System

Abstract

An object of a system according to an embodiment is to generate an appropriate live commentary and a fair support comment in real time when a gaming live commentary is performed alone.SOLUTION: A system according to an embodiment includes a generation AI, a voice dialog unit, and a support unit. The generation AI analyzes the progress of the game in real time. The audio interaction unit generates an appropriate live commentary based on the progress status of the game analyzed by the generation AI. The support unit generates a fair support comment based on the progress status of the game analyzed by the generation AI.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, there was a problem in that it was difficult to generate appropriate commentary and fair cheering comments in real time when a single person was commentating on a game.

[0005] The system according to the embodiment aims to generate appropriate commentary comments and fair cheering comments in real time when a single person is commentating on a game. [Means for solving the problem]

[0006] The system according to the embodiment includes a generation AI, a voice dialogue unit, and a cheering unit. The generation AI analyzes the progress of the game in real time. The voice dialogue unit generates appropriate commentary based on the progress of the game analyzed by the generation AI. The cheering unit generates fair cheering comments based on the progress of the game analyzed by the generation AI. [Effects of the Invention]

[0007] The system according to the embodiment can generate appropriate commentary comments and fair cheering comments in real time when a single person is commenting on a game. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

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

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) A commentary system according to an embodiment of the present invention is a system that allows a gamer to provide commentary by voice alone. This system also has a function for cheering on each player in a competitive game from an impartial standpoint. This allows the commentary system to allow a gamer to provide commentary by voice alone, thereby providing impartial cheering in a competitive game.

[0029] A commentary system according to an embodiment includes a generation AI, a voice dialogue unit, and a cheering unit. The generation AI analyzes the progress of a game in real time. For example, the generation AI analyzes the in-game score, player movements, and important events (e.g., goals, kills, item acquisition, etc.). The generation AI also generates appropriate commentary comments based on the progress of the game. The voice dialogue unit generates appropriate commentary comments based on the progress of the game analyzed by the generation AI. For example, the voice dialogue unit generates commentary comments such as, "Player A just made a great play!" or "Player B has a chance to turn the game around!" The voice dialogue unit can also refer to the players' past play data to generate commentary comments based on the characteristics and play styles of each player. The cheering unit generates fair cheering comments based on the progress of the game analyzed by the generation AI. For example, if player A is in the lead, the cheering unit may generate a comment such as, "Player A is leading, but player B is also doing well!" to cheer on player B. Furthermore, when player B makes a comeback, the cheering section generates a comment such as "Player B has made a comeback! Don't give up, player A!" to cheer on player A. As a result, the commentary system according to the embodiment allows a gamer to provide commentary by voice interaction alone, and can provide fair cheering in a competitive game.

[0030] The voice dialogue unit can refer to a player's past play data and generate commentary comments that match the player's characteristics and play style. For example, the voice dialogue unit uses a generation AI to analyze a player's past play data and understand the player's preferred tactics and play style. For example, if player A has an offensive style, the voice dialogue unit can generate a comment such as, "Player A has gone on the attack again!". The voice dialogue unit can also identify a player's characteristics based on the player's past play data and generate commentary comments that match the player's characteristics and play style. This makes it possible to generate commentary comments that match the player's characteristics and play style.

[0031] The voice dialogue unit can analyze viewers' real-time reactions and generate live commentary in response to them. For example, the voice dialogue unit uses a generation AI to analyze viewers' chat messages in real time and generate comments based on the viewers' reactions. For example, if a viewer comments "Amazing!", the voice dialogue unit can generate a comment such as "The viewers are surprised, too!". The voice dialogue unit can also identify the points that viewers are paying attention to based on the viewers' real-time reactions and generate live commentary in response to those points. This makes it possible to generate live commentary in response to the viewers' real-time reactions.

[0032] The cheering section can refer to the player's past match results and generate balanced cheering comments. For example, the cheering section generates a comment such as "Player A is on track for another win!" if the generation AI analyzes the player's past match results and player A has had many wins in the past. The cheering section can also generate balanced cheering comments based on the player's past match results. This makes it possible to generate balanced cheering comments based on the player's past match results.

[0033] The cheering section can generate cheering comments that reflect the viewer voting results and incorporate the viewer's opinions. For example, the cheering section analyzes the results of the viewers' real-time votes and generates comments such as "The majority of viewers are rooting for Player A!" for the player the viewers are rooting for. The cheering section can also generate cheering comments that incorporate the viewer's opinions based on the viewer voting results. This makes it possible to generate cheering comments that incorporate the viewer's opinions.

