System

Abstract

An object of the system according to the embodiment is to search for a specific scene in a moving image by text and automatically generate a highlight moving image.SOLUTION: A system according to an embodiment includes a moving image analysis unit, a scene extraction unit, and a highlight generation unit. The moving image analysis unit analyzes a moving image and text input from a user. The scene extraction unit extracts the scene designated by the text from the moving image analyzed by the moving image analysis unit. The highlight generation unit automatically generates a highlight moving image based on the scene extracted by the scene extraction unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the problem that it is difficult to search for specific scenes in a video using text and automatically generate a highlight video.

[0005] The system according to the embodiment aims to search for specific scenes in a video using text and automatically generate a highlight video. [Means for solving the problem]

[0006] The system according to the embodiment includes a video analysis unit, a scene extraction unit, and a highlight generation unit. The video analysis unit analyzes video and text input by a user. The scene extraction unit extracts scenes specified in the text from the video analyzed by the video analysis unit. The highlight generation unit automatically generates a highlight video based on the scenes extracted by the scene extraction unit. [Effects of the Invention]

[0007] The system according to the embodiment can search for a specific scene in a video using text and automatically generate a highlight video. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A highlight video generation system according to an embodiment of the present invention is a system that searches for a specific scene in a video using text and automatically generates a highlight video that includes the scene. This allows a user to easily create a video that includes the specific scene.

[0029] A highlight video generation system according to an embodiment includes a video analysis unit, a scene extraction unit, and a highlight generation unit. The video analysis unit analyzes video and text input by a user. For example, the video analysis unit analyzes the content of the video using a generation AI and identifies scenes specified in the text. The generation AI analyzes the relevance between the video and the text using a text generation AI (e.g., LLM) or a multimodal generation AI. The scene extraction unit extracts scenes specified in the text from the video analyzed by the video analysis unit. For example, the scene extraction unit cuts out the scenes identified by the generation AI from the video. The generation AI identifies the start and end times of the scenes and extracts video within that range. The highlight generation unit automatically generates a highlight video based on the scenes extracted by the scene extraction unit. For example, the highlight generation unit connects the extracted scenes to generate a visually appealing highlight video. The generation AI automatically adds scene transitions and effects to create a visually appealing video. This enables the highlight video generation system according to an embodiment to automatically generate a highlight video including specific scenes based on user input. For example, if a user inputs text such as "Yanagi's turn at bat in a baseball broadcast," the AI ​​will identify that scene and create a highlight video. Similarly, if a user inputs text such as "A specific member's part in a Naniwa Danshi concert," the AI ​​will identify that scene and create a highlight video.

[0030] The video analysis unit can analyze audio data in a video and extract scenes based on specific keywords or audio patterns. For example, the video analysis unit uses a generative AI to analyze audio data in a video and extract scenes based on specific keywords or audio patterns. For example, it can detect keywords such as "goal" or "home run" from the commentary of a sports broadcast and extract those scenes. The video analysis unit can also convert audio data into text using speech recognition technology and extract scenes based on that text data. For example, it can convert commentary audio into text using speech recognition technology and detect specific keywords from that text data. This makes it possible to analyze the audio data and extract scenes based on specific keywords or audio patterns.

[0031] The video analysis unit analyzes video metadata and can perform more accurate scene extraction. For example, the video analysis unit uses a generative AI to analyze video metadata and extract scenes based on the shooting date and time and location. For example, it extracts scenes shot on a specific date or location. The video analysis unit can also analyze performer information included in the metadata and extract scenes featuring specific performers. For example, it extracts scenes featuring specific people based on the performer information. This makes it possible to perform more accurate scene extraction by analyzing metadata.

[0032] The video analysis unit can analyze multiple videos simultaneously and extract common scenes between different videos. For example, the video analysis unit uses a generative AI to simultaneously analyze multiple videos and extract common scenes. For example, it extracts common scenes from videos of the same event filmed from different camera angles. The video analysis unit can also analyze videos obtained from different sources and extract common scenes. For example, it extracts scenes of the same news event from news videos from different news channels. This allows multiple videos to be analyzed simultaneously and common scenes to be extracted.

