System

Abstract

An object of a system according to an embodiment is to efficiently acquire necessary information from a moving image in a short time.SOLUTION: A system includes a summarization part, a chapter part, and a retrieval part. The summarizing unit analyzes the content of the moving image and generates a summary. The chapter division unit divides the moving image into chapters based on the summary generated by the summarization unit. When the user inputs a specific keyword, the search unit searches for a portion of the moving image related to the keyword and reproduces the portion.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 in a short time. [Means for solving the problem]

[0006] The system according to the embodiment includes a summarization unit, a chapter unit, and a search unit. The summarization unit analyzes the content of a video and generates a summary. The chapter unit divides the video into chapters based on the summary generated by the summarization unit. When a user inputs a specific keyword, the search unit searches for parts of the video related to the keyword and plays the relevant parts. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently acquire necessary information from a video in a short time. [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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0028] (Example 1) A system according to an embodiment of the present invention utilizes a generation AI to summarize and divide videos into chapters and has a reverse search function. The system includes a summarization unit that analyzes the content of a video and automatically generates a summary; a chapter unit that divides the video into chapters based on the summary generated by the summarization unit; and a search unit that, when a user inputs a specific keyword, searches for parts of the video related to the keyword and plays the relevant parts. For example, the summarization unit uses a generation AI to analyze the content of the video, extracts important points, and generates a summary. Next, the chapter unit divides the video into chapters based on the summary generated by the summarization unit and concisely displays the content of each chapter. Furthermore, when a user inputs a specific keyword, the search unit automatically searches for parts of the video related to the keyword and plays the relevant parts. This allows users to quickly obtain necessary information. This makes the system an effective means for quickly obtaining necessary information in today's information-overloaded world. For example, by automatically summarizing meeting minutes and displaying key points divided into chapters, users can efficiently understand the content of the meeting. In addition, the video version of the instruction manual divides the chapters into individual steps and displays the contents of each step concisely, which helps to make work more efficient.

[0029] The information processing system according to the embodiment includes a summarization unit, a chapter unit, and a search unit. The summarization unit analyzes the content of a video and generates a summary. The summarization unit, for example, uses a generation AI to analyze the content of the video and extract important points to generate a summary. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI. For example, the generation AI analyzes the content of the video and extracts important points to generate a summary. The summarization unit can also use the generation AI to summarize the content of the video. The chapter unit divides the video into chapters based on the summary generated by the summarization unit. The chapter unit analyzes the content of the video using the generation AI and concisely displays the content of each chapter. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI. For example, the generation AI analyzes the content of the video and concisely displays the content of each chapter. The chapter unit can also use the generation AI to divide the content of the video into chapters. When a user inputs a specific keyword, the search unit searches for a portion of a video related to the keyword and plays the corresponding portion. When a user inputs a specific keyword, the search unit uses, for example, a generation AI to automatically search for a portion of a video related to the keyword and plays the corresponding portion. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, when a user inputs a specific keyword, the generation AI automatically searches for a portion of a video related to the keyword and plays the corresponding portion. This allows the information processing system according to the embodiment to obtain the information the user needs in a short period of time.

[0030] The summarization unit can analyze the content of the video using a generation AI, extract important points, and generate a summary. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI. The summarization unit can, for example, analyze the content of the video using a generation AI, extract important points, and generate a summary. For example, the generation AI can analyze the content of the video, extract important points, and generate a summary. The summarization unit can also summarize the content of the video using a generation AI. In this way, the accuracy of the summary can be improved by using the generation AI. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input the content of the video into the generation AI, extract important points, and generate a summary.

[0031] The chapter section can analyze the content of the video using a generation AI and concisely display the content of each chapter. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI. The chapter section can analyze the content of the video using a generation AI and concisely display the content of each chapter. For example, the generation AI can analyze the content of the video and concisely display the content of each chapter. The chapter section can also divide the content of the video into chapters using a generation AI. This improves the accuracy of chapter division. Some or all of the above-mentioned processing in the chapter section can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chapter section can input the content of the video into a generation AI and concisely display the content of each chapter.

[0032] When a user inputs a specific keyword using the generation AI, the search unit can automatically search for parts of a video related to the keyword and play the relevant parts. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI. When a user inputs a specific keyword using the generation AI, the search unit can automatically search for parts of a video related to the keyword and play the relevant parts. For example, when a user inputs a specific keyword, the generation AI can automatically search for parts of a video related to the keyword and play the relevant parts. In this way, using the generation AI improves search accuracy. Some or all of the above-mentioned processing in the search unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the search unit can input a keyword entered by a user into the generation AI, automatically search for parts of a video related to the keyword, and play the relevant parts.

