system

Abstract

The system according to this embodiment aims to achieve efficient and rapid video production and provide attractive content that is in line with current trends. [Solution] The system according to the embodiment comprises an analysis unit, a generation unit, an effect selection unit, a BGM selection unit, a structure proposal unit, an editing unit, a highlight generation unit, and a catchphrase generation unit. The analysis unit analyzes trends. The generation unit generates a storyboard based on the trends analyzed by the analysis unit. The effect selection unit automatically selects effects in cooperation with other editing software. The BGM selection unit automatically selects background music in cooperation with other editing software. The structure proposal unit proposes the structure of the video. The editing unit performs editing based on the structure proposed by the structure proposal unit. The highlight generation unit generates highlight scenes that attract the viewer's attention. The catchphrase generation unit generates catchphrases.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that the process of coming up with ideas for content and editing is complicated, and it is difficult to produce videos that follow trends.

[0005] The system according to the embodiment aims to realize efficient and rapid video production and provide attractive content that matches trends.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a generation unit, an effect selection unit, a background music (BGM) selection unit, a structure proposal unit, an editing unit, a highlight generation unit, and a catchphrase generation unit. The analysis unit analyzes trends. The generation unit generates a storyboard based on the trends analyzed by the analysis unit. The effect selection unit automatically selects effects in cooperation with other editing software. The BGM selection unit automatically selects background music in cooperation with other editing software. The structure proposal unit proposes a video structure. The editing unit performs editing based on the structure proposed by the structure proposal unit. The highlight generation unit generates highlight scenes that attract the viewer's attention. The catchphrase generation unit generates catchphrases. [Effects of the Invention]

[0007] The system according to this embodiment enables efficient and rapid video production and can provide attractive content that is in line with current trends. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8]This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the tagged communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F manages 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), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by contact of an indicator (e.g., a pen or a finger, etc.) by detecting the contact of the indicator. The microphone 38B receives user input by voice by detecting the voice of the user. 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, a specific processing unit 290 (see FIG. 2) acquires data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The video production system according to an embodiment of the present invention is a system for efficiently and quickly producing video content using generative AI. This video production system first uses AI to analyze the latest trends and generate storyboards according to genre. Next, it automatically selects effects and background music in cooperation with other editing software. Furthermore, it proposes an "introduction → build-up → conclusion" flow to simplify editing. Finally, it automatically generates highlight scenes and catchy slogans to attract the viewer's attention. This mechanism enables efficient and rapid video production and allows for the provision of attractive content that matches current trends. It also saves time and significantly reduces the burden of production. For example, the AI ​​analyzes the latest trends. In this process, it collects data from social media and news sites, and the AI ​​analyzes it to grasp current trends. For example, it analyzes trends related to a specific genre or theme and generates a storyboard based on the results. This makes it possible to produce content that matches trends. Next, it automatically selects effects and background music in cooperation with other editing software. For example, it cooperates with video editing software, and the AI ​​selects the optimal effects and background music. This streamlines the editing process and reduces the burden on creators. Furthermore, it proposes an "introduction → build-up → conclusion" structure, simplifying editing. For example, the AI ​​suggests the structure of a video, and creators can edit according to that suggestion, enabling efficient video production. This simplifies the editing process and saves time. Finally, it automatically generates highlight scenes and catchy slogans to attract viewers' attention. For example, the AI ​​automatically selects scenes from the video that will capture viewers' attention and generates catchy slogans to match those scenes. This allows for the creation of videos that capture viewers' interest. This system enables efficient and rapid video production, allowing for the delivery of engaging content that aligns with current trends. It also saves time and significantly reduces the burden of production. For example, it is an extremely useful tool for people who need efficient and high-quality content production, such as social media managers, marketers, and short video creators.This enables the video production system to produce videos efficiently and quickly, and to deliver engaging content that is in line with current trends.

[0029] The video production system according to this embodiment comprises an analysis unit, a generation unit, an effect selection unit, a background music (BGM) selection unit, a composition proposal unit, an editing unit, a highlight generation unit, and a catchphrase generation unit. The analysis unit analyzes trends. The analysis unit collects data from sources such as social media and news sites and analyzes trends. The analysis unit uses AI to analyze the collected data and grasp current trends. The generation unit generates storyboards based on the trends analyzed by the analysis unit. The generation unit analyzes trends related to a specific genre or theme and generates storyboards based on the results. The generation unit uses generation AI to generate storyboards. The effect selection unit automatically selects effects in cooperation with other editing software. The effect selection unit, for example, works with video editing software, and the AI ​​selects the optimal effect. The effect selection unit can also automatically select effects using AI. The BGM selection unit automatically selects background music (BGM) in cooperation with other editing software. The BGM selection unit, for example, works with video editing software, and the AI ​​selects the optimal BGM. The BGM selection unit can also automatically select background music using AI. The structure proposal unit proposes the structure of the video. The structure proposal unit proposes, for example, a flow of "introduction → build-up → conclusion". The structure proposal unit proposes the structure of the video using AI. The editing unit performs editing based on the structure proposed by the structure proposal unit. The editing unit performs editing according to, for example, the structure proposed by AI. The editing unit can also perform editing using AI. The highlight generation unit generates highlight scenes that attract the viewer's attention. The highlight generation unit automatically selects, for example, scenes from the video that will attract the viewer's attention. The highlight generation unit generates highlight scenes using AI. The catchphrase generation unit generates catchphrases. The catchphrase generation unit generates, for example, catchphrases that will attract the viewer's attention. The catchphrase generation unit generates catchphrases using AI. As a result, the video production system according to this embodiment enables efficient and rapid video production based on trends.

[0030] The analysis department analyzes trends. For example, it collects data from social media and news sites to analyze trends. Specifically, the analysis department uses crawlers to collect data from various internet platforms. These crawlers regularly visit social media and news sites to collect the latest posts and articles. The collected data is analyzed using natural language processing technology to extract trending keywords and topics. For example, it analyzes the frequency of specific hashtags in social media posts to understand current trends. It also analyzes news site articles to identify trending news topics. The analysis department uses AI to analyze the collected data and understand current trends. The AI ​​uses machine learning algorithms to predict trend fluctuations by comparing them with past data. For example, based on data from the past few months, if the frequency of a particular keyword has suddenly increased, it determines that the keyword is a current trend. Furthermore, the analysis department can monitor trend fluctuations in real time and issue alerts if there are sudden changes. This allows the analysis department to always grasp the latest trend information and reflect it in video production.

[0031] The generation unit generates storyboards based on trends analyzed by the analysis unit. For example, the generation unit analyzes trends related to a specific genre or theme and generates storyboards based on the results. Specifically, the generation unit determines the theme and storyline of the video based on the trend information provided by the analysis unit. The generation unit generates storyboards using a generation AI. The generation AI uses natural language generation technology to automatically generate storyboard scenarios based on trends. For example, if the trend is "environmental protection," the generation AI will propose a storyline related to environmental protection and generate detailed explanations for each scene. The generated storyboards serve as a guide for video production, clearly showing the content and order of each scene. Furthermore, the generation unit can also revise the storyboards based on user feedback. This allows the generation unit to quickly generate compelling storyboards that are in line with trends, improving the efficiency of video production.

[0032] The effects selection unit automatically selects effects in conjunction with other editing software. For example, it can work with video editing software, and AI can select the optimal effects. Specifically, the effects selection unit uses the video editing software's API to access the software's effect library. The AI ​​analyzes the storyboard content and scene characteristics to select the most suitable effects. For example, it might apply fade-in / fade-out effects to emotional scenes and speed-up or slow-motion effects to action scenes. The effects selection unit can also learn the user's preferences and past editing history to provide more personalized effect selections. As a result, the effects selection unit can automatically select the optimal effects to improve video quality, significantly increasing the efficiency of the editing process.

[0033] The BGM selection function automatically selects background music (BGM) in conjunction with other editing software. For example, it can work with video editing software, and its AI will select the most suitable BGM. Specifically, the BGM selection function uses the video editing software's API to access the BGM library within the software. The AI ​​analyzes the storyboard content and scene characteristics to select the most appropriate BGM. For example, it might select a calm piano piece for an emotional scene and a fast-paced rock song for an action scene. The BGM selection function can also learn the user's preferences and past editing history to provide more personalized BGM selections. Furthermore, the BGM selection function can adjust the timing of the BGM according to the video length and scene transitions. As a result, the BGM selection function can automatically select BGM to optimize the atmosphere of the video, significantly improving the efficiency of the editing process.

[0034] The video composition proposal team proposes the structure of the video. For example, they might suggest a flow such as "introduction → build-up → conclusion." Specifically, the team designs the overall structure of the video based on the content of the storyboard and trend information. AI learns from data of past successful videos and extracts effective structure patterns. For example, it suggests an effective introduction to capture the viewer's attention, a build-up to evoke emotion, and a conclusion to leave a strong impression on the viewer. The video composition proposal team can also revise the structure based on user feedback. This allows the team to propose effective video structures that capture the viewer's attention and improve the quality of video production.

[0035] The editorial team edits based on the structure proposed by the structure proposal team. For example, the editorial team edits according to a structure proposed by AI. Specifically, the editorial team decides on cuts and transitions for each scene based on the structure proposal provided by the structure proposal team. The AI ​​analyzes the content and trend information of each scene and selects the optimal editing method. For example, it applies smooth transitions to emotional scenes and dynamic cuts to action scenes. The editorial team can also revise the editing based on user feedback. This allows the editorial team to create effective edits that capture the viewer's attention and improve the quality of the video.

[0036] The highlight generation unit generates highlight scenes that capture the viewer's attention. For example, the highlight generation unit automatically selects scenes from a video that are likely to attract the viewer's attention. Specifically, the highlight generation unit uses AI to analyze viewer reactions to each scene in the video. Based on viewer eye-tracking data and click data, the AI ​​identifies scenes that viewers paid particular attention to. For example, it selects scenes that viewers watched for a long time or scenes with a high number of views as highlights. The highlight generation unit can also predict scenes that will attract viewer interest based on the video's content and trend information. As a result, the highlight generation unit can generate effective highlight scenes that capture the viewer's attention and enhance the video's appeal.

[0037] The catchphrase generation unit generates catchphrases. For example, it generates catchphrases that will attract the viewer's attention. Specifically, the catchphrase generation unit uses AI to analyze the video content and trend information to generate effective catchphrases. The AI ​​uses natural language generation technology to automatically generate short phrases that will capture the viewer's attention. For example, if the theme of the video is "environmental protection," it will generate a catchphrase such as "What we can do now to protect the future." The catchphrase generation unit can also revise catchphrases based on user feedback. As a result, the catchphrase generation unit can quickly generate effective catchphrases that attract the viewer's attention and improve the appeal of the video.

