System

Abstract

An object of the system according to the embodiment is to automatically extract summary points of a moving image and efficiently generate a digest version.SOLUTION: A system according to an embodiment includes a video analysis unit, a summary extraction unit, a digest generation unit, and a distribution unit. The moving image analysis unit analyzes a moving image. The summary extraction unit extracts an important point from the moving image analyzed by the moving image analysis unit. The digest generation unit generates a digest version based on the summary points extracted by the summary extraction unit. The distribution unit distributes the digest version generated by the digest generation unit and the original full version of the moving image.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the problem that video editing requires a great deal of time and effort.

[0005] The system according to the embodiment aims to automatically extract summary points of a video and efficiently generate a digest version. [Means for solving the problem]

[0006] The system according to the embodiment includes a video analysis unit, a summary extraction unit, a digest generation unit, and a distribution unit. The video analysis unit analyzes a video. The summary extraction unit extracts important points from the video analyzed by the video analysis unit. The digest generation unit generates a digest version based on the summary points extracted by the summary extraction unit. The distribution unit distributes the digest version generated by the digest generation unit and the original full version of the video. [Effects of the Invention]

[0007] The system according to the embodiment can automatically extract summary points of a video and efficiently generate a digest version. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) The video editing system according to an embodiment of the present invention uses a generation AI to analyze a video and automatically generate a digest version that focuses on key points for summarization. This makes the video editing process more efficient and enables efficient distribution that meets the needs of viewers.

[0029] A video editing system according to an embodiment includes a video analysis unit, a summary extraction unit, a digest generation unit, and a distribution unit. The video analysis unit analyzes a video. For example, the video analysis unit performs frame analysis to analyze the content of each frame. The video analysis unit can also perform object detection to identify important objects within a video. The video analysis unit can also perform motion detection to analyze movement patterns within a video. The summary extraction unit extracts important points from the video analyzed by the video analysis unit. For example, the summary extraction unit extracts important points based on the viewer's interest level. The summary extraction unit can also extract important points based on playback time. The summary extraction unit can also extract important points based on specific keywords. The digest generation unit generates a digest version based on the summary points extracted by the summary extraction unit. For example, the digest generation unit generates a digest version by adjusting the length of the summary. The digest generation unit can also generate a digest version based on selection criteria for included scenes. The digest generation unit can also generate a digest version by adding visual effects. The distribution unit distributes the digest version generated by the digest generation unit and the original full version of the video. For example, the distribution unit selects a distribution platform to distribute the video. The distribution unit can also adjust the distribution format to distribute the video. The distribution unit can also adjust the distribution timing to distribute the video. As a result, the video editing system according to the embodiment can improve the efficiency of video editing work and realize efficient distribution that suits the viewer's convenience.

[0030] The video analysis unit can analyze audio data and extract important points based on the speaker's emotions and tone. For example, the video analysis unit uses generative AI to analyze the audio data of a video and extract important points based on the speaker's emotions and tone. For example, it identifies parts that the speaker emphasizes or parts where the speaker's emotions are high, and extracts those parts as summary points. The video analysis unit can also use speech recognition technology to convert audio data into text data and perform emotion analysis. For example, it analyzes the pitch and speed of the audio and assigns emotion labels. The video analysis unit can also perform tone analysis and extract important points based on changes in the speaker's tone. This makes it possible to extract important points based on the speaker's emotions and tone.

[0031] The video analysis unit can analyze slides and graphs to extract visually important information. For example, the video analysis unit uses generative AI to analyze slides and graphs in a video and extract visually important information. For example, it determines summary points based on slide titles and graph peak values. The video analysis unit can also use image recognition technology to convert the contents of slides and graphs into text data and extract important information. For example, it can extract text from slides and evaluate its importance. The video analysis unit can also analyze visual features and extract important information based on color emphasis and shape features. This makes it possible to extract visually important information from slides and graphs.

[0032] The summary extraction unit can analyze subtitle data and automatically generate summary points in different languages. For example, the summary extraction unit uses a generation AI to analyze video subtitle data and automatically generate summary points in different languages. For example, it analyzes English subtitle data and generates summary points in Japanese, French, etc. The summary extraction unit can also analyze subtitle data using text analysis technology and extract keywords. For example, it can extract important keywords in subtitles and generate summary points based on them. The summary extraction unit can also translate subtitle data into different languages ​​using language translation technology and generate summary points based on the translated data. This allows for the automatic generation of summary points in different languages.

[0033] The summary extraction unit can analyze background sounds and sound effects and identify important scenes. For example, the summary extraction unit uses a generation AI to analyze the background sounds and sound effects of a video and identify important scenes. For example, it extracts parts where sound effects are emphasized or parts where the background sounds change as summary points. The summary extraction unit can also use acoustic analysis technology to extract characteristics of background sounds and sound effects and identify important scenes based on those characteristics. For example, it can analyze the intensity and type of sound to identify important scenes. The summary extraction unit can also use speech recognition technology to convert background sounds and sound effects into text data and identify important scenes based on that text data. This makes it possible to identify important scenes based on background sounds and sound effects.

[0034] The digest generation unit can generate a digest version by adding visual effects and animations based on the summary points. For example, the generation AI can generate a digest version by adding visual effects and animations based on the summary points. For example, animations can be added to important points to visually emphasize them. The digest generation unit can also select the type of effect and add visual effects suitable for the summary points. For example, text effects and transition effects can be added. The digest generation unit can also select the animation style and add animations suitable for the summary points. In this way, a digest version can be generated by adding visual effects and animations.

