system

Abstract

The system according to this embodiment aims to automatically generate attractive thumbnail images from videos and images. [Solution] The system according to the embodiment comprises an analysis unit, a scoring unit, a cropping unit, and a generation unit. The analysis unit analyzes videos and images. The scoring unit scores the attractiveness of the video analyzed by the analysis unit. The cropping unit crops out scenes with high scores from the scoring unit. The generation unit generates thumbnail images based on the scenes cropped by the cropping unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it takes a great deal of labor and time to generate an attractive thumbnail image from a video or image.

[0005] The system according to the embodiment aims to automatically generate an attractive thumbnail image from a video or image.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a scoring unit, a cropping unit, and a generation unit. The analysis unit analyzes videos and images. The scoring unit scores the attractiveness of the images analyzed by the analysis unit. The cropping unit crops out scenes with high scores from the scoring unit. The generation unit generates thumbnail images based on the scenes cropped by the cropping unit. [Effects of the Invention]

[0007] The system according to this embodiment can automatically generate attractive thumbnail images from videos and images. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

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

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

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

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

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

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

[0028] (Example of form 1) The video thumbnail generation system according to an embodiment of the present invention is a system that uses a generation AI to analyze videos and images and generate attractive video thumbnail images that will draw viewers in. In the video thumbnail generation system, the generation AI analyzes the video and scores the attractiveness of the content. Next, it extracts scenes with high scores and creates thumbnail images using an image generation AI. This mechanism allows YouTubers and video creators to obtain attractive thumbnail images without much effort. The video thumbnail generation system uses a generation AI to analyze the video. In this process, the generation AI evaluates each scene in the video and scores its attractiveness. For example, it determines whether a particular scene in the video is interesting to the viewer and assigns a high score to that scene. This makes it possible to identify attractive points in the video. Next, it extracts scenes with high scores and creates thumbnail images using an image generation AI. The generation AI automatically selects scenes with high scores and generates thumbnail images based on those scenes. For example, if a particular scene in the video is determined to be attractive to the viewer, it extracts that scene and the image generation AI creates a thumbnail image. This makes it possible to obtain attractive thumbnail images that will draw viewers in. This system allows YouTubers and video creators to obtain attractive thumbnail images without much effort. Traditionally, creating attractive thumbnail images required reviewing one's own video, identifying appealing points, and then cropping and editing them. This invention eliminates that effort. The target audience is individual YouTubers who post videos on YouTube and corporate PR departments. The system can be expanded beyond video thumbnail images to include services that summarize and document footage from fixed-point cameras such as surveillance cameras and dashcams. For example, it can analyze surveillance camera footage, automatically extract and summarize important scenes, and efficiently manage surveillance camera footage. It can also analyze dashcam footage, automatically extract and summarize accident moments and other important scenes, and efficiently manage dashcam footage, allowing for quick access to necessary information.This allows the video thumbnail generation system to produce attractive thumbnail images that will draw viewers in.

[0029] The video thumbnail generation system according to this embodiment comprises an analysis unit, a scoring unit, a cropping unit, and a generation unit. The analysis unit analyzes the video or image. For example, the analysis unit analyzes the frames of the video or image and detects objects within each frame. The analysis unit can also analyze movement and changes within the image. For example, the analysis unit tracks the movement of a specific object within the image and analyzes the pattern of that movement. Furthermore, the analysis unit can analyze audio information within the image and evaluate the relationship between the audio and the image. For example, the analysis unit analyzes scenes in the image where the audio intensifies and evaluates the image of those scenes. The scoring unit scores the attractiveness of the image analyzed by the analysis unit. For example, the scoring unit determines whether a particular scene in the image is interesting to the viewer and assigns a high score to that scene. For example, the scoring unit assigns a score based on viewer reactions, viewing time, click-through rate, etc. The scoring unit can also assign a score considering color information, music, sound effects, etc., within the image. For example, the scoring unit assigns high scores to scenes with vibrant colors in the video. The cropping unit crops out scenes with high scores from the scoring unit. For example, the cropping unit can automatically select high-scoring scenes and crop them. For example, the cropping unit can crop specific scenes from the video frame by frame to use as material for a thumbnail image. The cropping unit can also detect important objects in the video and crop the image around those objects. For example, the cropping unit can detect people in the video and crop the image around them. The generation unit generates thumbnail images based on the scenes cropped by the cropping unit. For example, the generation unit can generate thumbnail images using image generation AI based on the cropped scenes. For example, the generation unit can use image generation AI to analyze the cropped scenes and generate the optimal thumbnail image. The generation unit can also estimate the viewer's emotions and adjust the design of the thumbnail image based on the estimated viewer emotions. For example, if the viewer is excited, the generation unit will generate a thumbnail image with vibrant colors. As a result, the video thumbnail generation system according to this embodiment can generate attractive thumbnail images that will draw viewers in.

[0030] The analysis unit analyzes videos and images. For example, the analysis unit analyzes frames of videos and images and detects objects within each frame. Specifically, the analysis unit uses image recognition technology to identify people, objects, backgrounds, etc., within frames and determine their respective positions and movements. For example, it can use facial recognition technology to detect a person's face and analyze their facial expression and gaze direction. It can also use object recognition technology to identify specific objects such as vehicles, buildings, and animals and track their movement and position. Furthermore, the analysis unit can also analyze movement and changes within the video. For example, it can use motion detection algorithms to track the movement of specific objects within the video and analyze their movement patterns. This allows for the identification of action scenes and important events within the video. In addition, the analysis unit can analyze audio information within the video and evaluate the relationship between audio and video. For example, it can use speech recognition technology to convert audio within the video into text and analyze its content. This allows for the identification of scenes where the audio intensifies or contains specific keywords, and the evaluation of the video in those scenes. Based on these analysis results, the analysis unit can identify important scenes and scenes that are appealing to viewers within the video.

[0031] The scoring unit scores the attractiveness of the video analyzed by the analysis unit. For example, the scoring unit determines whether a particular scene in the video is interesting to the viewer and assigns a high score to that scene. Specifically, the scoring unit assigns scores based on data such as viewer reactions, viewing time, and click-through rates. For example, it can assign high scores to scenes that viewers watched for a long time or scenes that received many clicks. The scoring unit can also assign scores considering color information, music, and sound effects in the video. For example, it can assign high scores to scenes with vivid colors or scenes with emotionally evocative music. Furthermore, the scoring unit can use AI to estimate the viewer's emotions and assign scores based on those emotions. For example, if the viewer is excited or moved, it can assign a high score to that scene. As a result, the scoring unit can accurately identify scenes that are attractive to viewers and provide material for thumbnail generation.

[0032] The cropping unit extracts scenes with high scores determined by the scoring unit. For example, the cropping unit can automatically select high-scoring scenes and crop them. Specifically, the cropping unit crops specific scenes from the video frame by frame to use as material for thumbnail images. For example, it can identify the start and end frames of a high-scoring scene and crop the frames within that range. The cropping unit can also detect important objects in the video and crop the frame around those objects. For example, it can detect a person's face or a specific object and crop the frame around that object. Furthermore, the cropping unit can select the optimal cropping range considering the composition and balance of the video. For example, it can crop frames so that important elements in the video are evenly distributed. As a result, the cropping unit can efficiently generate material for thumbnail images that are attractive to viewers.

