system

Abstract

The system according to this embodiment aims to automatically generate real-time commentary in accordance with the progress of the match. [Solution] The system according to the embodiment comprises a collection unit, a generation unit, and a provision unit. The collection unit collects match data, which is data from an ongoing match. The generation unit generates commentary based on the match data collected by the collection unit. The provision unit provides the commentary generated by the generation unit.

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, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds 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, real-time commentary according to the progress of a game has not been sufficiently automatically generated, and there is room for improvement.

[0005] The system according to an embodiment aims to automatically generate real-time commentary according to the progress of a game.

Means for Solving the Problems

[0006] The system according to an embodiment includes a collection unit, a generation unit, and a provision unit. The collection unit collects game data, which is data of a game in progress. The generation unit generates commentary based on the game data collected by the collection unit. The provision unit provides the commentary generated by the generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can automatically generate real-time commentary in accordance with the progress of the match. [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 signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface 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 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are 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) An embodiment of the present invention provides a real-time automatic comment generation system for sports viewing, which collects data from an ongoing match, generates commentary using a generating AI, and provides the commentary to the user. The real-time automatic comment generation system for sports viewing collects data from an ongoing match, generates commentary using a generating AI, and provides the commentary to the user. For example, the real-time automatic comment generation system for sports viewing collects data such as the match score, player movements, and the progress of the match. This data is collected by a collection unit. Next, based on the collected match data, the generating AI generates commentary. For example, if the match score changes, it generates a commentary such as "Player A has scored a goal!" based on the score. It can also refer to the player's past performance and information, and include background information and trivia. For example, it can generate a comment such as "Player A has scored 4 goals in the last 5 matches." Furthermore, it automatically detects highlights and notable moments of the match. For example, it detects the moment a player scores a goal or the moment an important play occurs. Based on this detection result, the generating AI emphasizes information about that moment and includes it in the commentary. For example, it generates a comment such as "A magnificent goal by Player B!" The generated commentary is provided to the user by the service provider. For example, it can be automatically posted to social media platforms. This allows users to keep track of the match's progress in real time. The generating AI can also generate comments by comparing a player's current performance with their past performance. For example, it can generate comments such as, "Player C is showing their best performance of the season." Furthermore, it can generate commentary in different tones depending on the progress of the match. For example, if the match is tense, it can generate comments such as, "The tension is rising!" Thus, the present invention is a system that automatically generates real-time comments for sports viewing. Based on the progress of the match and the points scored, the generating AI generates commentary, provides background information and trivia by referring to players' past performance and information, and can automatically detect and highlight highlights and noteworthy moments of the match in the comments.This allows the real-time automatic comment generation system for sports viewing to grasp the progress of the game in real time and provide it to users.

[0029] The real-time automatic comment generation system for sports viewing according to this embodiment comprises a collection unit, a generation unit, and a provision unit. The collection unit collects data on the ongoing match. For example, the collection unit collects data such as the match score, player movements, and the progress of the match. The collection unit can acquire the match score in real time and store it in a database. The collection unit can also track player movements and collect location data. The collection unit can also monitor the progress of the match and detect important events. The generation unit generates commentary based on the match data collected by the collection unit. For example, if the match score changes, the generation unit generates a commentary such as "Player A has scored!" based on the score. The generation unit can also refer to the player's past performance and information and include background information and trivia. For example, the generation unit generates a comment such as "Player A has scored 4 goals in the last 5 matches." The generation unit can also automatically detect highlights and notable moments of the match and include information about those moments in the commentary. The generation unit generates comments such as, for example, "A magnificent goal by player B!". Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary comments using, for example, a text generation AI (e.g., LLM). The generation AI takes match data as input and outputs commentary comments. The generation AI can also generate commentary comments in different tones depending on the progress of the match. For example, if the match is tense, the generation AI will generate comments such as "The tension is rising!". The provision unit provides the commentary comments generated by the generation unit to the user. The provision unit can, for example, automatically post to a social media platform. The provision unit can also notify the user of the commentary comments in real time. The provision unit can also select the optimal display method depending on the user's device. For example, the provision unit adjusts the display method of the commentary comments depending on the device, such as a smartphone, tablet, or PC. As a result, the real-time automatic comment generation system for sports viewing according to the embodiment can grasp the progress of the match in real time and provide it to the user.

[0030] The data collection unit collects data from ongoing matches. For example, it collects data such as match scores, player movements, and match progress. Specifically, match scores are acquired in real time and stored in a database. This allows for immediate understanding of score changes as the match progresses. Regarding player movements, location data is collected using a tracking system. For example, player location information is acquired with high accuracy using GPS and RFID tags, and player movement patterns and play details are recorded. Regarding match progress, the unit monitors important match events, automatically detecting events such as goals, fouls, and substitutions. This data is collected from various devices such as sensors, cameras, and microphones and integrated into a central database. Furthermore, the data collection unit processes this data in real time and can collaborate with other systems and departments as needed. For example, collected data is stored on a cloud server, making it accessible to the generation and provision units. Additionally, by adjusting the frequency and accuracy of data collection, flexible responses to specific situations and conditions are possible. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0031] The generation unit generates commentary based on match data collected by the collection unit. For example, if the score of the match changes, the generation unit generates commentary based on the score, such as "Player A has scored!" The generation unit can also refer to the player's past performance and information, and include background information and trivia. For example, it can generate a comment such as "Player A has scored 4 goals in the last 5 matches." The generation unit can also automatically detect highlights and notable moments of the match and include information about those moments in the commentary. For example, it can generate a comment such as "A magnificent goal by Player B!" Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). The generation AI takes match data as input and outputs commentary. The generation AI can also generate commentary in different tones depending on the progress of the match. For example, if the match is tense, it can generate a comment such as "The tension is rising!" The generation AI utilizes natural language processing technology to select appropriate expressions based on context, generating comments that are easy for users to understand and find interesting. Furthermore, the generation AI can learn from past match data and player statistics to generate even more accurate comments. As a result, the generation unit can generate and provide users with appropriate commentary in real time, according to the progress of the match.

[0032] The service provider delivers live commentary generated by the generation unit to the user. The service provider can, for example, automatically post to social media platforms. The service provider can also notify the user of the live commentary in real time. The service provider can also select the optimal display method depending on the user's device. For example, the service provider adjusts the display method of live commentary depending on the device, such as a smartphone, tablet, or PC. On smartphones, information can be delivered to the user instantly using push notifications or in-app notifications. On tablets and PCs, the display format of the comments can be adjusted according to the screen size to improve visibility. Furthermore, the service provider can provide notifications customized according to the user's preferences. For example, it is possible to set notifications to prioritize information about specific players or teams. The service provider can collect user feedback and continuously improve the accuracy and effectiveness of the information it provides. For example, it analyzes comments and reactions that users showed interest in and reflects them in the content of the next notification. In addition, the service provider can reliably transmit information using multiple communication methods. For example, it can reliably deliver important information by using not only smartphone notifications but also voice calls, SMS, email, etc. This allows the service provider to deliver live commentary to users quickly and reliably, enhancing the enjoyment of watching sports.

[0033] The acquisition unit acquires player data, which is data on players currently participating in a match. The acquisition unit acquires data such as the player's name, position, and statistical information. The acquisition unit can also acquire past performance data and information on players from a database. The acquisition unit can also collect real-time performance data of players. The acquisition unit can also track players' movements and collect location data. By acquiring player data, information about players can be included in the commentary. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input player movement data into a generating AI and have the generating AI process player performance data.

[0034] The detection unit detects important moments during a match. For example, it can detect important moments such as scoring plays, fouls, and turning points in the game. The detection unit can monitor the progress of the match in real time and detect important events. The detection unit can also track players' movements and detect important plays. The detection unit can also analyze the match score and player performance data to detect important moments. This allows for the detection of highlights and notable moments, enabling the inclusion of important scenes in commentary. Some or all of the above processing in the detection unit may be performed using AI or not. For example, the detection unit can input match progress data into a generating AI and have the generating AI perform the detection of important moments.

