system

Abstract

The system according to this embodiment aims to provide information and interactive experiences that allow spectators to enjoy the game more deeply. [Solution] The system according to the embodiment comprises an explanation unit, an analysis unit, a question answering unit, an emotion collection unit, and a feedback collection unit. The explanation unit provides commentary on the match. The analysis unit analyzes information about the players and the match. The question answering unit responds to questions from the audience. The emotion collection unit collects the emotions and reactions of the audience. The feedback collection unit collects feedback after the match.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, information provision and interactive experiences for spectators to enjoy the game more deeply are not sufficiently provided, and there is room for improvement. [[ID=B]]

[0005] The system according to the embodiment aims to provide information provision and interactive experiences for spectators to enjoy the game more deeply.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a commentary unit, an analysis unit, a question answering unit, an emotion collection unit, and a feedback collection unit. The commentary unit provides commentary on the match. The analysis unit analyzes information about the players and the match. The question answering unit responds to questions from the audience. The emotion collection unit collects the emotions and reactions of the audience. The feedback collection unit collects feedback after the match has ended. [Effects of the Invention]

[0007] The system according to this embodiment can provide information and interactive experiences that allow spectators to enjoy the game more deeply. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The AI ​​app for enhancing the MLB game-watching experience according to an embodiment of the present invention is an app designed to allow MLB fans to enjoy games more deeply. This app uses AI to provide real-time commentary on the game, analyze player performance, and answer questions during the game. Furthermore, it adds a function to collect audience emotions and reactions in real time and customize the commentary and information provided based on that. First, the user launches the app and watches the game. During the game, the AI ​​provides real-time commentary on the game. For example, it provides detailed information about players' past performance and the current game situation. Next, when the user enters a question during the game, the AI ​​responds immediately. Furthermore, the app collects audience emotions and reactions in real time and customizes the commentary and information provided based on this. After the game ends, the app collects feedback from the user, and the AI ​​improves the method of commentary and information provision for the next game. By introducing this app, MLB fans can gain a deeper understanding of the game details and obtain real-time background information on players and the game. In addition, the AI's immediate response to audience questions and information provision based on emotions and reactions significantly improves the game-watching experience. As a result, fan satisfaction will increase, and watching MLB games will become a more interactive and enjoyable experience. By continuously improving based on audience feedback, it will be possible to provide the ultimate viewing experience. The MLB viewing experience enhancement AI app is designed to help MLB fans enjoy games more deeply, with AI providing real-time commentary, player performance analysis, and answering questions during the game. Furthermore, it will add a feature to collect audience emotions and reactions in real time and customize commentary and information based on that. This allows MLB fans to gain a deeper understanding of game details and obtain real-time background information on players and the game. The AI's instant responses to audience questions and information based on emotions and reactions will significantly improve the viewing experience. As a result, fan satisfaction will increase, and watching MLB games will become a more interactive and enjoyable experience. By continuously improving based on audience feedback, it will be possible to provide the ultimate viewing experience.

[0029] The AI ​​app for enhancing the MLB viewing experience according to this embodiment comprises a commentary unit, an analysis unit, a question answering unit, an emotion collection unit, and a feedback collection unit. The commentary unit provides commentary on the game. For example, the commentary unit provides explanations of the game's progress, player performance, and tactics. The commentary unit grasps the game's progress in real time and provides appropriate commentary to the audience. For example, the commentary unit grasps the game's progress in real time and provides appropriate commentary to the audience. The commentary unit grasps the game's progress in real time and provides appropriate commentary to the audience. The analysis unit analyzes information about players and the game. For example, the analysis unit analyzes past player performance and game statistics. The analysis unit evaluates player performance and provides detailed information to the audience. For example, the analysis unit evaluates player performance and provides detailed information to the audience. The analysis unit evaluates player performance and provides detailed information to the audience. The question answering unit responds to questions from the audience. For example, the question answering unit receives questions from the audience and provides appropriate answers. The question-answering unit responds immediately to audience questions, deepening their understanding. The question-answering unit responds immediately to audience questions, deepening their understanding. The question-answering unit responds immediately to audience questions, deepening their understanding. The emotion collection unit collects audience emotions and reactions. The emotion collection unit collects emotions and reactions, for example, through audience facial expressions, voices, and surveys. The emotion collection unit collects audience emotions and reactions in real time and reflects them in commentary and information provision. The emotion collection unit collects audience emotions and reactions, for example, in real time and reflects them in commentary and information provision. The emotion collection unit collects audience emotions and reactions in real time and reflects them in commentary and information provision. The feedback collection unit collects feedback after the match. The feedback collection unit collects feedback, for example, through surveys, comment collection, and evaluation systems. The feedback collection unit collects feedback after the match and improves the methods of commentary and information provision for the next match. The feedback collection department, for example, collects feedback after a match and uses it to improve the methods of commentary and information provision for the next match.The feedback collection unit collects feedback after the game and improves the methods of providing commentary and information for the next game. As a result, the AI ​​app for enhancing the MLB viewing experience according to the embodiment enhances the MLB viewing experience and enables the provision of customized information based on the emotions and reactions of the audience.

[0030] The commentary team provides commentary on the game. This includes, for example, explaining the game's progress, player performance, and tactics. Specifically, the commentary team monitors the game's progress in real time and provides appropriate commentary to the audience. To understand the game's progress, the commentary team receives live game data feeds and analyzes this data using AI. For example, they analyze detailed data such as pitcher's pitching speed and pitch type, batter's batting statistics, and defensive positioning in real time and explain it clearly to the audience. Furthermore, the commentary team provides deeper insights by referring to past game data and player performance data and comparing it to the current game situation. For example, they explain how a particular player has performed against the same pitcher in the past, or what results a particular tactic has yielded. This allows the audience to gain a deeper understanding of the game's flow and player performance. The commentary team can also collect audience reactions and emotions in real time and adjust their commentary accordingly. For example, if the audience shows strong interest in a particular player or play, they will provide detailed commentary on that player or play. This allows the commentary team to provide customized commentary tailored to the audience's interests and concerns, thereby enhancing the viewing experience.

[0031] The analytics department analyzes information about players and games. Specifically, it analyzes players' past performance and game statistics to evaluate player performance. The analytics department uses AI to quickly and accurately analyze large amounts of data and provide detailed information to spectators. For example, it analyzes players' batting and pitching statistics and defensive performance in detail and explains them to spectators in an easy-to-understand manner. Furthermore, the analytics department evaluates the flow of the game and the effectiveness of tactics based on game statistics. For example, it analyzes what results specific tactics produced and how player performance influenced the outcome of the game. This allows spectators to gain a deeper understanding of game tactics and player performance. The analytics department can also use past data and statistics to predict future games and player performance. For example, it can predict how a particular player will perform in the next game or what results a particular tactic will bring in the next game. This allows spectators to predict the development of the game and player performance in advance, making the viewing experience more interesting. In addition, the analytics department can collect feedback from spectators and improve its analysis based on that feedback. For example, if spectators show strong interest in specific information, the analytics department will provide a detailed analysis of that information. This allows the analysis department to provide customized information tailored to the interests and concerns of the audience, thereby enhancing the viewing experience.

