system

Abstract

An object of the system according to the embodiment is to convert a sport video captured by a user into a professional highlight video or a news article and post the video or article on an SNS.SOLUTION: A system according to an embodiment includes a video uploading unit, a video analyzing unit, a supplementary information providing unit, a highlight generating unit, a news article generating unit, and an SNS posting unit. The video uploading unit uploads a video. The video analysis unit analyzes the video uploaded by the video upload unit. The supplementary information providing section provides supplementary information based on the video analyzed by the video analysis section. The highlight generator generates a highlight video on the basis of the supplementary information provided by the supplementary information provider. The news article generation unit generates a news article on the basis of the supplementary information provided by the supplementary information providing unit. The SNS posting unit posts the content generated by the highlight generation unit and the news article generation unit to the SNS.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has made it difficult for users to convert their own sports footage into professional highlight footage or news articles and post them on social media.

[0005] The system according to the embodiment aims to convert sports videos taken by users into professional highlight videos or news articles and post them on social networking sites. [Means for solving the problem]

[0006] The system according to the embodiment includes a video uploading unit, a video analysis unit, a supplemental information providing unit, a highlight generation unit, a news article generating unit, and an SNS posting unit. The video uploading unit uploads video. The video analysis unit analyzes the video uploaded by the video uploading unit. The supplemental information providing unit provides supplemental information based on the video analyzed by the video analysis unit. The highlight generating unit generates a highlight video based on the supplemental information provided by the supplemental information providing unit. The news article generating unit generates a news article based on the supplemental information provided by the supplemental information providing unit. The SNS posting unit posts the content generated by the highlight generating unit and the news article generating unit to an SNS. [Effects of the Invention]

[0007] The system according to the embodiment can convert sports videos taken by users into professional highlight videos or news articles and post them to social networking sites. [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 sports video generation system according to an embodiment of the present invention is a system in which a generation AI generates professional-quality highlight videos and news articles based on game videos posted by users, and posts these to social media. This allows users to easily generate professional-quality highlight videos and news articles and post them to social media.

[0029] A sports video generation system according to an embodiment includes a video upload unit, a video analysis unit, a supplemental information providing unit, a highlight generation unit, a news article generation unit, and a social media posting unit. The video upload unit uploads game videos posted by users. For example, game videos filmed by users can be uploaded to the system. The video upload unit can accept video in different formats, such as MP4, AVI, and MOV. The video analysis unit uses a generation AI to analyze the uploaded video. For example, the generation AI recognizes the players and play details in the video and extracts important scenes. The generation AI can also analyze movements and sounds in the video to identify important scenes. For example, it identifies goal scenes and important plays and generates a highlight video based on them. The supplemental information providing unit allows the user to provide supplemental information based on the video analyzed by the video analysis unit. For example, the supplemental information providing unit answers the question, "What is this player's name?" with "Shirato Jiro." This supplemental information is used by the generation AI to generate more accurate highlight videos and news articles. The highlight generation unit generates a highlight video to which the generation AI adds commentary, narration, and cheers based on the supplemental information provided by the supplemental information providing unit. For example, a commentary such as "Goal! Shiroto Jiro scores a great shot!" is added to a goal scene. The news article generation unit generates a professional-quality news article like that written by a sports reporter based on the supplemental information provided by the supplemental information providing unit. For example, an article with the content "Shiroto Jiro led his team to victory with a great shot" is generated. The SNS posting unit posts the content generated by the highlight generation unit and the news article generation unit to SNS. For example, the SNS posting unit provides a function that allows users to easily post the generated highlight video and news article to SNS such as TikTok and Instagram. This allows the sports video generation system according to the embodiment to easily generate professional-quality highlight videos and news articles and post them to SNS. For example, users can widely share the content they create and attract attention.

[0030] The video analysis unit can analyze the tactics and formations of a match and add tactical commentary. For example, the video analysis unit uses a generation AI to analyze the tactics and formations of a match and add tactical commentary. For example, it may explain the team's formation and tactics in a goal-scoring scene. The video analysis unit also analyzes the movements and positioning of players in the video and comment on the tactics and formations of the match. For example, it may explain defensive tactics and attacking patterns. The video analysis unit also uses a generation AI to analyze the tactics and formations of a match and add tactical commentary, allowing viewers to understand the tactical aspects of the match. For example, it may explain team tactical changes and player roles. This allows viewers to understand the tactical aspects of the match.

[0031] The video analysis unit can analyze the biometric data (heart rate, distance traveled, etc.) of players in the video and integrate it into the highlight footage. In the video analysis unit, for example, the generation AI analyzes the biometric data of players in the video and integrates it into the highlight footage. For example, it displays the player's heart rate and distance traveled. The video analysis unit also analyzes the biometric data of players in the video in real time and integrates it into the highlight footage. For example, it displays the player's fatigue level and performance. The video analysis unit also communicates the player's performance in detail to viewers by having the generation AI analyze the player's biometric data and integrate it into the highlight footage. For example, it displays the player's heart rate and distance traveled. This makes it possible to generate highlight footage that conveys the player's performance in detail.

[0032] The video analysis unit can expand the generation AI so that it can also handle game footage of different sports. For example, the video analysis unit expands the generation AI to handle game footage of different sports. For example, it analyzes game footage of basketball and tennis and generates highlight footage. The video analysis unit also improves the generation AI's algorithm to analyze game footage of different sports. For example, it analyzes basketball dribbles and shots, and tennis serves and rallies. The video analysis unit also expands the generation AI to handle game footage of different sports, thereby catering to a wide range of sports fans. For example, it analyzes game footage of basketball and tennis and generates highlight footage. This makes it possible to generate highlight footage that is compatible with a wide range of sports.

[0033] The supplemental information providing unit can automatically add a player's past performance and statistical data based on the supplemental information provided by the user. The supplemental information providing unit, for example, automatically adds a player's past performance and statistical data based on the supplemental information provided by the user. For example, it displays the number of goals and assists a player has. The supplemental information providing unit also enriches the content of highlight videos and news articles by automatically adding a player's past performance and statistical data based on the supplemental information. For example, it displays the results and performance of a player's past games. The supplemental information providing unit also builds a system that automatically adds a player's past performance and statistical data based on the supplemental information provided by the user. For example, it displays the player's career highs and the results of important games. In this way, the automatic addition of a player's past performance and statistical data enriches the content of highlight videos and news articles.

[0034] The supplemental information providing unit inputs supplemental information using voice recognition technology, thereby reducing the burden on the user. The supplemental information providing unit, for example, inputs supplemental information using voice recognition technology, thereby reducing the burden on the user. For example, the user inputs the name of a player by voice. The supplemental information providing unit also uses voice recognition technology to build a system that makes it easy to input supplemental information. For example, the user provides information about the player by voice. The supplemental information providing unit also inputs supplemental information using voice recognition technology, thereby reducing the burden on the user and improving input accuracy. For example, the user inputs the name of a player or the name of a team by voice. In this way, using voice recognition technology reduces the burden on the user and improves input accuracy.

[0035] The supplemental information providing unit allows the generation AI to automatically generate related questions when supplemental information is input and suggest them to the user. For example, the supplemental information providing unit allows the generation AI to automatically generate related questions when supplemental information is input and suggest them to the user. For example, it generates a question such as, "What is this player's position?" The supplemental information providing unit also builds a system where the generation AI automatically generates related questions and suggests them to the user, thereby enabling smooth input of supplemental information. For example, it generates a question such as, "What was the result of this game?" The supplemental information providing unit also improves the accuracy of input by allowing the generation AI to automatically generate related questions when supplemental information is input and suggest them to the user. For example, it generates a question such as, "What is this player's uniform number?" In this way, the generation AI automatically generates related questions, allowing smooth input of supplemental information.

[0036] The supplemental information providing unit can collect supplemental information input from other users through crowdsourcing to improve accuracy. The supplemental information providing unit, for example, collects supplemental information input from other users through crowdsourcing to improve accuracy. For example, it integrates information provided by multiple users. The supplemental information providing unit also uses crowdsourcing to build a system for inputting supplemental information. For example, it aggregates information provided by users to improve accuracy. The supplemental information providing unit also collects supplemental information through crowdsourcing from other users to improve accuracy, thereby generating more accurate highlight videos and news articles. For example, it verifies and integrates information provided by users. In this way, the accuracy of the supplemental information is improved by using crowdsourcing.

[0037] The highlight generation unit can analyze audio data in the video and add the sounds of spectators cheering and cheering in real time. The highlight generation unit, for example, analyzes audio data in the video and adds the sounds of spectators cheering and cheering in real time. For example, the cheers of spectators at goal scenes are reflected in the video. The highlight generation unit also builds a system in which a generation AI analyzes audio data and adds the sounds of spectators cheering and cheering in real time. For example, the cheers of spectators at important moments in the game are reflected in the video. The highlight generation unit also analyzes audio data in the video in real time and adds the sounds of spectators cheering and cheering to generate a highlight video with a sense of presence. For example, the cheers of spectators are reflected in the video. In this way, the sounds of spectators cheering and cheering can be added in real time to generate a highlight video with a sense of presence.