[0035] The generation unit generates commentary using a generation AI. For example, if the score of the match changes, the generation unit generates commentary based on the score, such as "Player A has scored!" The generation unit can also refer to the player's past performance and information, and include background information and trivia. For example, the generation unit generates commentary such as "Player A has scored 4 goals in the last 5 matches." The generation unit can also automatically detect highlights and notable moments of the match and include information about those moments in the commentary. For example, the generation unit generates commentary such as "A magnificent goal by Player B!" The generation unit can also generate commentary in different tones depending on the progress of the match. For example, if the match is tense, the generation unit generates commentary such as "The tension is rising!" Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). The generation AI takes match data as input and outputs commentary. The generating AI can also generate commentary in different tones depending on the progress of the match. For example, if the match is tense, the generating AI will generate a comment like, "The tension is rising!" This improves the accuracy of commentary generation when using the generating AI.

[0036] The service provider automatically posts the live commentary generated by the generation unit to social media. The service provider can, for example, automatically post to social media platforms. The service provider can also notify users of the live commentary in real time. The service provider can also select the optimal display method depending on the user's device. For example, the service provider adjusts the display method of the live commentary depending on the device, such as a smartphone, tablet, or PC. This allows users to share the progress of the match in real time by automatically posting the live commentary to social media platforms. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the generated live commentary into a generation AI and have the generation AI execute the posting to social media.

[0037] The generation unit generates comments by comparing a player's current performance with their past performance. For example, the generation unit compares a player's current performance with their past performance and generates a comment such as, "Player C is showing their best performance of the season." The generation unit can retrieve a player's past performance and information from a database and compare it with their current performance. The generation unit can also collect real-time performance data of players and compare it with their past performance. The generation unit can also track a player's movements and evaluate their current performance. This allows for the generation of more detailed commentary by comparing a player's current performance with their past performance. Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). The generation AI takes match data as input and outputs commentary. To compare a player's current performance with their past performance, the generation AI takes past performance data and real-time performance data as input and outputs the comparison results. This allows for the generation of detailed commentary by using a generation AI that compares a player's current performance with their past performance.

[0038] The generation unit generates commentary in different tones depending on the progress of the match. For example, if the match is tense, the generation unit will generate a comment such as "The tension is rising!" The generation unit can monitor the progress of the match in real time and generate commentary in the appropriate tone. The generation unit can also analyze the match score and player performance data and generate comments in a tone appropriate to the match situation. The generation unit can use excited tones, calm tones, explanatory tones, etc., depending on the progress of the match. By changing the tone according to the progress of the match, it is possible to provide more immersive commentary. Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). The generation AI takes match data as input and outputs commentary in a tone appropriate to the progress of the match. The generation AI can analyze the progress of the match in real time and generate comments in the appropriate tone. As a result, by using the generation AI, it is possible to generate immersive commentary in a tone appropriate to the progress of the match.

[0039] The generation unit provides different types of trivia information depending on the stage of the match. For example, the generation unit can provide different trivia information depending on the early, middle, and late stages of the match. The generation unit can monitor the progress of the match in real time and provide appropriate trivia information. The generation unit can also refer to players' past performance and information and provide trivia information appropriate to the stage of the match. For example, the generation unit can provide trivia information such as, "Player A has scored 4 goals in the last 5 matches." Depending on the stage of the match, the generation unit can provide trivia information including players' background information, past performance, and the history of the match. This allows for the generation of more interesting commentary by providing trivia information according to the stage of the match. Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates trivia information using, for example, a text generation AI (e.g., LLM). The generation AI takes match data as input and outputs trivia information appropriate to the stage of the match. The generation AI can analyze the progress of the match in real time and generate appropriate trivia information. This allows us to use a generation AI to create interesting commentary that includes trivia relevant to the stage of the match.

[0040] The generation unit generates commentary that includes comments generated by estimating the psychological state of players at important moments. For example, the generation unit estimates the psychological state of a player at the moment they score a goal or when an important play is made, and generates comments based on that psychological state. The generation unit can estimate a player's psychological state by analyzing their facial expressions, actions, and past statements. For example, the generation unit generates a comment such as, "Player B seems very pleased with this goal." The generation unit can estimate the psychological state of players in real time and generate commentary based on the results. This allows for the generation of more emotionally expressive commentary by estimating the psychological state of players. Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). To estimate a player's psychological state, the generation AI takes data on the player's facial expressions, actions, and past statements as input and outputs the psychological state. Based on the estimated psychological state, the generation AI can generate emotionally expressive commentary. This allows for the generation of emotionally rich commentary that estimates the psychological state of the players, using a generation AI.

[0041] The data collection unit collects data focusing on specific players or plays during match data collection. For example, the data collection unit prioritizes collecting data on the movements of players who are attracting attention during the match. The data collection unit can collect data focusing on specific plays (e.g., goals, home runs). The data collection unit can also collect data focusing on important moments in the match (e.g., penalty kicks, free throws). The data collection unit can monitor the progress of the match in real time and collect data focusing on specific players or plays. This allows for the collection of more detailed data by focusing on specific players or plays. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input match progress data into a generating AI and have the generating AI perform data collection focusing on specific players or plays.

[0042] The data collection unit dynamically changes the type of data it collects according to the progress of the match. For example, the data collection unit collects data on players' movements in the early stages of the match and data on the score in the later stages. The data collection unit can also collect data on spectator reactions as the match progresses. The data collection unit can also collect data on players' physical condition and performance as the match progresses. The data collection unit can monitor the progress of the match in real time and dynamically change the type of data it collects. This allows for more appropriate data collection by changing the type of data according to the progress of the match. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input data on the progress of the match into a generating AI and have the generating AI execute a process to dynamically change the type of data to collect.

[0043] The data collection unit collects audience reaction information when collecting match data and incorporates it into the commentary. For example, the data collection unit can collect cheers and boos from the audience and incorporate them into the commentary. The data collection unit can also collect data on applause and cheers from the audience and incorporate it into the commentary. The data collection unit can also collect audience reactions and incorporate them into the commentary. The data collection unit can monitor the progress of the match in real time and collect audience reaction data. By collecting audience reaction data, it is possible to generate more realistic commentary. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input audience audio and video data into a generating AI and have the generating AI collect audience reaction data.

[0044] The data collection unit collects weather and venue environmental data when collecting match data and incorporates it into the commentary. For example, the data collection unit can collect weather data during the match and incorporate it into the commentary. The data collection unit can also collect venue temperature and humidity data and incorporate it into the commentary. The data collection unit can also collect wind speed and wind direction data during the match and incorporate it into the commentary. The data collection unit can monitor the progress of the match in real time and collect weather and venue environmental data. By collecting weather and venue environmental data, it is possible to generate more detailed commentary. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input weather data and environmental data into a generating AI and have the generating AI perform the processing of incorporating it into the commentary.

[0045] The generation unit includes quotes and statements from past interviews and statements of players in the commentary it generates. For example, the generation unit can quote from past interviews of players and include them in the commentary. The generation unit can quote past statements of players and include them in the commentary. The generation unit can also quote past comments of players and include them in the commentary. The generation unit can retrieve past interviews and statements of players from a database and include them as quotes in the commentary. This makes it possible to generate more detailed commentary by quoting past interviews and statements of players. Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). The generation AI takes past interview data and statement data of players as input and outputs commentary that includes quotes. The generation AI can analyze past interviews and statements and generate commentary that includes appropriate quotes. This makes it possible to generate detailed commentary that quotes past interviews and statements of players by using a generation AI.

[0046] The generation unit includes the historical background and past memorable moments of the match in the commentary it generates. For example, the generation unit can generate commentary that includes the historical background of the match. The generation unit can generate commentary that includes past memorable moments. The generation unit can also generate commentary that includes historical events of the match. The generation unit can retrieve the historical background and past memorable moments of the match from a database and include them in the commentary. This makes it possible to generate more interesting commentary by including the historical background and past memorable moments of the match. Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). The generation AI takes historical background data and past memorable moments of the match as input and outputs commentary that includes them. The generation AI can analyze the historical background and past memorable moments and generate commentary that includes appropriate information. This makes it possible to generate interesting commentary that includes the historical background and past memorable moments of the match by using a generation AI.

[0047] The generation unit includes tactical commentary in the generated commentary, tailored to the progress of the match. For example, the generation unit generates commentary that includes tactical commentary according to the progress of the match. The generation unit can generate commentary that explains the tactical points of the match. The generation unit can also generate commentary that explains the tactical movements of the match. The generation unit can monitor the progress of the match in real time and generate commentary that includes tactical commentary. This allows for more detailed commentary by including tactical commentary tailored to the progress of the match. Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). The generation AI takes match data as input and outputs commentary that includes tactical commentary. The generation AI can analyze the progress of the match in real time and generate commentary that includes appropriate tactical commentary. This allows for the generation of detailed commentary that includes tactical commentary tailored to the progress of the match by using a generation AI.