[0034] The voice dialogue unit can also be applied to live commentary in entertainment fields other than games, such as sporting events and live concerts. For example, the voice dialogue unit uses a generative AI to build a system that provides live commentary of sporting events. For example, during a soccer match, it generates live commentary such as "Player A has scored a goal!" The voice dialogue unit can also be applied to live commentary of live concerts. This makes it possible to provide live commentary in entertainment fields other than games.

[0035] The voice dialogue unit generates live commentary comments in multiple languages, making it possible to accommodate international audiences. The voice dialogue unit, for example, uses a generation AI to generate live commentary comments in multiple languages, such as English and French. For example, "Player A made an amazing play!" is generated in English as "Player A made an amazing play!" The voice dialogue unit can also generate live commentary comments in multiple languages, making it possible to accommodate international audiences. This allows live commentary comments to be generated in multiple languages, making it possible to accommodate international audiences.

[0036] The voice dialogue unit can refer to the player's past play data and predict the player's behavior patterns. For example, the generation AI of the voice dialogue unit analyzes the player's past play data and predicts the player's behavior patterns. For example, it predicts the action that player A often takes in a specific situation and generates a comment such as, "It's highly likely that player A will launch an attack next!" The voice dialogue unit can also predict the player's next action based on the player's behavior patterns. This makes it possible to predict the player's behavior patterns and generate commentary.

[0037] The voice dialogue unit can analyze viewers' real-time reactions and identify the points they are paying attention to. For example, the voice dialogue unit uses a generation AI to analyze viewers' chat messages in real time and identify the points they are paying attention to. For example, it can analyze a scene where a viewer comments, "Amazing!", and generate a comment such as, "The viewers are paying attention!" The voice dialogue unit can also identify the points viewers are paying attention to based on the viewers' real-time reactions. This makes it possible to identify the points viewers are paying attention to and generate live comments.

[0038] The voice dialogue unit is capable of supporting multiple game titles and analyzing the progress of different games. The voice dialogue unit, for example, uses a generation AI to build a progress analysis system that supports multiple game titles. For example, it supports games of different genres, such as FPS games and MOBA games. The voice dialogue unit can also generate appropriate commentary based on the progress of different games. This allows it to support multiple game titles and analyze the progress of different games.

[0039] The voice dialogue unit can use voice synthesis technology to generate voices that resemble the voices of players. The voice dialogue unit, for example, uses voice synthesis technology to build a system that generates voices that resemble the voices of players. For example, the voice dialogue unit generates a comment such as "Player A made a great play!" in a voice that resembles the voice of player A. The voice dialogue unit can also generate commentary comments based on the voice that resembles the voice of a player. This allows the voice that resembles the voice of a player to be generated and commentary comments to be output.

[0040] The voice dialogue unit can analyze the real-time reactions of the viewers and adjust the voice tone according to the reactions. For example, the voice dialogue unit analyzes the real-time reactions of the viewers and raises the voice tone if the viewers are excited. For example, the voice dialogue unit outputs a comment such as "The viewers are excited!" in an uplifting tone. The voice dialogue unit can also adjust the voice tone based on the viewers' reactions. This allows the voice tone to be adjusted according to the viewers' reactions and the live commentary to be output.

[0041] The voice dialogue unit's voice output function can also be applied to entertainment fields other than games, such as sporting events and live concerts. For example, the voice dialogue unit uses the voice output function to build a system that provides live commentary of a sporting event. For example, during a soccer match, a live commentary such as "Player A has scored a goal!" can be output by voice. The voice dialogue unit can also be applied to live commentary of a live concert. This allows the voice output function to be applied to entertainment fields other than games.

[0042] The voice dialogue unit outputs voice in multiple languages, making it possible to accommodate an international audience. The voice dialogue unit, for example, uses the voice output function to output live commentary in multiple languages, such as English and French, by voice. For example, a comment such as "Player A made an amazing play!" can be output in English as "Player A made an amazing play!" The voice dialogue unit can also output voice in multiple languages ​​in order to accommodate an international audience. This allows voice output in multiple languages, making it possible to accommodate an international audience.