[0035] The digest generation unit can generate multiple digest versions tailored to different viewer demographics. For example, the digest generation unit uses a generation AI to generate multiple digest versions tailored to different viewer demographics. For example, it generates a digest version containing technical details for engineers and a digest version containing business key points for managers. The digest generation unit can also analyze the characteristics of the viewer demographics and adjust the content of the digest version based on that. For example, it customizes the content of the digest version based on the viewer's age group and occupation. The digest generation unit can also analyze the viewer's interests and adjust the content of the digest version based on that. This makes it possible to generate multiple digest versions tailored to different viewer demographics.

[0036] The digest generation unit can optimize the digest version for different platforms. For example, the digest generation unit uses generation AI to optimize the digest version for different platforms. For example, it adjusts the video length and format for YouTube, and emphasizes business-oriented key points for LinkedIn. The digest generation unit can also analyze the characteristics of each platform and adjust the content of the digest version based on that. For example, it customizes the content of the digest version based on the viewer behavior patterns for each platform. The digest generation unit can also generate the digest version in the optimal format for each platform, taking into account technical constraints. This allows the digest version to be optimized for different platforms.

[0037] The distribution unit can analyze the viewer's viewing history and automatically determine the optimal distribution timing. For example, the generation AI in the distribution unit analyzes the viewer's viewing history and automatically determines the optimal distribution timing. For example, the optimal distribution timing is set based on the time of day and day of the week that the viewer previously viewed. The distribution unit can also analyze the viewer's behavioral patterns and adjust the distribution timing based on that. For example, it identifies the time of day that the viewer is most likely to watch and distributes videos during that time. The distribution unit can also predict the distribution timing based on past data and distribute videos at the optimal timing. This makes it possible to automatically determine the optimal distribution timing based on the viewer's viewing history.

[0038] The distribution unit can distribute videos in the optimal image quality and format depending on the viewer's device. For example, the distribution unit uses a generation AI to distribute videos in the optimal image quality and format depending on the viewer's device. For example, it distributes low-resolution videos for smartphones and high-resolution videos for PCs. The distribution unit can also analyze the characteristics of the device and adjust the image quality and format based on that. For example, it adjusts the video image quality based on the device's screen size and resolution. The distribution unit can also distribute videos in the optimal format taking into account the technical constraints of the device. This allows videos to be distributed in the optimal image quality and format depending on the viewer's device.

[0039] The distribution unit can set an optimal distribution schedule for each region based on the viewer's geographic location information. For example, the generation AI of the distribution unit sets an optimal distribution schedule for each region based on the viewer's geographic location information. For example, videos are distributed at times when it is most convenient for viewers in each region to watch. The distribution unit can also analyze geographic location information and adjust the distribution schedule based on that. For example, the distribution schedule is set taking into account events and holidays in each region. The distribution unit can also analyze viewing patterns for each region and adjust the distribution schedule based on that. This makes it possible to set an optimal distribution schedule for each region based on the viewer's geographic location information.

[0040] The distribution unit can analyze viewers' social media activity and select the optimal distribution channel. For example, the distribution unit uses a generation AI to analyze viewers' social media activity and select the optimal distribution channel. For example, the distribution unit identifies social media platforms that viewers frequently use and distributes videos on those platforms. The distribution unit can also analyze social media activity and adjust distribution channels based on that. For example, the distribution unit selects distribution channels based on the content of viewers' posts and the number of likes and shares. The distribution unit can also analyze followers' reactions and adjust distribution channels based on that. This makes it possible to select the optimal distribution channel based on viewers' social media activity.

[0041] The system can analyze a viewer's viewing history and provide an individually customized digest version. For example, the system uses a generation AI to analyze a viewer's viewing history and provide an individually customized digest version. For example, a digest version containing summary points that are likely to be of interest to the viewer is generated based on content that the viewer has viewed in the past. The system can also analyze a viewer's interests and customize the content of the digest version based on that. For example, a digest version containing topics that are likely to be of interest to the viewer is generated based on the viewer's viewing history. The system can also analyze a viewer's behavioral patterns and customize the content of the digest version based on that. This makes it possible to provide an individually customized digest version based on the viewer's viewing history.

[0042] The system can collect viewer feedback in real time and improve the digest version based on that data. For example, the system uses a generative AI to collect viewer feedback in real time and improve the digest version based on that data. For example, the system adjusts the content of the digest version based on viewer comments and ratings. The system can also analyze viewer reactions and improve the content of the digest version based on that. For example, the system can identify areas for improvement based on viewer reaction data and revise the digest version. The system can also analyze the results of viewer surveys and improve the content of the digest version based on that. This allows the digest version to be improved based on viewer feedback.

[0043] The system can analyze the viewer's schedule and suggest the optimal viewing timing. For example, the system uses a generative AI to analyze the viewer's schedule and suggest the optimal viewing timing. For example, it can suggest the optimal viewing time based on the viewer's calendar or planner. The system can also analyze the viewer's behavioral patterns and suggest viewing timing based on that. For example, it can identify the time of day when the viewer is most likely to watch and suggest that time of day. The system can also predict viewing timing based on past data and suggest the optimal timing. This makes it possible to suggest the optimal viewing timing based on the viewer's schedule.