[0038] The highlight generation unit can automatically insert player interviews and comments into highlight footage. For example, the generation AI of the highlight generation unit automatically inserts player interviews and comments. For example, a player's comments are added after a goal is scored. The highlight generation unit also analyzes player interviews and comments in the footage and builds a system that automatically inserts them into the highlight footage. For example, post-match interviews are reflected in the footage. The highlight generation unit also directly delivers the voices of players to viewers by having the generation AI automatically insert player interviews and comments. For example, a player's post-match thoughts are reflected in the footage. In this way, the automatic insertion of player interviews and comments directly delivers the voices of players to viewers.

[0039] The highlight generation unit can display game statistical data and graphs in the highlight footage in real time. In the highlight generation unit, for example, a generation AI displays game statistical data and graphs in real time. For example, the number of goals scored and the number of assists by a player are displayed in the footage. The highlight generation unit also analyzes game statistical data in the footage in real time and builds a system to display graphs. For example, it displays team performance in a graph. In addition, the highlight generation unit provides viewers with detailed game data by having a generation AI display game statistical data and graphs in real time. For example, it displays player performance in a graph. In this way, detailed data is provided to viewers by displaying game statistical data and graphs in real time.

[0040] The highlight generation unit can automatically generate commentary and commentary in different languages ​​to accommodate international viewers. For example, the generation AI in the highlight generation unit automatically generates commentary and commentary in different languages. For example, commentary in English or Spanish is added. The highlight generation unit also automatically translates the commentary and commentary in the video into different languages, building a system that can accommodate international viewers. For example, commentary in French or German is added. The highlight generation unit also accommodates international viewers by having the generation AI automatically generate commentary and commentary in different languages. For example, commentary in Japanese or Chinese is added. This allows commentary and commentary in different languages ​​to be automatically generated, thereby accommodating international viewers.

[0041] The news article generation unit can automatically incorporate game statistical data and players' past performance into articles. In the news article generation unit, for example, the generation AI automatically incorporates game statistical data and players' past performance into articles. For example, it adds a player's number of goals and assists to an article. The news article generation unit also builds a system that analyzes game statistical data and players' past performance in video in real time and automatically incorporates them into articles. For example, it adds team performance to an article. In addition, the news article generation unit provides readers with detailed data by having the generation AI automatically incorporate game statistical data and players' past performance into articles. For example, it adds player performance to an article. In this way, the game statistical data and players' past performance are automatically incorporated into articles, providing readers with detailed data.

[0042] The news article generation unit can generate the content of an article from different perspectives (for example, the perspective of a player or a spectator). In the news article generation unit, for example, a generation AI generates the content of an article from different perspectives. For example, an article is generated from the perspective of a player or a spectator. The news article generation unit also builds a system that analyzes information within a video and generates articles from different perspectives. For example, an article is generated that reflects the impressions of the players and the reactions of the spectators. The news article generation unit also provides readers with a multifaceted perspective by having a generation AI generate the content of an article from different perspectives. For example, an article is generated from the perspective of a player or a spectator. In this way, by generating the content of an article from different perspectives, a multifaceted perspective is provided to readers.

[0043] The news article generation unit can also automatically translate news articles into different languages ​​to accommodate international readers. For example, the news article generation unit uses a generation AI to automatically translate news articles into different languages. For example, translating into English or Spanish. The news article generation unit also builds a system that automatically translates the content of an article into different languages ​​to accommodate international readers. For example, translating into French or German. The news article generation unit also builds a system that automatically translates news articles into different languages ​​to accommodate international readers. For example, translating into Japanese or Chinese. In this way, the news article generation unit can automatically translate news articles into different languages ​​to accommodate international readers.

[0044] The news article generation unit converts the content of an article into a visual note or infographic, making it easier to understand visually. In the news article generation unit, for example, a generation AI converts the content of an article into a visual note or infographic. For example, statistical data of a match is displayed in a graph. The news article generation unit also builds a system that converts the content of an article into a visual note or infographic to make it easier to understand visually. For example, player performance is displayed in a diagram. The news article generation unit also provides information that is easier to understand visually to readers by using a generation AI to convert the content of an article into a visual note or infographic. For example, highlights of a match are displayed in a diagram. In this way, by converting the content of an article into a visual note or infographic, information that is easier to understand visually is provided.

[0045] The SNS posting unit can analyze the optimal timing for the generation AI to post and make suggestions to the user. The SNS posting unit, for example, analyzes the optimal timing for the generation AI to post and makes suggestions to the user. For example, it suggests time periods when there are many SNS users. The SNS posting unit also builds a system that analyzes the optimal timing for posting and makes suggestions to the user. For example, it suggests specific days of the week or time periods. The SNS posting unit also analyzes the optimal timing for the generation AI to post and makes suggestions to the user, thereby maximizing the effectiveness of the post. For example, it suggests time periods when there are many SNS users. In this way, the optimal timing for posting is analyzed and suggestions to the user are made, thereby maximizing the effectiveness of the post.

[0046] The SNS posting unit can maximize the effectiveness of posts by automatically generating hashtags and captions when posting. For example, the SNS posting unit automatically generates hashtags and captions when the generation AI posts. For example, hashtags related to the content of the match are added. The SNS posting unit also builds a system that automatically generates hashtags and captions to maximize the effectiveness of posts. For example, popular hashtags are added. The SNS posting unit also maximizes the effectiveness of posts by automatically generating hashtags and captions when the generation AI posts. For example, captions related to the content of the match are added. In this way, the effectiveness of posts is maximized by automatically generating hashtags and captions.

[0047] The SNS posting unit can analyze reactions after posting in real time and provide feedback for the next post. In the SNS posting unit, for example, a generation AI analyzes reactions after posting in real time and provides feedback for the next post. For example, the content of the next post is suggested based on the reactions to the post. The SNS posting unit also builds a system that analyzes reactions after posting in real time and provides feedback for the next post. For example, it suggests improvements to the post based on user reactions. In addition, the SNS posting unit improves the effectiveness of the post by using a generation AI to analyze reactions after posting in real time and provide feedback for the next post. For example, it adjusts the content of the next post based on the reactions to the post. In this way, the effectiveness of the post is improved by analyzing reactions after posting in real time and providing feedback for the next post.

[0048] The SNS posting unit can support different SNS platforms and provide a function that allows posting to multiple platforms simultaneously. For example, the generation AI supports different SNS platforms and provides a function that allows posting to multiple platforms simultaneously. For example, posting to TikTok and Instagram simultaneously. The SNS posting unit also builds a system that can post to multiple SNS platforms simultaneously. For example, posting to Facebook and Twitter simultaneously. The SNS posting unit also maximizes the effectiveness of posts by supporting different SNS platforms and providing a function that allows posting to multiple platforms simultaneously. For example, posting to YouTube and LinkedIn simultaneously. This maximizes the effectiveness of posts by supporting different SNS platforms and providing a function that allows posting to multiple platforms simultaneously.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The video uploading unit uploads game videos posted by users. For example, users can upload game videos they have filmed to the system. The video uploading unit can also accept video in different formats, such as MP4, AVI, and MOV. The video analysis unit uses a generation AI to analyze the uploaded video. For example, the generation AI recognizes the players and play details in the video and extracts important scenes. The generation AI can also analyze the movements and sounds in the video to identify important scenes. For example, it identifies goal scenes and important plays and generates highlight videos based on them. The supplemental information provision unit allows users to provide supplemental information based on the video analyzed by the video analysis unit. For example, a user might respond with "Shirato Jiro" to the question, "What's this player's name?" This supplemental information is used by the generation AI to generate more accurate highlight videos and news articles. The highlight generation unit generates highlight videos with commentary, commentary, and cheers based on the supplemental information provided by the supplemental information provision unit. For example, a commentary such as "Goal! Shirato Jiro scores a great shot!" is added to a goal scene. The news article generation unit uses a generation AI to generate professional-quality news articles like those written by a sports reporter, based on the supplemental information provided by the supplemental information providing unit. For example, an article such as "Shirato Jiro led his team to victory with a spectacular shot" is generated. The SNS posting unit posts the content generated by the highlight generation unit and the news article generation unit to SNS. For example, it provides a function that allows users to easily post the generated highlight videos and news articles to SNS such as TikTok and Instagram. This allows the sports video generation system according to the embodiment to allow users to easily generate professional-quality highlight videos and news articles and post them to SNS. For example, users can widely share the content they create and attract attention.

[0051] The video analysis unit can analyze the tactics and formations of a match and add tactical commentary. For example, it can explain the team's formation and tactics in a goal-scoring scene. The video analysis unit can also analyze the movements and positioning of players in the video and add commentary on the tactics and formations of the match. For example, it can explain defensive tactics and attacking patterns. The video analysis unit can also use the generation AI to analyze the tactics and formations of a match and add tactical commentary to help viewers understand the tactical aspects of the match. For example, it can explain the team's tactical changes and the roles of players. This allows viewers to understand the tactical aspects of the match.

[0052] The video analysis unit can analyze the biometric data of players in the video (heart rate, distance traveled, etc.) and integrate it into the highlight footage. For example, it can display the player's heart rate and distance traveled. The video analysis unit also analyzes the biometric data of players in the video in real time and integrates it into the highlight footage. For example, it can display the player's fatigue level and performance. The video analysis unit also allows the generation AI to analyze the player's biometric data and integrate it into the highlight footage, thereby providing viewers with detailed information about the player's performance. For example, it can display the player's heart rate and distance traveled. This makes it possible to generate highlight footage that conveys the player's performance in detail.

