System

Abstract

An object of a system according to an embodiment is to efficiently acquire necessary information from a moving image.SOLUTION: A system according to an embodiment includes a moving image analysis unit, a summary generation unit, a chapter generation unit, and a reverse search unit. The moving image analysis unit analyzes a moving image. The summary generation unit summarizes the content of the moving image analyzed by the moving image analysis unit. The chapter generation unit generates a chapter based on the content of the moving image analyzed by the moving image analysis unit. The reverse search unit specifies a corresponding portion in the moving image based on a search request of the viewer.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 technologies have made it difficult to efficiently obtain the necessary information from videos, and this has required time and effort.

[0005] The system according to the embodiment aims to efficiently acquire necessary information from a video. [Means for solving the problem]

[0006] The system according to the embodiment includes a video analysis unit, a summary generation unit, a chapter generation unit, and a reverse search unit. The video analysis unit analyzes videos. The summary generation unit summarizes the content of the videos analyzed by the video analysis unit. The chapter generation unit generates chapters based on the content of the videos analyzed by the video analysis unit. The reverse search unit identifies relevant portions within the videos based on a viewer's search request. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently acquire necessary information from a 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) The video analysis system according to the embodiment of the present invention utilizes generative AI to provide automatic summaries and chapters for videos, as well as reverse search, thereby enabling viewers to obtain the information they need in a short amount of time.

[0029] A video analysis system according to an embodiment includes a video analysis unit, a summary generation unit, a chapter generation unit, and a reverse search unit. The video analysis unit analyzes a video. For example, the video analysis unit performs frame-by-frame analysis. The video analysis unit can also perform audio analysis. The video analysis unit can also perform motion analysis. For example, the video analysis unit analyzes image data for each frame to identify important scenes. In audio analysis, the video analysis unit analyzes audio data and extracts what a speaker is saying. In motion analysis, the video movement is analyzed and specific movements are detected. The summary generation unit summarizes the content of the video analyzed by the video analysis unit. For example, the summary generation unit extracts important scenes and creates a summary. The summary generation unit can also perform text summarization. The summary generation unit can also perform temporal summarization. For example, the summary generation unit selects particularly important scenes in a video and creates a summary based on them. In text summarization, the content of the video is summarized in text format. In temporal summarization, the video playback time is shortened and only the main points are included. The chapter generation unit generates chapters based on the content of the video analyzed by the video analysis unit. For example, the chapter generation unit generates chapters based on scene changes. The chapter generation unit can also generate chapters based on topic changes. The chapter generation unit can also generate chapters based on time divisions. For example, the chapter generation unit detects timings at which scenes change in the video and generates chapters at those timings. When generating chapters based on topic changes, points in the video at which the topic changes are identified and chapters are generated at those points. When generating chapters based on time divisions, chapters are generated at regular intervals. The reverse search unit identifies relevant portions in the video based on a viewer's search request. For example, the reverse search unit performs a keyword search. The reverse search unit can also perform a voice search. The reverse search unit can also perform an image search. For example, the reverse search unit identifies relevant portions in the video based on keywords entered by the viewer. In a voice search, the viewer enters a search request by voice, and the voice data is analyzed to identify the relevant portions. With image search, viewers input an image and the relevant part of the video is identified based on that image data.As a result, the video analysis system according to the embodiment can enable viewers to obtain necessary information in a short time. For example, when searching for specific information, viewers can pinpoint the relevant part without having to play the entire video. Viewers can efficiently obtain information by using video summaries and chapters. Viewers can quickly find specific information by using the reverse search function.

[0030] The summary generation unit can provide individually customized summaries by taking into account the viewer's past viewing history or interests. For example, the summary generation unit uses a generation AI to analyze the viewer's past viewing history and understand their interests in specific genres or themes. For example, it prioritizes summaries of videos in genres that the viewer has watched frequently in the past. The summary generation unit also customizes the content of the summary based on the viewer's interests. For example, if a viewer is interested in technical videos, it will focus on summarizing information related to that field. The summary generation unit also adjusts the length and level of detail of the summary by taking into account the viewer's viewing history and interests. For example, if a viewer wants to obtain information quickly, it will shorten the summary and include only the main points. This allows it to provide summaries that match the viewer's interests.

[0031] The summary generation unit can provide the summarized content not only as text but also as infographics or animations, making it easier to understand visually. For example, the summary generation unit provides the content summarized by the generation AI not only as text but also as infographics. For example, important data and statistical information may be displayed in graphs or charts. The summary generation unit can also provide the summarized content as animations, making it easier to understand visually. For example, the main points of a video may be explained using animations. The summary generation unit can also provide summaries by combining text, infographics, and animations, allowing viewers to intuitively understand the information. For example, related graphs and animations may be displayed while explaining in text. This makes it possible to provide summaries that are easy to understand visually.