[0048] The generation unit includes information about the rules and regulations of the match in the commentary it generates. For example, the generation unit generates commentary that includes information about the rules of the match. The generation unit can generate commentary that includes information about the rules of the match. The generation unit can also generate commentary that includes details about the rules and regulations of the match. The generation unit can retrieve information about the rules and regulations of the match from a database and include it in the commentary. This allows for the provision of commentary that is easier for viewers to understand by including information about the rules and regulations of the match. Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). The generation AI takes data about the rules and regulations of the match as input and outputs commentary that includes them. The generation AI can analyze the rules and regulations and generate commentary that includes appropriate information. This allows for the generation of easy-to-understand commentary that includes information about the rules and regulations of the match by using a generation AI.

[0049] The service provider adds relevant information to the commentary provided by the user by referring to the user's past viewing history. For example, the service provider can refer to the user's past viewing history and add relevant match information. The service provider can add relevant player information based on the user's past viewing history. The service provider can also add relevant trivia information based on the user's past viewing history. The service provider can retrieve the user's past viewing history from a database and add information related to the commentary. This allows the service provider to provide more relevant information by referring to the user's past viewing history. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the user's viewing history data into a generating AI and have the generating AI perform the addition of relevant information.

[0050] The service provider offers customization options for the commentary provided, tailored to the user's preferences. For example, the service provider can customize the tone of the commentary according to the user's preferences. The service provider can customize the length of the commentary according to the user's preferences. The service provider can also customize the content of the commentary according to the user's preferences. The service provider can provide customization options for the commentary based on the user's preferences. This allows for a more personalized experience by customizing the commentary according to the user's preferences. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input user preference data into a generating AI and have the generating AI perform the provision of customization options.

[0051] The service provider selects the optimal display method for the live commentary based on the user's device information. For example, if the user is using a smartphone, the service provider provides a display method that matches the screen size. If the user is using a tablet, the service provider can provide a display method optimized for a larger screen. If the user is using a smartwatch, the service provider can also provide a concise and highly visible display method. The service provider can acquire the user's device information in real time and select the optimal display method. This allows for the provision of more visually appealing live commentary by selecting the optimal display method based on the user's device information. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the user's device information into a generating AI and have the generating AI select the optimal display method.

[0052] The service provider adds relevant information to the live commentary by analyzing the user's social media activity. For example, the service provider can analyze the user's social media activity and add relevant match information. Based on the user's social media activity, the service provider can add relevant player information. Based on the user's social media activity, the service provider can also add relevant trivia information. The service provider can retrieve the user's social media activity from a database and add information related to the live commentary. This allows the service provider to provide more relevant information by analyzing the user's social media activity. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the user's social media activity data into a generating AI and have the generating AI add relevant information.

[0053] The acquisition unit acquires player data while considering the player's current condition and health status. For example, the acquisition unit can acquire data while considering the player's current condition. The acquisition unit can acquire data while considering the player's health status. The acquisition unit can also acquire data while considering the player's performance data. The acquisition unit can monitor the player's real-time condition and health status and acquire data based on that. This makes it possible to acquire more detailed data by considering the player's current condition and health status. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input player health data and performance data into a generating AI and have the generating AI perform the data acquisition.

[0054] The acquisition unit analyzes the player's social media activity and obtains relevant data when acquiring player data. For example, the acquisition unit can analyze the player's latest social media posts and obtain relevant data. The acquisition unit can also analyze the player's past social media activity and obtain relevant data. The acquisition unit can also analyze fan reactions to the player's social media and obtain relevant data. The acquisition unit can monitor the player's social media activity in real time and acquire data based on that. This makes it possible to acquire more detailed data by analyzing the player's social media activity. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input the player's social media data into a generating AI and have the generating AI perform the acquisition of relevant data.

[0055] The detection unit improves detection accuracy by analyzing the progress of the match and the movements of players in real time when detecting highlights and notable moments. For example, the detection unit can analyze the progress of the match in real time and detect highlights. The detection unit can analyze the movements of players in real time and detect notable moments. The detection unit can also improve detection accuracy by combining the progress of the match and the movements of players. The detection unit can monitor the progress of the match and the movements of players in real time and detect highlights and notable moments based on this. This enables more accurate detection by analyzing the progress of the match and the movements of players in real time. Some or all of the above processing in the detection unit may be performed using AI or not using AI. For example, the detection unit can input match progress data and player movement data into a generating AI and have the generating AI perform the detection of highlights and notable moments.

[0056] The detection unit improves detection accuracy by considering audience reaction data when detecting highlights and notable moments. For example, the detection unit can analyze audience cheers and boos to detect highlights. The detection unit can analyze audience applause and cheering data to detect notable moments. The detection unit can also analyze audience reactions to improve detection accuracy. The detection unit can monitor audience reaction data in real time and detect highlights and notable moments based on it. This allows for more accurate detection by considering audience reaction data. Some or all of the above processing in the detection unit may be performed using AI or not. For example, the detection unit can input audience audio and video data into a generating AI and have the generating AI perform the detection of highlights and notable moments.

[0057] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0058] A real-time automated comment generation system for sports viewing can analyze a user's past viewing history and provide relevant information. For example, it can refer to data from matches the user has watched in the past and provide information about relevant players and teams. If a user frequently watches a particular player, it can provide detailed information about that player. If a user supports a particular team, it can provide the latest information and trivia about that team. This allows for the provision of personalized information based on the user's viewing history. The analysis of viewing history is performed using past viewing data obtained from a database. The generating AI can receive this data as input and generate relevant information.

[0059] A real-time automatic comment generation system for sports viewing can provide different camera angles depending on the progress of the match. For example, when the match is tense, it can provide camera angles that zoom in on the players' expressions and movements. When the match is progressing smoothly, it can provide wide-angle camera angles that allow users to grasp the overall flow. During highlight scenes of the match, special camera angles can be added to visually emphasize them. This allows the system to provide users with a sense of realism through camera angles. The selection of camera angles is done by combining match data and user emotion data. The generating AI can receive this data as input and select the appropriate camera angle.

[0060] A real-time automated commentary generation system for sports viewing can provide different data visualizations depending on the progress of the match. For example, when the match is tense, it can visualize the players' movements and performance in real time. When the match is progressing smoothly, it can visualize match statistics and player performance. During match highlights, special visualizations can be added to visually emphasize them. This allows the system to provide users with a sense of realism through data visualizations. Data visualizations are generated by combining match data and user sentiment data. The generating AI can receive this data as input and generate appropriate data visualizations.

[0061] A real-time automatic comment generation system for sports viewing can provide different interactive features depending on the progress of the match. For example, when the match is tense, it can provide a feature that allows users to post comments in real time. When the match is progressing smoothly, it can provide a feature that allows users to check match statistics and player performance. During match highlights, it can provide a feature that allows users to replay specific moments. This allows the system to provide users with a sense of realism through interactive features. The provision of interactive features is done by combining match data and user sentiment data. The generating AI can receive this data as input and provide appropriate interactive features.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The data collection unit collects data from the ongoing match. The data collection unit collects data such as the match score, player movements, and the progress of the match. The data collection unit can acquire the match score in real time and store it in a database. The data collection unit can also track player movements and collect location data. The data collection unit can also monitor the progress of the match and detect important events. Step 2: The generation unit generates commentary based on the match data collected by the collection unit. For example, if the score of the match changes, the generation unit generates commentary based on the score, such as "Player A has scored!" The generation unit can also refer to the player's past performance and information, and include background information and trivia. For example, the generation unit generates commentary such as "Player A has scored 4 goals in the last 5 matches." The generation unit can also automatically detect highlights and notable moments of the match and include information about those moments in the commentary. For example, the generation unit generates commentary such as "A magnificent goal by Player B!" Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). The generation AI takes match data as input and outputs commentary. The generation AI can also generate commentary in different tones depending on the progress of the match. For example, if the match is tense, the generation AI generates commentary such as "The tension is rising!" Step 3: The provider unit provides the live commentary generated by the generator unit to the user. The provider unit can, for example, automatically post to social media platforms. The provider unit can also notify the user of the live commentary in real time. The provider unit can also select the optimal display method according to the user's device. For example, the provider unit adjusts the display method of the live commentary depending on the device, such as a smartphone, tablet, or PC.

