system

Abstract

The system according to the embodiment aims to deepen understanding of specific dance movements and techniques. [Solution] A system according to an embodiment includes a collection unit, a learning unit, and an explanation unit. The collection unit collects video data of dance. The learning unit studies the video data collected by the collection unit. The explanation unit provides explanations on specific dance movements and techniques based on the data learned by the learning unit.

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have the drawback of not providing a deep understanding of specific dance movements and techniques, making it difficult to recognize the difference between professionals and amateurs.

[0005] The system according to the embodiment aims to deepen understanding of specific dance movements and techniques. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a learning unit, and an explanation unit. The collection unit collects video data of dance. The learning unit studies the video data collected by the collection unit. The explanation unit provides explanations on specific dance movements and techniques based on the data learned by the learning unit. [Effects of the Invention]

[0007] The system according to the embodiment can enhance the understanding of specific dance movements and techniques. [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 dance commentary system according to an embodiment of the present invention collects dance video data, trains a generation AI, and provides commentary on each dance movement and technique. The dance commentary system collects dance video data and provides commentary on each dance movement and technique based on the data learned by the generation AI. For example, the dance commentary system may collect a balanced collection of videos of professional and amateur dancers and train the generation AI. Next, based on the data learned by the generation AI, it provides verbal commentary on each dance movement and technique. For example, it may provide detailed commentary on specific techniques and movements, such as the "arabesque" in ballet or the "popping" in hip-hop. Furthermore, the dance commentary system may provide visual aids. For example, it may replay a specific movement in slow motion and have the generation AI provide commentary on that movement in real time. This allows viewers to understand dance techniques in more detail. The dance commentary system also has an interactive feature that allows viewers to ask questions. For example, when a viewer asks a question about a specific movement, the generation AI provides commentary in response to the question. This allows viewers to gain a deeper understanding of the appeal of dance, recognize professional techniques, and find dance more appealing. This allows viewers to gain a deeper understanding of the appeal of dance and become more aware of professional techniques, making dance more appealing to them. For example, when watching a ballet performance, viewers can enjoy the performance more by understanding how professional dancers achieve beautiful arabesques. It can also be a useful tool for amateur dancers who want to learn dance techniques.

[0029] A dance commentary system according to an embodiment includes a collection unit, a learning unit, and a commentary unit. The collection unit collects dance video data. The dance video data includes, for example, videos of professional and amateur dancers, but is not limited to, such examples. The collection unit collects dance videos of various genres, such as ballet, hip hop, and jazz dance. The collection unit can also collect video data from multiple sources, such as publicly available videos on the Internet and videos filmed in dance studios. For example, the collection unit automatically collects dance videos from video sharing sites on the Internet. The collection unit can also directly collect videos filmed in dance studios. The collection unit can also collect dance videos uploaded by users. The learning unit uses a generation AI to learn from the video data collected by the collection unit. Learning is performed, for example, based on feature extraction from the video data and classification of movements, but is not limited to such examples. For example, the generation AI extracts dance movements from the video data and performs learning based on the extracted movements. The learning unit can also use the generation AI to learn the differences between professional and amateur dancers. For example, the generation AI compares the movements of professional dancers with those of amateur dancers and learns the differences. Furthermore, the learning unit can use the generation AI to learn the details of dance techniques and movements. For example, the generation AI learns specific techniques and movements, such as the "arabesque" in ballet or the "popping" in hip-hop. The commentary unit uses the generation AI to provide commentary on each dance movement and technique based on the data learned by the learning unit. The commentary may be, for example, in language, but is not limited to such an example. For example, the commentary unit uses the generation AI to provide detailed commentary on dance movements and techniques. The commentary unit can also use the generation AI to explain the differences between professional and amateur dancers. For example, the commentary unit may explain how professional dancers achieve specific techniques and how they differ from amateurs. Furthermore, the commentary unit can use the generation AI to provide visual aids. For example, the commentary unit replays a specific movement in slow motion and provides commentary on the movement in real time.This allows viewers to understand dance techniques in more detail. As a result, the dance commentary system according to the embodiment allows viewers to understand the appeal of dance more deeply and become aware of professional techniques, making dance more appealing to them. For example, when watching a ballet performance, viewers can enjoy the performance more by understanding how professional dancers achieve beautiful arabesques. The system also serves as a useful tool for amateur dancers who want to learn dance techniques to learn professional techniques.

[0030] The commentary unit can provide commentary that specifically explains the differences between professional and amateur dancers. For example, the commentary unit compares the movements of professional and amateur dancers and provides commentary that specifically explains the differences. For example, the commentary unit explains how professional dancers achieve certain techniques and how they differ from amateurs. The commentary unit can also play videos of professional and amateur dancers side by side to visually show the differences. For example, the commentary unit plays the movements of professional and amateur dancers in slow motion and explains the differences. The commentary unit can also provide detailed commentary on the technical differences between professional and amateur dancers. For example, the commentary unit explains how professional dancers maintain balance and how they differ from amateurs. This clearly shows the differences between professionals and amateurs, allowing viewers to gain a deeper understanding of dance techniques. Some or all of the above-described processing in the commentary unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the commentary department can input video data of professional and amateur dancers into the generation AI and have the generation AI generate text explaining the differences between them.

[0031] The commentary unit can play back specific movements in slow motion and provide commentary in real time. For example, the commentary unit plays back a specific movement in slow motion and provides commentary on the movement in real time. For example, the commentary unit plays back a specific technique or movement, such as an "arabesque" in ballet or a "popping" in hip hop, in slow motion and provides detailed commentary on the movement. The commentary unit can also provide commentary in real time using a generation AI during slow motion playback. For example, the commentary unit provides commentary on the movement during slow motion playback. Furthermore, the commentary unit can provide visual aids during slow motion playback. For example, the commentary unit highlights important points of a specific movement during slow motion playback and provides commentary on those points. This allows viewers to understand the dance techniques in detail by playing back in slow motion and providing commentary in real time. Some or all of the above-described processing in the commentary unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the commentary unit can input video data during slow-motion playback into the generation AI and have the generation AI generate commentary about the action.

[0032] The dance commentary system includes a visual aid unit that provides visual aids. For example, the visual aid unit plays back specific movements in slow motion and provides commentary on the movements in real time. For example, the visual aid unit plays back specific techniques or movements, such as ballet "arabesque" or hip-hop "popping," in slow motion and provides detailed commentary on the movements. The visual aid unit can also provide commentary in real time using a generation AI during slow-motion playback. For example, the visual aid unit can provide commentary on the movements during slow-motion playback. Furthermore, the visual aid unit can highlight important points of specific movements and provide commentary on those points during slow-motion playback. This provides visual aids to enable viewers to understand dance techniques in more detail. Some or all of the above-described processing in the visual aid unit may be performed using, or without, the generation AI. For example, the visual aid unit can input video data during slow-motion playback into the generation AI and have the generation AI generate commentary on the movements.

[0033] The dance commentary system includes an interactive unit that accepts questions from viewers. For example, when a viewer asks about a specific movement, the interactive unit provides an explanation in response to the question. For example, when a viewer asks, "What is the key to a ballet arabesque?", the interactive unit uses a generation AI to provide an explanation. The interactive unit can also provide explanations while playing related videos based on the content of the viewer's question. For example, when a viewer asks, "What is the trick to popping in hip-hop?", the interactive unit uses a generation AI to provide an explanation and play related videos. The interactive unit can also provide visual assistance based on the content of the viewer's question. For example, when a viewer asks, "What is the trick to turning in jazz dance?", the interactive unit uses a generation AI to provide an explanation while playing the turning movement in slow motion. This allows viewers to ask questions, deepening their understanding and allowing them to fully appreciate the appeal of dance. Some or all of the above-described processing in the interactive unit may be performed using, or without, the generation AI. For example, the interactive unit can input a viewer's question into the generation AI and have the generation AI generate an explanation for that question.

[0034] When collecting dance videos, the collection unit can analyze the user's past viewing history and select the optimal collection method. For example, the collection unit prioritizes collection of dance genres that the user has previously viewed. For example, the collection unit analyzes the user's viewing history and prioritizes collection of dance genres that the user has previously viewed. The collection unit can also collect similar videos based on dance videos that the user has previously rated highly. For example, the collection unit analyzes the user's viewing history and collects similar videos based on dance videos that the user has previously rated highly. Furthermore, the collection unit can analyze the time periods during which the user previously viewed videos and collect new videos that match those time periods. For example, the collection unit analyzes the user's viewing history and collects new videos that match the time periods during which the user previously viewed videos. In this way, optimal dance videos can be collected by analyzing the user's past viewing history. Some or all of the above-described processing in the collection unit can be performed using, or without, a generation AI. For example, the collection unit can input the user's viewing history data into the generation AI and cause the generation AI to select the optimal collection method.

[0035] When collecting dance videos, the collection unit can filter the videos based on the user's current interests. For example, the collection unit prioritizes collection of dance genres in which the user is currently interested. For example, the collection unit analyzes the user's current interests and prioritizes collection of dance genres in which the user is interested. The collection unit can also collect related dance videos based on keywords recently searched by the user. For example, the collection unit analyzes the user's search history and collects related dance videos based on the recently searched keywords. Furthermore, the collection unit can analyze trends in online communities in which the user participates and collect related videos. For example, the collection unit analyzes trends in online communities in which the user participates and collects related dance videos. This allows for filtering based on the user's current interests and provides more relevant dance videos. Some or all of the above-described processing in the collection unit can be performed using, or without, a generation AI. For example, the collection unit can input the user's interest data into the generation AI and have the generation AI perform filtering.

[0036] When collecting dance videos, the collection unit can select the optimal collection means depending on the user's input method. For example, if the user vocally inputs "I want to watch ballet videos," the collection unit collects ballet videos using voice recognition technology. For example, the collection unit analyzes the user's voice input and collects ballet videos. Alternatively, if the user textually inputs "latest hip hop videos," the collection unit can also collect hip hop videos using text analysis technology. For example, the collection unit analyzes the user's text input and collects hip hop videos. Furthermore, if the user uploads images, the collection unit can also collect related dance videos using image analysis technology. For example, the collection unit analyzes the images uploaded by the user and collects related dance videos. This allows for more efficient collection of dance videos by selecting the optimal collection means depending on the user's input method. Some or all of the above-described processing in the collection unit may be performed using, or without, a generation AI. For example, the collection unit may input the user's input data into a generation AI and have the generation AI select the optimal collection means.

