System

Abstract

An object of a system according to an embodiment is to provide excitement when playing a game alone.SOLUTION: A system includes a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects video data of a game or controller input data of a user. The analysis unit analyzes the data collected by the collection unit and estimates a current situation of the game. The generation unit generates a live commentary based on the situation estimated by the analysis unit. The provision unit provides the live commentary generated by the generation unit in real time.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of lacking excitement when playing games alone.

[0005] The system according to the embodiment aims to provide excitement when playing a game alone. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects game video data or user controller input data. The analysis unit analyzes the data collected by the collection unit and estimates the current situation of the game. The generation unit generates a commentary based on the situation estimated by the analysis unit. The provision unit provides the commentary generated by the generation unit in real time. [Effects of the Invention]

[0007] The system according to the embodiment can provide excitement when playing a game alone. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

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

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

[0028] (Example 1) An automated game commentary system according to an embodiment of the present invention collects game video data and user controller input data, and uses AI to estimate the current game situation and generate and provide commentary in real time. The automated game commentary system collects game video data and user controller input data while a user is playing a game, and the AI ​​generates appropriate commentary content based on the game's progress and the user's play style. For example, if a user is playing an action game, the system grasps the character's movements, attack timing, enemy appearance status, and so on. Next, based on the collected data, the system estimates the current game situation. For example, when a user enters a boss battle, the system recognizes the situation and generates a tense commentary. This estimation is performed by AI, and appropriate commentary content is generated based on the game's progress and the user's play style. Furthermore, the generated commentary content is provided to the user in real time. For example, when a user clears a difficult stage, an encouraging commentary such as "Great play! Let's do our best on the next stage!" is played. This allows users to experience the immersive experience of playing alone, as if they were playing with a commentator. The automated game commentary system can also accumulate user play data and provide commentary customized for each individual user. For example, if a user prefers to use a particular character, a special commentary for that character can be generated. This allows the user to become even more immersed in the game. This allows the automated game commentary system to improve the user's gaming experience. For example, when a user starts a new game, the system can provide advice and hints at the appropriate time, deepening the user's understanding of the game. Furthermore, even when a user is playing alone, the system can provide a sense of realism as if a commentator were playing the game. Furthermore, by accumulating user play data and providing commentary customized for each individual user, the user can become even more immersed in the game.

[0029] An automated game commentary system according to an embodiment includes a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects game video data or user controller input data. The game video data includes, for example, character movements, attack timing, and enemy appearance status. The user controller input data includes, for example, button presses, stick movements, and trigger operations. The collection unit collects this data in real time and transmits it to the analysis unit. The analysis unit analyzes the data collected by the collection unit to estimate the current game situation. The analysis unit generates appropriate commentary content based on the game progress and the user's play style, for example, using AI. For example, when a user enters a boss battle, the analysis unit recognizes the situation and generates a tense commentary. The generation unit generates a commentary based on the situation estimated by the analysis unit. For example, the generation unit generates a customized commentary tailored to the user's play style, using AI. For example, if a user prefers to use a specific character, the generation unit generates a special commentary for that character. The provision unit provides the commentary generated by the generation unit in real time. For example, when a user clears a difficult stage, the providing unit provides an encouraging commentary such as, "Great play! Let's do our best on the next stage!" This allows the automated game commentary system according to the embodiment to improve the user's gaming experience. For example, when a user starts a new game, the system can provide advice and hints at the appropriate time, deepening the user's understanding of the game. Furthermore, even when a user is playing alone, the system can provide a sense of realism as if a commentator were playing the game. Furthermore, by accumulating user play data and providing commentary customized for each individual user, the user can become even more immersed in the game.

[0030] The collection unit includes a storage unit that stores user play data. The storage unit stores the user play data. The user play data includes, for example, play time, operation history, and in-game actions. The storage unit stores this data over a long period of time and provides it to the analysis unit and generation unit. By storing the user play data, customization tailored to each individual user is possible. For example, if a user prefers to use a particular character, a special commentary about that character can be generated. Furthermore, the storage unit can analyze the user play data and grasp changes in the user's play style. For example, if a user changes from an offensive to a defensive play style, the change can be analyzed and appropriate commentary content can be provided. By storing the user play data, customization tailored to each individual user is possible, thereby improving the user's game experience.

[0031] The generation unit includes a customization unit that generates a customized commentary tailored to each individual user. The customization unit generates a customized commentary tailored to each individual user. The customized commentary reflects, for example, the user's play style, preferences, past play data, and the like. The customization unit generates commentary content optimal for the user based on this data. For example, if a user prefers to use a particular character, the customization unit generates a special commentary related to that character. The customization unit can also adjust the tone and content of the commentary according to the user's play style. For example, if the user has an aggressive play style, the customization unit can provide an energetic commentary tailored to that style. This allows for providing a customized commentary tailored to the user's play style and improving the user's gaming experience. Furthermore, the customization unit can analyze the user's play data and adjust the commentary content according to changes in the user's play style. For example, if the user changes from a defensive play style to an aggressive play style, the customization unit can provide a commentary that reflects that change. This allows for providing a customized commentary tailored to the user's play style and improving the user's gaming experience.

[0032] The analysis unit can generate specific commentary content according to the game progress and the user's play style. The analysis unit generates specific commentary content according to the game progress and the user's play style. The game progress includes, for example, the stage progress and the mission completion status. The user's play style includes, for example, attack type, defense type, exploration type, etc. The analysis unit generates commentary content optimal for the user based on this data. For example, when the user enters a boss battle, the analysis unit recognizes the situation and generates a tense commentary. Furthermore, when the user clears a difficult stage, the analysis unit generates an encouraging commentary such as, "Great play! Let's do our best in the next stage!" This makes it possible to provide commentary content appropriate for the game progress and the user's play style, thereby improving the user's gaming experience. Furthermore, the analysis unit can analyze the user's play data and adjust the commentary content according to changes in the user's play style. For example, if the user changes from a defensive play style to an offensive play style, a commentary that reflects the change is provided. This allows the user's gaming experience to be improved by providing commentary content appropriate for the user's play style.

[0033] The providing unit can provide a commentary that encourages the user when the user clears a difficult stage. The providing unit provides a commentary that encourages the user when the user clears a difficult stage. A difficult stage includes, for example, the strength of the enemy, the complexity of the stage, and the completion rate. The providing unit provides the user with optimal encouraging commentary based on this data. For example, when the user clears a difficult stage, the providing unit provides an encouraging commentary such as, "Great play! Let's do our best on the next stage!". This can increase the user's motivation by providing an encouraging commentary when the user clears a difficult stage. Furthermore, the providing unit can analyze the user's play data and adjust the commentary content according to the user's play style. For example, if the user changes from a defensive play style to an offensive play style, the providing unit provides a commentary that reflects that change. This can improve the user's game experience by providing appropriate commentary content according to the user's play style.

[0034] The providing unit can provide advice or hints to the user when the user starts a new game. The providing unit provides advice or hints to the user when the user starts a new game. The advice or hints include, for example, strategies, operation methods, and the like. The providing unit provides optimal advice or hints to the user based on this data. For example, when the user starts a new game, the providing unit can provide advice such as, "In this stage, it would be a good idea to first defeat the enemy before proceeding." This allows the user to deepen their understanding of the game by providing advice or hints when starting a new game. Furthermore, the providing unit can analyze the user's play data and adjust the advice or hints according to the user's play style. For example, if the user changes from a defensive play style to an offensive play style, the providing unit can provide advice or hints that reflect that change. This allows the user's game experience to be improved by providing appropriate advice or hints according to the user's play style.

[0035] The collection unit can set a priority order for the data to be collected according to the type of game. The collection unit sets a priority order for the data to be collected according to the type of game. The types of games include, for example, action games, puzzle games, racing games, etc. The collection unit changes the priority order for the data to be collected according to the type of game. For example, in an action game, character movements and attack timings can be collected with priority. In addition, in a puzzle game, user input timing and answer patterns can be collected with priority. Furthermore, in a racing game, car speed and progress status on the course can be collected with priority. Thus, by changing the priority order for the data to be collected according to the type of game, more appropriate data can be collected. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0036] The collection unit can set the frequency of data collection based on the user's play style. The collection unit sets the frequency of data collection based on the user's play style. User play styles include, for example, an aggressive play style, a slow play style, and a specific play style. The collection unit adjusts the frequency of data collection according to these play styles. For example, if the user plays aggressively, the frequency of data collection is increased to perform detailed analysis. On the other hand, if the user plays slowly, the frequency of data collection can be reduced to reduce the load on the system. Furthermore, if the user has a specific play style, the frequency of data collection can be adjusted to match that style. In this way, by adjusting the frequency of data collection according to the user's play style, it is possible to collect appropriate data while reducing the load on the system. Some or all of the above-mentioned processing by the collection unit may be performed, for example, using AI or without AI.

[0037] The collection unit can combine multiple sensor data to improve the accuracy of the collected data. The collection unit combines multiple sensor data to improve the accuracy of the collected data. The sensor data includes, for example, game video data, controller input data, biometric data such as heart rate and body temperature, and in-game audio data. The collection unit integrates these sensor data to more accurately grasp the game situation. For example, the game video data and controller input data can be integrated to more accurately grasp the game situation. Furthermore, biometric data such as the user's heart rate and body temperature can be integrated to more accurately grasp the user's condition. Furthermore, in-game audio data and video data can be integrated to generate a more realistic commentary. In this way, by integrating multiple sensor data, the accuracy of the collected data can be improved. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0038] The collection unit can analyze the collected data in real time and identify abnormal play actions. The collection unit analyzes the collected data in real time and identify abnormal play actions. Abnormal play actions include, for example, deviations from normal play patterns and error actions. The collection unit detects abnormal play actions based on this data. For example, if a user exhibits an input pattern that is different from normal, it can detect this as an abnormality. In addition, if an unexpected action occurs in the game, it can detect this as an abnormality. Furthermore, if a user exhibits abnormal behavior, such as repeatedly pressing a specific button, it can detect this as an abnormality. In this way, by analyzing the collected data in real time, abnormal play actions can be quickly detected. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without using AI.