[0033] The video analysis unit can analyze video in real time and extract specific scenes during live streaming. For example, the video analysis unit uses generative AI to analyze live streaming video in real time and extract specific scenes. For example, goal scenes during a sports game can be extracted in real time. The video analysis unit can also analyze audio data during live streaming and extract scenes based on specific keywords. For example, it can detect keywords such as "goal" or "score" from the commentary audio and extract those scenes in real time. This makes it possible to analyze video in real time and extract specific scenes during live streaming.

[0034] The video analysis unit can understand the context of the text input and extract scenes by taking synonyms and related words into consideration. For example, the video analysis unit uses a generative AI to analyze the context of the text input and extract scenes by taking synonyms and related words into consideration. For example, it treats "goal" and "score" as having the same meaning and extracts scenes. The video analysis unit can also refer to related background information and topic models to understand the context of the text input. For example, it collects related news articles and academic papers and extracts scenes based on that information. This allows it to understand the context of the text input and extract scenes by taking synonyms and related words into consideration.

[0035] The video analysis unit can refer to the user's past search history and extract scenes based on the user's preferences. For example, the video analysis unit uses a generation AI to analyze the user's past search history and extract scenes based on the user's preferences. For example, it prioritizes the extraction of scenes related to keywords that have been frequently searched in the past. The video analysis unit can also analyze the user's viewing history and extract scenes based on preferences. For example, it extracts related scenes based on the content of videos viewed in the past. This makes it possible to refer to the user's past search history and extract scenes based on preferences.

[0036] The video analysis unit can automatically translate text entered in different languages ​​and extract scenes in multiple languages. For example, the video analysis unit uses a generation AI to automatically translate text entered in different languages ​​and extract scenes in multiple languages. For example, it translates text entered in English or French into Japanese and extracts scenes. The video analysis unit can also use machine translation technology to translate text entered in different languages. For example, it uses neural translation technology to perform highly accurate translation and extracts scenes based on the translation results. This makes it possible to automatically translate text entered in different languages ​​and extract scenes in multiple languages.

[0037] The video analysis unit can analyze image data and audio data related to text input and perform multimodal scene extraction. For example, the video analysis unit can analyze image data and audio data related to text input using a generative AI and perform multimodal scene extraction. For example, it can extract scenes by combining text and image data. The video analysis unit can also extract scenes by combining text and audio data. For example, it can analyze the relevance between text and audio data and extract scenes based on that relevance. This makes it possible to analyze image and audio data related to text input and perform multimodal scene extraction.

[0038] The highlight generation unit can automatically edit the scenes extracted by the scene extraction unit to generate a visually appealing highlight video. The highlight generation unit, for example, automatically edits the scenes extracted by a generation AI to generate a visually appealing highlight video. For example, it automatically adds scene transitions and effects. The highlight generation unit can also perform color correction and audio adjustment for the scenes to generate a visually appealing video. For example, it performs color correction and adjusts the hue of the scenes. In this way, the extracted scenes can be automatically edited to generate a visually appealing highlight video.

[0039] The highlight generation unit can automatically add music and sound effects to scenes extracted by the scene extraction unit to enhance the entertainment value. The highlight generation unit can automatically add music and sound effects to scenes extracted by the generation AI to enhance the entertainment value. For example, it can select music that matches the atmosphere of the scene and add it to the background. The highlight generation unit can also add sound effects to important moments in a scene to attract the viewer's attention. For example, it can add sound effects of cheers to a goal scene. In this way, music and sound effects can be automatically added to extracted scenes to enhance the entertainment value.

[0040] The highlight generation unit can combine scenes extracted from different videos to generate a crossover highlight video. For example, the highlight generation unit uses a generation AI to combine scenes extracted from different videos to generate a crossover highlight video. For example, highlight scenes from different sports can be combined into a single video. The highlight generation unit can also combine videos of different genres to create a new story. For example, scenes from a music concert and a sporting event can be combined. This makes it possible to combine scenes extracted from different videos to generate a crossover highlight video.

