System

Abstract

An object of a system according to an embodiment is to provide a play-by-play commentary specialized in user's prediction in real time.SOLUTION: A system includes a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit receives information on the prediction from the user. The analysis unit analyzes the recommendation video on the basis of the information received by the reception unit. The generation unit generates a play-by-play commentary with an emotion based on the information analyzed 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] With conventional technology, it is difficult to provide real-time commentary specific to a user's favorite, and there is room for improvement.

[0005] The system according to the embodiment aims to provide real-time commentary that is specific to the user's favorite. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit receives information about a favorite person from a user. The analysis unit analyzes video of the favorite person based on the information received by the reception unit. The generation unit generates an emotional commentary based on the information analyzed 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 real-time commentary that is specific to the user's favorite. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention generates and supports live commentary in real time, focusing on a user's favorite idol. This system allows users to input information about their favorite idol, analyze video of the idol using the LLM's image recognition and interpretation functions, and generate commentary using an emotional voice synthesis function. It is also possible to create clipped videos and subtitles of the favorite idol based on the generated commentary. This allows the system to generate and support live commentary in real time, focusing on a user's favorite idol. For example, a user can input the name of a specific idol or athlete, and the system analyzes video of the favorite idol based on that information and generates an emotional commentary. Furthermore, based on the generated commentary, it can create a video by clipping highlight scenes of the favorite idol, or display the commentary as subtitles. This allows users to enjoy live commentary focusing on their favorite idol, making their favorite idol activities more fulfilling.

[0029] The cheering system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit receives information about a favorite person from a user. The reception unit receives input from the user of the name, image, and video link of the favorite person. For example, the user can input the name of a specific idol or athlete. The analysis unit analyzes video of the favorite person based on the information received by the reception unit. For example, it analyzes live video or game video to recognize the favorite person's movements and facial expressions. The generation unit generates an emotional commentary based on the information analyzed by the analysis unit. For example, it generates an emotional commentary at the moment the favorite person scores a goal or performs a specific performance. The provision unit provides the commentary generated by the generation unit in real time. For example, it can create clipped videos and subtitles of the favorite person based on the generated commentary content. As a result, the cheering system according to the embodiment can generate commentary centered on the user's favorite person in real time and cheer on the user.

[0030] The reception unit can accept the user's input of the name, image, and video link of their favorite idol. The name, image, and video link of their favorite idol can be in text format, image format, URL format, and the like, but are not limited to these examples. For example, the reception unit can accept the user's input of the name of a specific idol or athlete in text format. The reception unit can also accept the user's upload of an image of their favorite idol in image format. Furthermore, the reception unit can also accept the user's input of a link to a video of their favorite idol in URL format. This allows the user to easily input information about their favorite idol.

[0031] The analysis unit can analyze live video or game video to recognize the movements and facial expressions of the favorite player. Examples of live video or game video include, but are not limited to, video of a sports game or a live concert. The analysis unit can, for example, analyze live video to recognize the movements of the favorite player. For example, the analysis unit can analyze the movements of the favorite player as they move on stage. The analysis unit can also analyze game video to recognize the facial expressions of the favorite player. For example, the analysis unit can analyze the facial expressions of the favorite player at the moment they score a goal. Furthermore, the analysis unit can analyze live video or game video to comprehensively recognize the movements and facial expressions of the favorite player. For example, the analysis unit can simultaneously analyze the movements and facial expressions of the favorite player to grasp the situation of the favorite player in detail. This allows the movement and facial expressions of the favorite player to be accurately recognized.

[0032] The generation unit can generate emotional commentary the moment the favorite idol scores a goal or performs a specific performance. Examples of moments when a goal is scored or a specific performance include, but are not limited to, a goal scene or a dance performance. The generation unit generates emotional commentary the moment the favorite idol scores a goal. For example, the generation unit can generate emotional commentary such as "What a great goal!" the moment the favorite idol scores a goal. The generation unit can also generate emotional commentary the moment the favorite idol performs a specific performance. For example, the generation unit can generate emotional commentary such as "What a great dance!" the moment the favorite idol performs a dance performance. The generation unit can also generate emotional commentary based on the favorite idol's movements and facial expressions. For example, the generation unit can generate emotional commentary such as "What a beautiful smile!" the moment the favorite idol smiles. This generates emotional commentary, which can increase the user's excitement.

[0033] The providing unit can create clipped videos and subtitles of the favorite idol based on the generated commentary content. The clipped videos and subtitles include, for example, the length of the video and the content of the subtitles, but are not limited to these examples. For example, the providing unit can create a video by clipping highlight scenes of the favorite idol based on the generated commentary content. For example, the providing unit can create a video by clipping the moment the favorite idol scores a goal or performs a particular performance. The providing unit can also create subtitles based on the generated commentary content. For example, the providing unit can display the commentary content as subtitles and provide them to the user. Furthermore, the providing unit can combine clipped videos and subtitles of the favorite idol based on the generated commentary content and provide them. For example, the providing unit can add subtitles to a clipped video of the favorite idol's highlight scenes and provide it. In this way, creating clipped videos and subtitles of the favorite idol can support the user's activities.

[0034] The reception unit can analyze the user's past input history and suggest the optimal input method. For example, the reception unit automatically displays names and images of favorite characters that the user has frequently input in the past as candidates. For example, the reception unit displays names of favorite characters that the user has input in the past as candidates, allowing the user to quickly select one. The reception unit can also preferentially suggest input methods (voice, text, etc.) that the user has used in the past. For example, if the user has used voice input in the past, the reception unit preferentially displays the voice input option. Furthermore, the reception unit can predict and suggest information about favorite characters related to a specific event or time period based on the user's past input history. For example, the reception unit suggests information about favorite characters related to a similar event period based on information about favorite characters that the user has input in the past around a specific event period. This allows the optimal input method to be suggested based on the user's past input history.

[0035] When inputting information about a favorite person, the reception unit can present recommended favorite person candidates based on the user's current interests and trends. The reception unit presents related recommended favorite person candidates based on, for example, topics and trends recently searched by the user. For example, the reception unit presents recommended favorite person candidates related to idols or athletes recently searched by the user. The reception unit can also present recommended favorite person candidates based on accounts and hashtags the user follows on social media. For example, the reception unit presents recommended favorite person candidates related to accounts the user follows. Furthermore, the reception unit can present related recommended favorite person candidates based on videos or articles recently viewed by the user. For example, the reception unit presents recommended favorite person candidates related to videos recently viewed by the user. This makes it possible to present recommended favorite person candidates based on the user's interests and trends.

[0036] When inputting information about a favorite person, the reception unit can select the optimal input means depending on the user's input method. For example, if the user selects voice input, the reception unit uses voice recognition technology to input the name and information of the favorite person. For example, if the user selects voice input, the reception unit can input the name of the favorite person using voice recognition software. Furthermore, if the user selects text input, the reception unit can provide an input completion function to enable the favorite person to be quickly input. For example, if the user selects text input, the reception unit can use the input completion function to enable the favorite person to be quickly input. Furthermore, if the user selects image input, the reception unit can automatically extract information about the favorite person using image recognition technology. For example, if the user selects image input, the reception unit can extract information from an image of the favorite person using image recognition technology. This makes it possible to provide the optimal input means depending on the user's input method.