[0037] When collecting dance videos, the collection unit can prioritize collecting highly relevant videos by taking into account the user's geographical location information. For example, if the user is in a specific area, the collection unit collects dance videos that are popular in that area. For example, the collection unit analyzes the user's geographical location information and collects dance videos that are popular in that area. Furthermore, if the user is traveling, the collection unit can collect dance videos related to the culture of the destination. For example, the collection unit analyzes the user's geographical location information and collects dance videos related to the culture of the destination. Furthermore, if the user is at home, the collection unit can collect videos of local dance events. For example, the collection unit analyzes the user's geographical location information and collects videos of local dance events. This allows for providing more relevant dance videos by taking the user's geographical location information into account. Some or all of the above-described processing by the collection unit may be performed using, or without, a generation AI. For example, the collection unit may input the user's geographical location information to the generation AI and cause the generation AI to collect highly relevant videos.

[0038] When collecting dance videos, the collection unit can analyze the user's social media activity and collect related videos. The collection unit, for example, collects videos of dancers the user follows on social media. For example, the collection unit analyzes the user's social media activity and collects videos of the followed dancers. The collection unit can also collect videos related to dance videos the user has "liked" on social media. For example, the collection unit analyzes the user's social media activity and collects videos related to the dance videos the user has "liked." The collection unit can also analyze the content of the user's social media posts and collect related dance videos. For example, the collection unit analyzes the content of the user's social media posts and collects related dance videos. This allows for the provision of more relevant dance videos by analyzing the user's social media activity. Some or all of the above-described processing by the collection unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the collection unit can input the user's social media data into the generation AI and cause the generation AI to collect related videos.

[0039] When collecting dance videos, the collection unit can customize the collection method by reflecting the user's past feedback. For example, the collection unit collects similar videos based on videos that the user has previously rated highly. For example, the collection unit analyzes the user's past feedback and collects similar videos based on videos that the user has previously rated highly. The collection unit can also collect videos while avoiding videos that the user has previously rated poorly. For example, the collection unit analyzes the user's past feedback and collects videos while avoiding videos that the user has previously rated poorly. Furthermore, the collection unit can analyze the user's past feedback and suggest an optimal collection method. For example, the collection unit suggests an optimal collection method based on the user's past feedback. This allows for providing more appropriate dance videos by reflecting the user's past feedback. Some or all of the above-described processing in the collection unit may be performed using, or without, a generation AI. For example, the collection unit can input the user's feedback data into the generation AI and cause the generation AI to customize the collection method.

[0040] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, adjusts optimal learning parameters based on the past learning data. For example, the learning unit analyzes past learning data and adjusts optimal learning parameters. The learning unit can also analyze past learning data to identify areas for improvement in the learning algorithm. For example, the learning unit analyzes past learning data and identifies areas for improvement in the learning algorithm. Furthermore, the learning unit can also improve learning efficiency by referring to past learning data. For example, the learning unit analyzes past learning data and improves learning efficiency. This makes it possible to optimize the learning algorithm by referring to past learning data. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI. For example, the learning unit can input past learning data into the generation AI and cause the generation AI to optimize the learning algorithm.

[0041] The learning unit can apply different learning algorithms to each dance genre during learning. For example, when learning ballet, the learning unit applies an algorithm specialized for specific movements and poses. For example, when learning ballet, the learning unit applies an algorithm specialized for specific movements and poses. The learning unit can also apply an algorithm specialized for rhythm and beat when learning hip hop. For example, when learning hip hop, the learning unit applies an algorithm specialized for rhythm and beat. The learning unit can also apply an algorithm specialized for expressiveness and emotional expression when learning jazz dance. For example, when learning jazz dance, the learning unit applies an algorithm specialized for expressiveness and emotional expression. This enables more effective learning by applying different learning algorithms to each dance genre. Some or all of the above-mentioned processing in the learning unit may be performed using, or without, a generation AI. For example, the learning unit can apply different learning algorithms to the generation AI for each dance genre.

[0042] During learning, the learning unit can update the learning data by reflecting user feedback. For example, the learning unit adds videos that the user has given a high rating to the learning data. For example, the learning unit analyzes the user's feedback and adds videos that the user has given a high rating to the learning data. The learning unit can also exclude videos that the user has given a low rating from the learning data. For example, the learning unit analyzes the user's feedback and excludes videos that the user has given a low rating from the learning data. Furthermore, the learning unit can improve the quality of the learning data based on the user's feedback. For example, the learning unit analyzes the user's feedback and improves the quality of the learning data. In this way, the quality of the learning data can be improved by reflecting the user's feedback. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI. For example, the learning unit can input user feedback data to the generation AI and cause the generation AI to update the learning data.

[0043] During learning, the learning unit can weight the learning data based on the time when the dance videos were collected. For example, the learning unit weights recently collected videos more heavily during learning. For example, the learning unit analyzes when the dance videos were collected and weights recently collected videos more heavily during learning. The learning unit can also weight older videos less heavily during learning. For example, the learning unit analyzes when the dance videos were collected and weights older videos less heavily during learning. Furthermore, the learning unit can adjust the weighting for videos collected during a specific period during learning. For example, the learning unit analyzes when the dance videos were collected and weights videos collected during a specific period during learning. This weighting of the learning data based on when the dance videos were collected enables more effective learning. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI. For example, the learning unit can input data on when the dance videos were collected into the generation AI and have the generation AI weight the learning data.

[0044] During learning, the learning unit can integrate information from different data sources to enrich the training data. For example, the learning unit integrates videos collected from social media into the training data. For example, the learning unit integrates videos collected from social media into the training data. The learning unit can also integrate videos of online dance lessons into the training data. For example, the learning unit integrates videos of online dance lessons into the training data. The learning unit can also integrate videos of dance contests into the training data. For example, the learning unit integrates videos of dance contests into the training data. This allows the quality of the training data to be improved by integrating information from different data sources. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI. For example, the learning unit may input information from different data sources into the generation AI and cause the generation AI to integrate the training data.

[0045] During learning, the learning unit can adjust the learning algorithm according to the user's expertise level. The learning unit, for example, applies a learning algorithm for beginners to learn basic movements. For example, the learning unit analyzes the user's expertise level and applies a learning algorithm for beginners to learn basic movements. The learning unit can also apply a learning algorithm for intermediate users to learn more advanced techniques. For example, the learning unit analyzes the user's expertise level and applies a learning algorithm for intermediate users to learn advanced techniques. The learning unit can also apply a learning algorithm for advanced users to learn professional techniques. For example, the learning unit analyzes the user's expertise level and applies a learning algorithm for advanced users to learn professional techniques. This enables more effective learning by adjusting the learning algorithm according to the user's expertise level. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI. For example, the learning unit may input the user's expertise level data into the generation AI and cause the generation AI to adjust the learning algorithm.

[0046] When providing commentary, the commentary unit can adjust the level of detail of the commentary based on the technical difficulty of the dance. The commentary unit, for example, provides concise commentary for basic movements. For example, the commentary unit analyzes the technical difficulty of the dance and provides concise commentary for basic movements. The commentary unit can also provide detailed commentary for advanced techniques. For example, the commentary unit analyzes the technical difficulty of the dance and provides detailed commentary for advanced techniques. The commentary unit can also provide step-by-step commentary for specific techniques. For example, the commentary unit analyzes the technical difficulty of the dance and provides step-by-step commentary for specific techniques. This allows viewers to deepen their understanding by adjusting the level of detail of the commentary based on the technical difficulty of the dance. Some or all of the above-described processing in the commentary unit may be performed using, or without, a generation AI. For example, the commentary unit can input technical difficulty data for the dance into the generation AI and have the generation AI adjust the level of detail of the commentary.

[0047] The commentary unit can apply different commentary algorithms depending on the dance genre when providing commentary. For example, the commentary unit uses classical expressions when providing commentary on ballet. For example, the commentary unit analyzes the dance genre and uses classical expressions when providing commentary on ballet. The commentary unit can also use casual expressions when providing commentary on hip hop. For example, the commentary unit analyzes the dance genre and uses casual expressions when providing commentary on hip hop. The commentary unit can also use elegant expressions when providing commentary on jazz dance. For example, the commentary unit analyzes the dance genre and uses elegant expressions when providing commentary on jazz dance. This allows for different commentary algorithms to be applied depending on the dance genre, thereby deepening the viewer's understanding. Some or all of the above-mentioned processing in the commentary unit may be performed using, or without, a generation AI. For example, the commentary unit can input dance genre data into the generation AI and cause the generation AI to apply the commentary algorithm.

[0048] When providing commentary, the commentary unit can improve the accuracy of the commentary by referring to the user's past commentary results. The commentary unit, for example, provides commentary based on commentary styles that the user has previously rated highly. For example, the commentary unit analyzes the user's past commentary results and provides commentary based on commentary styles that the user has previously rated highly. The commentary unit can also provide commentary while avoiding commentary styles that the user has previously rated poorly. For example, the commentary unit analyzes the user's past commentary results and provides commentary while avoiding commentary styles that the user has previously rated poorly. Furthermore, the commentary unit can analyze the user's past commentary results and suggest an optimal commentary method. For example, the commentary unit analyzes the user's past commentary results and suggests an optimal commentary method. This improves the accuracy of the commentary by referring to the user's past commentary results. Some or all of the above-described processing in the commentary unit may be performed using, or without, a generation AI. For example, the commentary unit can input the user's past commentary result data into the generation AI and cause the generation AI to improve the accuracy of the commentary.

[0049] When providing commentary, the commentary unit can determine the priority of commentary based on the time of the dance performance. For example, the commentary unit prioritizes commentary on the most recent dance performance. For example, the commentary unit analyzes the time of the dance performance and prioritizes commentary on the most recent dance performance. The commentary unit can also provide commentary on past great performances as appropriate. For example, the commentary unit analyzes the time of the dance performance and provides commentary on past great performances as appropriate. Furthermore, the commentary unit can provide related commentary based on upcoming performance schedules. For example, the commentary unit analyzes the time of the dance performance and provides related commentary based on upcoming performance schedules. In this way, determining the priority of commentary based on the time of the dance performance deepens the viewer's understanding. Some or all of the above-mentioned processing in the commentary unit may be performed using, or without, a generation AI. For example, the commentary unit can input dance performance time data into the generation AI and have the generation AI determine the priority of commentary.

[0050] The commentary unit can adjust the order of commentary based on the relevance of the dances during commentary. For example, the commentary unit provides consecutive commentary on dances of the same genre. For example, the commentary unit analyzes the relevance of dances and provides consecutive commentary on dances of the same genre. The commentary unit can also provide commentary related to specific techniques or movements in a group. For example, the commentary unit analyzes the relevance of dances and provides commentary related to specific techniques or movements in a group. Furthermore, the commentary unit can prioritize highly relevant commentary based on the user's interests. For example, the commentary unit analyzes the relevance of dances and prioritizes highly relevant commentary based on the user's interests. This allows viewers to deepen their understanding by adjusting the order of commentary based on the relevance of dances. Some or all of the above-described processing in the commentary unit may be performed using, or without, a generation AI. For example, the commentary unit can input dance relevance data into the generation AI and cause the generation AI to adjust the order of commentary.

