system

Abstract

The system according to the embodiment aims to reduce the number of steps required for video editing and to perform editing efficiently. [Solution] A system according to an embodiment includes a learning unit, an input unit, an editing unit, and an output unit. The learning unit learns the style of a video editor. The input unit receives raw footage from a video uploader. The editing unit performs editing based on the style learned by the learning unit. The output unit outputs the edited video.

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the problem that video editing requires a large number of steps and is difficult to perform efficiently.

[0005] The system according to the embodiment aims to reduce the number of steps required for video editing and to perform editing efficiently. [Means for solving the problem]

[0006] The system according to the embodiment includes a learning unit, an input unit, an editing unit, and an output unit. The learning unit learns the style of a video editor. The input unit receives raw footage from a video poster. The editing unit performs editing based on the style learned by the learning unit. The output unit outputs the edited video. [Effects of the Invention]

[0007] The system according to the embodiment reduces the number of steps required for video editing and enables efficient editing. [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 video editing system according to an embodiment of the present invention utilizes a generation AI to quickly complete video editing. This video editing system trains the generation AI to learn a video editor's editing style, such as captions and sound effects. A video uploader shoots raw footage and inputs it into the generation AI. The system automatically inserts captions and sound effects based on the learned editing style and outputs the edited video. This system allows video uploaders to significantly reduce the time it takes to edit. This system is also applicable to real-time video editing, such as for television news flashes. For example, the generation AI can automatically insert captions and sound effects into breaking news footage. This significantly improves the efficiency of video editing and reduces the workload of video uploaders and television stations. For example, a video editor can train the generation AI to learn their own editing style, such as how to insert captions at specific times and when to use specific sound effects. This training is performed using past editing data. Next, the video uploader shoots raw footage. This raw footage is input into the generation AI. The generation AI automatically inserts captions and sound effects based on the learned editing style. For example, it is possible to insert captions in specific scenes and add sound effects at specific times. Videos edited by the generative AI are ready to post immediately, allowing video uploaders to significantly reduce the time required for editing. This system can also be applied to real-time video editing of things like television news flashes. For example, the generative AI can automatically insert captions and add sound effects to breaking news footage. This system significantly improves the efficiency of video editing and reduces the workload of video uploaders and television stations. As a result, the video editing system automatically edits videos by requiring only the video uploader to input raw footage, significantly improving the efficiency of editing work.

[0029] A video editing system according to an embodiment includes a learning unit, an input unit, an editing unit, and an output unit. The learning unit learns the style of a video editor. Examples of the video editor's style include, but are not limited to, the editing tempo, the effects used, and the frequency of cuts. For example, the learning unit uses past editing data to learn how to insert captions at specific times and when to use specific sound effects. For example, the learning unit analyzes past editing data to extract the editor's style. The input unit receives raw video from a video uploader. Examples of the raw video include, but are not limited to, resolution, frame rate, and file format. For example, the input unit inputs raw video captured by the video uploader into the system. The editing unit performs editing based on the style learned by the learning unit. Examples of editing include, but are not limited to, cuts, transitions, and effect application methods. For example, the editing unit inserts captions in specific scenes and adds sound effects at specific times based on the learned style. The output unit outputs the edited video. The output may include, but is not limited to, a file format, a resolution, a frame rate, etc. The output unit outputs the edited video in a specified file format, for example. As a result, the video editing system according to the embodiment automatically performs editing by simply inputting raw video footage by the video uploader, thereby significantly improving the efficiency of editing work.

[0030] The video editing apparatus includes a setting unit that sets the font or color of the caption. The setting unit sets the font and color of the caption. Examples of fonts include, but are not limited to, sans serif, serif, and handwritten style. The setting unit applies, for example, a font selected by a video editor to the caption. Examples of colors include, but are not limited to, hue, saturation, and brightness. The setting unit applies, for example, a color selected by the video editor to the caption. In this way, by setting the font and color of the caption, the visibility and design of the video are improved.

[0031] The video processing device includes a sound effects unit that adds sound effects. The sound effects include, but are not limited to, environmental sounds, sound effect libraries, and original sound sources. The sound effects unit adds sound effects selected by a video editor to the video. By adding sound effects, the video becomes more immersive and entertaining.

[0032] The system includes a real-time editing unit that performs real-time editing. The real-time editing unit performs editing in real time. Examples of real-time editing include, but are not limited to, editing delay times and the technologies used. For example, the real-time editing unit uses a generation AI to automatically insert captions and add sound effects to breaking news footage. This enables real-time editing and can handle footage with high urgency, such as breaking news.

[0033] The video system includes an analysis unit that analyzes news footage. The analysis unit analyzes the news footage. Examples of the analysis include, but are not limited to, video content analysis, audio analysis, and metadata analysis. The analysis unit analyzes the content of the news footage, for example, and performs appropriate editing based on the content of the video. In this way, analyzing the news footage enables appropriate editing based on the content of the video.

[0034] The system includes a breaking news generation unit that generates captions for breaking news. The breaking news generation unit generates captions for breaking news. Breaking news captions include, for example, text content, display position, and display time, but are not limited to these examples. In the breaking news generation unit, for example, a generation AI automatically generates and displays captions for breaking news video. In this way, by automatically generating captions for breaking news, highly timely information can be provided quickly.

[0035] The learning unit can analyze past editing data, extract a specific editing pattern, and learn it. The learning unit analyzes past editing data, extracts a specific editing pattern, and learns it. Editing patterns include, for example, caption patterns used in specific scenes, the timing of inserting sound effects, the frequency of cuts, and the type of transitions, but are not limited to these examples. For example, the learning unit extracts a caption pattern used in specific scenes from past editing data and learns it. It can also analyze the timing of inserting sound effects from past editing data and learn a pattern. It can also extract a specific editing style (for example, the frequency of cuts or the type of transitions) from past editing data and learn it. In this way, by learning a specific pattern from past editing data, the accuracy of the editing style is improved.

[0036] The learning unit can optimize the timing of learning based on the editor's work time period and frequency. The learning unit optimizes the timing of learning based on the editor's work time period and frequency. Examples of the timing of learning include, but are not limited to, the editor's work time period, frequency, and concentration level. For example, if the editor often works at night, the learning unit can optimize the timing to study at night. Also, if the editor works intensively on weekends, the learning unit can optimize the timing to study on weekends. Furthermore, if the editor works frequently in short periods of time, the learning unit can optimize the timing to study efficiently in a short period of time. This makes it possible to optimize the timing of learning according to the editor's work time period and frequency, allowing for efficient learning.

[0037] The learning unit can learn a region-specific editing style based on the geographical location information of the editor. The learning unit learns a region-specific editing style based on the geographical location information of the editor. Geographical location information includes, but is not limited to, GPS data, IP address, and region-specific data. For example, if the editor is in Japan, the learning unit can learn a Japanese-specific editing style (e.g., font and color of subtitles). Also, if the editor is in the United States, the learning unit can learn an American-specific editing style (e.g., type of sound effects and insertion timing). Furthermore, if the editor is in Europe, the learning unit can learn a European-specific editing style (e.g., type and frequency of transitions). In this way, by learning a region-specific editing style, editing appropriate for the region becomes possible.

[0038] The learning unit can analyze the social media activity of the editor and learn an editing style based on trends. The learning unit analyzes the social media activity of the editor and learns an editing style based on trends. Social media activity includes, but is not limited to, for example, the content of posts, the number of likes, and the number of followers. For example, the learning unit analyzes posts that the editor has received many likes on social media and learns their editing style. The learning unit can also analyze the editing styles of influencers that the editor follows and learn editing styles based on trends. Furthermore, the learning unit can analyze and learn editing styles that are popular in social media groups that the editor participates in. This makes it possible to learn an editing style based on social media trends, allowing editing that is in line with the latest trends.

[0039] The input unit can evaluate the quality of the raw video in real time and select the optimal input method. The input unit evaluates the quality of the raw video in real time and selects the optimal input method. The quality of the raw video includes, for example, resolution, frame rate, color tone, etc., but is not limited to these examples. The input unit can, for example, evaluate the resolution of the raw video in real time and select a high-quality input method if the resolution is high. The input unit can also evaluate the brightness of the raw video in real time and select a standard input method if the brightness is appropriate. Furthermore, the input unit can evaluate the audio quality of the raw video in real time and select a high-quality input method if the audio is clear. This makes it possible to select the optimal input method according to the quality of the raw video, allowing input while maintaining the quality of the video.

[0040] The input unit can automatically filter the video based on its content when it is input. The input unit automatically filters the video based on its content when it is input. Filtering includes, for example, a method for detecting inappropriate content, a filtering algorithm, and the like, but is not limited to these examples. For example, if the video contains inappropriate content, the input unit can automatically filter the video before inputting it. Furthermore, if the video contains a specific keyword, the input unit can automatically filter the video before inputting it. Furthermore, if the video contains a specific scene (for example, a violent scene), the input unit can automatically filter the video before inputting it. This enables automatic filtering based on the content of the video, making it possible to prevent inappropriate content from being input.