[0064] (Example of form 2) An embodiment of the present invention provides a real-time automatic comment generation system for sports viewing, which collects data from an ongoing match, generates commentary using a generating AI, and provides the commentary to the user. The real-time automatic comment generation system for sports viewing collects data from an ongoing match, generates commentary using a generating AI, and provides the commentary to the user. For example, the real-time automatic comment generation system for sports viewing collects data such as the match score, player movements, and the progress of the match. This data is collected by a collection unit. Next, based on the collected match data, the generating AI generates commentary. For example, if the match score changes, it generates a commentary such as "Player A has scored a goal!" based on the score. It can also refer to the player's past performance and information, and include background information and trivia. For example, it can generate a comment such as "Player A has scored 4 goals in the last 5 matches." Furthermore, it automatically detects highlights and notable moments of the match. For example, it detects the moment a player scores a goal or the moment an important play occurs. Based on this detection result, the generating AI emphasizes information about that moment and includes it in the commentary. For example, it generates a comment such as "A magnificent goal by Player B!" The generated commentary is provided to the user by the service provider. For example, it can be automatically posted to social media platforms. This allows users to keep track of the match's progress in real time. The generating AI can also generate comments by comparing a player's current performance with their past performance. For example, it can generate comments such as, "Player C is showing their best performance of the season." Furthermore, it can generate commentary in different tones depending on the progress of the match. For example, if the match is tense, it can generate comments such as, "The tension is rising!" Thus, the present invention is a system that automatically generates real-time comments for sports viewing. Based on the progress of the match and the points scored, the generating AI generates commentary, provides background information and trivia by referring to players' past performance and information, and can automatically detect and highlight highlights and noteworthy moments of the match in the comments.This allows the real-time automatic comment generation system for sports viewing to grasp the progress of the game in real time and provide it to users.

[0065] The real-time automatic comment generation system for sports viewing according to this embodiment comprises a collection unit, a generation unit, and a provision unit. The collection unit collects data on the ongoing match. For example, the collection unit collects data such as the match score, player movements, and the progress of the match. The collection unit can acquire the match score in real time and store it in a database. The collection unit can also track player movements and collect location data. The collection unit can also monitor the progress of the match and detect important events. The generation unit generates commentary based on the match data collected by the collection unit. For example, if the match score changes, the generation unit generates a commentary such as "Player A has scored!" based on the score. The generation unit can also refer to the player's past performance and information and include background information and trivia. For example, the generation unit generates a comment such as "Player A has scored 4 goals in the last 5 matches." The generation unit can also automatically detect highlights and notable moments of the match and include information about those moments in the commentary. The generation unit generates comments such as, for example, "A magnificent goal by player B!". Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary comments using, for example, a text generation AI (e.g., LLM). The generation AI takes match data as input and outputs commentary comments. The generation AI can also generate commentary comments in different tones depending on the progress of the match. For example, if the match is tense, the generation AI will generate comments such as "The tension is rising!". The provision unit provides the commentary comments generated by the generation unit to the user. The provision unit can, for example, automatically post to a social media platform. The provision unit can also notify the user of the commentary comments in real time. The provision unit can also select the optimal display method depending on the user's device. For example, the provision unit adjusts the display method of the commentary comments depending on the device, such as a smartphone, tablet, or PC. As a result, the real-time automatic comment generation system for sports viewing according to the embodiment can grasp the progress of the match in real time and provide it to the user.

[0066] The data collection unit collects data from ongoing matches. For example, it collects data such as match scores, player movements, and match progress. Specifically, match scores are acquired in real time and stored in a database. This allows for immediate understanding of score changes as the match progresses. Regarding player movements, location data is collected using a tracking system. For example, player location information is acquired with high accuracy using GPS and RFID tags, and player movement patterns and play details are recorded. Regarding match progress, the unit monitors important match events, automatically detecting events such as goals, fouls, and substitutions. This data is collected from various devices such as sensors, cameras, and microphones and integrated into a central database. Furthermore, the data collection unit processes this data in real time and can collaborate with other systems and departments as needed. For example, collected data is stored on a cloud server, making it accessible to the generation and provision units. Additionally, by adjusting the frequency and accuracy of data collection, flexible responses to specific situations and conditions are possible. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0067] The generation unit generates commentary based on match data collected by the collection unit. For example, if the score of the match changes, the generation unit generates commentary based on the score, such as "Player A has scored!" The generation unit can also refer to the player's past performance and information, and include background information and trivia. For example, it can generate a comment such as "Player A has scored 4 goals in the last 5 matches." The generation unit can also automatically detect highlights and notable moments of the match and include information about those moments in the commentary. For example, it can generate a comment such as "A magnificent goal by Player B!" Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). The generation AI takes match data as input and outputs commentary. The generation AI can also generate commentary in different tones depending on the progress of the match. For example, if the match is tense, it can generate a comment such as "The tension is rising!" The generation AI utilizes natural language processing technology to select appropriate expressions based on context, generating comments that are easy for users to understand and find interesting. Furthermore, the generation AI can learn from past match data and player statistics to generate even more accurate comments. As a result, the generation unit can generate and provide users with appropriate commentary in real time, according to the progress of the match.

[0068] The service provider delivers live commentary generated by the generation unit to the user. The service provider can, for example, automatically post to social media platforms. The service provider can also notify the user of the live commentary in real time. The service provider can also select the optimal display method depending on the user's device. For example, the service provider adjusts the display method of live commentary depending on the device, such as a smartphone, tablet, or PC. On smartphones, information can be delivered to the user instantly using push notifications or in-app notifications. On tablets and PCs, the display format of the comments can be adjusted according to the screen size to improve visibility. Furthermore, the service provider can provide notifications customized according to the user's preferences. For example, it is possible to set notifications to prioritize information about specific players or teams. The service provider can collect user feedback and continuously improve the accuracy and effectiveness of the information it provides. For example, it analyzes comments and reactions that users showed interest in and reflects them in the content of the next notification. In addition, the service provider can reliably transmit information using multiple communication methods. For example, it can reliably deliver important information by using not only smartphone notifications but also voice calls, SMS, email, etc. This allows the service provider to deliver live commentary to users quickly and reliably, enhancing the enjoyment of watching sports.

[0069] The acquisition unit acquires player data, which is data on players currently participating in a match. The acquisition unit acquires data such as the player's name, position, and statistical information. The acquisition unit can also acquire past performance data and information on players from a database. The acquisition unit can also collect real-time performance data of players. The acquisition unit can also track players' movements and collect location data. By acquiring player data, information about players can be included in the commentary. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input player movement data into a generating AI and have the generating AI process player performance data.

[0070] The detection unit detects important moments during a match. For example, it can detect important moments such as scoring plays, fouls, and turning points in the game. The detection unit can monitor the progress of the match in real time and detect important events. The detection unit can also track players' movements and detect important plays. The detection unit can also analyze the match score and player performance data to detect important moments. This allows for the detection of highlights and notable moments, enabling the inclusion of important scenes in commentary. Some or all of the above processing in the detection unit may be performed using AI or not. For example, the detection unit can input match progress data into a generating AI and have the generating AI perform the detection of important moments.

[0071] The generation unit generates commentary using a generation AI. For example, if the score of the match changes, the generation unit generates commentary based on the score, such as "Player A has scored!" The generation unit can also refer to the player's past performance and information, and include background information and trivia. For example, the generation unit generates commentary such as "Player A has scored 4 goals in the last 5 matches." The generation unit can also automatically detect highlights and notable moments of the match and include information about those moments in the commentary. For example, the generation unit generates commentary such as "A magnificent goal by Player B!" The generation unit can also generate commentary in different tones depending on the progress of the match. For example, if the match is tense, the generation unit generates commentary such as "The tension is rising!" Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). The generation AI takes match data as input and outputs commentary. The generating AI can also generate commentary in different tones depending on the progress of the match. For example, if the match is tense, the generating AI will generate a comment like, "The tension is rising!" This improves the accuracy of commentary generation when using the generating AI.

[0072] The service provider automatically posts the live commentary generated by the generation unit to social media. The service provider can, for example, automatically post to social media platforms. The service provider can also notify users of the live commentary in real time. The service provider can also select the optimal display method depending on the user's device. For example, the service provider adjusts the display method of the live commentary depending on the device, such as a smartphone, tablet, or PC. This allows users to share the progress of the match in real time by automatically posting the live commentary to social media platforms. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the generated live commentary into a generation AI and have the generation AI execute the posting to social media.