[0051] The commentary unit can adjust the use of technical terms in the commentary depending on the user's level of expertise during commentary. For example, the commentary unit provides commentary in simple language, avoiding technical terms, for beginners. For example, the commentary unit analyzes the user's level of expertise and provides commentary in simple language, avoiding technical terms, for beginners. The commentary unit can also provide commentary using technical terms moderately for intermediate users. For example, the commentary unit analyzes the user's level of expertise and provides commentary using technical terms moderately for intermediate users. Furthermore, the commentary unit can provide detailed commentary using a lot of technical terms for advanced users. For example, the commentary unit analyzes the user's level of expertise and provides detailed commentary using a lot of technical terms for advanced users. This allows viewers to deepen their understanding by adjusting the use of technical terms in the commentary depending on the user's level of expertise. Some or all of the above-described processing in the commentary unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the commentary unit can input the user's expertise level data into the generation AI and have the generation AI adjust the use of technical terms in the commentary.

[0052] When displaying a visual aid, the visual aid unit can select the optimal display method by referring to the user's past visual aid usage history. The visual aid unit, for example, performs optimal display based on the user's preferred display method in the past. For example, the visual aid unit analyzes the user's past visual aid usage history and performs optimal display based on the preferred display method. The visual aid unit can also perform display while avoiding display methods that the user avoided in the past. For example, the visual aid unit analyzes the user's past visual aid usage history and performs display while avoiding the avoided display methods. Furthermore, the visual aid unit can analyze the user's past usage history and suggest the optimal display method. For example, the visual aid unit analyzes the user's past visual aid usage history and suggests the optimal display method. In this way, the optimal display method can be provided by referring to the user's past visual aid usage history. Some or all of the above-described processing in the visual aid unit may be performed using, or without, a generation AI. For example, the visual aid unit can input the user's past visual aid usage history data into the generation AI and have the generation AI select the optimal display method.

[0053] When displaying visual aids, the visual aid unit can customize the display content according to the user's current task. For example, if the user is studying, the visual aid unit displays visual aids that are useful for studying. For example, the visual aid unit analyzes the user's current task and, if the user is studying, displays visual aids that are useful for studying. Furthermore, if the user is relaxing, the visual aid unit can display visual aids suitable for relaxation. For example, the visual aid unit analyzes the user's current task and, if the user is relaxing, displays visual aids suitable for relaxation. Furthermore, if the user is enjoying entertainment, the visual aid unit can display visual aids suitable for entertainment. For example, the visual aid unit analyzes the user's current task and, if the user is enjoying entertainment, displays visual aids suitable for entertainment. This allows the viewer to deepen their understanding by customizing the display content according to the user's current task. Some or all of the above-described processing in the visual aid unit may be performed using, or without, a generation AI. For example, the visual aid unit can input the user's current task data into the generation AI and have the generation AI customize the display content.

[0054] The visual aid unit can select the optimal display method by taking into account the user's device information when displaying visual aids. For example, if the user is using a smartphone, the visual aid unit provides a display method tailored to the screen size. For example, the visual aid unit analyzes the user's device information and provides a display method tailored to the screen size when using a smartphone. Furthermore, if the user is using a tablet, the visual aid unit can provide a display method optimized for a large screen. For example, the visual aid unit analyzes the user's device information and provides a display method optimized for a large screen when using a tablet. Furthermore, the visual aid unit can provide a simple and highly visible display method when using a smartwatch. For example, the visual aid unit analyzes the user's device information and provides a simple and highly visible display method when using a smartwatch. This allows the optimal display method to be provided by taking the user's device information into consideration. Some or all of the above-described processing in the visual aid unit may be performed using, or without, a generation AI. For example, the visual aid unit can input the user's device information into the generation AI and cause the generation AI to select the optimal display method.

[0055] The visual aid unit can make the display content multilingual according to the user's language setting when displaying the visual aid. The visual aid unit automatically sets the display content based on, for example, the language setting of the user's device. For example, the visual aid unit analyzes the language setting of the user's device and automatically sets the display content. The visual aid unit can also provide a language switching function when the user uses multiple languages. For example, the visual aid unit analyzes the user's language setting and provides a language switching function when the user uses multiple languages. Furthermore, the visual aid unit can provide the display content in a specific language when the user selects that language. For example, the visual aid unit analyzes the user's language setting and provides the display content in that language when the user selects a specific language. This allows the viewer to understand the display content in multiple languages ​​according to the user's language setting, thereby deepening the viewer's understanding. Some or all of the above-described processing in the visual aid unit may be performed using, or without, a generation AI. For example, the visual aid unit can input the user's language setting data into the generation AI and have the generation AI perform multilingual support for the display content.

[0056] During interactive question-answering, the interactive unit can select the optimal response method by referring to the user's past question history. The interactive unit, for example, provides the optimal response based on the content of questions asked by the user in the past. For example, the interactive unit analyzes the user's past question history and provides the optimal response based on the content of questions asked in the past. The interactive unit can also provide a response that avoids response methods that the user has avoided in the past. For example, the interactive unit analyzes the user's past question history and provides a response that avoids the response methods that the user has avoided in the past. Furthermore, the interactive unit can analyze the user's past question history and suggest the optimal response method. For example, the interactive unit analyzes the user's past question history and suggests the optimal response method. In this way, the optimal response method can be provided by referring to the user's past question history. Some or all of the above-described processing in the interactive unit may be performed using, or without, a generation AI. For example, the interactive unit can input the user's past question history data into the generation AI and have the generation AI select the optimal response method.

[0057] The interactive unit can customize the response content according to the user's current interests during interactive question-answering. The interactive unit, for example, provides a response based on topics in which the user is currently interested. For example, the interactive unit analyzes the user's current interests and provides a response based on the topics of interest. The interactive unit can also provide a response based on keywords recently searched by the user. For example, the interactive unit analyzes the user's search history and provides a response based on the recently searched keywords. The interactive unit can also analyze trends in online communities in which the user participates and provide relevant responses. For example, the interactive unit analyzes trends in online communities in which the user participates and provides relevant responses. This allows the viewer to deepen their understanding by customizing the response content according to the user's current interests. Some or all of the above-described processing in the interactive unit may be performed using, or without, a generation AI. For example, the interactive unit can input the user's current interest data into the generation AI and have the generation AI customize the response content.

[0058] The interactive unit can select the optimal response method during interactive question answering by taking into account the user's device information. For example, if the user is using a smartphone, the interactive unit provides a response method tailored to the screen size. For example, the interactive unit analyzes the user's device information and provides a response method tailored to the screen size when the user is using a smartphone. The interactive unit can also provide a response method optimized for a large screen when the user is using a tablet. For example, the interactive unit analyzes the user's device information and provides a response method optimized for a large screen when the user is using a tablet. Furthermore, the interactive unit can also provide a concise and highly visible response method when the user is using a smartwatch. For example, the interactive unit analyzes the user's device information and provides a concise and highly visible response method when the user is using a smartwatch. This makes it possible to provide the optimal response method by taking the user's device information into consideration. Some or all of the above-described processing in the interactive unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the interactive unit can input the user's device information into the generation AI and cause the generation AI to select the optimal response method.

[0059] The interactive unit can make the response content multilingual according to the user's language setting during interactive question-answering. The interactive unit, for example, automatically sets the response content based on the language setting of the user's device. For example, the interactive unit analyzes the language setting of the user's device and automatically sets the response content. The interactive unit can also provide a language switching function when the user uses multiple languages. For example, the interactive unit analyzes the user's language setting and provides a language switching function when the user uses multiple languages. Furthermore, the interactive unit can provide the response content in a specific language when the user selects that language. For example, the interactive unit analyzes the user's language setting and provides the response content in that language when the user selects a specific language. This allows the viewer to understand the response content in multiple languages ​​according to the user's language setting, thereby deepening the viewer's understanding. Some or all of the above-described processing in the interactive unit may be performed using, or without, a generation AI. For example, the interactive unit can input the user's language setting data into the generation AI and cause the generation AI to perform multilingual support for the response content.

[0060] The interactive unit can analyze the user's social media activity and provide related information during interactive question and answering. For example, the interactive unit can provide information about places where the user has checked in on social media. For example, the interactive unit can analyze the user's social media activity and provide information about the checked-in places. The interactive unit can also analyze the user's social media posts and provide information about related tourist spots and stores. For example, the interactive unit can analyze the user's social media activity and provide information about related tourist spots and stores based on the posted content. Furthermore, the interactive unit can provide information about related places and events based on the activities of the user's friends on social media. For example, the interactive unit can analyze the user's social media activity and provide information about related places and events based on the friends' activities. In this way, related information can be provided by analyzing the user's social media activity. Some or all of the above-described processing in the interactive unit can be performed using, or without, a generation AI. For example, the interactive unit can input the user's social media data into the generation AI and cause the generation AI to provide related information.

[0061] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0062] The collection unit can detect the user's physical movements using a sensor and collect related dance videos based on the movements. For example, the collection unit can detect the user's hand-raising movement and collect ballet videos related to that movement. The collection unit can also detect the user's foot-moving movement and collect hip-hop videos related to that movement. Furthermore, the collection unit can detect the user's jumping movement and collect jazz dance videos related to that movement. This makes it easier to attract viewers' interest by providing related dance videos based on the user's physical movements. Some or all of the above-described processing by the collection unit can be performed using, or without, a generation AI. For example, the collection unit can input the user's movement data into the generation AI and cause the generation AI to collect related videos.

[0063] The commentary unit can customize the commentary style based on the user's visual preferences. For example, if the user likes animation, the commentary unit can provide commentary that makes extensive use of animation. Furthermore, if the user likes live-action footage, the commentary unit can provide commentary using live-action footage. Furthermore, if the user likes infographics, the commentary unit can provide commentary using infographics. This allows the commentary style to be customized based on the user's visual preferences, making it easier for viewers to deepen their understanding. Some or all of the above-described processing in the commentary unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the commentary unit can input the user's visual preference data into the generation AI and cause the generation AI to customize the commentary style.