[0033] The generation unit generates thumbnail images based on the scenes cropped by the cropping unit. For example, the generation unit uses an image generation AI to generate thumbnail images based on the cropped scenes. Specifically, the generation unit uses the image generation AI to analyze the cropped scenes and generate the optimal thumbnail image. For example, the image generation AI can analyze the colors and composition of the cropped scenes to generate thumbnail images that are appealing to viewers. The generation unit can also estimate the viewer's emotions and adjust the design of the thumbnail image based on the estimated emotions. For example, if the viewer is excited, it can generate a thumbnail image with vibrant colors, and if the viewer is calm, it can generate a thumbnail image with calm colors. Furthermore, the generation unit can add text and graphic elements to the thumbnail image. For example, it can add the video title or catchphrase to the thumbnail image to attract the viewer's interest. As a result, the generation unit can generate attractive thumbnail images that draw viewers in, thereby improving video viewership.

[0034] The analysis unit can analyze video from fixed cameras such as surveillance cameras and dashcams. For example, the analysis unit can analyze surveillance camera video and automatically extract and summarize important scenes. For example, the analysis unit can detect specific movements in surveillance camera video and extract important scenes based on those movements. The analysis unit can also analyze dashcam video and automatically extract and summarize accident moments and other important scenes. For example, the analysis unit can detect collision or sudden braking scenes in dashcam video and extract those scenes. This allows for efficient management of surveillance camera and dashcam video by analyzing fixed camera video. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input surveillance camera video into a generative AI and have the generative AI extract important scenes.

[0035] The scoring unit can determine whether a particular scene in a video is interesting to the viewer and assign a high score to that scene. The scoring unit assigns scores based on factors such as viewer reactions, viewing time, and click-through rates. For example, the scoring unit assigns a high score to scenes that viewers watch for a long time. The scoring unit can also assign scores considering color information, music, and sound effects in the video. For example, the scoring unit assigns a high score to scenes with vivid colors in the video. This allows for the generation of attractive thumbnail images by highly valuing scenes that are interesting to the viewer. Some or all of the above processing in the scoring unit may be performed using, for example, a generative AI, or without a generative AI. For example, the scoring unit can input viewer reaction data into a generative AI and have the generative AI perform the determination of interesting scenes.

[0036] The cropping unit can automatically select high-scoring scenes and crop them. For example, the cropping unit can crop high-scoring scenes frame by frame and use them as material for thumbnail images. For example, the cropping unit can automatically select a specific scene in the video and crop it. The cropping unit can also detect important objects in the video and crop the image around those objects. For example, the cropping unit can detect a person in the video and crop the image around that person. This allows for efficient generation of thumbnail images by automatically selecting and cropping high-scoring scenes. Some or all of the above processing in the cropping unit may be performed using, for example, a generation AI, or without a generation AI. For example, the cropping unit can input high-scoring scenes from the scoring unit into the generation AI and have the generation AI perform the scene cropping.

[0037] The generation unit can generate thumbnail images based on the cropped scenes. For example, the generation unit can generate thumbnail images using an image generation AI based on the cropped scenes. For example, the generation unit can have the image generation AI analyze the cropped scenes and generate the optimal thumbnail image. The generation unit can also estimate the viewer's emotions and adjust the design of the thumbnail image based on the estimated viewer emotions. For example, if the viewer is excited, the generation unit will generate a thumbnail image with vivid colors. In this way, by generating thumbnail images based on cropped scenes, it is possible to obtain attractive thumbnail images that will draw in viewers. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input the cropped scenes into a generation AI and have the generation AI perform the generation of thumbnail images.

[0038] The analysis unit can analyze audio information within a video and evaluate the relationship between audio and video during video analysis. For example, the analysis unit can analyze scenes where the audio intensifies and evaluate the video in those scenes. It can also analyze scenes where the audio in the video becomes quieter and evaluate the video in those scenes. Furthermore, the analysis unit can analyze the synchronization between audio and video within a video and evaluate scenes with high correlation. By evaluating the relationship between audio and video, more accurate video analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input audio data from the video into a generative AI and have the generative AI perform the evaluation of the relationship between audio and video.

[0039] The analysis unit can analyze motion patterns within a video and extract motion characteristics during video analysis. For example, the analysis unit can analyze scenes with fast motion and extract their characteristics. It can also analyze scenes with slow motion and extract their characteristics. Furthermore, the analysis unit can analyze scenes with complex motion and extract their characteristics. By extracting motion characteristics in this way, the accuracy of video analysis is improved. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input motion data from the video into a generative AI and have the generative AI perform the extraction of motion characteristics.

[0040] The analysis unit can perform video analysis while taking into account information about the video's shooting location. For example, if the video was shot in a tourist area, the analysis unit can analyze the characteristics of that location. It can also analyze the characteristics of an urban area if the video was shot in a city. Furthermore, if the video was shot in a natural environment, the analysis unit can analyze the characteristics of that location. This improves the accuracy of video analysis by considering information about the shooting location. Some or all of the above-described processes in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input information about the video's shooting location into a generative AI and have the generative AI perform the analysis.

[0041] The analysis unit can analyze text information within a video and evaluate the relationship between the text and the video during video analysis. For example, the analysis unit can analyze scenes where text is displayed in the video and evaluate the video of those scenes. The analysis unit can also analyze scenes where the text in the video matches the content of the video and evaluate the relationship between them. Furthermore, the analysis unit can analyze scenes where the text in the video contains important information and evaluate the video of those scenes. By evaluating the relationship between text and video, the accuracy of video analysis is improved. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input text data from the video into a generative AI and have the generative AI perform the evaluation of the relationship between the text and the video.

[0042] The scoring unit can analyze the color information within the video during the scoring process and reflect the attractiveness of the colors in the score. For example, the scoring unit can assign a high score to scenes with vibrant colors in the video. It can also assign a high score to scenes with muted colors in the video. Furthermore, it can assign a high score to scenes with monochrome colors in the video. By reflecting the attractiveness of the colors in the score, more accurate scoring becomes possible. Some or all of the above processing in the scoring unit may be performed using, for example, a generative AI, or without a generative AI. For example, the scoring unit can input color data from the video into a generative AI and have the generative AI perform the scoring of the attractiveness of the colors.

[0043] The scoring unit can evaluate the influence of music and sound effects within the video during the scoring process and reflect this in the score. For example, the scoring unit can assign a high score to scenes where the music in the video builds up. It can also assign a high score to scenes where sound effects in the video are emphasized. Furthermore, the scoring unit can assign a high score to scenes where the music and video are synchronized. By reflecting the influence of music and sound effects in the score, more accurate scoring becomes possible. Some or all of the above processing in the scoring unit may be performed using, for example, a generative AI, or without a generative AI. For example, the scoring unit can input music data from the video into a generative AI and have the generative AI perform the evaluation of the influence of music and sound effects.

[0044] The scoring unit can adjust the score based on the length of the video during the scoring process. For example, if the video is short, the scoring unit will assign higher scores to important scenes. If the video is long, the scoring unit can also assign scores considering the overall balance. Furthermore, the scoring unit can adjust the weighting of the score according to the length of the video. This allows for more appropriate scoring by adjusting the score based on the length of the video. Some or all of the above processing in the scoring unit may be performed using, for example, a generative AI, or without a generative AI. For example, the scoring unit can input video length data into a generative AI and have the generative AI perform the score adjustments.