[0032] The summary generation unit can automatically translate the summarized content into different languages ​​to provide summaries that are suitable for international audiences. For example, the summary generation unit uses a generation AI to automatically translate the summarized content into different languages ​​to make it suitable for international audiences. For example, it translates into multiple languages ​​such as English, Japanese, and French. The summary generation unit also provides the automatically translated summaries on a multilingual platform to make them available to audiences around the world. For example, it provides summaries with subtitles and audio. The summary generation unit also collects feedback from international audiences based on the summaries translated into different languages ​​to improve the accuracy of the summaries. For example, it evaluates the quality of the translation and reflects improvements. This makes it possible to provide summaries that are suitable for international audiences.

[0033] The chapter generation unit can provide individually customized chapters by taking into account the viewer's past viewing history or interests. For example, the chapter generation unit uses a generation AI to analyze the viewer's past viewing history and identify interests in specific genres or themes. For example, it prioritizes chaptering videos in genres that the viewer has watched frequently in the past. The chapter generation unit also customizes the content of chapters based on the viewer's interests. For example, if a viewer is interested in technical videos, it will focus on creating chapters containing information related to that field. The chapter generation unit also adjusts the length and level of detail of chapters by taking into account the viewer's viewing history and interests. For example, if a viewer wants to obtain information in a short amount of time, it will shorten the chapters and include only the main points. This allows it to provide chapters that match the viewer's interests.

[0034] The chapter generation unit can add visual markers or icons when generating chapters to make them easier for viewers to intuitively understand. For example, the chapter generation unit adds visual markers or icons when the generation AI generates chapters. For example, it displays icons that indicate important points or sections. The chapter generation unit also adds infographics or animations to make the content of the chapters easier to visually understand. For example, it displays the main points of the chapters in graphs or diagrams. The chapter generation unit also uses visual markers or icons to make the content of the chapters easier to intuitively understand. For example, it displays icons that indicate the content of each chapter to make the content easier for viewers to grasp. This makes it possible to provide chapters that are visually easy to understand.

[0035] The chapter generation unit can automatically translate chapters into different languages ​​to provide chapters that are suitable for international audiences. For example, the chapter generation unit uses a generation AI to automatically translate the content of chapters into different languages ​​to accommodate international audiences. For example, it translates into multiple languages ​​such as English, Japanese, and French. The chapter generation unit also provides the automatically translated chapters on a multilingual platform to make them available to audiences around the world. For example, it provides chapters with subtitles and audio. The chapter generation unit also collects feedback from international audiences based on the chapters translated into different languages ​​to improve the accuracy of the chapters. For example, it evaluates the quality of the translation and reflects improvements. This makes it possible to provide chapters that are suitable for international audiences.

[0036] The reverse search unit can provide individually customized search results by taking into account the viewer's past search history or interests. For example, the reverse search unit uses a generation AI to analyze the viewer's past search history and understand their interests in specific genres or themes. For example, it can prioritize keywords that the viewer has searched for frequently in the past in the search results. The reverse search unit also customizes search results based on the viewer's interests. For example, if a viewer is interested in technical videos, it will prioritize displaying information related to that field. The reverse search unit also adjusts the display order and content of search results by taking into account the viewer's search history and interests. For example, if a viewer wants to obtain information quickly, it will display the most relevant results at the top. This allows the unit to provide search results that match the viewer's interests.

[0037] The reverse search unit can provide reverse search results not only as text but also as infographics or animations to make them easier to understand visually. For example, the generation AI can provide reverse search results not only as text but also as infographics. For example, important data and statistical information can be displayed in graphs and charts. The reverse search unit can also provide reverse search results as animations to make them easier to understand visually. For example, the reverse search unit can explain the main points of a video using animations. The reverse search unit can also provide reverse search results by combining text, infographics, and animations to allow viewers to intuitively understand the information. For example, the reverse search unit can display related graphs and animations while providing a text explanation. This makes it possible to provide search results that are easier to understand visually.

[0038] The reverse search unit can automatically translate the reverse search results into different languages ​​to provide search results that are suitable for international audiences. For example, the reverse search unit uses a generation AI to automatically translate the reverse search results into different languages ​​to accommodate international audiences. For example, it translates into multiple languages, such as English, Japanese, and French. The reverse search unit also provides the automatically translated reverse search results on a multilingual platform to make them available to audiences around the world. For example, it provides search results with subtitles and audio. The reverse search unit also collects feedback from international audiences based on the reverse search results translated into different languages ​​to improve the accuracy of the search results. For example, it evaluates the quality of the translation and reflects improvements. This makes it possible to provide search results that are suitable for international audiences.