[0043] The voice dialogue unit can refer to the player's past play data and suggest a commentary style that suits the player's preferences. For example, the voice dialogue unit uses a generation AI to analyze the player's past play data and suggest a commentary style that suits the player's preferences. For example, if player A likes excited commentary, it generates excited-style comments such as, "Player A made a great play!" The voice dialogue unit can also generate commentary comments based on the commentary style that suits the player's preferences. This makes it possible to suggest a commentary style that suits the player's preferences.

[0044] The voice dialogue unit can analyze the viewer's real-time reactions and suggest a commentary style that suits the viewer's preferences. For example, the voice dialogue unit uses a generation AI to analyze the viewer's chat messages in real time and suggest a commentary style that suits the viewer's preferences. For example, if a viewer comments, "I want a more exciting commentary!", the voice dialogue unit can generate an excited comment such as, "Player A made a great play!". The voice dialogue unit can also suggest a commentary style that suits the viewer's preferences based on the viewer's real-time reactions. This makes it possible to suggest a commentary style that suits the viewer's preferences.

[0045] The voice dialogue unit can also apply the customizable commentary style to entertainment fields other than games, such as sporting events and live concerts. For example, the voice dialogue unit can use generative AI to build a system that customizes the commentary style of a sporting event. For example, during a soccer game, the voice dialogue unit can generate excited comments such as "Player A has scored a goal!" The voice dialogue unit can also be applied to the commentary style of a live concert. This makes it possible to apply the customizable commentary style to entertainment fields other than games.

[0046] The voice dialogue unit can provide a commentary style that supports multiple languages, making it possible to accommodate international audiences. The voice dialogue unit can, for example, use a generation AI to provide a commentary style that supports multiple languages, such as English and French. For example, a comment such as "Player A made an amazing play!" can be generated in English to convey "Player A made an amazing play!" The voice dialogue unit can also provide a commentary style that supports multiple languages, making it possible to accommodate international audiences.

[0047] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0048] The commentary system can further include a health management unit that monitors the health of the player. For example, the health management unit measures the player's heart rate and stress level in real time, and generates a comment such as "Player A, please relax a bit" if the player is overly tense. The health management unit can also generate a comment encouraging the player to take a break based on the player's health condition. This allows commentary to be generated that takes the player's health condition into consideration.

[0049] The commentary system may further include a strategy analysis unit that analyzes the player's strategy. For example, the strategy analysis unit may analyze the player's past play data and identify the tactics the player frequently uses. If player A prefers defensive tactics, the strategy analysis unit may generate a comment such as "Player A is focusing on defense." The strategy analysis unit may also predict the player's next move based on the player's tactics. This allows the system to generate commentary that corresponds to the player's strategy.

[0050] The commentary system can further include a viewer learning unit that learns viewer preferences. For example, the viewer learning unit analyzes the viewer's past reactions and identifies the viewer's preferred commentary style. If the viewer prefers an exciting commentary, the unit generates a comment such as "The viewer is excited!". The viewer learning unit can also customize the commentary style based on the viewer's preferences. This allows the system to generate commentary comments that match the viewer's preferences.

[0051] The commentary system can further include a skill evaluation unit that evaluates the skill level of a player. For example, the skill evaluation unit analyzes the player's past play data and evaluates the player's skill level. If player A has high skill, it generates a comment such as "Player A is showing great skill!". The skill evaluation unit can also generate appropriate commentary comments based on the player's skill level. This allows commentary comments to be generated according to the player's skill level.

[0052] The commentary system can further include a performance analysis unit that analyzes the performance of a player. For example, the performance analysis unit analyzes the past play data of a player and evaluates the player's performance. If player A is showing a high performance, it can generate a comment such as "Player A is showing a great performance!". The performance analysis unit can also generate appropriate commentary comments based on the player's performance. This allows commentary comments to be generated according to the player's performance.