[0038] The analysis unit can collect data from social media and news sites and analyze trends. For example, the analysis unit collects data from social media and news sites and analyzes trends. The analysis unit uses AI to analyze the collected data and grasp current trends. This allows for the analysis of the latest trends by collecting data from social media and news sites. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input data collected from social media and news sites into a generating AI and have the generating AI perform the trend analysis.

[0039] The generation unit can analyze trends related to a specific genre or theme and generate storyboards based on the results. For example, the generation unit analyzes trends related to a specific genre or theme and generates storyboards based on the results. The generation unit generates storyboards using a generation AI. This makes it possible to generate storyboards tailored to a specific genre or theme. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit can input trend data related to a specific genre or theme into a generation AI and have the generation AI perform storyboard generation.

[0040] The effect selection unit can work in conjunction with video editing software to automatically select the optimal effect. For example, the effect selection unit can work in conjunction with video editing software, and AI can select the optimal effect. The effect selection unit can also automatically select effects using AI. This allows for the automatic selection of the optimal effect by working in conjunction with video editing software. Some or all of the above-described processes in the effect selection unit may be performed using AI or not. For example, the effect selection unit can input data obtained from video editing software into a generating AI and have the generating AI perform the effect selection.

[0041] The BGM selection unit can work in conjunction with video editing software to automatically select the optimal background music (BGM). For example, the BGM selection unit can work in conjunction with video editing software, and AI can select the optimal BGM. The BGM selection unit can also automatically select BGM using AI. This allows for the automatic selection of the optimal BGM by working in conjunction with video editing software. Some or all of the above-described processes in the BGM selection unit may be performed using AI or not. For example, the BGM selection unit can input data obtained from video editing software into a generating AI and have the generating AI perform the BGM selection.

[0042] The structure proposal unit can propose a flow of "introduction → build-up → conclusion". For example, the structure proposal unit proposes a flow of "introduction → build-up → conclusion". The structure proposal unit uses AI to propose the structure of the video. This simplifies the structure of the video by proposing a flow of "introduction → build-up → conclusion". Some or all of the above processing in the structure proposal unit may be performed using AI or not. For example, the structure proposal unit can input video structure data into a generating AI and have the generating AI execute a structure proposal.

[0043] The editorial department can perform editing based on the structure proposed by the structure proposal department. For example, the editorial department can perform editing according to a structure proposed by AI. The editorial department can also perform editing using AI. This makes the editing process more efficient by performing editing based on the structure proposed by the structure proposal department. Some or all of the above processes in the editorial department may be performed using AI or not. For example, the editorial department can input structure data obtained from the structure proposal department into a generation AI and have the generation AI perform the editing.

[0044] The highlight generation unit can automatically select scenes from a video that will attract the viewer's attention. For example, the highlight generation unit automatically selects scenes from a video that will attract the viewer's attention. The highlight generation unit generates highlight scenes using AI. This allows for the creation of compelling highlight scenes by automatically selecting scenes that will attract the viewer's attention. Some or all of the above-described processes in the highlight generation unit may be performed using AI or not. For example, the highlight generation unit can input video data into a generation AI and have the generation AI perform the selection of scenes that will attract the viewer's attention.

[0045] The catchphrase generation unit can generate catchphrases that attract the viewer's attention. For example, the catchphrase generation unit generates catchphrases that attract the viewer's attention. The catchphrase generation unit generates catchphrases using AI. This enhances the appeal of the video by generating catchphrases that attract the viewer's attention. Some or all of the above-described processes in the catchphrase generation unit may be performed using AI or not. For example, the catchphrase generation unit can input the video content into a generation AI and have the generation AI perform the generation of catchphrases.

[0046] The analysis unit can prioritize the analysis of trends based on specific regions or cultures. For example, the analysis unit can prioritize the collection of social media data from a specific region and analyze the trends in that region. The analysis unit can also prioritize the analysis of news sites related to a specific culture and grasp the trends of that culture. The analysis unit can also collect event information for each region and analyze trends specific to that region. By prioritizing the analysis of trends based on specific regions or cultures, it is possible to provide trend information tailored to specific regions and cultures. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input data related to a specific region or culture into a generating AI and have the generating AI perform trend analysis.

[0047] The analysis unit can predict future trends by referring to past trend data. For example, the analysis unit can analyze trend data from the past several years and predict seasonal trend patterns. The analysis unit can also predict the impact of specific events or occurrences on future trends based on past trend data. The analysis unit can also predict future trends for specific genres or themes by referring to past trend data. In this way, future trends can be predicted by referring to past trend data. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input past trend data into a generating AI and have the generating AI perform future trend predictions.

[0048] The analysis unit can analyze trends specific to particular industries or fields. For example, the analysis unit can prioritize collecting SNS data from a specific industry and analyze trends in that industry. The analysis unit can also prioritize analyzing news sites related to a specific field and grasp trends in that field. The analysis unit can also collect event information for each industry and analyze trends specific to that industry. In this way, by analyzing trends specific to particular industries or fields, it can provide trend information specific to those fields. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input data related to a specific industry or field into a generating AI and have the generating AI perform trend analysis.

[0049] The analysis unit can analyze trends that are changing in real time. For example, the analysis unit can collect real-time SNS data and instantly analyze current trends. The analysis unit can also analyze news sites in real time to grasp the latest trends. The analysis unit can also collect real-time event information and analyze trends at that moment. In this way, by analyzing trends that are changing in real time, it can provide the latest trend information. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input real-time data into a generating AI and have the generating AI perform trend analysis.

[0050] The generation unit can generate content tailored to a specific target audience. For example, to generate storyboards for young people, the generation unit can incorporate the latest trends and fashions. To generate storyboards for business professionals, the generation unit can include specialized information and data. To generate storyboards for seniors, the generation unit can provide simple and easy-to-understand content. In this way, by generating content tailored to a specific target audience, the generation unit can provide storyboards that are optimal for that target. Some or all of the above processes in the generation unit may be performed using AI or not. For example, the generation unit can input data about the target audience into a generation AI and have the generation AI perform the storyboard generation.

[0051] The generation unit can generate the optimal structure by referring to past success stories. For example, the generation unit can generate a new storyboard by referring to the storyboards of past successful videos. The generation unit can also extract the optimal structure for a specific genre or theme from past success stories. Based on past success stories, the generation unit can also generate a storyboard that incorporates elements that will attract the viewer's attention. In this way, the optimal structure can be generated by referring to past success stories. Some or all of the above processes in the generation unit may be performed using AI or not. For example, the generation unit can input past success story data into a generation AI and have the generation AI perform storyboard generation.

[0052] The generation unit can generate content tailored to specific events or seasons. For example, it can generate storyboards tailored to seasonal events. It can also generate storyboards tailored to specific holidays. It can also generate storyboards that adapt to seasonal changes. By generating content tailored to specific events or seasons, it can provide storyboards that are optimal for those events or seasons. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit can input data related to specific events or seasons into a generation AI and have the generation AI perform storyboard generation.

[0053] The generation unit can generate content that combines multiple genres. For example, it can generate a storyboard that combines comedy and drama. It can also generate a storyboard that combines action and romance. It can also generate a storyboard that combines documentary and fiction. This allows for the provision of a wider variety of storyboards by generating content that combines multiple genres. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit can input data on multiple genres into a generation AI and have the generation AI perform the generation of storyboards.

[0054] The effect selection unit can prioritize selecting effects that match a specific theme or mood. For example, the effect selection unit can select effects that match the theme of a horror movie. It can also select effects that match a romantic mood. It can also select effects that match an action scene. By prioritizing the selection of effects that match a specific theme or mood, it is possible to provide effects that are optimal for that theme or mood. Some or all of the above processing in the effect selection unit may be performed using AI or not. For example, the effect selection unit can input data related to a specific theme or mood into a generating AI and have the generating AI perform the effect selection.

[0055] The effect selection unit can select the optimal effect by referring to past usage history. For example, the effect selection unit can suggest the optimal effect based on the effects the user has used in the past. The effect selection unit can also select the optimal effect for a specific scene from past usage history. The effect selection unit can also analyze past usage history and select effects that received a good response from viewers. In this way, the optimal effect can be selected by referring to past usage history. Some or all of the above processes in the effect selection unit may be performed using AI or not. For example, the effect selection unit can input past usage history data into a generating AI and have the generating AI perform the effect selection.

[0056] The effect selection unit can select effects that match a specific visual style. For example, the effect selection unit can select effects that match a retro visual style. It can also select effects that match a modern visual style. It can also select effects that match a minimalist visual style. By selecting effects that match a specific visual style, it is possible to provide effects that are optimal for that visual style. Some or all of the above processing in the effect selection unit may be performed using AI or not. For example, the effect selection unit can input data about a specific visual style into a generating AI and have the generating AI perform the effect selection.

[0057] The effect selection unit can generate new effects by combining multiple effects. For example, the effect selection unit can generate a new effect by combining a glitch effect and a retro effect. It can also generate a new effect by combining a motion blur effect and a color filter. It can also generate a new effect by combining a light leak effect and a vignette effect. This allows for a wider variety of effects to be provided by combining multiple effects to generate new ones. Some or all of the above processing in the effect selection unit may be performed using AI or not. For example, the effect selection unit can input multiple effect data into a generation AI and have the generation AI execute the generation of a new effect.

[0058] The BGM selection unit can prioritize selecting background music that matches a specific scene or mood. For example, the BGM selection unit can select energetic background music to match an action scene. It can also select emotionally moving background music to match a romantic scene. It can also select upbeat background music to match a comedy scene. In this way, by prioritizing the selection of background music that matches a specific scene or mood, it is possible to provide background music that is optimal for that scene or mood. Some or all of the above processing in the BGM selection unit may be performed using AI, or it may be performed without using AI. For example, the BGM selection unit can input data about a specific scene or mood into a generating AI and have the generating AI perform the BGM selection.

[0059] The BGM selection unit can select the most suitable background music (BGM) by referring to past usage history. For example, the BGM selection unit can suggest the most suitable BGM based on the BGM the user has used in the past. The BGM selection unit can also select the most suitable BGM for a specific scene from past usage history. The BGM selection unit can also analyze past usage history and select BGM that received a good response from viewers. In this way, the most suitable BGM can be selected by referring to past usage history. Some or all of the above processes in the BGM selection unit may be performed using AI, or they may not be performed using AI. For example, the BGM selection unit can input past usage history data into a generating AI and have the generating AI perform the BGM selection.

[0060] The BGM selection unit can select background music (BGM) that specializes in a particular genre or artist. For example, the BGM selection unit can select BGM that specializes in the rock genre. The BGM selection unit can also select BGM that specializes in classical music artists. The BGM selection unit can also select BGM that specializes in the pop music genre. This allows the system to provide BGM that is optimal for a particular genre or artist by selecting BGM that specializes in that genre or artist. Some or all of the above processing in the BGM selection unit may be performed using AI, or it may be performed without AI. For example, the BGM selection unit can input data about a specific genre or artist into a generating AI and have the generating AI perform the BGM selection.