[0039] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0040] The video analysis system may further include an eye-tracking unit that acquires viewer eye-tracking data. The eye-tracking unit tracks the viewer's eye movements in real time while watching a video, and can identify which parts the viewer is focusing on. For example, the eye-tracking unit measures the amount of time the viewer focuses on a particular scene or object, and identifies important scenes based on that data. The eye-tracking unit may also analyze the speed and patterns of the viewer's eye movements to understand the viewer's interests and concerns. This makes it possible to generate summaries and chapters based on scenes that the viewer pays attention to. Furthermore, the eye-tracking data may be used to provide a function for replaying scenes that the viewer missed.

[0041] The summary generation unit may include a social media analysis unit that analyzes viewers' social media activities. The social media analysis unit may analyze content and comments shared by viewers on social media to understand the viewers' interests. For example, the social media analysis unit may identify the genres and themes of videos frequently shared by viewers and customize summaries based on that information. The social media analysis unit may also include scenes from videos for which viewers have left positive comments in the summary. This allows for more personalized summaries to be provided based on the viewers' social media activities. Furthermore, the social media analysis unit may also reflect trends and topics of interest to viewers in the summary.

[0042] The summary generation unit can provide the summarized content not only as text but also as infographics or animations, making it easier to understand visually. For example, the summary generation unit provides the content summarized by the generation AI not only as text but also as infographics. For example, important data and statistical information may be displayed in graphs or charts. The summary generation unit can also provide the summarized content as animations, making it easier to understand visually. For example, the main points of a video may be explained using animations. The summary generation unit can also provide summaries by combining text, infographics, and animations, allowing viewers to intuitively understand the information. For example, related graphs and animations may be displayed while explaining in text. This makes it possible to provide summaries that are easy to understand visually.

[0043] The summary generation unit can automatically translate the summarized content into different languages ​​to provide summaries that are suitable for international audiences. For example, the summary generation unit uses a generation AI to automatically translate the summarized content into different languages ​​to make it suitable for international audiences. For example, it translates into multiple languages ​​such as English, Japanese, and French. The summary generation unit also provides the automatically translated summaries on a multilingual platform to make them available to audiences around the world. For example, it provides summaries with subtitles and audio. The summary generation unit also collects feedback from international audiences based on the summaries translated into different languages ​​to improve the accuracy of the summaries. For example, it evaluates the quality of the translation and reflects improvements. This makes it possible to provide summaries that are suitable for international audiences.

[0044] The chapter generation unit can provide individually customized chapters by taking into account the viewer's past viewing history or interests. For example, the chapter generation unit uses a generation AI to analyze the viewer's past viewing history and identify interests in specific genres or themes. For example, it prioritizes chaptering videos in genres that the viewer has watched frequently in the past. The chapter generation unit also customizes the content of chapters based on the viewer's interests. For example, if a viewer is interested in technical videos, it will focus on creating chapters containing information related to that field. The chapter generation unit also adjusts the length and level of detail of chapters by taking into account the viewer's viewing history and interests. For example, if a viewer wants to obtain information in a short amount of time, it will shorten the chapters and include only the main points. This allows it to provide chapters that match the viewer's interests.

[0045] The chapter generation unit can add visual markers or icons when generating chapters to make them easier for viewers to intuitively understand. For example, the chapter generation unit adds visual markers or icons when the generation AI generates chapters. For example, it displays icons that indicate important points or sections. The chapter generation unit also adds infographics or animations to make the content of the chapters easier to visually understand. For example, it displays the main points of the chapters in graphs or diagrams. The chapter generation unit also uses visual markers or icons to make the content of the chapters easier to intuitively understand. For example, it displays icons that indicate the content of each chapter to make the content easier for viewers to grasp. This makes it possible to provide chapters that are visually easy to understand.

[0046] The processing flow of the first embodiment will be briefly explained below.

[0047] Step 1: The video analysis unit analyzes the video. For example, the video analysis unit performs frame-by-frame analysis and can also perform audio and motion analysis. It analyzes the image data for each frame to identify important scenes. Audio analysis involves analyzing the audio data and extracting what the speaker is saying. Motion analysis involves analyzing the movements within the video to detect specific movements. Step 2: The summary generator summarizes the video content analyzed by the video analyzer. For example, it can extract important scenes to create summaries, and it can also perform text summaries and temporal summaries. Text summaries summarize the video content in text format, while temporal summaries shorten the video playback time and include only the main points. Step 3: The chapter generation unit generates chapters based on the content of the video analyzed by the video analysis unit. For example, chapters are generated based on scene changes, topic changes, and time divisions. Chapters are generated at the timing of scene changes, points where the topic changes, and at regular intervals. Step 4: The reverse search unit identifies the relevant part of the video based on the viewer's search request. For example, it can perform a keyword search, voice search, or image search. It identifies the relevant part of the video based on the keywords, voice data, or image data entered by the viewer.