[0039] The collection unit can store the collected data in a cloud so that it can be accessed from other devices. The collection unit can store the collected data in a cloud so that it can be accessed from other devices. Examples of cloud services include AWS (registered trademark), Google (registered trademark), and Azure (registered trademark). The collection unit uses these cloud services to store the collected data. For example, a user can use the data stored in the cloud when playing a game on a different device. The user can also access the cloud to refer to past play data. Furthermore, the user can use the data stored in the cloud to share data with friends. Storing the collected data in the cloud thus makes it accessible from other devices, improving convenience. Some or all of the above-described processing by the collection unit may be performed, for example, using AI or without AI.

[0040] The collection unit can display the user's play history using the collected data. The collection unit uses the collected data to display the user's play history. The play history includes, for example, play time, cleared stages, and scores. The collection unit visualizes the user's play history based on this data. For example, it displays the stages the user has previously cleared and the scores they have achieved in a graph. The collection unit can also visualize the user's play time and frequency to analyze their play patterns. Furthermore, it can visualize the frequency with which the user used a particular character or weapon. In this way, the user's play pattern can be analyzed by visualizing the user's play history using the collected data. Some or all of the above-described processing in the collection unit may be performed, for example, using AI or without AI.

[0041] The analysis unit can adjust the accuracy of the analysis according to the progress of the game. The analysis unit adjusts the accuracy of the analysis according to the progress of the game. The progress of the game includes, for example, the progress of the stage and the completion status of the mission. The analysis unit dynamically changes the accuracy of the analysis based on this data. For example, in important scenes such as boss battles, detailed analysis is performed to provide highly accurate commentary. Furthermore, during normal play, basic analysis is performed to reduce the load on the system. Furthermore, when the user advances to a new stage, detailed analysis can be performed to provide appropriate advice. In this way, by dynamically changing the accuracy of the analysis according to the progress of the game, it is possible to reduce the load on the system and provide appropriate analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0042] The analysis unit can learn the user's play style and improve the accuracy of the analysis results. The analysis unit can learn the user's play style and improve the accuracy of the analysis results. The user's play style includes, for example, an offensive play style, a defensive play style, and the frequency of use of a particular character or weapon. The analysis unit learns the user's play style based on this data and reflects it in the analysis results. For example, if the user has an offensive play style, the analysis unit can perform an analysis tailored to that style. Also, if the user has a defensive play style, the analysis unit can perform an analysis tailored to that style. Furthermore, if the user prefers to use a particular character or weapon, the analysis unit can learn that tendency and reflect it in the analysis results. In this way, by learning the user's play style, the accuracy of the analysis results can be improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0043] The analysis unit can predict the next game stage using the analysis results. The analysis unit predicts the next game stage using the analysis results. The next game stage includes, for example, the stage progress conditions and a prediction algorithm. The analysis unit predicts the next game stage based on this data. For example, the analysis unit predicts the difficulty level of the next stage based on the progress of the current stage. The analysis unit can also predict how to clear the next stage based on the user's play style. Furthermore, the analysis unit can predict the development of the next stage based on in-game events and enemy appearance patterns. Thus, by predicting the next game stage using the analysis results, appropriate advice can be provided to the user. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0044] The analysis unit can share the analysis results with other users and collect feedback within the community. The analysis unit shares the analysis results with other users and collects feedback within the community. Feedback includes, for example, surveys, comments, and rating systems. The analysis unit improves the analysis results based on this feedback. For example, a user can share the analysis results of a stage they have cleared and receive advice from other users. A user can also share the analysis results of their achieved score and compete with other users. Furthermore, a user can share the analysis results of a specific play style and receive feedback from other users. By sharing the analysis results with other users, feedback within the community can be obtained. Some or all of the above-described processing by the analysis unit may be performed, for example, using AI or without AI.

[0045] The analysis unit can use the analysis results to suggest areas for improvement in the user's play style. The analysis unit can use the analysis results to suggest areas for improvement in the user's play style. The areas for improvement include, for example, analysis results of the play style and specific action plans. The analysis unit suggests optimal improvements for the user based on this data. For example, if the user has an offensive play style, the analysis unit can suggest improvements to the timing of defense. Also, if the user has a defensive play style, the analysis unit can suggest improvements to the timing of attacks. Furthermore, the analysis unit can suggest effective ways for the user to use specific characters or weapons. In this way, the analysis results can be used to suggest areas for improvement in the user's play style, thereby improving the user's play style. Some or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI or without AI.

[0046] The analysis unit can use the analysis results to send feedback to the game developer. The analysis unit uses the analysis results to send feedback to the game developer. Feedback includes, for example, bug reports, feature improvement suggestions, and user opinions. The analysis unit uses this feedback to help improve the game. For example, the analysis unit can provide feedback regarding game balance adjustments based on the user's play data. New game features can also be proposed based on the user's play style. Furthermore, bugs and malfunctions can be reported based on the user's play data. In this way, providing feedback to the game developer using the analysis results can help improve the game. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0047] The generation unit can adjust the content of the commentary according to the progress of the game. The generation unit adjusts the content of the commentary according to the progress of the game. The progress of the game includes, for example, the progress of the stage and the completion status of the mission. The generation unit dynamically changes the content of the commentary based on this data. For example, during a boss battle, a tense commentary can be provided. During normal play, a relaxed commentary can be provided. Furthermore, when the user advances to a new stage, a commentary including advice and hints can be provided. This makes it possible to provide a more appropriate commentary by dynamically changing the content of the commentary according to the progress of the game. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI or without AI.

[0048] The generation unit can create a customized commentary based on the user's play style. The generation unit creates a customized commentary based on the user's play style. The customized commentary reflects, for example, the user's play style, preferences, past play data, etc. The generation unit generates commentary content optimal for the user based on this data. For example, if the user has an offensive play style, the generation unit can provide commentary tailored to that style. Also, if the user has a defensive play style, the generation unit can provide commentary tailored to that style. Furthermore, if the user prefers to use a particular character or weapon, the generation unit can provide commentary related to that character or weapon. In this way, by generating a commentary customized based on the user's play style, a more appropriate commentary can be provided. Some or all of the above-described processing by the generation unit may be performed using, for example, AI, or may be performed without using AI.

[0049] The generation unit can display the generated commentary in multiple languages. The generation unit displays the generated commentary in multiple languages. The multiple languages ​​include, for example, English, Japanese, and Spanish. The generation unit translates the generated commentary to support these languages. For example, a commentary generated in English can be translated into Japanese and provided. A commentary generated in Spanish can be translated into English and provided. Furthermore, a commentary generated in French can be translated into German and provided. In this way, by providing the generated commentary in multiple languages, it is possible to accommodate users who speak different languages. Some or all of the above-described processing in the generation unit may be performed, for example, using AI or without using AI.

[0050] The generation unit can share the generated commentary with other users and collect feedback. The generation unit shares the generated commentary with other users and collects feedback. Feedback includes, for example, surveys, comments, and rating systems. The generation unit improves the commentary content based on this feedback. For example, a user can share a commentary of a stage they have cleared and receive feedback from other users. A user can also share a commentary of a score they have achieved and compete with other users. Furthermore, a user can share a commentary of a specific play style and receive feedback from other users. In this way, feedback can be obtained by sharing the generated commentary with other users. Some or all of the above-described processing in the generation unit may be performed, for example, using AI or without using AI.

[0051] The generation unit can automatically edit the user's gameplay video using the generated commentary. The generation unit automatically edits the user's gameplay video using the generated commentary. The automatic editing includes, for example, an editing algorithm, editing criteria, and editing purpose. The generation unit automatically edits the user's gameplay video based on this data. For example, the generation unit can automatically edit a gameplay video that includes commentary of stages cleared by the user. The generation unit can also automatically edit a gameplay video that includes commentary of scores achieved by the user. Furthermore, the generation unit can automatically edit a gameplay video that includes commentary of a specific play style by the user. This allows the user's gameplay video to be easily created by automatically editing the user's gameplay video using the generated commentary. Some or all of the above-described processing by the generation unit may be performed, for example, using AI or without AI.

[0052] The generation unit can automatically generate highlight scenes of the game using the generated commentary. The generation unit automatically generates highlight scenes of the game using the generated commentary. Highlight scenes include, for example, important events, specific actions, and user preferences. The generation unit automatically generates highlight scenes of the game based on this data. For example, the generation unit automatically generates highlight scenes of stages cleared by the user. It can also automatically generate highlight scenes of scores achieved by the user. Furthermore, the generation unit can automatically generate highlight scenes of a specific play style by the user. In this way, by automatically generating highlight scenes of the game using the generated commentary, it is possible to easily look back on important moments of the user's play. Some or all of the above-mentioned processing by the generation unit may be performed, for example, using AI or without using AI.

[0053] The providing unit can set a commentary provision method according to the progress of the game. The providing unit sets a commentary provision method according to the progress of the game. The progress of the game includes, for example, the stage progress and the mission completion status. The providing unit changes the commentary provision method based on this data. For example, during a boss battle, a tense commentary can be provided. Also, during normal play, a relaxed commentary can be provided. Furthermore, when the user advances to a new stage, a commentary including advice and hints can be provided. In this way, by changing the commentary provision method according to the progress of the game, a more appropriate commentary can be provided. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or without using AI.

[0054] The providing unit can display a commentary customized based on the user's play style. The providing unit displays a commentary customized based on the user's play style. The customized commentary reflects, for example, the user's play style, preferences, past play data, etc. The providing unit provides commentary content optimized for the user based on this data. For example, if the user has an offensive play style, the providing unit can provide commentary tailored to that style. Also, if the user has a defensive play style, the providing unit can provide commentary tailored to that style. Furthermore, if the user prefers to use a particular character or weapon, the providing unit can provide commentary related to that character or weapon. This allows for a more appropriate commentary to be provided by providing a commentary customized based on the user's play style. Some or all of the above-described processing by the providing unit may be performed, for example, using AI or without AI.

