the performance trend.

[0046] The performance comparison unit can propose optimal strategies based on the performance of players and teams. The performance comparison unit, for example, analyzes performance data of players and teams and builds a system that proposes optimal strategies. For example, the performance comparison unit proposes the positioning of batters against a specific pitcher. The performance comparison unit also proposes strategies during a game based on performance data. For example, the performance comparison unit proposes the timing of bunting or stealing bases in specific situations. The performance comparison unit also collects performance data of players and teams in real time and proposes optimal strategies. For example, the performance comparison unit proposes a strategy for the next game based on performance data from the day before the game. In this way, by proposing optimal strategies based on the performance of players and teams, game performance is improved.

[0047] The performance comparison unit can use the performance comparison to evaluate a player's potential and propose a development plan. The performance comparison unit, for example, analyzes a player's performance comparison data and builds a system for evaluating potential. For example, the performance comparison unit evaluates a player's potential based on fluctuations in batting average and earned run average. The performance comparison unit also proposes a player development plan based on the performance comparison data. For example, the performance comparison unit proposes a specific training menu or position change. The performance comparison unit also integrates the player's performance comparison data with training data to optimize the development plan. For example, the performance comparison unit proposes a training plan to improve performance. In this way, the performance comparison is used to evaluate a player's potential and propose a development plan, thereby supporting the player's growth.

[0048] The performance comparison unit can compare the performance data with those of other sports or competitions to analyze performance across different sports. The performance comparison unit, for example, compares performance data of baseball players with performance data of other sports players to build a system for analyzing performance. For example, the performance comparison unit compares the performance of baseball and soccer players. The performance comparison unit also integrates performance data from different sports to find common performance indicators. For example, the performance comparison unit analyzes the correlation between batting average and number of goals scored. The performance comparison unit also builds a model to predict the performance of baseball players using performance data from other sports. For example, the performance comparison unit predicts the performance of baseball players based on performance data of basketball players. This makes it possible to analyze performance across different sports by comparing the performance data with those of other sports or competitions.

[0049] The performance comparison unit can evaluate the possibility of a player being traded or transferred based on the performance comparison. For example, the performance comparison unit analyzes player performance comparison data and builds a system that evaluates the possibility of a trade or transfer. For example, the performance comparison unit evaluates the trade value of a player whose performance is improving. The performance comparison unit also suggests a player's transfer destination based on the performance comparison data. For example, the performance comparison unit suggests a player who is expected to improve his performance on a specific team. The performance comparison unit also integrates the player's performance comparison data with the team's needs and suggests the optimal timing for a trade or transfer. For example, the performance comparison unit suggests a trade for a player whose performance is declining. In this way, team composition can be optimized by evaluating the possibility of a player being traded or transferred based on the performance comparison.

[0050] The historical performance reference unit can predict future performance based on historical performance. The historical performance reference unit, for example, analyzes historical performance data of players or teams to build a system for predicting future performance. For example, the historical performance reference unit predicts performance for the next season based on performance data from the past 10 years. The historical performance reference unit also predicts future performance of players or teams based on historical performance data. For example, the historical performance reference unit predicts performance in the next game based on the past performance of a specific player. The historical performance reference unit also collects historical performance data in real time to predict future performance. For example, the historical performance reference unit predicts performance for the next game based on performance data from the day before the game. This makes it possible to optimize game preparations by predicting future performance based on historical performance.

[0051] The historical performance inquiry unit can analyze the growth and decline of a player or team using historical performance. The historical performance inquiry unit, for example, analyzes historical performance data of a player or team to build a system for evaluating growth and decline. For example, the historical performance inquiry unit evaluates the growth of a player or team based on fluctuations in batting average and earned run average. The historical performance inquiry unit also analyzes the growth and decline of a player or team based on historical performance data. For example, the historical performance inquiry unit evaluates fluctuations in performance over a specific period. The historical performance inquiry unit also integrates historical performance data of a player or team with training data to optimize growth and decline. For example, the historical performance inquiry unit proposes a training plan for improving performance. In this way, long-term performance can be improved by analyzing the growth and decline of a player or team using historical performance.

[0052] The historical performance reference unit can compare historical performance data of other sports or competitions to analyze performance across different sports. The historical performance reference unit, for example, compares historical performance data of baseball players with historical performance data of players of other sports to build a system for analyzing performance. For example, the historical performance reference unit compares the performance of baseball and soccer players. The historical performance reference unit also integrates historical performance data across different sports to find common performance indicators. For example, the historical performance reference unit analyzes the correlation between batting average and number of goals scored. The historical performance reference unit also builds a model to predict the performance of baseball players using historical performance data of other sports. For example, the historical performance reference unit predicts the performance of baseball players based on historical performance data of basketball players. This makes it possible to analyze performance across different sports by comparing historical performance data of other sports or competitions.

[0053] The historical performance reference unit can evaluate the possibility of a player being traded or transferred based on historical performance. The historical performance reference unit, for example, analyzes historical performance data of players and builds a system that evaluates the possibility of a trade or transfer. For example, the historical performance reference unit evaluates the trade value of a player whose performance is improving. The historical performance reference unit also suggests a transfer destination for a player based on historical performance data. For example, the historical performance reference unit suggests a player who is expected to improve his performance on a specific team. The historical performance reference unit also integrates the player's historical performance data with the team's needs and suggests the optimal timing for a trade or transfer. For example, the historical performance reference unit suggests a trade for a player whose performance is declining. In this way, team composition can be optimized by evaluating the possibility of a player being traded or transferred based on historical performance.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The performance inquiry unit can use the player's performance data to evaluate the player's performance and estimate the player's market value. For example, the performance inquiry unit can analyze the player's performance data, such as the player's batting average, number of home runs, and earned run average, to estimate the player's market value. The performance inquiry unit can also predict the player's future market value based on past performance data. For example, the performance inquiry unit can predict the player's market value for the next season based on the player's performance data from the past five years. The performance inquiry unit can also take the player's training data and health status into consideration to more accurately estimate the player's market value. This can support the team's strategic decision-making by evaluating the player's market value and predicting its future market value.