[0053] The commentary system may further include a style analysis unit that analyzes the player's play style. For example, the style analysis unit may analyze the player's past play data to identify the player's play style. If player A has an offensive style, the commentary unit may generate a comment such as, "Player A is on the attack again!". The style analysis unit may also generate appropriate commentary comments based on the player's play style. This allows the commentary comments to be generated according to the player's play style.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The generative AI analyzes the game progress in real time. For example, the generative AI analyzes the in-game score, player movements, and important events (e.g., goals, kills, item acquisition, etc.). Step 2: The voice dialogue unit generates appropriate commentary based on the game progress analyzed by the generation AI. For example, it generates commentary such as, "Player A just made a great play!" or "Player B has a chance to turn the game around!" The voice dialogue unit can also refer to the player's past play data to generate commentary that matches the player's characteristics and play style. Step 3: The cheering team generates fair cheering comments based on the game progress analyzed by the generation AI. For example, if player A is in the lead, the cheering team will generate a comment such as "Player A is leading, but player B is also doing his best!" to cheer on player B. If player B makes a comeback, the cheering team will generate a comment such as "Player B has made a comeback! Player A, do your best and don't give up!" to cheer on player A.

[0056] (Example 2) A commentary system according to an embodiment of the present invention is a system that allows a gamer to provide commentary by voice alone. This system also has a function for cheering on each player in a competitive game from an impartial standpoint. This allows the commentary system to allow a gamer to provide commentary by voice alone, thereby providing impartial cheering in a competitive game.

[0057] A commentary system according to an embodiment includes a generation AI, a voice dialogue unit, and a cheering unit. The generation AI analyzes the progress of a game in real time. For example, the generation AI analyzes the in-game score, player movements, and important events (e.g., goals, kills, item acquisition, etc.). The generation AI also generates appropriate commentary comments based on the progress of the game. The voice dialogue unit generates appropriate commentary comments based on the progress of the game analyzed by the generation AI. For example, the voice dialogue unit generates commentary comments such as, "Player A just made a great play!" or "Player B has a chance to turn the game around!" The voice dialogue unit can also refer to the players' past play data to generate commentary comments based on the characteristics and play styles of each player. The cheering unit generates fair cheering comments based on the progress of the game analyzed by the generation AI. For example, if player A is in the lead, the cheering unit may generate a comment such as, "Player A is leading, but player B is also doing well!" to cheer on player B. Furthermore, when player B makes a comeback, the cheering section generates a comment such as "Player B has made a comeback! Don't give up, player A!" to cheer on player A. As a result, the commentary system according to the embodiment allows a gamer to provide commentary by voice interaction alone, and can provide fair cheering in a competitive game.

[0058] The voice dialogue unit can refer to a player's past play data and generate commentary comments that match the player's characteristics and play style. For example, the voice dialogue unit uses a generation AI to analyze a player's past play data and understand the player's preferred tactics and play style. For example, if player A has an offensive style, the voice dialogue unit can generate a comment such as, "Player A has gone on the attack again!". The voice dialogue unit can also identify a player's characteristics based on the player's past play data and generate commentary comments that match the player's characteristics and play style. This makes it possible to generate commentary comments that match the player's characteristics and play style.

[0059] The voice dialogue unit can analyze viewers' real-time reactions and generate live commentary in response to them. For example, the voice dialogue unit uses a generation AI to analyze viewers' chat messages in real time and generate comments based on the viewers' reactions. For example, if a viewer comments "Amazing!", the voice dialogue unit can generate a comment such as "The viewers are surprised, too!". The voice dialogue unit can also identify the points that viewers are paying attention to based on the viewers' real-time reactions and generate live commentary in response to those points. This makes it possible to generate live commentary in response to the viewers' real-time reactions.

[0060] The voice dialogue unit can use the emotion estimation function to estimate the player's emotions and generate commentary comments according to those emotions. For example, the voice dialogue unit can use the emotion estimation function to analyze the player's facial expressions and tone of voice, and if the player is excited, generate a comment such as "Player A is excited!". The voice dialogue unit can also generate cheering comments to motivate the player based on the player's emotions. This makes it possible to generate commentary comments according to the player's emotions.

[0061] The cheering section can refer to the player's past match results and generate balanced cheering comments. For example, the cheering section generates a comment such as "Player A is on track for another win!" if the generation AI analyzes the player's past match results and player A has had many wins in the past. The cheering section can also generate balanced cheering comments based on the player's past match results. This makes it possible to generate balanced cheering comments based on the player's past match results.

[0062] The cheering section can generate cheering comments that reflect the viewer voting results and incorporate the viewer's opinions. For example, the cheering section analyzes the results of the viewers' real-time votes and generates comments such as "The majority of viewers are rooting for Player A!" for the player the viewers are rooting for. The cheering section can also generate cheering comments that incorporate the viewer's opinions based on the viewer voting results. This makes it possible to generate cheering comments that incorporate the viewer's opinions.