[0055] The providing unit can modify the provided commentary based on user feedback. The providing unit modifies the provided commentary based on user feedback. Feedback includes, for example, questionnaires, comments, rating systems, etc. The providing unit improves the commentary content based on this feedback. For example, a user provides feedback on the provided commentary, and the commentary is improved based on the content. Also, if a user prefers specific commentary content, that content can be provided preferentially. Furthermore, if a user is dissatisfied with the provided commentary, that content can be improved. In this way, by improving the provided commentary based on user feedback, a more appropriate commentary can be provided. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI.

[0056] The providing unit can synchronize the provided commentary with other devices, enabling use across multiple devices. The providing unit synchronizes the provided commentary with other devices, enabling use across multiple devices. Multi-devices include, for example, smartphones, tablets, and PCs. The providing unit synchronizes the commentary between these devices. For example, if a user is playing on a smartphone, the commentary can also be synchronized with a tablet. Also, if a user is playing on a PC, the commentary can also be synchronized with a smartwatch. Furthermore, if a user uses multiple devices, the commentary can be synchronized with all devices. This enables use across multiple devices by synchronizing the provided commentary with other devices, improving convenience. Some or all of the above-described processing in the providing unit may be performed, for example, using AI or without AI.

[0057] The providing unit can automatically generate a gameplay video of the user using the provided commentary. The providing unit automatically generates a gameplay video of the user using the provided commentary. Automatic generation includes, for example, a generation algorithm, generation criteria, and generation purpose. The providing unit automatically generates a gameplay video of the user based on this data. For example, the providing unit can automatically generate a gameplay video including a commentary of stages cleared by the user. The providing unit can also automatically generate a gameplay video including a commentary of scores achieved by the user. Furthermore, the providing unit can automatically generate a gameplay video including a commentary of a specific play style by the user. This allows the user's gameplay video to be easily created by automatically generating the user's gameplay video using the provided commentary. Some or all of the above-described processing by the providing unit may be performed, for example, using AI or without AI.

[0058] The providing unit can display the user's play history using the provided commentary. The providing unit displays the user's play history using the provided commentary. The play history includes, for example, play time, cleared stages, and scores. The providing unit visualizes the user's play history based on this data. For example, it displays the stages the user has previously cleared and the scores they have achieved in a graph. The providing unit can also visualize the user's play time and frequency to analyze their play patterns. Furthermore, it can visualize the frequency with which the user has used a particular character or weapon. In this way, the user's play pattern can be analyzed by visualizing the user's play history using the provided commentary. Some or all of the above-described processing in the providing unit may be performed, for example, using AI or without AI.

[0059] The storage unit can analyze changes in the user's play style using the stored data. The storage unit can analyze changes in the user's play style using the stored data. Changes in play style include, for example, changes in play time and changes in behavior patterns. The storage unit evaluates changes in the user's play style based on this data. For example, if the user changes from an offensive play style to a defensive play style, the storage unit can analyze the change. Also, if the frequency with which the user uses a particular character or weapon changes, the storage unit can analyze the change. Furthermore, if the user's play time or frequency changes, the change can be analyzed. In this way, by analyzing changes in the user's play style using the stored data, changes in the user's play style can be understood. Some or all of the above-mentioned processing in the storage unit can be performed, for example, using AI or without AI.

[0060] The accumulation unit can evaluate the progress of the game using the accumulated data. The accumulation unit uses the accumulated data to evaluate the progress of the game. The progress of the game includes, for example, the progress of a stage and the completion status of a mission. The accumulation unit predicts the progress of the game based on this data. For example, the accumulation unit predicts the difficulty of the next stage based on the progress of the current stage. The accumulation unit can also predict how to clear the next stage based on the user's play style. Furthermore, the accumulation unit can predict the development of the next stage based on events and enemy appearance patterns in the game. In this way, by predicting the progress of the game using the accumulated data, it is possible to provide the user with appropriate advice. Some or all of the above-mentioned processing in the accumulation unit may be performed, for example, using AI or without using AI.

[0061] The storage unit can display the user's play history using the stored data. The storage unit uses the stored data to display the user's play history. The play history includes, for example, play time, cleared stages, and scores. The storage unit visualizes the user's play history based on this data. For example, it displays the stages the user has previously cleared and the scores they have achieved in a graph. It can also visualize the user's play time and frequency to analyze their play patterns. It can also visualize the frequency with which the user used a particular character or weapon. In this way, it is possible to analyze the user's play patterns by visualizing the user's play history using the stored data. Some or all of the above-described processing in the storage unit may be performed, for example, using AI or without AI.

[0062] The storage unit can store the stored data in the cloud so that it can be accessed from other devices. The storage unit can store the stored data in the cloud so that it can be accessed from other devices. Examples of cloud services include AWS, Google Cloud, and Azure. The storage unit uses these cloud services to store the stored data. For example, a user can use the data stored in the cloud when playing a game on a different device. The user can also access the cloud to refer to past play data. Furthermore, the user can use the data stored in the cloud to share data with friends. Storing the stored data in the cloud thus makes it accessible from other devices, improving convenience. Some or all of the above-described processing in the storage unit may be performed, for example, using AI or without AI.

[0063] The accumulation unit can use the accumulated data to indicate areas for improvement in the user's play style. The accumulation unit can use the accumulated data to indicate areas for improvement in the user's play style. The areas for improvement include, for example, analysis results of the play style and specific action plans. The accumulation unit suggests optimal improvements for the user based on this data. For example, if the user has an offensive play style, the accumulation unit can suggest improvements to the timing of defense. Also, if the user has a defensive play style, the accumulation unit can suggest improvements to the timing of attacks. Furthermore, the accumulation unit can suggest effective ways for the user to use specific characters or weapons. In this way, the accumulation unit can suggest improvements to the user's play style using the accumulated data, thereby improving the user's play style. Some or all of the above-mentioned processing in the accumulation unit can be performed, for example, using AI or without AI.

[0064] The storage unit can use the stored data to send feedback to the game developer. The storage unit uses the stored data to send feedback to the game developer. Feedback includes, for example, bug reports, feature improvement suggestions, and user opinions. The storage unit uses this feedback to help improve the game. For example, the storage unit can provide feedback regarding game balance adjustments based on the user's play data. New game features can also be proposed based on the user's play style. Furthermore, bugs and malfunctions can be reported based on the user's play data. In this way, providing feedback to the game developer using the stored data can help improve the game. Some or all of the above-mentioned processing in the storage unit may be performed, for example, using AI or without using AI.

[0065] The customization unit can set the tone of the customized commentary based on the user's play style. The customization unit sets the tone of the customized commentary based on the user's play style. The user's play style includes, for example, an offensive play style, a defensive play style, and the frequency of use of a particular character or weapon. The customization unit adjusts the tone of the customized commentary based on this data. For example, if the user has an offensive play style, the commentary can be performed in an energetic tone that matches that style. On the other hand, if the user has a defensive play style, the commentary can be performed in a calm tone that matches that style. Furthermore, if the user prefers to use a particular character or weapon, the commentary can be performed in a tone related to that character or weapon. Thus, by changing the tone of the customized commentary based on the user's play style, a more appropriate commentary can be provided. Some or all of the above-described processing in the customization unit may be performed, for example, using AI or without AI.

[0066] The customization unit can automatically edit the user's gameplay video using the customized commentary. The customization unit automatically edits the user's gameplay video using the customized commentary. The automatic editing includes, for example, an editing algorithm, editing criteria, and editing purpose. The customization unit automatically edits the user's gameplay video based on this data. For example, the customization unit can automatically edit a gameplay video including a customized commentary of a stage the user has cleared. The customization unit can also automatically edit a gameplay video including a customized commentary of a score the user has achieved. Furthermore, the customization unit can automatically edit a gameplay video including a customized commentary of a specific play style. This allows the user's gameplay video to be easily created by automatically editing the user's gameplay video using the customized commentary. Some or all of the above-described processing in the customization unit may be performed, for example, using AI or without AI.

[0067] The customization unit can automatically generate highlight scenes of the game using the customized commentary. The customization unit automatically generates highlight scenes of the game using the customized commentary. Highlight scenes include, for example, important events, specific actions, and user preferences. The customization unit automatically generates highlight scenes of the game based on this data. For example, the customization unit automatically generates highlight scenes of stages cleared by the user, including the customized commentary. The customization unit can also automatically generate highlight scenes of scores achieved by the user, including the customized commentary. Furthermore, the customization unit can automatically generate highlight scenes of a specific play style by the user, including the customized commentary. In this way, by automatically generating highlight scenes of the game using the customized commentary, the user can easily look back on important moments of their play. Some or all of the above-described processing in the customization unit may be performed, for example, using AI or without AI.

[0068] The customization unit can share the customized commentary with other users and collect feedback. The customization unit shares the customized commentary with other users and collects feedback. Feedback includes, for example, surveys, comments, and rating systems. The customization unit improves the commentary content based on this feedback. For example, a user can share a customized commentary of a stage they have cleared and receive feedback from other users. A user can also share a customized commentary of a score they have achieved and compete with other users. Furthermore, a user can share a customized commentary of a particular play style and receive feedback from other users. In this way, feedback can be obtained by sharing the customized commentary with other users. Some or all of the above-described processing in the customization unit may be performed, for example, using AI or without AI.

[0069] The customization unit can display the user's play history using the customized commentary. The customization unit displays the user's play history using the customized commentary. The play history includes, for example, play time, cleared stages, and scores. The customization unit visualizes the user's play history based on this data. For example, the customization unit displays the user's previously cleared stages and achieved scores in a graph along with the customized commentary. The customization unit can also visualize the user's play time and frequency along with the customized commentary to analyze play patterns. Furthermore, the frequency with which the user uses a particular character or weapon can be visualized along with the customized commentary. In this way, the user's play history can be visualized using the customized commentary, thereby analyzing the user's play patterns. Some or all of the above-described processing in the customization unit may be performed, for example, using AI or without AI.

[0070] The customization unit can use the customized commentary to send feedback to the game developer. The customization unit uses the customized commentary to send feedback to the game developer. Feedback includes, for example, bug reports, feature improvement suggestions, and user opinions. The customization unit uses this feedback to help improve the game. For example, the customization unit provides feedback regarding game balance adjustments based on the user's play data. New game features can also be proposed based on the user's play style. Furthermore, bugs and malfunctions can be reported based on the user's play data. In this way, providing feedback to the game developer using the customized commentary can help improve the game. Some or all of the above-described processing in the customization unit may be performed, for example, using AI or without AI.