[0056] The performance inquiry unit can evaluate a player's performance using the player's performance data and visualize the effects of the player's training. For example, the performance inquiry unit can analyze performance data such as a player's batting average, number of home runs, and earned run average to evaluate the effects of training. The performance inquiry unit can also integrate training data and performance data to display the training effects in a graph. For example, the performance inquiry unit can display a graph showing the effect of a specific training menu on batting average. The performance inquiry unit can also propose an optimal training plan based on the effects of the player's training. In this way, the effects of a player's training can be visualized and an optimal training plan can be proposed to help improve the player's performance.

[0057] The result inquiry unit can compare the performance data of other sports and analyze the correlation of performance between different sports. For example, the result inquiry unit compares the performance data of a baseball player with the performance data of players of other sports and analyzes the correlation of performance. The result inquiry unit can also integrate the performance data of different sports to find common performance indicators. For example, the result inquiry unit can analyze the correlation between batting average and number of goals scored. The result inquiry unit can also use the performance data of other sports to build a model to predict the performance of a baseball player. In this way, analyzing the correlation of performance between different sports makes it possible to evaluate performance from a broader perspective.

[0058] The performance inquiry unit can use performance data to predict a player's health condition and injury risk. For example, the performance inquiry unit analyzes a player's performance data and health data to predict injury risk. The performance inquiry unit can also use performance data to build a model to evaluate a player's health condition. For example, the performance inquiry unit evaluates a player's health condition based on fluctuations in batting average and earned run average. The performance inquiry unit can also integrate health data and performance data to optimize a player's training plan. This makes it possible to predict a player's health condition and injury risk, thereby maintaining a player's performance and preventing injuries.

[0059] The game result confirmation unit can analyze the game results in real time and propose strategic changes during the game. For example, a system can be constructed in which the game result confirmation unit analyzes the game results in real time and proposes strategic changes during the game. For example, the game result confirmation unit proposes pitcher changes or defensive position changes. The game result confirmation unit can also collect data during the game in real time and evaluate the timing of strategic changes. For example, the game result confirmation unit proposes batter changes in specific situations. The game result confirmation unit can also propose a strategy for the next play in real time based on the game results. In this way, game performance can be optimized by proposing strategic changes during the game in real time.

[0060] The game result confirmation unit can automatically generate a strategy for the next game based on the game results. For example, the game result confirmation unit analyzes the game results and builds a system that automatically generates a strategy for the next game. For example, the game result confirmation unit suggests changes to pitcher rotations and batting orders. The game result confirmation unit can also propose an optimal strategy for the next game based on the results of past games. For example, the game result confirmation unit suggests the placement of batters against a specific pitcher. The game result confirmation unit can also simulate a strategy for the next game using game result data. This allows for the automatic generation of a strategy for the next game, making game preparation more efficient.

[0061] The game result confirmation unit can compare the results of games with those of other leagues and international games and conduct analysis from a global perspective. For example, the game result confirmation unit collects data on the results of games from other leagues and international games and builds a system for comparative analysis. For example, the game result confirmation unit compares the results of MLB and NPB games. The game result confirmation unit can also analyze the results of games from different leagues from a global perspective and find common performance indicators. For example, the game result confirmation unit makes international comparisons of batting averages and earned run averages. The game result confirmation unit can also propose global strategies based on the result data of other leagues and international games. This makes it possible to analyze games from a global perspective by comparing them with those of other leagues and international games.

[0062] The processing flow of the first embodiment will be briefly explained below.

[0063] Step 1: The performance inquiry unit inquires about various performance statistics, such as a player's batting average and number of home runs, and a pitcher's number of wins and earned run average. For example, when a user inputs a prompt such as "Tell me the top 10 batting averages this season," the performance inquiry unit uses the generation AI to analyze the instruction and display a list of the performance of the corresponding players. Also, when a user inputs a prompt such as "Tell me the number of home runs hit by player A," the performance inquiry unit uses the generation AI to analyze the instruction and display the corresponding performance. Also, when a user inputs a prompt such as "Tell me the earned run average of pitcher B," the performance inquiry unit uses the generation AI to analyze the instruction and display the corresponding performance. Step 2: The match result confirmation unit checks the previous day's match results and the current score sheet based on the results queried by the score inquiry unit. For example, when a user inputs a prompt such as "Tell me the results of yesterday's match," the match result confirmation unit uses the generation AI to analyze the instruction and display the previous day's match results. Also, when a user inputs a prompt such as "Tell me the current score sheet," the match result confirmation unit uses the generation AI to analyze the instruction and display the current score sheet. Also, when a user inputs a prompt such as "Tell me the results of this week's match," the match result confirmation unit uses the generation AI to analyze the instruction and display the corresponding match results. Step 3: The conditional performance reference unit searches for the number of spectators and weather information for that day from the match schedule confirmed by the match result confirmation unit, and finds the match results under those conditions. For example, when a user inputs a prompt such as "Tell me the number of spectators and weather for the next match," the conditional performance reference unit uses the generation AI to analyze the instruction and display the corresponding information. Also, when a user inputs a prompt such as "Tell me the results of matches played on rainy days," the conditional performance reference unit uses the generation AI to analyze the instruction and display the corresponding results. Also, when a user inputs a prompt such as "Tell me the results of matches with high attendances," the conditional performance reference unit uses the generation AI to analyze the instruction and display the corresponding results.

[0064] (Example 2) A performance inquiry system according to an embodiment of the present invention utilizes generative AI to inquire into and analyze the performance of baseball players and teams in detail. This performance inquiry system inquires into various performance data, such as a player's batting average and number of home runs, and a pitcher's number of wins and earned run average, checks the previous day's game results and the current score sheet, and searches the game schedule for attendance and weather information for that day to determine the game results under those conditions. This allows the user to quickly and accurately obtain detailed performance information.