[0037] When inputting information about a favorite idol, the reception unit can present highly relevant favorite idol candidates based on the user's geographical location information. The reception unit, for example, presents candidate favorite idols who will be appearing at events or live shows near the user's current location. For example, the reception unit presents candidate favorite idols who will be appearing at live shows or events held near the user's current location. The reception unit can also present candidate favorite idols related to places the user has visited in the past. For example, the reception unit presents candidate favorite idols who are active in places the user has visited in the past. The reception unit can also present candidate favorite idols related to the weather or season of the user's current location. For example, the reception unit presents candidate favorite idols who will be appearing at events related to the weather or season of the user's current location. In this way, highly relevant favorite idol candidates can be presented based on the user's geographical location information.

[0038] When inputting information about a favorite person, the reception unit can analyze the user's social media activity and automatically complete the related information about the favorite person. For example, the reception unit automatically completes information about the favorite person related to accounts the user follows on social media. For example, the reception unit can automatically complete information about the favorite person related to accounts the user follows. The reception unit can also automatically complete information about the favorite person related to hashtags the user uses on social media. For example, the reception unit automatically completes information about the favorite person related to hashtags used by the user. Furthermore, the reception unit can automatically complete information about the favorite person related to content the user shared on social media. For example, the reception unit automatically completes information about the favorite person related to content shared by the user. This makes it possible to automatically complete information about the favorite person based on the user's social media activity.

[0039] The reception unit can customize the input method by reflecting the user's past feedback when inputting information about a favorite person. For example, the reception unit preferentially suggests input methods that the user has used in the past. For example, the reception unit preferentially displays input methods that the user has used in the past. The reception unit can also improve the input interface based on feedback provided by the user in the past. For example, the reception unit improves the input interface based on feedback provided by the user in the past. Furthermore, the reception unit can also simplify the input procedure by referring to information input by the user in the past. For example, the reception unit simplifies the input procedure based on information input by the user in the past. This makes it possible to customize the input method based on the user's past feedback.

[0040] When analyzing the video, the analysis unit can track the movements and facial expressions of the favorite idol in real time and update the analysis results. For example, the analysis unit tracks the movements of the favorite idol in real time as they move on stage and updates the analysis results. For example, the analysis unit tracks the movements of the favorite idol as they move on stage in real time and updates the analysis results. The analysis unit can also analyze the facial expressions of the favorite idol in real time the moment they change their facial expressions and update the results. For example, the analysis unit analyzes the facial expressions of the favorite idol in real time the moment they smile and updates the results. The analysis unit can also analyze the movements and facial expressions of the favorite idol in real time when they perform a specific performance and update the results. For example, the analysis unit analyzes the movements and facial expressions of the favorite idol in real time the moment they perform a dance performance and updates the results. In this way, the movements and facial expressions of the favorite idol can be tracked in real time and the analysis results can be updated.

[0041] When analyzing the video, the analysis unit can improve the accuracy of the analysis by referring to the idol's past performance data. For example, the analysis unit can improve the accuracy of analysis of the idol's current performance by referring to past live video of the idol. For example, the analysis unit can improve the accuracy of analysis of the idol's current performance by referring to past live video of the idol. The analysis unit can also improve the accuracy of analysis of the idol's current movements and facial expressions by referring to video of the idol's past matches. For example, the analysis unit can improve the accuracy of analysis of the idol's current movements and facial expressions by referring to video of the idol's past matches. Furthermore, the analysis unit can improve the accuracy of analysis of the idol's current performance by referring to video of the idol's past events. For example, the analysis unit can improve the accuracy of analysis of the idol's current performance by referring to video of the idol's past events. In this way, the accuracy of analysis can be improved by referring to the idol's past performance data.

[0042] When analyzing the video, the analysis unit can complement the analysis results based on the idol's costume or background information. For example, if the idol is wearing a specific costume, the analysis unit complements the analysis results by taking into account the characteristics of the costume. For example, if the idol is wearing a specific costume, the analysis unit complements the analysis results by taking into account the characteristics of the costume. Furthermore, if the idol is performing against a specific background, the analysis unit can complement the analysis results by taking into account the background information. For example, if the idol is performing against a specific background, the analysis unit complements the analysis results by taking into account the background information. Furthermore, if the idol is performing at a specific event, the analysis unit can complement the analysis results by taking into account the characteristics of the event. For example, if the idol is performing at a specific event, the analysis unit complements the analysis results by taking into account the characteristics of the event. In this way, the analysis results can be complemented by taking into account the idol's costume and background information.

[0043] When analyzing the video, the analysis unit can take into account the geographical range of activity of the favorite idol. For example, if the favorite idol is active in a specific region, the analysis unit can take into account the characteristics of that region when analyzing. For example, if the favorite idol is active in a specific region, the analysis unit can take into account the characteristics of that region when analyzing. Furthermore, if the favorite idol is active in multiple regions, the analysis unit can take into account the characteristics of each region when analyzing. For example, if the favorite idol is active in multiple regions, the analysis unit can take into account the characteristics of each region when analyzing. Furthermore, if the favorite idol is active internationally, the analysis unit can take into account the characteristics of each country when analyzing. For example, if the favorite idol is active internationally, the analysis unit can take into account the characteristics of each country when analyzing. This makes it possible to perform an analysis taking into account the geographical range of activity of the favorite idol.

[0044] When analyzing the video, the analysis unit can improve the accuracy of the analysis by referring to literature and media information related to the favorite idol. For example, the analysis unit can improve the accuracy of the analysis by referring to literature related to the favorite idol. For example, the analysis unit can improve the accuracy of the analysis by referring to literature related to the favorite idol. The analysis unit can also improve the accuracy of the analysis by referring to media information related to the favorite idol. For example, the analysis unit can improve the accuracy of the analysis by referring to media information related to the favorite idol. The analysis unit can also improve the accuracy of the analysis by referring to past interviews and articles related to the favorite idol. For example, the analysis unit can improve the accuracy of the analysis by referring to past interviews and articles related to the favorite idol. In this way, the accuracy of the analysis can be improved by referring to literature and media information related to the favorite idol.

[0045] When analyzing the video, the analysis unit can perform analysis based on the market value or popularity of the favorite idol. For example, the analysis unit takes into account the market value of the favorite idol to supplement the analysis results. For example, the analysis unit takes into account the market value of the favorite idol to supplement the analysis results. The analysis unit can also take into account the popularity of the favorite idol to supplement the analysis results. For example, the analysis unit takes into account the popularity of the favorite idol to supplement the analysis results. Furthermore, the analysis unit can also take into account the characteristics of the favorite idol's fan base to supplement the analysis results. For example, the analysis unit takes into account the characteristics of the favorite idol's fan base to supplement the analysis results. This makes it possible to perform analysis taking into account the market value and popularity of the favorite idol.

[0046] When generating the commentary, the generation unit can adjust the level of detail of the commentary depending on important moments of the favorite player. For example, the generation unit generates a detailed commentary the moment the favorite player scores a goal. For example, the generation unit generates a detailed commentary the moment the favorite player scores a goal. The generation unit can also generate a detailed commentary the moment the favorite player performs a specific performance. For example, the generation unit generates a detailed commentary the moment the favorite player performs a specific performance. The generation unit can also generate a detailed commentary the moment the favorite player is being interviewed. For example, the generation unit generates a detailed commentary the moment the favorite player is being interviewed. This makes it possible to provide a detailed commentary that corresponds to important moments of the favorite player.