[0048] (Example 2) The video analysis system according to the embodiment of the present invention utilizes generative AI to provide automatic summaries and chapters for videos, as well as reverse search, thereby enabling viewers to obtain the information they need in a short amount of time.

[0049] A video analysis system according to an embodiment includes a video analysis unit, a summary generation unit, a chapter generation unit, and a reverse search unit. The video analysis unit analyzes a video. For example, the video analysis unit performs frame-by-frame analysis. The video analysis unit can also perform audio analysis. The video analysis unit can also perform motion analysis. For example, the video analysis unit analyzes image data for each frame to identify important scenes. In audio analysis, the video analysis unit analyzes audio data and extracts what a speaker is saying. In motion analysis, the video movement is analyzed and specific movements are detected. The summary generation unit summarizes the content of the video analyzed by the video analysis unit. For example, the summary generation unit extracts important scenes and creates a summary. The summary generation unit can also perform text summarization. The summary generation unit can also perform temporal summarization. For example, the summary generation unit selects particularly important scenes in a video and creates a summary based on them. In text summarization, the content of the video is summarized in text format. In temporal summarization, the video playback time is shortened and only the main points are included. The chapter generation unit generates chapters based on the content of the video analyzed by the video analysis unit. For example, the chapter generation unit generates chapters based on scene changes. The chapter generation unit can also generate chapters based on topic changes. The chapter generation unit can also generate chapters based on time divisions. For example, the chapter generation unit detects timings at which scenes change in the video and generates chapters at those timings. When generating chapters based on topic changes, points in the video at which the topic changes are identified and chapters are generated at those points. When generating chapters based on time divisions, chapters are generated at regular intervals. The reverse search unit identifies relevant portions in the video based on a viewer's search request. For example, the reverse search unit performs a keyword search. The reverse search unit can also perform a voice search. The reverse search unit can also perform an image search. For example, the reverse search unit identifies relevant portions in the video based on keywords entered by the viewer. In a voice search, the viewer enters a search request by voice, and the voice data is analyzed to identify the relevant portions. With image search, viewers input an image and the relevant part of the video is identified based on that image data.As a result, the video analysis system according to the embodiment can enable viewers to obtain necessary information in a short time. For example, when searching for specific information, viewers can pinpoint the relevant part without having to play the entire video. Viewers can efficiently obtain information by using video summaries and chapters. Viewers can quickly find specific information by using the reverse search function.

[0050] The summary generation unit can provide individually customized summaries by taking into account the viewer's past viewing history or interests. For example, the summary generation unit uses a generation AI to analyze the viewer's past viewing history and understand their interests in specific genres or themes. For example, it prioritizes summaries of videos in genres that the viewer has watched frequently in the past. The summary generation unit also customizes the content of the summary based on the viewer's interests. For example, if a viewer is interested in technical videos, it will focus on summarizing information related to that field. The summary generation unit also adjusts the length and level of detail of the summary by taking into account the viewer's viewing history and interests. For example, if a viewer wants to obtain information quickly, it will shorten the summary and include only the main points. This allows it to provide summaries that match the viewer's interests.

[0051] The summary generation unit can analyze the tone of voice or the speaker's facial expression in a video to generate a summary that emphasizes emotionally important parts. For example, the summary generation unit uses a generation AI to analyze the tone of voice in a video to identify emotionally emphasized parts. For example, parts where the speaker speaks with emphasis or parts where emotions are high are included in the summary. The summary generation unit also analyzes the speaker's facial expression to identify emotionally important parts. For example, parts where the speaker shows a smile or a surprised expression are included in the summary. The summary generation unit also combines the results of the analysis of the tone of voice and facial expression to generate a summary that emphasizes emotionally important parts. For example, a summary is created that focuses on parts that the speaker emphasizes emotionally. This makes it possible to provide a summary that emphasizes emotionally important parts.

[0052] The summary generation unit can use the emotion estimation function to identify the parts to which the viewer responds most emotionally and create a summary centered on those parts. For example, the summary generation unit uses a generation AI to analyze the viewer's emotional reactions in real time and identify the parts to which the viewer responds most emotionally. For example, it includes parts that make the viewer laugh or be surprised in the summary. The summary generation unit also uses the emotion estimation function to create a summary centered on parts to which the viewer responds strongly emotionally. For example, it focuses on summarizing parts that move the viewer. The summary generation unit also identifies emotionally important parts based on the viewer's emotional reaction data and creates a summary centered on those parts. For example, it includes parts that the viewer finds most interesting in the summary. This makes it possible to provide a summary centered on the parts to which the viewer responds emotionally.