[0071] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0072] The analysis unit can also provide strategic advice in the game based on the user's play style. For example, if the user has an offensive play style, the analysis unit can provide advice on when to defend and how to evade. If the user has a defensive play style, the analysis unit can provide advice on when to attack and how to effectively attack. Furthermore, the analysis unit can provide advice on how to best use a specific character or weapon when the user uses it. This can improve the user's game experience by providing strategic advice tailored to the user's play style.

[0073] The collection unit can not only accumulate the user's play data, but also have a function to compare it with the play data of other users. For example, it can compare the play data of other users who have cleared the same stage to analyze the strengths and weaknesses of the user's play style. It can also suggest new strategies to the user by referring to the strategies used by other users. Furthermore, it can set new goals worth challenging for the user based on the play data of other users. In this way, by comparing the play data of other users, the user's play style can be improved and the game experience can be enhanced.

[0074] The generation unit can also generate special commentary based on the user's play data to enhance the user's sense of accomplishment in the game. For example, when the user clears a stage with a specific level of difficulty, a commentary emphasizing the user's sense of accomplishment can be provided. Also, when the user achieves high scores consecutively, a commentary praising the user's success can be provided. Furthermore, when the user achieves a specific goal, a commentary celebrating the achievement of the goal can be provided. In this way, the user's gaming experience can be improved by providing a special commentary that enhances the user's sense of accomplishment.

[0075] The analysis unit can also provide in-game learning functions based on the user's play data. For example, if a user repeatedly fails at a particular stage, the analysis unit can analyze the cause and suggest areas for improvement. It can also provide tutorials for the user to learn new skills and strategies. Furthermore, it can analyze the factors behind success based on the user's past successful play styles and provide advice for reproducing them. In this way, by providing learning functions based on the user's play data, it is possible to support the user's skill improvement and improve the game experience.

[0076] The providing unit can also provide an in-game reward system based on the user's play data. For example, when the user achieves a specific goal, a special reward can be provided. Also, if the user continuously achieves high scores, a reward can be provided according to the continuity. Furthermore, if the user maintains a specific play style, a reward according to that style can be provided. In this way, by providing a reward system based on the user's play data, it is possible to increase the user's motivation and improve the game experience.

[0077] The processing flow of the first embodiment will be briefly explained below.

[0078] Step 1: The collection unit collects game video data or user controller input data. Game video data includes character movements, attack timing, enemy appearances, etc., while user controller input data includes button presses, stick movements, trigger operations, etc. The collection unit collects this data in real time and sends it to the analysis unit. Step 2: The analysis unit analyzes the data collected by the collection unit and estimates the current state of the game. Using AI, the analysis unit generates appropriate commentary content based on the game's progress and the user's play style. For example, if the user enters a boss battle, the analysis unit recognizes the situation and generates a tense commentary. Step 3: The generator generates a commentary based on the situation estimated by the analyzer. The generator uses AI to generate a customized commentary tailored to the user's play style. For example, if a user prefers to use a specific character, the generator generates a special commentary for that character. Step 4: The providing unit provides the commentary generated by the generating unit in real time. For example, when the user clears a difficult stage, the providing unit provides an encouraging commentary such as "Great play! Let's do our best on the next stage!"

[0079] (Example 2) An automated game commentary system according to an embodiment of the present invention collects game video data and user controller input data, and uses AI to estimate the current game situation and generate and provide commentary in real time. The automated game commentary system collects game video data and user controller input data while a user is playing a game, and the AI ​​generates appropriate commentary content based on the game's progress and the user's play style. For example, if a user is playing an action game, the system grasps the character's movements, attack timing, enemy appearance status, and so on. Next, based on the collected data, the system estimates the current game situation. For example, when a user enters a boss battle, the system recognizes the situation and generates a tense commentary. This estimation is performed by AI, and appropriate commentary content is generated based on the game's progress and the user's play style. Furthermore, the generated commentary content is provided to the user in real time. For example, when a user clears a difficult stage, an encouraging commentary such as "Great play! Let's do our best on the next stage!" is played. This allows users to experience the immersive experience of playing alone, as if they were playing with a commentator. The automated game commentary system can also accumulate user play data and provide commentary customized for each individual user. For example, if a user prefers to use a particular character, a special commentary for that character can be generated. This allows the user to become even more immersed in the game. This allows the automated game commentary system to improve the user's gaming experience. For example, when a user starts a new game, the system can provide advice and hints at the appropriate time, deepening the user's understanding of the game. Furthermore, even when a user is playing alone, the system can provide a sense of realism as if a commentator were playing the game. Furthermore, by accumulating user play data and providing commentary customized for each individual user, the user can become even more immersed in the game.

[0080] An automated game commentary system according to an embodiment includes a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects game video data or user controller input data. The game video data includes, for example, character movements, attack timing, and enemy appearance status. The user controller input data includes, for example, button presses, stick movements, and trigger operations. The collection unit collects this data in real time and transmits it to the analysis unit. The analysis unit analyzes the data collected by the collection unit to estimate the current game situation. The analysis unit generates appropriate commentary content based on the game progress and the user's play style, for example, using AI. For example, when a user enters a boss battle, the analysis unit recognizes the situation and generates a tense commentary. The generation unit generates a commentary based on the situation estimated by the analysis unit. For example, the generation unit generates a customized commentary tailored to the user's play style, using AI. For example, if a user prefers to use a specific character, the generation unit generates a special commentary for that character. The provision unit provides the commentary generated by the generation unit in real time. For example, when a user clears a difficult stage, the providing unit provides an encouraging commentary such as, "Great play! Let's do our best on the next stage!" This allows the automated game commentary system according to the embodiment to improve the user's gaming experience. For example, when a user starts a new game, the system can provide advice and hints at the appropriate time, deepening the user's understanding of the game. Furthermore, even when a user is playing alone, the system can provide a sense of realism as if a commentator were playing the game. Furthermore, by accumulating user play data and providing commentary customized for each individual user, the user can become even more immersed in the game.

[0081] The collection unit includes a storage unit that stores user play data. The storage unit stores the user play data. The user play data includes, for example, play time, operation history, and in-game actions. The storage unit stores this data over a long period of time and provides it to the analysis unit and generation unit. By storing the user play data, customization tailored to each individual user is possible. For example, if a user prefers to use a particular character, a special commentary about that character can be generated. Furthermore, the storage unit can analyze the user play data and grasp changes in the user's play style. For example, if a user changes from an offensive to a defensive play style, the change can be analyzed and appropriate commentary content can be provided. By storing the user play data, customization tailored to each individual user is possible, thereby improving the user's game experience.

[0082] The generation unit includes a customization unit that generates a customized commentary tailored to each individual user. The customization unit generates a customized commentary tailored to each individual user. The customized commentary reflects, for example, the user's play style, preferences, past play data, and the like. The customization unit generates commentary content optimal for the user based on this data. For example, if a user prefers to use a particular character, the customization unit generates a special commentary related to that character. The customization unit can also adjust the tone and content of the commentary according to the user's play style. For example, if the user has an aggressive play style, the customization unit can provide an energetic commentary tailored to that style. This allows for providing a customized commentary tailored to the user's play style and improving the user's gaming experience. Furthermore, the customization unit can analyze the user's play data and adjust the commentary content according to changes in the user's play style. For example, if the user changes from a defensive play style to an aggressive play style, the customization unit can provide a commentary that reflects that change. This allows for providing a customized commentary tailored to the user's play style and improving the user's gaming experience.

[0083] The analysis unit can generate specific commentary content according to the game progress and the user's play style. The analysis unit generates specific commentary content according to the game progress and the user's play style. The game progress includes, for example, the stage progress and the mission completion status. The user's play style includes, for example, attack type, defense type, exploration type, etc. The analysis unit generates commentary content optimal for the user based on this data. For example, when the user enters a boss battle, the analysis unit recognizes the situation and generates a tense commentary. Furthermore, when the user clears a difficult stage, the analysis unit generates an encouraging commentary such as, "Great play! Let's do our best in the next stage!" This makes it possible to provide commentary content appropriate for the game progress and the user's play style, thereby improving the user's gaming experience. Furthermore, the analysis unit can analyze the user's play data and adjust the commentary content according to changes in the user's play style. For example, if the user changes from a defensive play style to an offensive play style, a commentary that reflects the change is provided. This allows the user's gaming experience to be improved by providing commentary content appropriate for the user's play style.

[0084] The providing unit can provide a commentary that encourages the user when the user clears a difficult stage. The providing unit provides a commentary that encourages the user when the user clears a difficult stage. A difficult stage includes, for example, the strength of the enemy, the complexity of the stage, and the completion rate. The providing unit provides the user with optimal encouraging commentary based on this data. For example, when the user clears a difficult stage, the providing unit provides an encouraging commentary such as, "Great play! Let's do our best on the next stage!". This can increase the user's motivation by providing an encouraging commentary when the user clears a difficult stage. Furthermore, the providing unit can analyze the user's play data and adjust the commentary content according to the user's play style. For example, if the user changes from a defensive play style to an offensive play style, the providing unit provides a commentary that reflects that change. This can improve the user's game experience by providing appropriate commentary content according to the user's play style.

[0085] The providing unit can provide advice or hints to the user when the user starts a new game. The providing unit provides advice or hints to the user when the user starts a new game. The advice or hints include, for example, strategies, operation methods, and the like. The providing unit provides optimal advice or hints to the user based on this data. For example, when the user starts a new game, the providing unit can provide advice such as, "In this stage, it would be a good idea to first defeat the enemy before proceeding." This allows the user to deepen their understanding of the game by providing advice or hints when starting a new game. Furthermore, the providing unit can analyze the user's play data and adjust the advice or hints according to the user's play style. For example, if the user changes from a defensive play style to an offensive play style, the providing unit can provide advice or hints that reflect that change. This allows the user's game experience to be improved by providing appropriate advice or hints according to the user's play style.