[0033] The chapter section can summarize the minutes of a meeting and display important points by dividing them into chapters. The minutes of a meeting may be in, for example, text or audio format. The chapter section can, for example, use a generation AI to summarize the minutes of a meeting and display important points by dividing them into chapters. For example, the generation AI can analyze the minutes of a meeting, extract important points, generate a summary, and display the summary by dividing them into chapters. The chapter section can also summarize the minutes of a meeting and display important points by dividing them into chapters. This allows the content of the meeting to be efficiently understood. Some or all of the above-described processing in the chapter section can be performed by, for example, a generation AI, or can be performed without using a generation AI. For example, the chapter section can input the minutes of a meeting into a generation AI, extract important points, generate a summary, and display the summary by dividing it into chapters.

[0034] The chapter section can divide a video instruction manual into chapters by procedure and concisely display the content of each procedure. The video instruction manual can include, for example, the type of procedure and the level of detail of the procedure. The chapter section can, for example, analyze the video instruction manual using a generation AI, divide the chapters by procedure, and concisely display the content of each procedure. For example, the generation AI can analyze the video instruction manual, divide the chapters by procedure, and concisely display the content of each procedure. The chapter section can also use the generation AI to divide the video instruction manual into chapters by procedure and concisely display the content of each procedure. This can improve work efficiency. Some or all of the above-mentioned processing in the chapter section can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the chapter section can input the video instruction manual into the generation AI, divide the chapters by procedure, and concisely display the content of each procedure.

[0035] The summarization unit can adjust the level of detail of the summary based on the importance of the video when generating a summary. The summarization unit can adjust the level of detail of the summary based on the importance of the video when generating a summary using, for example, a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit generates a detailed summary for an important video. The summarization unit can also generate a concise summary for a general video. The summarization unit can also generate a summary including details of the event for a video related to a specific event. This makes it possible to provide a summary based on the importance of the video. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input video importance data into the generation AI and adjust the level of detail of the summary.

[0036] The summarization unit can apply different summarization algorithms depending on the category of the video when generating a summary. The summarization unit, for example, uses a generation AI to apply different summarization algorithms depending on the category of the video when generating a summary. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit can generate a summary that emphasizes learning points in the case of an educational video. The summarization unit can also generate a summary that emphasizes key scenes in the case of an entertainment video. The summarization unit can also generate a summary that emphasizes important news items in the case of a news video. This makes it possible to provide a summary according to the category of the video. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input video category data into the generation AI and apply different summarization algorithms.

[0037] The summarization unit can improve the accuracy of the summary by referring to the user's past summarization results when generating a summary. For example, the summarization unit can improve the accuracy of the summary by referring to the user's past summarization results when generating a summary using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit generates a summary by referring to the user's preferred summarization style in the past. The summarization unit can also highlight related information based on the content of summaries the user has viewed in the past. The summarization unit can also analyze the user's past summarization results and suggest an optimal summarization method. This improves the accuracy of the summary by referring to the user's past summarization results. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the summarization unit can input the user's past summarization result data into the generation AI to improve the accuracy of the summary.

[0038] The summarization unit can analyze the video viewing history when generating a summary and customize the summary based on the viewer's interests. The summarization unit can, for example, use a generation AI to analyze the video viewing history and customize the summary based on the viewer's interests when generating a summary. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit can highlight relevant information based on the content of videos the user has previously watched. The summarization unit can also include points of interest from the user's viewing history in the summary. The summarization unit can also analyze the user's viewing history and suggest an optimal summarization method. This makes it possible to provide a summary based on the viewer's interests. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input the user's viewing history data into the generation AI to customize the summary.

[0039] The summarization unit can adjust the length of the summary according to the length of the video when generating a summary. The summarization unit can adjust the length of the summary according to the length of the video when generating a summary using, for example, a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit can generate a detailed summary for a long video. The summarization unit can also generate a concise summary for a short video. The summarization unit can also generate a summary with an appropriate level of detail for a medium-length video. This makes it possible to provide a summary according to the length of the video. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input video length data into the generation AI and adjust the length of the summary.

[0040] The summarization unit can determine the priority of summaries based on the upload date of the video when generating summaries. The summarization unit can determine the priority of summaries based on the upload date of the video when generating summaries using, for example, a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit prioritizes the generation of summaries for the latest videos. The summarization unit can also postpone the generation of summaries for older videos. For videos related to a specific event, the summarization unit can also determine the priority of summaries based on the time of the event. This makes it possible to provide summary priorities according to the upload date of the video. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input video upload date data into the generation AI to determine the priority of summaries.