[0053] The video analysis unit can expand the generation AI to handle game footage from different sports. For example, it can analyze game footage from basketball and tennis to generate highlight footage. The video analysis unit also improves the generation AI's algorithms to analyze game footage from different sports. For example, it can analyze basketball dribbles and shots, and tennis serves and rallies. The video analysis unit can also expand the generation AI to handle game footage from different sports, thereby catering to a wide range of sports fans. For example, it can analyze game footage from basketball and tennis to generate highlight footage. This makes it possible to generate highlight footage for a wide range of sports.

[0054] The supplemental information providing unit can automatically add a player's past performance and statistical data based on the supplemental information provided by the user. For example, it displays the number of goals and assists the player has. The supplemental information providing unit also enriches the content of highlight videos and news articles by automatically adding a player's past performance and statistical data based on the supplemental information. For example, it displays the results and performance of a player's past games. The supplemental information providing unit also builds a system that automatically adds a player's past performance and statistical data based on the supplemental information provided by the user. For example, it displays the player's career highs and the results of important games. In this way, the automatic addition of a player's past performance and statistical data enriches the content of highlight videos and news articles.

[0055] The supplemental information providing unit inputs supplemental information using voice recognition technology, thereby reducing the burden on the user. For example, the user inputs the name of a player by voice. The supplemental information providing unit also uses voice recognition technology to build a system that makes it easy to input supplemental information. For example, the user provides player information by voice. The supplemental information providing unit also inputs supplemental information using voice recognition technology, thereby reducing the burden on the user and improving input accuracy. For example, the user inputs the name of a player or the name of a team by voice. In this way, using voice recognition technology reduces the burden on the user and improves input accuracy.

[0056] The supplemental information provision unit allows the generation AI to automatically generate related questions and suggest them to the user when supplemental information is input. For example, it generates a question such as, "What is this player's position?" The supplemental information provision unit also builds a system that allows the generation AI to automatically generate related questions and suggest them to the user, thereby enabling smooth input of supplemental information. For example, it generates a question such as, "What was the result of this game?" The supplemental information provision unit also improves the accuracy of input by allowing the generation AI to automatically generate related questions and suggest them to the user when supplemental information is input. For example, it generates a question such as, "What is this player's uniform number?" As a result, the generation AI automatically generates related questions, allowing smooth input of supplemental information.

[0057] The supplemental information providing unit can collect supplemental information input from other users through crowdsourcing to improve accuracy. For example, it integrates information provided by multiple users. The supplemental information providing unit also uses crowdsourcing to build a system for inputting supplemental information. For example, it aggregates information provided by users to improve accuracy. The supplemental information providing unit also collects supplemental information through crowdsourcing from other users to improve accuracy, thereby generating more accurate highlight videos and news articles. For example, it verifies and integrates information provided by users. In this way, the accuracy of the supplemental information is improved by using crowdsourcing.

[0058] The highlight generation unit can analyze audio data within the video and add the sounds of spectators cheering and cheering in real time. For example, it can reflect the sounds of spectators cheering at goal scenes in the video. The highlight generation unit also builds a system in which the generation AI analyzes audio data and adds the sounds of spectators cheering and cheering in real time. For example, it can reflect the sounds of spectators cheering at important moments in the game in the video. The highlight generation unit also analyzes audio data within the video in real time and adds the sounds of spectators cheering and cheering to generate highlight videos that feel more realistic. For example, it can reflect the sounds of spectators cheering and cheering in the video. This makes it possible to generate highlight videos that feel more realistic by adding the sounds of spectators cheering and cheering in real time.

[0059] The highlight generation unit can automatically insert player interviews and comments into highlight footage. For example, a player's comments are added after a goal is scored. The highlight generation unit also analyzes player interviews and comments in the footage and builds a system to automatically insert them into highlight footage. For example, post-match interviews are reflected in the footage. The highlight generation unit also uses generation AI to automatically insert player interviews and comments, directly delivering the players' voices to viewers. For example, a player's post-match thoughts are reflected in the footage. This automatically inserting player interviews and comments directly delivers the players' voices to viewers.

[0060] The highlight generation unit can display game statistical data and graphs in the highlight footage in real time. For example, it displays the number of goals and assists a player has in the footage. The highlight generation unit also builds a system that analyzes game statistical data in the footage in real time and displays graphs. For example, it displays team performance in a graph. The highlight generation unit also provides viewers with detailed game data by having the generation AI display game statistical data and graphs in real time. For example, it displays player performance in a graph. In this way, detailed data can be provided to viewers by displaying game statistical data and graphs in real time.

[0061] The highlight generation unit can automatically generate commentary and commentary in different languages ​​to accommodate international viewers. For example, the generation AI automatically generates commentary and commentary in different languages. For example, commentary in English and Spanish is added. The highlight generation unit also automatically translates the commentary and commentary in the video into different languages, building a system that can accommodate international viewers. For example, commentary in French and German is added. The highlight generation unit can also accommodate international viewers by having the generation AI automatically generate commentary and commentary in different languages. For example, commentary in Japanese and Chinese is added. This allows commentary and commentary in different languages ​​to be automatically generated, thereby catering to international viewers.

[0062] The news article generation unit can automatically incorporate game statistical data and players' past performance into articles. For example, it adds a player's number of goals and assists to the article. The news article generation unit also builds a system that analyzes game statistical data and players' past performance in the video in real time and automatically incorporates them into articles. For example, it adds team performance to the article. The news article generation unit also provides readers with detailed data by having the generation AI automatically incorporate game statistical data and players' past performance into articles. For example, it adds player performance to the article. This allows game statistical data and players' past performance to be automatically incorporated into articles, providing readers with detailed data.

[0063] The news article generation unit can generate article content from different perspectives (for example, the perspective of a player or a spectator). For example, a generation AI generates article content from different perspectives. For example, articles are generated from the perspective of a player or a spectator. The news article generation unit also builds a system that analyzes information within video and generates articles from different perspectives. For example, articles are generated that reflect the players' impressions and the reactions of the spectators. The news article generation unit also provides readers with a multifaceted perspective by having a generation AI generate article content from different perspectives. For example, articles are generated from the perspective of a player or a spectator. In this way, article content is generated from different perspectives, providing readers with a multifaceted perspective.

[0064] The news article generation unit can also automatically translate news articles into different languages ​​to accommodate international readers. For example, the generation AI automatically translates news articles into different languages. For example, into English or Spanish. The news article generation unit also builds a system that automatically translates the content of articles into different languages ​​to accommodate international readers. For example, into French or German. The news article generation unit also builds a system that automatically translates news articles into different languages ​​to accommodate international readers. For example, into Japanese or Chinese. In this way, the generation AI automatically translates news articles into different languages ​​to accommodate international readers.

[0065] The news article generation unit converts the content of an article into a visual note or infographic, making it easier to understand visually. For example, the generation AI converts the content of an article into a visual note or infographic. For example, it displays statistical data of a match in a graph. The news article generation unit also builds a system that converts the content of an article into a visual note or infographic, making it easier to understand visually. For example, it displays player performance in a diagram. The news article generation unit also provides readers with information that is easier to understand visually by converting the content of an article into a visual note or infographic. For example, it displays highlights of a match in a diagram. In this way, by converting the content of an article into a visual note or infographic, it provides readers with information that is easier to understand visually.

[0066] The SNS posting unit can analyze the optimal timing for the generation AI to post and make suggestions to the user. For example, it can suggest times when there are many SNS users. The SNS posting unit also builds a system that analyzes the optimal timing for posting and makes suggestions to the user. For example, it can suggest specific days of the week or time periods. The SNS posting unit also analyzes the optimal timing for the generation AI to post and makes suggestions to the user, thereby maximizing the effectiveness of the post. For example, it can suggest times when there are many SNS users. In this way, the optimal timing for posting can be analyzed and suggested to the user, thereby maximizing the effectiveness of the post.

[0067] The SNS posting unit can maximize the effectiveness of posts by automatically generating hashtags and captions when posting. For example, when the generation AI posts, it automatically generates hashtags and captions. For example, it adds hashtags related to the content of the game. The SNS posting unit also builds a system that automatically generates hashtags and captions to maximize the effectiveness of posts. For example, it adds popular hashtags. The SNS posting unit also maximizes the effectiveness of posts by automatically generating hashtags and captions when the generation AI posts. For example, it adds captions related to the content of the game. In this way, the effectiveness of posts is maximized by automatically generating hashtags and captions.

[0068] The SNS posting unit can analyze reactions after posting in real time and provide feedback for the next post. For example, the generation AI analyzes reactions after posting in real time and provides feedback for the next post. For example, it suggests the content of the next post based on the reactions to the post. The SNS posting unit also builds a system that analyzes reactions after posting in real time and provides feedback for the next post. For example, it suggests improvements to the post based on user reactions. The SNS posting unit also improves the effectiveness of the post by using the generation AI to analyze reactions after posting in real time and provide feedback for the next post. For example, it adjusts the content of the next post based on the reactions to the post. In this way, the effectiveness of the post is improved by analyzing reactions after posting in real time and providing feedback for the next post.

[0069] The SNS posting unit can support different SNS platforms and provide a function that allows posting to multiple platforms simultaneously. For example, the generation AI can support different SNS platforms and provide a function that allows posting to multiple platforms simultaneously. For example, posting to TikTok and Instagram at the same time. The SNS posting unit can also build a system that can post to multiple SNS platforms simultaneously. For example, posting to Facebook and Twitter at the same time. The SNS posting unit can also support different SNS platforms and provide a function that allows posting to multiple platforms simultaneously, maximizing the effectiveness of posting. For example, posting to YouTube and LinkedIn at the same time. This maximizes the effectiveness of posting by supporting different SNS platforms and providing a function that allows posting to multiple platforms simultaneously.