[0032] The question-answering unit responds to audience questions. Specifically, it receives questions from the audience and provides appropriate answers. The question-answering unit uses AI to analyze audience questions and generate answers quickly and accurately. For example, if an audience member asks about a specific player's performance or the rules of a match, the question-answering unit searches for relevant data and provides a clear answer. Furthermore, the question-answering unit responds to audience questions immediately, deepening their understanding. For example, if an audience member has a question during a match, the question-answering unit provides an answer in real time, allowing the audience to understand the match more deeply. The question-answering unit also stores past questions and answers in a database, enabling quick responses to similar questions in the future. This allows the question-answering unit to respond to audience questions quickly and accurately, improving the viewing experience. In addition, the question-answering unit can collect audience feedback and improve its answers based on that feedback. For example, if an audience member is not satisfied with a particular answer, the unit revises the answer based on that feedback and provides a more appropriate answer to the next question. This allows the question-answering unit not only to deepen the audience's understanding but also to improve their satisfaction.

[0033] The Emotion Collection Unit collects audience emotions and reactions. Specifically, it collects emotions and reactions through audience facial expressions, voices, and surveys. The Emotion Collection Unit uses AI to analyze audience facial expressions and voices to grasp emotions in real time. For example, it analyzes whether the audience is happy, surprised, or excited, and uses this information to inform commentary and information provision. Furthermore, the Emotion Collection Unit collects audience emotions and reactions through surveys to obtain detailed data. This allows the Emotion Collection Unit to collect audience emotions and reactions in real time and reflect them in commentary and information provision. For example, if an audience member shows strong interest in a particular player or play, it can provide detailed commentary on that player or play. The Emotion Collection Unit can also improve its methods of commentary and information provision based on audience emotions and reactions. For example, if an audience member is dissatisfied with a particular commentary, it can revise the commentary based on that feedback and provide more appropriate commentary for the next match. In this way, the Emotion Collection Unit can provide customized information based on audience emotions and reactions, improving the viewing experience. Furthermore, the emotion collection unit can monitor audience emotions and reactions over the long term, allowing it to understand changes in audience interests and preferences. This enables the emotion collection unit to provide information tailored to the audience's interests and preferences, thereby enriching the viewing experience.

[0034] The Feedback Collection Department collects feedback after matches. Specifically, it collects feedback through surveys, comment collection, and evaluation systems. The Feedback Collection Department conducts surveys with spectators after matches to collect evaluations and opinions on the match commentary and information provided. For example, it collects detailed information such as which commentary was helpful, which information was interesting, and which areas need improvement. Furthermore, the Feedback Collection Department collects free-flowing opinions and impressions from spectators through a comment collection system. This allows the Feedback Collection Department to collect a wide range of spectator opinions and impressions, enabling it to improve its commentary and information provision methods for future matches. In addition, the Feedback Collection Department uses an evaluation system to quantify the degree of spectator satisfaction with the commentary and information provision and identify specific areas for improvement. This allows the Feedback Collection Department to continuously improve its commentary and information provision methods based on spectator feedback, thereby enhancing the viewing experience. Furthermore, the Feedback Collection Department can analyze spectator feedback over the long term to understand changes in spectator interests and concerns. This allows the Feedback Collection Department to provide customized information tailored to spectators' interests and concerns, further enriching the viewing experience.

[0035] The commentary team provides real-time commentary on the match. For example, the commentary team will explain the progress of the match, player performance, and tactics. The commentary team will monitor the match's progress in real time and provide appropriate commentary to the audience. This real-time commentary will enhance the audience's understanding of the match.

[0036] The analytics department analyzes player performance and detailed match information. For example, the analytics department analyzes players' past performance and match statistics. The analytics department evaluates player performance and provides detailed information to the audience. For example, the analytics department evaluates player performance and provides detailed information to the audience. The analytics department evaluates player performance and provides detailed information to the audience. This allows the analytics department to provide deep insights to the audience by analyzing player performance and detailed match information.

[0037] The question-answering unit responds immediately to questions from the audience. For example, the question-answering unit receives questions from the audience and provides appropriate answers. The question-answering unit responds immediately to audience questions, deepening the audience's understanding. The question-answering unit responds immediately to audience questions, deepening the audience's understanding. This improves the viewing experience by providing immediate responses to audience questions.

[0038] The feedback collection department collects feedback after matches and improves the methods of commentary and information provision for the next match. The feedback collection department collects feedback through methods such as surveys, comment collection, and evaluation systems. The feedback collection department collects feedback after matches and improves the methods of commentary and information provision for the next match. The feedback collection department collects feedback after matches and improves the methods of commentary and information provision for the next match. This allows for a continuous improvement of the viewing experience by collecting feedback after matches and making improvements for the next match.

[0039] The commentary team will refer to past match data and provide commentary tailored to the current match situation. For example, if a particular player is performing well in the current match, the commentary team will incorporate that player's past performance and important plays into their commentary. If the current match is close, the commentary team will refer to data from similar close matches in the past to explain strategies and trends. If a particular tactic is being used in the current match, the commentary team will explain examples of successes and failures of similar tactics in past matches. In this way, by referring to past match data, they can provide commentary tailored to the current match situation.

[0040] The commentary team provides commentary that focuses on specific players or plays based on the audience's areas of interest. For example, if the audience is interested in a particular player, the commentary will include that player's past performance and anecdotes. If the audience is interested in a particular play, the commentary team will explain the technical details and strategies of that play. If the audience is interested in a particular team, the commentary team will include the team's history and tactics. This enhances the viewing experience by providing commentary tailored to the audience's areas of interest.

[0041] The commentary team will provide commentary that includes region-specific information, taking into account the geographical location of the audience. For example, if the audience is in a specific region, the commentary team will incorporate information about players or teams from that region into their commentary. If the audience is in a specific region, the commentary team will incorporate information about past matches or events in that region into their commentary. If the audience is in a specific region, the commentary team will incorporate information about the culture and sports history of that region into their commentary. By providing commentary that includes region-specific information, the commentary team aims to make it easier to capture the audience's interest.

[0042] The commentary team analyzes audience social media activity and incorporates relevant topics into their commentary. For example, if audience members are discussing a particular player on social media, they will include information about that player in their commentary. If audience members are discussing a particular play on social media, they will explain the technical details and strategies behind that play. If audience members are discussing a particular team on social media, they will include information about that team's history and tactics in their commentary. This allows the commentary team to incorporate relevant topics into their commentary by analyzing audience social media activity.

[0043] The analysis department meticulously analyzes players' past performance data and makes predictions based on the current game situation. For example, the analysis department predicts a player's performance in the current game based on their past batting average and earned run average. The analysis department predicts a player's performance against their current opponent based on their past head-to-head record. The analysis department predicts a player's tactics and strategies in the current game based on their past game performance. In this way, predictions based on players' past performance data make it easier to predict the course of the game.

[0044] The analysis department evaluates player performance in real time according to the progress of the game. For example, the analysis department evaluates players' batting average and earned run average in real time during the game and provides this information to the audience. The analysis department evaluates players' base running and fielding performance in real time and provides this information to the audience. The analysis department evaluates players' pitching and batting performance in real time and provides this information to the audience. By providing real-time evaluations according to the progress of the game, the analysis department deepens the audience's understanding.

[0045] The analytics department analyzes region-specific information about players and teams, taking into account the geographical location of the audience. For example, if the audience is in a specific region, the analytics department analyzes the performance of players and teams from that region. If the audience is in a specific region, the analytics department analyzes data on past matches and events in that region. If the audience is in a specific region, the analytics department analyzes data on the sports culture and history of that region. By analyzing region-specific information in this way, the department makes it easier to attract the audience's interest.