[0041] The highlight generation unit can automatically generate multiple highlight videos based on the user's preferences and provide the user with options. For example, the highlight generation unit uses a generation AI to automatically generate multiple highlight videos based on the user's preferences and provide the user with options. For example, multiple highlight videos using different editing styles or music are generated. The highlight generation unit can also suggest highlight videos that match the user's preferences based on the user's viewing history. For example, related highlight videos are generated based on the content of videos viewed in the past. This makes it possible to automatically generate multiple highlight videos based on the user's preferences and provide the user with options.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The highlight video generation system can also analyze a user's viewing history and extract scenes based on the content of videos previously viewed. For example, related scenes can be extracted based on scenes from sports games or live music concerts previously viewed by the user. The system can also learn the user's preferences based on the viewing history and preferentially extract scenes that match the preferences. This makes it possible to generate a more personalized highlight video by utilizing the user's viewing history.

[0044] The highlight video generation system can further analyze users' real-time viewing data and extract scenes based on their reactions while watching. For example, it can analyze the timing of clicks and playback stop while watching to identify scenes of interest. It can also collect comments and ratings while watching in real time and extract scenes based on their content. This makes it possible to use real-time viewing data to generate highlight videos that match the user's interests.

[0045] The highlight video generation system can also combine videos of different genres to create new stories. For example, it can combine scenes from a sports game and a live music concert to generate a highly entertaining highlight video. It can also combine scenes from a movie and a documentary to tell a story from a new perspective. This allows it to combine videos of different genres and provide viewers with a new experience.

[0046] The highlight video generation system can further refer to the user's past search history and extract scenes based on the user's preferences. For example, it can preferentially extract scenes related to keywords that have been frequently searched in the past. It can also analyze the user's viewing history and extract scenes based on the user's preferences. This makes it possible to refer to the user's past search history and extract scenes based on the user's preferences.

[0047] The highlight video generation system can also automatically translate text input in different languages ​​and extract scenes in multiple languages. For example, text input in English or French can be translated into Japanese and scenes extracted. Machine translation technology can also be used to translate text input in different languages. For example, neural translation technology can be used to perform highly accurate translation, and scenes can be extracted based on the translation results. This makes it possible to automatically translate text input in different languages ​​and extract scenes in multiple languages.

[0048] The highlight video generation system can also analyze image and audio data related to text input to perform multimodal scene extraction. For example, scenes can be extracted by combining text and image data. Scenes can also be extracted by combining text and audio data. This makes it possible to analyze image and audio data related to text input and perform multimodal scene extraction.

[0049] The processing flow of the first embodiment will be briefly explained below.

[0050] Step 1: The video analysis unit analyzes the video and text input by the user. Using a generation AI, the content of the video is analyzed and the scene specified in the text is identified. The generation AI then uses a text generation AI (e.g., LLM) or a multimodal generation AI to analyze the relevance between the video and the text. Step 2: The scene extraction unit extracts scenes specified by text from the video analyzed by the video analysis unit. It identifies the start and end times of the scenes identified by the generation AI and extracts videos within that range. Step 3: The highlight generation unit automatically generates a highlight video based on the scenes extracted by the scene extraction unit. The extracted scenes are linked together to generate a visually appealing highlight video. The generation AI automatically adds scene transitions and effects to create a visually appealing video.

[0051] (Example 2) A highlight video generation system according to an embodiment of the present invention is a system that searches for a specific scene in a video using text and automatically generates a highlight video that includes the scene. This allows a user to easily create a video that includes the specific scene.

[0052] A highlight video generation system according to an embodiment includes a video analysis unit, a scene extraction unit, and a highlight generation unit. The video analysis unit analyzes video and text input by a user. For example, the video analysis unit analyzes the content of the video using a generation AI and identifies scenes specified in the text. The generation AI analyzes the relevance between the video and the text using a text generation AI (e.g., LLM) or a multimodal generation AI. The scene extraction unit extracts scenes specified in the text from the video analyzed by the video analysis unit. For example, the scene extraction unit cuts out the scenes identified by the generation AI from the video. The generation AI identifies the start and end times of the scenes and extracts video within that range. The highlight generation unit automatically generates a highlight video based on the scenes extracted by the scene extraction unit. For example, the highlight generation unit connects the extracted scenes to generate a visually appealing highlight video. The generation AI automatically adds scene transitions and effects to create a visually appealing video. This enables the highlight video generation system according to an embodiment to automatically generate a highlight video including specific scenes based on user input. For example, if a user inputs text such as "Yanagi's turn at bat in a baseball broadcast," the AI ​​will identify that scene and create a highlight video. Similarly, if a user inputs text such as "A specific member's part in a Naniwa Danshi concert," the AI ​​will identify that scene and create a highlight video.