[0041] The input unit can prioritize inputting highly relevant videos based on the poster's geographical location information. The input unit prioritizes inputting highly relevant videos based on the poster's geographical location information. Geographical location information includes, but is not limited to, GPS data, IP address, and region-specific data. For example, if the poster is in a specific region, the input unit prioritizes inputting videos related to that region. Also, if the poster is traveling, the input unit can prioritize inputting videos related to the travel destination. Furthermore, if the poster is at an event venue, the input unit can prioritize inputting videos related to the event. This makes it possible to input highly relevant videos based on geographical location information, allowing videos appropriate for the region to be input.

[0042] The input unit can analyze the poster's social media activity and input related videos. The input unit analyzes the poster's social media activity and input related videos. Social media activity includes, for example, the content of the post, the number of likes, the number of followers, etc., but is not limited to these examples. The input unit, for example, preferentially inputs videos that the poster has shared on social media. It can also preferentially input videos that the poster has "liked" on social media. It can also preferentially input videos of accounts that the poster follows on social media. This makes it possible to input related videos based on social media activity, and to input videos that correspond to trends.

[0043] The editing department can adjust the level of editing detail based on the importance of the video during editing. The editing department adjusts the level of editing detail based on the importance of the video during editing. The importance of the video includes, but is not limited to, for example, the level of viewer interest, the content of the video, and the importance of the scene. For example, the editing department can perform detailed editing on important scenes. Also, the editing department can perform simplified editing on less important scenes. Furthermore, special effects can be added to scenes with high importance. This makes it possible to adjust the level of editing detail according to the importance of the video, and to perform appropriate editing on important scenes.

[0044] The editing department can apply different editing algorithms depending on the category of the video during editing. The editing department can apply different editing algorithms depending on the category of the video during editing. Video categories include, but are not limited to, news, entertainment, and education. For example, the editing department can apply a fast and accurate editing algorithm to news videos. Also, for entertainment videos, the editing department can apply a visually appealing editing algorithm. Furthermore, for educational videos, the editing department can apply an editing algorithm that emphasizes ease of understanding. This makes it possible to apply the optimal editing algorithm depending on the category of the video, allowing editing appropriate to the category.

[0045] The editing department can determine the editing priority based on the time when the video was shot during editing. The editing department can determine the editing priority based on the time when the video was shot during editing. The shooting time includes, but is not limited to, for example, a timestamp, calendar data, event information, etc. The editing department, for example, prioritizes editing the most recent video. It can also prioritize editing video of a specific event. It can also prioritize editing video related to a season. This makes it possible to determine the editing priority based on the time when the video was shot, and it is possible to prioritize editing the most recent video or video of an important event.

[0046] The editing department can adjust the editing order based on the relevance of the images during editing. The editing department can adjust the editing order based on the relevance of the images during editing. The relevance of the images includes, for example, the flow of the story, the continuity of the scenes, the degree of consistency of the content, etc., but is not limited to these examples. For example, the editing department edits highly relevant scenes consecutively. It can also edit less relevant scenes later. Furthermore, it can adjust the editing order taking into account the storyline of the images. This makes it possible to adjust the editing order based on the relevance of the images, allowing for editing with a storyline.

[0047] The output unit can evaluate the quality of the video at the time of output and select the optimal output method. The output unit evaluates the quality of the video at the time of output and selects the optimal output method. Video quality includes, for example, resolution, frame rate, color tone, etc., but is not limited to these examples. For example, the output unit selects a high-quality output method for high-resolution video. Also, for standard-resolution video, the output unit can select a standard output method. Furthermore, for low-resolution video, the output unit can select a lightweight output method. This makes it possible to select the optimal output method according to the video quality, and output while maintaining the video quality.

[0048] The output unit can apply different output formats depending on the category of the video at the time of output. The output unit can apply different output formats depending on the category of the video at the time of output. Examples of output formats include, but are not limited to, file formats, resolutions, and frame rates. For example, in the case of news video, the output unit can apply a format that allows for quick delivery. In addition, in the case of entertainment video, the output unit can apply a visually appealing format. Furthermore, in the case of educational video, a format that emphasizes ease of understanding can be applied. This makes it possible to apply the optimal output format depending on the category of the video, and to perform output appropriate for the category.

[0049] The output unit can adjust the output format based on the location where the video was shot at the time of output. The output unit can adjust the output format based on the location where the video was shot at the time of output. The shooting location includes, but is not limited to, GPS data, IP address, and region-specific data. For example, in the case of video shot in a specific region, the output unit outputs the video in a format appropriate for that region. In addition, in the case of video shot at a travel destination, the output unit can output the video in a format that makes use of the characteristics of the travel destination. Furthermore, in the case of video shot at an event venue, the output can be in a format related to the event. This makes it possible to adjust the output format according to the location where the video was shot, and output the video in a format appropriate for the region.

[0050] The output unit can adjust the output order based on the relevance of the images at the time of output. The output unit can adjust the output order based on the relevance of the images at the time of output. The relevance of the images includes, for example, the flow of the story, the continuity of the scenes, the degree of similarity of the contents, etc., but is not limited to these examples. The output unit, for example, outputs highly related scenes consecutively. It can also output less related scenes later. Furthermore, it can adjust the output order taking into account the storyline of the images. This makes it possible to adjust the output order based on the relevance of the images, allowing for output with a storyline.

[0051] The setting unit can optimize the display timing of the telop based on the content of the video. The setting unit optimizes the display timing of the telop based on the content of the video. The display timing includes, for example, the timing of scene changes, the timing of important information, etc., but is not limited to these examples. The setting unit, for example, optimizes the timing of displaying the telop in important scenes. It can also optimize the timing of displaying the telop in moving scenes. It can also optimize the timing of displaying the telop in comedic scenes. This makes it possible to optimize the display timing of the telop based on the content of the video, and the telop is displayed at a more appropriate timing.

[0052] The setting unit can customize the caption style according to the video category. The setting unit customizes the caption style according to the video category. Caption styles include, for example, font, color, size, background, etc., but are not limited to these examples. For example, the setting unit uses a simple, highly visible caption style for news video. Also, a visually appealing caption style can be used for entertainment video. Furthermore, a caption style that emphasizes ease of understanding can be used for educational video. This makes it possible to customize the caption style according to the video category, and caption appropriate for the category is displayed.

[0053] The setting unit can optimize the display position of the telop based on the composition of the video. The setting unit optimizes the display position of the telop based on the composition of the video. The display position includes, for example, the four corners, the center, the top, bottom, left, and right positions of the screen, but is not limited to these examples. The setting unit, for example, optimizes the display position of the telop so as not to obscure important parts of the video. The setting unit can also optimize the display position of the telop to improve the visibility of the video. Furthermore, the display position of the telop can be optimized taking into account the balance of the video. This makes it possible to optimize the display position of the telop based on the composition of the video, and highly visible telop is displayed.

[0054] The setting unit can automatically generate the content of the caption based on the related information of the video. The setting unit automatically generates the content of the caption based on the related information of the video. The related information includes, for example, metadata, tag information, related text, etc., but is not limited to these examples. The setting unit automatically generates related captions based on, for example, the content of the video. It can also automatically generate appropriate captions to match the scenes in the video. Furthermore, it can automatically generate the content of the caption based on the story of the video. This makes it possible to automatically generate the content of the caption based on the related information of the video, and more appropriate captions can be displayed.

[0055] The sound effects section can optimize the timing of inserting sound effects based on the content of the video. The sound effects section optimizes the timing of inserting sound effects based on the content of the video. Insertion timing includes, but is not limited to, timing of scene changes and important information. The sound effects section, for example, optimizes the timing of inserting sound effects in important scenes. It can also optimize the timing of inserting sound effects in moving scenes. It can also optimize the timing of inserting sound effects in comedy scenes. This makes it possible to optimize the timing of inserting sound effects based on the content of the video, and sound effects are added at more appropriate timing.

[0056] The sound effects section can customize the type of sound effects according to the video category. The sound effects section customizes the type of sound effects according to the video category. The types of sound effects include, but are not limited to, environmental sounds, sound effect libraries, and original sound sources. For example, for news videos, the sound effects section uses simple, highly visible sound effects. For entertainment videos, visually appealing sound effects can also be used. Furthermore, for educational videos, sound effects that emphasize ease of understanding can also be used. This makes it possible to customize the type of sound effects according to the video category, and sound effects appropriate for the category are added.

[0057] The sound effects section can optimize the insertion position of a sound effect based on the composition of the video. The sound effects section optimizes the insertion position of a sound effect based on the composition of the video. Insertion positions include, but are not limited to, the four corners, center, top, bottom, left, and right positions of the screen. The sound effects section can optimize the insertion position of a sound effect, for example, so as not to obscure important parts of the video. The sound effects section can also optimize the insertion position of a sound effect to improve the visibility of the video. Furthermore, the sound effects section can optimize the insertion position of a sound effect based on the balance of the video. This makes it possible to optimize the insertion position of a sound effect based on the composition of the video, and to add sound effects with high visibility.

[0058] The sound effect unit can automatically generate the content of the sound effect based on related information of the video. The sound effect unit automatically generates the content of the sound effect based on related information of the video. Related information includes, for example, metadata, tag information, related text, etc., but is not limited to these examples. The sound effect unit automatically generates related sound effects based on, for example, the content of the video. It can also automatically generate appropriate sound effects to match the scenes in the video. Furthermore, it can automatically generate the content of the sound effect based on the story of the video. This makes it possible to automatically generate the content of the sound effect based on related information of the video, and more appropriate sound effects can be added.