[0045] The scoring unit can apply different scoring algorithms depending on the genre of the video during the scoring process. For example, the scoring unit can apply a scoring algorithm that emphasizes action scenes to action videos. It can also apply a scoring algorithm that emphasizes the amount of information to documentary videos. Furthermore, it can apply a scoring algorithm that emphasizes the humorous elements to comedy videos. By applying a scoring algorithm according to the genre of the video, more appropriate scoring becomes possible. Some or all of the above processing in the scoring unit may be performed using, for example, a generative AI, or without a generative AI. For example, the scoring unit can input video genre data into a generative AI and have the generative AI execute the application of the scoring algorithm.

[0046] The cropping unit can select the optimal frame by considering the speed of motion within the video during the cropping process. For example, when cropping a scene with fast motion, the cropping unit can select the peak of the motion. It can also select the beginning and end of motion when cropping a scene with slow motion. Furthermore, when cropping a scene with complex motion, the cropping unit can select the center of motion. This allows for the selection of a more appropriate frame by considering the speed of motion. Some or all of the above processing in the cropping unit may be performed using, for example, a generative AI, or without one. For example, the cropping unit can input motion data from the video into a generative AI and have the generative AI select the optimal frame.

[0047] The cropping unit can detect important objects within the video during cropping and crop the image around those objects. For example, the cropping unit can detect a person in the video and crop the image around that person. It can also detect a vehicle in the video and crop the image around that vehicle. Furthermore, it can detect a building in the video and crop the image around that building. By cropping the image around important objects, it is possible to emphasize scenes that are appealing to the viewer. Some or all of the above processing in the cropping unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the cropping unit can input object data from the video into a generative AI and have the generative AI perform object detection and cropping.

[0048] The cropping unit can select the optimal frame during cropping, taking into account the resolution of the video. For example, in high-resolution video, the cropping unit can select a frame where details are clearly visible. In low-resolution video, the cropping unit can also select a frame that offers a good overall balance. Furthermore, the cropping unit can select the optimal frame according to the resolution. This allows for the selection of a more appropriate frame by considering the resolution. Some or all of the above processing in the cropping unit may be performed using, for example, a generation AI, or without a generation AI. For example, the cropping unit can input video resolution data into a generation AI and have the generation AI select the optimal frame.

[0049] The cropping unit can select the optimal frame by considering the text information within the video during the cropping process. For example, the cropping unit can prioritize cropping scenes where text is displayed in the video. It can also prioritize cropping scenes where the text in the video matches the content of the video. Furthermore, the cropping unit can prioritize cropping scenes where the text in the video contains important information. This allows for the selection of a more appropriate frame by considering the text information. Some or all of the above processing in the cropping unit may be performed using, for example, a generative AI, or without a generative AI. For example, the cropping unit can input text data from the video into a generative AI and have the generative AI select the optimal frame.

[0050] The generation unit can select the optimal color tone when generating thumbnail images, taking into account the color information within the video. For example, the generation unit can select the color tone of a thumbnail image based on scenes with vibrant colors within the video. It can also select the color tone of a thumbnail image based on scenes with muted colors within the video. Furthermore, the generation unit can select the color tone of a thumbnail image based on scenes with monochrome colors within the video. By considering color information, it is possible to generate more appealing thumbnail images. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the generation unit can input color data from the video into a generation AI and have the generation AI select the optimal color tone.

[0051] The generation unit can apply a design that emphasizes important objects in the video when generating thumbnail images. For example, the generation unit can apply a design that emphasizes people in the video. It can also apply a design that emphasizes vehicles in the video. Furthermore, it can apply a design that emphasizes buildings in the video. This allows for the creation of thumbnail images that are appealing to viewers by emphasizing important objects. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input object data from the video into a generation AI and have the generation AI execute the object emphasis design.

[0052] The generation unit can apply different design templates depending on the video genre when generating thumbnail images. For example, the generation unit can apply a design template that emphasizes action scenes to action videos. It can also apply a design template that prioritizes information to documentary videos. Furthermore, it can apply a design template that emphasizes humor to comedy videos. By applying a design template appropriate to the genre, it is possible to generate more appropriate thumbnail images. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input video genre data into a generation AI and have the generation AI apply the design template.

[0053] The generation unit can select the optimal layout when generating thumbnail images, taking into account the text information within the video. For example, the generation unit can select a thumbnail image layout based on scenes where text within the video is displayed. It can also select a thumbnail image layout based on scenes where the text within the video matches the content of the video. Furthermore, the generation unit can select a thumbnail image layout based on scenes where the text within the video contains important information. This allows for the selection of a more appropriate layout by considering the text information. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the generation unit can input text data from the video into a generation AI and have the generation AI select the optimal layout.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The analysis unit can analyze the speed of movement of objects in the video and evaluate the importance of a scene based on the speed of movement. For example, the analysis unit will rate scenes with fast movement highly and scenes with slow movement lower. The analysis unit can also rate scenes with abrupt changes in speed particularly highly. Furthermore, the analysis unit can evaluate the relationship between speed of movement and viewer reactions. This allows for a more accurate identification of scenes that are appealing to viewers by considering the speed of movement.

[0056] The cropping function can crop scenes considering the size of objects within the video. For example, it can prioritize cropping scenes containing large objects. It can also crop scenes containing small objects. Furthermore, it can select scenes by associating object size with viewer reactions. This allows for the efficient cropping of scenes that are appealing to viewers by considering object size.

[0057] The generation unit can select the optimal brightness for thumbnail images by considering the intensity of light in the video. For example, the generation unit can generate a bright thumbnail image based on a scene with strong light. It can also generate a dark thumbnail image based on a scene with weak light. Furthermore, the generation unit can adjust the brightness by relating the intensity of light to the viewer's reaction. This allows for the generation of thumbnail images that are appealing to viewers by considering the intensity of light.

[0058] The analysis unit can analyze background sounds within a video and evaluate the importance of a scene based on the type of sound. For example, the analysis unit can rate scenes with noisy background sounds highly. Conversely, it can rate scenes with quiet background sounds lower. Furthermore, the analysis unit can also evaluate the relationship between the type of background sound and the viewer's reaction. This allows for a more accurate identification of scenes that are appealing to viewers by considering background sounds.

[0059] The generation unit can select the optimal layout for thumbnail images by considering the direction of movement within the video. For example, based on a scene where movement moves from right to left, the generation unit will place important elements on the right side. Similarly, based on a scene where movement moves from left to right, it can place important elements on the left side. Furthermore, it can adjust the layout by associating the direction of movement with viewer reactions. This allows for the generation of thumbnail images that are appealing to viewers by considering the direction of movement.