[0065] A performance inquiry system according to an embodiment includes a performance inquiry unit, a game result confirmation unit, and a condition performance inquiry unit. The performance inquiry unit inquires about various performances, such as a player's batting average and number of home runs, and a pitcher's number of wins and earned run average. For example, when a user inputs a prompt such as "Tell me the top 10 batting averages this season," the performance inquiry unit uses a generation AI to analyze the instruction and display a list of the corresponding player's performance. Furthermore, when a user inputs a prompt such as "Tell me the number of home runs hit by player A," the performance inquiry unit uses a generation AI to analyze the instruction and display the corresponding performance. Furthermore, when a user inputs a prompt such as "Tell me the earned run average of pitcher B," the performance inquiry unit uses a generation AI to analyze the instruction and display the corresponding performance. The game result confirmation unit checks the previous day's game results and the current score sheet based on the performance inquired by the performance inquiry unit. For example, when a user inputs a prompt such as "Tell me the results of yesterday's game," the game result confirmation unit uses a generation AI to analyze the instruction and display the previous day's game results. Furthermore, when a user inputs a prompt such as "Tell me the current score sheet," the game result confirmation unit uses the generation AI to analyze the instruction and display the current score sheet. When a user inputs a prompt such as "Tell me the results of this week's games," the game result confirmation unit uses the generation AI to analyze the instruction and display the corresponding game results. The conditional score inquiry unit searches the game schedule confirmed by the game result confirmation unit for the number of spectators and weather information for that day, and obtains the game results under those conditions. For example, when a user inputs a prompt such as "Tell me the number of spectators and weather for the next game," the conditional score inquiry unit uses the generation AI to analyze the instruction and display the corresponding information. When a user inputs a prompt such as "Tell me the results of games played on rainy days," the conditional score inquiry unit uses the generation AI to analyze the instruction and display the corresponding results. When a user inputs a prompt such as "Tell me the results of games with high attendances," the conditional score inquiry unit uses the generation AI to analyze the instruction and display the corresponding results. As a result, the score inquiry system according to the embodiment allows users to quickly and accurately obtain detailed score information. For example, a user can use the generative AI to quickly query the performance of a particular player.Users can also use the AI ​​to easily check the previous day's game results and the current standings. Users can also use the AI ​​to search for attendance numbers and weather information from the game schedule and calculate game results under those conditions.

[0066] The performance inquiry unit can predict future performance based on performance data and provide the prediction to the user. The performance inquiry unit, for example, analyzes performance data such as a player's past batting average and number of home runs to predict future performance. For example, the performance inquiry unit predicts the batting average for the next season based on the player's data from the past five years. The performance inquiry unit also analyzes a pitcher's past number of wins and earned run average to predict his performance in the next game. For example, the performance inquiry unit predicts the earned run average for the next game based on the pitcher's past game data. The performance inquiry unit also predicts future performance by taking into account the player's training data and health condition. For example, the performance inquiry unit predicts the player's performance for the next season based on the player's training effects and injury history. In this way, future performance can be predicted and provided to the user, thereby providing more detailed information.

[0067] The performance inquiry unit can use performance data to analyze the training effects of a player and propose an optimal training plan. The performance inquiry unit, for example, analyzes a player's past performance data and training data to evaluate the training effects. For example, the performance inquiry unit analyzes the impact of a specific training menu on batting average. The performance inquiry unit also proposes an optimal training plan for a player based on the training effects. For example, the performance inquiry unit proposes a training menu to improve a pitcher's ERA. The performance inquiry unit also integrates the player's performance data and training data to visualize the training effects. For example, the performance inquiry unit displays a graph showing the effect of improving performance for each training menu. This helps improve the player's performance by analyzing the training effects of a player and proposing an optimal training plan.

[0068] The performance inquiry unit can use the emotion estimation function to analyze fans' emotional reactions to a player's performance and evaluate the impact of the performance. For example, the performance inquiry unit analyzes a player's performance data and fans' emotional reaction data to evaluate the impact of the performance on fans. For example, the performance inquiry unit analyzes the impact of the number of home runs on fans' joy. The performance inquiry unit also uses the emotion estimation function to collect fans' real-time emotional reactions to a player's performance. For example, the performance inquiry unit analyzes fans' tweets about the performance during a game. The performance inquiry unit also evaluates the impact of a player's performance on fan interest based on the fans' emotional reaction data. For example, the performance inquiry unit analyzes the extent to which a particular performance increases fan interest. In this way, the emotional reactions of fans to a player's performance are analyzed and the impact of the performance is evaluated, thereby attracting fan interest.

[0069] The result inquiry unit can compare the performance data of other sports and analyze the correlation of performance between different sports. For example, the result inquiry unit compares the performance data of a baseball player with the performance data of players of other sports and analyzes the correlation of performance. For example, the result inquiry unit compares the performance of baseball and soccer players. The result inquiry unit also integrates the performance data of different sports to find common performance indicators. For example, the result inquiry unit analyzes the correlation between batting average and number of goals scored. The result inquiry unit also uses the performance data of other sports to build a model to predict the performance of a baseball player. For example, the result inquiry unit predicts the performance of a baseball player based on the performance data of basketball players. In this way, by analyzing the correlation of performance between different sports, it is possible to evaluate performance from a broader perspective.

[0070] The performance inquiry unit can predict a player's health condition and injury risk using performance data. The performance inquiry unit, for example, analyzes a player's performance data and health data to predict injury risk. For example, the performance inquiry unit predicts injury risk for the next season based on past performance and injury history. The performance inquiry unit also uses performance data to build a model for evaluating a player's health condition. For example, the performance inquiry unit evaluates a player's health condition based on fluctuations in batting average and earned run average. The performance inquiry unit also integrates health data and performance data to optimize a player's training plan. For example, the performance inquiry unit suggests a training menu to reduce injury risk. In this way, by predicting a player's health condition and injury risk, it becomes possible to maintain a player's performance and prevent injuries.

[0071] The performance inquiry unit can use the emotion estimation function to analyze fans' expectations for a player's performance and attract fans' interest. The performance inquiry unit, for example, analyzes a player's performance data and fans' emotional response data to evaluate fans' expectations. For example, the performance inquiry unit analyzes the impact of the number of home runs on fans' expectations. The performance inquiry unit also uses the emotion estimation function to collect fans' expectations for a player's performance in real time. For example, the performance inquiry unit analyzes fans' expectations for in-game performance from tweets. The performance inquiry unit also evaluates the impact of a player's performance on fans' interest based on the fan expectation data. For example, the performance inquiry unit analyzes the extent to which a particular performance increases fans' interest. In this way, fans' expectations for a player's performance are analyzed and their interest is attracted, thereby increasing fan engagement.