[0073] The generation unit generates comments by comparing a player's current performance with their past performance. For example, the generation unit compares a player's current performance with their past performance and generates a comment such as, "Player C is showing their best performance of the season." The generation unit can retrieve a player's past performance and information from a database and compare it with their current performance. The generation unit can also collect real-time performance data of players and compare it with their past performance. The generation unit can also track a player's movements and evaluate their current performance. This allows for the generation of more detailed commentary by comparing a player's current performance with their past performance. Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). The generation AI takes match data as input and outputs commentary. To compare a player's current performance with their past performance, the generation AI takes past performance data and real-time performance data as input and outputs the comparison results. This allows for the generation of detailed commentary by using a generation AI that compares a player's current performance with their past performance.

[0074] The generation unit generates commentary in different tones depending on the progress of the match. For example, if the match is tense, the generation unit will generate a comment such as "The tension is rising!" The generation unit can monitor the progress of the match in real time and generate commentary in the appropriate tone. The generation unit can also analyze the match score and player performance data and generate comments in a tone appropriate to the match situation. The generation unit can use excited tones, calm tones, explanatory tones, etc., depending on the progress of the match. By changing the tone according to the progress of the match, it is possible to provide more immersive commentary. Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). The generation AI takes match data as input and outputs commentary in a tone appropriate to the progress of the match. The generation AI can analyze the progress of the match in real time and generate comments in the appropriate tone. As a result, by using the generation AI, it is possible to generate immersive commentary in a tone appropriate to the progress of the match.

[0075] The generation unit provides different types of trivia information depending on the stage of the match. For example, the generation unit can provide different trivia information depending on the early, middle, and late stages of the match. The generation unit can monitor the progress of the match in real time and provide appropriate trivia information. The generation unit can also refer to players' past performance and information and provide trivia information appropriate to the stage of the match. For example, the generation unit can provide trivia information such as, "Player A has scored 4 goals in the last 5 matches." Depending on the stage of the match, the generation unit can provide trivia information including players' background information, past performance, and the history of the match. This allows for the generation of more interesting commentary by providing trivia information according to the stage of the match. Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates trivia information using, for example, a text generation AI (e.g., LLM). The generation AI takes match data as input and outputs trivia information appropriate to the stage of the match. The generation AI can analyze the progress of the match in real time and generate appropriate trivia information. This allows us to use a generation AI to create interesting commentary that includes trivia relevant to the stage of the match.

[0076] The generation unit generates commentary that includes comments generated by estimating the psychological state of players at important moments. For example, the generation unit estimates the psychological state of a player at the moment they score a goal or when an important play is made, and generates comments based on that psychological state. The generation unit can estimate a player's psychological state by analyzing their facial expressions, actions, and past statements. For example, the generation unit generates a comment such as, "Player B seems very pleased with this goal." The generation unit can estimate the psychological state of players in real time and generate commentary based on the results. This allows for the generation of more emotionally expressive commentary by estimating the psychological state of players. Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). To estimate a player's psychological state, the generation AI takes data on the player's facial expressions, actions, and past statements as input and outputs the psychological state. Based on the estimated psychological state, the generation AI can generate emotionally expressive commentary. This allows for the generation of emotionally rich commentary that estimates the psychological state of the players, using a generation AI.

[0077] The data collection unit estimates the user's emotions and adjusts the timing of match data collection based on the estimated emotions. For example, if the user is excited, the data collection unit can collect important moments of the match in real time. If the user is relaxed, the data collection unit can collect data periodically in accordance with the progress of the match. If the user is nervous, the data collection unit can also prioritize collecting data from tense moments of the match. The data collection unit can estimate the user's emotions in real time and adjust the timing of match data collection based on the results. This allows for more appropriate data collection by adjusting the timing of match data collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the data collection unit may be performed using AI or not using AI. For example, the data collection unit can input user facial expression data and voice data into a generative AI and have the generative AI perform emotion estimation. This allows the data collection unit to adjust the timing of match data collection based on the user's emotions.

[0078] The data collection unit collects data focusing on specific players or plays during match data collection. For example, the data collection unit prioritizes collecting data on the movements of players who are attracting attention during the match. The data collection unit can collect data focusing on specific plays (e.g., goals, home runs). The data collection unit can also collect data focusing on important moments in the match (e.g., penalty kicks, free throws). The data collection unit can monitor the progress of the match in real time and collect data focusing on specific players or plays. This allows for the collection of more detailed data by focusing on specific players or plays. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input match progress data into a generating AI and have the generating AI perform data collection focusing on specific players or plays.

[0079] The data collection unit dynamically changes the type of data it collects according to the progress of the match. For example, the data collection unit collects data on players' movements in the early stages of the match and data on the score in the later stages. The data collection unit can also collect data on spectator reactions as the match progresses. The data collection unit can also collect data on players' physical condition and performance as the match progresses. The data collection unit can monitor the progress of the match in real time and dynamically change the type of data it collects. This allows for more appropriate data collection by changing the type of data according to the progress of the match. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input data on the progress of the match into a generating AI and have the generating AI execute a process to dynamically change the type of data to collect.

[0080] The data collection unit estimates the user's emotions and determines the priority of the match data to collect based on the estimated emotions. For example, if the user is excited, the data collection unit may prioritize collecting highlight scenes from the match. If the user is relaxed, the data collection unit may prioritize collecting the overall flow of the match. If the user is nervous, the data collection unit may also prioritize collecting tense moments from the match. The data collection unit can estimate the user's emotions in real time and determine the priority of the match data to collect based on the results. This allows for the priority collection of more important data by prioritizing data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the data collection unit may be performed using AI or not using AI. For example, the data collection unit can input user facial expression data or voice data into a generative AI and have the generative AI perform emotion estimation. This allows the data collection unit to prioritize the match data to be collected based on the user's emotions.

[0081] The data collection unit collects audience reaction information when collecting match data and incorporates it into the commentary. For example, the data collection unit can collect cheers and boos from the audience and incorporate them into the commentary. The data collection unit can also collect data on applause and cheers from the audience and incorporate it into the commentary. The data collection unit can also collect audience reactions and incorporate them into the commentary. The data collection unit can monitor the progress of the match in real time and collect audience reaction data. By collecting audience reaction data, it is possible to generate more realistic commentary. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input audience audio and video data into a generating AI and have the generating AI collect audience reaction data.

[0082] The data collection unit collects weather and venue environmental data when collecting match data and incorporates it into the commentary. For example, the data collection unit can collect weather data during the match and incorporate it into the commentary. The data collection unit can also collect venue temperature and humidity data and incorporate it into the commentary. The data collection unit can also collect wind speed and wind direction data during the match and incorporate it into the commentary. The data collection unit can monitor the progress of the match in real time and collect weather and venue environmental data. By collecting weather and venue environmental data, it is possible to generate more detailed commentary. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input weather data and environmental data into a generating AI and have the generating AI perform the processing of incorporating it into the commentary.

[0083] The generation unit estimates the user's emotions and adjusts the tone of the commentary based on the estimated emotions. For example, if the user is excited, the generation unit can raise the tone of the commentary. If the user is relaxed, the generation unit can lower the tone of the commentary. If the user is tense, the generation unit can make the tone of the commentary more intense. The generation unit can estimate the user's emotions in real time and adjust the tone of the commentary based on the result. This allows for the provision of more appropriate commentary by adjusting the tone of the commentary according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the generation unit is performed using the generation AI. The generation AI takes user facial expression data and voice data as input and outputs the emotion estimation result. The generation AI can adjust the tone of the commentary based on the estimated emotions. This allows the generation unit to adjust the tone of the commentary based on the user's emotions.

[0084] The generation unit includes quotes and statements from past interviews and statements of players in the commentary it generates. For example, the generation unit can quote from past interviews of players and include them in the commentary. The generation unit can quote past statements of players and include them in the commentary. The generation unit can also quote past comments of players and include them in the commentary. The generation unit can retrieve past interviews and statements of players from a database and include them as quotes in the commentary. This makes it possible to generate more detailed commentary by quoting past interviews and statements of players. Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). The generation AI takes past interview data and statement data of players as input and outputs commentary that includes quotes. The generation AI can analyze past interviews and statements and generate commentary that includes appropriate quotes. This makes it possible to generate detailed commentary that quotes past interviews and statements of players by using a generation AI.