[0053] The summary generation unit can provide the summarized content not only as text but also as infographics or animations, making it easier to understand visually. For example, the summary generation unit provides the content summarized by the generation AI not only as text but also as infographics. For example, important data and statistical information may be displayed in graphs or charts. The summary generation unit can also provide the summarized content as animations, making it easier to understand visually. For example, the main points of a video may be explained using animations. The summary generation unit can also provide summaries by combining text, infographics, and animations, allowing viewers to intuitively understand the information. For example, related graphs and animations may be displayed while explaining in text. This makes it possible to provide summaries that are easy to understand visually.

[0054] The summary generation unit can automatically translate the summarized content into different languages ​​to provide summaries that are suitable for international audiences. For example, the summary generation unit uses a generation AI to automatically translate the summarized content into different languages ​​to make it suitable for international audiences. For example, it translates into multiple languages ​​such as English, Japanese, and French. The summary generation unit also provides the automatically translated summaries on a multilingual platform to make them available to audiences around the world. For example, it provides summaries with subtitles and audio. The summary generation unit also collects feedback from international audiences based on the summaries translated into different languages ​​to improve the accuracy of the summaries. For example, it evaluates the quality of the translation and reflects improvements. This makes it possible to provide summaries that are suitable for international audiences.

[0055] The summary generation unit can use the emotion estimation function to collect viewers' emotional reactions to the summarized content and improve the accuracy of the summary. The summary generation unit, for example, collects viewers' emotional reactions to the summarized content in real time and improves the accuracy of the summary based on that data. For example, it prioritizes the adoption of summaries with a high number of positive reactions. The summary generation unit also uses the emotion estimation function to collect feedback on the summarized content and regenerates the summary if there are a high number of negative reactions. The summary generation unit also analyzes viewers' emotional reaction data and identifies areas for improvement in the summary based on the results. For example, it makes suggestions to correct parts with low emotion scores. This improves the accuracy of the summary based on viewers' emotional reactions.

[0056] The chapter generation unit can provide individually customized chapters by taking into account the viewer's past viewing history or interests. For example, the chapter generation unit uses a generation AI to analyze the viewer's past viewing history and identify interests in specific genres or themes. For example, it prioritizes chaptering videos in genres that the viewer has watched frequently in the past. The chapter generation unit also customizes the content of chapters based on the viewer's interests. For example, if a viewer is interested in technical videos, it will focus on creating chapters containing information related to that field. The chapter generation unit also adjusts the length and level of detail of chapters by taking into account the viewer's viewing history and interests. For example, if a viewer wants to obtain information in a short amount of time, it will shorten the chapters and include only the main points. This allows it to provide chapters that match the viewer's interests.

[0057] The chapter generation unit can analyze the tone of voice or the facial expression of the speaker in the video and generate chapters that emphasize emotionally important parts. For example, the chapter generation unit uses a generation AI to analyze the tone of voice in the video and identify emotionally emphasized parts. For example, parts where the speaker speaks with emphasis or parts where emotions are heightened are included in chapters. The chapter generation unit also analyzes the facial expression of the speaker and identifies emotionally important parts. For example, parts where the speaker shows a smile or a surprised expression are included in chapters. The chapter generation unit also combines the results of the analysis of the tone of voice and facial expression to generate chapters that emphasize emotionally important parts. For example, chapters are created around parts where the speaker emphasizes emotionally. This makes it possible to provide chapters that emphasize emotionally important parts.

[0058] The chapter generation unit can use the emotion estimation function to identify parts to which viewers have the most emotional reactions and create chapters centered around those parts. For example, the chapter generation unit uses a generation AI to analyze viewers' emotional reactions in real time and identify parts to which viewers have the most emotional reactions. For example, it includes parts that make viewers laugh or are surprised in chapters. The chapter generation unit also uses the emotion estimation function to create chapters centered around parts to which viewers have a strong emotional reaction. For example, it focuses on creating chapters that move viewers. The chapter generation unit also identifies emotionally important parts based on viewers' emotional reaction data and creates chapters centered around those parts. For example, it includes parts that viewers are most interested in in chapters. This makes it possible to provide chapters centered around parts to which viewers have an emotional reaction.

[0059] The chapter generation unit can add visual markers or icons when generating chapters to make them easier for viewers to intuitively understand. For example, the chapter generation unit adds visual markers or icons when the generation AI generates chapters. For example, it displays icons that indicate important points or sections. The chapter generation unit also adds infographics or animations to make the content of the chapters easier to visually understand. For example, it displays the main points of the chapters in graphs or diagrams. The chapter generation unit also uses visual markers or icons to make the content of the chapters easier to intuitively understand. For example, it displays icons that indicate the content of each chapter to make the content easier for viewers to grasp. This makes it possible to provide chapters that are visually easy to understand.