[0070] The processing flow of the first embodiment will be briefly explained below.

[0071] Step 1: The video uploading unit uploads game footage posted by users. For example, game footage filmed by users can be uploaded to the system. The video uploading unit can also accept video in different formats. For example, it supports formats such as MP4, AVI, and MOV. Step 2: In the video analysis section, the generation AI analyzes the uploaded video. For example, the generation AI recognizes the players and play details in the video and extracts important scenes. The generation AI can also analyze the movements and sounds in the video to identify important scenes. For example, it can identify goal scenes and important plays and generate a highlight video based on them. Step 3: The supplemental information provider allows the user to provide supplemental information based on the video analyzed by the video analysis unit. For example, the user might respond "Shirato Jiro" to the question "What is this player's name?" This supplemental information is used by the generation AI to generate more accurate highlight videos and news articles. Step 4: The highlight generation unit generates a highlight video with commentary, narration, and cheers added by the generation AI based on the supplementary information provided by the supplementary information provision unit. For example, in the case of a goal, a commentary such as "Goal! Shiroto Jiro scores a great shot!" is added. Step 5: Based on the supplementary information provided by the supplementary information provider, the news article generator generates a professional-quality news article, like that written by a sports journalist. For example, it generates an article such as "Shirato Jiro led his team to victory with a brilliant shot." Step 6: The SNS posting unit posts the content generated by the highlight generation unit and the news article generation unit to SNS. For example, it provides a function that allows users to easily post the generated highlight videos and news articles to SNS such as TikTok and Instagram.

[0072] (Example 2) A sports video generation system according to an embodiment of the present invention is a system in which a generation AI generates professional-quality highlight videos and news articles based on game videos posted by users, and posts these to social media. This allows users to easily generate professional-quality highlight videos and news articles and post them to social media.

[0073] A sports video generation system according to an embodiment includes a video upload unit, a video analysis unit, a supplemental information providing unit, a highlight generation unit, a news article generation unit, and a social media posting unit. The video upload unit uploads game videos posted by users. For example, game videos filmed by users can be uploaded to the system. The video upload unit can accept video in different formats, such as MP4, AVI, and MOV. The video analysis unit uses a generation AI to analyze the uploaded video. For example, the generation AI recognizes the players and play details in the video and extracts important scenes. The generation AI can also analyze movements and sounds in the video to identify important scenes. For example, it identifies goal scenes and important plays and generates a highlight video based on them. The supplemental information providing unit allows the user to provide supplemental information based on the video analyzed by the video analysis unit. For example, the supplemental information providing unit answers the question, "What is this player's name?" with "Shirato Jiro." This supplemental information is used by the generation AI to generate more accurate highlight videos and news articles. The highlight generation unit generates a highlight video to which the generation AI adds commentary, narration, and cheers based on the supplemental information provided by the supplemental information providing unit. For example, a commentary such as "Goal! Shiroto Jiro scores a great shot!" is added to a goal scene. The news article generation unit generates a professional-quality news article like that written by a sports reporter based on the supplemental information provided by the supplemental information providing unit. For example, an article with the content "Shiroto Jiro led his team to victory with a great shot" is generated. The SNS posting unit posts the content generated by the highlight generation unit and the news article generation unit to SNS. For example, the SNS posting unit provides a function that allows users to easily post the generated highlight video and news article to SNS such as TikTok and Instagram. This allows the sports video generation system according to the embodiment to easily generate professional-quality highlight videos and news articles and post them to SNS. For example, users can widely share the content they create and attract attention.

[0074] The video analysis unit analyzes the movements and facial expressions of players in the video, estimates the emotional state of the players, and reflects this in the highlight footage. In the video analysis unit, for example, the generation AI analyzes the movements and facial expressions of players in the video and estimates the emotional state of the players. For example, it analyzes the expression of joy of a player who scores a goal and reflects that emotion in the highlight footage. The video analysis unit also analyzes the movements and facial expressions of players in the video in real time and estimates the emotional state of the players. For example, it analyzes expressions that show tension and concentration during a game and reflects this in the highlight footage. The video analysis unit also generates emotionally rich highlight footage by having the generation AI analyze the movements and facial expressions of players and estimate their emotional state. For example, it reflects in the video the joy and excitement of a player at the moment they score a goal. This makes it possible to generate emotionally rich highlight footage that reflects the emotional state of the players.

[0075] The video analysis unit can analyze the audience's reactions in the video and incorporate the audience's level of excitement into the highlight footage. For example, the generation AI in the video analysis unit analyzes the audience's reactions in the video and incorporates the audience's level of excitement into the highlight footage. For example, it analyzes the audience's cheers and applause at goal scenes and reflects this in the video. The video analysis unit also analyzes the audience's reactions in the video in real time and incorporates the audience's level of excitement into the highlight footage. For example, it reflects the audience's excitement at important moments in the game in the video. The video analysis unit also generates realistic footage by having the generation AI analyze the audience's reactions and incorporate the audience's level of excitement into the highlight footage. For example, it reflects the audience's cheers and support in the video. This makes it possible to generate realistic highlight footage that reflects the audience's excitement.

[0076] The video analysis unit can analyze the tactics and formations of a match and add tactical commentary. For example, the video analysis unit uses a generation AI to analyze the tactics and formations of a match and add tactical commentary. For example, it may explain the team's formation and tactics in a goal-scoring scene. The video analysis unit also analyzes the movements and positioning of players in the video and comment on the tactics and formations of the match. For example, it may explain defensive tactics and attacking patterns. The video analysis unit also uses a generation AI to analyze the tactics and formations of a match and add tactical commentary, allowing viewers to understand the tactical aspects of the match. For example, it may explain team tactical changes and player roles. This allows viewers to understand the tactical aspects of the match.

[0077] The video analysis unit can analyze the biometric data (heart rate, distance traveled, etc.) of players in the video and integrate it into the highlight footage. In the video analysis unit, for example, the generation AI analyzes the biometric data of players in the video and integrates it into the highlight footage. For example, it displays the player's heart rate and distance traveled. The video analysis unit also analyzes the biometric data of players in the video in real time and integrates it into the highlight footage. For example, it displays the player's fatigue level and performance. The video analysis unit also communicates the player's performance in detail to viewers by having the generation AI analyze the player's biometric data and integrate it into the highlight footage. For example, it displays the player's heart rate and distance traveled. This makes it possible to generate highlight footage that conveys the player's performance in detail.

[0078] The video analysis unit can expand the generation AI so that it can also handle game footage of different sports. For example, the video analysis unit expands the generation AI to handle game footage of different sports. For example, it analyzes game footage of basketball and tennis and generates highlight footage. The video analysis unit also improves the generation AI's algorithm to analyze game footage of different sports. For example, it analyzes basketball dribbles and shots, and tennis serves and rallies. The video analysis unit also expands the generation AI to handle game footage of different sports, thereby catering to a wide range of sports fans. For example, it analyzes game footage of basketball and tennis and generates highlight footage. This makes it possible to generate highlight footage that is compatible with a wide range of sports.

[0079] The video analysis unit can use the emotion estimation function to analyze the emotional reactions of the audience and generate a highlight video based on the audience's emotions. The video analysis unit, for example, uses the emotion estimation function to analyze the emotional reactions of the audience and generate a highlight video based on the audience's emotions. For example, the video reflects the cheers and excitement of the audience. The video analysis unit also analyzes the emotional reactions of the audience in the video in real time and generates a highlight video based on the audience's emotions. For example, the joy and surprise of the audience are reflected in the video. The video analysis unit also uses the emotion estimation function to analyze the emotional reactions of the audience and generate a highlight video based on the audience's emotions, thereby providing viewers with an emotionally rich video. For example, the cheers and excitement of the audience are reflected in the video. This makes it possible to generate an emotionally rich highlight video that reflects the audience's emotions.

[0080] The supplemental information providing unit can automatically add a player's past performance and statistical data based on the supplemental information provided by the user. The supplemental information providing unit, for example, automatically adds a player's past performance and statistical data based on the supplemental information provided by the user. For example, it displays the number of goals and assists a player has. The supplemental information providing unit also enriches the content of highlight videos and news articles by automatically adding a player's past performance and statistical data based on the supplemental information. For example, it displays the results and performance of a player's past games. The supplemental information providing unit also builds a system that automatically adds a player's past performance and statistical data based on the supplemental information provided by the user. For example, it displays the player's career highs and the results of important games. In this way, the automatic addition of a player's past performance and statistical data enriches the content of highlight videos and news articles.

[0081] The supplemental information providing unit inputs supplemental information using voice recognition technology, thereby reducing the burden on the user. The supplemental information providing unit, for example, inputs supplemental information using voice recognition technology, thereby reducing the burden on the user. For example, the user inputs the name of a player by voice. The supplemental information providing unit also uses voice recognition technology to build a system that makes it easy to input supplemental information. For example, the user provides information about the player by voice. The supplemental information providing unit also inputs supplemental information using voice recognition technology, thereby reducing the burden on the user and improving input accuracy. For example, the user inputs the name of a player or the name of a team by voice. In this way, using voice recognition technology reduces the burden on the user and improves input accuracy.