[0046] The analytics department analyzes audience social media activity and incorporates relevant data into the analysis results. For example, if audience members are discussing a particular player on social media, the analytics department will incorporate that player's performance data into the analysis results. If audience members are discussing a particular play on social media, the analytics department will incorporate the technical details and strategies of that play into the analysis results. If audience members are discussing a particular team on social media, the analytics department will incorporate the team's performance and tactics into the analysis results. In this way, by analyzing audience social media activity, relevant data can be incorporated into the analysis results.

[0047] The question-answering unit refers to past question history and provides the best possible answer to similar questions. For example, the question-answering unit provides the best possible answer to similar questions based on questions previously asked by spectators. The question-answering unit analyzes questions previously asked by spectators and provides relevant additional information. The question-answering unit provides the best possible answer based on questions previously asked by spectators, taking into account the current match situation. This allows the system to provide the best possible answer to similar questions by referring to past question history.

[0048] The Q&A section provides additional relevant information depending on the content of the question. For example, if a spectator asks about a specific player, the Q&A section will provide information on that player's past performance and anecdotes. If a spectator asks about a specific play, the Q&A section will provide technical details and strategies for that play. If a spectator asks about a specific team, the Q&A section will provide information on that team's history and tactics. In this way, by providing additional information tailored to the content of the question, the Q&A section enhances the spectator's understanding.

[0049] The question-answering unit takes into account the audience's geographical location and provides responses that include region-specific information. For example, if the audience is in a specific region, the question-answering unit will include information about players or teams from that region in its response. If the audience is in a specific region, the question-answering unit will include information about past matches or events in that region in its response. If the audience is in a specific region, the question-answering unit will include information about the culture or sports history of that region in its response. By providing responses that include region-specific information, the system makes it easier to capture the audience's interest.

[0050] The Q&A department analyzes audience members' social media activity and incorporates relevant topics into its responses. For example, if an audience member is discussing a particular player on social media, the department will incorporate information about that player into its responses. If an audience member is discussing a particular play on social media, the department will incorporate technical details and strategies related to that play into its responses. If an audience member is discussing a particular team on social media, the department will incorporate the team's history and tactics into its responses. This allows the department to incorporate relevant topics into its responses by analyzing audience members' social media activity.

[0051] The emotion collection unit references past emotional data of the audience to more accurately estimate their current emotions. For example, the emotion collection unit estimates current emotions based on past emotional data of the audience. The emotion collection unit analyzes past emotional data of the audience to estimate emotions appropriate to the current game situation. The emotion collection unit predicts changes in current emotions based on past emotional data of the audience. In this way, by referencing past emotional data, current emotions can be estimated more accurately.

[0052] The emotion collection unit updates emotion data in real time according to the progress of the match. For example, the emotion collection unit updates emotion data in real time during important plays and scoring scenes in the match. The emotion collection unit collects and updates emotion data in real time according to the progress of the match. The emotion collection unit analyzes and updates spectator emotion data in real time according to the progress of the match. This allows for an accurate understanding of spectator emotions by providing real-time emotion data according to the progress of the match.

[0053] The sentiment collection unit collects region-specific sentiment data, taking into account the geographical location of the audience. For example, if an audience member is in a specific region, the sentiment collection unit prioritizes collecting sentiment data for that region. If an audience member is in a specific region, the sentiment collection unit collects sentiment data based on the culture and sports history of that region. If an audience member is in a specific region, the sentiment collection unit collects sentiment data based on past matches and events in that region. By collecting region-specific sentiment data, it becomes possible to understand audience sentiment more accurately.

[0054] The sentiment collection unit analyzes audience members' social media activity and collects relevant sentiment data. For example, if an audience member is discussing a particular player on social media, the sentiment collection unit collects sentiment data about that player. If an audience member is discussing a particular play on social media, the sentiment collection unit collects sentiment data about that play. If an audience member is discussing a particular team on social media, the sentiment collection unit collects sentiment data about that team. In this way, relevant sentiment data can be collected by analyzing audience members' social media activity.

[0055] The feedback collection unit refers to past feedback data to collect current feedback more accurately. For example, the feedback collection unit collects current feedback based on past audience feedback data. The feedback collection unit analyzes past audience feedback data to collect feedback appropriate to the current game situation. The feedback collection unit predicts changes in current feedback based on past audience feedback data. This allows for more accurate collection of current feedback by referring to past feedback data.

[0056] The feedback collection unit updates feedback data in real time according to the progress of the match. For example, the feedback collection unit updates feedback data in real time during important plays and scoring scenes in the match. The feedback collection unit collects and updates feedback data in real time according to the progress of the match. The feedback collection unit analyzes and updates spectator feedback data in real time according to the progress of the match. This allows for accurate understanding of spectator feedback by providing real-time feedback data according to the progress of the match.

[0057] The feedback collection unit collects region-specific feedback, taking into account the geographical location of the audience. For example, if an audience member is in a specific region, the feedback collection unit prioritizes collecting feedback from that region. If an audience member is in a specific region, the feedback collection unit collects feedback based on the culture and sport history of that region. If an audience member is in a specific region, the feedback collection unit collects feedback based on past matches and events in that region. By collecting region-specific feedback, it becomes possible to understand audience feedback more accurately.

[0058] The feedback collection unit analyzes audience members' social media activity and collects relevant feedback data. For example, if an audience member is discussing a particular player on social media, the feedback collection unit collects feedback data about that player. If an audience member is discussing a particular play on social media, the feedback collection unit collects feedback data about that play. If an audience member is discussing a particular team on social media, the feedback collection unit collects feedback data about that team. In this way, relevant feedback data can be collected by analyzing audience members' social media activity.

[0059] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0060] The commentary team can provide commentary that includes region-specific information, taking into account the geographical location of the audience. For example, if the audience is in a specific region, the commentary can include information about players or teams from that region. It can also include information about past matches or events in that region. Furthermore, it can include information about the culture and sports history of that region. By providing commentary that includes region-specific information, it becomes easier to capture the audience's interest.

[0061] The analytics department can analyze audience members' social media activity and reflect relevant data in the analysis results. For example, if audience members are discussing a particular player on social media, that player's performance data can be reflected in the analysis results. Similarly, if audience members are discussing a particular play on social media, the technical details and strategies of that play can be reflected in the analysis results. Furthermore, if audience members are discussing a particular team on social media, the team's performance and tactics can be reflected in the analysis results. In this way, by analyzing audience members' social media activity, relevant data can be reflected in the analysis results.

[0062] The question answering unit can refer to past question history and provide the best possible response to similar questions. For example, it can provide the best possible response to similar questions based on what spectators have asked in the past. It can also analyze what spectators have asked in the past and provide relevant additional information. Furthermore, it can provide the best possible response based on what spectators have asked in the past, taking into account the current match situation. In this way, by referring to past question history, it can provide the best possible response to similar questions.

[0063] The emotion collection unit can more accurately estimate current emotions by referring to past emotional data of the audience. For example, it can estimate current emotions based on past emotional data of the audience. It can also analyze past emotional data of the audience to estimate emotions appropriate to the current game situation. Furthermore, it can predict changes in current emotions based on past emotional data of the audience. In this way, current emotions can be estimated more accurately by referring to past emotional data.

[0064] The feedback collection unit can update feedback data in real time according to the progress of the match. For example, it can update feedback data in real time for important plays and scoring scenes during the match. It can also collect and update feedback data in real time according to the progress of the match. Furthermore, it can analyze and update spectator feedback data in real time according to the progress of the match. This allows for accurate understanding of spectator feedback by providing real-time feedback data according to the progress of the match.

[0065] The following briefly describes the processing flow for example form 1.