[0064] The collection unit can collect dance styles by region taking into account the user's geographical location information. For example, if the user is in Africa, the collection unit can collect traditional African dance videos. If the user is in South America, the collection unit can collect videos of samba, tango, and the like. Furthermore, if the user is in Asia, the collection unit can collect traditional Asian dance videos. This makes it easier to attract viewers' interest by providing dance styles by region based on the user's geographical location information. Some or all of the above-described processing by the collection unit can be performed using, or without, a generation AI. For example, the collection unit can input the user's geographical location information into the generation AI and cause the generation AI to collect dance videos by region.

[0065] The learning unit can reflect user feedback in real time and dynamically update the learning data. For example, the learning unit can instantly add videos that users have rated highly to the learning data. The learning unit can also instantly remove videos that users have rated poorly from the learning data. Furthermore, the learning unit can adjust the learning algorithm based on user feedback to perform more effective learning. This allows the quality of the learning data to be improved by reflecting user feedback in real time. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI. For example, the learning unit can input user feedback data into the generation AI and cause the generation AI to dynamically update the learning data.

[0066] The commentary unit can adjust the depth of the commentary according to the user's level of expertise. For example, the commentary unit can provide basic commentary for beginners. The commentary unit can also provide more detailed commentary for intermediate users. The commentary unit can also provide specialized commentary for advanced users. This makes it easier for viewers to deepen their understanding by adjusting the depth of the commentary according to the user's level of expertise. Some or all of the above-mentioned processing in the commentary unit may be performed using, or without, a generation AI. For example, the commentary unit can input the user's level of expertise data into the generation AI and have the generation AI adjust the depth of the commentary.

[0067] The visual aid unit can adjust the quality of the visual aid according to the performance of the user's device. For example, the visual aid unit can provide high-resolution visual aids when a high-performance device is used. The visual aid unit can also provide low-resolution visual aids when a low-performance device is used. Furthermore, the visual aid unit can adjust the quality of the visual aid according to the remaining battery level of the device. This improves the viewer's experience by adjusting the quality of the visual aid according to the performance of the user's device. Some or all of the above-described processing in the visual aid unit can be performed using, or without, a generation AI. For example, the visual aid unit can input the user's device information into the generation AI and cause the generation AI to adjust the quality of the visual aid.

[0068] The interactive unit can analyze the user's past question history and automatically generate related questions. For example, the interactive unit can generate new related questions based on the content of questions the user has previously asked. The interactive unit can also generate questions based on topics in which the user has previously shown interest. Furthermore, the interactive unit can analyze the user's past question history and generate follow-up questions to unresolved questions. In this way, by analyzing the user's past question history, more relevant questions can be provided. Some or all of the above-mentioned processing in the interactive unit may be performed using, or without, a generation AI. For example, the interactive unit can input the user's question history data into the generation AI and cause the generation AI to automatically generate related questions.

[0069] The processing flow of the first embodiment will be briefly explained below.

[0070] Step 1: The collection unit collects dance video data. The dance video data includes videos of professional and amateur dancers. The collection unit collects dance videos of various genres, such as ballet, hip hop, and jazz dance. The collection unit can also collect video data from multiple sources, such as publicly available videos on the Internet, videos filmed in dance studios, and dance videos uploaded by users. For example, dance videos can be automatically collected from video sharing sites on the Internet, or videos filmed in dance studios can be directly collected. Step 2: The learning unit uses the generation AI to learn the video data collected by the collection unit. Learning is based on extracting features from the video data and classifying movements. For example, the generation AI extracts dance movements from the video data and learns based on them. It can also learn about the differences between professional and amateur dancers, as well as specific techniques and movements (e.g., "arabesque" in ballet and "popping" in hip hop). Step 3: The commentary section uses the generative AI to provide commentary on each dance movement and technique based on the data learned by the learning section. The commentary is verbal, but visual aids can also be provided. For example, a specific movement can be replayed in slow motion and commented on in real time. It can also explain the differences between professional and amateur dancers.

[0071] (Example 2) A dance commentary system according to an embodiment of the present invention collects dance video data, trains a generation AI, and provides commentary on each dance movement and technique. The dance commentary system collects dance video data and provides commentary on each dance movement and technique based on the data learned by the generation AI. For example, the dance commentary system may collect a balanced collection of videos of professional and amateur dancers and train the generation AI. Next, based on the data learned by the generation AI, it provides verbal commentary on each dance movement and technique. For example, it may provide detailed commentary on specific techniques and movements, such as the "arabesque" in ballet or the "popping" in hip-hop. Furthermore, the dance commentary system may provide visual aids. For example, it may replay a specific movement in slow motion and have the generation AI provide commentary on that movement in real time. This allows viewers to understand dance techniques in more detail. The dance commentary system also has an interactive feature that allows viewers to ask questions. For example, when a viewer asks a question about a specific movement, the generation AI provides commentary in response to the question. This allows viewers to gain a deeper understanding of the appeal of dance, recognize professional techniques, and find dance more appealing. This allows viewers to gain a deeper understanding of the appeal of dance and become more aware of professional techniques, making dance more appealing to them. For example, when watching a ballet performance, viewers can enjoy the performance more by understanding how professional dancers achieve beautiful arabesques. It can also be a useful tool for amateur dancers who want to learn dance techniques.

[0072] A dance commentary system according to an embodiment includes a collection unit, a learning unit, and a commentary unit. The collection unit collects dance video data. The dance video data includes, for example, videos of professional and amateur dancers, but is not limited to, such examples. The collection unit collects dance videos of various genres, such as ballet, hip hop, and jazz dance. The collection unit can also collect video data from multiple sources, such as publicly available videos on the Internet and videos filmed in dance studios. For example, the collection unit automatically collects dance videos from video sharing sites on the Internet. The collection unit can also directly collect videos filmed in dance studios. The collection unit can also collect dance videos uploaded by users. The learning unit uses a generation AI to learn from the video data collected by the collection unit. Learning is performed, for example, based on feature extraction from the video data and classification of movements, but is not limited to such examples. For example, the generation AI extracts dance movements from the video data and performs learning based on the extracted movements. The learning unit can also use the generation AI to learn the differences between professional and amateur dancers. For example, the generation AI compares the movements of professional dancers with those of amateur dancers and learns the differences. Furthermore, the learning unit can use the generation AI to learn the details of dance techniques and movements. For example, the generation AI learns specific techniques and movements, such as the "arabesque" in ballet or the "popping" in hip-hop. The commentary unit uses the generation AI to provide commentary on each dance movement and technique based on the data learned by the learning unit. The commentary may be, for example, in language, but is not limited to such an example. For example, the commentary unit uses the generation AI to provide detailed commentary on dance movements and techniques. The commentary unit can also use the generation AI to explain the differences between professional and amateur dancers. For example, the commentary unit may explain how professional dancers achieve specific techniques and how they differ from amateurs. Furthermore, the commentary unit can use the generation AI to provide visual aids. For example, the commentary unit replays a specific movement in slow motion and provides commentary on the movement in real time.This allows viewers to understand dance techniques in more detail. As a result, the dance commentary system according to the embodiment allows viewers to understand the appeal of dance more deeply and become aware of professional techniques, making dance more appealing to them. For example, when watching a ballet performance, viewers can enjoy the performance more by understanding how professional dancers achieve beautiful arabesques. The system also serves as a useful tool for amateur dancers who want to learn dance techniques to learn professional techniques.

[0073] The commentary unit can provide commentary that specifically explains the differences between professional and amateur dancers. For example, the commentary unit compares the movements of professional and amateur dancers and provides commentary that specifically explains the differences. For example, the commentary unit explains how professional dancers achieve certain techniques and how they differ from amateurs. The commentary unit can also play videos of professional and amateur dancers side by side to visually show the differences. For example, the commentary unit plays the movements of professional and amateur dancers in slow motion and explains the differences. The commentary unit can also provide detailed commentary on the technical differences between professional and amateur dancers. For example, the commentary unit explains how professional dancers maintain balance and how they differ from amateurs. This clearly shows the differences between professionals and amateurs, allowing viewers to gain a deeper understanding of dance techniques. Some or all of the above-described processing in the commentary unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the commentary department can input video data of professional and amateur dancers into the generation AI and have the generation AI generate text explaining the differences between them.

[0074] The commentary unit can play back specific movements in slow motion and provide commentary in real time. For example, the commentary unit plays back a specific movement in slow motion and provides commentary on the movement in real time. For example, the commentary unit plays back a specific technique or movement, such as an "arabesque" in ballet or a "popping" in hip hop, in slow motion and provides detailed commentary on the movement. The commentary unit can also provide commentary in real time using a generation AI during slow motion playback. For example, the commentary unit provides commentary on the movement during slow motion playback. Furthermore, the commentary unit can provide visual aids during slow motion playback. For example, the commentary unit highlights important points of a specific movement during slow motion playback and provides commentary on those points. This allows viewers to understand the dance techniques in detail by playing back in slow motion and providing commentary in real time. Some or all of the above-described processing in the commentary unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the commentary unit can input video data during slow-motion playback into the generation AI and have the generation AI generate commentary about the action.

[0075] The dance commentary system includes a visual aid unit that provides visual aids. For example, the visual aid unit plays back specific movements in slow motion and provides commentary on the movements in real time. For example, the visual aid unit plays back specific techniques or movements, such as ballet "arabesque" or hip-hop "popping," in slow motion and provides detailed commentary on the movements. The visual aid unit can also provide commentary in real time using a generation AI during slow-motion playback. For example, the visual aid unit can provide commentary on the movements during slow-motion playback. Furthermore, the visual aid unit can highlight important points of specific movements and provide commentary on those points during slow-motion playback. This provides visual aids to enable viewers to understand dance techniques in more detail. Some or all of the above-described processing in the visual aid unit may be performed using, or without, the generation AI. For example, the visual aid unit can input video data during slow-motion playback into the generation AI and have the generation AI generate commentary on the movements.

[0076] The dance commentary system includes an interactive unit that accepts questions from viewers. For example, when a viewer asks about a specific movement, the interactive unit provides an explanation in response to the question. For example, when a viewer asks, "What is the key to a ballet arabesque?", the interactive unit uses a generation AI to provide an explanation. The interactive unit can also provide explanations while playing related videos based on the content of the viewer's question. For example, when a viewer asks, "What is the trick to popping in hip-hop?", the interactive unit uses a generation AI to provide an explanation and play related videos. The interactive unit can also provide visual assistance based on the content of the viewer's question. For example, when a viewer asks, "What is the trick to turning in jazz dance?", the interactive unit uses a generation AI to provide an explanation while playing the turning movement in slow motion. This allows viewers to ask questions, deepening their understanding and allowing them to fully appreciate the appeal of dance. Some or all of the above-described processing in the interactive unit may be performed using, or without, the generation AI. For example, the interactive unit can input a viewer's question into the generation AI and have the generation AI generate an explanation for that question.