[0053] The video analysis unit can analyze audio data in a video and extract scenes based on specific keywords or audio patterns. For example, the video analysis unit uses a generative AI to analyze audio data in a video and extract scenes based on specific keywords or audio patterns. For example, it can detect keywords such as "goal" or "home run" from the commentary of a sports broadcast and extract those scenes. The video analysis unit can also convert audio data into text using speech recognition technology and extract scenes based on that text data. For example, it can convert commentary audio into text using speech recognition technology and detect specific keywords from that text data. This makes it possible to analyze the audio data and extract scenes based on specific keywords or audio patterns.

[0054] The video analysis unit analyzes video metadata and can perform more accurate scene extraction. For example, the video analysis unit uses a generative AI to analyze video metadata and extract scenes based on the shooting date and time and location. For example, it extracts scenes shot on a specific date or location. The video analysis unit can also analyze performer information included in the metadata and extract scenes featuring specific performers. For example, it extracts scenes featuring specific people based on the performer information. This makes it possible to perform more accurate scene extraction by analyzing metadata.

[0055] The video analysis unit can use the emotion estimation function to analyze the facial expressions and tone of voice of people in a video and extract emotionally significant scenes. The video analysis unit, for example, uses the emotion estimation function to analyze the facial expressions of people in a video and extract emotionally significant scenes. For example, it detects smiles and tears and extracts those scenes. The video analysis unit can also use audio analysis technology to analyze the tone of voice and extract emotionally significant scenes. For example, it calculates an emotion score based on changes in the tone of voice and extracts scenes based on that score. In this way, the emotion estimation function can be used to extract emotionally significant scenes.

[0056] The video analysis unit can analyze multiple videos simultaneously and extract common scenes between different videos. For example, the video analysis unit uses a generative AI to simultaneously analyze multiple videos and extract common scenes. For example, it extracts common scenes from videos of the same event filmed from different camera angles. The video analysis unit can also analyze videos obtained from different sources and extract common scenes. For example, it extracts scenes of the same news event from news videos from different news channels. This allows multiple videos to be analyzed simultaneously and common scenes to be extracted.

[0057] The video analysis unit can analyze video in real time and extract specific scenes during live streaming. For example, the video analysis unit uses generative AI to analyze live streaming video in real time and extract specific scenes. For example, goal scenes during a sports game can be extracted in real time. The video analysis unit can also analyze audio data during live streaming and extract scenes based on specific keywords. For example, it can detect keywords such as "goal" or "score" from the commentary audio and extract those scenes in real time. This makes it possible to analyze video in real time and extract specific scenes during live streaming.

[0058] The video analysis unit uses the emotion estimation function to analyze the emotional response of a user when viewing a specific scene, and can extract scenes that are likely to resonate emotionally. The video analysis unit, for example, uses the emotion estimation function to analyze the emotional response of a user when viewing a specific scene, and extracts scenes that are likely to resonate emotionally. For example, it detects the viewer's smiles and tears and extracts those scenes. The video analysis unit can also analyze the viewer's biometric data (heart rate and electrodermal activity) to extract scenes that are likely to resonate emotionally. For example, it calculates an emotion score based on heart rate fluctuations and extracts scenes based on that score. This makes it possible to analyze the user's emotional response and extract scenes that are likely to resonate emotionally.