[0047] When generating commentary, the generation unit can apply different commentary algorithms depending on the category of the favorite. For example, if the favorite is an athlete, the generation unit applies a sports commentary algorithm. For example, if the favorite is an athlete, the generation unit applies a sports commentary algorithm. Furthermore, if the favorite is an idol, the generation unit can also apply an entertainment commentary algorithm. For example, if the favorite is an idol, the generation unit applies an entertainment commentary algorithm. Furthermore, if the favorite is an actor, the generation unit can also apply a movie or drama commentary algorithm. For example, if the favorite is an actor, the generation unit applies a movie or drama commentary algorithm. This makes it possible to provide the optimal commentary algorithm depending on the category of the favorite.

[0048] When generating a commentary, the generation unit can improve the accuracy of the commentary by referring to the user's past commentary results. The generation unit can improve the accuracy of the commentary by referring to, for example, a commentary style that the user previously preferred. For example, the generation unit can improve the accuracy of the commentary by referring to the commentary style that the user previously preferred. The generation unit can also improve the accuracy of the commentary based on feedback that the user previously provided. For example, the generation unit can improve the accuracy of the commentary based on feedback that the user previously provided. Furthermore, the generation unit can analyze the content of commentaries that the user previously viewed and generate an optimal commentary. For example, the generation unit can analyze the content of commentaries that the user previously viewed and generate an optimal commentary. This can improve the accuracy of the commentary by referring to the user's past commentary results.

[0049] When generating the commentary, the generation unit can determine the priority of the commentary based on the period of the favorite idol's activities. The generation unit, for example, determines the priority of the commentary based on the events and live performances that the favorite idol is currently participating in. For example, the generation unit determines the priority of the commentary based on the events and live performances that the favorite idol is currently participating in. The generation unit can also determine the priority of the commentary based on important events and live performances that the favorite idol has held in the past. For example, the generation unit determines the priority of the commentary based on important events and live performances that the favorite idol has held in the past. The generation unit can also determine the priority of the commentary based on events and live performances that the favorite idol has scheduled in the future. For example, the generation unit determines the priority of the commentary based on the events and live performances that the favorite idol has scheduled in the future. In this way, the priority of the commentary can be determined based on the period of the favorite idol's activities.

[0050] When generating commentary, the generation unit can adjust the order of the commentary based on the relevance of the favorite idol. The generation unit, for example, adjusts the order of the commentary based on programs and events in which the favorite idol is currently appearing. For example, the generation unit adjusts the order of the commentary based on programs and events in which the favorite idol is currently appearing. The generation unit can also adjust the order of the commentary based on programs and events in which the favorite idol has previously appeared. For example, the generation unit adjusts the order of the commentary based on programs and events in which the favorite idol has previously appeared. The generation unit can also adjust the order of the commentary based on programs and events in which the favorite idol is scheduled to appear in the future. For example, the generation unit adjusts the order of the commentary based on programs and events in which the favorite idol is scheduled to appear in the future. In this way, the order of the commentary can be adjusted based on the relevance of the favorite idol.

[0051] When generating a commentary, the generation unit can adjust the use of technical terms in the commentary according to the user's level of expertise. For example, if the user is a beginner, the generation unit generates a commentary that is easy to understand by avoiding technical terms. For example, if the user is a beginner, the generation unit generates a commentary that is easy to understand by avoiding technical terms. Furthermore, if the user is an intermediate player, the generation unit can generate a commentary that uses technical terms moderately. For example, if the user is an intermediate player, the generation unit generates a commentary that uses technical terms moderately. Furthermore, if the user is an advanced player, the generation unit can generate a detailed commentary that uses a lot of technical terms. For example, if the user is an advanced player, the generation unit generates a detailed commentary that uses a lot of technical terms. This makes it possible to provide an optimal commentary according to the user's level of expertise.

[0052] When providing live commentary, the providing unit can select the optimal providing method by referring to the user's past viewing history. The providing unit selects the optimal providing method, for example, by referring to the live commentary style that the user preferred in the past. For example, the providing unit selects the optimal providing method by referring to the live commentary style that the user preferred in the past. The providing unit can also select the optimal providing method based on feedback that the user provided in the past. For example, the providing unit selects the optimal providing method based on feedback that the user provided in the past. Furthermore, the providing unit can also analyze the content of live commentary that the user viewed in the past and select the optimal providing method. For example, the providing unit analyzes the content of live commentary that the user viewed in the past and selects the optimal providing method. In this way, the optimal providing method can be selected based on the user's past viewing history.

[0053] When providing commentary, the providing unit can customize the content to be provided according to the user's current viewing environment. For example, if the user is viewing on a smartphone, the providing unit provides commentary optimized for the screen size. For example, if the user is viewing on a smartphone, the providing unit provides commentary optimized for the screen size. Furthermore, if the user is viewing on a tablet, the providing unit can also provide commentary optimized for a large screen. For example, if the user is viewing on a tablet, the providing unit provides commentary optimized for a large screen. Furthermore, the providing unit can also provide commentary in high resolution if the user is viewing on a smart TV. For example, if the user is viewing on a smart TV, the providing unit provides commentary in high resolution. This makes it possible to provide content optimal for the user's viewing environment.

[0054] The providing unit can improve the commentary providing method by reflecting user feedback when providing commentary. The providing unit improves the commentary providing method based on, for example, feedback provided by the user. For example, the providing unit improves the commentary providing method based on feedback provided by the user. The providing unit can also analyze feedback provided by the user in the past and select an optimal providing method. For example, the providing unit analyzes feedback provided by the user in the past and selects an optimal providing method. Furthermore, the providing unit can adjust the commentary providing method by reflecting feedback provided by the user in real time. For example, the providing unit adjusts the commentary providing method by reflecting feedback provided by the user in real time. This makes it possible to improve the commentary providing method based on user feedback.

[0055] When providing commentary, the providing unit can select an appropriate providing method based on the user's geographical location information. For example, the providing unit prioritizes providing commentary of events or live shows close to the user's current location. For example, the providing unit prioritizes providing commentary of events or live shows close to the user's current location. The providing unit can also prioritize providing commentary related to places the user has visited in the past. For example, the providing unit prioritizes providing commentary related to places the user has visited in the past. Furthermore, the providing unit can also prioritize providing commentary related to the weather or season of the user's current location. For example, the providing unit prioritizes providing commentary related to the weather or season of the user's current location. This makes it possible to select an optimal providing method based on the user's geographical location information.

[0056] When providing commentary, the providing unit can analyze the user's social media activity and customize the content to be provided. The providing unit, for example, provides commentary related to accounts the user follows on social media. For example, the providing unit provides commentary related to accounts the user follows on social media. The providing unit can also provide commentary related to hashtags the user uses on social media. For example, the providing unit provides commentary related to hashtags the user uses on social media. The providing unit can also provide commentary related to content the user shared on social media. For example, the providing unit provides commentary related to content the user shared on social media. This makes it possible to customize the content to be provided based on the user's social media activity.

[0057] The providing unit can customize the providing method by reflecting the user's past feedback when providing commentary. The providing unit customizes the providing method, for example, by referring to a commentary style that the user has preferred to watch in the past. For example, the providing unit customizes the providing method by referring to a commentary style that the user has preferred to watch in the past. The providing unit can also customize the providing method based on feedback that the user has provided in the past. For example, the providing unit customizes the providing method based on feedback that the user has provided in the past. Furthermore, the providing unit can also customize the providing method by analyzing the content of commentaries that the user has viewed in the past. For example, the providing unit analyzes the content of commentaries that the user has viewed in the past and customizes the providing method. In this way, the providing method can be customized based on the user's past feedback.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The reception unit can analyze the user's past input history and suggest the optimal input method. For example, it can automatically display names and images of favorite characters that the user has frequently input in the past as candidates. It can also prioritize suggestions of input methods (voice, text, etc.) that the user has used in the past. Furthermore, it can predict and suggest information about favorite characters related to specific events or periods from the user's past input history. This makes it possible to suggest the optimal input method based on the user's past input history.