[0066] Step 1: The commentary team monitors the progress of the match, player performance, and tactical explanations in real time, and provides appropriate commentary to the audience. Step 2: The analysis department analyzes players' past performance and match statistics to evaluate their performance and provide detailed information to the audience. Step 3: The question-and-answer section receives questions from the audience, provides immediate and appropriate answers, and enhances the audience's understanding. Step 4: The emotion collection unit collects emotions and reactions in real time through audience facial expressions, voices, and surveys, and incorporates them into explanations and information provision. Step 5: The feedback collection department collects feedback after the match through surveys, comment collection, and evaluation systems, and uses this information to improve the methods of commentary and information provision for the next match.

[0067] (Example of form 2) The AI ​​app for enhancing the MLB game-watching experience according to an embodiment of the present invention is an app designed to allow MLB fans to enjoy games more deeply. This app uses AI to provide real-time commentary on the game, analyze player performance, and answer questions during the game. Furthermore, it adds a function to collect audience emotions and reactions in real time and customize the commentary and information provided based on that. First, the user launches the app and watches the game. During the game, the AI ​​provides real-time commentary on the game. For example, it provides detailed information about players' past performance and the current game situation. Next, when the user enters a question during the game, the AI ​​responds immediately. Furthermore, the app collects audience emotions and reactions in real time and customizes the commentary and information provided based on this. After the game ends, the app collects feedback from the user, and the AI ​​improves the method of commentary and information provision for the next game. By introducing this app, MLB fans can gain a deeper understanding of the game details and obtain real-time background information on players and the game. In addition, the AI's immediate response to audience questions and information provision based on emotions and reactions significantly improves the game-watching experience. As a result, fan satisfaction will increase, and watching MLB games will become a more interactive and enjoyable experience. By continuously improving based on audience feedback, it will be possible to provide the ultimate viewing experience. The MLB viewing experience enhancement AI app is designed to help MLB fans enjoy games more deeply, with AI providing real-time commentary, player performance analysis, and answering questions during the game. Furthermore, it will add a feature to collect audience emotions and reactions in real time and customize commentary and information based on that. This allows MLB fans to gain a deeper understanding of game details and obtain real-time background information on players and the game. The AI's instant responses to audience questions and information based on emotions and reactions will significantly improve the viewing experience. As a result, fan satisfaction will increase, and watching MLB games will become a more interactive and enjoyable experience. By continuously improving based on audience feedback, it will be possible to provide the ultimate viewing experience.

[0068] The AI ​​app for enhancing the MLB viewing experience according to this embodiment comprises a commentary unit, an analysis unit, a question answering unit, an emotion collection unit, and a feedback collection unit. The commentary unit provides commentary on the game. For example, the commentary unit provides explanations of the game's progress, player performance, and tactics. The commentary unit grasps the game's progress in real time and provides appropriate commentary to the audience. For example, the commentary unit grasps the game's progress in real time and provides appropriate commentary to the audience. The commentary unit grasps the game's progress in real time and provides appropriate commentary to the audience. The analysis unit analyzes information about players and the game. For example, the analysis unit analyzes past player performance and game statistics. The analysis unit evaluates player performance and provides detailed information to the audience. For example, the analysis unit evaluates player performance and provides detailed information to the audience. The analysis unit evaluates player performance and provides detailed information to the audience. The question answering unit responds to questions from the audience. For example, the question answering unit receives questions from the audience and provides appropriate answers. The question-answering unit responds immediately to audience questions, deepening their understanding. The question-answering unit responds immediately to audience questions, deepening their understanding. The question-answering unit responds immediately to audience questions, deepening their understanding. The emotion collection unit collects audience emotions and reactions. The emotion collection unit collects emotions and reactions, for example, through audience facial expressions, voices, and surveys. The emotion collection unit collects audience emotions and reactions in real time and reflects them in commentary and information provision. The emotion collection unit collects audience emotions and reactions, for example, in real time and reflects them in commentary and information provision. The emotion collection unit collects audience emotions and reactions in real time and reflects them in commentary and information provision. The feedback collection unit collects feedback after the match. The feedback collection unit collects feedback, for example, through surveys, comment collection, and evaluation systems. The feedback collection unit collects feedback after the match and improves the methods of commentary and information provision for the next match. The feedback collection department, for example, collects feedback after a match and uses it to improve the methods of commentary and information provision for the next match.The feedback collection unit collects feedback after the game and improves the methods of providing commentary and information for the next game. As a result, the AI ​​app for enhancing the MLB viewing experience according to the embodiment enhances the MLB viewing experience and enables the provision of customized information based on the emotions and reactions of the audience.

[0069] The commentary team provides commentary on the game. This includes, for example, explaining the game's progress, player performance, and tactics. Specifically, the commentary team monitors the game's progress in real time and provides appropriate commentary to the audience. To understand the game's progress, the commentary team receives live game data feeds and analyzes this data using AI. For example, they analyze detailed data such as pitcher's pitching speed and pitch type, batter's batting statistics, and defensive positioning in real time and explain it clearly to the audience. Furthermore, the commentary team provides deeper insights by referring to past game data and player performance data and comparing it to the current game situation. For example, they explain how a particular player has performed against the same pitcher in the past, or what results a particular tactic has yielded. This allows the audience to gain a deeper understanding of the game's flow and player performance. The commentary team can also collect audience reactions and emotions in real time and adjust their commentary accordingly. For example, if the audience shows strong interest in a particular player or play, they will provide detailed commentary on that player or play. This allows the commentary team to provide customized commentary tailored to the audience's interests and concerns, thereby enhancing the viewing experience.

[0070] The analytics department analyzes information about players and games. Specifically, it analyzes players' past performance and game statistics to evaluate player performance. The analytics department uses AI to quickly and accurately analyze large amounts of data and provide detailed information to spectators. For example, it analyzes players' batting and pitching statistics and defensive performance in detail and explains them to spectators in an easy-to-understand manner. Furthermore, the analytics department evaluates the flow of the game and the effectiveness of tactics based on game statistics. For example, it analyzes what results specific tactics produced and how player performance influenced the outcome of the game. This allows spectators to gain a deeper understanding of game tactics and player performance. The analytics department can also use past data and statistics to predict future games and player performance. For example, it can predict how a particular player will perform in the next game or what results a particular tactic will bring in the next game. This allows spectators to predict the development of the game and player performance in advance, making the viewing experience more interesting. In addition, the analytics department can collect feedback from spectators and improve its analysis based on that feedback. For example, if spectators show strong interest in specific information, the analytics department will provide a detailed analysis of that information. This allows the analysis department to provide customized information tailored to the interests and concerns of the audience, thereby enhancing the viewing experience.

[0071] The question-answering unit responds to audience questions. Specifically, it receives questions from the audience and provides appropriate answers. The question-answering unit uses AI to analyze audience questions and generate answers quickly and accurately. For example, if an audience member asks about a specific player's performance or the rules of a match, the question-answering unit searches for relevant data and provides a clear answer. Furthermore, the question-answering unit responds to audience questions immediately, deepening their understanding. For example, if an audience member has a question during a match, the question-answering unit provides an answer in real time, allowing the audience to understand the match more deeply. The question-answering unit also stores past questions and answers in a database, enabling quick responses to similar questions in the future. This allows the question-answering unit to respond to audience questions quickly and accurately, improving the viewing experience. In addition, the question-answering unit can collect audience feedback and improve its answers based on that feedback. For example, if an audience member is not satisfied with a particular answer, the unit revises the answer based on that feedback and provides a more appropriate answer to the next question. This allows the question-answering unit not only to deepen the audience's understanding but also to improve their satisfaction.