[0061] The BGM selection unit can generate new background music by combining multiple BGM tracks. For example, the BGM selection unit can combine classical music and electronica to generate new BGM. It can also combine jazz and hip hop to generate new BGM. It can also combine rock and pop to generate new BGM. This allows for a wider variety of background music to be provided by combining multiple BGM tracks to generate new BGM. Some or all of the above processing in the BGM selection unit may be performed using AI or not. For example, the BGM selection unit can input multiple BGM data into a generation AI and have the generation AI perform the generation of new BGM.

[0062] The program proposal unit can propose programs tailored to specific target audiences. For example, to propose a program for young people, the program proposal unit can incorporate the latest trends and fashions. To propose a program for business professionals, the program proposal unit can include specialized information and data. To propose a program for seniors, the program proposal unit can provide simple and easy-to-understand content. In this way, by proposing a program tailored to a specific target audience, the program can provide the most suitable program for that target audience. Some or all of the above processes in the program proposal unit may be performed using AI or not. For example, the program proposal unit can input data about the target audience into a generating AI and have the generating AI execute program proposals.

[0063] The structure proposal unit can propose the optimal structure by referring to past successful cases. For example, the structure proposal unit can propose a new structure by referring to the structure of a past successful video. The structure proposal unit can also extract the optimal structure for a specific genre or theme from past successful cases. Based on past successful cases, the structure proposal unit can also propose a structure that incorporates elements that will attract the viewer's interest. In this way, the optimal structure can be proposed by referring to past successful cases. Some or all of the above processes in the structure proposal unit may be performed using AI or not. For example, the structure proposal unit can input past successful case data into a generating AI and have the generating AI execute structure proposals.

[0064] The configuration proposal unit can propose configurations tailored to specific events or seasons. For example, it can propose configurations tailored to seasonal events. It can also propose configurations tailored to specific holidays. It can also propose configurations that adapt to seasonal changes. In this way, by proposing configurations tailored to specific events or seasons, it can provide the optimal configuration for events or seasons. Some or all of the above processing in the configuration proposal unit may be performed using AI or not. For example, the configuration proposal unit can input data related to specific events or seasons into a generating AI and have the generating AI execute configuration proposals.

[0065] The composition proposal unit can propose compositions that combine multiple genres. For example, it can propose a composition that combines comedy and drama. It can also propose a composition that combines action and romance. It can also propose a composition that combines documentary and fiction. By proposing compositions that combine multiple genres, it can provide a wider variety of compositions. Some or all of the above processing in the composition proposal unit may be performed using AI or not. For example, the composition proposal unit can input data on multiple genres into a generating AI and have the generating AI execute composition proposals.

[0066] The editorial team can tailor its content to a specific target audience. For example, to create content for a younger audience, the team can incorporate the latest trends and fashions. To create content for business professionals, the team can include specialized information and data. To create content for seniors, the team can provide simple and easy-to-understand content. By tailoring the content to a specific target audience, the team can provide content that is optimal for that target. Some or all of the processes described above in the editorial team may be performed using AI, or not. For example, the editorial team can input data about the target audience into a generative AI and have the generative AI perform the editing.

[0067] The editorial team can perform optimal editing by referring to past success stories. For example, the editorial team can create new edits by referencing the editing of past successful videos. The editorial team can also extract the most suitable editing for a specific genre or theme from past success stories. The editorial team can also create edits that incorporate elements that will attract viewers' attention, based on past success stories. In this way, optimal editing can be performed by referring to past success stories. Some or all of the above processes in the editorial team may be performed using AI or not. For example, the editorial team can input past success story data into a generating AI and have the generating AI perform the editing.

[0068] The editorial department can perform editing tailored to specific events or seasons. For example, the editorial department can perform editing tailored to seasonal events. The editorial department can also perform editing tailored to specific holidays. The editorial department can also perform editing in accordance with seasonal changes. This allows for the provision of editing that is optimal for specific events or seasons. Some or all of the above processes performed by the editorial department may be performed using AI or not. For example, the editorial department can input data related to specific events or seasons into a generating AI and have the generating AI perform the editing.

[0069] The editorial department can combine multiple editing techniques to create new edits. For example, the editorial department can combine cut editing and transitions to create new edits. The editorial department can also combine effects editing and color grading to create new edits. The editorial department can also combine motion graphics and text animation to create new edits. This allows for a wider variety of edits to be offered by combining multiple editing techniques. Some or all of the above processes in the editorial department may be performed using AI or not. For example, the editorial department can input data on multiple editing techniques into a generating AI and have the generating AI perform the new edits.

[0070] The highlight generation unit can generate highlight scenes tailored to a specific target audience. For example, to generate highlight scenes for younger audiences, the highlight generation unit can incorporate the latest trends and fashions. To generate highlight scenes for business professionals, the highlight generation unit can include specialized information and data. To generate highlight scenes for older adults, the highlight generation unit can provide simple and easy-to-understand content. In this way, by generating highlight scenes tailored to a specific target audience, the system can provide highlight scenes that are optimal for that target. Some or all of the above-described processes in the highlight generation unit may be performed using AI or not. For example, the highlight generation unit can input data about the target audience into a generation AI and have the generation AI perform the generation of highlight scenes.

[0071] The highlight generation unit can generate optimal highlight scenes by referring to past successful examples. For example, the highlight generation unit can generate new highlight scenes by referencing highlight scenes from past successful videos. The highlight generation unit can also extract the most suitable highlight scenes for a specific genre or theme from past successful examples. Based on past successful examples, the highlight generation unit can also generate highlight scenes that incorporate elements that will attract viewers' attention. In this way, optimal highlight scenes can be generated by referring to past successful examples. Some or all of the above processes in the highlight generation unit may be performed using AI or not. For example, the highlight generation unit can input past successful example data into a generation AI and have the generation AI perform the generation of highlight scenes.

[0072] The highlight generation unit can generate highlight scenes tailored to specific events or seasons. For example, it can generate highlight scenes tailored to seasonal events. It can also generate highlight scenes tailored to specific holidays. It can also generate highlight scenes that correspond to seasonal changes. In this way, by generating highlight scenes tailored to specific events or seasons, it can provide highlight scenes that are optimal for events or seasons. Some or all of the above-described processes in the highlight generation unit may be performed using AI or not. For example, the highlight generation unit can input data related to specific events or seasons into a generation AI and have the generation AI execute the generation of highlight scenes.

[0073] The highlight generation unit can generate new highlight scenes by combining multiple scenes. For example, it can combine action scenes and romance scenes to generate a new highlight scene. It can also combine comedy scenes and drama scenes to generate a new highlight scene. It can also combine documentary scenes and fiction scenes to generate a new highlight scene. This allows for a wider variety of highlight scenes to be provided by combining multiple scenes to generate a new highlight scene. Some or all of the above-described processes in the highlight generation unit may be performed using AI or not. For example, the highlight generation unit can input multiple scene data into a generation AI and have the generation AI perform the generation of a new highlight scene.

[0074] The tagline generation unit can generate taglines tailored to specific target audiences. For example, to generate taglines for young people, the tagline generation unit can incorporate the latest trends and fashions. To generate taglines for business professionals, the tagline generation unit can also include specialized information and data. To generate taglines for seniors, the tagline generation unit can provide simple and easy-to-understand content. In this way, by generating taglines tailored to specific target audiences, the unit can provide taglines that are optimal for the target. Some or all of the above-described processes in the tagline generation unit may be performed using AI or not. For example, the tagline generation unit can input data about the target audience into a generation AI and have the generation AI perform the tagline generation.

[0075] The catchphrase generation unit can generate the optimal catchphrase by referring to past success stories. For example, the catchphrase generation unit can generate a new catchphrase by referring to past successful catchphrases. The catchphrase generation unit can also extract the optimal catchphrase for a specific genre or theme from past success stories. The catchphrase generation unit can also generate a catchphrase that incorporates elements that will attract the viewer's attention, based on past success stories. In this way, the optimal catchphrase can be generated by referring to past success stories. Some or all of the above processes in the catchphrase generation unit may be performed using AI or not. For example, the catchphrase generation unit can input past success story data into a generation AI and have the generation AI perform the catchphrase generation.

[0076] The catchphrase generation unit can generate catchphrases tailored to specific events or seasons. For example, it can generate catchphrases tailored to seasonal events. It can also generate catchphrases tailored to specific holidays. It can also generate catchphrases that respond to seasonal changes. By generating catchphrases tailored to specific events or seasons, it can provide catchphrases that are optimal for those events or seasons. Some or all of the above-described processes in the catchphrase generation unit may be performed using AI or not. For example, the catchphrase generation unit can input data related to specific events or seasons into a generation AI and have the generation AI perform the catchphrase generation.

[0077] The catchphrase generation unit can generate new catchphrases by combining multiple existing catchphrases. For example, it can combine a visually stimulating catchphrase with a catchphrase with a gentle tone to generate a new catchphrase. It can also combine a simple catchphrase with a detailed catchphrase to generate a new catchphrase. Furthermore, it can combine past successful catchphrases with new ideas to generate a new catchphrase. This allows for a wider variety of catchphrases to be provided by combining multiple catchphrases to generate a new catchphrase. Some or all of the above-described processes in the catchphrase generation unit may be performed using AI or not. For example, the catchphrase generation unit can input data from multiple catchphrases into a generation AI and have the generation AI perform the generation of a new catchphrase.

[0078] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0079] The analysis unit can analyze a user's past viewing history and improve the accuracy of trend analysis based on that history. For example, it can analyze the genres and themes of videos a user has watched in the past and predict trends based on those tendencies. The analysis unit can also extract the characteristics of content that a user frequently watches and perform trend analysis based on that. This makes it possible to perform trend analysis based on the user's viewing history and provide more personalized trend information.

[0080] The effect selection section allows you to layer multiple effects to emphasize specific visual effects. For example, you can combine a glitch effect and a color filter to create a visually impactful effect. The effect selection section can also combine motion blur and particle effects to highlight dynamic scenes. This allows for a wider variety of visual effects by combining multiple effects.

[0081] The composition proposal department can propose compositions that incorporate specific storytelling techniques. For example, they can propose a composition using flashbacks, inserting scenes that look back on past events. The composition proposal department can also propose a composition using time leaps, creating a story that moves back and forth through time. In this way, by proposing compositions that incorporate specific storytelling techniques, it is possible to produce videos that capture the viewer's interest.

[0082] The highlight generation unit can generate highlight scenes tailored to specific audience demographics. For example, it can generate highlights that emphasize action scenes for younger audiences, or highlights that emphasize scenes containing important information for business professionals. By providing highlight scenes tailored to specific audiences, it is possible to capture their attention.