[0086] The collection unit can estimate the user's emotions and select the type of data to collect based on the estimated user emotions. The collection unit estimates the user's emotions and selects the type of data to collect based on the estimated user emotions. User emotions include, for example, excitement, relaxation, and stress. The collection unit adjusts the type of data to collect based on these emotions. For example, when the user is excited, more detailed gameplay data is collected to improve the accuracy of the commentary. When the user is relaxed, only basic data is collected to reduce the load on the system. Furthermore, when the user is stressed, the collected data can be minimized to improve the system's response speed. Thus, by adjusting the type of data to be collected according to the user's emotions, appropriate data can be collected while reducing the load on the system. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI.

[0087] The collection unit can set a priority order for the data to be collected according to the type of game. The collection unit sets a priority order for the data to be collected according to the type of game. The types of games include, for example, action games, puzzle games, racing games, etc. The collection unit changes the priority order for the data to be collected according to the type of game. For example, in an action game, character movements and attack timings can be collected with priority. In addition, in a puzzle game, user input timing and answer patterns can be collected with priority. Furthermore, in a racing game, car speed and progress status on the course can be collected with priority. Thus, by changing the priority order for the data to be collected according to the type of game, more appropriate data can be collected. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0088] The collection unit can set the frequency of data collection based on the user's play style. The collection unit sets the frequency of data collection based on the user's play style. User play styles include, for example, an aggressive play style, a slow play style, and a specific play style. The collection unit adjusts the frequency of data collection according to these play styles. For example, if the user plays aggressively, the frequency of data collection is increased to perform detailed analysis. On the other hand, if the user plays slowly, the frequency of data collection can be reduced to reduce the load on the system. Furthermore, if the user has a specific play style, the frequency of data collection can be adjusted to match that style. In this way, by adjusting the frequency of data collection according to the user's play style, it is possible to collect appropriate data while reducing the load on the system. Some or all of the above-mentioned processing by the collection unit may be performed, for example, using AI or without AI.

[0089] The collection unit can combine multiple sensor data to improve the accuracy of the collected data. The collection unit combines multiple sensor data to improve the accuracy of the collected data. The sensor data includes, for example, game video data, controller input data, biometric data such as heart rate and body temperature, and in-game audio data. The collection unit integrates these sensor data to more accurately grasp the game situation. For example, the game video data and controller input data can be integrated to more accurately grasp the game situation. Furthermore, biometric data such as the user's heart rate and body temperature can be integrated to more accurately grasp the user's condition. Furthermore, in-game audio data and video data can be integrated to generate a more realistic commentary. In this way, by integrating multiple sensor data, the accuracy of the collected data can be improved. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI.

[0090] The collection unit can estimate the user's emotions and select collected data based on the estimated user emotions. The collection unit estimates the user's emotions and selects collected data based on the estimated user emotions. User emotions include, for example, excitement, relaxation, and stress. The collection unit filters collected data based on these emotions. For example, when the user is excited, only important data is collected, reducing the load on the system. When the user is relaxed, detailed data is collected, allowing for more accurate analysis. Furthermore, when the user is stressed, collected data can be minimized, improving the system's response speed. Thus, by filtering collected data according to the user's emotions, appropriate data can be collected while reducing the load on the system. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI.

[0091] The collection unit can analyze the collected data in real time and identify abnormal play actions. The collection unit analyzes the collected data in real time and identify abnormal play actions. Abnormal play actions include, for example, deviations from normal play patterns and error actions. The collection unit detects abnormal play actions based on this data. For example, if a user exhibits an input pattern that is different from normal, it can detect this as an abnormality. In addition, if an unexpected action occurs in the game, it can detect this as an abnormality. Furthermore, if a user exhibits abnormal behavior, such as repeatedly pressing a specific button, it can detect this as an abnormality. In this way, by analyzing the collected data in real time, abnormal play actions can be quickly detected. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without using AI.

[0092] The collection unit can store the collected data in a cloud so that it can be accessed from other devices. The collection unit can store the collected data in a cloud so that it can be accessed from other devices. Examples of cloud services include AWS, Google Cloud, and Azure. The collection unit uses these cloud services to store the collected data. For example, a user can use the data stored in the cloud when playing a game on a different device. The user can also access the cloud to refer to past play data. Furthermore, the user can use the data stored in the cloud to share data with friends. Storing the collected data in the cloud thus makes it accessible from other devices, improving convenience. Some or all of the above-described processing by the collection unit may be performed, for example, using AI or without AI.

[0093] The collection unit can display the user's play history using the collected data. The collection unit uses the collected data to display the user's play history. The play history includes, for example, play time, cleared stages, and scores. The collection unit visualizes the user's play history based on this data. For example, it displays the stages the user has previously cleared and the scores they have achieved in a graph. The collection unit can also visualize the user's play time and frequency to analyze their play patterns. Furthermore, it can visualize the frequency with which the user used a particular character or weapon. In this way, the user's play pattern can be analyzed by visualizing the user's play history using the collected data. Some or all of the above-described processing in the collection unit may be performed, for example, using AI or without AI.

[0094] The analysis unit can estimate the user's emotions and set an analysis algorithm based on the estimated user emotions. The analysis unit estimates the user's emotions and sets an analysis algorithm based on the estimated user emotions. User emotions include, for example, excitement, relaxation, and stress. The analysis unit adjusts the analysis algorithm based on these emotions. For example, if the user is excited, a quick analysis can be performed to provide a real-time commentary. On the other hand, if the user is relaxed, a detailed analysis can be performed to provide a highly accurate commentary. Furthermore, if the user is stressed, a concise analysis can be performed to improve the system's response speed. This allows for adjusting the analysis algorithm according to the user's emotions to provide more appropriate analysis results. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI.

[0095] The analysis unit can adjust the accuracy of the analysis according to the progress of the game. The analysis unit adjusts the accuracy of the analysis according to the progress of the game. The progress of the game includes, for example, the progress of the stage and the completion status of the mission. The analysis unit dynamically changes the accuracy of the analysis based on this data. For example, in important scenes such as boss battles, detailed analysis is performed to provide highly accurate commentary. Furthermore, during normal play, basic analysis is performed to reduce the load on the system. Furthermore, when the user advances to a new stage, detailed analysis can be performed to provide appropriate advice. In this way, by dynamically changing the accuracy of the analysis according to the progress of the game, it is possible to reduce the load on the system and provide appropriate analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0096] The analysis unit can learn the user's play style and improve the accuracy of the analysis results. The analysis unit can learn the user's play style and improve the accuracy of the analysis results. The user's play style includes, for example, an offensive play style, a defensive play style, and the frequency of use of a particular character or weapon. The analysis unit learns the user's play style based on this data and reflects it in the analysis results. For example, if the user has an offensive play style, the analysis unit can perform an analysis tailored to that style. Also, if the user has a defensive play style, the analysis unit can perform an analysis tailored to that style. Furthermore, if the user prefers to use a particular character or weapon, the analysis unit can learn that tendency and reflect it in the analysis results. In this way, by learning the user's play style, the accuracy of the analysis results can be improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0097] The analysis unit can predict the next game stage using the analysis results. The analysis unit predicts the next game stage using the analysis results. The next game stage includes, for example, the stage progress conditions and a prediction algorithm. The analysis unit predicts the next game stage based on this data. For example, the analysis unit predicts the difficulty level of the next stage based on the progress of the current stage. The analysis unit can also predict how to clear the next stage based on the user's play style. Furthermore, the analysis unit can predict the development of the next stage based on in-game events and enemy appearance patterns. Thus, by predicting the next game stage using the analysis results, appropriate advice can be provided to the user. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0098] The analysis unit can estimate the user's emotion and set a display method for the analysis results based on the estimated user's emotion. The analysis unit can estimate the user's emotion and set a display method for the analysis results based on the estimated user's emotion. User emotions include, for example, excitement, relaxation, and stress. The analysis unit adjusts the display method for the analysis results based on these emotions. For example, if the user is excited, a visually stimulating display method can be provided. If the user is relaxed, a calm display method can be provided. Furthermore, if the user is stressed, a simple and highly visible display method can be provided. This allows for adjusting the display method for the analysis results according to the user's emotion to provide a more appropriate display method. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI.

[0099] The analysis unit can share the analysis results with other users and collect feedback within the community. The analysis unit shares the analysis results with other users and collects feedback within the community. Feedback includes, for example, surveys, comments, and rating systems. The analysis unit improves the analysis results based on this feedback. For example, a user can share the analysis results of a stage they have cleared and receive advice from other users. A user can also share the analysis results of their achieved score and compete with other users. Furthermore, a user can share the analysis results of a specific play style and receive feedback from other users. By sharing the analysis results with other users, feedback within the community can be obtained. Some or all of the above-described processing by the analysis unit may be performed, for example, using AI or without AI.

[0100] The analysis unit can use the analysis results to suggest areas for improvement in the user's play style. The analysis unit can use the analysis results to suggest areas for improvement in the user's play style. The areas for improvement include, for example, analysis results of the play style and specific action plans. The analysis unit suggests optimal improvements for the user based on this data. For example, if the user has an offensive play style, the analysis unit can suggest improvements to the timing of defense. Also, if the user has a defensive play style, the analysis unit can suggest improvements to the timing of attacks. Furthermore, the analysis unit can suggest effective ways for the user to use specific characters or weapons. In this way, the analysis results can be used to suggest areas for improvement in the user's play style, thereby improving the user's play style. Some or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI or without AI.

[0101] The analysis unit can use the analysis results to send feedback to the game developer. The analysis unit uses the analysis results to send feedback to the game developer. Feedback includes, for example, bug reports, feature improvement suggestions, and user opinions. The analysis unit uses this feedback to help improve the game. For example, the analysis unit can provide feedback regarding game balance adjustments based on the user's play data. New game features can also be proposed based on the user's play style. Furthermore, bugs and malfunctions can be reported based on the user's play data. In this way, providing feedback to the game developer using the analysis results can help improve the game. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI.