[0044] The system can monitor the progress of editing work in real time and propose an efficient work schedule. For example, the system uses a generation AI to monitor the progress of editing work in real time and propose an efficient work schedule. For example, it analyzes the progress of editing work and automatically generates an optimal work schedule. The system can also monitor the completion status of tasks and adjust the work schedule based on that. For example, it can adjust the work schedule based on task priority. The system can also monitor working hours and adjust the work schedule based on that. This makes it possible to monitor the progress of editing work in real time and propose an efficient work schedule.

[0045] The system can analyze the history of editing work and automatically suggest the optimal editing method. For example, the system uses a generative AI to analyze the history of editing work and automatically suggest the optimal editing method. For example, the system can suggest the optimal editing method based on data from past editing work. The system can also analyze editing patterns and suggest editing methods based on them. For example, the system can identify efficient editing patterns and suggest editing methods based on them. The system can also analyze the tools used and suggest editing methods based on them. This makes it possible to automatically suggest the optimal editing method based on the history of editing work.

[0046] The system can strengthen collaboration with different editing tools to achieve seamless editing. For example, the system can use generative AI to strengthen collaboration with different editing tools to achieve seamless editing. For example, it can integrate multiple editing tools and allow them to be operated with a single interface. The system can also use APIs to ensure compatibility of data formats between different editing tools. For example, it can achieve real-time data sharing, improving the efficiency of editing. The system can also synchronize data between tools to achieve an integrated workflow. This strengthens collaboration with different editing tools to achieve seamless editing.

[0047] The system can learn editing patterns using a machine learning algorithm to further automate editing tasks. For example, the system uses a machine learning algorithm to learn editing patterns so that a generative AI can further automate editing tasks. For example, the system learns optimal editing patterns based on data of past editing tasks. The system can also learn editing patterns using supervised learning. For example, the system learns based on labeled data of past editing tasks. The system can also learn editing patterns using unsupervised learning. For example, the system clusters editing tasks to identify patterns. The system can also learn editing patterns using reinforcement learning. For example, the system learns based on feedback from editing tasks. In this way, the system can learn editing patterns using a machine learning algorithm to further automate editing tasks.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The video analysis unit can also analyze background music in a video and extract important points based on the atmosphere of the scene. For example, it can identify scenes with tense or moving music and extract those parts as summary points. The video analysis unit can also analyze the tempo and rhythm of the music and extract important points based on the excitement of the scene. For example, it can identify parts where the tempo increases or the rhythm changes and extract those parts as summary points. The video analysis unit can also analyze the genre of the music and extract summary points that match the atmosphere of the scene. This makes it possible to analyze the atmosphere of a scene based on the background music and extract important points.

[0050] The video analysis unit can also analyze text data within a video to extract important information. For example, it can analyze subtitles and captions within a video to extract important keywords. The video analysis unit can also analyze the font size and color of the text to identify emphasized parts. For example, it can extract text that is displayed in a large font size or in a conspicuous color as summary points. The video analysis unit can also analyze the display time of the text and extract text that is displayed for a long time as important information. This makes it possible to extract important information based on the text data within a video.

[0051] The video analysis unit can also analyze camera angles and shot types in a video to identify important scenes. For example, it can identify close-up shots and panoramic shots and extract those parts as summary points. The video analysis unit can also analyze camera movement and extract scenes with movement as important points. For example, it can analyze camera work such as panning and zooming and extract those parts as summary points. The video analysis unit can also analyze the length of shots and extract long-lasting shots as important scenes. This makes it possible to identify important scenes based on camera angles and shot types.

[0052] The digest generation unit can generate a digest version by adding interactive elements based on the summary points. For example, an interactive digest version can be generated in which the next scene changes depending on the viewer's selection. The digest generation unit can also generate a digest version whose content changes depending on the viewer's reaction. For example, a different ending can be provided based on the viewer's selection. The digest generation unit can also generate a digest version whose content changes depending on the viewer's input of comments. In this way, a digest version can be generated by adding interactive elements.

[0053] The digest generation unit can generate a digest version by adding visual infographics based on the summary points. For example, infographics that visually display important data or statistical information can be added. The digest generation unit can also add visual charts and graphs to make the information easier to understand. For example, sales data or market share can be displayed in a graph. The digest generation unit can also add visual icons and symbols to emphasize the information. In this way, a digest version can be generated by adding visual infographics.

[0054] The distribution unit can analyze the viewer's internet connection status and automatically adjust the optimal distribution quality. For example, if the viewer's connection speed is slow, low-resolution video is distributed, and if the connection speed is fast, high-resolution video is distributed. The distribution unit can also analyze the remaining battery level of the viewer's device and adjust the distribution quality based on that. For example, if the remaining battery level is low, low-power video is distributed. The distribution unit can also analyze the viewer's data usage and adjust the distribution quality based on that. This makes it possible to automatically adjust the optimal distribution quality based on the viewer's internet connection status.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The video analysis unit analyzes the video. For example, the video analysis unit performs frame analysis to analyze the content of each frame. The video analysis unit can also perform object detection to identify important objects within the video. The video analysis unit can also perform motion detection to analyze movement patterns within the video. Step 2: The summary extraction unit extracts important points from the video analyzed by the video analysis unit. For example, the summary extraction unit extracts important points based on the viewer's level of interest. The summary extraction unit can also extract important points based on playback time. The summary extraction unit can also extract important points based on specific keywords. Step 3: The digest generation unit generates a digest version based on the summary points extracted by the summary extraction unit. For example, the digest generation unit may generate a digest version by adjusting the length of the summary. The digest generation unit may also generate a digest version based on selection criteria for included scenes. The digest generation unit may also generate a digest version by adding visual effects. Step 4: The distribution unit distributes the digest version generated by the digest generation unit and the original full version of the video. For example, the distribution unit selects a distribution platform and distributes the video. The distribution unit can also adjust the distribution format and distribute the video. The distribution unit can also adjust the distribution timing and distribute the video.