[0060] The chapter generation unit can automatically translate chapters into different languages ​​to provide chapters that are suitable for international audiences. For example, the chapter generation unit uses a generation AI to automatically translate the content of chapters into different languages ​​to accommodate international audiences. For example, it translates into multiple languages ​​such as English, Japanese, and French. The chapter generation unit also provides the automatically translated chapters on a multilingual platform to make them available to audiences around the world. For example, it provides chapters with subtitles and audio. The chapter generation unit also collects feedback from international audiences based on the chapters translated into different languages ​​to improve the accuracy of the chapters. For example, it evaluates the quality of the translation and reflects improvements. This makes it possible to provide chapters that are suitable for international audiences.

[0061] The chapter generation unit can use the emotion estimation function to collect viewers' emotional reactions to chapters and improve the accuracy of the chapters. The chapter generation unit, for example, collects viewers' emotional reactions to chapters in real time and improves the accuracy of the chapters based on that data. For example, it prioritizes the adoption of chapters that have a high number of positive reactions. The chapter generation unit also uses the emotion estimation function to collect feedback on chapters and regenerates chapters if there are a high number of negative reactions. The chapter generation unit also analyzes viewers' emotional reaction data and identifies areas for improvement in the chapters based on the results. For example, it makes suggestions to correct parts with low emotion scores. This improves the accuracy of the chapters based on viewers' emotional reactions.

[0062] The reverse search unit can provide individually customized search results by taking into account the viewer's past search history or interests. For example, the reverse search unit uses a generation AI to analyze the viewer's past search history and understand their interests in specific genres or themes. For example, it can prioritize keywords that the viewer has searched for frequently in the past in the search results. The reverse search unit also customizes search results based on the viewer's interests. For example, if a viewer is interested in technical videos, it will prioritize displaying information related to that field. The reverse search unit also adjusts the display order and content of search results by taking into account the viewer's search history and interests. For example, if a viewer wants to obtain information quickly, it will display the most relevant results at the top. This allows the unit to provide search results that match the viewer's interests.

[0063] The reverse search unit can analyze the tone of voice or the facial expression of the speaker in a video and generate search results that emphasize emotionally important parts. For example, the reverse search unit uses a generation AI to analyze the tone of voice in a video and identify emotionally emphasized parts. For example, parts where the speaker speaks with emphasis or parts where emotions are heightened are included in the search results. The reverse search unit also analyzes the speaker's facial expression and identifies emotionally important parts. For example, parts where the speaker shows a smile or a surprised expression are included in the search results. The reverse search unit also combines the results of the analysis of the tone of voice and facial expression to generate search results that emphasize emotionally important parts. For example, search results are created that focus on parts that the speaker emphasizes emotionally. This makes it possible to provide search results that emphasize emotionally important parts.

[0064] The reverse search unit can use an emotion estimation function to identify the parts to which viewers have the most emotional reactions and display search results centered on those parts. For example, the reverse search unit uses a generation AI to analyze viewers' emotional reactions in real time and identify the parts to which viewers have the most emotional reactions. For example, parts that make viewers laugh or are surprised are included in the search results. The reverse search unit also uses the emotion estimation function to display search results centered on parts to which viewers have a strong emotional reaction. For example, parts that move viewers are included in the search results. The reverse search unit also identifies emotionally important parts based on viewers' emotional reaction data and displays search results centered on those parts. For example, parts that viewers are most interested in are included in the search results. This makes it possible to provide search results centered on parts to which viewers have an emotional reaction.

[0065] The reverse search unit can provide reverse search results not only as text but also as infographics or animations to make them easier to understand visually. For example, the generation AI can provide reverse search results not only as text but also as infographics. For example, important data and statistical information can be displayed in graphs and charts. The reverse search unit can also provide reverse search results as animations to make them easier to understand visually. For example, the reverse search unit can explain the main points of a video using animations. The reverse search unit can also provide reverse search results by combining text, infographics, and animations to allow viewers to intuitively understand the information. For example, the reverse search unit can display related graphs and animations while providing a text explanation. This makes it possible to provide search results that are easier to understand visually.

[0066] The reverse search unit can automatically translate the reverse search results into different languages ​​to provide search results that are suitable for international audiences. For example, the reverse search unit uses a generation AI to automatically translate the reverse search results into different languages ​​to accommodate international audiences. For example, it translates into multiple languages, such as English, Japanese, and French. The reverse search unit also provides the automatically translated reverse search results on a multilingual platform to make them available to audiences around the world. For example, it provides search results with subtitles and audio. The reverse search unit also collects feedback from international audiences based on the reverse search results translated into different languages ​​to improve the accuracy of the search results. For example, it evaluates the quality of the translation and reflects improvements. This makes it possible to provide search results that are suitable for international audiences.