[0072] The Emotion Collection Unit collects audience emotions and reactions. Specifically, it collects emotions and reactions through audience facial expressions, voices, and surveys. The Emotion Collection Unit uses AI to analyze audience facial expressions and voices to grasp emotions in real time. For example, it analyzes whether the audience is happy, surprised, or excited, and uses this information to inform commentary and information provision. Furthermore, the Emotion Collection Unit collects audience emotions and reactions through surveys to obtain detailed data. This allows the Emotion Collection Unit to collect audience emotions and reactions in real time and reflect them in commentary and information provision. For example, if an audience member shows strong interest in a particular player or play, it can provide detailed commentary on that player or play. The Emotion Collection Unit can also improve its methods of commentary and information provision based on audience emotions and reactions. For example, if an audience member is dissatisfied with a particular commentary, it can revise the commentary based on that feedback and provide more appropriate commentary for the next match. In this way, the Emotion Collection Unit can provide customized information based on audience emotions and reactions, improving the viewing experience. Furthermore, the emotion collection unit can monitor audience emotions and reactions over the long term, allowing it to understand changes in audience interests and preferences. This enables the emotion collection unit to provide information tailored to the audience's interests and preferences, thereby enriching the viewing experience.

[0073] The Feedback Collection Department collects feedback after matches. Specifically, it collects feedback through surveys, comment collection, and evaluation systems. The Feedback Collection Department conducts surveys with spectators after matches to collect evaluations and opinions on the match commentary and information provided. For example, it collects detailed information such as which commentary was helpful, which information was interesting, and which areas need improvement. Furthermore, the Feedback Collection Department collects free-flowing opinions and impressions from spectators through a comment collection system. This allows the Feedback Collection Department to collect a wide range of spectator opinions and impressions, enabling it to improve its commentary and information provision methods for future matches. In addition, the Feedback Collection Department uses an evaluation system to quantify the degree of spectator satisfaction with the commentary and information provision and identify specific areas for improvement. This allows the Feedback Collection Department to continuously improve its commentary and information provision methods based on spectator feedback, thereby enhancing the viewing experience. Furthermore, the Feedback Collection Department can analyze spectator feedback over the long term to understand changes in spectator interests and concerns. This allows the Feedback Collection Department to provide customized information tailored to spectators' interests and concerns, further enriching the viewing experience.

[0074] The commentary team provides real-time commentary on the match. For example, the commentary team will explain the progress of the match, player performance, and tactics. The commentary team will monitor the match's progress in real time and provide appropriate commentary to the audience. This real-time commentary will enhance the audience's understanding of the match.

[0075] The analytics department analyzes player performance and detailed match information. For example, the analytics department analyzes players' past performance and match statistics. The analytics department evaluates player performance and provides detailed information to the audience. For example, the analytics department evaluates player performance and provides detailed information to the audience. The analytics department evaluates player performance and provides detailed information to the audience. This allows the analytics department to provide deep insights to the audience by analyzing player performance and detailed match information.

[0076] The question-answering unit responds immediately to questions from the audience. For example, the question-answering unit receives questions from the audience and provides appropriate answers. The question-answering unit responds immediately to audience questions, deepening the audience's understanding. The question-answering unit responds immediately to audience questions, deepening the audience's understanding. This improves the viewing experience by providing immediate responses to audience questions.

[0077] The emotion collection unit collects audience emotions and reactions in real time. The emotion collection unit collects emotions and reactions through, for example, audience facial expressions, voice, and surveys. The emotion collection unit collects audience emotions and reactions in real time and reflects them in commentary and information provision. The emotion collection unit collects audience emotions and reactions in real time and reflects them in commentary and information provision. This allows for customized information provision by collecting audience emotions and reactions in real time. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0078] The feedback collection department collects feedback after matches and improves the methods of commentary and information provision for the next match. The feedback collection department collects feedback through methods such as surveys, comment collection, and evaluation systems. The feedback collection department collects feedback after matches and improves the methods of commentary and information provision for the next match. The feedback collection department collects feedback after matches and improves the methods of commentary and information provision for the next match. This allows for a continuous improvement of the viewing experience by collecting feedback after matches and making improvements for the next match.

[0079] The commentary team estimates the audience's emotions and adjusts the tone and content of their commentary based on those estimates. For example, if the audience is excited, the commentary team will make their tone more energetic and convey the excitement in line with the audience's feelings. If the audience is calm, the commentary team will make their tone calmer and provide detailed technical explanations. If the audience is dissatisfied, the commentary team will make their tone neutral and emphasize the positive aspects of the match. This enhances the viewing experience by providing commentary that is tailored to the audience's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0080] The commentary team will refer to past match data and provide commentary tailored to the current match situation. For example, if a particular player is performing well in the current match, the commentary team will incorporate that player's past performance and important plays into their commentary. If the current match is close, the commentary team will refer to data from similar close matches in the past to explain strategies and trends. If a particular tactic is being used in the current match, the commentary team will explain examples of successes and failures of similar tactics in past matches. In this way, by referring to past match data, they can provide commentary tailored to the current match situation.

[0081] The commentary team provides commentary that focuses on specific players or plays based on the audience's areas of interest. For example, if the audience is interested in a particular player, the commentary will include that player's past performance and anecdotes. If the audience is interested in a particular play, the commentary team will explain the technical details and strategies of that play. If the audience is interested in a particular team, the commentary team will include the team's history and tactics. This enhances the viewing experience by providing commentary tailored to the audience's areas of interest.

[0082] The commentary team estimates the audience's emotions and adjusts the frequency of commentary based on these estimates. For example, if the audience is excited, the commentary team increases the frequency of commentary to provide real-time information that matches the progress of the match. If the audience is calm, the commentary team decreases the frequency of commentary to provide information focused on key points. If the audience is dissatisfied, the commentary team adjusts the frequency of commentary to emphasize the positive aspects of the match. This improves the viewing experience by adjusting the frequency of commentary according to the audience's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0083] The commentary team will provide commentary that includes region-specific information, taking into account the geographical location of the audience. For example, if the audience is in a specific region, the commentary team will incorporate information about players or teams from that region into their commentary. If the audience is in a specific region, the commentary team will incorporate information about past matches or events in that region into their commentary. If the audience is in a specific region, the commentary team will incorporate information about the culture and sports history of that region into their commentary. By providing commentary that includes region-specific information, the commentary team aims to make it easier to capture the audience's interest.

[0084] The commentary team analyzes audience social media activity and incorporates relevant topics into their commentary. For example, if audience members are discussing a particular player on social media, they will include information about that player in their commentary. If audience members are discussing a particular play on social media, they will explain the technical details and strategies behind that play. If audience members are discussing a particular team on social media, they will include information about that team's history and tactics in their commentary. This allows the commentary team to incorporate relevant topics into their commentary by analyzing audience social media activity.

[0085] The analysis unit estimates the audience's emotions and adjusts how the analysis results are displayed based on the estimated emotions. For example, if the audience is excited, the analysis unit displays the results using visually stimulating graphics. If the audience is calm, the analysis unit displays the results using detailed data and graphs. If the audience is dissatisfied, the analysis unit highlights positive data in the analysis results. This provides a display method that is tailored to the audience's emotions, thereby deepening the understanding of the analysis results. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0086] The analysis department meticulously analyzes players' past performance data and makes predictions based on the current game situation. For example, the analysis department predicts a player's performance in the current game based on their past batting average and earned run average. The analysis department predicts a player's performance against their current opponent based on their past head-to-head record. The analysis department predicts a player's tactics and strategies in the current game based on their past game performance. In this way, predictions based on players' past performance data make it easier to predict the course of the game.