[0072] The game result confirmation unit can analyze game results in real time and suggest strategic changes during the game. The game result confirmation unit, for example, builds a system that analyzes game results in real time and suggests strategic changes during the game. For example, the game result confirmation unit suggests pitcher changes or defensive position changes. The game result confirmation unit also collects game data in real time and evaluates the timing of strategic changes. For example, the game result confirmation unit suggests batter changes in specific situations. The game result confirmation unit also suggests strategies for the next play in real time based on the game results. For example, the game result confirmation unit suggests the timing of bunting or stealing bases in the next at-bat. In this way, game performance can be optimized by suggesting strategic changes during the game in real time.

[0073] The game result confirmation unit can automatically generate a strategy for the next game based on the game result. The game result confirmation unit, for example, analyzes the game result and builds a system that automatically generates a strategy for the next game. For example, the game result confirmation unit suggests changes to pitcher rotations and batting orders. The game result confirmation unit also suggests an optimal strategy for the next game based on the results of past games. For example, the game result confirmation unit suggests the placement of batters against a specific pitcher. The game result confirmation unit also uses game result data to simulate a strategy for the next game. For example, the game result confirmation unit compares different strategy scenarios and selects the optimal strategy. In this way, game preparation can be made more efficient by automatically generating a strategy for the next game.

[0074] The game result confirmation unit can use the emotion estimation function to analyze fans' emotional reactions to the game result and evaluate the impact of the game. The game result confirmation unit, for example, analyzes game result data and fans' emotional reaction data to evaluate the impact of the game result on fans. For example, the game result confirmation unit analyzes the impact of a victory on fans' joy. The game result confirmation unit also uses the emotion estimation function to collect fans' real-time emotional reactions to the game result. For example, the game result confirmation unit analyzes tweets during the game to evaluate fans' emotions. The game result confirmation unit also evaluates the impact of the game result on fans' interest based on the fans' emotional reaction data. For example, the game result confirmation unit analyzes to what extent a specific game result increases fans' interest. In this way, the emotional reactions of fans to the game result are analyzed and the impact of the game is evaluated, thereby attracting fans' interest.

[0075] The game result confirmation unit can compare the results with those of other leagues and international games and conduct analysis from a global perspective. The game result confirmation unit, for example, collects result data from other leagues and international games and builds a system for comparative analysis. For example, the game result confirmation unit compares the results of MLB and NPB games. The game result confirmation unit also analyzes the results of games from different leagues from a global perspective and finds common performance indicators. For example, the game result confirmation unit makes international comparisons of batting averages and earned run averages. The game result confirmation unit also proposes global strategies based on the result data from other leagues and international games. For example, the game result confirmation unit proposes strategies for international tournaments. This makes it possible to analyze from a global perspective by comparing the results of other leagues and international games.

[0076] The game result confirmation unit can evaluate a player's performance using game results and propose compensation and contract terms. The game result confirmation unit, for example, analyzes game result data and builds a system for evaluating a player's performance. For example, the game result confirmation unit evaluates a player based on batting average and earned run average. The game result confirmation unit also proposes a player's compensation and contract terms based on the performance evaluation. For example, the game result confirmation unit proposes incentives according to performance. The game result confirmation unit also integrates the game result data and performance evaluation to optimize the player's contract terms. For example, the game result confirmation unit proposes contract renewal terms based on past performance. In this way, the player's performance is evaluated and compensation and contract terms are proposed, thereby improving the player's motivation.

[0077] The match result confirmation unit uses the emotion estimation function to monitor fans' reactions to the match result in real time, thereby attracting their interest. The match result confirmation unit, for example, builds a system that monitors fans' emotional reactions to the match result in real time. For example, the match result confirmation unit analyzes tweets and comments during the match to evaluate fans' emotions. The match result confirmation unit also uses the emotion estimation function to collect fans' real-time reactions to the match result. For example, the match result confirmation unit analyzes social media posts during the match to evaluate fans' emotions. The match result confirmation unit also evaluates the impact of the match result on fans' interest based on the fans' emotional reaction data. For example, the match result confirmation unit analyzes the extent to which a specific match result increases fans' interest. In this way, fans' reactions to the match result are monitored in real time, thereby attracting their interest.

[0078] The conditional performance reference unit can predict game performance based on the game schedule and weather information. The conditional performance reference unit, for example, analyzes the game schedule and weather information to build a system that predicts game performance. For example, the conditional performance reference unit predicts batting average and earned run average in rainy weather. The conditional performance reference unit also builds a model that predicts game performance based on past game schedules and weather information. For example, the conditional performance reference unit predicts performance under specific weather conditions. The conditional performance reference unit also collects game schedules and weather information in real time to predict game performance. For example, the conditional performance reference unit predicts performance based on the weather forecast for the day before the game. In this way, game preparations can be optimized by predicting game performance based on the game schedule and weather information.

[0079] The condition and performance reference unit can analyze the correlation between attendance numbers and performance and propose a marketing strategy. The condition and performance reference unit, for example, builds a system that analyzes game schedules and attendance data and analyzes the correlation with performance. For example, the condition and performance reference unit analyzes performance at games with high attendance numbers. The condition and performance reference unit also proposes a marketing strategy based on the correlation between attendance numbers and performance. For example, the condition and performance reference unit proposes a promotion for a specific game. The condition and performance reference unit also integrates attendance number data and performance data to optimize the marketing strategy. For example, the condition and performance reference unit proposes an advertising strategy for games with high attendance numbers. In this way, the correlation between attendance numbers and performance is analyzed and a marketing strategy is proposed, thereby increasing the number of spectators.

[0080] The conditional performance query unit can use the emotion estimation function to analyze fans' emotional reactions to the game schedule and evaluate the impact of the game. The conditional performance query unit, for example, analyzes game schedule data and fan emotional reaction data to evaluate the impact of the game schedule on fans. For example, the conditional performance query unit analyzes the impact of weekend games on fan enjoyment. The conditional performance query unit also uses the emotion estimation function to collect fans' real-time emotional reactions to the game schedule. For example, the conditional performance query unit analyzes social media posts at the time the game schedule is announced to evaluate fans' emotions. The conditional performance query unit also evaluates the impact of the game schedule on fan interest based on the fan emotional reaction data. For example, the conditional performance query unit analyzes the extent to which a specific schedule increases fan interest. In this way, the emotional reactions of fans to the game schedule are analyzed and the impact of the game is evaluated, thereby attracting fan interest.