[0067] The reverse search unit can use the emotion estimation function to collect viewers' emotional reactions to the reverse search results and improve the accuracy of the search results. The reverse search unit, for example, collects viewers' emotional reactions to the reverse search results in real time and improves the accuracy of the search results based on that data. For example, it prioritizes the adoption of search results with a high number of positive reactions. The reverse search unit also uses the emotion estimation function to collect feedback on the reverse search results and regenerates the search results if there are a high number of negative reactions. The reverse search unit also analyzes viewers' emotional reaction data and identifies areas for improvement in the search results based on the results. For example, it makes suggestions to correct parts with low emotional scores. This improves the accuracy of the search results based on viewers' emotional reactions.

[0068] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0069] The video analysis system may further include an eye-tracking unit that acquires viewer eye-tracking data. The eye-tracking unit tracks the viewer's eye movements in real time while watching a video, and can identify which parts the viewer is focusing on. For example, the eye-tracking unit measures the amount of time the viewer focuses on a particular scene or object, and identifies important scenes based on that data. The eye-tracking unit may also analyze the speed and patterns of the viewer's eye movements to understand the viewer's interests and concerns. This makes it possible to generate summaries and chapters based on scenes that the viewer pays attention to. Furthermore, the eye-tracking data may be used to provide a function for replaying scenes that the viewer missed.

[0070] The summary generation unit may include a biometric information acquisition unit that acquires biometric information of the viewer. The biometric information acquisition unit can acquire biometric information such as the viewer's heart rate and galvanic skin response in real time and measure the viewer's level of excitement or relaxation. For example, the biometric information acquisition unit can identify scenes in which the viewer is excited and include those scenes in the summary. The biometric information acquisition unit can also identify scenes in which the viewer is relaxed and exclude those scenes from the summary. This makes it possible to provide a more personalized summary based on the viewer's biometric information. Furthermore, the biometric information acquisition unit can measure the viewer's stress level and include relaxing scenes to reduce stress in the summary.

[0071] The summary generation unit may include a social media analysis unit that analyzes viewers' social media activities. The social media analysis unit may analyze content and comments shared by viewers on social media to understand the viewers' interests. For example, the social media analysis unit may identify the genres and themes of videos frequently shared by viewers and customize summaries based on that information. The social media analysis unit may also include scenes from videos for which viewers have left positive comments in the summary. This allows for more personalized summaries to be provided based on the viewers' social media activities. Furthermore, the social media analysis unit may also reflect trends and topics of interest to viewers in the summary.

[0072] The summary generation unit can use the viewer emotion estimation function to identify the parts to which the viewer responds most emotionally and create a summary centered on those parts. For example, the summary generation unit uses a generation AI to analyze the viewer's emotional response in real time and identify the parts to which the viewer responds most emotionally. For example, it includes parts that make the viewer laugh or be surprised in the summary. The summary generation unit also uses the emotion estimation function to create a summary centered on parts to which the viewer responds strongly emotionally. For example, it focuses on summarizing parts that move the viewer. The summary generation unit also identifies emotionally important parts based on the viewer's emotional response data and creates a summary centered on those parts. For example, it includes parts that the viewer finds most interesting in the summary. This makes it possible to provide a summary centered on the parts to which the viewer responds emotionally.

[0073] The summary generation unit can provide the summarized content not only as text but also as infographics or animations, making it easier to understand visually. For example, the summary generation unit provides the content summarized by the generation AI not only as text but also as infographics. For example, important data and statistical information may be displayed in graphs or charts. The summary generation unit can also provide the summarized content as animations, making it easier to understand visually. For example, the main points of a video may be explained using animations. The summary generation unit can also provide summaries by combining text, infographics, and animations, allowing viewers to intuitively understand the information. For example, related graphs and animations may be displayed while explaining in text. This makes it possible to provide summaries that are easy to understand visually.

[0074] The summary generation unit can automatically translate the summarized content into different languages ​​to provide summaries that are suitable for international audiences. For example, the summary generation unit uses a generation AI to automatically translate the summarized content into different languages ​​to make it suitable for international audiences. For example, it translates into multiple languages ​​such as English, Japanese, and French. The summary generation unit also provides the automatically translated summaries on a multilingual platform to make them available to audiences around the world. For example, it provides summaries with subtitles and audio. The summary generation unit also collects feedback from international audiences based on the summaries translated into different languages ​​to improve the accuracy of the summaries. For example, it evaluates the quality of the translation and reflects improvements. This makes it possible to provide summaries that are suitable for international audiences.

[0075] The summary generation unit can use the emotion estimation function to collect viewers' emotional reactions to the summarized content and improve the accuracy of the summary. The summary generation unit, for example, collects viewers' emotional reactions to the summarized content in real time and improves the accuracy of the summary based on that data. For example, it prioritizes the adoption of summaries with a high number of positive reactions. The summary generation unit also uses the emotion estimation function to collect feedback on the summarized content and regenerates the summary if there are a high number of negative reactions. The summary generation unit also analyzes viewers' emotional reaction data and identifies areas for improvement in the summary based on the results. For example, it makes suggestions to correct parts with low emotion scores. This improves the accuracy of the summary based on viewers' emotional reactions.