[0060] When analyzing the video, the analysis unit can improve the accuracy of the analysis by referring to the idol's past performance data. For example, by referring to past live video of the idol, the accuracy of the analysis of the idol's current performance can be improved. Also, by referring to video of the idol's past matches, the accuracy of the analysis of the idol's current movements and facial expressions can be improved. Furthermore, by referring to video of the idol's past events, the accuracy of the analysis of the idol's current performance can be improved. In this way, the accuracy of the analysis can be improved by referring to the idol's past performance data.

[0061] When providing commentary, the providing unit can customize the content to be provided according to the user's current viewing environment. For example, if the user is watching on a smartphone, the providing unit can provide commentary optimized for the screen size. Also, if the user is watching on a tablet, the providing unit can provide commentary optimized for a large screen. Furthermore, if the user is watching on a smart TV, the providing unit can provide commentary in high resolution. This makes it possible to provide optimal content according to the user's viewing environment.

[0062] When generating commentary, the generation unit can apply different commentary algorithms depending on the category of the favorite. For example, if the favorite is a sports player, a sports commentary algorithm can be applied. If the favorite is an idol, an entertainment commentary algorithm can be applied. Furthermore, if the favorite is an actor, a movie or drama commentary algorithm can be applied. This makes it possible to provide the optimal commentary algorithm depending on the category of the favorite.

[0063] When providing commentary, the providing unit can analyze the user's social media activity and customize the content provided. For example, the providing unit can provide commentary related to accounts the user follows on social media. It can also provide commentary related to hashtags the user uses on social media. It can also provide commentary related to content the user has shared on social media. This allows the providing unit to customize the content provided based on the user's social media activity.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The reception unit accepts information about the user's favorite idol. The reception unit accepts the user's input of the idol's name, image, and video link. For example, the user can input the name of a specific idol or athlete. Step 2: The analysis unit analyzes the video of the favorite idol based on the information received by the reception unit. For example, it analyzes live footage or game footage to recognize the favorite idol's movements and facial expressions. Step 3: The generator generates emotional commentary based on the information analyzed by the analyzer. For example, it generates emotional commentary when a favorite idol scores a goal or performs a specific performance. Step 4: The providing unit provides the commentary generated by the generating unit in real time. For example, a clipped video or subtitles of the favorite person can be created based on the generated commentary content.

[0066] (Example 2) A system according to an embodiment of the present invention generates and supports live commentary in real time, focusing on a user's favorite idol. This system allows users to input information about their favorite idol, analyze video of the idol using the LLM's image recognition and interpretation functions, and generate commentary using an emotional voice synthesis function. It is also possible to create clipped videos and subtitles of the favorite idol based on the generated commentary. This allows the system to generate and support live commentary in real time, focusing on a user's favorite idol. For example, a user can input the name of a specific idol or athlete, and the system analyzes video of the favorite idol based on that information and generates an emotional commentary. Furthermore, based on the generated commentary, it can create a video by clipping highlight scenes of the favorite idol, or display the commentary as subtitles. This allows users to enjoy live commentary focusing on their favorite idol, making their favorite idol activities more fulfilling.

[0067] The cheering system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit receives information about a favorite person from a user. The reception unit receives input from the user of the name, image, and video link of the favorite person. For example, the user can input the name of a specific idol or athlete. The analysis unit analyzes video of the favorite person based on the information received by the reception unit. For example, it analyzes live video or game video to recognize the favorite person's movements and facial expressions. The generation unit generates an emotional commentary based on the information analyzed by the analysis unit. For example, it generates an emotional commentary at the moment the favorite person scores a goal or performs a specific performance. The provision unit provides the commentary generated by the generation unit in real time. For example, it can create clipped videos and subtitles of the favorite person based on the generated commentary content. As a result, the cheering system according to the embodiment can generate commentary centered on the user's favorite person in real time and cheer on the user.

[0068] The reception unit can accept the user's input of the name, image, and video link of their favorite idol. The name, image, and video link of their favorite idol can be in text format, image format, URL format, and the like, but are not limited to these examples. For example, the reception unit can accept the user's input of the name of a specific idol or athlete in text format. The reception unit can also accept the user's upload of an image of their favorite idol in image format. Furthermore, the reception unit can also accept the user's input of a link to a video of their favorite idol in URL format. This allows the user to easily input information about their favorite idol.

[0069] The analysis unit can analyze live video or game video to recognize the movements and facial expressions of the favorite player. Examples of live video or game video include, but are not limited to, video of a sports game or a live concert. The analysis unit can, for example, analyze live video to recognize the movements of the favorite player. For example, the analysis unit can analyze the movements of the favorite player as they move on stage. The analysis unit can also analyze game video to recognize the facial expressions of the favorite player. For example, the analysis unit can analyze the facial expressions of the favorite player at the moment they score a goal. Furthermore, the analysis unit can analyze live video or game video to comprehensively recognize the movements and facial expressions of the favorite player. For example, the analysis unit can simultaneously analyze the movements and facial expressions of the favorite player to grasp the situation of the favorite player in detail. This allows the movement and facial expressions of the favorite player to be accurately recognized.

[0070] The generation unit can generate emotional commentary the moment the favorite idol scores a goal or performs a specific performance. Examples of moments when a goal is scored or a specific performance include, but are not limited to, a goal scene or a dance performance. The generation unit generates emotional commentary the moment the favorite idol scores a goal. For example, the generation unit can generate emotional commentary such as "What a great goal!" the moment the favorite idol scores a goal. The generation unit can also generate emotional commentary the moment the favorite idol performs a specific performance. For example, the generation unit can generate emotional commentary such as "What a great dance!" the moment the favorite idol performs a dance performance. The generation unit can also generate emotional commentary based on the favorite idol's movements and facial expressions. For example, the generation unit can generate emotional commentary such as "What a beautiful smile!" the moment the favorite idol smiles. This generates emotional commentary, which can increase the user's excitement.

[0071] The providing unit can create clipped videos and subtitles of the favorite idol based on the generated commentary content. The clipped videos and subtitles include, for example, the length of the video and the content of the subtitles, but are not limited to these examples. For example, the providing unit can create a video by clipping highlight scenes of the favorite idol based on the generated commentary content. For example, the providing unit can create a video by clipping the moment the favorite idol scores a goal or performs a particular performance. The providing unit can also create subtitles based on the generated commentary content. For example, the providing unit can display the commentary content as subtitles and provide them to the user. Furthermore, the providing unit can combine clipped videos and subtitles of the favorite idol based on the generated commentary content and provide them. For example, the providing unit can add subtitles to a clipped video of the favorite idol's highlight scenes and provide it. In this way, creating clipped videos and subtitles of the favorite idol can support the user's activities.