[0082] The supplemental information providing unit allows the generation AI to automatically generate related questions when supplemental information is input and suggest them to the user. For example, the supplemental information providing unit allows the generation AI to automatically generate related questions when supplemental information is input and suggest them to the user. For example, it generates a question such as, "What is this player's position?" The supplemental information providing unit also builds a system where the generation AI automatically generates related questions and suggests them to the user, thereby enabling smooth input of supplemental information. For example, it generates a question such as, "What was the result of this game?" The supplemental information providing unit also improves the accuracy of input by allowing the generation AI to automatically generate related questions when supplemental information is input and suggest them to the user. For example, it generates a question such as, "What is this player's uniform number?" In this way, the generation AI automatically generates related questions, allowing smooth input of supplemental information.

[0083] The supplemental information providing unit can collect supplemental information input from other users through crowdsourcing to improve accuracy. The supplemental information providing unit, for example, collects supplemental information input from other users through crowdsourcing to improve accuracy. For example, it integrates information provided by multiple users. The supplemental information providing unit also uses crowdsourcing to build a system for inputting supplemental information. For example, it aggregates information provided by users to improve accuracy. The supplemental information providing unit also collects supplemental information through crowdsourcing from other users to improve accuracy, thereby generating more accurate highlight videos and news articles. For example, it verifies and integrates information provided by users. In this way, the accuracy of the supplemental information is improved by using crowdsourcing.

[0084] The supplemental information providing unit can analyze the emotional state of the user when inputting supplemental information and generate a question based on the emotion. For example, the supplemental information providing unit analyzes the emotional state of the user when inputting supplemental information and generates a question based on the emotion. For example, if the user is excited, it generates a question such as "What were the highlights of this game?" The supplemental information providing unit also builds a system that analyzes the emotional state of the user and generates a question based on the emotion. For example, if the user is happy, it generates a question such as "What were the scenes where this player scored?" The supplemental information providing unit also analyzes the emotional state of the user when inputting supplemental information and generates a question based on the emotion, thereby improving the accuracy of the input. For example, if the user is surprised, it generates a question such as "What are the details of this play?" In this way, by generating a question based on the user's emotional state, the accuracy of the input is improved.

[0085] The supplemental information providing unit can use the emotion estimation function to analyze the emotion a user has when inputting supplemental information and provide an interface that elicits positive emotions. The supplemental information providing unit, for example, uses the emotion estimation function to analyze the emotion a user has when inputting supplemental information and provide an interface that elicits positive emotions. For example, an encouraging message is displayed while the user is inputting. The supplemental information providing unit also builds a system that analyzes the emotion of a user and provides an interface that elicits positive emotions. For example, success stories are presented while the user is inputting. The supplemental information providing unit also uses the emotion estimation function to analyze the emotion a user has when inputting supplemental information and provide an interface that elicits positive emotions, thereby improving the accuracy of input. For example, compliments are displayed while the user is inputting. This provides an interface that elicits positive emotions and improves the accuracy of input.

[0086] The highlight generation unit can analyze the emotional state of players and add commentary and narration based on their emotions. In the highlight generation unit, for example, the generation AI analyzes the emotional state of players and adds commentary and narration based on their emotions. For example, commentary that reflects the joy of a player at a goal is added. The highlight generation unit also analyzes the emotional state of players in the video in real time and adds commentary and narration based on their emotions. For example, commentary that reflects the tension during the game is added. In addition, the highlight generation unit provides viewers with emotionally rich video by analyzing the emotional state of players and adding commentary and narration based on their emotions. For example, commentary that reflects the joy and excitement of a player is added. This makes it possible to add emotional commentary and narration that reflects the emotional state of players.

[0087] The highlight generation unit can analyze audio data in the video and add the sounds of spectators cheering and cheering in real time. The highlight generation unit, for example, analyzes audio data in the video and adds the sounds of spectators cheering and cheering in real time. For example, the cheers of spectators at goal scenes are reflected in the video. The highlight generation unit also builds a system in which a generation AI analyzes audio data and adds the sounds of spectators cheering and cheering in real time. For example, the cheers of spectators at important moments in the game are reflected in the video. The highlight generation unit also analyzes audio data in the video in real time and adds the sounds of spectators cheering and cheering to generate a highlight video with a sense of presence. For example, the cheers of spectators are reflected in the video. In this way, the sounds of spectators cheering and cheering can be added in real time to generate a highlight video with a sense of presence.

[0088] The highlight generation unit can automatically insert player interviews and comments into highlight footage. For example, the generation AI of the highlight generation unit automatically inserts player interviews and comments. For example, a player's comments are added after a goal is scored. The highlight generation unit also analyzes player interviews and comments in the footage and builds a system that automatically inserts them into the highlight footage. For example, post-match interviews are reflected in the footage. The highlight generation unit also directly delivers the voices of players to viewers by having the generation AI automatically insert player interviews and comments. For example, a player's post-match thoughts are reflected in the footage. In this way, the automatic insertion of player interviews and comments directly delivers the voices of players to viewers.

[0089] The highlight generation unit can display game statistical data and graphs in the highlight footage in real time. In the highlight generation unit, for example, a generation AI displays game statistical data and graphs in real time. For example, the number of goals scored and the number of assists by a player are displayed in the footage. The highlight generation unit also analyzes game statistical data in the footage in real time and builds a system to display graphs. For example, it displays team performance in a graph. In addition, the highlight generation unit provides viewers with detailed game data by having a generation AI display game statistical data and graphs in real time. For example, it displays player performance in a graph. In this way, detailed data is provided to viewers by displaying game statistical data and graphs in real time.

[0090] The highlight generation unit can automatically generate commentary and commentary in different languages ​​to accommodate international viewers. For example, the generation AI in the highlight generation unit automatically generates commentary and commentary in different languages. For example, commentary in English or Spanish is added. The highlight generation unit also automatically translates the commentary and commentary in the video into different languages, building a system that can accommodate international viewers. For example, commentary in French or German is added. The highlight generation unit also accommodates international viewers by having the generation AI automatically generate commentary and commentary in different languages. For example, commentary in Japanese or Chinese is added. This allows commentary and commentary in different languages ​​to be automatically generated, thereby accommodating international viewers.

[0091] The highlight generation unit can use the emotion estimation function to identify the scene that moves the user the most and generate a highlight video that emphasizes that scene. The highlight generation unit, for example, uses the emotion estimation function to identify the scene that moves the user the most and generate a highlight video that emphasizes that scene. For example, it emphasizes a goal scene or an important play. The highlight generation unit also analyzes emotional responses in the video in real time and builds a system that identifies the scene that moves the user the most. For example, it emphasizes the cheers of the audience and the joy of the players. The highlight generation unit also uses the emotion estimation function to identify the scene that moves the user the most and generate a highlight video that emphasizes that scene, thereby moving the viewer. For example, it emphasizes the joy and excitement of the players. In this way, it is possible to generate a highlight video that moves the viewer by emphasizing the scene that moves the user the most.

[0092] The news article generation unit can analyze the emotional state of players and generate articles based on their emotions. In the news article generation unit, for example, a generation AI analyzes the emotional state of players and generates articles based on their emotions. For example, an article is generated that reflects the joy of a player at a goal scene. The news article generation unit also builds a system that analyzes the emotional state of players in video in real time and generates articles based on their emotions. For example, an article is generated that reflects the tension during a game. The news article generation unit also provides readers with emotionally rich articles by using a generation AI to analyze the emotional state of players and generate articles based on their emotions. For example, an article is generated that reflects the joy and excitement of a player. This makes it possible to generate emotionally rich articles that reflect the emotional state of players.

[0093] The news article generation unit can automatically incorporate game statistical data and players' past performance into articles. In the news article generation unit, for example, the generation AI automatically incorporates game statistical data and players' past performance into articles. For example, it adds a player's number of goals and assists to an article. The news article generation unit also builds a system that analyzes game statistical data and players' past performance in video in real time and automatically incorporates them into articles. For example, it adds team performance to an article. In addition, the news article generation unit provides readers with detailed data by having the generation AI automatically incorporate game statistical data and players' past performance into articles. For example, it adds player performance to an article. In this way, the game statistical data and players' past performance are automatically incorporated into articles, providing readers with detailed data.

[0094] The news article generation unit can generate the content of an article from different perspectives (for example, the perspective of a player or a spectator). In the news article generation unit, for example, a generation AI generates the content of an article from different perspectives. For example, an article is generated from the perspective of a player or a spectator. The news article generation unit also builds a system that analyzes information within a video and generates articles from different perspectives. For example, an article is generated that reflects the impressions of the players and the reactions of the spectators. The news article generation unit also provides readers with a multifaceted perspective by having a generation AI generate the content of an article from different perspectives. For example, an article is generated from the perspective of a player or a spectator. In this way, by generating the content of an article from different perspectives, a multifaceted perspective is provided to readers.

[0095] The news article generation unit can also automatically translate news articles into different languages ​​to accommodate international readers. For example, the news article generation unit uses a generation AI to automatically translate news articles into different languages. For example, translating into English or Spanish. The news article generation unit also builds a system that automatically translates the content of an article into different languages ​​to accommodate international readers. For example, translating into French or German. The news article generation unit also builds a system that automatically translates news articles into different languages ​​to accommodate international readers. For example, translating into Japanese or Chinese. In this way, the news article generation unit can automatically translate news articles into different languages ​​to accommodate international readers.