[0077] The dance commentary system includes a collection unit that estimates a user's emotions and adjusts the timing of dance video collection based on the estimated user emotions. For example, if the user is excited, the collection unit collects new dance videos in real time and provides them immediately. For example, the collection unit analyzes the user's emotions and determines that the user is excited, and then collects and provides the latest dance videos. Furthermore, if the user is relaxed, the collection unit can provide previously collected videos again, providing a stable viewing experience. For example, the collection unit analyzes the user's emotions and determines that the user is relaxed, and then provides previously collected videos again. Furthermore, if the user is tired, the collection unit can prioritize collecting dance videos that can be viewed in a short time. For example, if the collection unit analyzes the user's emotions and determines that the user is tired, it prioritizes collecting dance videos that can be viewed in a short time. By adjusting the collection timing based on the user's emotions, dance videos can be provided at more appropriate times. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit may input user emotion data into the generation AI and cause the generation AI to adjust the collection timing.

[0078] When collecting dance videos, the collection unit can analyze the user's past viewing history and select the optimal collection method. For example, the collection unit prioritizes collection of dance genres that the user has previously viewed. For example, the collection unit analyzes the user's viewing history and prioritizes collection of dance genres that the user has previously viewed. The collection unit can also collect similar videos based on dance videos that the user has previously rated highly. For example, the collection unit analyzes the user's viewing history and collects similar videos based on dance videos that the user has previously rated highly. Furthermore, the collection unit can analyze the time periods during which the user previously viewed videos and collect new videos that match those time periods. For example, the collection unit analyzes the user's viewing history and collects new videos that match the time periods during which the user previously viewed videos. In this way, optimal dance videos can be collected by analyzing the user's past viewing history. Some or all of the above-described processing in the collection unit can be performed using, or without, a generation AI. For example, the collection unit can input the user's viewing history data into the generation AI and cause the generation AI to select the optimal collection method.

[0079] When collecting dance videos, the collection unit can filter the videos based on the user's current interests. For example, the collection unit prioritizes collection of dance genres in which the user is currently interested. For example, the collection unit analyzes the user's current interests and prioritizes collection of dance genres in which the user is interested. The collection unit can also collect related dance videos based on keywords recently searched by the user. For example, the collection unit analyzes the user's search history and collects related dance videos based on the recently searched keywords. Furthermore, the collection unit can analyze trends in online communities in which the user participates and collect related videos. For example, the collection unit analyzes trends in online communities in which the user participates and collects related dance videos. This allows for filtering based on the user's current interests and provides more relevant dance videos. Some or all of the above-described processing in the collection unit can be performed using, or without, a generation AI. For example, the collection unit can input the user's interest data into the generation AI and have the generation AI perform filtering.

[0080] When collecting dance videos, the collection unit can select the optimal collection means depending on the user's input method. For example, if the user vocally inputs "I want to watch ballet videos," the collection unit collects ballet videos using voice recognition technology. For example, the collection unit analyzes the user's voice input and collects ballet videos. Alternatively, if the user textually inputs "latest hip hop videos," the collection unit can also collect hip hop videos using text analysis technology. For example, the collection unit analyzes the user's text input and collects hip hop videos. Furthermore, if the user uploads images, the collection unit can also collect related dance videos using image analysis technology. For example, the collection unit analyzes the images uploaded by the user and collects related dance videos. This allows for more efficient collection of dance videos by selecting the optimal collection means depending on the user's input method. Some or all of the above-described processing in the collection unit may be performed using, or without, a generation AI. For example, the collection unit may input the user's input data into a generation AI and have the generation AI select the optimal collection means.

[0081] The collection unit can estimate the user's emotions and prioritize the dance videos to be collected based on the estimated user emotions. For example, if the user is excited, the collection unit prioritizes collecting energetic dance videos. For example, if the collection unit analyzes the user's emotions and determines that the user is excited, it prioritizes collecting energetic dance videos. The collection unit can also prioritize collecting slow dance videos if the user is relaxed. For example, if the collection unit analyzes the user's emotions and determines that the user is relaxed, it prioritizes collecting slow dance videos. Furthermore, if the user is sad, the collection unit can prioritize collecting moving dance videos. For example, if the collection unit analyzes the user's emotions and determines that the user is sad, it prioritizes collecting moving dance videos. This allows for more appropriate videos to be provided by prioritizing the dance videos to be collected 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. Some or all of the above-described processing in the collection unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the collection unit may input user emotion data into the generation AI and have the generation AI determine the priority of the dance videos to be collected.

[0082] When collecting dance videos, the collection unit can prioritize collecting highly relevant videos by taking into account the user's geographical location information. For example, if the user is in a specific area, the collection unit collects dance videos that are popular in that area. For example, the collection unit analyzes the user's geographical location information and collects dance videos that are popular in that area. Furthermore, if the user is traveling, the collection unit can collect dance videos related to the culture of the destination. For example, the collection unit analyzes the user's geographical location information and collects dance videos related to the culture of the destination. Furthermore, if the user is at home, the collection unit can collect videos of local dance events. For example, the collection unit analyzes the user's geographical location information and collects videos of local dance events. This allows for providing more relevant dance videos by taking the user's geographical location information into account. Some or all of the above-described processing by the collection unit may be performed using, or without, a generation AI. For example, the collection unit may input the user's geographical location information to the generation AI and cause the generation AI to collect highly relevant videos.

[0083] When collecting dance videos, the collection unit can analyze the user's social media activity and collect related videos. The collection unit, for example, collects videos of dancers the user follows on social media. For example, the collection unit analyzes the user's social media activity and collects videos of the followed dancers. The collection unit can also collect videos related to dance videos the user has "liked" on social media. For example, the collection unit analyzes the user's social media activity and collects videos related to the dance videos the user has "liked." The collection unit can also analyze the content of the user's social media posts and collect related dance videos. For example, the collection unit analyzes the content of the user's social media posts and collects related dance videos. This allows for the provision of more relevant dance videos by analyzing the user's social media activity. Some or all of the above-described processing by the collection unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the collection unit can input the user's social media data into the generation AI and cause the generation AI to collect related videos.

[0084] When collecting dance videos, the collection unit can customize the collection method by reflecting the user's past feedback. For example, the collection unit collects similar videos based on videos that the user has previously rated highly. For example, the collection unit analyzes the user's past feedback and collects similar videos based on videos that the user has previously rated highly. The collection unit can also collect videos while avoiding videos that the user has previously rated poorly. For example, the collection unit analyzes the user's past feedback and collects videos while avoiding videos that the user has previously rated poorly. Furthermore, the collection unit can analyze the user's past feedback and suggest an optimal collection method. For example, the collection unit suggests an optimal collection method based on the user's past feedback. This allows for providing more appropriate dance videos by reflecting the user's past feedback. Some or all of the above-described processing in the collection unit may be performed using, or without, a generation AI. For example, the collection unit can input the user's feedback data into the generation AI and cause the generation AI to customize the collection method.

[0085] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, if the user is excited, the learning unit selects energetic dance videos as training data. For example, if the learning unit analyzes the user's emotions and determines that the user is excited, it selects energetic dance videos as training data. Furthermore, if the user is relaxed, the learning unit can select slow dance videos as training data. For example, if the learning unit analyzes the user's emotions and determines that the user is relaxed, it selects slow dance videos as training data. Furthermore, if the user is sad, the learning unit can select moving dance videos as training data. For example, if the learning unit analyzes the user's emotions and determines that the user is sad, it selects moving dance videos as training data. This enables more effective learning by selecting training data based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the learning unit may input user emotion data to the generation AI and have the generation AI select learning data.

[0086] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, adjusts optimal learning parameters based on the past learning data. For example, the learning unit analyzes past learning data and adjusts optimal learning parameters. The learning unit can also analyze past learning data to identify areas for improvement in the learning algorithm. For example, the learning unit analyzes past learning data and identifies areas for improvement in the learning algorithm. Furthermore, the learning unit can also improve learning efficiency by referring to past learning data. For example, the learning unit analyzes past learning data and improves learning efficiency. This makes it possible to optimize the learning algorithm by referring to past learning data. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI. For example, the learning unit can input past learning data into the generation AI and cause the generation AI to optimize the learning algorithm.

[0087] The learning unit can apply different learning algorithms to each dance genre during learning. For example, when learning ballet, the learning unit applies an algorithm specialized for specific movements and poses. For example, when learning ballet, the learning unit applies an algorithm specialized for specific movements and poses. The learning unit can also apply an algorithm specialized for rhythm and beat when learning hip hop. For example, when learning hip hop, the learning unit applies an algorithm specialized for rhythm and beat. The learning unit can also apply an algorithm specialized for expressiveness and emotional expression when learning jazz dance. For example, when learning jazz dance, the learning unit applies an algorithm specialized for expressiveness and emotional expression. This enables more effective learning by applying different learning algorithms to each dance genre. Some or all of the above-mentioned processing in the learning unit may be performed using, or without, a generation AI. For example, the learning unit can apply different learning algorithms to the generation AI for each dance genre.

[0088] During learning, the learning unit can update the learning data by reflecting user feedback. For example, the learning unit adds videos that the user has given a high rating to the learning data. For example, the learning unit analyzes the user's feedback and adds videos that the user has given a high rating to the learning data. The learning unit can also exclude videos that the user has given a low rating from the learning data. For example, the learning unit analyzes the user's feedback and excludes videos that the user has given a low rating from the learning data. Furthermore, the learning unit can improve the quality of the learning data based on the user's feedback. For example, the learning unit analyzes the user's feedback and improves the quality of the learning data. In this way, the quality of the learning data can be improved by reflecting the user's feedback. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI. For example, the learning unit can input user feedback data to the generation AI and cause the generation AI to update the learning data.

[0089] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated user emotions. For example, if the user is excited, the learning unit increases the learning frequency to quickly learn new data. For example, if the learning unit analyzes the user's emotions and determines that the user is excited, it increases the learning frequency to quickly learn new data. The learning unit can also reduce the learning frequency to perform stable learning if the user is relaxed. For example, if the learning unit analyzes the user's emotions and determines that the user is relaxed, it reduces the learning frequency to perform stable learning. Furthermore, the learning unit can adjust the learning frequency to reduce the burden on the user if the user is tired. For example, if the learning unit analyzes the user's emotions and determines that the user is tired, it adjusts the learning frequency to reduce the burden. This enables more effective learning by adjusting the learning frequency based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the learning unit may input user emotion data into the generation AI and cause the generation AI to adjust the frequency of learning.