[0087] The analysis department evaluates player performance in real time according to the progress of the game. For example, the analysis department evaluates players' batting average and earned run average in real time during the game and provides this information to the audience. The analysis department evaluates players' base running and fielding performance in real time and provides this information to the audience. The analysis department evaluates players' pitching and batting performance in real time and provides this information to the audience. By providing real-time evaluations according to the progress of the game, the analysis department deepens the audience's understanding.

[0088] The analysis unit estimates the audience's emotions and prioritizes the analysis results based on the estimated emotions. For example, if the audience is excited, the analysis unit prioritizes displaying important data and highlights. If the audience is calm, the analysis unit prioritizes displaying detailed data and statistics. If the audience is dissatisfied, the analysis unit prioritizes displaying positive data and success stories. This allows for the priority of important information to be provided according to the audience's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0089] The analytics department analyzes region-specific information about players and teams, taking into account the geographical location of the audience. For example, if the audience is in a specific region, the analytics department analyzes the performance of players and teams from that region. If the audience is in a specific region, the analytics department analyzes data on past matches and events in that region. If the audience is in a specific region, the analytics department analyzes data on the sports culture and history of that region. By analyzing region-specific information in this way, the department makes it easier to attract the audience's interest.

[0090] The analytics department analyzes audience social media activity and incorporates relevant data into the analysis results. For example, if audience members are discussing a particular player on social media, the analytics department will incorporate that player's performance data into the analysis results. If audience members are discussing a particular play on social media, the analytics department will incorporate the technical details and strategies of that play into the analysis results. If audience members are discussing a particular team on social media, the analytics department will incorporate the team's performance and tactics into the analysis results. In this way, by analyzing audience social media activity, relevant data can be incorporated into the analysis results.

[0091] The question-answering unit estimates the audience's emotions and adjusts the tone and content of its responses based on the estimated emotions. For example, if the audience is excited, the question-answering unit will make its response tone energetic and convey excitement that matches the emotion. If the audience is calm, the question-answering unit will make its response tone gentle and provide detailed technical explanations. If the audience is dissatisfied, the question-answering unit will make its response tone neutral and emphasize the positive aspects of the game. This enhances the viewing experience by providing responses that match the audience's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0092] The question-answering unit refers to past question history and provides the best possible answer to similar questions. For example, the question-answering unit provides the best possible answer to similar questions based on questions previously asked by spectators. The question-answering unit analyzes questions previously asked by spectators and provides relevant additional information. The question-answering unit provides the best possible answer based on questions previously asked by spectators, taking into account the current match situation. This allows the system to provide the best possible answer to similar questions by referring to past question history.

[0093] The Q&A section provides additional relevant information depending on the content of the question. For example, if a spectator asks about a specific player, the Q&A section will provide information on that player's past performance and anecdotes. If a spectator asks about a specific play, the Q&A section will provide technical details and strategies for that play. If a spectator asks about a specific team, the Q&A section will provide information on that team's history and tactics. In this way, by providing additional information tailored to the content of the question, the Q&A section enhances the spectator's understanding.

[0094] The question-answering unit estimates the audience's emotions and prioritizes responses based on those emotions. For example, if the audience is excited, the unit prioritizes responses to important questions and highlights. If the audience is calm, the unit prioritizes responses to detailed and technical questions. If the audience is dissatisfied, the unit prioritizes responses to positive questions and success stories. This ensures that responses to important questions are prioritized by determining priorities according to the audience's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0095] The question-answering unit takes into account the audience's geographical location and provides responses that include region-specific information. For example, if the audience is in a specific region, the question-answering unit will include information about players or teams from that region in its response. If the audience is in a specific region, the question-answering unit will include information about past matches or events in that region in its response. If the audience is in a specific region, the question-answering unit will include information about the culture or sports history of that region in its response. By providing responses that include region-specific information, the system makes it easier to capture the audience's interest.

[0096] The Q&A department analyzes audience members' social media activity and incorporates relevant topics into its responses. For example, if an audience member is discussing a particular player on social media, the department will incorporate information about that player into its responses. If an audience member is discussing a particular play on social media, the department will incorporate technical details and strategies related to that play into its responses. If an audience member is discussing a particular team on social media, the department will incorporate the team's history and tactics into its responses. This allows the department to incorporate relevant topics into its responses by analyzing audience members' social media activity.

[0097] The emotion collection unit estimates the audience's emotions and adjusts the collection method based on the estimated emotions. For example, if the audience is excited, the emotion collection unit collects emotion data frequently in real time. If the audience is calm, the emotion collection unit reduces the frequency of emotion data collection and collects more detailed data. If the audience is dissatisfied, the emotion collection unit adjusts the emotion data collection method, prioritizing the collection of positive data. This improves the accuracy of emotion data collection by providing a collection method that is tailored to the audience's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0098] The emotion collection unit references past emotional data of the audience to more accurately estimate their current emotions. For example, the emotion collection unit estimates current emotions based on past emotional data of the audience. The emotion collection unit analyzes past emotional data of the audience to estimate emotions appropriate to the current game situation. The emotion collection unit predicts changes in current emotions based on past emotional data of the audience. In this way, by referencing past emotional data, current emotions can be estimated more accurately.

[0099] The emotion collection unit updates emotion data in real time according to the progress of the match. For example, the emotion collection unit updates emotion data in real time during important plays and scoring scenes in the match. The emotion collection unit collects and updates emotion data in real time according to the progress of the match. The emotion collection unit analyzes and updates spectator emotion data in real time according to the progress of the match. This allows for an accurate understanding of spectator emotions by providing real-time emotion data according to the progress of the match.

[0100] The emotion collection unit estimates the audience's emotions and determines the priority of the data to be collected based on the estimated audience emotions. For example, if the audience is excited, the emotion collection unit prioritizes collecting important emotional data. If the audience is calm, the emotion collection unit prioritizes collecting detailed emotional data. If the audience is dissatisfied, the emotion collection unit prioritizes collecting positive emotional data. In this way, important emotional data can be collected preferentially by determining priorities according to the audience's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0101] The sentiment collection unit collects region-specific sentiment data, taking into account the geographical location of the audience. For example, if an audience member is in a specific region, the sentiment collection unit prioritizes collecting sentiment data for that region. If an audience member is in a specific region, the sentiment collection unit collects sentiment data based on the culture and sports history of that region. If an audience member is in a specific region, the sentiment collection unit collects sentiment data based on past matches and events in that region. By collecting region-specific sentiment data, it becomes possible to understand audience sentiment more accurately.

[0102] The sentiment collection unit analyzes audience members' social media activity and collects relevant sentiment data. For example, if an audience member is discussing a particular player on social media, the sentiment collection unit collects sentiment data about that player. If an audience member is discussing a particular play on social media, the sentiment collection unit collects sentiment data about that play. If an audience member is discussing a particular team on social media, the sentiment collection unit collects sentiment data about that team. In this way, relevant sentiment data can be collected by analyzing audience members' social media activity.