[0081] The condition result reference unit can compare the game schedules of other events and sports and perform competitive analysis. The condition result reference unit, for example, collects game schedule data of other events and sports and builds a system for comparative analysis. For example, the condition result reference unit compares it with soccer and basketball game schedules. The condition result reference unit also analyzes game schedules of different events and sports and performs competitive analysis. For example, the condition result reference unit evaluates competition with other sporting events held on the same day. The condition result reference unit also performs competitive analysis based on game schedule data of other events and sports and proposes the optimal game schedule. For example, the condition result reference unit selects a schedule with minimal competition. This makes it possible to perform competitive analysis by comparing it with game schedules of other events and sports.

[0082] The condition performance reference unit can optimize a player's rest and training schedule based on the game schedule. The condition performance reference unit, for example, analyzes game schedule data and builds a system that optimizes a player's rest and training schedule. For example, the condition performance reference unit proposes a training plan that takes into account rest days between games. The condition performance reference unit also proposes an optimal rest schedule based on a player's past performance data and the game schedule. For example, the condition performance reference unit sets rest days after consecutive games. The condition performance reference unit also integrates game schedule data and player health data to optimize the training schedule. For example, the condition performance reference unit proposes a training plan to reduce the risk of injury. In this way, a player's performance can be maintained by optimizing a player's rest and training schedule based on the game schedule.

[0083] The condition and performance reference unit can use the emotion estimation function to analyze fans' expectations regarding the game schedule and attract their interest. The condition and performance reference unit, for example, analyzes game schedule data and fans' emotional response data to evaluate fans' expectations. For example, the condition and performance reference unit analyzes the impact of a specific schedule on fans' expectations. The condition and performance reference unit also uses the emotion estimation function to collect fans' expectations regarding the game schedule in real time. For example, the condition and performance reference unit analyzes social media posts at the time the game schedule is announced to evaluate fans' expectations. The condition and performance reference unit also evaluates the impact of the game schedule on fans' interest based on the fan expectation data. For example, the condition and performance reference unit analyzes the extent to which a specific schedule increases fans' interest. This analyzes fans' expectations regarding the game schedule and attracts their interest, thereby increasing fan engagement.

[0084] The performance trend analysis unit can predict future match results based on performance trends. The performance trend analysis unit, for example, analyzes past performance trend data between players and builds a system that predicts future match results. For example, the performance trend analysis unit predicts the result of the next match based on the match results between a specific pitcher and batter. The performance trend analysis unit also evaluates the compatibility between players based on the performance trend data and predicts future match results. For example, the performance trend analysis unit predicts performance in the next match based on past match results. The performance trend analysis unit also collects performance trend data between players in real time and predicts future match results. For example, the performance trend analysis unit predicts the result of the next match based on performance data from the day before the game. In this way, preparations for the match can be optimized by predicting future match results based on the performance trends between players.

[0085] The performance trend analysis unit can analyze a player's growth or decline using performance trends and propose a career plan. The performance trend analysis unit, for example, analyzes a player's performance trend data and builds a system to evaluate growth or decline. For example, the performance trend analysis unit evaluates a player's growth based on fluctuations in batting average and earned run average. The performance trend analysis unit also proposes a player's career plan based on the performance trend data. For example, the performance trend analysis unit proposes a specific training menu or position change. The performance trend analysis unit also integrates the player's performance trend data and training data to optimize the career plan. For example, the performance trend analysis unit proposes a training plan to improve performance. In this way, the player's growth or decline is analyzed and a career plan is proposed, thereby improving the player's long-term performance.

[0086] The performance trend analysis unit can use the emotion estimation function to analyze fans' emotional reactions to performance trends between players and evaluate the impact of performance. The performance trend analysis unit, for example, analyzes performance trend data between players and emotional reaction data of fans to evaluate the impact of performance on fans. For example, the performance trend analysis unit analyzes the impact of specific match results on fan joy. The performance trend analysis unit also uses the emotion estimation function to collect fans' real-time emotional reactions to performance trends between players. For example, the performance trend analysis unit analyzes tweets during a game to evaluate fans' emotions. The performance trend analysis unit also evaluates the impact of performance trends between players on fan interest based on the fan emotional reaction data. For example, the performance trend analysis unit analyzes to what extent a specific performance trend increases fan interest. In this way, the emotional reactions of fans to performance trends between players are analyzed and the impact of performance is evaluated, thereby attracting fan interest.

[0087] The performance trend analysis unit can compare the performance trends of baseball players with those of other sports or competitions to analyze compatibility between different sports. The performance trend analysis unit, for example, compares performance trend data of baseball players with performance trend data of other sports players to build a system for analyzing compatibility. For example, the performance trend analysis unit compares the performance trends of baseball and soccer players. The performance trend analysis unit also integrates performance trend data from different sports to find common performance indicators. For example, the performance trend analysis unit analyzes the correlation between batting average and number of goals scored. The performance trend analysis unit also builds a model to predict the performance of baseball players using performance trend data from other sports. For example, the performance trend analysis unit predicts the performance of baseball players based on performance trend data of basketball players. This makes it possible to analyze compatibility between different sports by comparing performance trends with those of other sports or competitions.

[0088] The performance trend analysis unit can evaluate the possibility of a player being traded or transferred based on the performance trend. The performance trend analysis unit, for example, analyzes player performance trend data and builds a system that evaluates the possibility of a trade or transfer. For example, the performance trend analysis unit evaluates the trade value of a player whose performance is improving. The performance trend analysis unit also suggests a player's transfer destination based on the performance trend data. For example, the performance trend analysis unit suggests a player who is expected to improve his performance on a specific team. The performance trend analysis unit also integrates the player's performance trend data with the team's needs and suggests the optimal timing for a trade or transfer. For example, the performance trend analysis unit suggests a trade for a player whose performance is declining. In this way, team composition can be optimized by evaluating the possibility of a player being traded or transferred based on the performance trend.

[0089] The performance trend analysis unit uses the emotion estimation function to analyze fans' expectations regarding performance trends between players, thereby attracting fan interest. The performance trend analysis unit, for example, analyzes performance trend data between players and fan emotional response data to evaluate fan expectations. For example, the performance trend analysis unit analyzes the impact of specific match results on fan expectations. The performance trend analysis unit also uses the emotion estimation function to collect fans' expectations regarding performance trends between players in real time. For example, the performance trend analysis unit analyzes tweets during a game to evaluate fan expectations. The performance trend analysis unit also evaluates the impact of performance trends between players on fan interest based on fan expectation data. For example, the performance trend analysis unit analyzes to what extent a specific performance trend increases fan interest. In this way, fans' expectations regarding performance trends between players are analyzed, and fan interest is attracted, thereby increasing fan engagement.