[0041] The summarization unit can adjust the order of summaries based on the relevance of the videos when generating summaries. The summarization unit adjusts the order of summaries based on the relevance of the videos when generating summaries using, for example, a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit prioritizes generating summaries for highly relevant videos. The summarization unit can also postpone generating summaries for less relevant videos. The summarization unit can also adjust the order of summaries based on the importance of the topic for videos related to a specific topic. This makes it possible to provide an order of summaries according to the relevance of the videos. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input video relevance data into the generation AI and adjust the order of summaries.

[0042] The summarization unit can adjust the use of technical terms in the summary according to the user's level of expertise when generating a summary. For example, the summarization unit can adjust the use of technical terms in the summary according to the user's level of expertise when generating a summary using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit can generate a summary that uses a lot of technical terms for a user with high expertise. For a user with low expertise, the summarization unit can also generate a summary that explains things in simple terms. For a user with medium expertise, the summarization unit can also generate a summary that uses appropriate technical terms. This allows a summary to be provided that is appropriate for the user's level of expertise. Some or all of the above-described processing in the summarization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input the user's level of expertise data into the generation AI to adjust the use of technical terms in the summary.

[0043] The summarization unit can improve the content of the summary by reflecting feedback from viewers of the video when generating a summary. The summarization unit can improve the content of the summary by reflecting feedback from viewers of the video when generating a summary, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit generates a summary by referring to a summary style that viewers have highly rated. The summarization unit can also improve the content of the summary based on viewer feedback. The summarization unit can also analyze viewer comments and reflect them in the content of the summary. This makes it possible to provide a summary that reflects viewer feedback. Some or all of the above-mentioned processing in the summarization unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input viewer feedback data into the generation AI to improve the content of the summary.

[0044] The summarization unit can improve the accuracy of the summary by utilizing subtitle information of the video when generating a summary. The summarization unit can improve the accuracy of the summary by utilizing subtitle information of the video when generating a summary using, for example, a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit can analyze the subtitle information of the video and extract important points to generate a summary. The summarization unit can also complement the content of the summary based on the subtitle information. The summarization unit can also improve the accuracy of the summary by utilizing the subtitle information. This improves the accuracy of the summary using the subtitle information. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input subtitle information of the video into the generation AI to improve the accuracy of the summary.

[0045] The chapter section can improve the accuracy of chapters based on the interrelationships between videos when dividing a video into chapters. The chapter section can improve the accuracy of chapters based on the interrelationships between videos when dividing a video into chapters, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, when the content of videos is continuous, the chapter section can group related parts into one chapter. Furthermore, when the content of videos is different, the chapter section can clearly divide and generate chapters. Furthermore, the chapter section can analyze the interrelationships between videos and perform optimal chapter division. This enables chapter division that takes into account the interrelationships between videos. Some or all of the above-mentioned processing in the chapter section can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chapter section can input interrelationship data between videos into the generation AI to improve the accuracy of chapters.

[0046] The chapter section can divide the video into chapters based on the attribute information of the person who submitted the video. For example, the chapter section uses a generation AI to divide the video into chapters based on the attribute information of the person who submitted the video. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, if the submitter is an expert, the chapter section can divide the video into detailed chapters. Also, if the submitter is a general user, the chapter section can divide the video into simple chapters. Also, the chapter section can divide the video into optimal chapters based on the attribute information of the submitter. This enables chapter division based on the attribute information of the submitter. Some or all of the above-mentioned processing in the chapter section can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chapter section can input attribute information data of the submitter into the generation AI to perform chaptering.

[0047] The chapter section can weight chapters based on the frequency of submission of videos when dividing the chapters. The chapter section, for example, uses a generation AI to weight chapters based on the frequency of submission of videos when dividing the chapters. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the chapter section can divide videos that are submitted frequently into detailed chapters. The chapter section can also divide videos that are submitted infrequently into simple chapters. The chapter section can also adjust the weighting of chapters based on the submission frequency. This enables chapter division based on the submission frequency. Some or all of the above-mentioned processing in the chapter section can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chapter section can input submission frequency data into the generation AI and weight the chapters.

[0048] The chapter unit can analyze the viewing history of the video when dividing the video into chapters and customize the chapters based on the viewer's interests. The chapter unit can, for example, use a generation AI to analyze the viewing history of the video when dividing the video into chapters and customize the chapters based on the viewer's interests. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the chapter unit can include points of interest in chapters based on the user's viewing history. The chapter unit can also include related information from the viewing history in the chapters. The chapter unit can also analyze the viewing history and divide the chapters optimally. This enables chapter division based on the viewer's interests. Some or all of the above-mentioned processing in the chapter unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chapter unit can input viewing history data into the generation AI to customize the chapters.