[0057] (Example 2) The video editing system according to an embodiment of the present invention uses a generation AI to analyze a video and automatically generate a digest version that focuses on key points for summarization. This makes the video editing process more efficient and enables efficient distribution that meets the needs of viewers.

[0058] A video editing system according to an embodiment includes a video analysis unit, a summary extraction unit, a digest generation unit, and a distribution unit. The video analysis unit analyzes a video. For example, the video analysis unit performs frame analysis to analyze the content of each frame. The video analysis unit can also perform object detection to identify important objects within a video. The video analysis unit can also perform motion detection to analyze movement patterns within a video. The summary extraction unit extracts important points from the video analyzed by the video analysis unit. For example, the summary extraction unit extracts important points based on the viewer's interest level. The summary extraction unit can also extract important points based on playback time. The summary extraction unit can also extract important points based on specific keywords. The digest generation unit generates a digest version based on the summary points extracted by the summary extraction unit. For example, the digest generation unit generates a digest version by adjusting the length of the summary. The digest generation unit can also generate a digest version based on selection criteria for included scenes. The digest generation unit can also generate a digest version by adding visual effects. The distribution unit distributes the digest version generated by the digest generation unit and the original full version of the video. For example, the distribution unit selects a distribution platform to distribute the video. The distribution unit can also adjust the distribution format to distribute the video. The distribution unit can also adjust the distribution timing to distribute the video. As a result, the video editing system according to the embodiment can improve the efficiency of video editing work and realize efficient distribution that suits the viewer's convenience.

[0059] The video analysis unit can analyze audio data and extract important points based on the speaker's emotions and tone. For example, the video analysis unit uses generative AI to analyze the audio data of a video and extract important points based on the speaker's emotions and tone. For example, it identifies parts that the speaker emphasizes or parts where the speaker's emotions are high, and extracts those parts as summary points. The video analysis unit can also use speech recognition technology to convert audio data into text data and perform emotion analysis. For example, it analyzes the pitch and speed of the audio and assigns emotion labels. The video analysis unit can also perform tone analysis and extract important points based on changes in the speaker's tone. This makes it possible to extract important points based on the speaker's emotions and tone.

[0060] The video analysis unit can analyze slides and graphs to extract visually important information. For example, the video analysis unit uses generative AI to analyze slides and graphs in a video and extract visually important information. For example, it determines summary points based on slide titles and graph peak values. The video analysis unit can also use image recognition technology to convert the contents of slides and graphs into text data and extract important information. For example, it can extract text from slides and evaluate its importance. The video analysis unit can also analyze visual features and extract important information based on color emphasis and shape features. This makes it possible to extract visually important information from slides and graphs.

[0061] The video analysis unit can use the emotion estimation function to identify parts that are likely to interest the viewer and extract those parts as summary points. The video analysis unit, for example, uses the emotion estimation function to identify parts that are likely to interest the viewer and extract those parts as summary points. For example, parts that are likely to interest the viewer may be identified based on emotion data. The video analysis unit can also analyze the viewer's facial expressions and identify parts that are likely to interest the viewer based on changes in the viewer's facial expressions. For example, the video analysis unit can detect the viewer's smiling or surprised expressions and extract those parts as summary points. The video analysis unit can also analyze the viewer's voice and identify parts that are likely to interest the viewer based on the tone and speed of the viewer's voice. This allows the video analysis unit to identify parts that are likely to interest the viewer and extract them as summary points.

[0062] The summary extraction unit can analyze subtitle data and automatically generate summary points in different languages. For example, the summary extraction unit uses a generation AI to analyze video subtitle data and automatically generate summary points in different languages. For example, it analyzes English subtitle data and generates summary points in Japanese, French, etc. The summary extraction unit can also analyze subtitle data using text analysis technology and extract keywords. For example, it can extract important keywords in subtitles and generate summary points based on them. The summary extraction unit can also translate subtitle data into different languages ​​using language translation technology and generate summary points based on the translated data. This allows for the automatic generation of summary points in different languages.

[0063] The summary extraction unit can analyze background sounds and sound effects and identify important scenes. For example, the summary extraction unit uses a generation AI to analyze the background sounds and sound effects of a video and identify important scenes. For example, it extracts parts where sound effects are emphasized or parts where the background sounds change as summary points. The summary extraction unit can also use acoustic analysis technology to extract characteristics of background sounds and sound effects and identify important scenes based on those characteristics. For example, it can analyze the intensity and type of sound to identify important scenes. The summary extraction unit can also use speech recognition technology to convert background sounds and sound effects into text data and identify important scenes based on that text data. This makes it possible to identify important scenes based on background sounds and sound effects.