[0090] The performance comparison unit can propose optimal strategies based on the performance of players and teams. The performance comparison unit, for example, analyzes performance data of players and teams and builds a system that proposes optimal strategies. For example, the performance comparison unit proposes the positioning of batters against a specific pitcher. The performance comparison unit also proposes strategies during a game based on performance data. For example, the performance comparison unit proposes the timing of bunting or stealing bases in specific situations. The performance comparison unit also collects performance data of players and teams in real time and proposes optimal strategies. For example, the performance comparison unit proposes a strategy for the next game based on performance data from the day before the game. In this way, by proposing optimal strategies based on the performance of players and teams, game performance is improved.

[0091] The performance comparison unit can use the performance comparison to evaluate a player's potential and propose a development plan. The performance comparison unit, for example, analyzes a player's performance comparison data and builds a system for evaluating potential. For example, the performance comparison unit evaluates a player's potential based on fluctuations in batting average and earned run average. The performance comparison unit also proposes a player development plan based on the performance comparison data. For example, the performance comparison unit proposes a specific training menu or position change. The performance comparison unit also integrates the player's performance comparison data with training data to optimize the development plan. For example, the performance comparison unit proposes a training plan to improve performance. In this way, the performance comparison is used to evaluate a player's potential and propose a development plan, thereby supporting the player's growth.

[0092] The performance comparison unit can use the emotion estimation function to analyze fans' emotional reactions to performance comparisons and evaluate the impact of the comparisons. For example, the performance comparison unit analyzes performance comparison data and fans' emotional reaction data to evaluate the impact of the comparisons on fans. For example, the performance comparison unit analyzes the impact of a specific performance comparison on fans' joy. The performance comparison unit also uses the emotion estimation function to collect fans' real-time emotional reactions to the performance comparisons. For example, the performance comparison unit analyzes tweets during a game to evaluate fans' emotions. The performance comparison unit also evaluates the impact of the performance comparisons on fans' interest based on the fans' emotional reaction data. For example, the performance comparison unit analyzes to what extent a specific performance comparison increases fans' interest. In this way, fans' emotional reactions to the performance comparisons are analyzed and the impact of the comparisons is evaluated, thereby attracting fans' interest.

[0093] The performance comparison unit can compare the performance data with those of other sports or competitions to analyze performance across different sports. The performance comparison unit, for example, compares performance data of baseball players with performance data of other sports players to build a system for analyzing performance. For example, the performance comparison unit compares the performance of baseball and soccer players. The performance comparison unit also integrates performance data from different sports to find common performance indicators. For example, the performance comparison unit analyzes the correlation between batting average and number of goals scored. The performance comparison unit also builds a model to predict the performance of baseball players using performance data from other sports. For example, the performance comparison unit predicts the performance of baseball players based on performance data of basketball players. This makes it possible to analyze performance across different sports by comparing the performance data with those of other sports or competitions.

[0094] The performance comparison unit can evaluate the possibility of a player being traded or transferred based on the performance comparison. For example, the performance comparison unit analyzes player performance comparison data and builds a system that evaluates the possibility of a trade or transfer. For example, the performance comparison unit evaluates the trade value of a player whose performance is improving. The performance comparison unit also suggests a player's transfer destination based on the performance comparison data. For example, the performance comparison unit suggests a player who is expected to improve his performance on a specific team. The performance comparison unit also integrates the player's performance comparison data with the team's needs and suggests the optimal timing for a trade or transfer. For example, the performance comparison unit suggests a trade for a player whose performance is declining. In this way, team composition can be optimized by evaluating the possibility of a player being traded or transferred based on the performance comparison.

[0095] The performance comparison unit can use the emotion estimation function to analyze fans' expectations for performance comparisons and attract fans' interest. The performance comparison unit, for example, analyzes performance comparison data and fans' emotional response data to evaluate fans' expectations. For example, the performance comparison unit analyzes the impact of a specific performance comparison on fans' expectations. The performance comparison unit also uses the emotion estimation function to collect fans' expectations for performance comparisons in real time. For example, the performance comparison unit analyzes tweets during a game to evaluate fans' expectations. The performance comparison unit also evaluates the impact of performance comparisons on fans' interest based on fan expectation data. For example, the performance comparison unit analyzes to what extent a specific performance comparison increases fans' interest. In this way, fans' expectations for performance comparisons are analyzed and their interest is attracted, thereby increasing fan engagement.

[0096] The historical performance reference unit can predict future performance based on historical performance. The historical performance reference unit, for example, analyzes historical performance data of players or teams to build a system for predicting future performance. For example, the historical performance reference unit predicts performance for the next season based on performance data from the past 10 years. The historical performance reference unit also predicts future performance of players or teams based on historical performance data. For example, the historical performance reference unit predicts performance in the next game based on the past performance of a specific player. The historical performance reference unit also collects historical performance data in real time to predict future performance. For example, the historical performance reference unit predicts performance for the next game based on performance data from the day before the game. This makes it possible to optimize game preparations by predicting future performance based on historical performance.

[0097] The historical performance inquiry unit can analyze the growth and decline of a player or team using historical performance. The historical performance inquiry unit, for example, analyzes historical performance data of a player or team to build a system for evaluating growth and decline. For example, the historical performance inquiry unit evaluates the growth of a player or team based on fluctuations in batting average and earned run average. The historical performance inquiry unit also analyzes the growth and decline of a player or team based on historical performance data. For example, the historical performance inquiry unit evaluates fluctuations in performance over a specific period. The historical performance inquiry unit also integrates historical performance data of a player or team with training data to optimize growth and decline. For example, the historical performance inquiry unit proposes a training plan for improving performance. In this way, long-term performance can be improved by analyzing the growth and decline of a player or team using historical performance.