[0083] The analysis unit can analyze trends based on specific keywords. For example, it can analyze keywords related to specific product names or brand names to understand their trends. The analysis unit can also analyze keywords related to specific events or campaigns and evaluate their impact. This enables trend analysis based on specific keywords, allowing for the provision of more accurate trend information.

[0084] The following briefly describes the processing flow for example form 1.

[0085] Step 1: The analysis unit analyzes trends. The analysis unit collects data from sources such as social media and news sites, uses AI to analyze the collected data, and grasps current trends. Step 2: The generation unit generates storyboards based on the trends analyzed by the analysis unit. For example, the generation unit analyzes trends related to a specific genre or theme and generates storyboards using a generation AI based on the results. Step 3: The effect selection section automatically selects effects in conjunction with other editing software. For example, the effect selection section works with video editing software, and the AI ​​selects the optimal effect. Step 4: The BGM selection section automatically selects background music in conjunction with other editing software. For example, the BGM selection section works with video editing software, and the AI ​​selects the most suitable background music. Step 5: The composition proposal team proposes the video's structure. For example, the composition proposal team proposes a flow such as "introduction → build-up → conclusion." The composition proposal team uses AI to propose the video's structure. Step 6: The editorial department edits based on the structure proposed by the structure proposal department. For example, the editorial department edits according to the structure proposed by the AI. Step 7: The highlight generation unit generates highlight scenes that will capture the viewer's attention. For example, the highlight generation unit automatically selects scenes from the video that will attract the viewer's attention. Step 8: The catchphrase generation unit generates a catchphrase. The catchphrase generation unit generates, for example, a catchphrase that will attract the viewer's attention.

[0086] (Example of form 2) The video production system according to an embodiment of the present invention is a system for efficiently and quickly producing video content using generative AI. This video production system first uses AI to analyze the latest trends and generate storyboards according to genre. Next, it automatically selects effects and background music in cooperation with other editing software. Furthermore, it proposes an "introduction → build-up → conclusion" flow to simplify editing. Finally, it automatically generates highlight scenes and catchy slogans to attract the viewer's attention. This mechanism enables efficient and rapid video production and allows for the provision of attractive content that matches current trends. It also saves time and significantly reduces the burden of production. For example, the AI ​​analyzes the latest trends. In this process, it collects data from social media and news sites, and the AI ​​analyzes it to grasp current trends. For example, it analyzes trends related to a specific genre or theme and generates a storyboard based on the results. This makes it possible to produce content that matches trends. Next, it automatically selects effects and background music in cooperation with other editing software. For example, it cooperates with video editing software, and the AI ​​selects the optimal effects and background music. This streamlines the editing process and reduces the burden on creators. Furthermore, it proposes an "introduction → build-up → conclusion" structure, simplifying editing. For example, the AI ​​suggests the structure of a video, and creators can edit according to that suggestion, enabling efficient video production. This simplifies the editing process and saves time. Finally, it automatically generates highlight scenes and catchy slogans to attract viewers' attention. For example, the AI ​​automatically selects scenes from the video that will capture viewers' attention and generates catchy slogans to match those scenes. This allows for the creation of videos that capture viewers' interest. This system enables efficient and rapid video production, allowing for the delivery of engaging content that aligns with current trends. It also saves time and significantly reduces the burden of production. For example, it is an extremely useful tool for people who need efficient and high-quality content production, such as social media managers, marketers, and short video creators.This enables the video production system to produce videos efficiently and quickly, and to deliver engaging content that is in line with current trends.

[0087] The video production system according to this embodiment comprises an analysis unit, a generation unit, an effect selection unit, a background music (BGM) selection unit, a composition proposal unit, an editing unit, a highlight generation unit, and a catchphrase generation unit. The analysis unit analyzes trends. The analysis unit collects data from sources such as social media and news sites and analyzes trends. The analysis unit uses AI to analyze the collected data and grasp current trends. The generation unit generates storyboards based on the trends analyzed by the analysis unit. The generation unit analyzes trends related to a specific genre or theme and generates storyboards based on the results. The generation unit uses generation AI to generate storyboards. The effect selection unit automatically selects effects in cooperation with other editing software. The effect selection unit, for example, works with video editing software, and the AI ​​selects the optimal effect. The effect selection unit can also automatically select effects using AI. The BGM selection unit automatically selects background music (BGM) in cooperation with other editing software. The BGM selection unit, for example, works with video editing software, and the AI ​​selects the optimal BGM. The BGM selection unit can also automatically select background music using AI. The structure proposal unit proposes the structure of the video. The structure proposal unit proposes, for example, a flow of "introduction → build-up → conclusion". The structure proposal unit proposes the structure of the video using AI. The editing unit performs editing based on the structure proposed by the structure proposal unit. The editing unit performs editing according to, for example, the structure proposed by AI. The editing unit can also perform editing using AI. The highlight generation unit generates highlight scenes that attract the viewer's attention. The highlight generation unit automatically selects, for example, scenes from the video that will attract the viewer's attention. The highlight generation unit generates highlight scenes using AI. The catchphrase generation unit generates catchphrases. The catchphrase generation unit generates, for example, catchphrases that will attract the viewer's attention. The catchphrase generation unit generates catchphrases using AI. As a result, the video production system according to this embodiment enables efficient and rapid video production based on trends.

[0088] The analysis department analyzes trends. For example, it collects data from social media and news sites to analyze trends. Specifically, the analysis department uses crawlers to collect data from various internet platforms. These crawlers regularly visit social media and news sites to collect the latest posts and articles. The collected data is analyzed using natural language processing technology to extract trending keywords and topics. For example, it analyzes the frequency of specific hashtags in social media posts to understand current trends. It also analyzes news site articles to identify trending news topics. The analysis department uses AI to analyze the collected data and understand current trends. The AI ​​uses machine learning algorithms to predict trend fluctuations by comparing them with past data. For example, based on data from the past few months, if the frequency of a particular keyword has suddenly increased, it determines that the keyword is a current trend. Furthermore, the analysis department can monitor trend fluctuations in real time and issue alerts if there are sudden changes. This allows the analysis department to always grasp the latest trend information and reflect it in video production.

[0089] The generation unit generates storyboards based on trends analyzed by the analysis unit. For example, the generation unit analyzes trends related to a specific genre or theme and generates storyboards based on the results. Specifically, the generation unit determines the theme and storyline of the video based on the trend information provided by the analysis unit. The generation unit generates storyboards using a generation AI. The generation AI uses natural language generation technology to automatically generate storyboard scenarios based on trends. For example, if the trend is "environmental protection," the generation AI will propose a storyline related to environmental protection and generate detailed explanations for each scene. The generated storyboards serve as a guide for video production, clearly showing the content and order of each scene. Furthermore, the generation unit can also revise the storyboards based on user feedback. This allows the generation unit to quickly generate compelling storyboards that are in line with trends, improving the efficiency of video production.

[0090] The effects selection unit automatically selects effects in conjunction with other editing software. For example, it can work with video editing software, and AI can select the optimal effects. Specifically, the effects selection unit uses the video editing software's API to access the software's effect library. The AI ​​analyzes the storyboard content and scene characteristics to select the most suitable effects. For example, it might apply fade-in / fade-out effects to emotional scenes and speed-up or slow-motion effects to action scenes. The effects selection unit can also learn the user's preferences and past editing history to provide more personalized effect selections. As a result, the effects selection unit can automatically select the optimal effects to improve video quality, significantly increasing the efficiency of the editing process.

[0091] The BGM selection function automatically selects background music (BGM) in conjunction with other editing software. For example, it can work with video editing software, and its AI will select the most suitable BGM. Specifically, the BGM selection function uses the video editing software's API to access the BGM library within the software. The AI ​​analyzes the storyboard content and scene characteristics to select the most appropriate BGM. For example, it might select a calm piano piece for an emotional scene and a fast-paced rock song for an action scene. The BGM selection function can also learn the user's preferences and past editing history to provide more personalized BGM selections. Furthermore, the BGM selection function can adjust the timing of the BGM according to the video length and scene transitions. As a result, the BGM selection function can automatically select BGM to optimize the atmosphere of the video, significantly improving the efficiency of the editing process.

[0092] The video composition proposal team proposes the structure of the video. For example, they might suggest a flow such as "introduction → build-up → conclusion." Specifically, the team designs the overall structure of the video based on the content of the storyboard and trend information. AI learns from data of past successful videos and extracts effective structure patterns. For example, it suggests an effective introduction to capture the viewer's attention, a build-up to evoke emotion, and a conclusion to leave a strong impression on the viewer. The video composition proposal team can also revise the structure based on user feedback. This allows the team to propose effective video structures that capture the viewer's attention and improve the quality of video production.

[0093] The editorial team edits based on the structure proposed by the structure proposal team. For example, the editorial team edits according to a structure proposed by AI. Specifically, the editorial team decides on cuts and transitions for each scene based on the structure proposal provided by the structure proposal team. The AI ​​analyzes the content and trend information of each scene and selects the optimal editing method. For example, it applies smooth transitions to emotional scenes and dynamic cuts to action scenes. The editorial team can also revise the editing based on user feedback. This allows the editorial team to create effective edits that capture the viewer's attention and improve the quality of the video.

[0094] The highlight generation unit generates highlight scenes that capture the viewer's attention. For example, the highlight generation unit automatically selects scenes from a video that are likely to attract the viewer's attention. Specifically, the highlight generation unit uses AI to analyze viewer reactions to each scene in the video. Based on viewer eye-tracking data and click data, the AI ​​identifies scenes that viewers paid particular attention to. For example, it selects scenes that viewers watched for a long time or scenes with a high number of views as highlights. The highlight generation unit can also predict scenes that will attract viewer interest based on the video's content and trend information. As a result, the highlight generation unit can generate effective highlight scenes that capture the viewer's attention and enhance the video's appeal.

[0095] The catchphrase generation unit generates catchphrases. For example, it generates catchphrases that will attract the viewer's attention. Specifically, the catchphrase generation unit uses AI to analyze the video content and trend information to generate effective catchphrases. The AI ​​uses natural language generation technology to automatically generate short phrases that will capture the viewer's attention. For example, if the theme of the video is "environmental protection," it will generate a catchphrase such as "What we can do now to protect the future." The catchphrase generation unit can also revise catchphrases based on user feedback. As a result, the catchphrase generation unit can quickly generate effective catchphrases that attract the viewer's attention and improve the appeal of the video.

[0096] The analysis unit can collect data from social media and news sites and analyze trends. For example, the analysis unit collects data from social media and news sites and analyzes trends. The analysis unit uses AI to analyze the collected data and grasp current trends. This allows for the analysis of the latest trends by collecting data from social media and news sites. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input data collected from social media and news sites into a generating AI and have the generating AI perform the trend analysis.