[0064] The summary extraction unit can use the emotion estimation function to collect real-time emotional responses from viewers and dynamically adjust summary points based on the data. For example, the summary extraction unit can use the emotion estimation function to collect real-time emotional responses from viewers and dynamically adjust summary points based on the data. For example, it can prioritize sections with high viewer emotion scores as summary points. The summary extraction unit can also analyze the viewer's facial expressions and adjust summary points based on changes in the viewer's facial expressions. For example, it can detect a viewer's smiling or surprised expression and select those sections as summary points. The summary extraction unit can also analyze the viewer's voice and adjust summary points based on the viewer's tone and speed of voice. This allows the summary points to be dynamically adjusted based on the viewer's real-time emotional responses.

[0065] The digest generation unit can generate a digest version by adding visual effects and animations based on the summary points. For example, the generation AI can generate a digest version by adding visual effects and animations based on the summary points. For example, animations can be added to important points to visually emphasize them. The digest generation unit can also select the type of effect and add visual effects suitable for the summary points. For example, text effects and transition effects can be added. The digest generation unit can also select the animation style and add animations suitable for the summary points. In this way, a digest version can be generated by adding visual effects and animations.

[0066] The digest generation unit can generate multiple digest versions tailored to different viewer demographics. For example, the digest generation unit uses a generation AI to generate multiple digest versions tailored to different viewer demographics. For example, it generates a digest version containing technical details for engineers and a digest version containing business key points for managers. The digest generation unit can also analyze the characteristics of the viewer demographics and adjust the content of the digest version based on that. For example, it customizes the content of the digest version based on the viewer's age group and occupation. The digest generation unit can also analyze the viewer's interests and adjust the content of the digest version based on that. This makes it possible to generate multiple digest versions tailored to different viewer demographics.

[0067] The digest generation unit uses the emotion estimation function to perform editing that appeals to the viewer's emotions and can generate a digest version that is easy to empathize with emotionally. The digest generation unit, for example, uses the emotion estimation function to perform editing that appeals to the viewer's emotions and generates a digest version that is easy to empathize with emotionally. For example, editing is performed to emphasize emotionally charged parts. The digest generation unit can also add emotional music to perform editing that draws out the viewer's emotions. For example, emotional music is added to moving scenes. The digest generation unit can also perform editing that emphasizes moving scenes and draw out the viewer's empathy. In this way, editing that appeals to the viewer's emotions can be performed and a digest version that is easy to empathize with emotionally can be generated.

[0068] The digest generation unit can optimize the digest version for different platforms. For example, the digest generation unit uses generation AI to optimize the digest version for different platforms. For example, it adjusts the video length and format for YouTube, and emphasizes business-oriented key points for LinkedIn. The digest generation unit can also analyze the characteristics of each platform and adjust the content of the digest version based on that. For example, it customizes the content of the digest version based on the viewer behavior patterns for each platform. The digest generation unit can also generate the digest version in the optimal format for each platform, taking into account technical constraints. This allows the digest version to be optimized for different platforms.

[0069] The digest generation unit can dynamically change the content of the digest version based on the viewer's real-time emotional response using the emotion estimation function. The digest generation unit, for example, dynamically changes the content of the digest version based on the viewer's real-time emotional response using the emotion estimation function. For example, it can prioritize displaying parts with a high viewer emotion score. The digest generation unit can also analyze the viewer's facial expressions and adjust the content of the digest version based on changes in the viewer's facial expressions. For example, it can detect the viewer's smiling or surprised expressions and emphasize those parts. The digest generation unit can also analyze the viewer's voice and adjust the content of the digest version based on the viewer's tone and speed of voice. This allows the content of the digest version to dynamically change based on the viewer's real-time emotional response.

[0070] The distribution unit can analyze the viewer's viewing history and automatically determine the optimal distribution timing. For example, the generation AI in the distribution unit analyzes the viewer's viewing history and automatically determines the optimal distribution timing. For example, the optimal distribution timing is set based on the time of day and day of the week that the viewer previously viewed. The distribution unit can also analyze the viewer's behavioral patterns and adjust the distribution timing based on that. For example, it identifies the time of day that the viewer is most likely to watch and distributes videos during that time. The distribution unit can also predict the distribution timing based on past data and distribute videos at the optimal timing. This makes it possible to automatically determine the optimal distribution timing based on the viewer's viewing history.

[0071] The distribution unit can distribute videos in the optimal image quality and format depending on the viewer's device. For example, the distribution unit uses a generation AI to distribute videos in the optimal image quality and format depending on the viewer's device. For example, it distributes low-resolution videos for smartphones and high-resolution videos for PCs. The distribution unit can also analyze the characteristics of the device and adjust the image quality and format based on that. For example, it adjusts the video image quality based on the device's screen size and resolution. The distribution unit can also distribute videos in the optimal format taking into account the technical constraints of the device. This allows videos to be distributed in the optimal image quality and format depending on the viewer's device.

[0072] The distribution unit can use the emotion estimation function to send customized notifications based on the viewer's emotions. The distribution unit, for example, uses the emotion estimation function to send customized notifications based on the viewer's emotions. For example, the distribution unit sends a notification including content that the viewer is likely to be interested in. The distribution unit can also analyze the viewer's facial expressions and customize the notification content based on changes in the viewer's facial expressions. For example, the distribution unit can detect the viewer's smiling or surprised expression and send a notification based on that content. The distribution unit can also analyze the viewer's voice and customize the notification content based on the tone and speed of the viewer's voice. This makes it possible to send customized notifications based on the viewer's emotions.