[0102] The generation unit can estimate the user's emotion and set the tone of the commentary based on the estimated user's emotion. The generation unit can estimate the user's emotion and set the tone of the commentary based on the estimated user's emotion. User emotions include, for example, excitement, relaxation, and stress. The generation unit adjusts the tone of the commentary based on these emotions. For example, if the user is excited, the commentary can be performed in an energetic tone. On the other hand, if the user is relaxed, the commentary can be performed in a calm tone. Furthermore, if the user is stressed, the commentary can be performed in an encouraging tone. This allows the commentary tone to be adjusted according to the user's emotion, thereby providing a more appropriate commentary. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the generation unit can be performed, for example, using AI or without AI.

[0103] The generation unit can adjust the content of the commentary according to the progress of the game. The generation unit adjusts the content of the commentary according to the progress of the game. The progress of the game includes, for example, the progress of the stage and the completion status of the mission. The generation unit dynamically changes the content of the commentary based on this data. For example, during a boss battle, a tense commentary can be provided. During normal play, a relaxed commentary can be provided. Furthermore, when the user advances to a new stage, a commentary including advice and hints can be provided. This makes it possible to provide a more appropriate commentary by dynamically changing the content of the commentary according to the progress of the game. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI or without AI.

[0104] The generation unit can create a customized commentary based on the user's play style. The generation unit creates a customized commentary based on the user's play style. The customized commentary reflects, for example, the user's play style, preferences, past play data, etc. The generation unit generates commentary content optimal for the user based on this data. For example, if the user has an offensive play style, the generation unit can provide commentary tailored to that style. Also, if the user has a defensive play style, the generation unit can provide commentary tailored to that style. Furthermore, if the user prefers to use a particular character or weapon, the generation unit can provide commentary related to that character or weapon. In this way, by generating a commentary customized based on the user's play style, a more appropriate commentary can be provided. Some or all of the above-described processing by the generation unit may be performed using, for example, AI, or may be performed without using AI.

[0105] The generation unit can display the generated commentary in multiple languages. The generation unit displays the generated commentary in multiple languages. The multiple languages ​​include, for example, English, Japanese, and Spanish. The generation unit translates the generated commentary to support these languages. For example, a commentary generated in English can be translated into Japanese and provided. A commentary generated in Spanish can be translated into English and provided. Furthermore, a commentary generated in French can be translated into German and provided. In this way, by providing the generated commentary in multiple languages, it is possible to accommodate users who speak different languages. Some or all of the above-described processing in the generation unit may be performed, for example, using AI or without using AI.

[0106] The generation unit can estimate the user's emotions and set the length of the commentary based on the estimated user emotions. The generation unit can estimate the user's emotions and set the length of the commentary based on the estimated user emotions. User emotions include, for example, excitement, relaxation, and stress. The generation unit adjusts the length of the commentary based on these emotions. For example, if the user is excited, the commentary can be short and to the point. On the other hand, if the user is relaxed, the commentary can be longer and includes detailed explanations. Furthermore, if the user is stressed, the commentary can be concise and includes words of encouragement. This allows the commentary length to be adjusted according to the user's emotions, thereby providing a more appropriate commentary. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI.

[0107] The generation unit can share the generated commentary with other users and collect feedback. The generation unit shares the generated commentary with other users and collects feedback. Feedback includes, for example, surveys, comments, and rating systems. The generation unit improves the commentary content based on this feedback. For example, a user can share a commentary of a stage they have cleared and receive feedback from other users. A user can also share a commentary of a score they have achieved and compete with other users. Furthermore, a user can share a commentary of a specific play style and receive feedback from other users. In this way, feedback can be obtained by sharing the generated commentary with other users. Some or all of the above-described processing in the generation unit may be performed, for example, using AI or without using AI.

[0108] The generation unit can automatically edit the user's gameplay video using the generated commentary. The generation unit automatically edits the user's gameplay video using the generated commentary. The automatic editing includes, for example, an editing algorithm, editing criteria, and editing purpose. The generation unit automatically edits the user's gameplay video based on this data. For example, the generation unit can automatically edit a gameplay video that includes commentary of stages cleared by the user. The generation unit can also automatically edit a gameplay video that includes commentary of scores achieved by the user. Furthermore, the generation unit can automatically edit a gameplay video that includes commentary of a specific play style by the user. This allows the user's gameplay video to be easily created by automatically editing the user's gameplay video using the generated commentary. Some or all of the above-described processing by the generation unit may be performed, for example, using AI or without AI.

[0109] The generation unit can automatically generate highlight scenes of the game using the generated commentary. The generation unit automatically generates highlight scenes of the game using the generated commentary. Highlight scenes include, for example, important events, specific actions, and user preferences. The generation unit automatically generates highlight scenes of the game based on this data. For example, the generation unit automatically generates highlight scenes of stages cleared by the user. It can also automatically generate highlight scenes of scores achieved by the user. Furthermore, the generation unit can automatically generate highlight scenes of a specific play style by the user. In this way, by automatically generating highlight scenes of the game using the generated commentary, it is possible to easily look back on important moments of the user's play. Some or all of the above-mentioned processing by the generation unit may be performed, for example, using AI or without using AI.

[0110] The providing unit can estimate the user's emotions and set the timing of providing commentary based on the estimated user's emotions. The providing unit can estimate the user's emotions and set the timing of providing commentary based on the estimated user's emotions. User emotions include, for example, excitement, relaxation, and stress. The providing unit adjusts the timing of providing commentary based on these emotions. For example, if the user is excited, a commentary can be provided at an important moment. Also, if the user is relaxed, a commentary can be provided at an appropriate timing. Furthermore, if the user is stressed, a commentary including words of encouragement can be provided. This allows the timing of providing commentary to be adjusted according to the user's emotions, thereby providing commentary at a more appropriate timing. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI.

[0111] The providing unit can set a commentary provision method according to the progress of the game. The providing unit sets a commentary provision method according to the progress of the game. The progress of the game includes, for example, the stage progress and the mission completion status. The providing unit changes the commentary provision method based on this data. For example, during a boss battle, a tense commentary can be provided. Also, during normal play, a relaxed commentary can be provided. Furthermore, when the user advances to a new stage, a commentary including advice and hints can be provided. In this way, by changing the commentary provision method according to the progress of the game, a more appropriate commentary can be provided. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or without using AI.

[0112] The providing unit can display a commentary customized based on the user's play style. The providing unit displays a commentary customized based on the user's play style. The customized commentary reflects, for example, the user's play style, preferences, past play data, etc. The providing unit provides commentary content optimized for the user based on this data. For example, if the user has an offensive play style, the providing unit can provide commentary tailored to that style. Also, if the user has a defensive play style, the providing unit can provide commentary tailored to that style. Furthermore, if the user prefers to use a particular character or weapon, the providing unit can provide commentary related to that character or weapon. This allows for a more appropriate commentary to be provided by providing a commentary customized based on the user's play style. Some or all of the above-described processing by the providing unit may be performed, for example, using AI or without AI.

[0113] The providing unit can modify the provided commentary based on user feedback. The providing unit modifies the provided commentary based on user feedback. Feedback includes, for example, questionnaires, comments, rating systems, etc. The providing unit improves the commentary content based on this feedback. For example, a user provides feedback on the provided commentary, and the commentary is improved based on the content. Also, if a user prefers specific commentary content, that content can be provided preferentially. Furthermore, if a user is dissatisfied with the provided commentary, that content can be improved. In this way, by improving the provided commentary based on user feedback, a more appropriate commentary can be provided. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI.

[0114] The providing unit can estimate the user's emotions and set the frequency of providing commentary based on the estimated user's emotions. The providing unit can estimate the user's emotions and set the frequency of providing commentary based on the estimated user's emotions. User emotions include, for example, excitement, relaxation, and stress. The providing unit adjusts the frequency of providing commentary based on these emotions. For example, if the user is excited, the commentary can be provided frequently. Also, if the user is relaxed, the commentary can be provided at an appropriate frequency. Furthermore, if the user is stressed, the commentary can be provided with encouraging words. In this way, by adjusting the frequency of providing commentary according to the user's emotions, the commentary can be provided at a more appropriate frequency. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the providing unit can be performed, for example, using AI or without AI.

[0115] The providing unit can synchronize the provided commentary with other devices, enabling use across multiple devices. The providing unit synchronizes the provided commentary with other devices, enabling use across multiple devices. Multi-devices include, for example, smartphones, tablets, and PCs. The providing unit synchronizes the commentary between these devices. For example, if a user is playing on a smartphone, the commentary can also be synchronized with a tablet. Also, if a user is playing on a PC, the commentary can also be synchronized with a smartwatch. Furthermore, if a user uses multiple devices, the commentary can be synchronized with all devices. This enables use across multiple devices by synchronizing the provided commentary with other devices, improving convenience. Some or all of the above-described processing in the providing unit may be performed, for example, using AI or without AI.

[0116] The providing unit can automatically generate a gameplay video of the user using the provided commentary. The providing unit automatically generates a gameplay video of the user using the provided commentary. Automatic generation includes, for example, a generation algorithm, generation criteria, and generation purpose. The providing unit automatically generates a gameplay video of the user based on this data. For example, the providing unit can automatically generate a gameplay video including a commentary of stages cleared by the user. The providing unit can also automatically generate a gameplay video including a commentary of scores achieved by the user. Furthermore, the providing unit can automatically generate a gameplay video including a commentary of a specific play style by the user. This allows the user's gameplay video to be easily created by automatically generating the user's gameplay video using the provided commentary. Some or all of the above-described processing by the providing unit may be performed, for example, using AI or without AI.

[0117] The providing unit can display the user's play history using the provided commentary. The providing unit displays the user's play history using the provided commentary. The play history includes, for example, play time, cleared stages, and scores. The providing unit visualizes the user's play history based on this data. For example, it displays the stages the user has previously cleared and the scores they have achieved in a graph. The providing unit can also visualize the user's play time and frequency to analyze their play patterns. Furthermore, it can visualize the frequency with which the user has used a particular character or weapon. In this way, the user's play pattern can be analyzed by visualizing the user's play history using the provided commentary. Some or all of the above-described processing in the providing unit may be performed, for example, using AI or without AI.