[0085] The generation unit includes the historical background and past memorable moments of the match in the commentary it generates. For example, the generation unit can generate commentary that includes the historical background of the match. The generation unit can generate commentary that includes past memorable moments. The generation unit can also generate commentary that includes historical events of the match. The generation unit can retrieve the historical background and past memorable moments of the match from a database and include them in the commentary. This makes it possible to generate more interesting commentary by including the historical background and past memorable moments of the match. Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). The generation AI takes historical background data and past memorable moments of the match as input and outputs commentary that includes them. The generation AI can analyze the historical background and past memorable moments and generate commentary that includes appropriate information. This makes it possible to generate interesting commentary that includes the historical background and past memorable moments of the match by using a generation AI.

[0086] The generation unit estimates the user's emotions and adjusts the length of the commentary based on the estimated emotions. For example, if the user is excited, the generation unit generates a short, concise commentary. If the user is relaxed, the generation unit can generate a longer commentary with more detailed explanations. If the user is nervous, the generation unit can also generate a concise, to-the-point commentary. The generation unit can estimate the user's emotions in real time and adjust the length of the commentary based on the result. This allows for the provision of more appropriate commentary by adjusting the length of the commentary according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the generation unit is performed using the generation AI. The generation AI takes user facial expression data and voice data as input and outputs the emotion estimation result. The generation AI can adjust the length of the commentary based on the estimated emotion. This allows the generation unit to adjust the length of the commentary based on the user's emotions.

[0087] The generation unit includes tactical commentary in the generated commentary, tailored to the progress of the match. For example, the generation unit generates commentary that includes tactical commentary according to the progress of the match. The generation unit can generate commentary that explains the tactical points of the match. The generation unit can also generate commentary that explains the tactical movements of the match. The generation unit can monitor the progress of the match in real time and generate commentary that includes tactical commentary. This allows for more detailed commentary by including tactical commentary tailored to the progress of the match. Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). The generation AI takes match data as input and outputs commentary that includes tactical commentary. The generation AI can analyze the progress of the match in real time and generate commentary that includes appropriate tactical commentary. This allows for the generation of detailed commentary that includes tactical commentary tailored to the progress of the match by using a generation AI.

[0088] The generation unit includes information about the rules and regulations of the match in the commentary it generates. For example, the generation unit generates commentary that includes information about the rules of the match. The generation unit can generate commentary that includes information about the rules of the match. The generation unit can also generate commentary that includes details about the rules and regulations of the match. The generation unit can retrieve information about the rules and regulations of the match from a database and include it in the commentary. This allows for the provision of commentary that is easier for viewers to understand by including information about the rules and regulations of the match. Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). The generation AI takes data about the rules and regulations of the match as input and outputs commentary that includes them. The generation AI can analyze the rules and regulations and generate commentary that includes appropriate information. This allows for the generation of easy-to-understand commentary that includes information about the rules and regulations of the match by using a generation AI.

[0089] The service provider estimates the user's emotions and adjusts the display method of the commentary based on the estimated emotions. For example, if the user is excited, the service provider can provide a visually emphasized display method. If the user is relaxed, the service provider can provide a calm display method. If the user is tense, the service provider can also provide a simple and easy-to-read display method. The service provider can estimate the user's emotions in real time and adjust the display method of the commentary based on the result. This allows for more easily readable commentary by adjusting the display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the service provider may be performed using AI or not using AI. For example, the service provider can input user facial expression data and voice data into a generative AI and have the generative AI perform emotion estimation. This allows the service provider to adjust the display method of the commentary based on the user's emotions.

[0090] The service provider adds relevant information to the commentary provided by the user by referring to the user's past viewing history. For example, the service provider can refer to the user's past viewing history and add relevant match information. The service provider can add relevant player information based on the user's past viewing history. The service provider can also add relevant trivia information based on the user's past viewing history. The service provider can retrieve the user's past viewing history from a database and add information related to the commentary. This allows the service provider to provide more relevant information by referring to the user's past viewing history. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the user's viewing history data into a generating AI and have the generating AI perform the addition of relevant information.

[0091] The service provider offers customization options for the commentary provided, tailored to the user's preferences. For example, the service provider can customize the tone of the commentary according to the user's preferences. The service provider can customize the length of the commentary according to the user's preferences. The service provider can also customize the content of the commentary according to the user's preferences. The service provider can provide customization options for the commentary based on the user's preferences. This allows for a more personalized experience by customizing the commentary according to the user's preferences. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input user preference data into a generating AI and have the generating AI perform the provision of customization options.

[0092] The service provider estimates the user's emotions and adjusts the frequency of live commentary notifications based on the estimated emotions. For example, if the user is excited, the service provider will notify the user of live commentary frequently. If the user is relaxed, the service provider can notify the user of live commentary at a moderate frequency. If the user is nervous, the service provider can notify the user of live commentary only at important moments. The service provider can estimate the user's emotions in real time and adjust the frequency of live commentary notifications based on the results. This allows for the provision of live commentary at a more appropriate time by adjusting the notification frequency according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the service provider may be performed using AI or not using AI. For example, the service provider can input user facial expression data and voice data into a generative AI and have the generative AI perform emotion estimation. This allows the service provider to adjust the frequency of live commentary notifications based on the user's emotions.

[0093] The service provider selects the optimal display method for the live commentary based on the user's device information. For example, if the user is using a smartphone, the service provider provides a display method that matches the screen size. If the user is using a tablet, the service provider can provide a display method optimized for a larger screen. If the user is using a smartwatch, the service provider can also provide a concise and highly visible display method. The service provider can acquire the user's device information in real time and select the optimal display method. This allows for the provision of more visually appealing live commentary by selecting the optimal display method based on the user's device information. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the user's device information into a generating AI and have the generating AI select the optimal display method.

[0094] The service provider adds relevant information to the live commentary by analyzing the user's social media activity. For example, the service provider can analyze the user's social media activity and add relevant match information. Based on the user's social media activity, the service provider can add relevant player information. Based on the user's social media activity, the service provider can also add relevant trivia information. The service provider can retrieve the user's social media activity from a database and add information related to the live commentary. This allows the service provider to provide more relevant information by analyzing the user's social media activity. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the user's social media activity data into a generating AI and have the generating AI add relevant information.

[0095] The acquisition unit estimates the user's emotions and adjusts the timing of player data acquisition based on the estimated user emotions. For example, if the user is excited, the acquisition unit can acquire player data in real time. If the user is relaxed, the acquisition unit can acquire player data periodically. If the user is tense, the acquisition unit can also acquire player data at important moments. The acquisition unit can estimate the user's emotions in real time and adjust the timing of player data acquisition based on the result. This allows for more appropriate data acquisition by adjusting the timing of player data acquisition according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the acquisition unit may be performed using AI or not using AI. For example, the acquisition unit can input the user's facial expression data or voice data into the generative AI and have the generative AI perform emotion estimation. This allows the acquisition unit to adjust the timing of player data acquisition based on the user's emotions.

[0096] The acquisition unit acquires player data while considering the player's current condition and health status. For example, the acquisition unit can acquire data while considering the player's current condition. The acquisition unit can acquire data while considering the player's health status. The acquisition unit can also acquire data while considering the player's performance data. The acquisition unit can monitor the player's real-time condition and health status and acquire data based on that. This makes it possible to acquire more detailed data by considering the player's current condition and health status. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input player health data and performance data into a generating AI and have the generating AI perform the data acquisition.

[0097] The acquisition unit estimates the user's emotions and determines the priority of player data to acquire based on the estimated user emotions. For example, if the user is excited, the acquisition unit will prioritize acquiring data on players of interest. If the user is relaxed, the acquisition unit can acquire data on all players equally. If the user is nervous, the acquisition unit can also prioritize acquiring data on important players in the match. The acquisition unit can estimate the user's emotions in real time and determine the priority of player data to acquire based on the result. This allows for the acquisition of more important data by prioritizing player data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the acquisition unit may be performed using AI or not using AI. For example, the acquisition unit can input the user's facial expression data or voice data into a generative AI and have the generative AI perform emotion estimation. This allows the data acquisition unit to determine the priority of player data to acquire based on the user's emotions.

[0098] The acquisition unit analyzes the player's social media activity and obtains relevant data when acquiring player data. For example, the acquisition unit can analyze the player's latest social media posts and obtain relevant data. The acquisition unit can also analyze the player's past social media activity and obtain relevant data. The acquisition unit can also analyze fan reactions to the player's social media and obtain relevant data. The acquisition unit can monitor the player's social media activity in real time and acquire data based on that. This makes it possible to acquire more detailed data by analyzing the player's social media activity. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input the player's social media data into a generating AI and have the generating AI perform the acquisition of relevant data.