[0073] The distribution unit can set an optimal distribution schedule for each region based on the viewer's geographic location information. For example, the generation AI of the distribution unit sets an optimal distribution schedule for each region based on the viewer's geographic location information. For example, videos are distributed at times when it is most convenient for viewers in each region to watch. The distribution unit can also analyze geographic location information and adjust the distribution schedule based on that. For example, the distribution schedule is set taking into account events and holidays in each region. The distribution unit can also analyze viewing patterns for each region and adjust the distribution schedule based on that. This makes it possible to set an optimal distribution schedule for each region based on the viewer's geographic location information.

[0074] The distribution unit can analyze viewers' social media activity and select the optimal distribution channel. For example, the distribution unit uses a generation AI to analyze viewers' social media activity and select the optimal distribution channel. For example, the distribution unit identifies social media platforms that viewers frequently use and distributes videos on those platforms. The distribution unit can also analyze social media activity and adjust distribution channels based on that. For example, the distribution unit selects distribution channels based on the content of viewers' posts and the number of likes and shares. The distribution unit can also analyze followers' reactions and adjust distribution channels based on that. This makes it possible to select the optimal distribution channel based on viewers' social media activity.

[0075] The distribution unit can dynamically adjust the distribution content based on the viewer's real-time emotional response using the emotion estimation function. The distribution unit, for example, dynamically adjusts the distribution content based on the viewer's real-time emotional response using the emotion estimation function. For example, the distribution unit prioritizes the distribution of parts with a high viewer emotion score. The distribution unit can also analyze the viewer's facial expressions and adjust the distribution content based on changes in the viewer's facial expressions. For example, the distribution unit can detect the viewer's smiling or surprised expression and emphasize those parts. The distribution unit can also analyze the viewer's voice and adjust the distribution content based on the viewer's tone and speed of voice. This allows the distribution content to be dynamically adjusted based on the viewer's real-time emotional response.

[0076] The system can analyze a viewer's viewing history and provide an individually customized digest version. For example, the system uses a generation AI to analyze a viewer's viewing history and provide an individually customized digest version. For example, a digest version containing summary points that are likely to be of interest to the viewer is generated based on content that the viewer has viewed in the past. The system can also analyze a viewer's interests and customize the content of the digest version based on that. For example, a digest version containing topics that are likely to be of interest to the viewer is generated based on the viewer's viewing history. The system can also analyze a viewer's behavioral patterns and customize the content of the digest version based on that. This makes it possible to provide an individually customized digest version based on the viewer's viewing history.

[0077] The system can collect viewer feedback in real time and improve the digest version based on that data. For example, the system uses a generative AI to collect viewer feedback in real time and improve the digest version based on that data. For example, the system adjusts the content of the digest version based on viewer comments and ratings. The system can also analyze viewer reactions and improve the content of the digest version based on that. For example, the system can identify areas for improvement based on viewer reaction data and revise the digest version. The system can also analyze the results of viewer surveys and improve the content of the digest version based on that. This allows the digest version to be improved based on viewer feedback.

[0078] The system can provide a customized viewing experience based on the viewer's emotions using the emotion estimation function. For example, the system can provide a customized viewing experience based on the viewer's emotions using the emotion estimation function. For example, content with a high viewer emotion score can be preferentially displayed. The system can also analyze the viewer's facial expressions and customize the viewing experience based on changes in the viewer's facial expressions. For example, the system can detect the viewer's smiling or surprised expressions and provide a viewing experience based on the content. The system can also analyze the viewer's voice and customize the viewing experience based on the tone and speed of the viewer's voice. This makes it possible to provide a customized viewing experience based on the viewer's emotions.

[0079] The system can analyze the viewer's schedule and suggest the optimal viewing timing. For example, the system uses a generative AI to analyze the viewer's schedule and suggest the optimal viewing timing. For example, it can suggest the optimal viewing time based on the viewer's calendar or planner. The system can also analyze the viewer's behavioral patterns and suggest viewing timing based on that. For example, it can identify the time of day when the viewer is most likely to watch and suggest that time of day. The system can also predict viewing timing based on past data and suggest the optimal timing. This makes it possible to suggest the optimal viewing timing based on the viewer's schedule.

[0080] The system can dynamically adjust the viewing experience based on the viewer's real-time emotional reactions using an emotion estimation function. For example, the system can dynamically adjust the viewing experience based on the viewer's real-time emotional reactions using the emotion estimation function. For example, the system can prioritize displaying parts with a high viewer emotion score. The system can also analyze the viewer's facial expressions and adjust the viewing experience based on changes in the viewer's facial expressions. For example, the system can detect the viewer's smiling or surprised expressions and emphasize those parts. The system can also analyze the viewer's voice and adjust the viewing experience based on the viewer's tone and speed of voice. This makes it possible to dynamically adjust the viewing experience based on the viewer's real-time emotional reactions.

[0081] The system can monitor the progress of editing work in real time and propose an efficient work schedule. For example, the system uses a generation AI to monitor the progress of editing work in real time and propose an efficient work schedule. For example, it analyzes the progress of editing work and automatically generates an optimal work schedule. The system can also monitor the completion status of tasks and adjust the work schedule based on that. For example, it can adjust the work schedule based on task priority. The system can also monitor working hours and adjust the work schedule based on that. This makes it possible to monitor the progress of editing work in real time and propose an efficient work schedule.