[0059] The real-time editing unit can evaluate the quality of video during real-time editing and select the optimal editing method. The real-time editing unit evaluates the quality of video during real-time editing and selects the optimal editing method. Video quality includes, for example, resolution, frame rate, color tone, etc., but is not limited to these examples. For example, the real-time editing unit selects a high-quality editing method for high-resolution video. Also, for standard-resolution video, it can select a standard editing method. Furthermore, for low-resolution video, it can select a lightweight editing method. This makes it possible to select the optimal real-time editing method according to the video quality, and perform real-time editing while maintaining the video quality.

[0060] The real-time editing unit can apply different editing algorithms depending on the category of the video during real-time editing. The real-time editing unit applies different editing algorithms depending on the category of the video during real-time editing. Video categories include, but are not limited to, news, entertainment, and education. For example, the real-time editing unit applies a fast and accurate editing algorithm to news videos. Also, a visually appealing editing algorithm can be applied to entertainment videos. Furthermore, an editing algorithm that emphasizes ease of understanding can be applied to educational videos. This makes it possible to apply the optimal real-time editing algorithm depending on the category of the video, allowing for real-time editing appropriate for the category.

[0061] The real-time editing unit can adjust the editing method based on the shooting location of the video during real-time editing. The real-time editing unit can adjust the editing method based on the shooting location of the video during real-time editing. The shooting location includes, for example, but is not limited to, GPS data, IP address, and region-specific data. For example, in the case of video shot in a specific region, the real-time editing unit can select an editing method appropriate for that region. In addition, in the case of video shot at a travel destination, the real-time editing unit can select an editing method that makes use of the characteristics of the travel destination. Furthermore, in the case of video shot at an event venue, an editing method related to the event can be selected. This makes it possible to adjust the real-time editing method according to the shooting location of the video, allowing real-time editing to be performed that is appropriate for the region.

[0062] The real-time editing unit can adjust the editing order based on the relevance of the images during real-time editing. The real-time editing unit adjusts the editing order based on the relevance of the images during real-time editing. The relevance of the images includes, for example, the flow of the story, the continuity of the scenes, and the degree of consistency of the content, but is not limited to these examples. The real-time editing unit, for example, edits highly relevant scenes consecutively. It can also edit less relevant scenes later. Furthermore, it can adjust the editing order taking into account the storyline of the images. This makes it possible to adjust the real-time editing order based on the relevance of the images, allowing for real-time editing with a storyline.

[0063] The analysis unit can analyze the content of the news video in real time and select the optimal analysis method. The analysis unit analyzes the content of the news video in real time and selects the optimal analysis method. The content of the news video includes, but is not limited to, video content analysis, audio analysis, and metadata analysis. For example, the analysis unit analyzes important parts of the news video in real time and selects the optimal analysis method. It can also analyze moving parts of the news video in real time and select the optimal analysis method. It can also analyze comedic parts of the news video in real time and select the optimal analysis method. This makes it possible to select the optimal analysis method based on the content of the news video, allowing for appropriate analysis according to the content of the video.

[0064] The analysis unit can apply different analysis algorithms depending on the category of the news video. The analysis unit applies different analysis algorithms depending on the category of the news video. Categories of news videos include, but are not limited to, politics, economics, sports, etc. For example, the analysis unit applies a fast and accurate analysis algorithm to news videos. Furthermore, for entertainment videos, it can apply a visually appealing analysis algorithm. Furthermore, for educational videos, it can apply an analysis algorithm that emphasizes ease of understanding. This makes it possible to apply the optimal analysis algorithm depending on the category of the news video, allowing for analysis appropriate to the category.

[0065] The analysis unit can adjust the analysis method based on the shooting location of the news footage. The analysis unit adjusts the analysis method based on the shooting location of the news footage. The shooting location includes, but is not limited to, GPS data, IP address, and region-specific data. For example, in the case of news footage shot in a specific region, the analysis unit selects an analysis method appropriate for that region. In addition, in the case of news footage shot at a travel destination, the analysis unit can select an analysis method that takes advantage of the characteristics of the travel destination. Furthermore, in the case of news footage shot at an event venue, the analysis unit can select an analysis method related to the event. This makes it possible to adjust the analysis method according to the shooting location of the news footage, allowing for analysis appropriate for the region.

[0066] The analysis unit can adjust the order of analysis based on related information of the news video. The analysis unit adjusts the order of analysis based on related information of the news video. Related information includes, for example, metadata, tag information, related text, etc., but is not limited to these examples. The analysis unit, for example, analyzes highly related news videos consecutively. It can also analyze less related news videos later. Furthermore, it can adjust the order of analysis taking into account the storyline of the news video. This makes it possible to adjust the order of analysis based on related information of the news video, allowing for story-like analysis.

[0067] The breaking news generation unit can optimize the timing of displaying breaking news captions based on the content of the news video. The breaking news generation unit optimizes the timing of displaying breaking news captions based on the content of the news video. Display timing includes, for example, scene changes, timing of important information, etc., but is not limited to these examples. The breaking news generation unit, for example, optimizes the timing of displaying breaking news captions for important news video. It can also optimize the timing of displaying breaking news captions for moving news video. It can also optimize the timing of displaying breaking news captions for comedic news video. This makes it possible to optimize the display timing of breaking news captions based on the content of the news video, and breaking news captions are displayed at more appropriate timing.

[0068] The breaking news generation unit can customize the style of the breaking news caption according to the news category. The breaking news generation unit customizes the style of the breaking news caption according to the news category. Examples of the style of the breaking news caption include, but are not limited to, font, color, size, background, etc. For example, the breaking news generation unit uses a simple, highly visible breaking news caption style for news video. Also, for entertainment news video, a visually appealing breaking news caption style can be used. Furthermore, for educational news video, a breaking news caption style that emphasizes ease of understanding can be used. This makes it possible to customize the style of the breaking news caption according to the news category, and breaking news captions appropriate for the category are displayed.

[0069] The breaking news generation unit can optimize the display position of the breaking news caption based on the composition of the news video. The breaking news generation unit optimizes the display position of the breaking news caption based on the composition of the news video. Examples of display positions include, but are not limited to, the four corners, center, top, bottom, left, and right positions of the screen. The breaking news generation unit, for example, optimizes the display position of the breaking news caption so as not to obscure important parts of the news video. The display position of the breaking news caption can also be optimized to improve the visibility of the news video. Furthermore, the display position of the breaking news caption can also be optimized taking into account the balance of the news video. This makes it possible to optimize the display position of the breaking news caption based on the composition of the news video, and breaking news captions with high visibility are displayed.

[0070] The breaking news generation unit can automatically generate the content of the breaking news caption based on related information about the news. The breaking news generation unit automatically generates the content of the breaking news caption based on related information about the news. Related information includes, for example, metadata, tag information, related text, etc., but is not limited to these examples. The breaking news generation unit automatically generates related breaking news captions based on, for example, the content of the news. It can also automatically generate appropriate breaking news captions to match the news scenes. Furthermore, it can automatically generate the content of the breaking news caption based on the news story. This makes it possible to automatically generate the content of the breaking news caption based on related information about the news, and more appropriate breaking news captions can be displayed.

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

[0072] The learning unit can learn not only from the video editor's past editing data but also from publicly available data from other video editors. For example, a video editor can adopt a new editing style by learning from the data of other editors with a specific style. The learning unit can also learn from editing data of different genres and automatically apply an editing style appropriate to the genre. Furthermore, the learning unit can receive feedback from video editors and update the learning data based on that feedback. This allows the learning unit to learn a wider variety of editing styles and perform editing that meets the needs of the video editor.

[0073] The setting unit can set not only the font and color of the caption, but also the animation effect of the caption. For example, it can set the effect of the caption fading in or sliding in. The setting unit can also customize the display time and display position of the caption for each scene. Furthermore, the setting unit can automatically translate the content of the caption and display it in multiple languages. This allows the setting unit to create visually appealing captions and help viewers understand them better.

[0074] The sound effects department can not only add sound effects, but also adjust the volume and pitch of the sound effects for each scene. For example, the volume can be increased in tense scenes and decreased in relaxed scenes. The sound effects department can also add effects such as echo and reverb to sound effects. Furthermore, the sound effects department can fine-tune the timing of sound effects to match the movement of the images. This allows the sound effects department to provide sound effects that match the atmosphere of the images, enhancing the viewer's sense of immersion.

[0075] The real-time editing department can not only edit in real time, but also apply effects in real time. For example, it can perform color correction and noise removal in real time on breaking news footage. The real-time editing department can also switch between multiple camera feeds in real time. Furthermore, the real-time editing department can receive real-time feedback from viewers and adjust the editing content based on that feedback. This allows the real-time editing department to provide higher quality footage and improve viewer satisfaction.

[0076] The analysis unit can not only analyze news footage, but also recognize people and objects within the footage. For example, it can recognize a specific person within news footage and display information related to that person. The analysis unit can also recognize objects within the footage and provide data related to the object. Furthermore, the analysis unit can analyze audio within the footage and perform appropriate editing based on the content of the audio. This allows the analysis unit to perform advanced analysis based on the content of the video, enabling more accurate editing.