[0097] The generation unit can analyze trends related to a specific genre or theme and generate storyboards based on the results. For example, the generation unit analyzes trends related to a specific genre or theme and generates storyboards based on the results. The generation unit generates storyboards using a generation AI. This makes it possible to generate storyboards tailored to a specific genre or theme. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit can input trend data related to a specific genre or theme into a generation AI and have the generation AI perform storyboard generation.

[0098] The effect selection unit can work in conjunction with video editing software to automatically select the optimal effect. For example, the effect selection unit can work in conjunction with video editing software, and AI can select the optimal effect. The effect selection unit can also automatically select effects using AI. This allows for the automatic selection of the optimal effect by working in conjunction with video editing software. Some or all of the above-described processes in the effect selection unit may be performed using AI or not. For example, the effect selection unit can input data obtained from video editing software into a generating AI and have the generating AI perform the effect selection.

[0099] The BGM selection unit can work in conjunction with video editing software to automatically select the optimal background music (BGM). For example, the BGM selection unit can work in conjunction with video editing software, and AI can select the optimal BGM. The BGM selection unit can also automatically select BGM using AI. This allows for the automatic selection of the optimal BGM by working in conjunction with video editing software. Some or all of the above-described processes in the BGM selection unit may be performed using AI or not. For example, the BGM selection unit can input data obtained from video editing software into a generating AI and have the generating AI perform the BGM selection.

[0100] The structure proposal unit can propose a flow of "introduction → build-up → conclusion". For example, the structure proposal unit proposes a flow of "introduction → build-up → conclusion". The structure proposal unit uses AI to propose the structure of the video. This simplifies the structure of the video by proposing a flow of "introduction → build-up → conclusion". Some or all of the above processing in the structure proposal unit may be performed using AI or not. For example, the structure proposal unit can input video structure data into a generating AI and have the generating AI execute a structure proposal.

[0101] The editorial department can perform editing based on the structure proposed by the structure proposal department. For example, the editorial department can perform editing according to a structure proposed by AI. The editorial department can also perform editing using AI. This makes the editing process more efficient by performing editing based on the structure proposed by the structure proposal department. Some or all of the above processes in the editorial department may be performed using AI or not. For example, the editorial department can input structure data obtained from the structure proposal department into a generation AI and have the generation AI perform the editing.

[0102] The highlight generation unit can automatically select scenes from a video that will attract the viewer's attention. For example, the highlight generation unit automatically selects scenes from a video that will attract the viewer's attention. The highlight generation unit generates highlight scenes using AI. This allows for the creation of compelling highlight scenes by automatically selecting scenes that will attract the viewer's attention. Some or all of the above-described processes in the highlight generation unit may be performed using AI or not. For example, the highlight generation unit can input video data into a generation AI and have the generation AI perform the selection of scenes that will attract the viewer's attention.

[0103] The catchphrase generation unit can generate catchphrases that attract the viewer's attention. For example, the catchphrase generation unit generates catchphrases that attract the viewer's attention. The catchphrase generation unit generates catchphrases using AI. This enhances the appeal of the video by generating catchphrases that attract the viewer's attention. Some or all of the above-described processes in the catchphrase generation unit may be performed using AI or not. For example, the catchphrase generation unit can input the video content into a generation AI and have the generation AI perform the generation of catchphrases.

[0104] The analysis unit can estimate the user's emotions and adjust the accuracy of the trend analysis based on the estimated emotions. For example, if the user is excited, the analysis unit can prioritize analyzing the latest trends and provide results quickly. If the user is relaxed, the analysis unit can also perform a detailed trend analysis and provide deeper insights. If the user is stressed, the analysis unit can also provide simple and intuitive trend analysis results. This allows for more appropriate trend analysis results by adjusting the accuracy of the trend analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the accuracy of the trend analysis.

[0105] The analysis unit can prioritize the analysis of trends based on specific regions or cultures. For example, the analysis unit can prioritize the collection of social media data from a specific region and analyze the trends in that region. The analysis unit can also prioritize the analysis of news sites related to a specific culture and grasp the trends of that culture. The analysis unit can also collect event information for each region and analyze trends specific to that region. By prioritizing the analysis of trends based on specific regions or cultures, it is possible to provide trend information tailored to specific regions and cultures. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input data related to a specific region or culture into a generating AI and have the generating AI perform trend analysis.

[0106] The analysis unit can predict future trends by referring to past trend data. For example, the analysis unit can analyze trend data from the past several years and predict seasonal trend patterns. The analysis unit can also predict the impact of specific events or occurrences on future trends based on past trend data. The analysis unit can also predict future trends for specific genres or themes by referring to past trend data. In this way, future trends can be predicted by referring to past trend data. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input past trend data into a generating AI and have the generating AI perform future trend predictions.

[0107] The analysis unit can estimate the user's emotions and adjust the order in which the trend analysis results are displayed based on the estimated user emotions. For example, if the user is excited, the analysis unit will display the most noteworthy trends first. If the user is relaxed, the analysis unit can also display detailed trend analysis results in a sequential order. If the user is stressed, the analysis unit can also display simple and important trends first. This allows the system to provide trend information to the user in the most optimal order by adjusting the order in which the trend analysis results are displayed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the display order of the trend analysis results.

[0108] The analysis unit can analyze trends specific to particular industries or fields. For example, the analysis unit can prioritize collecting SNS data from a specific industry and analyze trends in that industry. The analysis unit can also prioritize analyzing news sites related to a specific field and grasp trends in that field. The analysis unit can also collect event information for each industry and analyze trends specific to that industry. In this way, by analyzing trends specific to particular industries or fields, it can provide trend information specific to those fields. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input data related to a specific industry or field into a generating AI and have the generating AI perform trend analysis.

[0109] The analysis unit can analyze trends that are changing in real time. For example, the analysis unit can collect real-time SNS data and instantly analyze current trends. The analysis unit can also analyze news sites in real time to grasp the latest trends. The analysis unit can also collect real-time event information and analyze trends at that moment. In this way, by analyzing trends that are changing in real time, it can provide the latest trend information. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input real-time data into a generating AI and have the generating AI perform trend analysis.

[0110] The generation unit can estimate the user's emotions and adjust the storyboard content based on the estimated emotions. For example, if the user is relaxed, the generation unit can generate a storyboard that progresses at a leisurely pace. If the user is in a hurry, the generation unit can also generate a storyboard that emphasizes the shortest route. If the user is excited, the generation unit can also generate a storyboard with visually stimulating effects. This allows for the generation of more appropriate storyboards by adjusting the content based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI or not. For example, the generation unit can input user emotion data into a generation AI and have the generation AI perform storyboard content adjustments.

[0111] The generation unit can generate content tailored to a specific target audience. For example, to generate storyboards for young people, the generation unit can incorporate the latest trends and fashions. To generate storyboards for business professionals, the generation unit can include specialized information and data. To generate storyboards for seniors, the generation unit can provide simple and easy-to-understand content. In this way, by generating content tailored to a specific target audience, the generation unit can provide storyboards that are optimal for that target. Some or all of the above processes in the generation unit may be performed using AI or not. For example, the generation unit can input data about the target audience into a generation AI and have the generation AI perform the storyboard generation.

[0112] The generation unit can generate the optimal structure by referring to past success stories. For example, the generation unit can generate a new storyboard by referring to the storyboards of past successful videos. The generation unit can also extract the optimal structure for a specific genre or theme from past success stories. Based on past success stories, the generation unit can also generate a storyboard that incorporates elements that will attract the viewer's attention. In this way, the optimal structure can be generated by referring to past success stories. Some or all of the above processes in the generation unit may be performed using AI or not. For example, the generation unit can input past success story data into a generation AI and have the generation AI perform storyboard generation.

[0113] The generation unit can estimate the user's emotions and adjust the length of the storyboard based on the estimated emotions. For example, if the user is in a hurry, the generation unit can generate a short, concise storyboard. If the user is relaxed, the generation unit can also generate a longer storyboard with detailed explanations. If the user is excited, the generation unit can also generate a storyboard with visually stimulating effects. This allows for the generation of more appropriate storyboards by adjusting the length based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI or not. For example, the generation unit can input user emotion data into the generation AI and have the generation AI perform storyboard length adjustments.

[0114] The generation unit can generate content tailored to specific events or seasons. For example, it can generate storyboards tailored to seasonal events. It can also generate storyboards tailored to specific holidays. It can also generate storyboards that adapt to seasonal changes. By generating content tailored to specific events or seasons, it can provide storyboards that are optimal for those events or seasons. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit can input data related to specific events or seasons into a generation AI and have the generation AI perform storyboard generation.

[0115] The generation unit can generate content that combines multiple genres. For example, it can generate a storyboard that combines comedy and drama. It can also generate a storyboard that combines action and romance. It can also generate a storyboard that combines documentary and fiction. This allows for the provision of a wider variety of storyboards by generating content that combines multiple genres. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit can input data on multiple genres into a generation AI and have the generation AI perform the generation of storyboards.

[0116] The effect selection unit can estimate the user's emotions and adjust the selection of effects based on the estimated emotions. For example, if the user is relaxed, the effect selection unit will select a calming effect. If the user is excited, the effect selection unit may also select a visually stimulating effect. If the user is stressed, the effect selection unit may also select a simple and calming effect. This allows for the provision of more appropriate effects by adjusting the selection of effects based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the effect selection unit may be performed using AI or not. For example, the effect selection unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the effect selection.

[0117] The effect selection unit can prioritize selecting effects that match a specific theme or mood. For example, the effect selection unit can select effects that match the theme of a horror movie. It can also select effects that match a romantic mood. It can also select effects that match an action scene. By prioritizing the selection of effects that match a specific theme or mood, it is possible to provide effects that are optimal for that theme or mood. Some or all of the above processing in the effect selection unit may be performed using AI or not. For example, the effect selection unit can input data related to a specific theme or mood into a generating AI and have the generating AI perform the effect selection.

[0118] The effect selection unit can select the optimal effect by referring to past usage history. For example, the effect selection unit can suggest the optimal effect based on the effects the user has used in the past. The effect selection unit can also select the optimal effect for a specific scene from past usage history. The effect selection unit can also analyze past usage history and select effects that received a good response from viewers. In this way, the optimal effect can be selected by referring to past usage history. Some or all of the above processes in the effect selection unit may be performed using AI or not. For example, the effect selection unit can input past usage history data into a generating AI and have the generating AI perform the effect selection.

[0119] The effect selection unit can estimate the user's emotions and adjust the order in which effects are applied based on the estimated emotions. For example, if the user is relaxed, the effect selection unit may apply calming effects first. If the user is excited, the effect selection unit may also apply visually stimulating effects first. If the user is stressed, the effect selection unit may also apply simple and calming effects first. This allows for the provision of effects in a more appropriate order by adjusting the order of application based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the effect selection unit may be performed using AI or not. For example, the effect selection unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the order in which effects are applied.