[0063] The cheering section can use the emotion estimation function to estimate the player's emotions and generate cheering comments that will motivate the player. For example, the cheering section can use the emotion estimation function to analyze the player's facial expressions and tone of voice, and if the player is feeling down, generate cheering comments such as "Player A, do your best!". The cheering section can also generate cheering comments that will motivate the player based on the player's emotions. This allows the cheering section to generate cheering comments that correspond to the player's emotions and increase their motivation.

[0064] The voice dialogue unit can also be applied to live commentary in entertainment fields other than games, such as sporting events and live concerts. For example, the voice dialogue unit uses a generative AI to build a system that provides live commentary of sporting events. For example, during a soccer match, it generates live commentary such as "Player A has scored a goal!" The voice dialogue unit can also be applied to live commentary of live concerts. This makes it possible to provide live commentary in entertainment fields other than games.

[0065] The voice dialogue unit generates live commentary comments in multiple languages, making it possible to accommodate international audiences. The voice dialogue unit, for example, uses a generation AI to generate live commentary comments in multiple languages, such as English and French. For example, "Player A made an amazing play!" is generated in English as "Player A made an amazing play!" The voice dialogue unit can also generate live commentary comments in multiple languages, making it possible to accommodate international audiences. This allows live commentary comments to be generated in multiple languages, making it possible to accommodate international audiences.

[0066] The voice dialogue unit can use the emotion estimation function to analyze the viewer's emotions in real time and generate live commentary in accordance with the viewer's emotions. For example, the voice dialogue unit can use the emotion estimation function to analyze the viewer's facial expressions and chat messages, and generate a comment such as "The viewers are excited too!" if the viewer is excited. The voice dialogue unit can also generate live commentary in accordance with the viewer's emotions based on the viewer's emotions. This makes it possible to generate live commentary in accordance with the viewer's emotions.

[0067] The voice dialogue unit can refer to the player's past play data and predict the player's behavior patterns. For example, the generation AI of the voice dialogue unit analyzes the player's past play data and predicts the player's behavior patterns. For example, it predicts the action that player A often takes in a specific situation and generates a comment such as, "It's highly likely that player A will launch an attack next!" The voice dialogue unit can also predict the player's next action based on the player's behavior patterns. This makes it possible to predict the player's behavior patterns and generate commentary.

[0068] The voice dialogue unit can analyze viewers' real-time reactions and identify the points they are paying attention to. For example, the voice dialogue unit uses a generation AI to analyze viewers' chat messages in real time and identify the points they are paying attention to. For example, it can analyze a scene where a viewer comments, "Amazing!", and generate a comment such as, "The viewers are paying attention!" The voice dialogue unit can also identify the points viewers are paying attention to based on the viewers' real-time reactions. This makes it possible to identify the points viewers are paying attention to and generate live comments.

[0069] The voice dialogue unit can use the emotion estimation function to estimate the player's emotions and identify important events based on those emotions. For example, the voice dialogue unit can use the emotion estimation function to analyze the player's facial expressions and tone of voice to identify scenes in which the player is excited. For example, the voice dialogue unit can generate a comment such as "Player A is excited!". The voice dialogue unit can also identify important events in the game based on the player's emotions. This makes it possible to identify important events based on the player's emotions and generate commentary.

[0070] The voice dialogue unit is capable of supporting multiple game titles and analyzing the progress of different games. The voice dialogue unit, for example, uses a generation AI to build a progress analysis system that supports multiple game titles. For example, it supports games of different genres, such as FPS games and MOBA games. The voice dialogue unit can also generate appropriate commentary based on the progress of different games. This allows it to support multiple game titles and analyze the progress of different games.

[0071] The voice dialogue unit can use the emotion estimation function to analyze the viewer's emotions in real time and identify points of interest to the viewer. For example, the voice dialogue unit can use the emotion estimation function to analyze the viewer's facial expressions and chat messages and identify scenes in which the viewer is excited. For example, the voice dialogue unit can generate a comment such as "The viewer is excited!". The voice dialogue unit can also identify points of interest to the viewer based on the viewer's emotions. This allows the voice dialogue unit to identify points of interest to the viewer and generate live comments.