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

[0078] Step 1: The learning unit learns the video editor's style. A video editor's style includes the tempo of editing, the effects used, the frequency of cuts, etc. The learning unit uses past editing data to learn how to insert subtitles at specific times and when to use specific sound effects. For example, the learning unit analyzes past editing data to extract the editor's style. Step 2: The input unit receives raw video footage from the video uploader. The raw video footage includes information such as resolution, frame rate, and file format. The input unit inputs the raw video footage captured by the video uploader into the system. Step 3: The editing team edits the video based on the style learned by the learning team. This includes cuts, transitions, and applying effects. Based on the learned style, the editing team inserts captions in specific scenes and adds sound effects at specific times. Step 4: The output unit outputs the edited video. The output includes the file format, resolution, frame rate, etc. The output unit outputs the edited video in the specified file format.

[0079] (Example 2) A video editing system according to an embodiment of the present invention utilizes a generation AI to quickly complete video editing. This video editing system trains the generation AI to learn a video editor's editing style, such as captions and sound effects. A video uploader shoots raw footage and inputs it into the generation AI. The system automatically inserts captions and sound effects based on the learned editing style and outputs the edited video. This system allows video uploaders to significantly reduce the time it takes to edit. This system is also applicable to real-time video editing, such as for television news flashes. For example, the generation AI can automatically insert captions and sound effects into breaking news footage. This significantly improves the efficiency of video editing and reduces the workload of video uploaders and television stations. For example, a video editor can train the generation AI to learn their own editing style, such as how to insert captions at specific times and when to use specific sound effects. This training is performed using past editing data. Next, the video uploader shoots raw footage. This raw footage is input into the generation AI. The generation AI automatically inserts captions and sound effects based on the learned editing style. For example, it is possible to insert captions in specific scenes and add sound effects at specific times. Videos edited by the generative AI are ready to post immediately, allowing video uploaders to significantly reduce the time required for editing. This system can also be applied to real-time video editing of things like television news flashes. For example, the generative AI can automatically insert captions and add sound effects to breaking news footage. This system significantly improves the efficiency of video editing and reduces the workload of video uploaders and television stations. As a result, the video editing system automatically edits videos by requiring only the video uploader to input raw footage, significantly improving the efficiency of editing work.

[0080] A video editing system according to an embodiment includes a learning unit, an input unit, an editing unit, and an output unit. The learning unit learns the style of a video editor. Examples of the video editor's style include, but are not limited to, the editing tempo, the effects used, and the frequency of cuts. For example, the learning unit uses past editing data to learn how to insert captions at specific times and when to use specific sound effects. For example, the learning unit analyzes past editing data to extract the editor's style. The input unit receives raw video from a video uploader. Examples of the raw video include, but are not limited to, resolution, frame rate, and file format. For example, the input unit inputs raw video captured by the video uploader into the system. The editing unit performs editing based on the style learned by the learning unit. Examples of editing include, but are not limited to, cuts, transitions, and effect application methods. For example, the editing unit inserts captions in specific scenes and adds sound effects at specific times based on the learned style. The output unit outputs the edited video. The output may include, but is not limited to, a file format, a resolution, a frame rate, etc. The output unit outputs the edited video in a specified file format, for example. As a result, the video editing system according to the embodiment automatically performs editing by simply inputting raw video footage by the video uploader, thereby significantly improving the efficiency of editing work.

[0081] The video editing apparatus includes a setting unit that sets the font or color of the caption. The setting unit sets the font and color of the caption. Examples of fonts include, but are not limited to, sans serif, serif, and handwritten style. The setting unit applies, for example, a font selected by a video editor to the caption. Examples of colors include, but are not limited to, hue, saturation, and brightness. The setting unit applies, for example, a color selected by the video editor to the caption. In this way, by setting the font and color of the caption, the visibility and design of the video are improved.

[0082] The video processing device includes a sound effects unit that adds sound effects. The sound effects include, but are not limited to, environmental sounds, sound effect libraries, and original sound sources. The sound effects unit adds sound effects selected by a video editor to the video. By adding sound effects, the video becomes more immersive and entertaining.

[0083] The system includes a real-time editing unit that performs real-time editing. The real-time editing unit performs editing in real time. Examples of real-time editing include, but are not limited to, editing delay times and the technologies used. For example, the real-time editing unit uses a generation AI to automatically insert captions and add sound effects to breaking news footage. This enables real-time editing and can handle footage with high urgency, such as breaking news.

[0084] The video system includes an analysis unit that analyzes news footage. The analysis unit analyzes the news footage. Examples of the analysis include, but are not limited to, video content analysis, audio analysis, and metadata analysis. The analysis unit analyzes the content of the news footage, for example, and performs appropriate editing based on the content of the video. In this way, analyzing the news footage enables appropriate editing based on the content of the video.

[0085] The system includes a breaking news generation unit that generates captions for breaking news. The breaking news generation unit generates captions for breaking news. Breaking news captions include, for example, text content, display position, and display time, but are not limited to these examples. In the breaking news generation unit, for example, a generation AI automatically generates and displays captions for breaking news video. In this way, by automatically generating captions for breaking news, highly timely information can be provided quickly.

[0086] The learning unit can analyze the emotions of the video editor and select learning data based on the analyzed emotions. The learning unit can analyze the emotions of the video editor and select learning data based on the analyzed emotions. Emotions include, but are not limited to, relaxation, stress, and excitement. For example, if the video editor is relaxed, the learning unit can preferentially select past successful editing data as learning data. Also, if the video editor is stressed, the learning unit can select simple and effective editing data as learning data. Furthermore, if the video editor is excited, creative editing data can be selected as learning data. This makes it possible to select learning data according to the emotions of the video editor, allowing for learning of a more appropriate editing style.

[0087] The learning unit can analyze past editing data, extract a specific editing pattern, and learn it. The learning unit analyzes past editing data, extracts a specific editing pattern, and learns it. Editing patterns include, for example, caption patterns used in specific scenes, the timing of inserting sound effects, the frequency of cuts, and the type of transitions, but are not limited to these examples. For example, the learning unit extracts a caption pattern used in specific scenes from past editing data and learns it. It can also analyze the timing of inserting sound effects from past editing data and learn a pattern. It can also extract a specific editing style (for example, the frequency of cuts or the type of transitions) from past editing data and learn it. In this way, by learning a specific pattern from past editing data, the accuracy of the editing style is improved.

[0088] The learning unit can optimize the timing of learning based on the editor's work time period and frequency. The learning unit optimizes the timing of learning based on the editor's work time period and frequency. Examples of the timing of learning include, but are not limited to, the editor's work time period, frequency, and concentration level. For example, if the editor often works at night, the learning unit can optimize the timing to study at night. Also, if the editor works intensively on weekends, the learning unit can optimize the timing to study on weekends. Furthermore, if the editor works frequently in short periods of time, the learning unit can optimize the timing to study efficiently in a short period of time. This makes it possible to optimize the timing of learning according to the editor's work time period and frequency, allowing for efficient learning.

[0089] The learning unit can analyze the emotions of the video editor and determine learning priorities based on the analyzed emotions. The learning unit can analyze the emotions of the video editor and determine learning priorities based on the analyzed emotions. Learning priorities include, but are not limited to, for example, the intensity of emotions and the importance of editing. For example, if the video editor is relaxed, the learning unit can prioritize learning a complex editing style. Also, if the video editor is stressed, the learning unit can prioritize learning a simple editing style. Furthermore, if the video editor is excited, the learning unit can prioritize learning a creative editing style. This makes it possible to determine learning priorities according to the emotions of the video editor, allowing for efficient learning.

[0090] The learning unit can learn a region-specific editing style based on the geographical location information of the editor. The learning unit learns a region-specific editing style based on the geographical location information of the editor. Geographical location information includes, but is not limited to, GPS data, IP address, and region-specific data. For example, if the editor is in Japan, the learning unit can learn a Japanese-specific editing style (e.g., font and color of subtitles). Also, if the editor is in the United States, the learning unit can learn an American-specific editing style (e.g., type of sound effects and insertion timing). Furthermore, if the editor is in Europe, the learning unit can learn a European-specific editing style (e.g., type and frequency of transitions). In this way, by learning a region-specific editing style, editing appropriate for the region becomes possible.

[0091] The learning unit can analyze the social media activity of the editor and learn an editing style based on trends. The learning unit analyzes the social media activity of the editor and learns an editing style based on trends. Social media activity includes, but is not limited to, for example, the content of posts, the number of likes, and the number of followers. For example, the learning unit analyzes posts that the editor has received many likes on social media and learns their editing style. The learning unit can also analyze the editing styles of influencers that the editor follows and learn editing styles based on trends. Furthermore, the learning unit can analyze and learn editing styles that are popular in social media groups that the editor participates in. This makes it possible to learn an editing style based on social media trends, allowing editing that is in line with the latest trends.