[0060] The analysis unit can analyze changes in color within the video and evaluate the importance of scenes based on those changes. For example, it can give a higher rating to scenes where colors change rapidly, and a lower rating to scenes where colors change gradually. Furthermore, it can also evaluate the relationship between color changes and viewer reactions. This allows for a more accurate identification of scenes that are appealing to viewers by considering changes in color.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The analysis unit analyzes the video or image. The analysis unit analyzes the frames of the video or image and detects objects within each frame. It also analyzes movement and changes within the image, tracks the movement of specific objects, and analyzes the patterns of that movement. Furthermore, it can analyze the audio information within the image and evaluate the relationship between the audio and the image. For example, it can analyze scenes where the audio intensifies and evaluate the video of those scenes. Step 2: The scoring unit scores the attractiveness of the video analyzed by the analysis unit. The scoring unit determines whether a particular scene in the video is interesting to the viewer and assigns a high score to that scene. The score is based on viewer reactions, viewing time, click-through rate, etc. It can also take into account color information, music, sound effects, etc. in the video when assigning a score. For example, a scene with vivid colors will be given a high score. Step 3: The cropping unit extracts scenes with high scores determined by the scoring unit. The cropping unit automatically selects high-scoring scenes and crops them. For example, it can crop specific scenes frame by frame to use as material for a thumbnail image. It can also detect important objects and crop the image around them. For example, it can detect a person and crop the image around that person. Step 4: The generation unit generates thumbnail images based on the scenes cropped by the cropping unit. The generation unit uses an image generation AI to generate thumbnail images based on the cropped scenes. For example, the image generation AI analyzes the cropped scenes and generates the optimal thumbnail image. It can also estimate the viewer's emotions and adjust the thumbnail image design based on the estimated viewer emotions. For example, if the viewer is excited, a thumbnail image with vibrant colors will be generated.

[0063] (Example of form 2) The video thumbnail generation system according to an embodiment of the present invention is a system that uses a generation AI to analyze videos and images and generate attractive video thumbnail images that will draw viewers in. In the video thumbnail generation system, the generation AI analyzes the video and scores the attractiveness of the content. Next, it extracts scenes with high scores and creates thumbnail images using an image generation AI. This mechanism allows YouTubers and video creators to obtain attractive thumbnail images without much effort. The video thumbnail generation system uses a generation AI to analyze the video. In this process, the generation AI evaluates each scene in the video and scores its attractiveness. For example, it determines whether a particular scene in the video is interesting to the viewer and assigns a high score to that scene. This makes it possible to identify attractive points in the video. Next, it extracts scenes with high scores and creates thumbnail images using an image generation AI. The generation AI automatically selects scenes with high scores and generates thumbnail images based on those scenes. For example, if a particular scene in the video is determined to be attractive to the viewer, it extracts that scene and the image generation AI creates a thumbnail image. This makes it possible to obtain attractive thumbnail images that will draw viewers in. This system allows YouTubers and video creators to obtain attractive thumbnail images without much effort. Traditionally, creating attractive thumbnail images required reviewing one's own video, identifying appealing points, and then cropping and editing them. This invention eliminates that effort. The target audience is individual YouTubers who post videos on YouTube and corporate PR departments. The system can be expanded beyond video thumbnail images to include services that summarize and document footage from fixed-point cameras such as surveillance cameras and dashcams. For example, it can analyze surveillance camera footage, automatically extract and summarize important scenes, and efficiently manage surveillance camera footage. It can also analyze dashcam footage, automatically extract and summarize accident moments and other important scenes, and efficiently manage dashcam footage, allowing for quick access to necessary information.This allows the video thumbnail generation system to produce attractive thumbnail images that will draw viewers in.

[0064] The video thumbnail generation system according to this embodiment comprises an analysis unit, a scoring unit, a cropping unit, and a generation unit. The analysis unit analyzes the video or image. For example, the analysis unit analyzes the frames of the video or image and detects objects within each frame. The analysis unit can also analyze movement and changes within the image. For example, the analysis unit tracks the movement of a specific object within the image and analyzes the pattern of that movement. Furthermore, the analysis unit can analyze audio information within the image and evaluate the relationship between the audio and the image. For example, the analysis unit analyzes scenes in the image where the audio intensifies and evaluates the image of those scenes. The scoring unit scores the attractiveness of the image analyzed by the analysis unit. For example, the scoring unit determines whether a particular scene in the image is interesting to the viewer and assigns a high score to that scene. For example, the scoring unit assigns a score based on viewer reactions, viewing time, click-through rate, etc. The scoring unit can also assign a score considering color information, music, sound effects, etc., within the image. For example, the scoring unit assigns high scores to scenes with vibrant colors in the video. The cropping unit crops out scenes with high scores from the scoring unit. For example, the cropping unit can automatically select high-scoring scenes and crop them. For example, the cropping unit can crop specific scenes from the video frame by frame to use as material for a thumbnail image. The cropping unit can also detect important objects in the video and crop the image around those objects. For example, the cropping unit can detect people in the video and crop the image around them. The generation unit generates thumbnail images based on the scenes cropped by the cropping unit. For example, the generation unit can generate thumbnail images using image generation AI based on the cropped scenes. For example, the generation unit can use image generation AI to analyze the cropped scenes and generate the optimal thumbnail image. The generation unit can also estimate the viewer's emotions and adjust the design of the thumbnail image based on the estimated viewer emotions. For example, if the viewer is excited, the generation unit will generate a thumbnail image with vibrant colors. As a result, the video thumbnail generation system according to this embodiment can generate attractive thumbnail images that will draw viewers in.

[0065] The analysis unit analyzes videos and images. For example, the analysis unit analyzes frames of videos and images and detects objects within each frame. Specifically, the analysis unit uses image recognition technology to identify people, objects, backgrounds, etc., within frames and determine their respective positions and movements. For example, it can use facial recognition technology to detect a person's face and analyze their facial expression and gaze direction. It can also use object recognition technology to identify specific objects such as vehicles, buildings, and animals and track their movement and position. Furthermore, the analysis unit can also analyze movement and changes within the video. For example, it can use motion detection algorithms to track the movement of specific objects within the video and analyze their movement patterns. This allows for the identification of action scenes and important events within the video. In addition, the analysis unit can analyze audio information within the video and evaluate the relationship between audio and video. For example, it can use speech recognition technology to convert audio within the video into text and analyze its content. This allows for the identification of scenes where the audio intensifies or contains specific keywords, and the evaluation of the video in those scenes. Based on these analysis results, the analysis unit can identify important scenes and scenes that are appealing to viewers within the video.

[0066] The scoring unit scores the attractiveness of the video analyzed by the analysis unit. For example, the scoring unit determines whether a particular scene in the video is interesting to the viewer and assigns a high score to that scene. Specifically, the scoring unit assigns scores based on data such as viewer reactions, viewing time, and click-through rates. For example, it can assign high scores to scenes that viewers watched for a long time or scenes that received many clicks. The scoring unit can also assign scores considering color information, music, and sound effects in the video. For example, it can assign high scores to scenes with vivid colors or scenes with emotionally evocative music. Furthermore, the scoring unit can use AI to estimate the viewer's emotions and assign scores based on those emotions. For example, if the viewer is excited or moved, it can assign a high score to that scene. As a result, the scoring unit can accurately identify scenes that are attractive to viewers and provide material for thumbnail generation.

[0067] The cropping unit extracts scenes with high scores determined by the scoring unit. For example, the cropping unit can automatically select high-scoring scenes and crop them. Specifically, the cropping unit crops specific scenes from the video frame by frame to use as material for thumbnail images. For example, it can identify the start and end frames of a high-scoring scene and crop the frames within that range. The cropping unit can also detect important objects in the video and crop the frame around those objects. For example, it can detect a person's face or a specific object and crop the frame around that object. Furthermore, the cropping unit can select the optimal cropping range considering the composition and balance of the video. For example, it can crop frames so that important elements in the video are evenly distributed. As a result, the cropping unit can efficiently generate material for thumbnail images that are attractive to viewers.