[0072] The reception unit can estimate the user's emotions and adjust the input method for information about their favorite idol based on the estimated user emotions. For example, if the user is excited, the reception unit can provide a simple and intuitive interface, allowing the user to quickly input information about their favorite idol. For example, if the user is excited, the reception unit can display a simple input form, allowing the user to quickly input the name and image of their favorite idol. Furthermore, if the user is relaxed, the reception unit can provide detailed input options and suggest a customizable input method. For example, if the user is relaxed, the reception unit can display a detailed input form, allowing the user to input detailed information about their favorite idol. Furthermore, if the user is stressed, the reception unit can prioritize voice input and minimize the input steps. For example, if the user is stressed, the reception unit can display a voice input option, allowing the user to input information about their favorite idol by voice. This allows the user to receive the optimal input method based on their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0073] The reception unit can analyze the user's past input history and suggest the optimal input method. For example, the reception unit automatically displays names and images of favorite characters that the user has frequently input in the past as candidates. For example, the reception unit displays names of favorite characters that the user has input in the past as candidates, allowing the user to quickly select one. The reception unit can also preferentially suggest input methods (voice, text, etc.) that the user has used in the past. For example, if the user has used voice input in the past, the reception unit preferentially displays the voice input option. Furthermore, the reception unit can predict and suggest information about favorite characters related to a specific event or time period based on the user's past input history. For example, the reception unit suggests information about favorite characters related to a similar event period based on information about favorite characters that the user has input in the past around a specific event period. This allows the optimal input method to be suggested based on the user's past input history.

[0074] When inputting information about a favorite person, the reception unit can present recommended favorite person candidates based on the user's current interests and trends. The reception unit presents related recommended favorite person candidates based on, for example, topics and trends recently searched by the user. For example, the reception unit presents recommended favorite person candidates related to idols or athletes recently searched by the user. The reception unit can also present recommended favorite person candidates based on accounts and hashtags the user follows on social media. For example, the reception unit presents recommended favorite person candidates related to accounts the user follows. Furthermore, the reception unit can present related recommended favorite person candidates based on videos or articles recently viewed by the user. For example, the reception unit presents recommended favorite person candidates related to videos recently viewed by the user. This makes it possible to present recommended favorite person candidates based on the user's interests and trends.

[0075] When inputting information about a favorite person, the reception unit can select the optimal input means depending on the user's input method. For example, if the user selects voice input, the reception unit uses voice recognition technology to input the name and information of the favorite person. For example, if the user selects voice input, the reception unit can input the name of the favorite person using voice recognition software. Furthermore, if the user selects text input, the reception unit can provide an input completion function to enable the favorite person to be quickly input. For example, if the user selects text input, the reception unit can use the input completion function to enable the favorite person to be quickly input. Furthermore, if the user selects image input, the reception unit can automatically extract information about the favorite person using image recognition technology. For example, if the user selects image input, the reception unit can extract information from an image of the favorite person using image recognition technology. This makes it possible to provide the optimal input means depending on the user's input method.

[0076] The reception unit can estimate the user's emotions and prioritize the input information about the favorite idol based on the estimated user emotions. For example, if the user is excited, the reception unit can prioritize displaying the latest information about the favorite idol. For example, if the user is excited, the reception unit can prioritize displaying the latest live video or match results of the favorite idol. Furthermore, if the user is relaxed, the reception unit can prioritize displaying past highlights or memorable scenes of the favorite idol. For example, if the user is relaxed, the reception unit can prioritize displaying past live video or highlights of a specific event of the favorite idol. Furthermore, if the user is stressed, the reception unit can prioritize displaying soothing content about the favorite idol. For example, if the user is stressed, the reception unit can prioritize displaying relaxing videos or music of the favorite idol. This allows the priority of information about the favorite idol to be determined based on the user's emotions. 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.

[0077] When inputting information about a favorite idol, the reception unit can present highly relevant favorite idol candidates based on the user's geographical location information. The reception unit, for example, presents candidate favorite idols who will be appearing at events or live shows near the user's current location. For example, the reception unit presents candidate favorite idols who will be appearing at live shows or events held near the user's current location. The reception unit can also present candidate favorite idols related to places the user has visited in the past. For example, the reception unit presents candidate favorite idols who are active in places the user has visited in the past. The reception unit can also present candidate favorite idols related to the weather or season of the user's current location. For example, the reception unit presents candidate favorite idols who will be appearing at events related to the weather or season of the user's current location. In this way, highly relevant favorite idol candidates can be presented based on the user's geographical location information.

[0078] When inputting information about a favorite person, the reception unit can analyze the user's social media activity and automatically complete the related information about the favorite person. For example, the reception unit automatically completes information about the favorite person related to accounts the user follows on social media. For example, the reception unit can automatically complete information about the favorite person related to accounts the user follows. The reception unit can also automatically complete information about the favorite person related to hashtags the user uses on social media. For example, the reception unit automatically completes information about the favorite person related to hashtags used by the user. Furthermore, the reception unit can automatically complete information about the favorite person related to content the user shared on social media. For example, the reception unit automatically completes information about the favorite person related to content shared by the user. This makes it possible to automatically complete information about the favorite person based on the user's social media activity.

[0079] The reception unit can customize the input method by reflecting the user's past feedback when inputting information about a favorite person. For example, the reception unit preferentially suggests input methods that the user has used in the past. For example, the reception unit preferentially displays input methods that the user has used in the past. The reception unit can also improve the input interface based on feedback provided by the user in the past. For example, the reception unit improves the input interface based on feedback provided by the user in the past. Furthermore, the reception unit can also simplify the input procedure by referring to information input by the user in the past. For example, the reception unit simplifies the input procedure based on information input by the user in the past. This makes it possible to customize the input method based on the user's past feedback.

[0080] The analysis unit can estimate the user's emotions and adjust the accuracy of video analysis based on the estimated user emotions. For example, when the user is excited, the analysis unit increases the accuracy of the video analysis to analyze small movements and facial expressions in detail. For example, when the user is excited, the analysis unit analyzes the small movements and facial expressions of the user's favorite idol in detail. Furthermore, when the user is relaxed, the analysis unit can appropriately adjust the accuracy of the video analysis to emphasize overall movements. For example, when the user is relaxed, the analysis unit emphasizes the overall movements of the user's favorite idol in analysis. Furthermore, when the user is stressed, the analysis unit can lower the accuracy of the video analysis to focus on key movements and facial expressions. For example, when the user is stressed, the analysis unit focuses on the key movements and facial expressions of the user's favorite idol in analysis. This allows for optimal video analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0081] When analyzing the video, the analysis unit can track the movements and facial expressions of the favorite idol in real time and update the analysis results. For example, the analysis unit tracks the movements of the favorite idol in real time as they move on stage and updates the analysis results. For example, the analysis unit tracks the movements of the favorite idol as they move on stage in real time and updates the analysis results. The analysis unit can also analyze the facial expressions of the favorite idol in real time the moment they change their facial expressions and update the results. For example, the analysis unit analyzes the facial expressions of the favorite idol in real time the moment they smile and updates the results. The analysis unit can also analyze the movements and facial expressions of the favorite idol in real time when they perform a specific performance and update the results. For example, the analysis unit analyzes the movements and facial expressions of the favorite idol in real time the moment they perform a dance performance and updates the results. In this way, the movements and facial expressions of the favorite idol can be tracked in real time and the analysis results can be updated.

[0082] When analyzing the video, the analysis unit can improve the accuracy of the analysis by referring to the idol's past performance data. For example, the analysis unit can improve the accuracy of analysis of the idol's current performance by referring to past live video of the idol. For example, the analysis unit can improve the accuracy of analysis of the idol's current performance by referring to past live video of the idol. The analysis unit can also improve the accuracy of analysis of the idol's current movements and facial expressions by referring to video of the idol's past matches. For example, the analysis unit can improve the accuracy of analysis of the idol's current movements and facial expressions by referring to video of the idol's past matches. Furthermore, the analysis unit can improve the accuracy of analysis of the idol's current performance by referring to video of the idol's past events. For example, the analysis unit can improve the accuracy of analysis of the idol's current performance by referring to video of the idol's past events. In this way, the accuracy of analysis can be improved by referring to the idol's past performance data.