[0098] The historical performance inquiry unit can use the emotion estimation function to analyze fans' emotional reactions to historical performance and evaluate the impact of performance. For example, the historical performance inquiry unit analyzes historical performance data and fans' emotional reaction data to evaluate the impact of performance on fans. For example, the historical performance inquiry unit analyzes the impact of a particular performance on fan joy. The historical performance inquiry unit also uses the emotion estimation function to collect fans' real-time emotional reactions to historical performance. For example, the historical performance inquiry unit analyzes tweets during a game to evaluate fans' emotions. The historical performance inquiry unit also evaluates the impact of historical performance on fan interest based on the fans' emotional reaction data. For example, the historical performance inquiry unit analyzes the extent to which a particular performance increases fan interest. In this way, the emotional reactions of fans to historical performance are analyzed and the impact of performance is evaluated, thereby attracting fan interest.

[0099] The historical performance reference unit can compare historical performance data of other sports or competitions to analyze performance across different sports. The historical performance reference unit, for example, compares historical performance data of baseball players with historical performance data of players of other sports to build a system for analyzing performance. For example, the historical performance reference unit compares the performance of baseball and soccer players. The historical performance reference unit also integrates historical performance data across different sports to find common performance indicators. For example, the historical performance reference unit analyzes the correlation between batting average and number of goals scored. The historical performance reference unit also builds a model to predict the performance of baseball players using historical performance data of other sports. For example, the historical performance reference unit predicts the performance of baseball players based on historical performance data of basketball players. This makes it possible to analyze performance across different sports by comparing historical performance data of other sports or competitions.

[0100] The historical performance reference unit can evaluate the possibility of a player being traded or transferred based on historical performance. The historical performance reference unit, for example, analyzes historical performance data of players and builds a system that evaluates the possibility of a trade or transfer. For example, the historical performance reference unit evaluates the trade value of a player whose performance is improving. The historical performance reference unit also suggests a transfer destination for a player based on historical performance data. For example, the historical performance reference unit suggests a player who is expected to improve his performance on a specific team. The historical performance reference unit also integrates the player's historical performance data with the team's needs and suggests the optimal timing for a trade or transfer. For example, the historical performance reference unit suggests a trade for a player whose performance is declining. In this way, team composition can be optimized by evaluating the possibility of a player being traded or transferred based on historical performance.

[0101] The historical performance inquiry unit can use the emotion estimation function to analyze fans' expectations regarding historical performance and attract fan interest. The historical performance inquiry unit, for example, analyzes historical performance data and fans' emotional response data to evaluate fans' expectations. For example, the historical performance inquiry unit analyzes the impact of a specific performance on fans' expectations. The historical performance inquiry unit also uses the emotion estimation function to collect fans' expectations regarding historical performance in real time. For example, the historical performance inquiry unit analyzes tweets during a game to evaluate fans' expectations. The historical performance inquiry unit also evaluates the impact of historical performance on fans' interest based on the fan expectation data. For example, the historical performance inquiry unit analyzes to what extent a specific performance increases fans' interest. In this way, fans' expectations regarding historical performance are analyzed and their interest is attracted, thereby increasing fan engagement.

[0102] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0103] The performance inquiry unit can use the player's performance data to evaluate the player's performance and estimate the player's market value. For example, the performance inquiry unit can analyze the player's performance data, such as the player's batting average, number of home runs, and earned run average, to estimate the player's market value. The performance inquiry unit can also predict the player's future market value based on past performance data. For example, the performance inquiry unit can predict the player's market value for the next season based on the player's performance data from the past five years. The performance inquiry unit can also take the player's training data and health status into consideration to more accurately estimate the player's market value. This can support the team's strategic decision-making by evaluating the player's market value and predicting its future market value.

[0104] The performance inquiry unit can evaluate a player's performance using the player's performance data and visualize the effects of the player's training. For example, the performance inquiry unit can analyze performance data such as a player's batting average, number of home runs, and earned run average to evaluate the effects of training. The performance inquiry unit can also integrate training data and performance data to display the training effects in a graph. For example, the performance inquiry unit can display a graph showing the effect of a specific training menu on batting average. The performance inquiry unit can also propose an optimal training plan based on the effects of the player's training. In this way, the effects of a player's training can be visualized and an optimal training plan can be proposed to help improve the player's performance.

[0105] The performance inquiry unit can use the emotion estimation function to analyze fans' emotional reactions to a player's performance and evaluate the player's popularity. For example, the performance inquiry unit can analyze a player's performance data and fans' emotional reaction data to evaluate the player's popularity. The performance inquiry unit can also use the emotion estimation function to collect fans' real-time emotional reactions to a player's performance. For example, the performance inquiry unit can analyze fans' tweets about the player's performance during a game. The performance inquiry unit can also evaluate the impact of a player's performance on fans' popularity based on the fans' emotional reaction data. In this way, the emotional reactions of fans to a player's performance can be analyzed and the player's popularity can be evaluated, thereby attracting fan interest.

[0106] The result inquiry unit can compare the performance data of other sports and analyze the correlation of performance between different sports. For example, the result inquiry unit compares the performance data of a baseball player with the performance data of players of other sports and analyzes the correlation of performance. The result inquiry unit can also integrate the performance data of different sports to find common performance indicators. For example, the result inquiry unit can analyze the correlation between batting average and number of goals scored. The result inquiry unit can also use the performance data of other sports to build a model to predict the performance of a baseball player. In this way, analyzing the correlation of performance between different sports makes it possible to evaluate performance from a broader perspective.

[0107] The performance inquiry unit can use performance data to predict a player's health condition and injury risk. For example, the performance inquiry unit analyzes a player's performance data and health data to predict injury risk. The performance inquiry unit can also use performance data to build a model to evaluate a player's health condition. For example, the performance inquiry unit evaluates a player's health condition based on fluctuations in batting average and earned run average. The performance inquiry unit can also integrate health data and performance data to optimize a player's training plan. This makes it possible to predict a player's health condition and injury risk, thereby maintaining a player's performance and preventing injuries.

[0108] The performance inquiry unit can use the emotion estimation function to analyze fans' expectations for a player's performance and attract fans' interest. For example, the performance inquiry unit can analyze a player's performance data and fans' emotional response data to evaluate fans' expectations. The performance inquiry unit can also use the emotion estimation function to collect fans' expectations for a player's performance in real time. For example, the performance inquiry unit can analyze fans' expectations for a game's performance from tweets. The performance inquiry unit can also evaluate the impact of a player's performance on fan interest based on the fan expectation data. This can analyze fans' expectations for a player's performance and attract fans' interest, thereby increasing fan engagement.