[0103] The feedback collection unit estimates the audience's emotions and adjusts the feedback collection method based on the estimated emotions. For example, if the audience is excited, the feedback collection unit collects feedback frequently in real time. If the audience is calm, the feedback collection unit reduces the frequency of feedback collection and collects more detailed feedback. If the audience is dissatisfied, the feedback collection unit adjusts the feedback collection method and prioritizes collecting positive feedback. This improves the accuracy of feedback collection by providing a collection method that is tailored to the audience's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0104] The feedback collection unit refers to past feedback data to collect current feedback more accurately. For example, the feedback collection unit collects current feedback based on past audience feedback data. The feedback collection unit analyzes past audience feedback data to collect feedback appropriate to the current game situation. The feedback collection unit predicts changes in current feedback based on past audience feedback data. This allows for more accurate collection of current feedback by referring to past feedback data.

[0105] The feedback collection unit updates feedback data in real time according to the progress of the match. For example, the feedback collection unit updates feedback data in real time during important plays and scoring scenes in the match. The feedback collection unit collects and updates feedback data in real time according to the progress of the match. The feedback collection unit analyzes and updates spectator feedback data in real time according to the progress of the match. This allows for accurate understanding of spectator feedback by providing real-time feedback data according to the progress of the match.

[0106] The feedback collection unit estimates the audience's emotions and prioritizes feedback based on those emotions. For example, if the audience is excited, the feedback collection unit prioritizes collecting important feedback. If the audience is calm, the feedback collection unit prioritizes collecting detailed feedback. If the audience is dissatisfied, the feedback collection unit prioritizes collecting positive feedback. This allows for the priority collection of important feedback by determining priorities according to the audience's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0107] The feedback collection unit collects region-specific feedback, taking into account the geographical location of the audience. For example, if an audience member is in a specific region, the feedback collection unit prioritizes collecting feedback from that region. If an audience member is in a specific region, the feedback collection unit collects feedback based on the culture and sport history of that region. If an audience member is in a specific region, the feedback collection unit collects feedback based on past matches and events in that region. By collecting region-specific feedback, it becomes possible to understand audience feedback more accurately.

[0108] The feedback collection unit analyzes audience members' social media activity and collects relevant feedback data. For example, if an audience member is discussing a particular player on social media, the feedback collection unit collects feedback data about that player. If an audience member is discussing a particular play on social media, the feedback collection unit collects feedback data about that play. If an audience member is discussing a particular team on social media, the feedback collection unit collects feedback data about that team. In this way, relevant feedback data can be collected by analyzing audience members' social media activity.

[0109] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0110] The commentary team can estimate the audience's emotions and adjust the tone and content of their commentary based on those estimates. For example, if the audience is excited, the commentary can be made more energetic to convey the excitement in line with their feelings. If the audience is calm, the commentary can be made calmer and detailed technical explanations can be provided. Furthermore, if the audience is dissatisfied, the commentary can be made neutral and the positive aspects of the match can be emphasized. In this way, the viewing experience can be improved by providing commentary that is tailored to the audience's emotions.

[0111] The analysis unit can estimate the audience's emotions and adjust how the analysis results are displayed based on those estimated emotions. For example, if the audience is excited, the analysis results can be displayed using visually stimulating graphics. If the audience is calm, the analysis results can be displayed using detailed data and graphs. Furthermore, if the audience is dissatisfied, the analysis results can be displayed by highlighting positive data. This allows for a deeper understanding of the analysis results by providing a display method that is tailored to the audience's emotions.

[0112] The question-answering unit can estimate the audience's emotions and adjust the tone and content of its responses based on those estimates. For example, if the audience is excited, the response tone can be energetic to convey excitement that matches their emotions. If the audience is calm, the response tone can be gentle, and detailed technical explanations can be provided. Furthermore, if the audience is dissatisfied, the response tone can be neutral, and the positive aspects of the match can be emphasized. In this way, the viewing experience can be improved by providing responses that match the audience's emotions.

[0113] The emotion collection unit can estimate the audience's emotions and adjust the collection method based on the estimated emotions. For example, if the audience is excited, emotion data can be collected frequently in real time. If the audience is calm, the frequency of emotion data collection can be reduced, and more detailed data can be collected. Furthermore, if the audience is dissatisfied, the emotion data collection method can be adjusted to prioritize the collection of positive data. By providing a collection method that is tailored to the audience's emotions, the accuracy of emotion data collection can be improved.

[0114] The feedback collection unit can estimate the audience's emotions and adjust the feedback collection method based on those estimated emotions. For example, if the audience is excited, feedback can be collected frequently in real time. If the audience is calm, the frequency of feedback collection can be reduced, and more detailed feedback can be collected. Furthermore, if the audience is dissatisfied, the feedback collection method can be adjusted to prioritize the collection of positive feedback. By providing a collection method that responds to the audience's emotions, the accuracy of feedback collection can be improved.

[0115] The commentary team can provide commentary that includes region-specific information, taking into account the geographical location of the audience. For example, if the audience is in a specific region, the commentary can include information about players or teams from that region. It can also include information about past matches or events in that region. Furthermore, it can include information about the culture and sports history of that region. By providing commentary that includes region-specific information, it becomes easier to capture the audience's interest.

[0116] The analytics department can analyze audience members' social media activity and reflect relevant data in the analysis results. For example, if audience members are discussing a particular player on social media, that player's performance data can be reflected in the analysis results. Similarly, if audience members are discussing a particular play on social media, the technical details and strategies of that play can be reflected in the analysis results. Furthermore, if audience members are discussing a particular team on social media, the team's performance and tactics can be reflected in the analysis results. In this way, by analyzing audience members' social media activity, relevant data can be reflected in the analysis results.

[0117] The question answering unit can refer to past question history and provide the best possible response to similar questions. For example, it can provide the best possible response to similar questions based on what spectators have asked in the past. It can also analyze what spectators have asked in the past and provide relevant additional information. Furthermore, it can provide the best possible response based on what spectators have asked in the past, taking into account the current match situation. In this way, by referring to past question history, it can provide the best possible response to similar questions.

[0118] The emotion collection unit can more accurately estimate current emotions by referring to past emotional data of the audience. For example, it can estimate current emotions based on past emotional data of the audience. It can also analyze past emotional data of the audience to estimate emotions appropriate to the current game situation. Furthermore, it can predict changes in current emotions based on past emotional data of the audience. In this way, current emotions can be estimated more accurately by referring to past emotional data.

[0119] The feedback collection unit can update feedback data in real time according to the progress of the match. For example, it can update feedback data in real time for important plays and scoring scenes during the match. It can also collect and update feedback data in real time according to the progress of the match. Furthermore, it can analyze and update spectator feedback data in real time according to the progress of the match. This allows for accurate understanding of spectator feedback by providing real-time feedback data according to the progress of the match.

[0120] The following briefly describes the processing flow for example form 2.

[0121] Step 1: The commentary team monitors the progress of the match, player performance, and tactical explanations in real time, and provides appropriate commentary to the audience. Step 2: The analysis department analyzes players' past performance and match statistics to evaluate their performance and provide detailed information to the audience. Step 3: The question-and-answer section receives questions from the audience, provides immediate and appropriate answers, and enhances the audience's understanding. Step 4: The emotion collection unit collects emotions and reactions in real time through audience facial expressions, voices, and surveys, and incorporates them into explanations and information provision. Step 5: The feedback collection department collects feedback after the match through surveys, comment collection, and evaluation systems, and uses this information to improve the methods of commentary and information provision for the next match.