[0083] When analyzing the video, the analysis unit can complement the analysis results based on the idol's costume or background information. For example, if the idol is wearing a specific costume, the analysis unit complements the analysis results by taking into account the characteristics of the costume. For example, if the idol is wearing a specific costume, the analysis unit complements the analysis results by taking into account the characteristics of the costume. Furthermore, if the idol is performing against a specific background, the analysis unit can complement the analysis results by taking into account the background information. For example, if the idol is performing against a specific background, the analysis unit complements the analysis results by taking into account the background information. Furthermore, if the idol is performing at a specific event, the analysis unit can complement the analysis results by taking into account the characteristics of the event. For example, if the idol is performing at a specific event, the analysis unit complements the analysis results by taking into account the characteristics of the event. In this way, the analysis results can be complemented by taking into account the idol's costume and background information.

[0084] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is excited, the analysis unit displays detailed analysis results and emphasizes the detailed movements and expressions of the idol. For example, if the user is excited, the analysis unit displays the detailed movements and expressions of the idol. Furthermore, if the user is relaxed, the analysis unit can display overall analysis results and emphasize the idol's overall performance. For example, if the user is relaxed, the analysis unit displays the overall performance of the idol. Furthermore, if the user is stressed, the analysis unit can display the main analysis results and emphasize the idol's important movements and expressions. For example, if the user is stressed, the analysis unit displays the idol's important movements and expressions. This makes it possible to provide an optimal display method of the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. Generation AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0085] When analyzing the video, the analysis unit can take into account the geographical range of activity of the favorite idol. For example, if the favorite idol is active in a specific region, the analysis unit can take into account the characteristics of that region when analyzing. For example, if the favorite idol is active in a specific region, the analysis unit can take into account the characteristics of that region when analyzing. Furthermore, if the favorite idol is active in multiple regions, the analysis unit can take into account the characteristics of each region when analyzing. For example, if the favorite idol is active in multiple regions, the analysis unit can take into account the characteristics of each region when analyzing. Furthermore, if the favorite idol is active internationally, the analysis unit can take into account the characteristics of each country when analyzing. For example, if the favorite idol is active internationally, the analysis unit can take into account the characteristics of each country when analyzing. This makes it possible to perform an analysis taking into account the geographical range of activity of the favorite idol.

[0086] When analyzing the video, the analysis unit can improve the accuracy of the analysis by referring to literature and media information related to the favorite idol. For example, the analysis unit can improve the accuracy of the analysis by referring to literature related to the favorite idol. For example, the analysis unit can improve the accuracy of the analysis by referring to literature related to the favorite idol. The analysis unit can also improve the accuracy of the analysis by referring to media information related to the favorite idol. For example, the analysis unit can improve the accuracy of the analysis by referring to media information related to the favorite idol. The analysis unit can also improve the accuracy of the analysis by referring to past interviews and articles related to the favorite idol. For example, the analysis unit can improve the accuracy of the analysis by referring to past interviews and articles related to the favorite idol. In this way, the accuracy of the analysis can be improved by referring to literature and media information related to the favorite idol.

[0087] When analyzing the video, the analysis unit can perform analysis based on the market value or popularity of the favorite idol. For example, the analysis unit takes into account the market value of the favorite idol to supplement the analysis results. For example, the analysis unit takes into account the market value of the favorite idol to supplement the analysis results. The analysis unit can also take into account the popularity of the favorite idol to supplement the analysis results. For example, the analysis unit takes into account the popularity of the favorite idol to supplement the analysis results. Furthermore, the analysis unit can also take into account the characteristics of the favorite idol's fan base to supplement the analysis results. For example, the analysis unit takes into account the characteristics of the favorite idol's fan base to supplement the analysis results. This makes it possible to perform analysis taking into account the market value and popularity of the favorite idol.

[0088] The generation unit can estimate the user's emotions and adjust the way the commentary is expressed based on the estimated user's emotions. For example, when the user is excited, the generation unit generates an emotional commentary. For example, when the user is excited, the generation unit generates an emotional commentary. The generation unit can also generate a commentary in a calm tone when the user is relaxed. For example, when the user is relaxed, the generation unit generates a commentary in a calm tone. Furthermore, when the user is stressed, the generation unit can also generate a simple and easy-to-understand commentary. For example, when the user is stressed, the generation unit generates a simple and easy-to-understand commentary. This makes it possible to provide an optimal way to express the commentary according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or 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.

[0089] When generating the commentary, the generation unit can adjust the level of detail of the commentary depending on important moments of the favorite player. For example, the generation unit generates a detailed commentary the moment the favorite player scores a goal. For example, the generation unit generates a detailed commentary the moment the favorite player scores a goal. The generation unit can also generate a detailed commentary the moment the favorite player performs a specific performance. For example, the generation unit generates a detailed commentary the moment the favorite player performs a specific performance. The generation unit can also generate a detailed commentary the moment the favorite player is being interviewed. For example, the generation unit generates a detailed commentary the moment the favorite player is being interviewed. This makes it possible to provide a detailed commentary that corresponds to important moments of the favorite player.

[0090] When generating commentary, the generation unit can apply different commentary algorithms depending on the category of the favorite. For example, if the favorite is an athlete, the generation unit applies a sports commentary algorithm. For example, if the favorite is an athlete, the generation unit applies a sports commentary algorithm. Furthermore, if the favorite is an idol, the generation unit can also apply an entertainment commentary algorithm. For example, if the favorite is an idol, the generation unit applies an entertainment commentary algorithm. Furthermore, if the favorite is an actor, the generation unit can also apply a movie or drama commentary algorithm. For example, if the favorite is an actor, the generation unit applies a movie or drama commentary algorithm. This makes it possible to provide the optimal commentary algorithm depending on the category of the favorite.

[0091] When generating a commentary, the generation unit can improve the accuracy of the commentary by referring to the user's past commentary results. The generation unit can improve the accuracy of the commentary by referring to, for example, a commentary style that the user previously preferred. For example, the generation unit can improve the accuracy of the commentary by referring to the commentary style that the user previously preferred. The generation unit can also improve the accuracy of the commentary based on feedback that the user previously provided. For example, the generation unit can improve the accuracy of the commentary based on feedback that the user previously provided. Furthermore, the generation unit can analyze the content of commentaries that the user previously viewed and generate an optimal commentary. For example, the generation unit can analyze the content of commentaries that the user previously viewed and generate an optimal commentary. This can improve the accuracy of the commentary by referring to the user's past commentary results.