[0072] The voice dialogue unit can use voice synthesis technology to generate voices that resemble the voices of players. The voice dialogue unit, for example, uses voice synthesis technology to build a system that generates voices that resemble the voices of players. For example, the voice dialogue unit generates a comment such as "Player A made a great play!" in a voice that resembles the voice of player A. The voice dialogue unit can also generate commentary comments based on the voice that resembles the voice of a player. This allows the voice that resembles the voice of a player to be generated and commentary comments to be output.

[0073] The voice dialogue unit can analyze the real-time reactions of the viewers and adjust the voice tone according to the reactions. For example, the voice dialogue unit analyzes the real-time reactions of the viewers and raises the voice tone if the viewers are excited. For example, the voice dialogue unit outputs a comment such as "The viewers are excited!" in an uplifting tone. The voice dialogue unit can also adjust the voice tone based on the viewers' reactions. This allows the voice tone to be adjusted according to the viewers' reactions and the live commentary to be output.

[0074] The voice dialogue unit can use the emotion estimation function to estimate the player's emotion and generate an audio tone corresponding to that emotion. For example, the voice dialogue unit uses the emotion estimation function to analyze the player's facial expression and tone of voice, and generate an uplifting audio tone when the player is excited. For example, the voice dialogue unit outputs a comment such as "Player A is excited!" in an uplifting tone. The voice dialogue unit can also generate an audio tone based on the player's emotion. This allows for generating an audio tone corresponding to the player's emotion and outputting a commentary.

[0075] The voice dialogue unit's voice output function can also be applied to entertainment fields other than games, such as sporting events and live concerts. For example, the voice dialogue unit uses the voice output function to build a system that provides live commentary of a sporting event. For example, during a soccer match, a live commentary such as "Player A has scored a goal!" can be output by voice. The voice dialogue unit can also be applied to live commentary of a live concert. This allows the voice output function to be applied to entertainment fields other than games.

[0076] The voice dialogue unit outputs voice in multiple languages, making it possible to accommodate an international audience. The voice dialogue unit, for example, uses the voice output function to output live commentary in multiple languages, such as English and French, by voice. For example, a comment such as "Player A made an amazing play!" can be output in English as "Player A made an amazing play!" The voice dialogue unit can also output voice in multiple languages ​​in order to accommodate an international audience. This allows voice output in multiple languages, making it possible to accommodate an international audience.

[0077] The voice dialogue unit can use the emotion estimation function to analyze the viewer's emotions in real time and generate a voice tone corresponding to the viewer's emotions. For example, the voice dialogue unit uses the emotion estimation function to analyze the viewer's facial expressions and chat messages, and generate an uplifting voice tone when the viewer is excited. For example, the voice dialogue unit outputs a comment such as "The viewers are excited!" in an uplifting tone. The voice dialogue unit can also generate a voice tone based on the viewer's emotions. This allows the voice tone to be generated according to the viewer's emotions and the live commentary to be output.

[0078] The voice dialogue unit can refer to the player's past play data and suggest a commentary style that suits the player's preferences. For example, the voice dialogue unit uses a generation AI to analyze the player's past play data and suggest a commentary style that suits the player's preferences. For example, if player A likes excited commentary, it generates excited-style comments such as, "Player A made a great play!" The voice dialogue unit can also generate commentary comments based on the commentary style that suits the player's preferences. This makes it possible to suggest a commentary style that suits the player's preferences.

[0079] The voice dialogue unit can analyze the viewer's real-time reactions and suggest a commentary style that suits the viewer's preferences. For example, the voice dialogue unit uses a generation AI to analyze the viewer's chat messages in real time and suggest a commentary style that suits the viewer's preferences. For example, if a viewer comments, "I want a more exciting commentary!", the voice dialogue unit can generate an excited comment such as, "Player A made a great play!". The voice dialogue unit can also suggest a commentary style that suits the viewer's preferences based on the viewer's real-time reactions. This makes it possible to suggest a commentary style that suits the viewer's preferences.

[0080] The voice dialogue unit can use the emotion estimation function to estimate the player's emotions and propose a commentary style that matches those emotions. For example, the voice dialogue unit can use the emotion estimation function to analyze the player's facial expressions and tone of voice, and propose an excited commentary style if the player is excited. For example, the voice dialogue unit can generate an excited-style comment such as, "Player A is excited!" The voice dialogue unit can also propose a commentary style based on the player's emotions. This makes it possible to propose a commentary style that matches the player's emotions.