[0092] The input unit can analyze the emotions of the video poster and adjust the timing of the input based on the analyzed emotions. The input unit can analyze the emotions of the video poster and adjust the timing of the input based on the analyzed emotions. The timing of the input includes, for example, changes in emotions, the content of the video, the poster's intentions, etc., but is not limited to these examples. For example, if the video poster is relaxed, the input unit can encourage the video poster to input at a leisurely pace. Also, if the video poster is in a hurry, the input unit can encourage the video poster to input quickly. Furthermore, if the video poster is excited, the input unit can encourage the video poster to input at a tempo that matches the emotion. This makes it possible to adjust the input timing according to the emotions of the video poster, allowing for more appropriate input.

[0093] The input unit can evaluate the quality of the raw video in real time and select the optimal input method. The input unit evaluates the quality of the raw video in real time and selects the optimal input method. The quality of the raw video includes, for example, resolution, frame rate, color tone, etc., but is not limited to these examples. The input unit can, for example, evaluate the resolution of the raw video in real time and select a high-quality input method if the resolution is high. The input unit can also evaluate the brightness of the raw video in real time and select a standard input method if the brightness is appropriate. Furthermore, the input unit can evaluate the audio quality of the raw video in real time and select a high-quality input method if the audio is clear. This makes it possible to select the optimal input method according to the quality of the raw video, allowing input while maintaining the quality of the video.

[0094] The input unit can automatically filter the video based on its content when it is input. The input unit automatically filters the video based on its content when it is input. Filtering includes, for example, a method for detecting inappropriate content, a filtering algorithm, and the like, but is not limited to these examples. For example, if the video contains inappropriate content, the input unit can automatically filter the video before inputting it. Furthermore, if the video contains a specific keyword, the input unit can automatically filter the video before inputting it. Furthermore, if the video contains a specific scene (for example, a violent scene), the input unit can automatically filter the video before inputting it. This enables automatic filtering based on the content of the video, making it possible to prevent inappropriate content from being input.

[0095] The input unit can analyze the emotions of the video poster and determine the priority of the videos to be input based on the analyzed emotions. The input unit can analyze the emotions of the video poster and determine the priority of the videos to be input based on the analyzed emotions. The priority of the videos includes, for example, the intensity of the emotion and the importance of the video, but is not limited to these examples. For example, if the video poster is relaxed, the input unit can prioritize input of relaxing scenes. Also, if the video poster is in a hurry, the input unit can prioritize input of important scenes. Furthermore, if the video poster is excited, the input unit can prioritize input of scenes that match the emotion. This makes it possible to determine the priority of videos according to the emotions of the video poster, allowing for more appropriate video input.

[0096] The input unit can prioritize inputting highly relevant videos based on the poster's geographical location information. The input unit prioritizes inputting highly relevant videos based on the poster's geographical location information. Geographical location information includes, but is not limited to, GPS data, IP address, and region-specific data. For example, if the poster is in a specific region, the input unit prioritizes inputting videos related to that region. Also, if the poster is traveling, the input unit can prioritize inputting videos related to the travel destination. Furthermore, if the poster is at an event venue, the input unit can prioritize inputting videos related to the event. This makes it possible to input highly relevant videos based on geographical location information, allowing videos appropriate for the region to be input.

[0097] The input unit can analyze the poster's social media activity and input related videos. The input unit analyzes the poster's social media activity and input related videos. Social media activity includes, for example, the content of the post, the number of likes, the number of followers, etc., but is not limited to these examples. The input unit, for example, preferentially inputs videos that the poster has shared on social media. It can also preferentially input videos that the poster has "liked" on social media. It can also preferentially input videos of accounts that the poster follows on social media. This makes it possible to input related videos based on social media activity, and to input videos that correspond to trends.

[0098] The editing department can analyze the emotions of the video poster and adjust the editing expression method based on the analyzed emotions. The editing department can analyze the emotions of the video poster and adjust the editing expression method based on the analyzed emotions. Editing expression methods include, but are not limited to, the frequency of cuts, the type of effect, and the transition method, for example. For example, if the video poster is relaxed, the editing department can edit using a calm expression method. Also, if the video poster is in a hurry, the editing department can edit using a quick and concise expression method. Furthermore, if the video poster is excited, the editing department can edit using a visually stimulating expression method. This makes it possible to adjust the editing expression method according to the emotions of the video poster, resulting in more appropriate editing.

[0099] The editing department can adjust the level of editing detail based on the importance of the video during editing. The editing department adjusts the level of editing detail based on the importance of the video during editing. The importance of the video includes, but is not limited to, for example, the level of viewer interest, the content of the video, and the importance of the scene. For example, the editing department can perform detailed editing on important scenes. Also, the editing department can perform simplified editing on less important scenes. Furthermore, special effects can be added to scenes with high importance. This makes it possible to adjust the level of editing detail according to the importance of the video, and to perform appropriate editing on important scenes.

[0100] The editing department can apply different editing algorithms depending on the category of the video during editing. The editing department can apply different editing algorithms depending on the category of the video during editing. Video categories include, but are not limited to, news, entertainment, and education. For example, the editing department can apply a fast and accurate editing algorithm to news videos. Also, for entertainment videos, the editing department can apply a visually appealing editing algorithm. Furthermore, for educational videos, the editing department can apply an editing algorithm that emphasizes ease of understanding. This makes it possible to apply the optimal editing algorithm depending on the category of the video, allowing editing appropriate to the category.

[0101] The editing department can analyze the emotions of the video poster and adjust the length of the edited video based on the analyzed emotions. The editing department can analyze the emotions of the video poster and adjust the length of the edited video based on the analyzed emotions. The length of the edited video includes, but is not limited to, the importance of the scene, the level of interest of the viewer, and the content of the video. For example, if the video poster is relaxed, the editing department can edit the video to be longer. Also, if the video poster is in a hurry, the editing department can edit the video to be shorter. Furthermore, if the video poster is excited, the editing department can edit the video to a length that matches the emotion. This makes it possible to adjust the length of the edited video according to the emotions of the video poster, resulting in more appropriate editing.

[0102] The editing department can determine the editing priority based on the time when the video was shot during editing. The editing department can determine the editing priority based on the time when the video was shot during editing. The shooting time includes, but is not limited to, for example, a timestamp, calendar data, event information, etc. The editing department, for example, prioritizes editing the most recent video. It can also prioritize editing video of a specific event. It can also prioritize editing video related to a season. This makes it possible to determine the editing priority based on the time when the video was shot, and it is possible to prioritize editing the most recent video or video of an important event.

[0103] The editing department can adjust the editing order based on the relevance of the images during editing. The editing department can adjust the editing order based on the relevance of the images during editing. The relevance of the images includes, for example, the flow of the story, the continuity of the scenes, the degree of consistency of the content, etc., but is not limited to these examples. For example, the editing department edits highly relevant scenes consecutively. It can also edit less relevant scenes later. Furthermore, it can adjust the editing order taking into account the storyline of the images. This makes it possible to adjust the editing order based on the relevance of the images, allowing for editing with a storyline.

[0104] The output unit can analyze the emotions of the video poster and adjust the output format based on the analyzed emotions. The output unit can analyze the emotions of the video poster and adjust the output format based on the analyzed emotions. Examples of output formats include, but are not limited to, file formats, resolutions, and frame rates. For example, if the video poster is relaxed, the output unit can output in a relaxed format. Also, if the video poster is in a hurry, the output unit can output in a quick format. Furthermore, if the video poster is excited, the output unit can output in a visually stimulating format. This makes it possible to adjust the output format according to the emotions of the video poster, and output in a more appropriate format.

[0105] The output unit can evaluate the quality of the video at the time of output and select the optimal output method. The output unit evaluates the quality of the video at the time of output and selects the optimal output method. Video quality includes, for example, resolution, frame rate, color tone, etc., but is not limited to these examples. For example, the output unit selects a high-quality output method for high-resolution video. Also, for standard-resolution video, the output unit can select a standard output method. Furthermore, for low-resolution video, the output unit can select a lightweight output method. This makes it possible to select the optimal output method according to the video quality, and output while maintaining the video quality.

[0106] The output unit can apply different output formats depending on the category of the video at the time of output. The output unit can apply different output formats depending on the category of the video at the time of output. Examples of output formats include, but are not limited to, file formats, resolutions, and frame rates. For example, in the case of news video, the output unit can apply a format that allows for quick delivery. In addition, in the case of entertainment video, the output unit can apply a visually appealing format. Furthermore, in the case of educational video, a format that emphasizes ease of understanding can be applied. This makes it possible to apply the optimal output format depending on the category of the video, and to perform output appropriate for the category.

[0107] The output unit can analyze the emotions of the video poster and determine output priorities based on the analyzed emotions. The output unit can analyze the emotions of the video poster and determine output priorities based on the analyzed emotions. Output priorities include, but are not limited to, for example, intensity of emotions and importance of videos. For example, if the video poster is relaxed, the output unit can prioritize output of relaxed scenes. Also, if the video poster is in a hurry, the output unit can prioritize output of important scenes. Furthermore, if the video poster is excited, the output unit can prioritize output of scenes that match the emotion. This makes it possible to determine output priorities according to the emotions of the video poster, allowing more appropriate scenes to be output.

[0108] The output unit can adjust the output format based on the location where the video was shot at the time of output. The output unit can adjust the output format based on the location where the video was shot at the time of output. The shooting location includes, but is not limited to, GPS data, IP address, and region-specific data. For example, in the case of video shot in a specific region, the output unit outputs the video in a format appropriate for that region. In addition, in the case of video shot at a travel destination, the output unit can output the video in a format that makes use of the characteristics of the travel destination. Furthermore, in the case of video shot at an event venue, the output can be in a format related to the event. This makes it possible to adjust the output format according to the location where the video was shot, and output the video in a format appropriate for the region.