[0099] The detection unit estimates the user's emotions and adjusts the detection criteria for highlights and notable moments based on the estimated emotions. For example, if the user is excited, the detection unit may prioritize detecting dramatic moments in the game. If the user is relaxed, the detection unit may prioritize detecting the overall flow of the game. If the user is tense, the detection unit may also prioritize detecting tense moments in the game. The detection unit can estimate the user's emotions in real time and adjust the detection criteria for highlights and notable moments based on the results. This allows for the detection of more appropriate highlights and notable moments by adjusting the detection criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the detection unit may be performed using AI or not using AI. For example, the detection unit may input user facial expression data or voice data into a generative AI and have the generative AI perform emotion estimation. This allows the detection unit to adjust the detection criteria for highlights and noteworthy moments based on the user's emotions.

[0100] The detection unit improves detection accuracy by analyzing the progress of the match and the movements of players in real time when detecting highlights and notable moments. For example, the detection unit can analyze the progress of the match in real time and detect highlights. The detection unit can analyze the movements of players in real time and detect notable moments. The detection unit can also improve detection accuracy by combining the progress of the match and the movements of players. The detection unit can monitor the progress of the match and the movements of players in real time and detect highlights and notable moments based on this. This enables more accurate detection by analyzing the progress of the match and the movements of players in real time. Some or all of the above processing in the detection unit may be performed using AI or not using AI. For example, the detection unit can input match progress data and player movement data into a generating AI and have the generating AI perform the detection of highlights and notable moments.

[0101] The detection unit estimates the user's emotions and adjusts the display method of the detection results based on the estimated user emotions. For example, if the user is excited, the detection unit can provide a visually emphasized display method. If the user is relaxed, the detection unit can provide a calm display method. If the user is tense, the detection unit can also provide a simple and highly visible display method. The detection unit can estimate the user's emotions in real time and adjust the display method of the detection results based on the estimate. This allows for more visually appealing detection results by adjusting the display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the detection unit may be performed using AI or not using AI. For example, the detection unit can input user facial expression data or voice data into a generative AI and have the generative AI perform emotion estimation. This allows the detection unit to adjust the display method of the detection results based on the user's emotions.

[0102] The detection unit improves detection accuracy by considering audience reaction data when detecting highlights and notable moments. For example, the detection unit can analyze audience cheers and boos to detect highlights. The detection unit can analyze audience applause and cheering data to detect notable moments. The detection unit can also analyze audience reactions to improve detection accuracy. The detection unit can monitor audience reaction data in real time and detect highlights and notable moments based on it. This allows for more accurate detection by considering audience reaction data. Some or all of the above processing in the detection unit may be performed using AI or not. For example, the detection unit can input audience audio and video data into a generating AI and have the generating AI perform the detection of highlights and notable moments.

[0103] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0104] A real-time automatic commentary generation system for sports viewing can estimate the user's emotions and adjust the content of the commentary based on those emotions. For example, if the user is excited, the commentary can include more energetic and emotional expressions. If the user is relaxed, the commentary can include calm and detailed explanations. If the user is nervous, the commentary can be concise and to the point. This allows for the provision of appropriate commentary tailored to the user's emotions. Emotion estimation is performed, for example, by analyzing the user's facial expression data and voice data. The generating AI can receive this data as input, estimate the user's emotions, and generate commentary based on the results.

[0105] A real-time automatic comment generation system for sports viewing can provide different visual effects depending on the progress of the match. For example, when the match is tense, an emphasized effect can be displayed on the screen. When the match is progressing smoothly, a gentle effect can be displayed on the screen. During highlight scenes of the match, special effects can be added to visually emphasize them. This allows the system to provide users with a sense of realism through visual effects. Visual effects are generated by combining match data and user emotion data. The generating AI can receive this data as input and generate appropriate visual effects.

[0106] A real-time automated comment generation system for sports viewing can analyze a user's past viewing history and provide relevant information. For example, it can refer to data from matches the user has watched in the past and provide information about relevant players and teams. If a user frequently watches a particular player, it can provide detailed information about that player. If a user supports a particular team, it can provide the latest information and trivia about that team. This allows for the provision of personalized information based on the user's viewing history. The analysis of viewing history is performed using past viewing data obtained from a database. The generating AI can receive this data as input and generate relevant information.

[0107] A real-time automated commentary generation system for sports viewing can provide different audio effects depending on the progress of the match. For example, when the match is tense, the audio effects can be emphasized to enhance the sense of realism. When the match is progressing smoothly, the audio effects can be kept subtle to provide a relaxed atmosphere. During highlight scenes of the match, special audio effects can be added to visually emphasize them. This allows the system to provide users with a sense of realism through audio effects. Audio effects are generated by combining match data and user emotion data. The generating AI can receive this data as input and generate appropriate audio effects.

[0108] A real-time automatic comment generation system for sports viewing can estimate the user's emotions and adjust the display method of the commentary based on those emotions. For example, if the user is excited, the commentary can be displayed in a large font for visual emphasis. If the user is relaxed, the commentary can be displayed in a calm font to provide a visually soothing atmosphere. If the user is tense, the commentary can be displayed in a simple, highly legible font. This allows the system to provide an appropriate display method according to the user's emotions. Emotion estimation is performed, for example, by analyzing the user's facial expression data and voice data. The generating AI can receive this data as input, estimate the user's emotions, and adjust the display method of the commentary based on the result.

[0109] A real-time automatic comment generation system for sports viewing can provide different camera angles depending on the progress of the match. For example, when the match is tense, it can provide camera angles that zoom in on the players' expressions and movements. When the match is progressing smoothly, it can provide wide-angle camera angles that allow users to grasp the overall flow. During highlight scenes of the match, special camera angles can be added to visually emphasize them. This allows the system to provide users with a sense of realism through camera angles. The selection of camera angles is done by combining match data and user emotion data. The generating AI can receive this data as input and select the appropriate camera angle.

[0110] A real-time automatic commentary generation system for sports viewing can estimate the user's emotions and adjust the frequency of commentary notifications based on those emotions. For example, if the user is excited, commentary can be notified frequently. If the user is relaxed, commentary can be notified at a moderate frequency. If the user is nervous, commentary can be notified only at important moments. This allows for providing an appropriate notification frequency according to the user's emotions. Emotion estimation is performed, for example, by analyzing the user's facial expression data and voice data. The generating AI can receive this data as input, estimate the user's emotions, and adjust the frequency of commentary notifications based on the result.

[0111] A real-time automated commentary generation system for sports viewing can provide different data visualizations depending on the progress of the match. For example, when the match is tense, it can visualize the players' movements and performance in real time. When the match is progressing smoothly, it can visualize match statistics and player performance. During match highlights, special visualizations can be added to visually emphasize them. This allows the system to provide users with a sense of realism through data visualizations. Data visualizations are generated by combining match data and user sentiment data. The generating AI can receive this data as input and generate appropriate data visualizations.

[0112] A real-time automatic commentary generation system for sports viewing can estimate the user's emotions and adjust the tone of the commentary based on those emotions. For example, if the user is excited, the tone of the commentary can be heightened. If the user is relaxed, the tone of the commentary can be made calmer. If the user is nervous, the tone of the commentary can be made more intense. This allows the system to provide commentary with an appropriate tone that matches the user's emotions. Emotion estimation is performed, for example, by analyzing the user's facial expression data and voice data. The generating AI can receive this data as input, estimate the user's emotions, and adjust the tone of the commentary based on the result.

[0113] A real-time automatic comment generation system for sports viewing can provide different interactive features depending on the progress of the match. For example, when the match is tense, it can provide a feature that allows users to post comments in real time. When the match is progressing smoothly, it can provide a feature that allows users to check match statistics and player performance. During match highlights, it can provide a feature that allows users to replay specific moments. This allows the system to provide users with a sense of realism through interactive features. The provision of interactive features is done by combining match data and user sentiment data. The generating AI can receive this data as input and provide appropriate interactive features.

[0114] The following briefly describes the processing flow for example form 2.