[0092] The generation unit can estimate the user's emotions and adjust the length of the commentary based on the estimated user's emotions. For example, if the user is excited, the generation unit generates a longer commentary. For example, if the user is excited, the generation unit generates a longer commentary. Furthermore, if the user is relaxed, the generation unit can generate a commentary of an appropriate length. For example, if the user is relaxed, the generation unit generates a commentary of an appropriate length. Furthermore, if the user is in a hurry, the generation unit can generate a commentary that is short and to the point. For example, if the user is in a hurry, the generation unit generates a commentary that is short and to the point. This makes it possible to provide an optimal commentary length according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0093] When generating the commentary, the generation unit can determine the priority of the commentary based on the period of the favorite idol's activities. The generation unit, for example, determines the priority of the commentary based on the events and live performances that the favorite idol is currently participating in. For example, the generation unit determines the priority of the commentary based on the events and live performances that the favorite idol is currently participating in. The generation unit can also determine the priority of the commentary based on important events and live performances that the favorite idol has held in the past. For example, the generation unit determines the priority of the commentary based on important events and live performances that the favorite idol has held in the past. The generation unit can also determine the priority of the commentary based on events and live performances that the favorite idol has scheduled in the future. For example, the generation unit determines the priority of the commentary based on the events and live performances that the favorite idol has scheduled in the future. In this way, the priority of the commentary can be determined based on the period of the favorite idol's activities.

[0094] When generating commentary, the generation unit can adjust the order of the commentary based on the relevance of the favorite idol. The generation unit, for example, adjusts the order of the commentary based on programs and events in which the favorite idol is currently appearing. For example, the generation unit adjusts the order of the commentary based on programs and events in which the favorite idol is currently appearing. The generation unit can also adjust the order of the commentary based on programs and events in which the favorite idol has previously appeared. For example, the generation unit adjusts the order of the commentary based on programs and events in which the favorite idol has previously appeared. The generation unit can also adjust the order of the commentary based on programs and events in which the favorite idol is scheduled to appear in the future. For example, the generation unit adjusts the order of the commentary based on programs and events in which the favorite idol is scheduled to appear in the future. In this way, the order of the commentary can be adjusted based on the relevance of the favorite idol.

[0095] When generating a commentary, the generation unit can adjust the use of technical terms in the commentary according to the user's level of expertise. For example, if the user is a beginner, the generation unit generates a commentary that is easy to understand by avoiding technical terms. For example, if the user is a beginner, the generation unit generates a commentary that is easy to understand by avoiding technical terms. Furthermore, if the user is an intermediate player, the generation unit can generate a commentary that uses technical terms moderately. For example, if the user is an intermediate player, the generation unit generates a commentary that uses technical terms moderately. Furthermore, if the user is an advanced player, the generation unit can generate a detailed commentary that uses a lot of technical terms. For example, if the user is an advanced player, the generation unit generates a detailed commentary that uses a lot of technical terms. This makes it possible to provide an optimal commentary according to the user's level of expertise.

[0096] The providing unit can estimate the user's emotions and adjust the commentary provision method based on the estimated user's emotions. For example, when the user is excited, the providing unit provides an emotional commentary in real time. For example, when the user is excited, the providing unit provides an emotional commentary in real time. Furthermore, when the user is relaxed, the providing unit can also provide a commentary in a calm tone. For example, when the user is relaxed, the providing unit provides a commentary in a calm tone. Furthermore, when the user is stressed, the providing unit can also provide a simple and easy-to-understand commentary. For example, when the user is stressed, the providing unit provides a simple and easy-to-understand commentary. This makes it possible to provide an optimal commentary provision method according to the user's emotions. Emotion estimation is realized using an emotion estimation function using, 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.

[0097] When providing live commentary, the providing unit can select the optimal providing method by referring to the user's past viewing history. The providing unit selects the optimal providing method, for example, by referring to the live commentary style that the user preferred in the past. For example, the providing unit selects the optimal providing method by referring to the live commentary style that the user preferred in the past. The providing unit can also select the optimal providing method based on feedback that the user provided in the past. For example, the providing unit selects the optimal providing method based on feedback that the user provided in the past. Furthermore, the providing unit can also analyze the content of live commentary that the user viewed in the past and select the optimal providing method. For example, the providing unit analyzes the content of live commentary that the user viewed in the past and selects the optimal providing method. In this way, the optimal providing method can be selected based on the user's past viewing history.

[0098] When providing commentary, the providing unit can customize the content to be provided according to the user's current viewing environment. For example, if the user is viewing on a smartphone, the providing unit provides commentary optimized for the screen size. For example, if the user is viewing on a smartphone, the providing unit provides commentary optimized for the screen size. Furthermore, if the user is viewing on a tablet, the providing unit can also provide commentary optimized for a large screen. For example, if the user is viewing on a tablet, the providing unit provides commentary optimized for a large screen. Furthermore, the providing unit can also provide commentary in high resolution if the user is viewing on a smart TV. For example, if the user is viewing on a smart TV, the providing unit provides commentary in high resolution. This makes it possible to provide content optimal for the user's viewing environment.

[0099] The providing unit can improve the commentary providing method by reflecting user feedback when providing commentary. The providing unit improves the commentary providing method based on, for example, feedback provided by the user. For example, the providing unit improves the commentary providing method based on feedback provided by the user. The providing unit can also analyze feedback provided by the user in the past and select an optimal providing method. For example, the providing unit analyzes feedback provided by the user in the past and selects an optimal providing method. Furthermore, the providing unit can adjust the commentary providing method by reflecting feedback provided by the user in real time. For example, the providing unit adjusts the commentary providing method by reflecting feedback provided by the user in real time. This makes it possible to improve the commentary providing method based on user feedback.

[0100] The providing unit can estimate the user's emotions and determine the priority of providing commentary based on the estimated user's emotions. For example, when the user is excited, the providing unit prioritizes providing the latest commentary. For example, when the user is excited, the providing unit prioritizes providing the latest commentary. Furthermore, when the user is relaxed, the providing unit can also prioritize providing past highlight commentary. For example, when the user is relaxed, the providing unit prioritizes providing past highlight commentary. Furthermore, when the user is stressed, the providing unit can also prioritize providing soothing commentary. For example, when the user is stressed, the providing unit prioritizes providing soothing commentary. This makes it possible to determine the priority of providing commentary based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0101] When providing commentary, the providing unit can select an appropriate providing method based on the user's geographical location information. For example, the providing unit prioritizes providing commentary of events or live shows close to the user's current location. For example, the providing unit prioritizes providing commentary of events or live shows close to the user's current location. The providing unit can also prioritize providing commentary related to places the user has visited in the past. For example, the providing unit prioritizes providing commentary related to places the user has visited in the past. Furthermore, the providing unit can also prioritize providing commentary related to the weather or season of the user's current location. For example, the providing unit prioritizes providing commentary related to the weather or season of the user's current location. This makes it possible to select an optimal providing method based on the user's geographical location information.

[0102] When providing commentary, the providing unit can analyze the user's social media activity and customize the content to be provided. The providing unit, for example, provides commentary related to accounts the user follows on social media. For example, the providing unit provides commentary related to accounts the user follows on social media. The providing unit can also provide commentary related to hashtags the user uses on social media. For example, the providing unit provides commentary related to hashtags the user uses on social media. The providing unit can also provide commentary related to content the user shared on social media. For example, the providing unit provides commentary related to content the user shared on social media. This makes it possible to customize the content to be provided based on the user's social media activity.