[0109] The output unit can adjust the output order based on the relevance of the images at the time of output. The output unit can adjust the output order based on the relevance of the images at the time of output. The relevance of the images includes, for example, the flow of the story, the continuity of the scenes, the degree of similarity of the contents, etc., but is not limited to these examples. The output unit, for example, outputs highly related scenes consecutively. It can also output less related scenes later. Furthermore, it can adjust the output order taking into account the storyline of the images. This makes it possible to adjust the output order based on the relevance of the images, allowing for output with a storyline.

[0110] The setting unit can analyze the emotions of the video poster and adjust the font or color of the caption based on the analyzed emotions. The setting unit can analyze the emotions of the video poster and adjust the font or color of the caption based on the analyzed emotions. Fonts include, but are not limited to, sans serif, serif, and handwritten styles, for example. For example, if the video poster is relaxed, the setting unit can use a font with a calm color. Also, if the video poster is in a hurry, the setting unit can use a font with high visibility. Furthermore, if the video poster is excited, the setting unit can use a font with a vivid color. This makes it possible to adjust the font and color of the caption according to the emotions of the video poster, and more appropriate captions can be displayed.

[0111] The setting unit can optimize the display timing of the telop based on the content of the video. The setting unit optimizes the display timing of the telop based on the content of the video. The display timing includes, for example, the timing of scene changes, the timing of important information, etc., but is not limited to these examples. The setting unit, for example, optimizes the timing of displaying the telop in important scenes. It can also optimize the timing of displaying the telop in moving scenes. It can also optimize the timing of displaying the telop in comedic scenes. This makes it possible to optimize the display timing of the telop based on the content of the video, and the telop is displayed at a more appropriate timing.

[0112] The setting unit can customize the caption style according to the video category. The setting unit customizes the caption style according to the video category. Caption styles include, for example, font, color, size, background, etc., but are not limited to these examples. For example, the setting unit uses a simple, highly visible caption style for news video. Also, a visually appealing caption style can be used for entertainment video. Furthermore, a caption style that emphasizes ease of understanding can be used for educational video. This makes it possible to customize the caption style according to the video category, and caption appropriate for the category is displayed.

[0113] The setting unit can analyze the emotions of the video poster and adjust the display order of the captions based on the analyzed emotions. The setting unit can analyze the emotions of the video poster and adjust the display order of the captions based on the analyzed emotions. The display order can include, for example, the importance of the information, the flow of the scenes, the level of viewer interest, etc., but is not limited to these examples. For example, if the video poster is relaxed, the setting unit can adjust the display order of the captions to match the relaxed scenes. Also, if the video poster is in a hurry, the setting unit can adjust the display order of the captions to match the important scenes. Furthermore, if the video poster is excited, the setting unit can adjust the display order of the captions to match the scenes that match the emotions. This makes it possible to adjust the display order of the captions based on the emotions of the video poster, and the captions can be displayed in a more appropriate order.

[0114] The setting unit can optimize the display position of the telop based on the composition of the video. The setting unit optimizes the display position of the telop based on the composition of the video. The display position includes, for example, the four corners, the center, the top, bottom, left, and right positions of the screen, but is not limited to these examples. The setting unit, for example, optimizes the display position of the telop so as not to obscure important parts of the video. The setting unit can also optimize the display position of the telop to improve the visibility of the video. Furthermore, the display position of the telop can be optimized taking into account the balance of the video. This makes it possible to optimize the display position of the telop based on the composition of the video, and highly visible telop is displayed.

[0115] The setting unit can automatically generate the content of the caption based on the related information of the video. The setting unit automatically generates the content of the caption based on the related information of the video. The related information includes, for example, metadata, tag information, related text, etc., but is not limited to these examples. The setting unit automatically generates related captions based on, for example, the content of the video. It can also automatically generate appropriate captions to match the scenes in the video. Furthermore, it can automatically generate the content of the caption based on the story of the video. This makes it possible to automatically generate the content of the caption based on the related information of the video, and more appropriate captions can be displayed.

[0116] The sound effects unit can analyze the emotions of the video uploader and select sound effects based on the analyzed emotions. The sound effects unit can analyze the emotions of the video uploader and select sound effects based on the analyzed emotions. Sound effects include, but are not limited to, environmental sounds, sound effect libraries, original sound sources, etc. For example, if the video uploader is relaxed, the sound effects unit can select calm sound effects. If the video uploader is in a hurry, the sound effects unit can select quick and concise sound effects. Furthermore, if the video uploader is excited, the sound effects unit can select visually stimulating sound effects. This makes it possible to select sound effects according to the emotions of the video uploader, and more appropriate sound effects can be added.

[0117] The sound effects section can optimize the timing of inserting sound effects based on the content of the video. The sound effects section optimizes the timing of inserting sound effects based on the content of the video. Insertion timing includes, but is not limited to, timing of scene changes and important information. The sound effects section, for example, optimizes the timing of inserting sound effects in important scenes. It can also optimize the timing of inserting sound effects in moving scenes. It can also optimize the timing of inserting sound effects in comedy scenes. This makes it possible to optimize the timing of inserting sound effects based on the content of the video, and sound effects are added at more appropriate timing.

[0118] The sound effects section can customize the type of sound effects according to the video category. The sound effects section customizes the type of sound effects according to the video category. The types of sound effects include, but are not limited to, environmental sounds, sound effect libraries, and original sound sources. For example, for news videos, the sound effects section uses simple, highly visible sound effects. For entertainment videos, visually appealing sound effects can also be used. Furthermore, for educational videos, sound effects that emphasize ease of understanding can also be used. This makes it possible to customize the type of sound effects according to the video category, and sound effects appropriate for the category are added.

[0119] The sound effects unit can analyze the emotions of the video uploader and adjust the volume of the sound effects based on the analyzed emotions. The sound effects unit can analyze the emotions of the video uploader and adjust the volume of the sound effects based on the analyzed emotions. The volume can include, but is not limited to, decibel values, scene importance, and viewer interest, for example. For example, if the video uploader is relaxed, the sound effects unit can play sound effects at a gentle volume. Also, if the video uploader is in a hurry, the sound effects unit can play sound effects at a highly visible volume. Furthermore, if the video uploader is excited, the sound effects can be played at a vivid volume. This makes it possible to adjust the volume of sound effects according to the emotions of the video uploader, and sound effects can be played at a more appropriate volume.

[0120] The sound effects section can optimize the insertion position of a sound effect based on the composition of the video. The sound effects section optimizes the insertion position of a sound effect based on the composition of the video. Insertion positions include, but are not limited to, the four corners, center, top, bottom, left, and right positions of the screen. The sound effects section can optimize the insertion position of a sound effect, for example, so as not to obscure important parts of the video. The sound effects section can also optimize the insertion position of a sound effect to improve the visibility of the video. Furthermore, the sound effects section can optimize the insertion position of a sound effect based on the balance of the video. This makes it possible to optimize the insertion position of a sound effect based on the composition of the video, and to add sound effects with high visibility.

[0121] The sound effect unit can automatically generate the content of the sound effect based on related information of the video. The sound effect unit automatically generates the content of the sound effect based on related information of the video. Related information includes, for example, metadata, tag information, related text, etc., but is not limited to these examples. The sound effect unit automatically generates related sound effects based on, for example, the content of the video. It can also automatically generate appropriate sound effects to match the scenes in the video. Furthermore, it can automatically generate the content of the sound effect based on the story of the video. This makes it possible to automatically generate the content of the sound effect based on related information of the video, and more appropriate sound effects can be added.

[0122] The real-time editing unit can analyze the emotions of the video poster and adjust the real-time editing method based on the analyzed emotions. The real-time editing unit can analyze the emotions of the video poster and adjust the real-time editing method based on the analyzed emotions. Real-time editing includes, for example, an editing delay time, a technique to be used, and the like, but is not limited to these examples. For example, if the video poster is relaxed, the real-time editing unit can perform real-time editing using a gentle editing method. Also, if the video poster is in a hurry, the real-time editing unit can perform real-time editing using a quick and concise editing method. Furthermore, if the video poster is excited, the real-time editing unit can perform real-time editing using a visually stimulating editing method. This makes it possible to adjust the real-time editing method according to the emotions of the video poster, resulting in more appropriate real-time editing.

[0123] The real-time editing unit can evaluate the quality of video during real-time editing and select the optimal editing method. The real-time editing unit evaluates the quality of video during real-time editing and selects the optimal editing method. Video quality includes, for example, resolution, frame rate, color tone, etc., but is not limited to these examples. For example, the real-time editing unit selects a high-quality editing method for high-resolution video. Also, for standard-resolution video, it can select a standard editing method. Furthermore, for low-resolution video, it can select a lightweight editing method. This makes it possible to select the optimal real-time editing method according to the video quality, and perform real-time editing while maintaining the video quality.