[0059] The video analysis unit can understand the context of the text input and extract scenes by taking synonyms and related words into consideration. For example, the video analysis unit uses a generative AI to analyze the context of the text input and extract scenes by taking synonyms and related words into consideration. For example, it treats "goal" and "score" as having the same meaning and extracts scenes. The video analysis unit can also refer to related background information and topic models to understand the context of the text input. For example, it collects related news articles and academic papers and extracts scenes based on that information. This allows it to understand the context of the text input and extract scenes by taking synonyms and related words into consideration.

[0060] The video analysis unit can refer to the user's past search history and extract scenes based on the user's preferences. For example, the video analysis unit uses a generation AI to analyze the user's past search history and extract scenes based on the user's preferences. For example, it prioritizes the extraction of scenes related to keywords that have been frequently searched in the past. The video analysis unit can also analyze the user's viewing history and extract scenes based on preferences. For example, it extracts related scenes based on the content of videos viewed in the past. This makes it possible to refer to the user's past search history and extract scenes based on preferences.

[0061] The video analysis unit can use the emotion estimation function to analyze the emotional nuances of the text entered by the user and extract scenes that match the emotion. The video analysis unit, for example, uses the emotion estimation function to analyze the emotional nuances of the text entered by the user and extract scenes that match the emotion. For example, moving scenes and exciting scenes are extracted. The video analysis unit can also use text analysis technology to analyze the emotional nuances of the text. For example, an emotion score of the text is calculated and scenes are extracted based on the score. This allows the emotional nuances of the text entered by the user to be analyzed and scenes that match the emotion to be extracted.

[0062] The video analysis unit can automatically translate text entered in different languages ​​and extract scenes in multiple languages. For example, the video analysis unit uses a generation AI to automatically translate text entered in different languages ​​and extract scenes in multiple languages. For example, it translates text entered in English or French into Japanese and extracts scenes. The video analysis unit can also use machine translation technology to translate text entered in different languages. For example, it uses neural translation technology to perform highly accurate translation and extracts scenes based on the translation results. This makes it possible to automatically translate text entered in different languages ​​and extract scenes in multiple languages.

[0063] The video analysis unit can analyze image data and audio data related to text input and perform multimodal scene extraction. For example, the video analysis unit can analyze image data and audio data related to text input using a generative AI and perform multimodal scene extraction. For example, it can extract scenes by combining text and image data. The video analysis unit can also extract scenes by combining text and audio data. For example, it can analyze the relevance between text and audio data and extract scenes based on that relevance. This makes it possible to analyze image and audio data related to text input and perform multimodal scene extraction.

[0064] The video analysis unit can use the emotion estimation function to analyze other users' emotional reactions to text entered by the user and extract scenes that are likely to be empathetic. The video analysis unit, for example, uses the emotion estimation function to analyze other users' emotional reactions to text entered by the user and extract scenes that are likely to be empathetic. For example, scenes with many positive emotional reactions are extracted. The video analysis unit can also analyze other users' comments and ratings and extract scenes that are likely to be empathetic. For example, the content of the comments and ratings is analyzed and scenes are extracted based on the content. In this way, it is possible to analyze other users' emotional reactions to text entered by the user and extract scenes that are likely to be empathetic.

[0065] The highlight generation unit can automatically edit the scenes extracted by the scene extraction unit to generate a visually appealing highlight video. The highlight generation unit, for example, automatically edits the scenes extracted by a generation AI to generate a visually appealing highlight video. For example, it automatically adds scene transitions and effects. The highlight generation unit can also perform color correction and audio adjustment for the scenes to generate a visually appealing video. For example, it performs color correction and adjusts the hue of the scenes. In this way, the extracted scenes can be automatically edited to generate a visually appealing highlight video.

[0066] The highlight generation unit can automatically add music and sound effects to scenes extracted by the scene extraction unit to enhance the entertainment value. The highlight generation unit can automatically add music and sound effects to scenes extracted by the generation AI to enhance the entertainment value. For example, it can select music that matches the atmosphere of the scene and add it to the background. The highlight generation unit can also add sound effects to important moments in a scene to attract the viewer's attention. For example, it can add sound effects of cheers to a goal scene. In this way, music and sound effects can be automatically added to extracted scenes to enhance the entertainment value.