[0103] The providing unit can customize the providing method by reflecting the user's past feedback when providing commentary. The providing unit customizes the providing method, for example, by referring to a commentary style that the user has preferred to watch in the past. For example, the providing unit customizes the providing method by referring to a commentary style that the user has preferred to watch in the past. The providing unit can also customize the providing method based on feedback that the user has provided in the past. For example, the providing unit customizes the providing method based on feedback that the user has provided in the past. Furthermore, the providing unit can also customize the providing method by analyzing the content of commentaries that the user has viewed in the past. For example, the providing unit analyzes the content of commentaries that the user has viewed in the past and customizes the providing method. In this way, the providing method can be customized based on the user's past feedback. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, generation unit, and provision unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the reception device 38 of the smart device 14 and receives input from the user of the name, image, and video link of the favorite idol. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the video of the favorite idol based on the information received by the reception unit. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates an emotional commentary based on the information analyzed by the analysis unit. For example, the provision unit is realized by the output device 40 of the smart device 14 and provides the commentary generated by the generation unit in real time. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, generation unit, and provision unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the smart glasses 214 and receives input of the user's name, image, and video link of their favorite idol. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the video of their favorite idol based on the information received by the reception unit. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates an emotional commentary based on the information analyzed by the analysis unit. For example, the provision unit is realized by the speaker 240 of the smart glasses 214 and provides the commentary generated by the generation unit in real time. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, generation unit, and provision unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the headset-type terminal 314 and receives input from the user of the name, image, and video link of the favorite idol. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the video of the favorite idol based on the information received by the reception unit. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates an emotional commentary based on the information analyzed by the analysis unit. For example, the provision unit is realized by the speaker 240 of the headset-type terminal 314 and provides the commentary generated by the generation unit in real time. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, generation unit, and provision unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the robot 414 and receives input from the user of the name, image, and video link of the favorite idol. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the video of the favorite idol based on the information received by the reception unit. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates an emotional commentary based on the information analyzed by the analysis unit. For example, the provision unit is realized by the speaker 240 of the robot 414 and provides the commentary generated by the generation unit in real time.

[0104] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0105] The analysis unit can estimate the user's emotions and adjust the priority of video analysis based on the estimated user emotions. For example, if the user is excited, analysis of the movements and facial expressions of the favorite character can be prioritized. If the user is relaxed, analysis of the overall video can be prioritized. Furthermore, if the user is stressed, analysis of key scenes can be prioritized. This allows for optimal video analysis according to the user's emotions.

[0106] The providing unit can estimate the user's emotions and adjust the commentary providing method based on the estimated user's emotions. For example, if the user is excited, an emotional commentary can be provided in real time. If the user is relaxed, a calm commentary can be provided. Furthermore, if the user is stressed, a simple and easy-to-understand commentary can be provided. This makes it possible to provide an optimal commentary providing method according to the user's emotions.

[0107] The generation unit can estimate the user's emotions and adjust the commentary expression method based on the estimated user's emotions. For example, if the user is excited, an emotional commentary can be generated. If the user is relaxed, a calm commentary can be generated. Furthermore, if the user is stressed, a simple and easy-to-understand commentary can be generated. This makes it possible to provide an optimal commentary expression method according to the user's emotions.

[0108] The reception unit can estimate the user's emotions and adjust the input method for information about their favorite idol based on the estimated user emotions. For example, if the user is excited, a simple and intuitive interface can be provided, allowing the user to quickly input information about their favorite idol. Alternatively, if the user is relaxed, detailed input options can be provided and a customizable input method can be suggested. Furthermore, if the user is stressed, voice input can be prioritized, minimizing input steps. This allows the optimal input method to be provided according to the user's emotions.

[0109] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is excited, detailed analysis results can be displayed, emphasizing the idol's detailed movements and facial expressions. If the user is relaxed, overall analysis results can be displayed, emphasizing the idol's overall performance. Furthermore, if the user is stressed, key analysis results can be displayed, emphasizing the idol's important movements and facial expressions. This makes it possible to provide an optimal display method of the analysis results according to the user's emotions.

[0110] The reception unit can analyze the user's past input history and suggest the optimal input method. For example, it can automatically display names and images of favorite characters that the user has frequently input in the past as candidates. It can also prioritize suggestions of input methods (voice, text, etc.) that the user has used in the past. Furthermore, it can predict and suggest information about favorite characters related to specific events or periods from the user's past input history. This makes it possible to suggest the optimal input method based on the user's past input history.

[0111] When analyzing the video, the analysis unit can improve the accuracy of the analysis by referring to the idol's past performance data. For example, by referring to past live video of the idol, the accuracy of the analysis of the idol's current performance can be improved. Also, by referring to video of the idol's past matches, the accuracy of the analysis of the idol's current movements and facial expressions can be improved. Furthermore, by referring to video of the idol's past events, the accuracy of the analysis of the idol's current performance can be improved. In this way, the accuracy of the analysis can be improved by referring to the idol's past performance data.

[0112] When providing commentary, the providing unit can customize the content to be provided according to the user's current viewing environment. For example, if the user is watching on a smartphone, the providing unit can provide commentary optimized for the screen size. Also, if the user is watching on a tablet, the providing unit can provide commentary optimized for a large screen. Furthermore, if the user is watching on a smart TV, the providing unit can provide commentary in high resolution. This makes it possible to provide optimal content according to the user's viewing environment.

[0113] When generating commentary, the generation unit can apply different commentary algorithms depending on the category of the favorite. For example, if the favorite is a sports player, a sports commentary algorithm can be applied. If the favorite is an idol, an entertainment commentary algorithm can be applied. Furthermore, if the favorite is an actor, a movie or drama commentary algorithm can be applied. This makes it possible to provide the optimal commentary algorithm depending on the category of the favorite.

[0114] When providing commentary, the providing unit can analyze the user's social media activity and customize the content provided. For example, the providing unit can provide commentary related to accounts the user follows on social media. It can also provide commentary related to hashtags the user uses on social media. It can also provide commentary related to content the user has shared on social media. This allows the providing unit to customize the content provided based on the user's social media activity.

[0115] The processing flow of the second embodiment will be briefly explained below.

[0116] Step 1: The reception unit accepts information about the user's favorite idol. The reception unit accepts the user's input of the idol's name, image, and video link. For example, the user can input the name of a specific idol or athlete. Step 2: The analysis unit analyzes the video of the favorite idol based on the information received by the reception unit. For example, it analyzes live footage or game footage to recognize the favorite idol's movements and facial expressions. Step 3: The generator generates emotional commentary based on the information analyzed by the analyzer. For example, it generates emotional commentary when a favorite idol scores a goal or performs a specific performance. Step 4: The providing unit provides the commentary generated by the generating unit in real time. For example, a clipped video or subtitles of the favorite person can be created based on the generated commentary content.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0121] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] 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.

[0136] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0137] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0138] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] 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.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0154] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0168] 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.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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).

[0174] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0175] 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."

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] [Explanation of symbols]

[0189] 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 reception unit that receives information about a favorite person from a user; an analysis unit that analyzes the video of the favorite person based on the information received by the reception unit; a generating unit that generates an emotional commentary based on the information analyzed by the analyzing unit; a providing unit that provides the commentary generated by the generating unit in real time. A system characterized by:

2. The reception unit Accepts users to enter the name, image, and video link of their favorite.

2. The system of claim 1.

3. The analysis unit Analyze live or match footage to recognize the movements and expressions of your favorite player 2. The system of claim 1.

4. The generation unit Generate emotional commentary when your favorite idol scores a goal or performs a specific performance 2. The system of claim 1.

5. The providing unit Create clips and subtitles of your favorite characters based on the generated commentary 2. The system of claim 1.

6. The reception unit Estimate the user's emotions and adjust the input method for the user's favorite information based on the estimated user emotions.

2. The system of claim 1.

7. The reception unit Analyzes the user's past input history and suggests the optimal input method 2. The system of claim 1.

8. The reception unit When entering information about your favorite person, we will suggest recommended people based on your current interests and trends.

2. The system of claim 1.

Images