[0118] The storage unit can estimate the user's emotions and select the type of stored data based on the estimated user emotions. The storage unit can estimate the user's emotions and select the type of stored data based on the estimated user emotions. User emotions include, for example, excitement, relaxation, and stress. The storage unit adjusts the type of stored data based on these emotions. For example, if the user is excited, detailed play data can be stored. Alternatively, if the user is relaxed, only basic data can be stored. Furthermore, if the user is stressed, only important data can be stored. By adjusting the type of stored data according to the user's emotions, more appropriate data can be stored. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the storage unit can be performed, for example, using AI or without AI.

[0119] The storage unit can analyze changes in the user's play style using the stored data. The storage unit can analyze changes in the user's play style using the stored data. Changes in play style include, for example, changes in play time and changes in behavior patterns. The storage unit evaluates changes in the user's play style based on this data. For example, if the user changes from an offensive play style to a defensive play style, the storage unit can analyze the change. Also, if the frequency with which the user uses a particular character or weapon changes, the storage unit can analyze the change. Furthermore, if the user's play time or frequency changes, the change can be analyzed. In this way, by analyzing changes in the user's play style using the stored data, changes in the user's play style can be understood. Some or all of the above-mentioned processing in the storage unit can be performed, for example, using AI or without AI.

[0120] The accumulation unit can evaluate the progress of the game using the accumulated data. The accumulation unit uses the accumulated data to evaluate the progress of the game. The progress of the game includes, for example, the progress of a stage and the completion status of a mission. The accumulation unit predicts the progress of the game based on this data. For example, the accumulation unit predicts the difficulty of the next stage based on the progress of the current stage. The accumulation unit can also predict how to clear the next stage based on the user's play style. Furthermore, the accumulation unit can predict the development of the next stage based on events and enemy appearance patterns in the game. In this way, by predicting the progress of the game using the accumulated data, it is possible to provide the user with appropriate advice. Some or all of the above-mentioned processing in the accumulation unit may be performed, for example, using AI or without using AI.

[0121] The storage unit can display the user's play history using the stored data. The storage unit uses the stored data to display the user's play history. The play history includes, for example, play time, cleared stages, and scores. The storage unit visualizes the user's play history based on this data. For example, it displays the stages the user has previously cleared and the scores they have achieved in a graph. It can also visualize the user's play time and frequency to analyze their play patterns. It can also visualize the frequency with which the user used a particular character or weapon. In this way, it is possible to analyze the user's play patterns by visualizing the user's play history using the stored data. Some or all of the above-described processing in the storage unit may be performed, for example, using AI or without AI.

[0122] The storage unit can estimate the user's emotions and select stored data based on the estimated user emotions. The storage unit estimates the user's emotions and selects stored data based on the estimated user emotions. User emotions include, for example, excitement, relaxation, and stress. The storage unit filters the stored data based on these emotions. For example, if the user is excited, only important data can be stored. On the other hand, if the user is relaxed, detailed data can be stored. Furthermore, if the user is stressed, only basic data can be stored. By filtering the stored data according to the user's emotions, appropriate data can be stored while reducing the load on the system. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the storage unit can be performed using, for example, AI, or without AI.

[0123] The storage unit can store the stored data in the cloud so that it can be accessed from other devices. The storage unit can store the stored data in the cloud so that it can be accessed from other devices. Examples of cloud services include AWS, Google Cloud, and Azure. The storage unit uses these cloud services to store the stored data. For example, a user can use the data stored in the cloud when playing a game on a different device. The user can also access the cloud to refer to past play data. Furthermore, the user can use the data stored in the cloud to share data with friends. Storing the stored data in the cloud thus makes it accessible from other devices, improving convenience. Some or all of the above-described processing in the storage unit may be performed, for example, using AI or without AI.

[0124] The accumulation unit can use the accumulated data to indicate areas for improvement in the user's play style. The accumulation unit can use the accumulated data to indicate areas for improvement in the user's play style. The areas for improvement include, for example, analysis results of the play style and specific action plans. The accumulation unit suggests optimal improvements for the user based on this data. For example, if the user has an offensive play style, the accumulation unit can suggest improvements to the timing of defense. Also, if the user has a defensive play style, the accumulation unit can suggest improvements to the timing of attacks. Furthermore, the accumulation unit can suggest effective ways for the user to use specific characters or weapons. In this way, the accumulation unit can suggest improvements to the user's play style using the accumulated data, thereby improving the user's play style. Some or all of the above-mentioned processing in the accumulation unit can be performed, for example, using AI or without AI.

[0125] The storage unit can use the stored data to send feedback to the game developer. The storage unit uses the stored data to send feedback to the game developer. Feedback includes, for example, bug reports, feature improvement suggestions, and user opinions. The storage unit uses this feedback to help improve the game. For example, the storage unit can provide feedback regarding game balance adjustments based on the user's play data. New game features can also be proposed based on the user's play style. Furthermore, bugs and malfunctions can be reported based on the user's play data. In this way, providing feedback to the game developer using the stored data can help improve the game. Some or all of the above-mentioned processing in the storage unit may be performed, for example, using AI or without using AI.

[0126] The customization unit can estimate the user's emotions and set the customized commentary content based on the estimated user emotions. The customization unit can estimate the user's emotions and set the customized commentary content based on the estimated user emotions. User emotions include, for example, excitement, relaxation, and stress. The customization unit adjusts the customized commentary content based on these emotions. For example, if the user is excited, an energetic commentary content can be provided. On the other hand, if the user is relaxed, a calm commentary content can be provided. Furthermore, if the user is stressed, a commentary content including encouraging words can be provided. This allows the customized commentary content to be adjusted according to the user's emotions, thereby providing a more appropriate commentary. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the customization unit can be performed, for example, using AI or without AI.

[0127] The customization unit can set the tone of the customized commentary based on the user's play style. The customization unit sets the tone of the customized commentary based on the user's play style. The user's play style includes, for example, an offensive play style, a defensive play style, and the frequency of use of a particular character or weapon. The customization unit adjusts the tone of the customized commentary based on this data. For example, if the user has an offensive play style, the commentary can be performed in an energetic tone that matches that style. On the other hand, if the user has a defensive play style, the commentary can be performed in a calm tone that matches that style. Furthermore, if the user prefers to use a particular character or weapon, the commentary can be performed in a tone related to that character or weapon. Thus, by changing the tone of the customized commentary based on the user's play style, a more appropriate commentary can be provided. Some or all of the above-described processing in the customization unit may be performed, for example, using AI or without AI.

[0128] The customization unit can automatically edit the user's gameplay video using the customized commentary. The customization unit automatically edits the user's gameplay video using the customized commentary. The automatic editing includes, for example, an editing algorithm, editing criteria, and editing purpose. The customization unit automatically edits the user's gameplay video based on this data. For example, the customization unit can automatically edit a gameplay video including a customized commentary of a stage the user has cleared. The customization unit can also automatically edit a gameplay video including a customized commentary of a score the user has achieved. Furthermore, the customization unit can automatically edit a gameplay video including a customized commentary of a specific play style. This allows the user's gameplay video to be easily created by automatically editing the user's gameplay video using the customized commentary. Some or all of the above-described processing in the customization unit may be performed, for example, using AI or without AI.

[0129] The customization unit can automatically generate highlight scenes of the game using the customized commentary. The customization unit automatically generates highlight scenes of the game using the customized commentary. Highlight scenes include, for example, important events, specific actions, and user preferences. The customization unit automatically generates highlight scenes of the game based on this data. For example, the customization unit automatically generates highlight scenes of stages cleared by the user, including the customized commentary. The customization unit can also automatically generate highlight scenes of scores achieved by the user, including the customized commentary. Furthermore, the customization unit can automatically generate highlight scenes of a specific play style by the user, including the customized commentary. In this way, by automatically generating highlight scenes of the game using the customized commentary, the user can easily look back on important moments of their play. Some or all of the above-described processing in the customization unit may be performed, for example, using AI or without AI.

[0130] The customization unit can estimate the user's emotions and set the frequency of providing customized commentary based on the estimated user emotions. The customization unit can estimate the user's emotions and set the frequency of providing customized commentary based on the estimated user emotions. User emotions include, for example, excitement, relaxation, and stress. The customization unit adjusts the frequency of providing customized commentary based on these emotions. For example, if the user is excited, the customized commentary can be provided frequently. On the other hand, if the user is relaxed, the customized commentary can be provided at an appropriate frequency. Furthermore, if the user is stressed, the customized commentary can be provided with words of encouragement. By adjusting the frequency of providing customized commentary according to the user's emotions, commentary can be provided at a more appropriate frequency. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the customization unit can be performed, for example, using AI or without AI.

[0131] The customization unit can share the customized commentary with other users and collect feedback. The customization unit shares the customized commentary with other users and collects feedback. Feedback includes, for example, surveys, comments, and rating systems. The customization unit improves the commentary content based on this feedback. For example, a user can share a customized commentary of a stage they have cleared and receive feedback from other users. A user can also share a customized commentary of a score they have achieved and compete with other users. Furthermore, a user can share a customized commentary of a particular play style and receive feedback from other users. In this way, feedback can be obtained by sharing the customized commentary with other users. Some or all of the above-described processing in the customization unit may be performed, for example, using AI or without AI.

[0132] The customization unit can display the user's play history using the customized commentary. The customization unit displays the user's play history using the customized commentary. The play history includes, for example, play time, cleared stages, and scores. The customization unit visualizes the user's play history based on this data. For example, the customization unit displays the user's previously cleared stages and achieved scores in a graph along with the customized commentary. The customization unit can also visualize the user's play time and frequency along with the customized commentary to analyze play patterns. Furthermore, the frequency with which the user uses a particular character or weapon can be visualized along with the customized commentary. In this way, the user's play history can be visualized using the customized commentary, thereby analyzing the user's play patterns. Some or all of the above-described processing in the customization unit may be performed, for example, using AI or without AI.