[0090] During learning, the learning unit can weight the learning data based on the time when the dance videos were collected. For example, the learning unit weights recently collected videos more heavily during learning. For example, the learning unit analyzes when the dance videos were collected and weights recently collected videos more heavily during learning. The learning unit can also weight older videos less heavily during learning. For example, the learning unit analyzes when the dance videos were collected and weights older videos less heavily during learning. Furthermore, the learning unit can adjust the weighting for videos collected during a specific period during learning. For example, the learning unit analyzes when the dance videos were collected and weights videos collected during a specific period during learning. This weighting of the learning data based on when the dance videos were collected enables more effective learning. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI. For example, the learning unit can input data on when the dance videos were collected into the generation AI and have the generation AI weight the learning data.

[0091] During learning, the learning unit can integrate information from different data sources to enrich the training data. For example, the learning unit integrates videos collected from social media into the training data. For example, the learning unit integrates videos collected from social media into the training data. The learning unit can also integrate videos of online dance lessons into the training data. For example, the learning unit integrates videos of online dance lessons into the training data. The learning unit can also integrate videos of dance contests into the training data. For example, the learning unit integrates videos of dance contests into the training data. This allows the quality of the training data to be improved by integrating information from different data sources. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI. For example, the learning unit may input information from different data sources into the generation AI and cause the generation AI to integrate the training data.

[0092] During learning, the learning unit can adjust the learning algorithm according to the user's expertise level. The learning unit, for example, applies a learning algorithm for beginners to learn basic movements. For example, the learning unit analyzes the user's expertise level and applies a learning algorithm for beginners to learn basic movements. The learning unit can also apply a learning algorithm for intermediate users to learn more advanced techniques. For example, the learning unit analyzes the user's expertise level and applies a learning algorithm for intermediate users to learn advanced techniques. The learning unit can also apply a learning algorithm for advanced users to learn professional techniques. For example, the learning unit analyzes the user's expertise level and applies a learning algorithm for advanced users to learn professional techniques. This enables more effective learning by adjusting the learning algorithm according to the user's expertise level. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI. For example, the learning unit may input the user's expertise level data into the generation AI and cause the generation AI to adjust the learning algorithm.

[0093] The commentary unit can estimate the user's emotions and adjust the way the commentary is expressed based on the estimated user's emotions. For example, if the user is excited, the commentary unit uses energetic expressions to provide commentary. For example, if the commentary unit analyzes the user's emotions and determines that the user is excited, it uses energetic expressions to provide commentary. Furthermore, if the user is relaxed, the commentary unit can use calm expressions to provide commentary. For example, if the commentary unit analyzes the user's emotions and determines that the user is relaxed, it uses calm expressions to provide commentary. Furthermore, if the user is sad, the commentary unit can use moving expressions to provide commentary. For example, if the commentary unit analyzes the user's emotions and determines that the user is sad, it uses moving expressions to provide commentary. This allows for more effective commentary by adjusting the way the commentary is expressed based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the commentary unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the commentary unit may input user emotion data into the generation AI and have the generation AI adjust the way the commentary is expressed.

[0094] When providing commentary, the commentary unit can adjust the level of detail of the commentary based on the technical difficulty of the dance. The commentary unit, for example, provides concise commentary for basic movements. For example, the commentary unit analyzes the technical difficulty of the dance and provides concise commentary for basic movements. The commentary unit can also provide detailed commentary for advanced techniques. For example, the commentary unit analyzes the technical difficulty of the dance and provides detailed commentary for advanced techniques. The commentary unit can also provide step-by-step commentary for specific techniques. For example, the commentary unit analyzes the technical difficulty of the dance and provides step-by-step commentary for specific techniques. This allows viewers to deepen their understanding by adjusting the level of detail of the commentary based on the technical difficulty of the dance. Some or all of the above-described processing in the commentary unit may be performed using, or without, a generation AI. For example, the commentary unit can input technical difficulty data for the dance into the generation AI and have the generation AI adjust the level of detail of the commentary.

[0095] The commentary unit can apply different commentary algorithms depending on the dance genre when providing commentary. For example, the commentary unit uses classical expressions when providing commentary on ballet. For example, the commentary unit analyzes the dance genre and uses classical expressions when providing commentary on ballet. The commentary unit can also use casual expressions when providing commentary on hip hop. For example, the commentary unit analyzes the dance genre and uses casual expressions when providing commentary on hip hop. The commentary unit can also use elegant expressions when providing commentary on jazz dance. For example, the commentary unit analyzes the dance genre and uses elegant expressions when providing commentary on jazz dance. This allows for different commentary algorithms to be applied depending on the dance genre, thereby deepening the viewer's understanding. Some or all of the above-mentioned processing in the commentary unit may be performed using, or without, a generation AI. For example, the commentary unit can input dance genre data into the generation AI and cause the generation AI to apply the commentary algorithm.

[0096] When providing commentary, the commentary unit can improve the accuracy of the commentary by referring to the user's past commentary results. The commentary unit, for example, provides commentary based on commentary styles that the user has previously rated highly. For example, the commentary unit analyzes the user's past commentary results and provides commentary based on commentary styles that the user has previously rated highly. The commentary unit can also provide commentary while avoiding commentary styles that the user has previously rated poorly. For example, the commentary unit analyzes the user's past commentary results and provides commentary while avoiding commentary styles that the user has previously rated poorly. Furthermore, the commentary unit can analyze the user's past commentary results and suggest an optimal commentary method. For example, the commentary unit analyzes the user's past commentary results and suggests an optimal commentary method. This improves the accuracy of the commentary by referring to the user's past commentary results. Some or all of the above-described processing in the commentary unit may be performed using, or without, a generation AI. For example, the commentary unit can input the user's past commentary result data into the generation AI and cause the generation AI to improve the accuracy of the commentary.

[0097] The commentary unit can estimate the user's emotions and adjust the length of the commentary based on the estimated user emotions. For example, if the user is in a hurry, the commentary unit provides a short, concise commentary. For example, if the commentary unit analyzes the user's emotions and determines that the user is in a hurry, it provides a short, concise commentary. Furthermore, if the user is relaxed, the commentary unit can provide a longer commentary including detailed explanations. For example, if the commentary unit analyzes the user's emotions and determines that the user is relaxed, it provides a longer commentary including detailed explanations. Furthermore, if the user is excited, the commentary unit can provide commentary with visually stimulating effects. For example, if the commentary unit analyzes the user's emotions and determines that the user is excited, it provides commentary with visually stimulating effects. This allows the viewer to deepen their understanding by adjusting the length of the commentary based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the commentary unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the commentary unit may input user emotion data into the generation AI and have the generation AI adjust the length of the commentary.

[0098] When providing commentary, the commentary unit can determine the priority of commentary based on the time of the dance performance. For example, the commentary unit prioritizes commentary on the most recent dance performance. For example, the commentary unit analyzes the time of the dance performance and prioritizes commentary on the most recent dance performance. The commentary unit can also provide commentary on past great performances as appropriate. For example, the commentary unit analyzes the time of the dance performance and provides commentary on past great performances as appropriate. Furthermore, the commentary unit can provide related commentary based on upcoming performance schedules. For example, the commentary unit analyzes the time of the dance performance and provides related commentary based on upcoming performance schedules. In this way, determining the priority of commentary based on the time of the dance performance deepens the viewer's understanding. Some or all of the above-mentioned processing in the commentary unit may be performed using, or without, a generation AI. For example, the commentary unit can input dance performance time data into the generation AI and have the generation AI determine the priority of commentary.

[0099] The commentary unit can adjust the order of commentary based on the relevance of the dances during commentary. For example, the commentary unit provides consecutive commentary on dances of the same genre. For example, the commentary unit analyzes the relevance of dances and provides consecutive commentary on dances of the same genre. The commentary unit can also provide commentary related to specific techniques or movements in a group. For example, the commentary unit analyzes the relevance of dances and provides commentary related to specific techniques or movements in a group. Furthermore, the commentary unit can prioritize highly relevant commentary based on the user's interests. For example, the commentary unit analyzes the relevance of dances and prioritizes highly relevant commentary based on the user's interests. This allows viewers to deepen their understanding by adjusting the order of commentary based on the relevance of dances. Some or all of the above-described processing in the commentary unit may be performed using, or without, a generation AI. For example, the commentary unit can input dance relevance data into the generation AI and cause the generation AI to adjust the order of commentary.

[0100] The commentary unit can adjust the use of technical terms in the commentary depending on the user's level of expertise during commentary. For example, the commentary unit provides commentary in simple language, avoiding technical terms, for beginners. For example, the commentary unit analyzes the user's level of expertise and provides commentary in simple language, avoiding technical terms, for beginners. The commentary unit can also provide commentary using technical terms moderately for intermediate users. For example, the commentary unit analyzes the user's level of expertise and provides commentary using technical terms moderately for intermediate users. Furthermore, the commentary unit can provide detailed commentary using a lot of technical terms for advanced users. For example, the commentary unit analyzes the user's level of expertise and provides detailed commentary using a lot of technical terms for advanced users. This allows viewers to deepen their understanding by adjusting the use of technical terms in the commentary depending on the user's level of expertise. Some or all of the above-described processing in the commentary unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the commentary unit can input the user's expertise level data into the generation AI and have the generation AI adjust the use of technical terms in the commentary.

[0101] The visual aid unit can estimate the user's emotions and adjust the display method of the visual aid based on the estimated user's emotions. For example, if the user is excited, the visual aid unit adds a visually stimulating effect to the display. For example, if the visual aid unit analyzes the user's emotions and determines that the user is excited, it adds a visually stimulating effect to the display. The visual aid unit can also display calm colors if the user is relaxed. For example, if the visual aid unit analyzes the user's emotions and determines that the user is relaxed, it displays calm colors. Furthermore, if the user is sad, the visual aid unit can display an emotional video. For example, if the visual aid unit analyzes the user's emotions and determines that the user is sad, it displays an emotional video. This adjusts the display method of the visual aid based on the user's emotions, thereby deepening the viewer's understanding. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the visual aid unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the visual aid unit may input user emotion data into the generation AI and have the generation AI adjust the display method of the visual aid.

[0102] When displaying a visual aid, the visual aid unit can select the optimal display method by referring to the user's past visual aid usage history. The visual aid unit, for example, performs optimal display based on the user's preferred display method in the past. For example, the visual aid unit analyzes the user's past visual aid usage history and performs optimal display based on the preferred display method. The visual aid unit can also perform display while avoiding display methods that the user avoided in the past. For example, the visual aid unit analyzes the user's past visual aid usage history and performs display while avoiding the avoided display methods. Furthermore, the visual aid unit can analyze the user's past usage history and suggest the optimal display method. For example, the visual aid unit analyzes the user's past visual aid usage history and suggests the optimal display method. In this way, the optimal display method can be provided by referring to the user's past visual aid usage history. Some or all of the above-described processing in the visual aid unit may be performed using, or without, a generation AI. For example, the visual aid unit can input the user's past visual aid usage history data into the generation AI and have the generation AI select the optimal display method.