[0120] The effect selection unit can select effects that match a specific visual style. For example, the effect selection unit can select effects that match a retro visual style. It can also select effects that match a modern visual style. It can also select effects that match a minimalist visual style. By selecting effects that match a specific visual style, it is possible to provide effects that are optimal for that visual style. Some or all of the above processing in the effect selection unit may be performed using AI or not. For example, the effect selection unit can input data about a specific visual style into a generating AI and have the generating AI perform the effect selection.

[0121] The effect selection unit can generate new effects by combining multiple effects. For example, the effect selection unit can generate a new effect by combining a glitch effect and a retro effect. It can also generate a new effect by combining a motion blur effect and a color filter. It can also generate a new effect by combining a light leak effect and a vignette effect. This allows for a wider variety of effects to be provided by combining multiple effects to generate new ones. Some or all of the above processing in the effect selection unit may be performed using AI or not. For example, the effect selection unit can input multiple effect data into a generation AI and have the generation AI execute the generation of a new effect.

[0122] The BGM selection unit can estimate the user's emotions and adjust the BGM selection based on the estimated emotions. For example, if the user is relaxed, the BGM selection unit can select calming BGM. If the user is excited, the BGM selection unit can also select upbeat BGM. If the user is stressed, the BGM selection unit can also select soothing BGM. In this way, by adjusting the BGM selection based on the user's emotions, more appropriate BGM can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the BGM selection unit may be performed using AI or not using AI. For example, the BGM selection unit can input user emotion data into a generative AI and have the generative AI perform the BGM selection adjustment.

[0123] The BGM selection unit can prioritize selecting background music that matches a specific scene or mood. For example, the BGM selection unit can select energetic background music to match an action scene. It can also select emotionally moving background music to match a romantic scene. It can also select upbeat background music to match a comedy scene. In this way, by prioritizing the selection of background music that matches a specific scene or mood, it is possible to provide background music that is optimal for that scene or mood. Some or all of the above processing in the BGM selection unit may be performed using AI, or it may be performed without using AI. For example, the BGM selection unit can input data about a specific scene or mood into a generating AI and have the generating AI perform the BGM selection.

[0124] The BGM selection unit can select the most suitable background music (BGM) by referring to past usage history. For example, the BGM selection unit can suggest the most suitable BGM based on the BGM the user has used in the past. The BGM selection unit can also select the most suitable BGM for a specific scene from past usage history. The BGM selection unit can also analyze past usage history and select BGM that received a good response from viewers. In this way, the most suitable BGM can be selected by referring to past usage history. Some or all of the above processes in the BGM selection unit may be performed using AI, or they may not be performed using AI. For example, the BGM selection unit can input past usage history data into a generating AI and have the generating AI perform the BGM selection.

[0125] The BGM selection unit can estimate the user's emotions and adjust the order in which the background music is applied based on the estimated emotions. For example, if the user is relaxed, the BGM selection unit may apply calm background music first. If the user is excited, the BGM selection unit may also apply upbeat background music first. If the user is stressed, the BGM selection unit may also apply calming background music first. In this way, by adjusting the order in which the background music is applied based on the user's emotions, background music can be provided in a more appropriate order. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the BGM selection unit may be performed using AI or not using AI. For example, the BGM selection unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the BGM application order.

[0126] The BGM selection unit can select background music (BGM) that specializes in a particular genre or artist. For example, the BGM selection unit can select BGM that specializes in the rock genre. The BGM selection unit can also select BGM that specializes in classical music artists. The BGM selection unit can also select BGM that specializes in the pop music genre. This allows the system to provide BGM that is optimal for a particular genre or artist by selecting BGM that specializes in that genre or artist. Some or all of the above processing in the BGM selection unit may be performed using AI, or it may be performed without AI. For example, the BGM selection unit can input data about a specific genre or artist into a generating AI and have the generating AI perform the BGM selection.

[0127] The BGM selection unit can generate new background music by combining multiple BGM tracks. For example, the BGM selection unit can combine classical music and electronica to generate new BGM. It can also combine jazz and hip hop to generate new BGM. It can also combine rock and pop to generate new BGM. This allows for a wider variety of background music to be provided by combining multiple BGM tracks to generate new BGM. Some or all of the above processing in the BGM selection unit may be performed using AI or not. For example, the BGM selection unit can input multiple BGM data into a generation AI and have the generation AI perform the generation of new BGM.

[0128] The configuration suggestion unit can estimate the user's emotions and adjust the suggested configuration based on those emotions. For example, if the user is relaxed, the configuration suggestion unit can suggest a configuration that proceeds at a leisurely pace. If the user is in a hurry, the configuration suggestion unit can also suggest a configuration that emphasizes the shortest route. If the user is excited, the configuration suggestion unit can also suggest a configuration that includes visually stimulating effects. In this way, by adjusting the suggested configuration based on the user's emotions, a more appropriate configuration can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the configuration suggestion unit may be performed using AI or not. For example, the configuration suggestion unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the suggested configuration.

[0129] The program proposal unit can propose programs tailored to specific target audiences. For example, to propose a program for young people, the program proposal unit can incorporate the latest trends and fashions. To propose a program for business professionals, the program proposal unit can include specialized information and data. To propose a program for seniors, the program proposal unit can provide simple and easy-to-understand content. In this way, by proposing a program tailored to a specific target audience, the program can provide the most suitable program for that target audience. Some or all of the above processes in the program proposal unit may be performed using AI or not. For example, the program proposal unit can input data about the target audience into a generating AI and have the generating AI execute program proposals.

[0130] The structure proposal unit can propose the optimal structure by referring to past successful cases. For example, the structure proposal unit can propose a new structure by referring to the structure of a past successful video. The structure proposal unit can also extract the optimal structure for a specific genre or theme from past successful cases. Based on past successful cases, the structure proposal unit can also propose a structure that incorporates elements that will attract the viewer's interest. In this way, the optimal structure can be proposed by referring to past successful cases. Some or all of the above processes in the structure proposal unit may be performed using AI or not. For example, the structure proposal unit can input past successful case data into a generating AI and have the generating AI execute structure proposals.

[0131] The configuration suggestion unit can estimate the user's emotions and adjust the order of suggested configurations based on the estimated emotions. For example, if the user is relaxed, the configuration suggestion unit may first suggest configurations that proceed at a leisurely pace. If the user is in a hurry, the configuration suggestion unit may first suggest configurations that emphasize the shortest route. If the user is excited, the configuration suggestion unit may first suggest configurations that include visually stimulating effects. This allows for the provision of configurations in a more appropriate order by adjusting the order of suggested configurations based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the configuration suggestion unit may be performed using AI or not. For example, the configuration suggestion unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the suggested configuration order.

[0132] The configuration proposal unit can propose configurations tailored to specific events or seasons. For example, it can propose configurations tailored to seasonal events. It can also propose configurations tailored to specific holidays. It can also propose configurations that adapt to seasonal changes. In this way, by proposing configurations tailored to specific events or seasons, it can provide the optimal configuration for events or seasons. Some or all of the above processing in the configuration proposal unit may be performed using AI or not. For example, the configuration proposal unit can input data related to specific events or seasons into a generating AI and have the generating AI execute configuration proposals.

[0133] The composition proposal unit can propose compositions that combine multiple genres. For example, it can propose a composition that combines comedy and drama. It can also propose a composition that combines action and romance. It can also propose a composition that combines documentary and fiction. By proposing compositions that combine multiple genres, it can provide a wider variety of compositions. Some or all of the above processing in the composition proposal unit may be performed using AI or not. For example, the composition proposal unit can input data on multiple genres into a generating AI and have the generating AI execute composition proposals.

[0134] The editorial team can estimate the user's emotions and adjust the content of the edit based on those emotions. For example, if the user is relaxed, the editorial team can edit at a leisurely pace. If the user is in a hurry, the editorial team can also edit to emphasize the shortest route. If the user is excited, the editorial team can add visually stimulating effects to the edit. This allows for more appropriate editing by adjusting the content based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the editorial team may be performed using AI or not. For example, the editorial team can input user emotion data into a generative AI and have the generative AI perform the editing content adjustments.

[0135] The editorial team can tailor its content to a specific target audience. For example, to create content for a younger audience, the team can incorporate the latest trends and fashions. To create content for business professionals, the team can include specialized information and data. To create content for seniors, the team can provide simple and easy-to-understand content. By tailoring the content to a specific target audience, the team can provide content that is optimal for that target. Some or all of the processes described above in the editorial team may be performed using AI, or not. For example, the editorial team can input data about the target audience into a generative AI and have the generative AI perform the editing.

[0136] The editorial team can perform optimal editing by referring to past success stories. For example, the editorial team can create new edits by referencing the editing of past successful videos. The editorial team can also extract the most suitable editing for a specific genre or theme from past success stories. The editorial team can also create edits that incorporate elements that will attract viewers' attention, based on past success stories. In this way, optimal editing can be performed by referring to past success stories. Some or all of the above processes in the editorial team may be performed using AI or not. For example, the editorial team can input past success story data into a generating AI and have the generating AI perform the editing.

[0137] The editorial team can estimate the user's emotions and adjust the editing order based on those emotions. For example, if the user is relaxed, the editorial team might start with editing that proceeds at a leisurely pace. If the user is in a hurry, the editorial team might start with editing that emphasizes the shortest route. If the user is excited, the editorial team might start with editing that adds visually stimulating effects. This allows for a more appropriate order of editing by adjusting the editing order based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the editorial team may be performed using AI or not. For example, the editorial team can input user emotion data into a generative AI and have the generative AI perform the editing order adjustment.

[0138] The editorial department can perform editing tailored to specific events or seasons. For example, the editorial department can perform editing tailored to seasonal events. The editorial department can also perform editing tailored to specific holidays. The editorial department can also perform editing in accordance with seasonal changes. This allows for the provision of editing that is optimal for specific events or seasons. Some or all of the above processes performed by the editorial department may be performed using AI or not. For example, the editorial department can input data related to specific events or seasons into a generating AI and have the generating AI perform the editing.

[0139] The editorial department can combine multiple editing techniques to create new edits. For example, the editorial department can combine cut editing and transitions to create new edits. The editorial department can also combine effects editing and color grading to create new edits. The editorial department can also combine motion graphics and text animation to create new edits. This allows for a wider variety of edits to be offered by combining multiple editing techniques. Some or all of the above processes in the editorial department may be performed using AI or not. For example, the editorial department can input data on multiple editing techniques into a generating AI and have the generating AI perform the new edits.

[0140] The highlight generation unit can estimate the user's emotions and adjust the selection of highlight scenes based on the estimated emotions. For example, if the user is relaxed, the highlight generation unit may select calm scenes as highlights. If the user is excited, the highlight generation unit may also select visually stimulating scenes as highlights. If the user is stressed, the highlight generation unit may also select simple and calming scenes as highlights. This allows for the provision of more appropriate highlight scenes by adjusting the selection of highlight scenes based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the highlight generation unit may be performed using AI or not. For example, the highlight generation unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of highlight scene selection.