[0096] The news article generation unit converts the content of an article into a visual note or infographic, making it easier to understand visually. In the news article generation unit, for example, a generation AI converts the content of an article into a visual note or infographic. For example, statistical data of a match is displayed in a graph. The news article generation unit also builds a system that converts the content of an article into a visual note or infographic to make it easier to understand visually. For example, player performance is displayed in a diagram. The news article generation unit also provides information that is easier to understand visually to readers by using a generation AI to convert the content of an article into a visual note or infographic. For example, highlights of a match are displayed in a diagram. In this way, by converting the content of an article into a visual note or infographic, information that is easier to understand visually is provided.

[0097] The news article generation unit can use the emotion estimation function to identify content that readers are most interested in and generate articles that emphasize that content. The news article generation unit, for example, uses the emotion estimation function to identify content that readers are most interested in and generate articles that emphasize that content. For example, it emphasizes goal scenes and important plays. The news article generation unit also analyzes the content of articles using the emotion estimation function and builds a system that identifies content that readers are most interested in. For example, it emphasizes the cheers of the spectators and the joy of the players. The news article generation unit also uses the emotion estimation function to identify content that readers are most interested in and generate articles that emphasize that content, thereby moving the reader. For example, it emphasizes the joy and excitement of the players. In this way, it is possible to generate articles that move the reader by emphasizing the content that readers are most interested in.

[0098] The SNS posting unit can analyze the optimal timing for the generation AI to post and make suggestions to the user. The SNS posting unit, for example, analyzes the optimal timing for the generation AI to post and makes suggestions to the user. For example, it suggests time periods when there are many SNS users. The SNS posting unit also builds a system that analyzes the optimal timing for posting and makes suggestions to the user. For example, it suggests specific days of the week or time periods. The SNS posting unit also analyzes the optimal timing for the generation AI to post and makes suggestions to the user, thereby maximizing the effectiveness of the post. For example, it suggests time periods when there are many SNS users. In this way, the optimal timing for posting is analyzed and suggestions to the user are made, thereby maximizing the effectiveness of the post.

[0099] The SNS posting unit can maximize the effectiveness of posts by automatically generating hashtags and captions when posting. For example, the SNS posting unit automatically generates hashtags and captions when the generation AI posts. For example, hashtags related to the content of the match are added. The SNS posting unit also builds a system that automatically generates hashtags and captions to maximize the effectiveness of posts. For example, popular hashtags are added. The SNS posting unit also maximizes the effectiveness of posts by automatically generating hashtags and captions when the generation AI posts. For example, captions related to the content of the match are added. In this way, the effectiveness of posts is maximized by automatically generating hashtags and captions.

[0100] The SNS posting unit can analyze reactions after posting in real time and provide feedback for the next post. In the SNS posting unit, for example, a generation AI analyzes reactions after posting in real time and provides feedback for the next post. For example, the content of the next post is suggested based on the reactions to the post. The SNS posting unit also builds a system that analyzes reactions after posting in real time and provides feedback for the next post. For example, it suggests improvements to the post based on user reactions. In addition, the SNS posting unit improves the effectiveness of the post by using a generation AI to analyze reactions after posting in real time and provide feedback for the next post. For example, it adjusts the content of the next post based on the reactions to the post. In this way, the effectiveness of the post is improved by analyzing reactions after posting in real time and providing feedback for the next post.

[0101] The SNS posting unit can support different SNS platforms and provide a function that allows posting to multiple platforms simultaneously. For example, the generation AI supports different SNS platforms and provides a function that allows posting to multiple platforms simultaneously. For example, posting to TikTok and Instagram simultaneously. The SNS posting unit also builds a system that can post to multiple SNS platforms simultaneously. For example, posting to Facebook and Twitter simultaneously. The SNS posting unit also maximizes the effectiveness of posts by supporting different SNS platforms and providing a function that allows posting to multiple platforms simultaneously. For example, posting to YouTube and LinkedIn simultaneously. This maximizes the effectiveness of posts by supporting different SNS platforms and providing a function that allows posting to multiple platforms simultaneously.

[0102] The SNS posting unit can analyze the user's emotional state when posting and suggest captions and comments based on the emotions. For example, when the generation AI posts, the SNS posting unit analyzes the user's emotional state and suggests captions and comments based on the emotions. For example, if the user is happy, a positive caption is suggested. The SNS posting unit also builds a system that analyzes the user's emotional state and suggests captions and comments based on the emotions. For example, if the user is excited, an inspiring comment is suggested. The SNS posting unit also analyzes the user's emotional state when the generation AI posts and suggests captions and comments based on the emotions, thereby improving the effectiveness of the post. For example, if the user is surprised, a caption that expresses surprise is suggested. In this way, the effectiveness of the post is improved by suggesting captions and comments based on the user's emotional state.

[0103] The SNS posting unit can use the emotion estimation function to analyze the user's emotional response after posting and suggest optimal content for the next post. The SNS posting unit, for example, uses the emotion estimation function to analyze the user's emotional response after posting and suggest optimal content for the next post. For example, it suggests content that receives a lot of positive responses. The SNS posting unit also builds a system that analyzes the user's emotional response after posting in real time and suggests optimal content for the next post. For example, it suggests content based on the user's emotion score. The SNS posting unit also uses the emotion estimation function to analyze the user's emotional response after posting and suggest optimal content for the next post, thereby improving the effectiveness of the post. For example, it suggests content according to the user's emotional changes. In this way, the effectiveness of the post is improved by analyzing the user's emotional response after posting and suggesting optimal content for the next post.

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

[0105] The video uploading unit uploads game videos posted by users. For example, users can upload game videos they have filmed to the system. The video uploading unit can also accept video in different formats, such as MP4, AVI, and MOV. The video analysis unit uses a generation AI to analyze the uploaded video. For example, the generation AI recognizes the players and play details in the video and extracts important scenes. The generation AI can also analyze the movements and sounds in the video to identify important scenes. For example, it identifies goal scenes and important plays and generates highlight videos based on them. The supplemental information provision unit allows users to provide supplemental information based on the video analyzed by the video analysis unit. For example, a user might respond with "Shirato Jiro" to the question, "What's this player's name?" This supplemental information is used by the generation AI to generate more accurate highlight videos and news articles. The highlight generation unit generates highlight videos with commentary, commentary, and cheers based on the supplemental information provided by the supplemental information provision unit. For example, a commentary such as "Goal! Shirato Jiro scores a great shot!" is added to a goal scene. The news article generation unit uses a generation AI to generate professional-quality news articles like those written by a sports reporter, based on the supplemental information provided by the supplemental information providing unit. For example, an article such as "Shirato Jiro led his team to victory with a spectacular shot" is generated. The SNS posting unit posts the content generated by the highlight generation unit and the news article generation unit to SNS. For example, it provides a function that allows users to easily post the generated highlight videos and news articles to SNS such as TikTok and Instagram. This allows the sports video generation system according to the embodiment to allow users to easily generate professional-quality highlight videos and news articles and post them to SNS. For example, users can widely share the content they create and attract attention.

[0106] The video analysis unit analyzes the movements and facial expressions of players in the video to estimate the player's emotional state and reflect this in the highlight video. For example, it can analyze the joyful expression of a player who scores a goal and reflect this emotion in the highlight video. The video analysis unit also analyzes the movements and facial expressions of players in the video in real time to estimate the player's emotional state. For example, it can analyze facial expressions that show tension or concentration during a game and reflect this in the highlight video. The video analysis unit also generates emotionally rich highlight videos by having the generation AI analyze the players' movements and facial expressions and estimate their emotional state. For example, it can reflect in the video the joy and excitement of a player when he scores a goal. This makes it possible to generate emotionally rich highlight videos that reflect the player's emotional state.

[0107] The video analysis unit analyzes the reactions of the spectators in the video and can incorporate the level of excitement of the spectators into the highlight footage. For example, it analyzes the cheers and applause of the spectators at goal scenes and reflects this in the video. The video analysis unit also analyzes the reactions of the spectators in the video in real time and incorporates the level of excitement of the spectators into the highlight footage. For example, it reflects the excitement of the spectators at important moments in the game in the video. The video analysis unit also uses the generation AI to analyze the reactions of the spectators and incorporate the level of excitement of the spectators into the highlight footage, thereby generating realistic footage. For example, it reflects the cheers and support of the spectators in the video. This makes it possible to generate realistic highlight footage that reflects the excitement of the spectators.

[0108] The video analysis unit can analyze the tactics and formations of a match and add tactical commentary. For example, it can explain the team's formation and tactics in a goal-scoring scene. The video analysis unit can also analyze the movements and positioning of players in the video and add commentary on the tactics and formations of the match. For example, it can explain defensive tactics and attacking patterns. The video analysis unit can also use the generation AI to analyze the tactics and formations of a match and add tactical commentary to help viewers understand the tactical aspects of the match. For example, it can explain the team's tactical changes and the roles of players. This allows viewers to understand the tactical aspects of the match.

[0109] The video analysis unit can analyze the biometric data of players in the video (heart rate, distance traveled, etc.) and integrate it into the highlight footage. For example, it can display the player's heart rate and distance traveled. The video analysis unit also analyzes the biometric data of players in the video in real time and integrates it into the highlight footage. For example, it can display the player's fatigue level and performance. The video analysis unit also allows the generation AI to analyze the player's biometric data and integrate it into the highlight footage, thereby providing viewers with detailed information about the player's performance. For example, it can display the player's heart rate and distance traveled. This makes it possible to generate highlight footage that conveys the player's performance in detail.