[0067] The highlight generation unit can use the emotion estimation function to perform editing that will have the most emotional impact on the user when viewing. The highlight generation unit can, for example, use the emotion estimation function to perform editing that will have the most emotional impact on the user when viewing. For example, slow motion or music can be added to emphasize moving scenes. The highlight generation unit can also adjust the order of scenes based on the viewer's emotional response to maximize the emotional impact. For example, moving scenes can be placed at the end. In this way, the emotion estimation function can be used to perform editing that will have the most emotional impact on the user when viewing.

[0068] The highlight generation unit can combine scenes extracted from different videos to generate a crossover highlight video. For example, the highlight generation unit uses a generation AI to combine scenes extracted from different videos to generate a crossover highlight video. For example, highlight scenes from different sports can be combined into a single video. The highlight generation unit can also combine videos of different genres to create a new story. For example, scenes from a music concert and a sporting event can be combined. This makes it possible to combine scenes extracted from different videos to generate a crossover highlight video.

[0069] The highlight generation unit can automatically generate multiple highlight videos based on the user's preferences and provide the user with options. For example, the highlight generation unit uses a generation AI to automatically generate multiple highlight videos based on the user's preferences and provide the user with options. For example, multiple highlight videos using different editing styles or music are generated. The highlight generation unit can also suggest highlight videos that match the user's preferences based on the user's viewing history. For example, related highlight videos are generated based on the content of videos viewed in the past. This makes it possible to automatically generate multiple highlight videos based on the user's preferences and provide the user with options.

[0070] The highlight generation unit uses the emotion estimation function to monitor the emotional response of the user when viewing in real time and generate an optimal highlight video. The highlight generation unit, for example, uses the emotion estimation function to monitor the emotional response of the user when viewing in real time and generate an optimal highlight video. For example, the highlight generation unit adjusts the video based on the emotion score during viewing. The highlight generation unit can also analyze the emotional response in real time and provide feedback according to the viewer's emotion. For example, it can highlight scenes with a high emotion score. This makes it possible to monitor the emotional response of the user when viewing in real time and generate an optimal highlight video.

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

[0072] The highlight video generation system can also analyze a user's viewing history and extract scenes based on the content of videos previously viewed. For example, related scenes can be extracted based on scenes from sports games or live music concerts previously viewed by the user. The system can also learn the user's preferences based on the viewing history and preferentially extract scenes that match the preferences. This makes it possible to generate a more personalized highlight video by utilizing the user's viewing history.

[0073] The highlight video generation system can further analyze users' real-time viewing data and extract scenes based on their reactions while watching. For example, it can analyze the timing of clicks and playback stop while watching to identify scenes of interest. It can also collect comments and ratings while watching in real time and extract scenes based on their content. This makes it possible to use real-time viewing data to generate highlight videos that match the user's interests.

[0074] The highlight video generation system can further estimate the user's emotions and extract scenes based on the estimated emotions. For example, it can identify scenes in which the user smiled or cried while watching and extract those scenes. It can also analyze the user's heart rate and electrodermal activity while watching and extract scenes that elicit an emotional response. This makes it possible to generate a highlight video that includes emotionally significant scenes based on the user's emotions.

[0075] The highlight video generation system can also combine videos of different genres to create new stories. For example, it can combine scenes from a sports game and a live music concert to generate a highly entertaining highlight video. It can also combine scenes from a movie and a documentary to tell a story from a new perspective. This allows it to combine videos of different genres and provide viewers with a new experience.

[0076] The highlight video generation system can further analyze the emotional nuances of the text entered by the user and extract scenes that match the emotion. For example, moving or exciting scenes can be extracted. In addition, text analysis technology can be used to analyze the emotional nuances of the text. For example, an emotional score of the text can be calculated and scenes can be extracted based on the score. This allows the emotional nuances of the text entered by the user to be analyzed and scenes that match the emotion to be extracted.

[0077] The highlight video generation system can further refer to the user's past search history and extract scenes based on the user's preferences. For example, it can preferentially extract scenes related to keywords that have been frequently searched in the past. It can also analyze the user's viewing history and extract scenes based on the user's preferences. This makes it possible to refer to the user's past search history and extract scenes based on the user's preferences.