[0068] The generation unit generates thumbnail images based on the scenes cropped by the cropping unit. For example, the generation unit uses an image generation AI to generate thumbnail images based on the cropped scenes. Specifically, the generation unit uses the image generation AI to analyze the cropped scenes and generate the optimal thumbnail image. For example, the image generation AI can analyze the colors and composition of the cropped scenes to generate thumbnail images that are appealing to viewers. The generation unit can also estimate the viewer's emotions and adjust the design of the thumbnail image based on the estimated emotions. For example, if the viewer is excited, it can generate a thumbnail image with vibrant colors, and if the viewer is calm, it can generate a thumbnail image with calm colors. Furthermore, the generation unit can add text and graphic elements to the thumbnail image. For example, it can add the video title or catchphrase to the thumbnail image to attract the viewer's interest. As a result, the generation unit can generate attractive thumbnail images that draw viewers in, thereby improving video viewership.

[0069] The analysis unit can analyze video from fixed cameras such as surveillance cameras and dashcams. For example, the analysis unit can analyze surveillance camera video and automatically extract and summarize important scenes. For example, the analysis unit can detect specific movements in surveillance camera video and extract important scenes based on those movements. The analysis unit can also analyze dashcam video and automatically extract and summarize accident moments and other important scenes. For example, the analysis unit can detect collision or sudden braking scenes in dashcam video and extract those scenes. This allows for efficient management of surveillance camera and dashcam video by analyzing fixed camera video. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input surveillance camera video into a generative AI and have the generative AI extract important scenes.

[0070] The scoring unit can determine whether a particular scene in a video is interesting to the viewer and assign a high score to that scene. The scoring unit assigns scores based on factors such as viewer reactions, viewing time, and click-through rates. For example, the scoring unit assigns a high score to scenes that viewers watch for a long time. The scoring unit can also assign scores considering color information, music, and sound effects in the video. For example, the scoring unit assigns a high score to scenes with vivid colors in the video. This allows for the generation of attractive thumbnail images by highly valuing scenes that are interesting to the viewer. Some or all of the above processing in the scoring unit may be performed using, for example, a generative AI, or without a generative AI. For example, the scoring unit can input viewer reaction data into a generative AI and have the generative AI perform the determination of interesting scenes.

[0071] The cropping unit can automatically select high-scoring scenes and crop them. For example, the cropping unit can crop high-scoring scenes frame by frame and use them as material for thumbnail images. For example, the cropping unit can automatically select a specific scene in the video and crop it. The cropping unit can also detect important objects in the video and crop the image around those objects. For example, the cropping unit can detect a person in the video and crop the image around that person. This allows for efficient generation of thumbnail images by automatically selecting and cropping high-scoring scenes. Some or all of the above processing in the cropping unit may be performed using, for example, a generation AI, or without a generation AI. For example, the cropping unit can input high-scoring scenes from the scoring unit into the generation AI and have the generation AI perform the scene cropping.

[0072] The generation unit can generate thumbnail images based on the cropped scenes. For example, the generation unit can generate thumbnail images using an image generation AI based on the cropped scenes. For example, the generation unit can have the image generation AI analyze the cropped scenes and generate the optimal thumbnail image. The generation unit can also estimate the viewer's emotions and adjust the design of the thumbnail image based on the estimated viewer emotions. For example, if the viewer is excited, the generation unit will generate a thumbnail image with vivid colors. In this way, by generating thumbnail images based on cropped scenes, it is possible to obtain attractive thumbnail images that will draw in viewers. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input the cropped scenes into a generation AI and have the generation AI perform the generation of thumbnail images.

[0073] The analysis unit can estimate the viewer's emotions and adjust the video analysis method based on the estimated viewer emotions. For example, if the viewer is excited, the generation AI may prioritize analyzing action scenes in the video. Similarly, if the viewer is relaxed, the generation AI may prioritize analyzing landscape scenes. Furthermore, if the viewer is sad, the generation AI may prioritize analyzing emotional scenes. This allows for more appropriate analysis by adjusting the video analysis method according to the viewer's emotions. The estimation of viewer emotions is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using a generation AI, or not. For example, the analysis unit can input viewer emotion data into a generation AI and have the generation AI adjust the video analysis method.

[0074] The analysis unit can analyze audio information within a video and evaluate the relationship between audio and video during video analysis. For example, the analysis unit can analyze scenes where the audio intensifies and evaluate the video in those scenes. It can also analyze scenes where the audio in the video becomes quieter and evaluate the video in those scenes. Furthermore, the analysis unit can analyze the synchronization between audio and video within a video and evaluate scenes with high correlation. By evaluating the relationship between audio and video, more accurate video analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input audio data from the video into a generative AI and have the generative AI perform the evaluation of the relationship between audio and video.

[0075] The analysis unit can analyze motion patterns within a video and extract motion characteristics during video analysis. For example, the analysis unit can analyze scenes with fast motion and extract their characteristics. It can also analyze scenes with slow motion and extract their characteristics. Furthermore, the analysis unit can analyze scenes with complex motion and extract their characteristics. By extracting motion characteristics in this way, the accuracy of video analysis is improved. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input motion data from the video into a generative AI and have the generative AI perform the extraction of motion characteristics.

[0076] The analysis unit can estimate the viewer's emotions and determine the priority of the video to be analyzed based on the estimated viewer emotions. For example, if the viewer is excited, the analysis unit may prioritize analyzing action scenes. It may also prioritize analyzing landscape scenes if the viewer is relaxed. Furthermore, if the viewer is sad, it may prioritize analyzing emotional scenes. This allows for more effective video analysis by prioritizing the video according to the viewer's emotions. The estimation of the viewer's emotions is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or not. For example, the analysis unit can input viewer emotion data into a generative AI and have the generative AI determine the video prioritization.

[0077] The analysis unit can perform video analysis while taking into account information about the video's shooting location. For example, if the video was shot in a tourist area, the analysis unit can analyze the characteristics of that location. It can also analyze the characteristics of an urban area if the video was shot in a city. Furthermore, if the video was shot in a natural environment, the analysis unit can analyze the characteristics of that location. This improves the accuracy of video analysis by considering information about the shooting location. Some or all of the above-described processes in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input information about the video's shooting location into a generative AI and have the generative AI perform the analysis.

[0078] The analysis unit can analyze text information within a video and evaluate the relationship between the text and the video during video analysis. For example, the analysis unit can analyze scenes where text is displayed in the video and evaluate the video of those scenes. The analysis unit can also analyze scenes where the text in the video matches the content of the video and evaluate the relationship between them. Furthermore, the analysis unit can analyze scenes where the text in the video contains important information and evaluate the video of those scenes. By evaluating the relationship between text and video, the accuracy of video analysis is improved. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input text data from the video into a generative AI and have the generative AI perform the evaluation of the relationship between the text and the video.

[0079] The scoring unit can estimate the viewer's emotions and adjust the scoring method based on the estimated viewer emotions. For example, if the viewer is excited, the scoring unit may give a high score to action scenes. Similarly, if the viewer is relaxed, the scoring unit may give a high score to landscape scenes. Furthermore, if the viewer is sad, the scoring unit may give a high score to emotional scenes. This allows for more appropriate scoring by adjusting the scoring method according to the viewer's emotions. The estimation of viewer emotions is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the scoring unit may be performed using, for example, a generative AI, or not. For example, the scoring unit can input viewer emotion data into a generative AI and have the generative AI adjust the scoring method.