[0133] The customization unit can use the customized commentary to send feedback to the game developer. The customization unit uses the customized commentary to send feedback to the game developer. Feedback includes, for example, bug reports, feature improvement suggestions, and user opinions. The customization unit uses this feedback to help improve the game. For example, the customization unit provides feedback regarding game balance adjustments based on the user's play data. New game features can also be proposed based on the user's play style. Furthermore, bugs and malfunctions can be reported based on the user's play data. In this way, providing feedback to the game developer using the customized commentary can help improve the game. Some or all of the above-described processing in the customization unit may be performed, for example, using AI or without AI. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and provision unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects game video data and user controller input data using the camera 42 and microphone 38B of the smart device 14. The analysis unit, realized by the specific processing unit 290 of the data processing device 12, analyzes the collected data and estimates the current situation of the game. The generation unit, realized by the specific processing unit 290 of the data processing device 12, generates a commentary based on the estimated situation. The provision unit, realized by the control unit 46A of the smart device 14, provides the generated commentary to the user in real time. The accumulation unit accumulates user play data in the database 24 of the data processing device 12. The customization unit, realized by the specific processing unit 290 of the data processing device 12, generates a customized commentary tailored to each individual user. The emotion estimation function, realized by the specific processing unit 290 of the data processing device 12, estimates the user's emotion and selects the type of data to collect. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and provision unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects game video data and user controller input data using the camera 42 and microphone 238 of the smart glasses 214. The analysis unit, realized by the specific processing unit 290 of the data processing device 12, analyzes the collected data and estimates the current situation of the game. The generation unit, realized by the specific processing unit 290 of the data processing device 12, generates a commentary based on the estimated situation. The provision unit, realized by the control unit 46A of the smart glasses 214, provides the generated commentary to the user in real time. The accumulation unit accumulates the user's play data in the database 24 of the data processing device 12. The customization unit, realized by the specific processing unit 290 of the data processing device 12, generates a customized commentary tailored to each individual user. The emotion estimation function, realized by the specific processing unit 290 of the data processing device 12, estimates the user's emotion and selects the type of data to collect. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and provision unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit collects game video data and user controller input data using the camera 42 and microphone 238 of the headset-type terminal 314. The analysis unit, realized by the specific processing unit 290 of the data processing device 12, analyzes the collected data and estimates the current situation of the game. The generation unit, realized by the specific processing unit 290 of the data processing device 12, generates a commentary based on the estimated situation. The provision unit, realized by the control unit 46A of the headset-type terminal 314, provides the generated commentary to the user in real time. The accumulation unit accumulates user play data in the database 24 of the data processing device 12. The customization unit, realized by the specific processing unit 290 of the data processing device 12, generates a customized commentary tailored to each individual user. The emotion estimation function, realized by the specific processing unit 290 of the data processing device 12, estimates the user's emotion and selects the type of data to collect. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and provision unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects game video data and user controller input data using the camera 42 and microphone 238 of the robot 414. The analysis unit, realized by the specific processing unit 290 of the data processing device 12, analyzes the collected data and estimates the current situation of the game. The generation unit, realized by the specific processing unit 290 of the data processing device 12, generates a commentary based on the estimated situation. The provision unit, realized by the control unit 46A of the robot 414, provides the generated commentary to the user in real time. The accumulation unit accumulates the user's play data in the database 24 of the data processing device 12. The customization unit, realized by the specific processing unit 290 of the data processing device 12, generates a customized commentary tailored to each individual user. The emotion estimation function, realized by the specific processing unit 290 of the data processing device 12, estimates the user's emotion and selects the type of data to collect.

[0134] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0135] The analysis unit can also provide strategic advice in the game based on the user's play style. For example, if the user has an offensive play style, the analysis unit can provide advice on when to defend and how to evade. If the user has a defensive play style, the analysis unit can provide advice on when to attack and how to effectively attack. Furthermore, the analysis unit can provide advice on how to best use a specific character or weapon when the user uses it. This can improve the user's game experience by providing strategic advice tailored to the user's play style.

[0136] The collection unit can not only accumulate the user's play data, but also have a function to compare it with the play data of other users. For example, it can compare the play data of other users who have cleared the same stage to analyze the strengths and weaknesses of the user's play style. It can also suggest new strategies to the user by referring to the strategies used by other users. Furthermore, it can set new goals worth challenging for the user based on the play data of other users. In this way, by comparing the play data of other users, the user's play style can be improved and the game experience can be enhanced.

[0137] The generation unit can also generate special commentary based on the user's play data to enhance the user's sense of accomplishment in the game. For example, when the user clears a stage with a specific level of difficulty, a commentary emphasizing the user's sense of accomplishment can be provided. Also, when the user achieves high scores consecutively, a commentary praising the user's success can be provided. Furthermore, when the user achieves a specific goal, a commentary celebrating the achievement of the goal can be provided. In this way, the user's gaming experience can be improved by providing a special commentary that enhances the user's sense of accomplishment.

[0138] The analysis unit can also provide in-game learning functions based on the user's play data. For example, if a user repeatedly fails at a particular stage, the analysis unit can analyze the cause and suggest areas for improvement. It can also provide tutorials for the user to learn new skills and strategies. Furthermore, it can analyze the factors behind success based on the user's past successful play styles and provide advice for reproducing them. In this way, by providing learning functions based on the user's play data, it is possible to support the user's skill improvement and improve the game experience.

[0139] The providing unit can also provide an in-game reward system based on the user's play data. For example, when the user achieves a specific goal, a special reward can be provided. Also, if the user continuously achieves high scores, a reward can be provided according to the continuity. Furthermore, if the user maintains a specific play style, a reward according to that style can be provided. In this way, by providing a reward system based on the user's play data, it is possible to increase the user's motivation and improve the game experience.

[0140] The collection unit can estimate the user's emotions and adjust the in-game music and sound effects based on the estimated emotions. For example, if the user is excited, energetic music can be played. If the user is relaxed, calming music can be played. Furthermore, if the user is stressed, music with a relaxing effect can be played. In this way, by adjusting the in-game music and sound effects according to the user's emotions, a more appropriate gaming experience can be provided.

[0141] The analysis unit can estimate the user's emotions and dynamically adjust the in-game difficulty level based on the estimated emotions. For example, if the user is excited, the difficulty level can be increased to provide a challenging gameplay. If the user is relaxed, the difficulty level can be decreased to provide a relaxed gameplay. Furthermore, if the user is stressed, the difficulty level can be adjusted to reduce stress. In this way, a more appropriate game experience can be provided by dynamically adjusting the in-game difficulty level according to the user's emotions.

[0142] The generation unit can estimate the user's emotions and adjust the dialogue of the in-game character based on the estimated emotions. For example, if the user is excited, the character can speak energetic dialogue. If the user is relaxed, the character can speak calm dialogue. Furthermore, if the user is stressed, the character can speak encouraging dialogue. In this way, by adjusting the dialogue of the in-game character according to the user's emotions, a more appropriate gaming experience can be provided.

[0143] The providing unit can estimate the user's emotions and adjust in-game visual effects based on the estimated emotions. For example, if the user is excited, the visual effects can be enhanced. If the user is relaxed, the visual effects can be toned down. Furthermore, if the user is feeling stressed, the visual effects can be changed to have a relaxing effect. In this way, by adjusting the in-game visual effects according to the user's emotions, a more appropriate gaming experience can be provided.

[0144] The collection unit can estimate the user's emotions and customize the in-game interface based on the estimated emotions. For example, if the user is excited, the interface can be simplified to make it easier to operate. Alternatively, if the user is relaxed, the interface can be made more detailed to provide more information. Furthermore, if the user is stressed, the interface can be made more intuitive to reduce the burden of operation. In this way, a more appropriate game experience can be provided by customizing the in-game interface according to the user's emotions.

[0145] The processing flow of the second embodiment will be briefly explained below.

[0146] Step 1: The collection unit collects game video data or user controller input data. Game video data includes character movements, attack timing, enemy appearances, etc., while user controller input data includes button presses, stick movements, trigger operations, etc. The collection unit collects this data in real time and sends it to the analysis unit. Step 2: The analysis unit analyzes the data collected by the collection unit and estimates the current state of the game. Using AI, the analysis unit generates appropriate commentary content based on the game's progress and the user's play style. For example, if the user enters a boss battle, the analysis unit recognizes the situation and generates a tense commentary. Step 3: The generator generates a commentary based on the situation estimated by the analyzer. The generator uses AI to generate a customized commentary tailored to the user's play style. For example, if a user prefers to use a specific character, the generator generates a special commentary for that character. Step 4: The providing unit provides the commentary generated by the generating unit in real time. For example, when the user clears a difficult stage, the providing unit provides an encouraging commentary such as "Great play! Let's do our best on the next stage!"

[0147] 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.

[0148] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<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.

[0149] 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.

[0150] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0151] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0152] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0161] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0162] 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.

[0163] 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.

[0164] 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 AI 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.

[0165] 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.

[0166] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0167] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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).

[0173] 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.

[0174] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0175] 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.

[0176] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0177] 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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0178] 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.

[0179] 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.

[0180] 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 AI 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.

[0181] 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.

[0182] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0183] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0184] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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).

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0194] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. 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 the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0195] 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.

[0196] 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.

[0197] 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 AI 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.

[0198] 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.

[0199] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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).

[0204] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0205] 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."

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] [Explanation of symbols]

[0219] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects game video data or user controller input data; an analysis unit that analyzes the data collected by the collection unit and estimates a current situation of the game; a generation unit that generates a commentary based on the situation estimated by the analysis unit; a providing unit that provides the commentary generated by the generating unit in real time. A system characterized by:

2. The collecting unit Equipped with a storage unit that stores user play data 2. The system of claim 1.

3. The generation unit Equipped with a customization section that generates customized commentary for each individual user 2. The system of claim 1.

4. The analysis unit Generate specific commentary content according to the game progress and the user's play style 2. The system of claim 1.

5. The providing unit Providing commentary to encourage users when they clear a difficult stage 2. The system of claim 1.

6. The providing unit Providing advice or tips when users start a new game 2. The system of claim 1.

7. The collecting unit Inferring user emotions and selecting the type of data to collect based on the estimated user emotions 2. The system of claim 1.

8. The collecting unit Prioritize data collection based on game type 2. The system of claim 1.

9. The collecting unit Set the frequency of data collection based on your play style 2. The system of claim 1.

10. The collecting unit Combining multiple sensor data to improve the accuracy of collected data 2. The system of claim 1.

Images