[0141] The highlight generation unit can generate highlight scenes tailored to a specific target audience. For example, to generate highlight scenes for younger audiences, the highlight generation unit can incorporate the latest trends and fashions. To generate highlight scenes for business professionals, the highlight generation unit can include specialized information and data. To generate highlight scenes for older adults, the highlight generation unit can provide simple and easy-to-understand content. In this way, by generating highlight scenes tailored to a specific target audience, the system can provide highlight scenes that are optimal for that target. Some or all of the above-described processes in the highlight generation unit may be performed using AI or not. For example, the highlight generation unit can input data about the target audience into a generation AI and have the generation AI perform the generation of highlight scenes.

[0142] The highlight generation unit can generate optimal highlight scenes by referring to past successful examples. For example, the highlight generation unit can generate new highlight scenes by referencing highlight scenes from past successful videos. The highlight generation unit can also extract the most suitable highlight scenes for a specific genre or theme from past successful examples. Based on past successful examples, the highlight generation unit can also generate highlight scenes that incorporate elements that will attract viewers' attention. In this way, optimal highlight scenes can be generated by referring to past successful examples. Some or all of the above processes in the highlight generation unit may be performed using AI or not. For example, the highlight generation unit can input past successful example data into a generation AI and have the generation AI perform the generation of highlight scenes.

[0143] The highlight generation unit can estimate the user's emotions and adjust the order of highlight scenes based on the estimated emotions. For example, if the user is relaxed, the highlight generation unit may select calm scenes as the first highlights. If the user is excited, the highlight generation unit may also select visually stimulating scenes as the first highlights. If the user is stressed, the highlight generation unit may also select simple and calming scenes as the first highlights. This allows for the provision of highlight scenes in a more appropriate order by adjusting the order of highlight scenes based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the highlight generation unit may be performed using AI or not. For example, the highlight generation unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the order of highlight scenes.

[0144] The highlight generation unit can generate highlight scenes tailored to specific events or seasons. For example, it can generate highlight scenes tailored to seasonal events. It can also generate highlight scenes tailored to specific holidays. It can also generate highlight scenes that correspond to seasonal changes. In this way, by generating highlight scenes tailored to specific events or seasons, it can provide highlight scenes that are optimal for events or seasons. Some or all of the above-described processes in the highlight generation unit may be performed using AI or not. For example, the highlight generation unit can input data related to specific events or seasons into a generation AI and have the generation AI execute the generation of highlight scenes.

[0145] The highlight generation unit can generate new highlight scenes by combining multiple scenes. For example, it can combine action scenes and romance scenes to generate a new highlight scene. It can also combine comedy scenes and drama scenes to generate a new highlight scene. It can also combine documentary scenes and fiction scenes to generate a new highlight scene. This allows for a wider variety of highlight scenes to be provided by combining multiple scenes to generate a new highlight scene. Some or all of the above-described processes in the highlight generation unit may be performed using AI or not. For example, the highlight generation unit can input multiple scene data into a generation AI and have the generation AI perform the generation of a new highlight scene.

[0146] The tagline generation unit can estimate the user's emotions and adjust the content of the tagline based on the estimated emotions. For example, if the user is relaxed, the tagline generation unit will generate a tagline in a calm tone. If the user is excited, the tagline generation unit can also generate a visually stimulating tagline. If the user is stressed, the tagline generation unit can also generate a simple and calming tagline. In this way, by adjusting the content of the tagline based on the user's emotions, a more appropriate tagline can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the tagline generation unit may be performed using AI or not using AI. For example, the tagline generation unit can input user emotion data into the generation AI and have the generation AI perform the adjustment of the tagline content.

[0147] The tagline generation unit can generate taglines tailored to specific target audiences. For example, to generate taglines for young people, the tagline generation unit can incorporate the latest trends and fashions. To generate taglines for business professionals, the tagline generation unit can also include specialized information and data. To generate taglines for seniors, the tagline generation unit can provide simple and easy-to-understand content. In this way, by generating taglines tailored to specific target audiences, the unit can provide taglines that are optimal for the target. Some or all of the above-described processes in the tagline generation unit may be performed using AI or not. For example, the tagline generation unit can input data about the target audience into a generation AI and have the generation AI perform the tagline generation.

[0148] The catchphrase generation unit can generate the optimal catchphrase by referring to past success stories. For example, the catchphrase generation unit can generate a new catchphrase by referring to past successful catchphrases. The catchphrase generation unit can also extract the optimal catchphrase for a specific genre or theme from past success stories. The catchphrase generation unit can also generate a catchphrase that incorporates elements that will attract the viewer's attention, based on past success stories. In this way, the optimal catchphrase can be generated by referring to past success stories. Some or all of the above processes in the catchphrase generation unit may be performed using AI or not. For example, the catchphrase generation unit can input past success story data into a generation AI and have the generation AI perform the catchphrase generation.

[0149] The tagline generation unit can estimate the user's emotions and adjust the order of taglines based on the estimated emotions. For example, if the user is relaxed, the tagline generation unit may display a calm-toned tagline first. If the user is excited, the tagline generation unit may also display a visually stimulating tagline first. If the user is stressed, the tagline generation unit may also display a simple and calming tagline first. This allows for the provision of taglines in a more appropriate order by adjusting the order based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the tagline generation unit may be performed using AI or not. For example, the tagline generation unit can input user emotion data into the generative AI and have the generative AI perform the tagline order adjustment.

[0150] The catchphrase generation unit can generate catchphrases tailored to specific events or seasons. For example, it can generate catchphrases tailored to seasonal events. It can also generate catchphrases tailored to specific holidays. It can also generate catchphrases that respond to seasonal changes. By generating catchphrases tailored to specific events or seasons, it can provide catchphrases that are optimal for those events or seasons. Some or all of the above-described processes in the catchphrase generation unit may be performed using AI or not. For example, the catchphrase generation unit can input data related to specific events or seasons into a generation AI and have the generation AI perform the catchphrase generation.

[0151] The catchphrase generation unit can generate new catchphrases by combining multiple existing catchphrases. For example, it can combine a visually stimulating catchphrase with a catchphrase with a gentle tone to generate a new catchphrase. It can also combine a simple catchphrase with a detailed catchphrase to generate a new catchphrase. Furthermore, it can combine past successful catchphrases with new ideas to generate a new catchphrase. This allows for a wider variety of catchphrases to be provided by combining multiple catchphrases to generate a new catchphrase. Some or all of the above-described processes in the catchphrase generation unit may be performed using AI or not. For example, the catchphrase generation unit can input data from multiple catchphrases into a generation AI and have the generation AI perform the generation of a new catchphrase.

[0152] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0153] The analysis unit can analyze a user's past viewing history and improve the accuracy of trend analysis based on that history. For example, it can analyze the genres and themes of videos a user has watched in the past and predict trends based on those tendencies. The analysis unit can also extract the characteristics of content that a user frequently watches and perform trend analysis based on that. This makes it possible to perform trend analysis based on the user's viewing history and provide more personalized trend information.

[0154] The generation unit can estimate the user's emotions and adjust the tempo of the storyboards based on those emotions. For example, if the user is relaxed, it can generate storyboards with a slow tempo. If the user is excited, it can generate storyboards with a faster tempo. This improves the viewing experience by providing storyboards with a tempo that matches the user's emotions.

[0155] The effect selection section allows you to layer multiple effects to emphasize specific visual effects. For example, you can combine a glitch effect and a color filter to create a visually impactful effect. The effect selection section can also combine motion blur and particle effects to highlight dynamic scenes. This allows for a wider variety of visual effects by combining multiple effects.

[0156] The background music (BGM) selection unit can estimate the user's emotions and adjust the BGM volume based on those estimates. For example, if the user is relaxed, calming BGM can be played at a low volume. If the user is excited, upbeat BGM can be played at a high volume. This allows for BGM volume adjustment according to the user's emotions, providing a more appropriate sound experience.

[0157] The composition proposal department can propose compositions that incorporate specific storytelling techniques. For example, they can propose a composition using flashbacks, inserting scenes that look back on past events. The composition proposal department can also propose a composition using time leaps, creating a story that moves back and forth through time. In this way, by proposing compositions that incorporate specific storytelling techniques, it is possible to produce videos that capture the viewer's interest.

[0158] The editorial team can estimate the user's emotions and adjust the editing style based on those estimates. For example, if the user is relaxed, they might use editing with many smooth transitions. If the user is excited, they might use dynamic editing with many cuts. This allows them to provide an editing style that matches the user's emotions, thereby improving the viewing experience.

[0159] The highlight generation unit can generate highlight scenes tailored to specific audience demographics. For example, it can generate highlights that emphasize action scenes for younger audiences, or highlights that emphasize scenes containing important information for business professionals. By providing highlight scenes tailored to specific audiences, it is possible to capture their attention.

[0160] The tagline generation unit can estimate the user's emotions and adjust the font and color of the tagline based on those emotions. For example, if the user is relaxed, it can use calm colors and a soft font. If the user is excited, it can use bright colors and a strong font. This allows for a more visually impactful tagline design that responds to the user's emotions.

[0161] The analysis unit can analyze trends based on specific keywords. For example, it can analyze keywords related to specific product names or brand names to understand their trends. The analysis unit can also analyze keywords related to specific events or campaigns and evaluate their impact. This enables trend analysis based on specific keywords, allowing for the provision of more accurate trend information.

[0162] The generation unit can estimate the user's emotions and adjust the visual style of the storyboard based on those emotions. For example, if the user is relaxed, it can use calm colors and a soft visual style. If the user is excited, it can use vibrant colors and a dynamic visual style. This enhances the visual appeal of storyboards by providing them with visual styles that match the user's emotions.

[0163] The following briefly describes the processing flow for example form 2.

[0164] Step 1: The analysis unit analyzes trends. The analysis unit collects data from sources such as social media and news sites, uses AI to analyze the collected data, and grasps current trends. Step 2: The generation unit generates storyboards based on the trends analyzed by the analysis unit. For example, the generation unit analyzes trends related to a specific genre or theme and generates storyboards using a generation AI based on the results. Step 3: The effect selection section automatically selects effects in conjunction with other editing software. For example, the effect selection section works with video editing software, and the AI ​​selects the optimal effect. Step 4: The BGM selection section automatically selects background music in conjunction with other editing software. For example, the BGM selection section works with video editing software, and the AI ​​selects the most suitable background music. Step 5: The composition proposal team proposes the video's structure. For example, the composition proposal team proposes a flow such as "introduction → build-up → conclusion." The composition proposal team uses AI to propose the video's structure. Step 6: The editorial department edits based on the structure proposed by the structure proposal department. For example, the editorial department edits according to the structure proposed by the AI. Step 7: The highlight generation unit generates highlight scenes that will capture the viewer's attention. For example, the highlight generation unit automatically selects scenes from the video that will attract the viewer's attention. Step 8: The catchphrase generation unit generates a catchphrase. The catchphrase generation unit generates, for example, a catchphrase that will attract the viewer's attention.