[0115] Step 1: The data collection unit collects data from the ongoing match. The data collection unit collects data such as the match score, player movements, and the progress of the match. The data collection unit can acquire the match score in real time and store it in a database. The data collection unit can also track player movements and collect location data. The data collection unit can also monitor the progress of the match and detect important events. Step 2: The generation unit generates commentary based on the match data collected by the collection unit. For example, if the score of the match changes, the generation unit generates commentary based on the score, such as "Player A has scored!" The generation unit can also refer to the player's past performance and information, and include background information and trivia. For example, the generation unit generates commentary such as "Player A has scored 4 goals in the last 5 matches." The generation unit can also automatically detect highlights and notable moments of the match and include information about those moments in the commentary. For example, the generation unit generates commentary such as "A magnificent goal by Player B!" Some or all of the above processing in the generation unit is performed using a generation AI. The generation AI generates commentary using, for example, a text generation AI (e.g., LLM). The generation AI takes match data as input and outputs commentary. The generation AI can also generate commentary in different tones depending on the progress of the match. For example, if the match is tense, the generation AI generates commentary such as "The tension is rising!" Step 3: The provider unit provides the live commentary generated by the generator unit to the user. The provider unit can, for example, automatically post to social media platforms. The provider unit can also notify the user of the live commentary in real time. The provider unit can also select the optimal display method according to the user's device. For example, the provider unit adjusts the display method of the live commentary depending on the device, such as a smartphone, tablet, or PC.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] For example, the collection unit can collect match scores and player movements using the camera 42 and microphone 38B of the smart device 14. The collection unit can also be implemented by the specific processing unit 290 of the data processing device 12, which can monitor the progress of the match in real time and detect important events. The generation unit can generate commentary using, for example, the control unit 46A of the smart device 14. The generation unit can also be implemented by the specific processing unit 290 of the data processing device 12, which generates commentary based on the collected match data. The provision unit can provide commentary to the user using the output device 40 of the smart device 14. The provision unit can also be implemented by the specific processing unit 290 of the data processing device 12, which can automatically post the generated commentary to a social media platform. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various modifications are possible.

[0120] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] For example, the collection unit can collect match scores and player movements using the camera 42 and microphone 238 of the smart glasses 214. The collection unit can also be implemented by the specific processing unit 290 of the data processing device 12, which can monitor the progress of the match in real time and detect important events. The generation unit can generate commentary using, for example, the control unit 46A of the smart glasses 214. The generation unit can also be implemented by the specific processing unit 290 of the data processing device 12, which generates commentary based on the collected match data. The provision unit can provide commentary to the user using the speaker 240 of the smart glasses 214. The provision unit can also be implemented by the specific processing unit 290 of the data processing device 12, which can automatically post the generated commentary to a social media platform. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0136] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.).

[0148] 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.

[0149] 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.

[0150] 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.

[0151] For example, the collection unit can collect match scores and player movements using the camera 42 and microphone 238 of the headset terminal 314. The collection unit can also be implemented by the specific processing unit 290 of the data processing device 12, which can monitor the progress of the match in real time and detect important events. The generation unit can generate commentary using, for example, the control unit 46A of the headset terminal 314. The generation unit can also be implemented by the specific processing unit 290 of the data processing device 12, which generates commentary based on the collected match data. The provision unit can provide commentary to the user using the display 343 of the headset terminal 314. The provision unit can also be implemented by the specific processing unit 290 of the data processing device 12, which can automatically post the generated commentary to a social media platform. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0152] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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).

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] For example, the collection unit can collect match scores and player movements using the camera 42 and microphone 238 of the robot 414. The collection unit can also be implemented by the specific processing unit 290 of the data processing device 12, which can monitor the progress of the match in real time and detect important events. The generation unit can generate commentary using, for example, the control unit 46A of the robot 414. The generation unit can also be implemented by the specific processing unit 290 of the data processing device 12, which generates commentary based on the collected match data. The provision unit can provide commentary to the user using the speaker 240 of the robot 414. The provision unit can also be implemented by the specific processing unit 290 of the data processing device 12, which can automatically post the generated commentary to a social media platform. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various modifications are possible.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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."

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] (Note 1) The data collection unit collects match data, which is data from ongoing matches. Based on the match data collected by the aforementioned collection unit, a generation unit generates commentary comments, The system includes a providing unit that provides the commentary generated by the generation unit. A system characterized by the following features. (Note 2) The system includes an acquisition unit that acquires player data, which is data on players participating in the aforementioned match. The system described in Appendix 1, characterized by the features described herein. (Note 3) The system includes a detection unit that detects important moments during the aforementioned match. The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is Generate commentary using a generation AI. The system described in Appendix 1, characterized by the features described herein. (Note 5) The live commentary generated by the aforementioned generation unit is automatically posted to social media. The system described in Appendix 1, characterized by the features described herein. (Note 6) The generating unit is Compare a player's current performance with their past results to generate comments. The system described in Appendix 1, characterized by the features described herein. (Note 7) The generating unit is The commentary is generated in a different tone depending on the progress of the match. The system described in Appendix 1, characterized by the features described herein. (Note 8) The generating unit is The aforementioned match will provide different types of trivia information depending on the stage of the game. The system described in Appendix 1, characterized by the features described herein. (Note 9) The commentary is generated, including comments that are generated by estimating the psychological state of the players at the aforementioned important moments. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is The system estimates the user's emotions and adjusts the timing of match data collection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) When collecting match data, focus on specific players or plays to gather data. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When collecting match data, the type of data collected is dynamically changed according to the progress of the match. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned collection unit is It estimates the user's emotions and determines the priority of the match data to collect based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) When collecting match data, gather information on audience reactions and incorporate it into the commentary. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned collection unit is When collecting match data, weather and venue environmental data will be collected and incorporated into the commentary. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is It estimates the user's emotions and adjusts the tone of the live commentary based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is The generated commentary will include quotes from past interviews and statements of the players. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is The generated commentary will include the historical background of the match and memorable moments from the past. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is It estimates the user's emotions and adjusts the length of the commentary based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is The generated commentary will include tactical explanations that reflect the progress of the match. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is The generated commentary will include information about the rules and regulations of the match. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, The system estimates the user's emotions and adjusts how live commentary is displayed based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, The live commentary will include relevant information based on the user's past viewing history. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, We offer customization options for the live commentary to suit the user's preferences. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, The system estimates the user's emotions and adjusts the frequency of live commentary notifications based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, The system selects the optimal display method for the live commentary based on the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, We will add relevant information to the live commentary we provide by analyzing users' social media activity. The system described in Appendix 1, characterized by the features described herein. (Note 28) The acquisition unit is, The system estimates the user's emotions and adjusts the timing of player data acquisition based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 29) The acquisition unit is, When acquiring player data, the data is acquired while taking into account the player's current condition and health status. The system described in Appendix 2, characterized by the features described herein. (Note 30) The acquisition unit is, The system estimates the user's emotions and determines the priority of player data to retrieve based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 31) The acquisition unit is, When acquiring player data, we analyze the players' social media activity to obtain relevant data. The system described in Appendix 2, characterized by the features described herein. (Note 32) The detection unit is It estimates the user's emotions and adjusts the detection criteria for highlights and noteworthy moments based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 33) The detection unit is When detecting highlights and notable moments, the system analyzes the progress of the match and player movements in real time to improve detection accuracy. The system described in Appendix 3, characterized by the features described herein. (Note 34) The detection unit is It estimates the user's emotions and adjusts how the detection results are displayed based on the estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 35) The detection unit is When detecting highlights and notable moments, audience reaction data is taken into consideration to improve detection accuracy. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0188] 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 data collection unit collects match data, which is data from ongoing matches. Based on the match data collected by the aforementioned collection unit, a generation unit generates commentary comments, The system includes a providing unit that provides the commentary generated by the generation unit. A system characterized by the following features.

2. The system includes an acquisition unit that acquires player data, which is data on players participating in the aforementioned match. The system according to feature 1.

3. The system includes a detection unit that detects important moments during the aforementioned match. The system according to feature 1.

4. The generating unit is The AI ​​is used to generate the commentary comments. The system according to feature 1.

5. The live commentary generated by the aforementioned generation unit is automatically posted to social media. The system according to feature 1.

6. The generating unit is Compare a player's current performance with their past results to generate comments. The system according to feature 1.

7. The generating unit is The commentary is generated in a different tone depending on the progress of the match. The system according to feature 1.

8. The generating unit is The aforementioned match will provide different types of trivia information depending on the stage of the game. The system according to feature 1.

9. The commentary is generated, including comments that are generated by estimating the psychological state of the players at the aforementioned important moments. The system according to claim 3.

Images