[0080] The scoring unit can analyze the color information within the video during the scoring process and reflect the attractiveness of the colors in the score. For example, the scoring unit can assign a high score to scenes with vibrant colors in the video. It can also assign a high score to scenes with muted colors in the video. Furthermore, it can assign a high score to scenes with monochrome colors in the video. By reflecting the attractiveness of the colors in the score, more accurate scoring becomes possible. Some or all of the above processing in the scoring unit may be performed using, for example, a generative AI, or without a generative AI. For example, the scoring unit can input color data from the video into a generative AI and have the generative AI perform the scoring of the attractiveness of the colors.

[0081] The scoring unit can evaluate the influence of music and sound effects within the video during the scoring process and reflect this in the score. For example, the scoring unit can assign a high score to scenes where the music in the video builds up. It can also assign a high score to scenes where sound effects in the video are emphasized. Furthermore, the scoring unit can assign a high score to scenes where the music and video are synchronized. By reflecting the influence of music and sound effects in the score, more accurate scoring becomes possible. Some or all of the above processing in the scoring unit may be performed using, for example, a generative AI, or without a generative AI. For example, the scoring unit can input music data from the video into a generative AI and have the generative AI perform the evaluation of the influence of music and sound effects.

[0082] The scoring unit can estimate the viewer's emotions and adjust the weighting of the score based on the estimated viewer emotions. For example, if the viewer is excited, the scoring unit may give more weight to action scenes. It can also give more weight to landscape scenes if the viewer is relaxed. Furthermore, if the viewer is sad, the scoring unit may give more weight to emotional scenes. This allows for more appropriate scoring by adjusting the weighting of the score according to the viewer's emotions. The estimation of viewer emotions is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the scoring unit may be performed using, for example, a generative AI, or not. For example, the scoring unit can input viewer emotion data into a generative AI and have the generative AI adjust the weighting of the score.

[0083] The scoring unit can adjust the score based on the length of the video during the scoring process. For example, if the video is short, the scoring unit will assign higher scores to important scenes. If the video is long, the scoring unit can also assign scores considering the overall balance. Furthermore, the scoring unit can adjust the weighting of the score according to the length of the video. This allows for more appropriate scoring by adjusting the score based on the length of the video. Some or all of the above processing in the scoring unit may be performed using, for example, a generative AI, or without a generative AI. For example, the scoring unit can input video length data into a generative AI and have the generative AI perform the score adjustments.

[0084] The scoring unit can apply different scoring algorithms depending on the genre of the video during the scoring process. For example, the scoring unit can apply a scoring algorithm that emphasizes action scenes to action videos. It can also apply a scoring algorithm that emphasizes the amount of information to documentary videos. Furthermore, it can apply a scoring algorithm that emphasizes the humorous elements to comedy videos. By applying a scoring algorithm according to the genre of the video, more appropriate scoring becomes possible. Some or all of the above processing in the scoring unit may be performed using, for example, a generative AI, or without a generative AI. For example, the scoring unit can input video genre data into a generative AI and have the generative AI execute the application of the scoring algorithm.

[0085] The editing unit can estimate the viewer's emotions and select scenes to edit based on those emotions. For example, if the viewer is excited, the editing unit may prioritize editing action scenes. If the viewer is relaxed, it may prioritize editing landscape scenes. Furthermore, if the viewer is sad, it may prioritize editing emotional scenes. This allows for the selection of more appropriate scenes by tailoring the scene selection to the viewer's emotions. The estimation of the viewer's emotions is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the editing unit may be performed using a generative AI, or not. For example, the editing unit can input viewer emotion data into a generative AI and have the generative AI perform the scene selection.

[0086] The cropping unit can select the optimal frame by considering the speed of motion within the video during the cropping process. For example, when cropping a scene with fast motion, the cropping unit can select the peak of the motion. It can also select the beginning and end of motion when cropping a scene with slow motion. Furthermore, when cropping a scene with complex motion, the cropping unit can select the center of motion. This allows for the selection of a more appropriate frame by considering the speed of motion. Some or all of the above processing in the cropping unit may be performed using, for example, a generative AI, or without one. For example, the cropping unit can input motion data from the video into a generative AI and have the generative AI select the optimal frame.

[0087] The cropping unit can detect important objects within the video during cropping and crop the image around those objects. For example, the cropping unit can detect a person in the video and crop the image around that person. It can also detect a vehicle in the video and crop the image around that vehicle. Furthermore, it can detect a building in the video and crop the image around that building. By cropping the image around important objects, it is possible to emphasize scenes that are appealing to the viewer. Some or all of the above processing in the cropping unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the cropping unit can input object data from the video into a generative AI and have the generative AI perform object detection and cropping.

[0088] The editing unit can estimate the viewer's emotions and adjust the order of scenes to be edited based on those emotions. For example, if the viewer is excited, the editing unit can place action scenes first. If the viewer is relaxed, it can place landscape scenes first. Furthermore, if the viewer is sad, it can place emotional scenes first. This allows for more effective video editing by adjusting the order of scenes according to the viewer's emotions. The estimation of the viewer's emotions is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the editing unit may be performed using a generative AI, or not. For example, the editing unit can input viewer emotion data into a generative AI and have the generative AI adjust the order of scenes.

[0089] The cropping unit can select the optimal frame during cropping, taking into account the resolution of the video. For example, in high-resolution video, the cropping unit can select a frame where details are clearly visible. In low-resolution video, the cropping unit can also select a frame that offers a good overall balance. Furthermore, the cropping unit can select the optimal frame according to the resolution. This allows for the selection of a more appropriate frame by considering the resolution. Some or all of the above processing in the cropping unit may be performed using, for example, a generation AI, or without a generation AI. For example, the cropping unit can input video resolution data into a generation AI and have the generation AI select the optimal frame.

[0090] The cropping unit can select the optimal frame by considering the text information within the video during the cropping process. For example, the cropping unit can prioritize cropping scenes where text is displayed in the video. It can also prioritize cropping scenes where the text in the video matches the content of the video. Furthermore, the cropping unit can prioritize cropping scenes where the text in the video contains important information. This allows for the selection of a more appropriate frame by considering the text information. Some or all of the above processing in the cropping unit may be performed using, for example, a generative AI, or without a generative AI. For example, the cropping unit can input text data from the video into a generative AI and have the generative AI select the optimal frame.

[0091] The generation unit can estimate the viewer's emotions and adjust the thumbnail image design based on the estimated emotions. For example, if the viewer is excited, the generation unit can generate a thumbnail image with vibrant colors. It can also generate a thumbnail image with calm colors if the viewer is relaxed. Furthermore, if the viewer is sad, the generation unit can generate an emotionally resonant thumbnail image. This allows for the creation of more appealing thumbnail images by adjusting the design according to the viewer's emotions. The estimation of the viewer's emotions is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using a generative AI, or not. For example, the generation unit can input viewer emotion data into a generative AI and have the generative AI adjust the thumbnail image design.

[0092] The generation unit can select the optimal color tone when generating thumbnail images, taking into account the color information within the video. For example, the generation unit can select the color tone of a thumbnail image based on scenes with vibrant colors within the video. It can also select the color tone of a thumbnail image based on scenes with muted colors within the video. Furthermore, the generation unit can select the color tone of a thumbnail image based on scenes with monochrome colors within the video. By considering color information, it is possible to generate more appealing thumbnail images. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the generation unit can input color data from the video into a generation AI and have the generation AI select the optimal color tone.