[0110] The video analysis unit can expand the generation AI to handle game footage from different sports. For example, it can analyze game footage from basketball and tennis to generate highlight footage. The video analysis unit also improves the generation AI's algorithms to analyze game footage from different sports. For example, it can analyze basketball dribbles and shots, and tennis serves and rallies. The video analysis unit can also expand the generation AI to handle game footage from different sports, thereby catering to a wide range of sports fans. For example, it can analyze game footage from basketball and tennis to generate highlight footage. This makes it possible to generate highlight footage for a wide range of sports.

[0111] The video analysis unit can use the emotion estimation function to analyze the emotional reactions of the audience and generate highlight footage based on the audience's emotions. For example, the cheers and excitement of the audience can be reflected in the video. The video analysis unit can also analyze the emotional reactions of the audience in the video in real time and generate highlight footage based on the audience's emotions. For example, the joy and surprise of the audience can be reflected in the video. The video analysis unit can also use the emotion estimation function to analyze the emotional reactions of the audience and generate highlight footage based on the audience's emotions, thereby providing viewers with emotionally rich footage. For example, the cheers and excitement of the audience can be reflected in the video. This makes it possible to generate emotionally rich highlight footage that reflects the audience's emotions.

[0112] The supplemental information providing unit can automatically add a player's past performance and statistical data based on the supplemental information provided by the user. For example, it displays the number of goals and assists the player has. The supplemental information providing unit also enriches the content of highlight videos and news articles by automatically adding a player's past performance and statistical data based on the supplemental information. For example, it displays the results and performance of a player's past games. The supplemental information providing unit also builds a system that automatically adds a player's past performance and statistical data based on the supplemental information provided by the user. For example, it displays the player's career highs and the results of important games. In this way, the automatic addition of a player's past performance and statistical data enriches the content of highlight videos and news articles.

[0113] The supplemental information providing unit inputs supplemental information using voice recognition technology, thereby reducing the burden on the user. For example, the user inputs the name of a player by voice. The supplemental information providing unit also uses voice recognition technology to build a system that makes it easy to input supplemental information. For example, the user provides player information by voice. The supplemental information providing unit also inputs supplemental information using voice recognition technology, thereby reducing the burden on the user and improving input accuracy. For example, the user inputs the name of a player or the name of a team by voice. In this way, using voice recognition technology reduces the burden on the user and improves input accuracy.

[0114] The supplemental information provision unit allows the generation AI to automatically generate related questions and suggest them to the user when supplemental information is input. For example, it generates a question such as, "What is this player's position?" The supplemental information provision unit also builds a system that allows the generation AI to automatically generate related questions and suggest them to the user, thereby enabling smooth input of supplemental information. For example, it generates a question such as, "What was the result of this game?" The supplemental information provision unit also improves the accuracy of input by allowing the generation AI to automatically generate related questions and suggest them to the user when supplemental information is input. For example, it generates a question such as, "What is this player's uniform number?" As a result, the generation AI automatically generates related questions, allowing smooth input of supplemental information.

[0115] The supplemental information providing unit can collect supplemental information input from other users through crowdsourcing to improve accuracy. For example, it integrates information provided by multiple users. The supplemental information providing unit also uses crowdsourcing to build a system for inputting supplemental information. For example, it aggregates information provided by users to improve accuracy. The supplemental information providing unit also collects supplemental information through crowdsourcing from other users to improve accuracy, thereby generating more accurate highlight videos and news articles. For example, it verifies and integrates information provided by users. In this way, the accuracy of the supplemental information is improved by using crowdsourcing.

[0116] The supplemental information providing unit can analyze the emotional state of the user when inputting supplemental information and generate a question based on the emotion. For example, if the user is excited, it generates a question such as "What were the highlights of this game?" The supplemental information providing unit also builds a system that analyzes the emotional state of the user and generates a question based on the emotion. For example, if the user is happy, it generates a question such as "What was the scene where this player scored?" The supplemental information providing unit also analyzes the emotional state of the user when inputting supplemental information and generates a question based on the emotion, thereby improving the accuracy of the input. For example, if the user is surprised, it generates a question such as "What are the details of this play?" In this way, by generating a question based on the user's emotional state, the accuracy of the input is improved.

[0117] The supplemental information providing unit can use the emotion estimation function to analyze the emotion a user has when inputting supplemental information and provide an interface that elicits positive emotions. For example, an encouraging message is displayed while the user is inputting. The supplemental information providing unit also builds a system that analyzes the emotion a user has and provides an interface that elicits positive emotions. For example, success stories are presented while the user is inputting. The supplemental information providing unit also uses the emotion estimation function to analyze the emotion a user has when inputting supplemental information and provides an interface that elicits positive emotions, thereby improving the accuracy of input. For example, compliments are displayed while the user is inputting. This provides an interface that elicits positive emotions, thereby improving the accuracy of input.

[0118] The highlight generation unit can analyze the emotional state of players and add commentary and narration based on their emotions. For example, commentary that reflects the player's joy when a goal is scored can be added. The highlight generation unit also analyzes the emotional state of players in the video in real time and adds commentary and narration based on their emotions. For example, commentary that reflects the tension during the game can be added. The highlight generation unit also provides viewers with emotionally rich footage by using the generation AI to analyze the emotional state of players and add commentary and narration based on their emotions. For example, commentary that reflects the player's joy and excitement can be added. This makes it possible to add commentary and narration that reflects the player's emotional state.

[0119] The highlight generation unit can analyze audio data within the video and add the sounds of spectators cheering and cheering in real time. For example, it can reflect the sounds of spectators cheering at goal scenes in the video. The highlight generation unit also builds a system in which the generation AI analyzes audio data and adds the sounds of spectators cheering and cheering in real time. For example, it can reflect the sounds of spectators cheering at important moments in the game in the video. The highlight generation unit also analyzes audio data within the video in real time and adds the sounds of spectators cheering and cheering to generate highlight videos that feel more realistic. For example, it can reflect the sounds of spectators cheering and cheering in the video. This makes it possible to generate highlight videos that feel more realistic by adding the sounds of spectators cheering and cheering in real time.

[0120] The highlight generation unit can automatically insert player interviews and comments into highlight footage. For example, a player's comments are added after a goal is scored. The highlight generation unit also analyzes player interviews and comments in the footage and builds a system to automatically insert them into highlight footage. For example, post-match interviews are reflected in the footage. The highlight generation unit also uses generation AI to automatically insert player interviews and comments, directly delivering the players' voices to viewers. For example, a player's post-match thoughts are reflected in the footage. This automatically inserting player interviews and comments directly delivers the players' voices to viewers.

[0121] The highlight generation unit can display game statistical data and graphs in the highlight footage in real time. For example, it displays the number of goals and assists a player has in the footage. The highlight generation unit also builds a system that analyzes game statistical data in the footage in real time and displays graphs. For example, it displays team performance in a graph. The highlight generation unit also provides viewers with detailed game data by having the generation AI display game statistical data and graphs in real time. For example, it displays player performance in a graph. In this way, detailed data can be provided to viewers by displaying game statistical data and graphs in real time.

[0122] The highlight generation unit can automatically generate commentary and commentary in different languages ​​to accommodate international viewers. For example, the generation AI automatically generates commentary and commentary in different languages. For example, commentary in English and Spanish is added. The highlight generation unit also automatically translates the commentary and commentary in the video into different languages, building a system that can accommodate international viewers. For example, commentary in French and German is added. The highlight generation unit can also accommodate international viewers by having the generation AI automatically generate commentary and commentary in different languages. For example, commentary in Japanese and Chinese is added. This allows commentary and commentary in different languages ​​to be automatically generated, thereby catering to international viewers.

[0123] The highlight generation unit can use the emotion estimation function to identify the scenes that move the user most and generate a highlight video that emphasizes those scenes. For example, it can emphasize goal scenes and important plays. The highlight generation unit also analyzes emotional responses in the video in real time to build a system that identifies the scenes that move the user most. For example, it can emphasize the cheers of the audience and the joy of the players. The highlight generation unit also uses the emotion estimation function to identify the scenes that move the user most and generate a highlight video that emphasizes those scenes, thereby moving the viewer. For example, it can emphasize the joy and excitement of the players. In this way, it is possible to generate a highlight video that moves the viewer by emphasizing the scenes that move the user most.

[0124] The news article generation unit can analyze the emotional state of players and generate articles based on their emotions. For example, it generates an article that reflects the joy of a player when a goal is scored. The news article generation unit also builds a system that analyzes the emotional state of players in video footage in real time and generates articles based on their emotions. For example, it generates articles that reflect the tension during a game. The news article generation unit also provides readers with emotionally rich articles by using a generation AI to analyze the emotional state of players and generate articles based on their emotions. For example, it generates an article that reflects the joy and excitement of a player. This makes it possible to generate emotionally rich articles that reflect the emotional state of players.