[0081] The voice dialogue unit can also apply the customizable commentary style to entertainment fields other than games, such as sporting events and live concerts. For example, the voice dialogue unit can use generative AI to build a system that customizes the commentary style of a sporting event. For example, during a soccer game, the voice dialogue unit can generate excited comments such as "Player A has scored a goal!" The voice dialogue unit can also be applied to the commentary style of a live concert. This makes it possible to apply the customizable commentary style to entertainment fields other than games.

[0082] The voice dialogue unit can provide a commentary style that supports multiple languages, making it possible to accommodate international audiences. The voice dialogue unit can, for example, use a generation AI to provide a commentary style that supports multiple languages, such as English and French. For example, a comment such as "Player A made an amazing play!" can be generated in English to convey "Player A made an amazing play!" The voice dialogue unit can also provide a commentary style that supports multiple languages, making it possible to accommodate international audiences.

[0083] The voice dialogue unit can use the emotion estimation function to analyze the viewer's emotions in real time and propose a commentary style that matches the viewer's emotions. For example, the voice dialogue unit can use the emotion estimation function to analyze the viewer's facial expressions and chat messages, and propose an excited commentary style if the viewer is excited. For example, the voice dialogue unit can generate an excited-style comment such as "The viewer is excited!". The voice dialogue unit can also propose a commentary style based on the viewer's emotions. This makes it possible to propose a commentary style that matches the viewer's emotions.

[0084] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0085] The commentary system can further include a health management unit that monitors the health of the player. For example, the health management unit measures the player's heart rate and stress level in real time, and generates a comment such as "Player A, please relax a bit" if the player is overly tense. The health management unit can also generate a comment encouraging the player to take a break based on the player's health condition. This allows commentary to be generated that takes the player's health condition into consideration.

[0086] The commentary system may further include a strategy analysis unit that analyzes the player's strategy. For example, the strategy analysis unit may analyze the player's past play data and identify the tactics the player frequently uses. If player A prefers defensive tactics, the strategy analysis unit may generate a comment such as "Player A is focusing on defense." The strategy analysis unit may also predict the player's next move based on the player's tactics. This allows the system to generate commentary that corresponds to the player's strategy.

[0087] The commentary system can further include a viewer learning unit that learns viewer preferences. For example, the viewer learning unit analyzes the viewer's past reactions and identifies the viewer's preferred commentary style. If the viewer prefers an exciting commentary, the unit generates a comment such as "The viewer is excited!". The viewer learning unit can also customize the commentary style based on the viewer's preferences. This allows the system to generate commentary comments that match the viewer's preferences.

[0088] The commentary system can further include a behavior prediction unit that estimates the player's emotions and predicts the player's behavior based on those emotions. For example, the behavior prediction unit analyzes the player's facial expressions and tone of voice, and if the player is excited, generates a comment such as "Player A is likely to launch an attack next!". The behavior prediction unit can also predict the player's next behavior based on the player's emotions. This makes it possible to predict the player's behavior according to the player's emotions and generate commentary comments.

[0089] The live commentary system may further include an interest identification unit that estimates the viewer's emotions and identifies points that will interest the viewer based on those emotions. For example, the interest identification unit may analyze the viewer's facial expressions and chat messages to identify scenes in which the viewer is excited. If the viewer is excited, the interest identification unit may generate a comment such as "The viewer is excited!". The interest identification unit may also identify points that will interest the viewer based on the viewer's emotions. This allows live commentary comments to be generated that correspond to the viewer's emotions.

[0090] The commentary system can further include a skill evaluation unit that evaluates the skill level of a player. For example, the skill evaluation unit analyzes the player's past play data and evaluates the player's skill level. If player A has high skill, it generates a comment such as "Player A is showing great skill!". The skill evaluation unit can also generate appropriate commentary comments based on the player's skill level. This allows commentary comments to be generated according to the player's skill level.

[0091] The live commentary system can further include a reaction prediction unit that estimates the viewer's emotions and predicts the viewer's reaction based on those emotions. For example, the reaction prediction unit analyzes the viewer's facial expressions and chat messages, and if the viewer is excited, generates a comment such as "predict how the viewer will react next." The reaction prediction unit can also predict the viewer's next reaction based on the viewer's emotions. This makes it possible to predict reactions according to the viewer's emotions and generate live commentary comments.