[0093] The generation unit can apply a design that emphasizes important objects in the video when generating thumbnail images. For example, the generation unit can apply a design that emphasizes people in the video. It can also apply a design that emphasizes vehicles in the video. Furthermore, it can apply a design that emphasizes buildings in the video. This allows for the creation of thumbnail images that are appealing to viewers by emphasizing important objects. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input object data from the video into a generation AI and have the generation AI execute the object emphasis design.

[0094] The generation unit can estimate the viewer's emotions and adjust the placement of thumbnail images based on the estimated emotions. For example, if the viewer is excited, the generation unit may center the thumbnail images around action scenes. If the viewer is relaxed, the generation unit may center the thumbnail images around landscape scenes. Furthermore, if the viewer is sad, the generation unit may center the thumbnail images around emotional scenes. By adjusting the placement of thumbnail images according to the viewer's emotions, more appealing thumbnail images can be generated. The estimation of the viewer's emotions is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input viewer emotion data into a generation AI and have the generation AI adjust the placement of thumbnail images.

[0095] The generation unit can apply different design templates depending on the video genre when generating thumbnail images. For example, the generation unit can apply a design template that emphasizes action scenes to action videos. It can also apply a design template that prioritizes information to documentary videos. Furthermore, it can apply a design template that emphasizes humor to comedy videos. By applying a design template appropriate to the genre, it is possible to generate more appropriate thumbnail images. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input video genre data into a generation AI and have the generation AI apply the design template.

[0096] The generation unit can select the optimal layout when generating thumbnail images, taking into account the text information within the video. For example, the generation unit can select a thumbnail image layout based on scenes where text within the video is displayed. It can also select a thumbnail image layout based on scenes where the text within the video matches the content of the video. Furthermore, the generation unit can select a thumbnail image layout based on scenes where the text within the video contains important information. This allows for the selection of a more appropriate layout by considering the text information. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the generation unit can input text data from the video into a generation AI and have the generation AI select the optimal layout.

[0097] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0098] The analysis unit can analyze the speed of movement of objects in the video and evaluate the importance of a scene based on the speed of movement. For example, the analysis unit will rate scenes with fast movement highly and scenes with slow movement lower. The analysis unit can also rate scenes with abrupt changes in speed particularly highly. Furthermore, the analysis unit can evaluate the relationship between speed of movement and viewer reactions. This allows for a more accurate identification of scenes that are appealing to viewers by considering the speed of movement.

[0099] The scoring unit can analyze the emotional tone of the audio within the video and assign a score based on that tone. For example, if the audio in the video is exciting, the scoring unit will assign a high score to that scene. Conversely, if the audio is calm, the scoring unit can assign a low score to that scene. Furthermore, the scoring unit can also associate the emotional tone of the audio with the viewer's reaction and assign a score accordingly. This allows for a more accurate evaluation of scenes that are appealing to viewers by considering the emotional tone of the audio.

[0100] The cropping function can crop scenes considering the size of objects within the video. For example, it can prioritize cropping scenes containing large objects. It can also crop scenes containing small objects. Furthermore, it can select scenes by associating object size with viewer reactions. This allows for the efficient cropping of scenes that are appealing to viewers by considering object size.

[0101] The generation unit can select the optimal brightness for thumbnail images by considering the intensity of light in the video. For example, the generation unit can generate a bright thumbnail image based on a scene with strong light. It can also generate a dark thumbnail image based on a scene with weak light. Furthermore, the generation unit can adjust the brightness by relating the intensity of light to the viewer's reaction. This allows for the generation of thumbnail images that are appealing to viewers by considering the intensity of light.

[0102] The analysis unit can analyze background sounds within a video and evaluate the importance of a scene based on the type of sound. For example, the analysis unit can rate scenes with noisy background sounds highly. Conversely, it can rate scenes with quiet background sounds lower. Furthermore, the analysis unit can also evaluate the relationship between the type of background sound and the viewer's reaction. This allows for a more accurate identification of scenes that are appealing to viewers by considering background sounds.

[0103] The scoring unit can estimate the viewer's emotions and evaluate the facial expressions of characters in the video based on those estimated emotions. For example, if the viewer is excited, scenes with smiling characters will receive a high score. Similarly, if the viewer is sad, scenes with crying characters will receive a high score. Furthermore, if the viewer is relaxed, scenes with calm-looking characters will receive a high score. This allows for more appropriate scoring by evaluating character expressions according to the viewer's emotions.

[0104] The cropping function can estimate the viewer's emotions and adjust how scenes are cropped based on those emotions. For example, if the viewer is excited, it can crop action scenes more prominently. If the viewer is relaxed, it can crop landscape scenes more broadly. Furthermore, if the viewer is sad, it can crop to focus on emotional scenes. By adjusting how scenes are cropped according to the viewer's emotions, it is possible to generate more effective thumbnail images.

[0105] The generation unit can select the optimal layout for thumbnail images by considering the direction of movement within the video. For example, based on a scene where movement moves from right to left, the generation unit will place important elements on the right side. Similarly, based on a scene where movement moves from left to right, it can place important elements on the left side. Furthermore, it can adjust the layout by associating the direction of movement with viewer reactions. This allows for the generation of thumbnail images that are appealing to viewers by considering the direction of movement.

[0106] The analysis unit can analyze changes in color within the video and evaluate the importance of scenes based on those changes. For example, it can give a higher rating to scenes where colors change rapidly, and a lower rating to scenes where colors change gradually. Furthermore, it can also evaluate the relationship between color changes and viewer reactions. This allows for a more accurate identification of scenes that are appealing to viewers by considering changes in color.

[0107] The scoring unit can estimate the viewer's emotions and evaluate the impact of the music in the video based on those estimated emotions. For example, if the viewer is excited, scenes with upbeat music will receive a high score. Similarly, if the viewer is relaxed, scenes with slow-tempo music will receive a high score. Furthermore, if the viewer is sad, scenes with emotionally moving music will receive a high score. This allows for more appropriate scoring by evaluating the impact of music according to the viewer's emotions.

[0108] The following briefly describes the processing flow for example form 2.

[0109] Step 1: The analysis unit analyzes the video or image. The analysis unit analyzes the frames of the video or image and detects objects within each frame. It also analyzes movement and changes within the image, tracks the movement of specific objects, and analyzes the patterns of that movement. Furthermore, it can analyze the audio information within the image and evaluate the relationship between the audio and the image. For example, it can analyze scenes where the audio intensifies and evaluate the video of those scenes. Step 2: The scoring unit scores the attractiveness of the video analyzed by the analysis unit. The scoring unit determines whether a particular scene in the video is interesting to the viewer and assigns a high score to that scene. The score is based on viewer reactions, viewing time, click-through rate, etc. It can also take into account color information, music, sound effects, etc. in the video when assigning a score. For example, a scene with vivid colors will be given a high score. Step 3: The cropping unit extracts scenes with high scores determined by the scoring unit. The cropping unit automatically selects high-scoring scenes and crops them. For example, it can crop specific scenes frame by frame to use as material for a thumbnail image. It can also detect important objects and crop the image around them. For example, it can detect a person and crop the image around that person. Step 4: The generation unit generates thumbnail images based on the scenes cropped by the cropping unit. The generation unit uses an image generation AI to generate thumbnail images based on the cropped scenes. For example, the image generation AI analyzes the cropped scenes and generates the optimal thumbnail image. It can also estimate the viewer's emotions and adjust the thumbnail image design based on the estimated viewer emotions. For example, if the viewer is excited, a thumbnail image with vibrant colors will be generated.