[0165] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0166] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, 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), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0167] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0168] Each of the multiple elements described above, including the analysis unit, generation unit, effect selection unit, BGM selection unit, configuration proposal unit, editing unit, highlight generation unit, and catchphrase generation unit, is implemented by, for example, at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing device 12. The effect selection unit and BGM selection unit are implemented by, for example, the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The configuration proposal unit and editing unit are implemented by, for example, the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The highlight generation unit and catchphrase generation unit are implemented by, for example, the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0169] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0170] As shown in Figure 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.

[0171] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0172] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0173] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0175] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0176] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0177] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0178] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0179] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0180] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0181] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0182] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0183] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0184] Each of the multiple elements described above, including the analysis unit, generation unit, effect selection unit, BGM selection unit, configuration proposal unit, editing unit, highlight generation unit, and catchphrase generation unit, is implemented by, for example, at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing device 12. The effect selection unit and BGM selection unit are implemented by, for example, the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The configuration proposal unit and editing unit are implemented by, for example, the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The highlight generation unit and catchphrase generation unit are implemented by, for example, the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0185] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0186] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0187] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0188] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0189] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0190] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0191] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0192] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0193] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0194] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0195] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0196] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0197] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0198] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0199] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0200] Each of the multiple elements described above, including the analysis unit, generation unit, effect selection unit, BGM selection unit, configuration proposal unit, editing unit, highlight generation unit, and catchphrase generation unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12. The effect selection unit and BGM selection unit are implemented by, for example, the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The configuration proposal unit and editing unit are implemented by, for example, the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The highlight generation unit and catchphrase generation unit are implemented by, for example, the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0201] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0202] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0203] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0204] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0205] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0206] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0207] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0208] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0209] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0210] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0211] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0212] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0213] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0214] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0215] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0216] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0217] Each of the multiple elements described above, including the analysis unit, generation unit, effect selection unit, BGM selection unit, configuration proposal unit, editing unit, highlight generation unit, and catchphrase generation unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12. The effect selection unit and BGM selection unit are implemented by, for example, the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The configuration proposal unit and editing unit are implemented by, for example, the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The highlight generation unit and catchphrase generation unit are implemented by, for example, the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0218] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0219] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0220] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0221] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0222] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0223] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0224] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0225] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0226] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0227] 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.

[0228] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0229] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0230] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0231] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0232] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0233] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0234] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0235] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0236] (Note 1) The analysis unit analyzes trends, A generation unit that generates a storyboard based on the trend analyzed by the analysis unit, An effect selection section that automatically selects effects in conjunction with other editing software, A BGM selection section that automatically selects background music in conjunction with other editing software, The composition proposal department proposes the structure of the video, An editorial department that performs editing based on the configuration proposed by the aforementioned configuration proposal department, A highlight generation unit that generates highlight scenes that attract the viewer's attention, A catchphrase generation unit that generates catchphrases, A system characterized by the following features. (Note 2) The aforementioned analysis unit, We collect data from social media and news sites and analyze trends. The system described in Appendix 1, characterized by the features described herein. (Note 3) The generating unit is Analyze trends related to specific genres or themes, and generate storyboards based on the results. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned effect selection unit is It integrates with video editing software and automatically selects the optimal effects. The system described in Appendix 1, characterized by the features described herein. (Note 5) The BGM selection unit is, It integrates with video editing software to automatically select the most suitable background music. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned configuration proposal unit is I propose a flow of "introduction → build-up → conclusion". The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned editorial department, Editing is performed based on the configuration proposed by the aforementioned configuration proposal unit. The system described in Appendix 1, characterized by the features described herein. (Note 8) The highlight generation unit, Automatically selects scenes from a video that will capture the viewer's attention. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned catchphrase generation unit, Generate catchy slogans that will grab the viewer's attention. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, It estimates user sentiment and adjusts the accuracy of trend analysis based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, Prioritize analyzing trends based on specific regions or cultures. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, Predicting future trends by referring to past trend data. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, It estimates user sentiment and adjusts the order in which trend analysis results are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, Analyzing trends specific to particular industries or fields. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, Analyze trends that are changing in real time. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is The system estimates the user's emotions and adjusts the storyboard content based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is Generate content tailored to a specific target audience. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is By referring to past success stories, we can generate the optimal configuration. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is It estimates the user's emotions and adjusts the length of the storyboard based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is Generate content tailored to specific events or seasons. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is Generate content that combines multiple genres. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned effect selection unit is It estimates the user's emotions and adjusts the selection of effects based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned effect selection unit is Prioritize selecting effects that match a specific theme or mood. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned effect selection unit is Refer to your past usage history to select the most suitable effect. The system described in Appendix 1, characterized by the features described herein. (Appendix 25) The effect selection unit estimates the user's emotion and adjusts the application order of effects based on the estimated user's emotion The system according to Appendix 1, characterized in that (Appendix 26) The effect selection unit selects an effect that matches a specific visual style The system according to Appendix 1, characterized in that (Appendix 27) The effect selection unit combines multiple effects to generate a new effect The system according to Appendix 1, characterized in that (Appendix 28) The BGM selection unit estimates the user's emotion and adjusts the selection of BGM based on the estimated user's emotion The system according to Appendix 1, characterized in that (Appendix 29) The BGM selection unit preferably selects a BGM that matches a specific scene or mood The system according to Appendix 1, characterized in that (Appendix 30) The BGM selection unit selects the optimal BGM by referring to the past usage history The system according to Appendix 1, characterized in that (Appendix 31) The BGM selection unit estimates the user's emotion and adjusts the application order of BGM based on the estimated user's emotion The system according to Appendix 1, characterized in that (Appendix 32) The BGM selection unit selects a BGM specialized for a specific genre or artist The system according to Appendix 1, characterized in that (Appendix 33) The BGM selection unit Generating a new BGM by combining multiple BGMs The system according to appendix 1, characterized by the above. (Appendix 34) The configuration proposal department Estimates the user's emotions and adjusts the proposed content of the configuration based on the estimated user's emotions The system according to appendix 1, characterized by the above. (Appendix 35) The configuration proposal department Proposes a configuration suitable for a specific target audience The system according to appendix 1, characterized by the above. (Appendix 36) The configuration proposal department Refers to past successful cases and proposes an optimal configuration The system according to appendix 1, characterized by the above. (Appendix 37) The configuration proposal department Estimates the user's emotions and adjusts the order of proposed configurations based on the estimated user's emotions The system according to appendix 1, characterized by the above. (Appendix 38) The configuration proposal department Proposes a configuration suitable for a specific event or season The system according to appendix 1, characterized by the above. (Appendix 39) The configuration proposal department Proposes a configuration combining multiple genres The system according to appendix 1, characterized by the above. (Appendix 40) The editing department Estimates the user's emotions and adjusts the content of the editing based on the estimated user's emotions The system according to appendix 1, characterized by the above. (Appendix 41) The editing department Performs editing suitable for a specific target audience The system according to appendix 1, characterized by the above. (Supplementary Note 42) The editing unit performs optimal editing by referring to past successful cases The system according to Supplementary Note 1, characterized in that. (Supplementary Note 43) The editing unit estimates the user's emotion and adjusts the order of editing based on the estimated user's emotion The system according to Supplementary Note 1, characterized in that. (Supplementary Note 44) The editing unit performs editing according to specific events or seasons The system according to Supplementary Note 1, characterized in that. (Supplementary Note 45) The editing unit performs new editing by combining multiple editing methods The system according to Supplementary Note 1, characterized in that. (Supplementary Note 46) The highlight generation unit estimates the user's emotion and adjusts the selection of highlight scenes based on the estimated user's emotion The system according to Supplementary Note 1, characterized in that. (Supplementary Note 47) The highlight generation unit generates highlight scenes according to a specific target audience The system according to Supplementary Note 1, characterized in that. (Supplementary Note 48) The highlight generation unit generates optimal highlight scenes by referring to past successful cases The system according to Supplementary Note 1, characterized in that. (Supplementary Note 49) The highlight generation unit estimates the user's emotion and adjusts the order of highlight scenes based on the estimated user's emotion The system according to Supplementary Note 1, characterized in that. (Supplementary Note 50) The highlight generation unit Generate highlight scenes tailored to specific events or seasons. The system described in Appendix 1, characterized by the features described herein. (Note 51) The highlight generation unit, Combine multiple scenes to generate a new highlight scene. The system described in Appendix 1, characterized by the features described herein. (Note 52) The aforementioned catchphrase generation unit, The system estimates the user's emotions and adjusts the content of the tagline based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 53) The aforementioned catchphrase generation unit, Generate taglines tailored to specific target audiences. The system described in Appendix 1, characterized by the features described herein. (Note 54) The aforementioned catchphrase generation unit, By referring to past success stories, we can generate the optimal tagline. The system described in Appendix 1, characterized by the features described herein. (Note 55) The aforementioned catchphrase generation unit, It estimates the user's emotions and adjusts the order of taglines based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 56) The aforementioned catchphrase generation unit, Generate catchy slogans tailored to specific events or seasons. The system described in Appendix 1, characterized by the features described herein. (Note 57) The aforementioned catchphrase generation unit, Combine multiple taglines to generate a new tagline. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0237] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The analysis unit analyzes trends, A generation unit that generates a storyboard based on the trend analyzed by the analysis unit, An effect selection section that automatically selects effects in conjunction with other editing software, A BGM selection section that automatically selects background music in conjunction with other editing software, The composition proposal department proposes the structure of the video, An editorial department that performs editing based on the configuration proposed by the aforementioned configuration proposal department, A highlight generation unit that generates highlight scenes that attract the viewer's attention, A catchphrase generation unit that generates catchphrases, A system characterized by the following features.

2. The aforementioned analysis unit, We collect data from social media and news sites and analyze trends. The system according to feature 1.

3. The generating unit is Analyze trends related to specific genres or themes, and generate storyboards based on the results. The system according to feature 1.

4. The aforementioned effect selection unit is It integrates with video editing software and automatically selects the optimal effects. The system according to feature 1.

5. The BGM selection unit is, It integrates with video editing software to automatically select the most suitable background music. The system according to feature 1.

6. The aforementioned editorial department, Editing is performed based on the configuration proposed by the aforementioned configuration proposal unit. The system according to feature 1.

7. The highlight generation unit, Automatically selects scenes from a video that will capture the viewer's attention. The system according to feature 1.

Images