[0082] The system can analyze the history of editing work and automatically suggest the optimal editing method. For example, the system uses a generative AI to analyze the history of editing work and automatically suggest the optimal editing method. For example, the system can suggest the optimal editing method based on data from past editing work. The system can also analyze editing patterns and suggest editing methods based on them. For example, the system can identify efficient editing patterns and suggest editing methods based on them. The system can also analyze the tools used and suggest editing methods based on them. This makes it possible to automatically suggest the optimal editing method based on the history of editing work.

[0083] The system can monitor the emotional state of an editor using an emotion estimation function and make suggestions to reduce stress. For example, the system can monitor the emotional state of an editor using the emotion estimation function and make suggestions to reduce stress. For example, if the editor's emotion score is low, the system can suggest relaxation methods. The system can also analyze the editor's facial expressions and make suggestions to reduce stress based on changes in the editor's facial expressions. For example, the system can detect a tired expression on the editor's face and suggest taking a break. The system can also analyze the editor's voice and make suggestions to reduce stress based on the tone and speed of the editor's voice. This makes it possible to monitor the emotional state of an editor and make suggestions to reduce stress.

[0084] The system can strengthen collaboration with different editing tools to achieve seamless editing. For example, the system can use generative AI to strengthen collaboration with different editing tools to achieve seamless editing. For example, it can integrate multiple editing tools and allow them to be operated with a single interface. The system can also use APIs to ensure compatibility of data formats between different editing tools. For example, it can achieve real-time data sharing, improving the efficiency of editing. The system can also synchronize data between tools to achieve an integrated workflow. This strengthens collaboration with different editing tools to achieve seamless editing.

[0085] The system can learn editing patterns using a machine learning algorithm to further automate editing tasks. For example, the system uses a machine learning algorithm to learn editing patterns so that a generative AI can further automate editing tasks. For example, the system learns optimal editing patterns based on data of past editing tasks. The system can also learn editing patterns using supervised learning. For example, the system learns based on labeled data of past editing tasks. The system can also learn editing patterns using unsupervised learning. For example, the system clusters editing tasks to identify patterns. The system can also learn editing patterns using reinforcement learning. For example, the system learns based on feedback from editing tasks. In this way, the system can learn editing patterns using a machine learning algorithm to further automate editing tasks.

[0086] The system can dynamically adjust editing work based on the real-time emotional reactions of an editor using an emotion estimation function. For example, the system can dynamically adjust editing work based on the real-time emotional reactions of an editor using the emotion estimation function. For example, if the editor's emotion score is low, the system can suggest pausing the work. The system can also analyze the editor's facial expressions and adjust editing work based on changes in the editor's facial expressions. For example, the system can detect a tired expression on the editor's face and suggest taking a break. The system can also analyze the editor's voice and adjust editing work based on the tone and speed of the editor's voice. This allows the system to dynamically adjust editing work based on the editor's real-time emotional reactions.

[0087] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0088] The video analysis unit can also analyze background music in a video and extract important points based on the atmosphere of the scene. For example, it can identify scenes with tense or moving music and extract those parts as summary points. The video analysis unit can also analyze the tempo and rhythm of the music and extract important points based on the excitement of the scene. For example, it can identify parts where the tempo increases or the rhythm changes and extract those parts as summary points. The video analysis unit can also analyze the genre of the music and extract summary points that match the atmosphere of the scene. This makes it possible to analyze the atmosphere of a scene based on the background music and extract important points.

[0089] The video analysis unit can also analyze text data within a video to extract important information. For example, it can analyze subtitles and captions within a video to extract important keywords. The video analysis unit can also analyze the font size and color of the text to identify emphasized parts. For example, it can extract text that is displayed in a large font size or in a conspicuous color as summary points. The video analysis unit can also analyze the display time of the text and extract text that is displayed for a long time as important information. This makes it possible to extract important information based on the text data within a video.

[0090] The video analysis unit can also analyze camera angles and shot types in a video to identify important scenes. For example, it can identify close-up shots and panoramic shots and extract those parts as summary points. The video analysis unit can also analyze camera movement and extract scenes with movement as important points. For example, it can analyze camera work such as panning and zooming and extract those parts as summary points. The video analysis unit can also analyze the length of shots and extract long-lasting shots as important scenes. This makes it possible to identify important scenes based on camera angles and shot types.

[0091] The summary extraction unit can analyze viewer gaze data and extract portions that viewers pay attention to as summary points. For example, it identifies portions where viewers' gazes are focused and extracts those portions as summary points. The summary extraction unit can also analyze viewer gaze movements and extract portions where the gazes move frequently as important points. For example, it identifies portions where the gazes are focused on a specific object and extracts those portions as summary points. The summary extraction unit can also analyze the duration of viewer gaze retention and extract portions where the gazes remain for a long time as important points. In this way, important points can be extracted based on viewer gaze data.

[0092] The summary extraction unit can analyze the viewer's biometric data and extract important points based on the viewer's physiological reactions. For example, it can analyze the viewer's heart rate and electrodermal activity and extract parts of the viewer that are excited as summary points. The summary extraction unit can also analyze the viewer's breathing patterns and extract parts of the viewer that are irregularly ventilated as important points. For example, it can identify parts of the viewer's breathing that become faster and extract those parts as summary points. The summary extraction unit can also analyze changes in the viewer's body temperature and extract parts of the viewer that are prone to temperature rise as important points. In this way, it is possible to extract important points based on the viewer's biometric data.