[0110] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0111] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0112] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0113] Each of the multiple elements described above, including the analysis unit, scoring unit, cropping unit, and generation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit analyzes video and images using the camera 42 and microphone 38B of the smart device 14 and detects objects in each frame using the control unit 46A. The scoring unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and scores the attractiveness of the analyzed video. The cropping unit automatically selects and crops scenes with high scores using, for example, the control unit 46A of the smart device 14. The generation unit generates thumbnail images based on the cropped scenes using, for example, the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0114] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0115] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0116] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0117] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0118] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0120] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0121] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0122] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0123] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0124] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0125] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0126] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0127] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0128] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0129] Each of the multiple elements described above, including the analysis unit, scoring unit, cropping unit, and generation unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit analyzes video and images using the camera 42 and microphone 238 of the smart glasses 214 and detects objects in each frame using the control unit 46A. The scoring unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and scores the attractiveness of the analyzed video. The cropping unit automatically selects and crops scenes with high scores using the control unit 46A of the smart glasses 214. The generation unit generates thumbnail images based on the cropped scenes using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0130] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0131] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0132] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0133] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0134] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0136] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0137] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0138] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0139] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0140] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0141] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0142] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0143] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0144] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0145] Each of the multiple elements described above, including the analysis unit, scoring unit, cropping unit, and generation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit analyzes video and images using the camera 42 and microphone 238 of the headset terminal 314 and detects objects in each frame using the control unit 46A. The scoring unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and scores the attractiveness of the analyzed video. The cropping unit automatically selects and crops scenes with high scores using the control unit 46A of the headset terminal 314. The generation unit generates thumbnail images based on the cropped scenes using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0146] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0147] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0148] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0150] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0152] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0153] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0154] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0155] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0156] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0157] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0158] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0159] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0160] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0161] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0162] Each of the multiple elements described above, including the analysis unit, scoring unit, cropping unit, and generation unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit analyzes video and images using the camera 42 and microphone 238 of the robot 414 and detects objects in each frame using the control unit 46A. The scoring unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and scores the attractiveness of the analyzed video. The cropping unit automatically selects and crops scenes with high scores using, for example, the control unit 46A of the robot 414. The generation unit generates thumbnail images based on the cropped scenes using, for example, the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0163] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0164] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0165] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0166] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0167] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0168] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0170] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0171] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0172] 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.

[0173] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0174] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0175] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0176] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0177] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0178] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0179] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0180] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0181] (Note 1) The analysis unit analyzes videos and images, A scoring unit that scores the attractiveness of the video analyzed by the aforementioned analysis unit, The aforementioned scoring unit extracts scenes with high scores, The system includes a generation unit that generates a thumbnail image based on the scene cropped by the cropping unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Analyzes footage from fixed cameras such as surveillance cameras and dashcams. The system described in Appendix 1, characterized by the features described herein. (Note 3) The scoring unit, The system determines whether a particular scene in the video is interesting to the viewer and assigns a high score to that scene. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned cut portion is, Automatically selects scenes with high scores and cuts them out. The system described in Appendix 1, characterized by the features described herein. (Note 5) The generating unit is Generate a thumbnail image based on the extracted scene. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, The system estimates the viewer's emotions and adjusts the video analysis method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, During video analysis, the audio information within the video is analyzed to evaluate the relationship between the audio and the video. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, When analyzing video, the patterns of movement within the video are analyzed, and the characteristics of the movement are extracted. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, It estimates the viewer's emotions and determines the priority of videos to analyze based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, When analyzing video footage, the analysis takes into account information about the location where the video was filmed. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, During video analysis, the text information within the video is analyzed, and the relationship between the text and the video is evaluated. The system described in Appendix 1, characterized by the features described herein. (Note 12) The scoring unit, The system estimates the audience's emotions and adjusts the scoring based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The scoring unit, During the scoring process, the color information within the video is analyzed, and the attractiveness of the colors is reflected in the score. The system described in Appendix 1, characterized by the features described herein. (Note 14) The scoring unit, When scoring, the influence of music and sound effects in the video is evaluated and reflected in the score. The system described in Appendix 1, characterized by the features described herein. (Note 15) The scoring unit, The system estimates the audience's emotions and adjusts the score weighting based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The scoring unit, When scoring, the score is adjusted based on the length of the video. The system described in Appendix 1, characterized by the features described herein. (Note 17) The scoring unit, When scoring, different scoring algorithms are applied depending on the genre of the video. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned cut portion is, The program estimates the viewer's emotions and selects scenes to include based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned cut portion is, When cropping, the optimal frame is selected considering the speed of movement within the video. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned cut portion is, During cropping, the system detects important objects within the video and crops the image with those objects as the center. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned cut portion is, The system estimates the viewer's emotions and adjusts the order of scenes to be edited based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned cut portion is, When cropping, the optimal frame is selected considering the video resolution. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned cut portion is, When cropping, the optimal frame is selected considering the text information within the video. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is It estimates the viewer's emotions and adjusts the thumbnail image design based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The generating unit is When generating thumbnail images, the system selects the optimal color scheme by considering the color information within the video. The system described in Appendix 1, characterized by the features described herein. (Note 26) The generating unit is When generating thumbnail images, apply a design that highlights important objects within the video. The system described in Appendix 1, characterized by the features described herein. (Note 27) The generating unit is It estimates the viewer's emotions and adjusts the placement of thumbnail images based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The generating unit is When generating thumbnail images, different design templates are applied depending on the video genre. The system described in Appendix 1, characterized by the features described herein. (Note 29) The generating unit is When generating thumbnail images, the optimal layout is selected by considering the text information within the video. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The analysis unit analyzes videos and images, A scoring unit that scores the attractiveness of the video analyzed by the aforementioned analysis unit, The aforementioned scoring unit extracts scenes with high scores, The system includes a generation unit that generates a thumbnail image based on the scene cropped by the cropping unit. A system characterized by the following features.

2. The aforementioned analysis unit, Analyzes footage from fixed cameras such as surveillance cameras and dashcams. The system according to feature 1.

3. The scoring unit, The system determines whether a particular scene in the video is interesting to the viewer and assigns a high score to that scene. The system according to feature 1.

4. The aforementioned cut portion is, Automatically selects scenes with high scores and cuts them out. The system according to feature 1.

5. The generating unit is Generate a thumbnail image based on the extracted scene. The system according to feature 1.

6. The aforementioned analysis unit, The system estimates the viewer's emotions and adjusts the video analysis method based on those estimated emotions. The system according to feature 1.

7. The aforementioned analysis unit, During video analysis, the audio information within the video is analyzed to evaluate the relationship between the audio and the video. The system according to feature 1.

8. The aforementioned analysis unit, When analyzing video, the patterns of movement within the video are analyzed, and the characteristics of the movement are extracted. The system according to feature 1.

9. The aforementioned analysis unit, It estimates the viewer's emotions and determines the priority of videos to analyze based on those estimated emotions. The system according to feature 1.

10. The aforementioned analysis unit, When analyzing video footage, the analysis takes into account information about the location where the video was filmed. The system according to feature 1.

Images