[0122] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0123] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0124] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0125] Each of the multiple elements described above, including the commentary unit, analysis unit, question answering unit, emotion collection unit, and feedback collection unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the commentary unit is implemented by the control unit 46A of the smart device 14, which grasps the progress of the match in real time and provides appropriate commentary to the audience. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes the past performance of players and statistical data of the match. The question answering unit is implemented by the control unit 46A of the smart device 14, which responds immediately to questions from the audience. The emotion collection unit collects the emotions and reactions of the audience in real time using the camera 42 and microphone 38B of the smart device 14, for example. The feedback collection unit is implemented by the specific processing unit 290 of the data processing unit 12, for example, which collects feedback after the match and improves the method of commentary and information provision for the next match. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0126] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0127] As shown in Figure 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.

[0128] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0129] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0130] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0132] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0133] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0134] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0135] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0136] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0137] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0138] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0140] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0141] Each of the multiple elements described above, including the commentary unit, analysis unit, question answering unit, emotion collection unit, and feedback collection unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the commentary unit is implemented by the control unit 46A of the smart glasses 214, which grasps the progress of the match in real time and provides appropriate commentary to the audience. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes the past performance of players and statistical data of the match. The question answering unit is implemented by the control unit 46A of the smart glasses 214, which responds immediately to questions from the audience. The emotion collection unit collects the emotions and reactions of the audience in real time using the camera 42 and microphone 238 of the smart glasses 214, for example. The feedback collection unit is implemented by the specific processing unit 290 of the data processing unit 12, for example, which collects feedback after the match and improves the method of commentary and information provision for the next match. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0142] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0143] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0144] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0145] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0146] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0148] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0149] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0150] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0151] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0152] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0153] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0154] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0155] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0156] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0157] Each of the multiple elements described above, including the commentary unit, analysis unit, question answering unit, emotion collection unit, and feedback collection unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the commentary unit is implemented by the control unit 46A of the headset terminal 314, which grasps the progress of the match in real time and provides appropriate commentary to the audience. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes the past performance of players and statistical data of the match. The question answering unit is implemented by the control unit 46A of the headset terminal 314, which responds immediately to questions from the audience. The emotion collection unit collects the emotions and reactions of the audience in real time using the camera 42 and microphone 238 of the headset terminal 314, for example. The feedback collection unit is implemented by the specific processing unit 290 of the data processing unit 12, for example, which collects feedback after the match and improves the method of commentary and information provision for the next match. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0158] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0159] As shown in Figure 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.

[0160] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0161] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0162] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0163] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0164] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0165] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0166] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0167] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0168] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0169] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0170] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0171] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0172] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0173] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0174] Each of the multiple elements described above, including the commentary unit, analysis unit, question answering unit, emotion collection unit, and feedback collection unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the commentary unit is implemented by the control unit 46A of the robot 414, which grasps the progress of the match in real time and provides appropriate commentary to the audience. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes the past performance of players and statistical data of the match. The question answering unit is implemented by the control unit 46A of the robot 414, which responds immediately to questions from the audience. The emotion collection unit collects the emotions and reactions of the audience in real time using the camera 42 and microphone 238 of the robot 414, for example. The feedback collection unit is implemented by the specific processing unit 290 of the data processing unit 12, for example, which collects feedback after the match and improves the method of commentary and information provision for the next match. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0175] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0176] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0177] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0178] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0179] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0180] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0181] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0182] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0183] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0184] 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.

[0185] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0186] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0187] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0188] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0189] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0190] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0191] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0192] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0193] (Note 1) The commentary team provides commentary on the match, The analysis department analyzes information about players and matches, A question-and-answer section that responds to questions from the audience, The emotion collection department collects the emotions and reactions of the audience, It includes a feedback collection unit that collects feedback after the end of the match. A system characterized by the following features. (Note 2) The aforementioned explanatory section is, Providing real-time commentary for the match The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit is Analyze player performance and detailed match information. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned question answering unit is Responding immediately to questions from the audience The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned emotion collection unit, Collect audience emotions and reactions in real time. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned feedback collection unit is We collect feedback after the match and use it to improve our commentary and information provision methods for the next match. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned explanatory section is, The system estimates the audience's emotions and adjusts the tone and content of the commentary based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned explanatory section is, We will refer to past match data and provide commentary tailored to the current match situation. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned explanatory section is, Based on the audience's areas of interest, the commentary will focus on specific players or plays. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned explanatory section is, The system estimates the audience's emotions and adjusts the frequency of commentary based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned explanatory section is, Providing commentary that includes region-specific information, taking into account the audience's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned explanatory section is, Analyze the audience's social media activity and incorporate relevant topics into the commentary. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit is It estimates the audience's emotions and adjusts how the analysis results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit is We analyze players' past performance data in detail and make predictions based on the current game situation. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit is Player performance is evaluated in real time according to the progress of the match. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit is The system estimates the audience's emotions and prioritizes the analysis results based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit is Analyze region-specific player and team information, taking into account the geographical location of the audience. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit is Analyze audience social media activity and incorporate relevant data into the analysis results. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned question answering unit is It estimates the audience's emotions and adjusts the tone and content of the response based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned question answering unit is Refer to past question history and provide the best answer to similar questions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned question answering unit is Depending on the nature of the question, we will provide relevant additional information. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned question answering unit is It estimates the audience's emotions and determines the priority of responses based on the estimated audience emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned question answering unit is Provide responses that include region-specific information, taking into account the audience's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned question answering unit is Analyze the audience's social media activity and incorporate relevant topics into the responses. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned emotion collection unit, We estimate the audience's emotions and adjust the data collection method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned emotion collection unit, Referencing past emotional data of the audience will allow for a more accurate estimation of their current emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned emotion collection unit, The emotional data is updated in real time according to the progress of the match. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned emotion collection unit, The system estimates audience emotions and prioritizes data collection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned emotion collection unit, Collect region-specific sentiment data, taking into account the audience's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned emotion collection unit, Analyze audience social media activity and collect relevant sentiment data. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned feedback collection unit is We estimate the audience's emotions and adjust the feedback collection method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned feedback collection unit is Referencing past feedback data allows for more accurate collection of current feedback. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned feedback collection unit is The feedback data is updated in real time according to the progress of the match. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned feedback collection unit is It estimates the audience's emotions and prioritizes feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned feedback collection unit is Collect region-specific feedback by considering the audience's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned feedback collection unit is Analyze audience social media activity and collect relevant feedback data. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0194] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The commentary team provides commentary on the match, The analysis department analyzes information about players and matches, A question-and-answer section that responds to questions from the audience, The emotion collection department collects the emotions and reactions of the audience, It includes a feedback collection unit that collects feedback after the end of the match. A system characterized by the following features.

2. The aforementioned explanatory section is, Providing real-time commentary for the match The system according to feature 1.

3. The aforementioned analysis unit is Analyze player performance and detailed match information. The system according to feature 1.

4. The aforementioned question answering unit is Responding immediately to questions from the audience The system according to feature 1.

5. The aforementioned emotion collection unit, Collect audience emotions and reactions in real time. The system according to feature 1.

6. The aforementioned feedback collection unit is We collect feedback after the match and use it to improve our commentary and information provision methods for the next match. The system according to feature 1.

7. The aforementioned explanatory section is, The system estimates the audience's emotions and adjusts the tone and content of the commentary based on those estimated emotions. The system according to feature 1.

8. The aforementioned explanatory section is, We will refer to past match data and provide commentary tailored to the current match situation. The system according to feature 1.

9. The aforementioned explanatory section is, Based on the audience's areas of interest, the commentary will focus on specific players or plays. The system according to feature 1.

10. The aforementioned explanatory section is, The system estimates the audience's emotions and adjusts the frequency of commentary based on those estimated emotions. The system according to feature 1.

Images