[0093] The digest generation unit can generate a digest version by adding interactive elements based on the summary points. For example, an interactive digest version can be generated in which the next scene changes depending on the viewer's selection. The digest generation unit can also generate a digest version whose content changes depending on the viewer's reaction. For example, a different ending can be provided based on the viewer's selection. The digest generation unit can also generate a digest version whose content changes depending on the viewer's input of comments. In this way, a digest version can be generated by adding interactive elements.

[0094] The digest generation unit can use the emotion estimation function to select music based on the viewer's emotions and add it to the digest version. For example, if the viewer is moved, it adds moving music, and if the viewer is excited, it adds energetic music. The digest generation unit can also adjust the tempo and rhythm of the music based on the viewer's emotions. For example, it can speed up the tempo in parts where the viewer's emotions are heightened and slow down the tempo in parts where the viewer's emotions are calmed. The digest generation unit can also adjust the volume of the music based on the viewer's emotions. In this way, a digest version can be generated by adding music based on the viewer's emotions.

[0095] The digest generation unit can generate a digest version by adding visual infographics based on the summary points. For example, infographics that visually display important data or statistical information can be added. The digest generation unit can also add visual charts and graphs to make the information easier to understand. For example, sales data or market share can be displayed in a graph. The digest generation unit can also add visual icons and symbols to emphasize the information. In this way, a digest version can be generated by adding visual infographics.

[0096] The digest generation unit can generate a digest version by adding narration based on the viewer's emotions using the emotion estimation function. For example, if the viewer is moved, an emotional narration is added, and if the viewer is excited, an energetic narration is added. The digest generation unit can also adjust the tone and speed of the narration based on the viewer's emotions. For example, the tone can be increased in parts where the viewer's emotions are heightened and decreased in parts where the viewer's emotions are calmed. The digest generation unit can also adjust the content of the narration based on the viewer's emotions. In this way, a digest version can be generated by adding narration based on the viewer's emotions.

[0097] The distribution unit can analyze the viewer's internet connection status and automatically adjust the optimal distribution quality. For example, if the viewer's connection speed is slow, low-resolution video is distributed, and if the connection speed is fast, high-resolution video is distributed. The distribution unit can also analyze the remaining battery level of the viewer's device and adjust the distribution quality based on that. For example, if the remaining battery level is low, low-power video is distributed. The distribution unit can also analyze the viewer's data usage and adjust the distribution quality based on that. This makes it possible to automatically adjust the optimal distribution quality based on the viewer's internet connection status.

[0098] The processing flow of the second embodiment will be briefly explained below.

[0099] Step 1: The video analysis unit analyzes the video. For example, the video analysis unit performs frame analysis to analyze the content of each frame. The video analysis unit can also perform object detection to identify important objects within the video. The video analysis unit can also perform motion detection to analyze movement patterns within the video. Step 2: The summary extraction unit extracts important points from the video analyzed by the video analysis unit. For example, the summary extraction unit extracts important points based on the viewer's level of interest. The summary extraction unit can also extract important points based on playback time. The summary extraction unit can also extract important points based on specific keywords. Step 3: The digest generation unit generates a digest version based on the summary points extracted by the summary extraction unit. For example, the digest generation unit may generate a digest version by adjusting the length of the summary. The digest generation unit may also generate a digest version based on selection criteria for included scenes. The digest generation unit may also generate a digest version by adding visual effects. Step 4: The distribution unit distributes the digest version generated by the digest generation unit and the original full version of the video. For example, the distribution unit selects a distribution platform and distributes the video. The distribution unit can also adjust the distribution format and distribute the video. The distribution unit can also adjust the distribution timing and distribute the video.

[0100] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0101] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0102] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0103] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0104] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0105] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0106] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0107] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0108] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0109] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0110] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0111] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0112] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0113] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0114] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0115] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0116] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0117] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0118] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0119] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0120] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0121] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0122] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0124] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0125] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0126] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0127] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0128] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0129] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0130] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0131] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0132] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0133] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0134] 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.

[0135] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0136] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0137] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0140] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0141] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0142] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0143] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0144] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0145] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0146] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0147] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0148] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0149] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0150] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0151] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0152] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0153] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0154] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0155] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0156] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0157] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0158] 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.

[0159] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0160] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0161] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0162] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0163] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0164] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0165] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0166] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0167] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a video analysis unit that analyzes the video; a summary extraction unit that extracts important points from the video analyzed by the video analysis unit; a digest generation unit that generates a digest version based on the summary points extracted by the summary extraction unit; a distribution unit that distributes the digest version generated by the digest generation unit and the original full version of the video. A system characterized by:

2. The video analysis unit Identify the part that is most interesting to the viewer and extract that part as the summary point.

2. The system of claim 1.

3. The summary extraction unit Analyzes subtitle data and automatically generates summary points in different languages 2. The system of claim 1.

4. The digest generation unit Based on the summary points, visual effects and animations are added to generate the digest version.

2. The system of claim 1.

5. The distribution unit Analyzes viewers' viewing history and automatically determines the optimal distribution timing 2. The system of claim 1.

6. The system comprises: Deliver a personalized viewing experience based on viewer emotions 2. The system of claim 1.

7. The system comprises: Monitor editors' emotional state and offer suggestions to reduce stress 2. The system of claim 1.

8. The distribution unit Dynamically adjust content based on viewers' real-time emotional responses 2. The system of claim 1.

Images