[0078] The highlight video generation system further uses an emotion estimation function to monitor the emotional response of the user while watching in real time and generate an optimal highlight video. For example, the system adjusts the video based on the emotional score during viewing. It can also analyze the emotional response in real time and provide feedback according to the viewer's emotions. This allows the system to monitor the emotional response of the user while watching in real time and generate an optimal highlight video.

[0079] The highlight video generation system can also automatically translate text input in different languages ​​and extract scenes in multiple languages. For example, text input in English or French can be translated into Japanese and scenes extracted. Machine translation technology can also be used to translate text input in different languages. For example, neural translation technology can be used to perform highly accurate translation, and scenes can be extracted based on the translation results. This makes it possible to automatically translate text input in different languages ​​and extract scenes in multiple languages.

[0080] The highlight video generation system further uses an emotion estimation function to analyze other users' emotional reactions to text entered by the user and extract scenes that are likely to resonate with the user. For example, scenes with many positive emotional reactions are extracted. The system can also analyze other users' comments and ratings to extract scenes that are likely to resonate with the user. This allows the system to analyze other users' emotional reactions to text entered by the user and extract scenes that are likely to resonate with the user.

[0081] The highlight video generation system can also analyze image and audio data related to text input to perform multimodal scene extraction. For example, scenes can be extracted by combining text and image data. Scenes can also be extracted by combining text and audio data. This makes it possible to analyze image and audio data related to text input and perform multimodal scene extraction.

[0082] The processing flow of the second embodiment will be briefly explained below.

[0083] Step 1: The video analysis unit analyzes the video and text input by the user. Using a generation AI, the content of the video is analyzed and the scene specified in the text is identified. The generation AI then uses a text generation AI (e.g., LLM) or a multimodal generation AI to analyze the relevance between the video and the text. Step 2: The scene extraction unit extracts scenes specified by text from the video analyzed by the video analysis unit. It identifies the start and end times of the scenes identified by the generation AI and extracts videos within that range. Step 3: The highlight generation unit automatically generates a highlight video based on the scenes extracted by the scene extraction unit. The extracted scenes are linked together to generate a visually appealing highlight video. The generation AI automatically adds scene transitions and effects to create a visually appealing video.

[0084] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0085] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0086] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0087] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0088] 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.

[0089] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0090] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0091] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0092] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0093] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0094] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0095] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0096] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0097] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0098] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0099] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0100] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0101] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0102] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0103] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0104] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0105] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0106] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0107] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0108] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0109] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0110] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0111] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0112] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0113] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0114] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0115] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0116] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0117] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0118] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0119] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0120] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0121] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0123] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0124] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0125] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

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

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

[0128] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0130] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

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

[0132] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0133] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0134] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0135] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0136] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0137] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0138] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0139] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0140] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0141] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0142] 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.

[0143] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0144] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0145] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0146] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0147] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0148] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0149] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0150] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0151] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. Using generative AI, a video analysis unit that analyzes the video and text input by the user; a scene extraction unit that extracts a scene specified by text from the video analyzed by the video analysis unit; a highlight generation unit that automatically generates a highlight video based on the scenes extracted by the scene extraction unit. A system characterized by:

2. The video analysis unit Analyze the audio data in the video and extract scenes based on specific keywords or audio patterns.

2. The system of claim 1.

3. The video analysis unit Analyze multiple videos simultaneously and extract common scenes between different videos 2. The system of claim 1.

4. The video analysis unit Understand the context of text input and extract scenes by considering synonyms and related words 2. The system of claim 1.

5. The video analysis unit Analyzes facial expressions and tone of voice of people in videos to extract emotionally significant scenes 2. The system of claim 1.

6. The video analysis unit Analyzing the emotional nuances of the text entered by the user and extracting scenes that match the emotions.

2. The system of claim 1.

7. The highlight generation unit Editing the content to have the most emotional impact when viewed by the user 2. The system of claim 1.

8. The highlight generation unit The emotional response of the user when viewing is monitored in real time, and an optimal highlight video is generated.

2. The system of claim 1.

Images