[0109] The game result confirmation unit can analyze the game results in real time and propose strategic changes during the game. For example, a system can be constructed in which the game result confirmation unit analyzes the game results in real time and proposes strategic changes during the game. For example, the game result confirmation unit proposes pitcher changes or defensive position changes. The game result confirmation unit can also collect data during the game in real time and evaluate the timing of strategic changes. For example, the game result confirmation unit proposes batter changes in specific situations. The game result confirmation unit can also propose a strategy for the next play in real time based on the game results. In this way, game performance can be optimized by proposing strategic changes during the game in real time.

[0110] The game result confirmation unit can automatically generate a strategy for the next game based on the game results. For example, the game result confirmation unit analyzes the game results and builds a system that automatically generates a strategy for the next game. For example, the game result confirmation unit suggests changes to pitcher rotations and batting orders. The game result confirmation unit can also propose an optimal strategy for the next game based on the results of past games. For example, the game result confirmation unit suggests the placement of batters against a specific pitcher. The game result confirmation unit can also simulate a strategy for the next game using game result data. This allows for the automatic generation of a strategy for the next game, making game preparation more efficient.

[0111] The match result confirmation unit can use the emotion estimation function to analyze fans' emotional reactions to the match result and evaluate the impact of the match. For example, the match result confirmation unit can analyze match result data and fans' emotional reaction data to evaluate the impact of the match result on fans. The match result confirmation unit can also use the emotion estimation function to collect fans' real-time emotional reactions to the match result. For example, the match result confirmation unit can analyze tweets during the match to evaluate fans' emotions. The match result confirmation unit can also evaluate the impact of the match result on fans' interest based on the fans' emotional reaction data. In this way, it is possible to attract fans' interest by analyzing fans' emotional reactions to the match result and evaluating the impact of the match.

[0112] The game result confirmation unit can compare the results of games with those of other leagues and international games and conduct analysis from a global perspective. For example, the game result confirmation unit collects data on the results of games from other leagues and international games and builds a system for comparative analysis. For example, the game result confirmation unit compares the results of MLB and NPB games. The game result confirmation unit can also analyze the results of games from different leagues from a global perspective and find common performance indicators. For example, the game result confirmation unit makes international comparisons of batting averages and earned run averages. The game result confirmation unit can also propose global strategies based on the result data of other leagues and international games. This makes it possible to analyze games from a global perspective by comparing them with those of other leagues and international games.

[0113] The processing flow of the second embodiment will be briefly explained below.

[0114] Step 1: The performance inquiry unit inquires about various performance statistics, such as a player's batting average and number of home runs, and a pitcher's number of wins and earned run average. For example, when a user inputs a prompt such as "Tell me the top 10 batting averages this season," the performance inquiry unit uses the generation AI to analyze the instruction and display a list of the performance of the corresponding players. Also, when a user inputs a prompt such as "Tell me the number of home runs hit by player A," the performance inquiry unit uses the generation AI to analyze the instruction and display the corresponding performance. Also, when a user inputs a prompt such as "Tell me the earned run average of pitcher B," the performance inquiry unit uses the generation AI to analyze the instruction and display the corresponding performance. Step 2: The match result confirmation unit checks the previous day's match results and the current score sheet based on the results queried by the score inquiry unit. For example, when a user inputs a prompt such as "Tell me the results of yesterday's match," the match result confirmation unit uses the generation AI to analyze the instruction and display the previous day's match results. Also, when a user inputs a prompt such as "Tell me the current score sheet," the match result confirmation unit uses the generation AI to analyze the instruction and display the current score sheet. Also, when a user inputs a prompt such as "Tell me the results of this week's match," the match result confirmation unit uses the generation AI to analyze the instruction and display the corresponding match results. Step 3: The conditional performance reference unit searches for the number of spectators and weather information for that day from the match schedule confirmed by the match result confirmation unit, and finds the match results under those conditions. For example, when a user inputs a prompt such as "Tell me the number of spectators and weather for the next match," the conditional performance reference unit uses the generation AI to analyze the instruction and display the corresponding information. Also, when a user inputs a prompt such as "Tell me the results of matches played on rainy days," the conditional performance reference unit uses the generation AI to analyze the instruction and display the corresponding results. Also, when a user inputs a prompt such as "Tell me the results of matches with high attendances," the conditional performance reference unit uses the generation AI to analyze the instruction and display the corresponding results.

[0115] 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.

[0116] 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> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). 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 speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. 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. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0117] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0118] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0119] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0120] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0121] 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.

[0122] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0123] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0128] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0129] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0130] 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.

[0131] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0132] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0133] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0134] 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.

[0135] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0136] 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.

[0137] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0138] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0143] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0144] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0145] 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.

[0146] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0147] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0148] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0149] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0150] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0151] 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.

[0152] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0153] 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 image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0154] 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.

[0155] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the 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.

[0156] 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.

[0157] 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.

[0158] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0159] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0160] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0161] 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.

[0162] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0163] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0164] 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.

[0165] FIG. 9 illustrates 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 behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions 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.

[0166] 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.

[0167] 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).

[0168] 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 expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, 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 expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0169] 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."

[0170] 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.

[0171] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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. A processor also includes 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.

[0176] The hardware resource that executes the specific process 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 process may be a single processor.

[0177] 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.

[0178] 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.

[0179] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0180] 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.

[0181] 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. [Explanation of symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A performance inquiry section that queries various performance data, such as players' batting averages and home runs, and pitchers' wins and earned run averages, a match result confirmation unit that checks the previous day's match results and the current score sheet based on the results inquired by the result inquiry unit; a condition result inquiry unit that searches for the number of spectators and weather information for that day from the match schedule confirmed by the match result confirmation unit, and obtains the match results under those conditions. A system characterized by:

2. The grade inquiry unit Predict future grades based on grade data and provide them to users 2. The system of claim 1.

3. The grade inquiry unit Analyze the effectiveness of athletes' training using performance data and propose optimal training plans 2. The system of claim 1.

4. The grade inquiry unit Analyzing fans' emotional responses to players' performance and assessing the impact of performance 2. The system of claim 1.

5. The grade inquiry unit Compare performance data from other sports and analyze correlations between performance across different sports 2. The system of claim 1.

Images