[0103] When displaying visual aids, the visual aid unit can customize the display content according to the user's current task. For example, if the user is studying, the visual aid unit displays visual aids that are useful for studying. For example, the visual aid unit analyzes the user's current task and, if the user is studying, displays visual aids that are useful for studying. Furthermore, if the user is relaxing, the visual aid unit can display visual aids suitable for relaxation. For example, the visual aid unit analyzes the user's current task and, if the user is relaxing, displays visual aids suitable for relaxation. Furthermore, if the user is enjoying entertainment, the visual aid unit can display visual aids suitable for entertainment. For example, the visual aid unit analyzes the user's current task and, if the user is enjoying entertainment, displays visual aids suitable for entertainment. This allows the viewer to deepen their understanding by customizing the display content according to the user's current task. Some or all of the above-described processing in the visual aid unit may be performed using, or without, a generation AI. For example, the visual aid unit can input the user's current task data into the generation AI and have the generation AI customize the display content.

[0104] The visual aid unit can estimate the user's emotions and adjust the operation procedures of the visual aid based on the estimated user's emotions. For example, if the user is excited, the visual aid unit provides simple operation procedures. For example, if the visual aid unit analyzes the user's emotions and determines that the user is excited, it provides simple operation procedures. The visual aid unit can also provide detailed operation procedures if the user is relaxed. For example, if the visual aid unit analyzes the user's emotions and determines that the user is relaxed, it provides detailed operation procedures. Furthermore, the visual aid unit can minimize operation procedures if the user is tired. For example, if the visual aid unit analyzes the user's emotions and determines that the user is tired, it minimizes operation procedures. This allows the viewer to deepen their understanding by adjusting the operation procedures of the visual aid based on the user's emotions. Emotion estimation is achieved 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. Some or all of the above-described processing in the visual assistance unit may be performed using, for example, a generation AI. For example, the visual assistance unit may input user emotion data into the generation AI and have the generation AI adjust the operation procedure.

[0105] The visual aid unit can select the optimal display method by taking into account the user's device information when displaying visual aids. For example, if the user is using a smartphone, the visual aid unit provides a display method tailored to the screen size. For example, the visual aid unit analyzes the user's device information and provides a display method tailored to the screen size when using a smartphone. Furthermore, if the user is using a tablet, the visual aid unit can provide a display method optimized for a large screen. For example, the visual aid unit analyzes the user's device information and provides a display method optimized for a large screen when using a tablet. Furthermore, the visual aid unit can provide a simple and highly visible display method when using a smartwatch. For example, the visual aid unit analyzes the user's device information and provides a simple and highly visible display method when using a smartwatch. This allows the optimal display method to be provided by taking the user's device information into consideration. Some or all of the above-described processing in the visual aid unit may be performed using, or without, a generation AI. For example, the visual aid unit can input the user's device information into the generation AI and cause the generation AI to select the optimal display method.

[0106] The visual aid unit can make the display content multilingual according to the user's language setting when displaying the visual aid. The visual aid unit automatically sets the display content based on, for example, the language setting of the user's device. For example, the visual aid unit analyzes the language setting of the user's device and automatically sets the display content. The visual aid unit can also provide a language switching function when the user uses multiple languages. For example, the visual aid unit analyzes the user's language setting and provides a language switching function when the user uses multiple languages. Furthermore, the visual aid unit can provide the display content in a specific language when the user selects that language. For example, the visual aid unit analyzes the user's language setting and provides the display content in that language when the user selects a specific language. This allows the viewer to understand the display content in multiple languages ​​according to the user's language setting, thereby deepening the viewer's understanding. Some or all of the above-described processing in the visual aid unit may be performed using, or without, a generation AI. For example, the visual aid unit can input the user's language setting data into the generation AI and have the generation AI perform multilingual support for the display content.

[0107] The interactive unit can estimate the user's emotions and adjust the interactive question response method based on the estimated user's emotions. For example, if the user is excited, the interactive unit provides an energetic response. For example, if the interactive unit analyzes the user's emotions and determines that the user is excited, the interactive unit provides an energetic response. The interactive unit can also provide a calm response if the user is relaxed. For example, if the interactive unit analyzes the user's emotions and determines that the user is relaxed, the interactive unit provides a calm response. The interactive unit can also provide a moving response if the user is sad. For example, if the interactive unit analyzes the user's emotions and determines that the user is sad, the interactive unit provides a moving response. This allows the viewer's understanding to be deepened by adjusting the interactive question response method based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the interactive unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the interactive unit can input user emotional data into the generation AI and cause the generation AI to adjust the way interactive questions are answered.

[0108] During interactive question-answering, the interactive unit can select the optimal response method by referring to the user's past question history. The interactive unit, for example, provides the optimal response based on the content of questions asked by the user in the past. For example, the interactive unit analyzes the user's past question history and provides the optimal response based on the content of questions asked in the past. The interactive unit can also provide a response that avoids response methods that the user has avoided in the past. For example, the interactive unit analyzes the user's past question history and provides a response that avoids the response methods that the user has avoided in the past. Furthermore, the interactive unit can analyze the user's past question history and suggest the optimal response method. For example, the interactive unit analyzes the user's past question history and suggests the optimal response method. In this way, the optimal response method can be provided by referring to the user's past question history. Some or all of the above-described processing in the interactive unit may be performed using, or without, a generation AI. For example, the interactive unit can input the user's past question history data into the generation AI and have the generation AI select the optimal response method.

[0109] The interactive unit can customize the response content according to the user's current interests during interactive question-answering. The interactive unit, for example, provides a response based on topics in which the user is currently interested. For example, the interactive unit analyzes the user's current interests and provides a response based on the topics of interest. The interactive unit can also provide a response based on keywords recently searched by the user. For example, the interactive unit analyzes the user's search history and provides a response based on the recently searched keywords. The interactive unit can also analyze trends in online communities in which the user participates and provide relevant responses. For example, the interactive unit analyzes trends in online communities in which the user participates and provides relevant responses. This allows the viewer to deepen their understanding by customizing the response content according to the user's current interests. Some or all of the above-described processing in the interactive unit may be performed using, or without, a generation AI. For example, the interactive unit can input the user's current interest data into the generation AI and have the generation AI customize the response content.

[0110] The interactive unit can estimate the user's emotions and prioritize interactive questions based on the estimated user emotions. For example, if the user is excited, the interactive unit prioritizes energetic questions. For example, if the interactive unit analyzes the user's emotions and determines that the user is excited, it prioritizes energetic questions. The interactive unit can also prioritize calm questions if the user is relaxed. For example, if the interactive unit analyzes the user's emotions and determines that the user is relaxed, it prioritizes calm questions. Furthermore, if the user is sad, the interactive unit can prioritize emotional questions. For example, if the interactive unit analyzes the user's emotions and determines that the user is sad, it prioritizes emotional questions. This allows for a deeper viewer understanding by prioritizing interactive questions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the interactive unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the interactive unit may input user emotion data into the generation AI and have the generation AI determine the priority of interactive questions.

[0111] The interactive unit can select the optimal response method during interactive question answering by taking into account the user's device information. For example, if the user is using a smartphone, the interactive unit provides a response method tailored to the screen size. For example, the interactive unit analyzes the user's device information and provides a response method tailored to the screen size when the user is using a smartphone. The interactive unit can also provide a response method optimized for a large screen when the user is using a tablet. For example, the interactive unit analyzes the user's device information and provides a response method optimized for a large screen when the user is using a tablet. Furthermore, the interactive unit can also provide a concise and highly visible response method when the user is using a smartwatch. For example, the interactive unit analyzes the user's device information and provides a concise and highly visible response method when the user is using a smartwatch. This makes it possible to provide the optimal response method by taking the user's device information into consideration. Some or all of the above-described processing in the interactive unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the interactive unit can input the user's device information into the generation AI and cause the generation AI to select the optimal response method.

[0112] The interactive unit can make the response content multilingual according to the user's language setting during interactive question-answering. The interactive unit, for example, automatically sets the response content based on the language setting of the user's device. For example, the interactive unit analyzes the language setting of the user's device and automatically sets the response content. The interactive unit can also provide a language switching function when the user uses multiple languages. For example, the interactive unit analyzes the user's language setting and provides a language switching function when the user uses multiple languages. Furthermore, the interactive unit can provide the response content in a specific language when the user selects that language. For example, the interactive unit analyzes the user's language setting and provides the response content in that language when the user selects a specific language. This allows the viewer to understand the response content in multiple languages ​​according to the user's language setting, thereby deepening the viewer's understanding. Some or all of the above-described processing in the interactive unit may be performed using, or without, a generation AI. For example, the interactive unit can input the user's language setting data into the generation AI and cause the generation AI to perform multilingual support for the response content.