[0124] The real-time editing unit can apply different editing algorithms depending on the category of the video during real-time editing. The real-time editing unit applies different editing algorithms depending on the category of the video during real-time editing. Video categories include, but are not limited to, news, entertainment, and education. For example, the real-time editing unit applies a fast and accurate editing algorithm to news videos. Also, a visually appealing editing algorithm can be applied to entertainment videos. Furthermore, an editing algorithm that emphasizes ease of understanding can be applied to educational videos. This makes it possible to apply the optimal real-time editing algorithm depending on the category of the video, allowing for real-time editing appropriate for the category.

[0125] The real-time editing unit can analyze the emotions of the video poster and determine real-time editing priorities based on the analyzed emotions. The real-time editing unit analyzes the emotions of the video poster and determines real-time editing priorities based on the analyzed emotions. Real-time editing priorities include, but are not limited to, for example, the intensity of emotions and the importance of the video. For example, if the video poster is relaxed, the real-time editing unit can prioritize editing of relaxed scenes. Also, if the video poster is in a hurry, the real-time editing unit can prioritize editing of important scenes. Furthermore, if the video poster is excited, the real-time editing unit can prioritize editing of scenes that match the video poster's emotions. This makes it possible to determine real-time editing priorities based on the emotions of the video poster, allowing for more appropriate real-time editing of scenes.

[0126] The real-time editing unit can adjust the editing method based on the shooting location of the video during real-time editing. The real-time editing unit can adjust the editing method based on the shooting location of the video during real-time editing. The shooting location includes, for example, but is not limited to, GPS data, IP address, and region-specific data. For example, in the case of video shot in a specific region, the real-time editing unit can select an editing method appropriate for that region. In addition, in the case of video shot at a travel destination, the real-time editing unit can select an editing method that makes use of the characteristics of the travel destination. Furthermore, in the case of video shot at an event venue, an editing method related to the event can be selected. This makes it possible to adjust the real-time editing method according to the shooting location of the video, allowing real-time editing to be performed that is appropriate for the region.

[0127] The real-time editing unit can adjust the editing order based on the relevance of the images during real-time editing. The real-time editing unit adjusts the editing order based on the relevance of the images during real-time editing. The relevance of the images includes, for example, the flow of the story, the continuity of the scenes, and the degree of consistency of the content, but is not limited to these examples. The real-time editing unit, for example, edits highly relevant scenes consecutively. It can also edit less relevant scenes later. Furthermore, it can adjust the editing order taking into account the storyline of the images. This makes it possible to adjust the real-time editing order based on the relevance of the images, allowing for real-time editing with a storyline.

[0128] The analysis unit can analyze the emotions of the video poster and adjust the analysis method of the news video based on the analyzed emotions. The analysis unit can analyze the emotions of the video poster and adjust the analysis method of the news video based on the analyzed emotions. News video analysis methods include, but are not limited to, video content analysis, audio analysis, and metadata analysis, for example. For example, the analysis unit can use a gentle analysis method if the video poster is relaxed. Also, if the video poster is in a hurry, the analysis unit can use a quick and concise analysis method. Furthermore, if the video poster is excited, the analysis unit can use a visually stimulating analysis method. This makes it possible to adjust the analysis method of the news video according to the emotions of the video poster, resulting in more appropriate analysis.

[0129] The analysis unit can analyze the content of the news video in real time and select the optimal analysis method. The analysis unit analyzes the content of the news video in real time and selects the optimal analysis method. The content of the news video includes, but is not limited to, video content analysis, audio analysis, and metadata analysis. For example, the analysis unit analyzes important parts of the news video in real time and selects the optimal analysis method. It can also analyze moving parts of the news video in real time and select the optimal analysis method. It can also analyze comedic parts of the news video in real time and select the optimal analysis method. This makes it possible to select the optimal analysis method based on the content of the news video, allowing for appropriate analysis according to the content of the video.

[0130] The analysis unit can apply different analysis algorithms depending on the category of the news video. The analysis unit applies different analysis algorithms depending on the category of the news video. Categories of news videos include, but are not limited to, politics, economics, sports, etc. For example, the analysis unit applies a fast and accurate analysis algorithm to news videos. Furthermore, for entertainment videos, it can apply a visually appealing analysis algorithm. Furthermore, for educational videos, it can apply an analysis algorithm that emphasizes ease of understanding. This makes it possible to apply the optimal analysis algorithm depending on the category of the news video, allowing for analysis appropriate to the category.

[0131] The analysis unit can analyze the emotions of the video poster and determine the analysis priority of the news video based on the analyzed emotions. The analysis unit can analyze the emotions of the video poster and determine the analysis priority of the news video based on the analyzed emotions. The analysis priority of the news video includes, for example, the intensity of the emotion and the importance of the video, but is not limited to these examples. For example, if the video poster is relaxed, the analysis unit can prioritize analyzing relaxed scenes. Also, if the video poster is in a hurry, the analysis unit can prioritize analyzing important scenes. Furthermore, if the video poster is excited, the analysis unit can prioritize analyzing scenes that match the emotion. This makes it possible to determine the analysis priority of the news video according to the emotion of the video poster, allowing for more appropriate scene analysis.

[0132] The analysis unit can adjust the analysis method based on the shooting location of the news footage. The analysis unit adjusts the analysis method based on the shooting location of the news footage. The shooting location includes, but is not limited to, GPS data, IP address, and region-specific data. For example, in the case of news footage shot in a specific region, the analysis unit selects an analysis method appropriate for that region. In addition, in the case of news footage shot at a travel destination, the analysis unit can select an analysis method that takes advantage of the characteristics of the travel destination. Furthermore, in the case of news footage shot at an event venue, the analysis unit can select an analysis method related to the event. This makes it possible to adjust the analysis method according to the shooting location of the news footage, allowing for analysis appropriate for the region.

[0133] The analysis unit can adjust the order of analysis based on related information of the news video. The analysis unit adjusts the order of analysis based on related information of the news video. Related information includes, for example, metadata, tag information, related text, etc., but is not limited to these examples. The analysis unit, for example, analyzes highly related news videos consecutively. It can also analyze less related news videos later. Furthermore, it can adjust the order of analysis taking into account the storyline of the news video. This makes it possible to adjust the order of analysis based on related information of the news video, allowing for story-like analysis.

[0134] The breaking news generation unit can analyze the emotions of the video poster and adjust the method for generating breaking news captions based on the analyzed emotions. The breaking news generation unit can analyze the emotions of the video poster and adjust the method for generating breaking news captions based on the analyzed emotions. The method for generating breaking news captions includes, for example, text content, display position, display time, etc., but is not limited to these examples. For example, if the video poster is relaxed, the breaking news generation unit can generate calm breaking news captions. Also, if the video poster is in a hurry, the breaking news generation unit can generate quick and concise breaking news captions. Furthermore, if the video poster is excited, the breaking news generation unit can generate visually stimulating breaking news captions. This makes it possible to adjust the method for generating breaking news captions according to the emotions of the video poster, and more appropriate breaking news captions can be generated.

[0135] The breaking news generation unit can optimize the timing of displaying breaking news captions based on the content of the news video. The breaking news generation unit optimizes the timing of displaying breaking news captions based on the content of the news video. Display timing includes, for example, scene changes, timing of important information, etc., but is not limited to these examples. The breaking news generation unit, for example, optimizes the timing of displaying breaking news captions for important news video. It can also optimize the timing of displaying breaking news captions for moving news video. It can also optimize the timing of displaying breaking news captions for comedic news video. This makes it possible to optimize the display timing of breaking news captions based on the content of the news video, and breaking news captions are displayed at more appropriate timing.

[0136] The breaking news generation unit can customize the style of the breaking news caption according to the news category. The breaking news generation unit customizes the style of the breaking news caption according to the news category. Examples of the style of the breaking news caption include, but are not limited to, font, color, size, background, etc. For example, the breaking news generation unit uses a simple, highly visible breaking news caption style for news video. Also, for entertainment news video, a visually appealing breaking news caption style can be used. Furthermore, for educational news video, a breaking news caption style that emphasizes ease of understanding can be used. This makes it possible to customize the style of the breaking news caption according to the news category, and breaking news captions appropriate for the category are displayed.

[0137] The breaking news generation unit can analyze the emotions of the video poster and adjust the display order of breaking news captions based on the analyzed emotions. The breaking news generation unit analyzes the emotions of the video poster and adjusts the display order of breaking news captions based on the analyzed emotions. The display order includes, for example, the importance of the information, the flow of the scenes, the viewer's interest, etc., but is not limited to these examples. For example, if the video poster is relaxed, the breaking news generation unit can adjust the display order of breaking news captions to match the relaxed scenes. Also, if the video poster is in a hurry, the breaking news generation unit can adjust the display order of breaking news captions to match the important scenes. Furthermore, if the video poster is excited, the display order of breaking news captions can be adjusted to match the scenes that match the video poster's emotions. This makes it possible to adjust the display order of breaking news captions according to the emotions of the video poster, and breaking news captions can be displayed in a more appropriate order.

[0138] The breaking news generation unit can optimize the display position of the breaking news caption based on the composition of the news video. The breaking news generation unit optimizes the display position of the breaking news caption based on the composition of the news video. Examples of display positions include, but are not limited to, the four corners, center, top, bottom, left, and right positions of the screen. The breaking news generation unit, for example, optimizes the display position of the breaking news caption so as not to obscure important parts of the news video. The display position of the breaking news caption can also be optimized to improve the visibility of the news video. Furthermore, the display position of the breaking news caption can also be optimized taking into account the balance of the news video. This makes it possible to optimize the display position of the breaking news caption based on the composition of the news video, and breaking news captions with high visibility are displayed.