[0125] The news article generation unit can automatically incorporate game statistical data and players' past performance into articles. For example, it adds a player's number of goals and assists to the article. The news article generation unit also builds a system that analyzes game statistical data and players' past performance in the video in real time and automatically incorporates them into articles. For example, it adds team performance to the article. The news article generation unit also provides readers with detailed data by having the generation AI automatically incorporate game statistical data and players' past performance into articles. For example, it adds player performance to the article. This allows game statistical data and players' past performance to be automatically incorporated into articles, providing readers with detailed data.

[0126] The news article generation unit can generate article content from different perspectives (for example, the perspective of a player or a spectator). For example, a generation AI generates article content from different perspectives. For example, articles are generated from the perspective of a player or a spectator. The news article generation unit also builds a system that analyzes information within video and generates articles from different perspectives. For example, articles are generated that reflect the players' impressions and the reactions of the spectators. The news article generation unit also provides readers with a multifaceted perspective by having a generation AI generate article content from different perspectives. For example, articles are generated from the perspective of a player or a spectator. In this way, article content is generated from different perspectives, providing readers with a multifaceted perspective.

[0127] The news article generation unit can also automatically translate news articles into different languages ​​to accommodate international readers. For example, the generation AI automatically translates news articles into different languages. For example, into English or Spanish. The news article generation unit also builds a system that automatically translates the content of articles into different languages ​​to accommodate international readers. For example, into French or German. The news article generation unit also builds a system that automatically translates news articles into different languages ​​to accommodate international readers. For example, into Japanese or Chinese. In this way, the generation AI automatically translates news articles into different languages ​​to accommodate international readers.

[0128] The news article generation unit converts the content of an article into a visual note or infographic, making it easier to understand visually. For example, the generation AI converts the content of an article into a visual note or infographic. For example, it displays statistical data of a match in a graph. The news article generation unit also builds a system that converts the content of an article into a visual note or infographic, making it easier to understand visually. For example, it displays player performance in a diagram. The news article generation unit also provides readers with information that is easier to understand visually by converting the content of an article into a visual note or infographic. For example, it displays highlights of a match in a diagram. In this way, by converting the content of an article into a visual note or infographic, it provides readers with information that is easier to understand visually.

[0129] The news article generation unit can use the emotion estimation function to identify the content that readers are most interested in and generate articles that emphasize that content. For example, it can emphasize goal scenes and important plays. The news article generation unit also uses the emotion estimation function to analyze the content of articles and build a system that identifies the content that readers are most interested in. For example, it can emphasize the cheers of the spectators and the joy of the players. The news article generation unit also uses the emotion estimation function to identify the content that readers are most interested in and generate articles that emphasize that content, thereby moving the reader. For example, it can emphasize the joy and excitement of the players. In this way, it is possible to generate articles that move the reader by emphasizing the content that readers are most interested in.

[0130] The SNS posting unit can analyze the optimal timing for the generation AI to post and make suggestions to the user. For example, it can suggest times when there are many SNS users. The SNS posting unit also builds a system that analyzes the optimal timing for posting and makes suggestions to the user. For example, it can suggest specific days of the week or time periods. The SNS posting unit also analyzes the optimal timing for the generation AI to post and makes suggestions to the user, thereby maximizing the effectiveness of the post. For example, it can suggest times when there are many SNS users. In this way, the optimal timing for posting can be analyzed and suggested to the user, thereby maximizing the effectiveness of the post.

[0131] The SNS posting unit can maximize the effectiveness of posts by automatically generating hashtags and captions when posting. For example, when the generation AI posts, it automatically generates hashtags and captions. For example, it adds hashtags related to the content of the game. The SNS posting unit also builds a system that automatically generates hashtags and captions to maximize the effectiveness of posts. For example, it adds popular hashtags. The SNS posting unit also maximizes the effectiveness of posts by automatically generating hashtags and captions when the generation AI posts. For example, it adds captions related to the content of the game. In this way, the effectiveness of posts is maximized by automatically generating hashtags and captions.

[0132] The SNS posting unit can analyze reactions after posting in real time and provide feedback for the next post. For example, the generation AI analyzes reactions after posting in real time and provides feedback for the next post. For example, it suggests the content of the next post based on the reactions to the post. The SNS posting unit also builds a system that analyzes reactions after posting in real time and provides feedback for the next post. For example, it suggests improvements to the post based on user reactions. The SNS posting unit also improves the effectiveness of the post by using the generation AI to analyze reactions after posting in real time and provide feedback for the next post. For example, it adjusts the content of the next post based on the reactions to the post. In this way, the effectiveness of the post is improved by analyzing reactions after posting in real time and providing feedback for the next post.

[0133] The SNS posting unit can support different SNS platforms and provide a function that allows posting to multiple platforms simultaneously. For example, the generation AI can support different SNS platforms and provide a function that allows posting to multiple platforms simultaneously. For example, posting to TikTok and Instagram at the same time. The SNS posting unit can also build a system that can post to multiple SNS platforms simultaneously. For example, posting to Facebook and Twitter at the same time. The SNS posting unit can also support different SNS platforms and provide a function that allows posting to multiple platforms simultaneously, maximizing the effectiveness of posting. For example, posting to YouTube and LinkedIn at the same time. This maximizes the effectiveness of posting by supporting different SNS platforms and providing a function that allows posting to multiple platforms simultaneously.

[0134] The SNS posting unit can analyze the user's emotional state when posting and suggest captions and comments based on the emotion. For example, when the generation AI posts, it analyzes the user's emotional state and suggests captions and comments based on the emotion. For example, if the user is happy, it suggests a positive caption. The SNS posting unit also builds a system that analyzes the user's emotional state and suggests captions and comments based on the emotion. For example, if the user is excited, it suggests an inspiring comment. The SNS posting unit also analyzes the user's emotional state when posting and suggests captions and comments based on the emotion, thereby improving the effectiveness of the post. For example, if the user is surprised, it suggests a caption that expresses surprise. In this way, the effectiveness of the post is improved by suggesting captions and comments based on the user's emotional state.

[0135] The SNS posting unit can use the emotion estimation function to analyze the user's emotional response after posting and suggest optimal content for the next post. For example, the emotion estimation function can be used to analyze the user's emotional response after posting and suggest optimal content for the next post. For example, content with a large number of positive responses can be suggested. The SNS posting unit can also build a system that analyzes the user's emotional response after posting in real time and suggests optimal content for the next post. For example, content can be suggested based on the user's emotion score. The SNS posting unit can also use the emotion estimation function to analyze the user's emotional response after posting and suggest optimal content for the next post, thereby improving the effectiveness of the post. For example, content can be suggested according to changes in the user's emotions. In this way, the effectiveness of the post can be improved by analyzing the user's emotional response after posting and suggesting optimal content for the next post.

[0136] The processing flow of the second embodiment will be briefly explained below.

[0137] Step 1: The video uploading unit uploads game footage posted by users. For example, game footage filmed by users can be uploaded to the system. The video uploading unit can also accept video in different formats. For example, it supports formats such as MP4, AVI, and MOV. Step 2: In the video analysis section, the generation AI analyzes the uploaded video. For example, the generation AI recognizes the players and play details in the video and extracts important scenes. The generation AI can also analyze the movements and sounds in the video to identify important scenes. For example, it can identify goal scenes and important plays and generate a highlight video based on them. Step 3: The supplemental information provider allows the user to provide supplemental information based on the video analyzed by the video analysis unit. For example, the user might respond "Shirato Jiro" to the question "What is this player's name?" This supplemental information is used by the generation AI to generate more accurate highlight videos and news articles. Step 4: The highlight generation unit generates a highlight video with commentary, narration, and cheers added by the generation AI based on the supplementary information provided by the supplementary information provision unit. For example, in the case of a goal, a commentary such as "Goal! Shiroto Jiro scores a great shot!" is added. Step 5: Based on the supplementary information provided by the supplementary information provider, the news article generator generates a professional-quality news article, like that written by a sports journalist. For example, it generates an article such as "Shirato Jiro led his team to victory with a brilliant shot." Step 6: The SNS posting unit posts the content generated by the highlight generation unit and the news article generation unit to SNS. For example, it provides a function that allows users to easily post the generated highlight videos and news articles to SNS such as TikTok and Instagram.

[0138] 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.

[0139] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0140] 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.

[0141] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0142] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the 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 specific processing unit 290 using these models.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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).

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] In the robot 414, 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 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 processing similar to that of the specific processing unit 290 using these models.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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).

[0191] 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.

[0192] 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."

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0205] 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 video upload unit for uploading videos; a video analysis unit that analyzes the video uploaded by the video upload unit; a supplemental information providing unit that provides supplemental information based on the video analyzed by the video analyzing unit; a highlight generation unit that generates a highlight video based on the supplemental information provided by the supplemental information providing unit; a news article generating unit that generates a news article based on the supplemental information provided by the supplemental information providing unit; a social networking service posting unit that posts the content generated by the highlight generation unit and the news article generation unit to a social networking service.

2. The video analysis unit The movements and facial expressions of the players in the video are analyzed, and the emotional state of the players is estimated and reflected in the highlight video.

2. The system of claim 1.

3. The video analysis unit The reaction of the audience in the video is analyzed, and the degree of excitement of the audience is incorporated into the highlight video.

2. The system of claim 1.

4. The video analysis unit Analyze match tactics and formations and add tactical commentary 2. The system of claim 1.

5. The video analysis unit Analyzing biometric data of players in the video and integrating it into the highlight video.

2. The system of claim 1.

6. The video analysis unit Expand the generation AI to handle game footage of different sports.

2. The system of claim 1.

Images