[0076] The chapter generation unit can provide individually customized chapters by taking into account the viewer's past viewing history or interests. For example, the chapter generation unit uses a generation AI to analyze the viewer's past viewing history and identify interests in specific genres or themes. For example, it prioritizes chaptering videos in genres that the viewer has watched frequently in the past. The chapter generation unit also customizes the content of chapters based on the viewer's interests. For example, if a viewer is interested in technical videos, it will focus on creating chapters containing information related to that field. The chapter generation unit also adjusts the length and level of detail of chapters by taking into account the viewer's viewing history and interests. For example, if a viewer wants to obtain information in a short amount of time, it will shorten the chapters and include only the main points. This allows it to provide chapters that match the viewer's interests.

[0077] The chapter generation unit can analyze the tone of voice or the facial expression of the speaker in the video and generate chapters that emphasize emotionally important parts. For example, the chapter generation unit uses a generation AI to analyze the tone of voice in the video and identify emotionally emphasized parts. For example, parts where the speaker speaks with emphasis or parts where emotions are heightened are included in chapters. The chapter generation unit also analyzes the facial expression of the speaker and identifies emotionally important parts. For example, parts where the speaker shows a smile or a surprised expression are included in chapters. The chapter generation unit also combines the results of the analysis of the tone of voice and facial expression to generate chapters that emphasize emotionally important parts. For example, chapters are created around parts where the speaker emphasizes emotionally. This makes it possible to provide chapters that emphasize emotionally important parts.

[0078] The chapter generation unit can add visual markers or icons when generating chapters to make them easier for viewers to intuitively understand. For example, the chapter generation unit adds visual markers or icons when the generation AI generates chapters. For example, it displays icons that indicate important points or sections. The chapter generation unit also adds infographics or animations to make the content of the chapters easier to visually understand. For example, it displays the main points of the chapters in graphs or diagrams. The chapter generation unit also uses visual markers or icons to make the content of the chapters easier to intuitively understand. For example, it displays icons that indicate the content of each chapter to make the content easier for viewers to grasp. This makes it possible to provide chapters that are visually easy to understand.

[0079] The processing flow of the second embodiment will be briefly explained below.

[0080] Step 1: The video analysis unit analyzes the video. For example, the video analysis unit performs frame-by-frame analysis and can also perform audio and motion analysis. It analyzes the image data for each frame to identify important scenes. Audio analysis involves analyzing the audio data and extracting what the speaker is saying. Motion analysis involves analyzing the movements within the video to detect specific movements. Step 2: The summary generator summarizes the video content analyzed by the video analyzer. For example, it can extract important scenes to create summaries, and it can also perform text summaries and temporal summaries. Text summaries summarize the video content in text format, while temporal summaries shorten the video playback time and include only the main points. Step 3: The chapter generation unit generates chapters based on the content of the video analyzed by the video analysis unit. For example, chapters are generated based on scene changes, topic changes, and time divisions. Chapters are generated at the timing of scene changes, points where the topic changes, and at regular intervals. Step 4: The reverse search unit identifies the relevant part of the video based on the viewer's search request. For example, it can perform a keyword search, voice search, or image search. It identifies the relevant part of the video based on the keywords, voice data, or image data entered by the viewer.

[0081] 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.

[0082] 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.

[0083] 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.

[0084] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0085] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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).

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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).

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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).

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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."

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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]

[0148] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a video analysis unit that analyzes the video; a summary generation unit that summarizes the content of the video analyzed by the video analysis unit; a chapter generation unit that generates chapters based on the content of the moving image analyzed by the moving image analysis unit; a reverse search unit that identifies a relevant portion of a video based on a viewer's search request; A system characterized by:

2. The summary generation unit The summarized content is presented not only as text but also as infographics or animations to make it easier to understand visually.

2. The system of claim 1.

3. The chapter generation unit Providing individually customized chapters based on the viewer's past viewing history or interests 2. The system of claim 1.

4. The reverse search unit Providing individually tailored search results that take into account the viewer's past search history or interests 2. The system of claim 1.

5. The summary generation unit Analyzing the tone of voice or facial expressions of the speaker in the video and generating a summary that highlights emotionally significant parts 2. The system of claim 1.

6. The chapter generation unit Analyzing the tone of voice or facial expressions of the speaker in the video and generating chapters that highlight emotionally important parts 2. The system of claim 1.

7. The reverse search unit Analyzing the tone of voice or facial expressions of the speaker in the video to generate search results that highlight emotionally significant parts 2. The system of claim 1.

8. The summary generation unit Identify the parts of the video that resonate most emotionally with the viewer and create a summary around those parts 2. The system of claim 1.

Images