[0139] The breaking news generation unit can automatically generate the content of the breaking news caption based on related information about the news. The breaking news generation unit automatically generates the content of the breaking news caption based on related information about the news. Related information includes, for example, metadata, tag information, related text, etc., but is not limited to these examples. The breaking news generation unit automatically generates related breaking news captions based on, for example, the content of the news. It can also automatically generate appropriate breaking news captions to match the news scenes. Furthermore, it can automatically generate the content of the breaking news caption based on the news story. This makes it possible to automatically generate the content of the breaking news caption based on related information about the news, and more appropriate breaking news captions can be displayed. === Hard Collateral 1-1 === Each of the multiple elements including the learning unit, input unit, editing unit, and output unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the learning unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes past editing data to extract the editor's style. The input unit is realized by the control unit 46A of the smart device 14 and inputs raw video captured by a video poster into the system. The editing unit is realized by the specific processing unit 290 of the data processing device 12 and performs editing based on the learned style. The output unit is realized by the control unit 46A of the smart device 14 and outputs the edited video in a specified file format. === Hard Collateral 1-2 === Each of the multiple elements including the learning unit, input unit, editing unit, and output unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the learning unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes past editing data to extract the editor's style. The input unit is realized by the control unit 46A of the smart glasses 214 and inputs raw video captured by a video poster into the system. The editing unit is realized by the specific processing unit 290 of the data processing device 12 and performs editing based on the learned style. The output unit is realized by the control unit 46A of the smart glasses 214 and outputs the edited video in a specified file format. === Hard Collateral 1-3 === Each of the multiple elements including the learning unit, input unit, editing unit, and output unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the learning unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes past editing data to extract the editor's style. The input unit is realized by the control unit 46A of the headset type terminal 314 and inputs raw video captured by a video poster into the system. The editing unit is realized by the specific processing unit 290 of the data processing device 12 and performs editing based on the learned style. The output unit is realized by the control unit 46A of the headset type terminal 314 and outputs the edited video in a specified file format. === Hard Collateral 1-4 === Each of the multiple elements including the learning unit, input unit, editing unit, and output unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the learning unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes past editing data to extract the editor's style. The input unit is realized by the control unit 46A of the robot 414 and inputs raw video footage shot by a video poster into the system. The editing unit is realized by the specific processing unit 290 of the data processing device 12 and performs editing based on the learned style. The output unit is realized by the control unit 46A of the robot 414 and outputs the edited video in a specified file format.

[0140] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0141] The learning unit can learn not only from the video editor's past editing data but also from publicly available data from other video editors. For example, a video editor can adopt a new editing style by learning from the data of other editors with a specific style. The learning unit can also learn from editing data of different genres and automatically apply an editing style appropriate to the genre. Furthermore, the learning unit can receive feedback from video editors and update the learning data based on that feedback. This allows the learning unit to learn a wider variety of editing styles and perform editing that meets the needs of the video editor.

[0142] The setting unit can set not only the font and color of the caption, but also the animation effect of the caption. For example, it can set the effect of the caption fading in or sliding in. The setting unit can also customize the display time and display position of the caption for each scene. Furthermore, the setting unit can automatically translate the content of the caption and display it in multiple languages. This allows the setting unit to create visually appealing captions and help viewers understand them better.

[0143] The sound effects department can not only add sound effects, but also adjust the volume and pitch of the sound effects for each scene. For example, the volume can be increased in tense scenes and decreased in relaxed scenes. The sound effects department can also add effects such as echo and reverb to sound effects. Furthermore, the sound effects department can fine-tune the timing of sound effects to match the movement of the images. This allows the sound effects department to provide sound effects that match the atmosphere of the images, enhancing the viewer's sense of immersion.

[0144] The real-time editing department can not only edit in real time, but also apply effects in real time. For example, it can perform color correction and noise removal in real time on breaking news footage. The real-time editing department can also switch between multiple camera feeds in real time. Furthermore, the real-time editing department can receive real-time feedback from viewers and adjust the editing content based on that feedback. This allows the real-time editing department to provide higher quality footage and improve viewer satisfaction.

[0145] The analysis unit can not only analyze news footage, but also recognize people and objects within the footage. For example, it can recognize a specific person within news footage and display information related to that person. The analysis unit can also recognize objects within the footage and provide data related to the object. Furthermore, the analysis unit can analyze audio within the footage and perform appropriate editing based on the content of the audio. This allows the analysis unit to perform advanced analysis based on the content of the video, enabling more accurate editing.

[0146] The learning unit can analyze the emotions of the video editor and select learning data based on the analyzed emotions. For example, if the video editor is relaxed, past successful editing data can be preferentially selected as learning data. Also, if the video editor is stressed, simple and effective editing data can be selected as learning data. Furthermore, if the video editor is excited, creative editing data can be selected as learning data. This makes it possible to select learning data according to the video editor's emotions, allowing for learning of a more appropriate editing style.

[0147] The input unit can analyze the emotions of the video poster and adjust the timing of input based on the analyzed emotions. For example, if the video poster is relaxed, it can encourage them to input at a leisurely pace. If the video poster is in a hurry, it can encourage them to input quickly. Furthermore, if the video poster is excited, it can encourage them to input at a tempo that matches their emotions. This makes it possible to adjust the input timing according to the emotions of the video poster, allowing for more appropriate input.

[0148] The editing department can analyze the emotions of the video uploader and adjust the editing style based on the analyzed emotions. For example, if the video uploader is relaxed, the editing can be done using calm expressions. If the video uploader is in a hurry, the editing can be done using quick and concise expressions. Furthermore, if the video uploader is excited, the editing can be done using visually stimulating expressions. This makes it possible to adjust the editing style according to the video uploader's emotions, resulting in more appropriate editing.

[0149] The output unit can analyze the emotions of the video poster and adjust the output format based on the analyzed emotions. For example, if the video poster is relaxed, the output can be in a relaxed format. If the video poster is in a hurry, the output can be quick. Furthermore, if the video poster is excited, the output can be in a visually stimulating format. This makes it possible to adjust the output format according to the emotions of the video poster, and output in a more appropriate format.

[0150] The sound effects section can analyze the emotions of the video uploader and select sound effects based on the analyzed emotions. For example, if the video uploader is relaxed, calm sound effects can be selected. If the video uploader is in a hurry, quick and concise sound effects can be selected. Furthermore, if the video uploader is excited, visually stimulating sound effects can be selected. This makes it possible to select sound effects according to the video uploader's emotions, and more appropriate sound effects can be added.

[0151] The processing flow of the second embodiment will be briefly explained below.

[0152] Step 1: The learning unit learns the video editor's style. A video editor's style includes the tempo of editing, the effects used, the frequency of cuts, etc. The learning unit uses past editing data to learn how to insert subtitles at specific times and when to use specific sound effects. For example, the learning unit analyzes past editing data to extract the editor's style. Step 2: The input unit receives raw video footage from the video uploader. The raw video footage includes information such as resolution, frame rate, and file format. The input unit inputs the raw video footage captured by the video uploader into the system. Step 3: The editing team edits the video based on the style learned by the learning team. This includes cuts, transitions, and applying effects. Based on the learned style, the editing team inserts captions in specific scenes and adds sound effects at specific times. Step 4: The output unit outputs the edited video. The output includes the file format, resolution, frame rate, etc. The output unit outputs the edited video in the specified file format.

[0153] 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.

[0154] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0155] 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.

[0156] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0157] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0171] 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.

[0172] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0173] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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).

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0184] 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.

[0185] 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.

[0186] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0187] 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.

[0188] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0189] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0190] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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).

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0201] 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.

[0202] 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.

[0203] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0204] 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.

[0205] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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).

[0210] 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 indicated, and when they approach the ideal, a state of pleasure is indicated. 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 indicated, and when they approach the ideal, a state of pleasure is indicated. 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.

[0211] 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."

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] [Explanation of symbols]

[0225] 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 learning department that teaches video editor styles, an input unit where a video poster inputs raw video; an editing unit that performs editing based on the style learned by the learning unit; an output unit that outputs the edited video; A system characterized by:

2. A setting section is provided for setting the font or color of the subtitles.

2. The system of claim 1.

3. Equipped with a sound effects section that adds sound effects 2. The system of claim 1.

4. Equipped with a real-time editing section for real-time editing 2. The system of claim 1.

5. Equipped with an analysis unit that analyzes news footage 2. The system of claim 1.

6. Equipped with a breaking news generation unit that generates subtitles for breaking news 2. The system of claim 1.

7. The learning unit Analyze the emotions of video editors and select learning data based on the analyzed emotions.

2. The system of claim 1.

8. The learning unit Analyzes past editing data, extracts and learns specific editing patterns 2. The system of claim 1.

9. The learning unit Optimize learning timing based on editors' work hours and frequency 2. The system of claim 1.

10. The learning unit Estimate the emotions of video editors and prioritize learning based on the estimated emotions.

2. The system of claim 1.

Images