[0092] The commentary system can further include a performance analysis unit that analyzes the performance of a player. For example, the performance analysis unit analyzes the past play data of a player and evaluates the player's performance. If player A is showing a high performance, it can generate a comment such as "Player A is showing a great performance!". The performance analysis unit can also generate appropriate commentary comments based on the player's performance. This allows commentary comments to be generated according to the player's performance.

[0093] The live commentary system may further include a preference identification unit that estimates the viewer's emotions and identifies the viewer's preferences based on those emotions. For example, the preference identification unit may analyze the viewer's facial expressions and chat messages to identify scenes in which the viewer is excited. If the viewer is excited, the preference identification unit may generate a comment such as "The viewer is excited!". The preference identification unit may also identify the viewer's preferences based on the viewer's emotions. This allows live commentary comments to be generated that correspond to the viewer's emotions.

[0094] The commentary system may further include a style analysis unit that analyzes the player's play style. For example, the style analysis unit may analyze the player's past play data to identify the player's play style. If player A has an offensive style, the commentary unit may generate a comment such as, "Player A is on the attack again!". The style analysis unit may also generate appropriate commentary comments based on the player's play style. This allows the commentary comments to be generated according to the player's play style.

[0095] The processing flow of the second embodiment will be briefly explained below.

[0096] Step 1: The generative AI analyzes the game progress in real time. For example, the generative AI analyzes the in-game score, player movements, and important events (e.g., goals, kills, item acquisition, etc.). Step 2: The voice dialogue unit generates appropriate commentary based on the game progress analyzed by the generation AI. For example, it generates commentary such as, "Player A just made a great play!" or "Player B has a chance to turn the game around!" The voice dialogue unit can also refer to the player's past play data to generate commentary that matches the player's characteristics and play style. Step 3: The cheering team generates fair cheering comments based on the game progress analyzed by the generation AI. For example, if player A is in the lead, the cheering team will generate a comment such as "Player A is leading, but player B is also doing his best!" to cheer on player B. If player B makes a comeback, the cheering team will generate a comment such as "Player B has made a comeback! Player A, do your best and don't give up!" to cheer on player A.

[0097] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0098] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0099] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0100] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0101] 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.

[0102] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0103] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0104] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0105] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0106] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0107] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0108] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0109] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0110] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0111] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0112] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0113] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0114] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0115] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0116] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0117] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0118] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0119] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0121] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0122] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0123] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0124] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0125] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0126] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0127] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0128] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0129] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0130] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0131] 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.

[0132] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0133] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0134] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0136] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0137] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0138] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0139] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0140] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0141] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0142] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0143] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0144] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0145] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0146] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0147] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0148] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0149] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0150] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0151] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0152] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0153] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0154] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0155] 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.

[0156] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0157] The hardware resource for executing a specific process can be any of the following processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and uses the memory to execute the specific process.

[0158] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0159] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0160] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0161] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0162] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0163] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0164] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. Equipped with generative AI, The generated AI is Analyze the game progress in real time, a voice dialogue unit that generates appropriate commentary comments based on the progress of the game analyzed by the generation AI; and a cheering unit that generates fair cheering comments based on the progress of the game analyzed by the generation AI. A system characterized by:

2. The voice dialogue unit Using emotion estimation function, the player's emotions are estimated and commentary is generated according to those emotions.

2. The system of claim 1.

3. The cheering section: Using an emotion estimation function, the player's emotions are estimated and cheering comments that motivate the player are generated.

2. The system of claim 1.

4. The voice dialogue unit Using emotion estimation function, the emotions of viewers are analyzed in real time and live commentary is generated according to the emotions of the viewers.

2. The system of claim 1.

5. The voice dialogue unit Emotion estimation feature to estimate player emotions and identify important events based on those emotions 2. The system of claim 1.

6. The voice dialogue unit Using emotion estimation function, the player's emotions are estimated and an audio tone is generated according to the emotions.

2. The system of claim 1.

7. The voice dialogue unit Using emotion estimation function, we estimate the player's emotions and suggest commentary styles according to those emotions.

2. The system of claim 1.

8. The voice dialogue unit Using emotion estimation function, the system analyzes viewers' emotions in real time and proposes a commentary style that matches the viewers' emotions.

2. The system of claim 1.

Images