[0113] The interactive unit can analyze the user's social media activity and provide related information during interactive question and answering. For example, the interactive unit can provide information about places where the user has checked in on social media. For example, the interactive unit can analyze the user's social media activity and provide information about the checked-in places. The interactive unit can also analyze the user's social media posts and provide information about related tourist spots and stores. For example, the interactive unit can analyze the user's social media activity and provide information about related tourist spots and stores based on the posted content. Furthermore, the interactive unit can provide information about related places and events based on the activities of the user's friends on social media. For example, the interactive unit can analyze the user's social media activity and provide information about related places and events based on the friends' activities. In this way, related information can be provided by analyzing the user's social media activity. Some or all of the above-described processing in the interactive unit can be performed using, or without, a generation AI. For example, the interactive unit can input the user's social media data into the generation AI and cause the generation AI to provide related information. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, learning unit, commentary unit, visual assistance unit, interactive unit, and emotion estimation unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects dance videos using the camera 42 and communication I / F 44 of the smart device 14 and processes the collected video data using the specific processing unit 290 of the data processing device 12. The learning unit learns the video data using the generation AI by the specific processing unit 290 of the data processing device 12. The commentary unit provides commentary on dance movements and techniques using the generation AI by the specific processing unit 290 of the data processing device 12. The visual assistance unit performs slow-motion playback using the display 40A of the smart device 14 and provides real-time commentary by the generation AI. The interactive unit accepts questions from viewers using the microphone 38B of the smart device 14 and provides commentary using the generation AI by the specific processing unit 290 of the data processing device 12. The emotion estimation unit estimates the user's emotion using the specific processing unit 290 of the data processing device 12 and adjusts the collection timing of the collection unit. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, learning unit, commentary unit, visual assistance unit, interactive unit, and emotion estimation unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects dance videos using the camera 42 and communication I / F 44 of the smart glasses 214 and processes the collected video data using the specific processing unit 290 of the data processing device 12. The learning unit learns the video data using a generation AI by the specific processing unit 290 of the data processing device 12. The commentary unit provides commentary on dance movements and techniques using a generation AI by the specific processing unit 290 of the data processing device 12. The visual assistance unit performs slow-motion playback using the display of the smart glasses 214 and provides real-time commentary by the generation AI. The interactive unit accepts questions from viewers using the microphone 238 of the smart glasses 214 and provides commentary using a generation AI by the specific processing unit 290 of the data processing device 12. The emotion estimation unit estimates the user's emotion using the specific processing unit 290 of the data processing device 12 and adjusts the collection timing of the collection unit. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, learning unit, commentary unit, visual assistance unit, interactive unit, and emotion estimation unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit collects dance videos using the camera 42 and communication I / F 44 of the headset-type terminal 314 and processes the collected video data using the specific processing unit 290 of the data processing device 12. The learning unit learns the video data using a generation AI by the specific processing unit 290 of the data processing device 12. The commentary unit provides commentary on dance movements and techniques using a generation AI by the specific processing unit 290 of the data processing device 12. The visual assistance unit performs slow-motion playback using the display 343 of the headset-type terminal 314 and provides real-time commentary by the generation AI. The interactive unit accepts questions from viewers using the microphone 238 of the headset-type terminal 314 and provides commentary using a generation AI by the specific processing unit 290 of the data processing device 12. The emotion estimation unit estimates the user's emotion using the specific processing unit 290 of the data processing device 12 and adjusts the collection timing of the collection unit. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, learning unit, commentary unit, visual assistance unit, interactive unit, and emotion estimation unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects dance videos using the camera 42 and communication I / F 44 of the robot 414 and processes the collected video data using the specific processing unit 290 of the data processing device 12. The learning unit learns the video data using a generation AI by the specific processing unit 290 of the data processing device 12. The commentary unit provides commentary on dance movements and techniques using a generation AI by the specific processing unit 290 of the data processing device 12. The visual assistance unit performs slow-motion playback using the display of the robot 414 and provides real-time commentary by the generation AI. The interactive unit accepts questions from viewers using the microphone 238 of the robot 414 and provides commentary using a generation AI by the specific processing unit 290 of the data processing device 12. The emotion estimation unit estimates the user's emotion using the specific processing unit 290 of the data processing device 12 and adjusts the collection timing of the collection unit.

[0114] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0115] The collection unit can detect the user's physical movements using a sensor and collect related dance videos based on the movements. For example, the collection unit can detect the user's hand-raising movement and collect ballet videos related to that movement. The collection unit can also detect the user's foot-moving movement and collect hip-hop videos related to that movement. Furthermore, the collection unit can detect the user's jumping movement and collect jazz dance videos related to that movement. This makes it easier to attract viewers' interest by providing related dance videos based on the user's physical movements. Some or all of the above-described processing by the collection unit can be performed using, or without, a generation AI. For example, the collection unit can input the user's movement data into the generation AI and cause the generation AI to collect related videos.

[0116] The commentary unit can estimate the user's emotions and adjust the tone of the commentary based on the estimated user's emotions. For example, if the user is excited, the commentary unit can provide commentary in an energetic tone. Furthermore, if the user is relaxed, the commentary unit can provide commentary in a calm tone. Furthermore, if the user is sad, the commentary unit can provide commentary in an emotional tone. By adjusting the tone of the commentary based on the user's emotions, the viewer's understanding can be enhanced. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the commentary unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the commentary unit can input the user's emotion data into the generation AI and have the generation AI adjust the tone of the commentary.

[0117] The commentary unit can customize the commentary style based on the user's visual preferences. For example, if the user likes animation, the commentary unit can provide commentary that makes extensive use of animation. Furthermore, if the user likes live-action footage, the commentary unit can provide commentary using live-action footage. Furthermore, if the user likes infographics, the commentary unit can provide commentary using infographics. This allows the commentary style to be customized based on the user's visual preferences, making it easier for viewers to deepen their understanding. Some or all of the above-described processing in the commentary unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the commentary unit can input the user's visual preference data into the generation AI and cause the generation AI to customize the commentary style.

[0118] The visual aid unit can estimate the user's emotions and adjust the color of the visual aid based on the estimated user's emotions. For example, if the user is excited, the visual aid unit can display the visual aid using vibrant colors. Furthermore, if the user is relaxed, the visual aid unit can display the visual aid using subdued colors. Furthermore, if the user is sad, the visual aid unit can display the visual aid using warm colors. Adjusting the color of the visual aid based on the user's emotions can thereby deepen the viewer's understanding. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the visual aid unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the visual aid unit can input the user's emotion data into the generation AI and have the generation AI adjust the color of the visual aid.

[0119] The interactive unit can estimate the user's emotions and adjust the difficulty of interactive questions based on the estimated user emotions. For example, the interactive unit can provide more difficult questions when the user is excited. The interactive unit can also provide less difficult questions when the user is relaxed. Furthermore, the interactive unit can also provide easier questions when the user is tired. This adjusts the difficulty of interactive questions based on the user's emotions, making it easier for viewers to understand. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the interactive unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the interactive unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the difficulty of the interactive questions.

[0120] The collection unit can collect dance styles by region taking into account the user's geographical location information. For example, if the user is in Africa, the collection unit can collect traditional African dance videos. If the user is in South America, the collection unit can collect videos of samba, tango, and the like. Furthermore, if the user is in Asia, the collection unit can collect traditional Asian dance videos. This makes it easier to attract viewers' interest by providing dance styles by region based on the user's geographical location information. Some or all of the above-described processing by the collection unit can be performed using, or without, a generation AI. For example, the collection unit can input the user's geographical location information into the generation AI and cause the generation AI to collect dance videos by region.

[0121] The learning unit can reflect user feedback in real time and dynamically update the learning data. For example, the learning unit can instantly add videos that users have rated highly to the learning data. The learning unit can also instantly remove videos that users have rated poorly from the learning data. Furthermore, the learning unit can adjust the learning algorithm based on user feedback to perform more effective learning. This allows the quality of the learning data to be improved by reflecting user feedback in real time. Some or all of the above-described processing in the learning unit may be performed using, or without, a generation AI. For example, the learning unit can input user feedback data into the generation AI and cause the generation AI to dynamically update the learning data.

[0122] The commentary unit can adjust the depth of the commentary according to the user's level of expertise. For example, the commentary unit can provide basic commentary for beginners. The commentary unit can also provide more detailed commentary for intermediate users. The commentary unit can also provide specialized commentary for advanced users. This makes it easier for viewers to deepen their understanding by adjusting the depth of the commentary according to the user's level of expertise. Some or all of the above-mentioned processing in the commentary unit may be performed using, or without, a generation AI. For example, the commentary unit can input the user's level of expertise data into the generation AI and have the generation AI adjust the depth of the commentary.

[0123] The visual aid unit can adjust the quality of the visual aid according to the performance of the user's device. For example, the visual aid unit can provide high-resolution visual aids when a high-performance device is used. The visual aid unit can also provide low-resolution visual aids when a low-performance device is used. Furthermore, the visual aid unit can adjust the quality of the visual aid according to the remaining battery level of the device. This improves the viewer's experience by adjusting the quality of the visual aid according to the performance of the user's device. Some or all of the above-described processing in the visual aid unit can be performed using, or without, a generation AI. For example, the visual aid unit can input the user's device information into the generation AI and cause the generation AI to adjust the quality of the visual aid.

[0124] The interactive unit can analyze the user's past question history and automatically generate related questions. For example, the interactive unit can generate new related questions based on the content of questions the user has previously asked. The interactive unit can also generate questions based on topics in which the user has previously shown interest. Furthermore, the interactive unit can analyze the user's past question history and generate follow-up questions to unresolved questions. In this way, by analyzing the user's past question history, more relevant questions can be provided. Some or all of the above-mentioned processing in the interactive unit may be performed using, or without, a generation AI. For example, the interactive unit can input the user's question history data into the generation AI and cause the generation AI to automatically generate related questions.

[0125] The processing flow of the second embodiment will be briefly explained below.

[0126] Step 1: The collection unit collects dance video data. The dance video data includes videos of professional and amateur dancers. The collection unit collects dance videos of various genres, such as ballet, hip hop, and jazz dance. The collection unit can also collect video data from multiple sources, such as publicly available videos on the Internet, videos filmed in dance studios, and dance videos uploaded by users. For example, dance videos can be automatically collected from video sharing sites on the Internet, or videos filmed in dance studios can be directly collected. Step 2: The learning unit uses the generation AI to learn the video data collected by the collection unit. Learning is based on extracting features from the video data and classifying movements. For example, the generation AI extracts dance movements from the video data and learns based on them. It can also learn about the differences between professional and amateur dancers, as well as specific techniques and movements (e.g., "arabesque" in ballet and "popping" in hip hop). Step 3: The commentary section uses the generative AI to provide commentary on each dance movement and technique based on the data learned by the learning section. The commentary is verbal, but visual aids can also be provided. For example, a specific movement can be replayed in slow motion and commented on in real time. It can also explain the differences between professional and amateur dancers.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0131] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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.

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

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

[0141] 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.

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

[0143] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0145] The data processing system 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.

[0146] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0147] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0163] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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).

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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).

[0184] 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.

[0185] 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."

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] [Explanation of symbols]

[0199] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects dance video data; a learning unit that learns the video data collected by the collecting unit; a commentary unit that provides commentary on specific dance movements and techniques based on the data learned by the learning unit; Equipped with A system characterized by:

2. The commentary section Provide concrete explanations that show the differences between professional and amateur dancers 2. The system of claim 1.

3. The commentary section Specific actions are played back in slow motion and explained in real time 2. The system of claim 1.

4. Equipped with visual aids that provide specific visual aids 2. The system of claim 1.

5. It will have an interactive section where viewers can ask questions.

2. The system of claim 1.

6. The collecting unit Analyzes user emotions and adjusts the timing of dance video collection based on the analyzed user emotions.

2. The system of claim 1.

7. The collecting unit When collecting dance videos, analyze users' past viewing history and select the optimal collection method.

2. The system of claim 1.

8. The collecting unit When collecting dance videos, filtering is performed based on the user's current interests.

2. The system of claim 1.

Images