[0049] The chapter section can adjust the length of the chapters according to the length of the video when dividing the video into chapters. The chapter section adjusts the length of the chapters according to the length of the video when dividing the video into chapters, for example, using a generation AI. The generation AI can be a text generation AI (for example, LLM) or a multimodal generation AI. For example, the chapter section can divide a long video into detailed chapters. Furthermore, the chapter section can divide a short video into concise chapters. Furthermore, the chapter section can divide a medium-length video into chapters with an appropriate level of detail. This enables chapter division according to the length of the video. Some or all of the above-mentioned processing in the chapter section can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chapter section can input video length data into the generation AI and adjust the chapter length.

[0050] The chapter section can divide a video into chapters taking into account the geographical distribution of the video. For example, the chapter section uses a generation AI to divide the video into chapters taking into account the geographical distribution of the video. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the chapter section groups geographically related parts into one chapter. The chapter section can also clearly divide geographically different parts to generate chapters. The chapter section can also analyze the geographical distribution and divide the video into optimal chapters. This enables chapter division based on the geographical distribution. Some or all of the above-described processing in the chapter section can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the chapter section can input geographical distribution data into the generation AI to generate chapters.

[0051] The chapter section can improve the accuracy of chapters by referring to related literature of the video when dividing the chapters. The chapter section can improve the accuracy of chapters by referring to related literature of the video when dividing the chapters, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the chapter section can include important points in chapters based on related literature. The chapter section can also complement the content of the chapters by referring to related literature. The chapter section can also improve the accuracy of chapters by utilizing related literature. This makes it possible to divide the chapters by referring to related literature. Some or all of the above-mentioned processing in the chapter section can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chapter section can input related literature data into the generation AI to improve the accuracy of the chapters.

[0052] The chapter section can divide the video into chapters based on the market value of the video. For example, the chapter section uses a generation AI to divide the video into chapters based on the market value of the video. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the chapter section can divide the video into detailed chapters for a video with high market value. Also, the chapter section can divide the video into simple chapters for a video with low market value. Also, the chapter section can divide the video into optimal chapters based on the market value. This enables chapter division based on market value. Some or all of the above-mentioned processing in the chapter section can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the chapter section can input market value data into the generation AI and perform chaptering.

[0053] The chapter section can improve the content of the chapters by reflecting the feedback of viewers of the video when dividing the chapters. The chapter section can improve the content of the chapters by using, for example, a generation AI when dividing the chapters. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the chapter section can generate chapters by referring to chapter styles that viewers have highly rated. The chapter section can also improve the content of the chapters based on the viewer feedback. The chapter section can also analyze viewer comments and reflect them in the content of the chapters. This enables chapter division that reflects viewer feedback. Some or all of the above-mentioned processing in the chapter section can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the chapter section can input viewer feedback data into the generation AI to improve the content of the chapters.

[0054] The chapter section can improve the accuracy of chapters by utilizing subtitle information of the video when dividing the video into chapters. For example, the chapter section can improve the accuracy of chapters by utilizing subtitle information of the video when dividing the video into chapters using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the chapter section can analyze subtitle information of the video and include important points in the chapters. The chapter section can also complement the content of the chapters based on the subtitle information. The chapter section can also improve the accuracy of chapters by utilizing the subtitle information. This enables chapter division using subtitle information. Some or all of the above-mentioned processing in the chapter section can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chapter section can input subtitle information of the video into the generation AI to improve the accuracy of chapters.

[0055] The search unit can improve search accuracy based on the interrelationships between videos during a search. The search unit can improve search accuracy based on the interrelationships between videos during a search, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, if the content of videos is continuous, the search unit prioritizes searching for related parts. Furthermore, if the content of videos is different, the search unit can clearly divide the videos and display search results. Furthermore, the search unit can analyze the interrelationships between videos and provide optimal search results. This enables searches that take into account the interrelationships between videos. Some or all of the above-described processing in the search unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the search unit can input video interrelationship data into the generation AI to improve search accuracy.

[0056] The search unit can perform a search taking into account the attribute information of the video submitter when searching. The search unit can perform a search taking into account the attribute information of the video submitter when searching, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit provides detailed search results when the submitter is an expert. The search unit can also provide concise search results when the submitter is a general user. The search unit can also provide optimal search results based on the attribute information of the submitter. This enables a search based on the attribute information of the submitter. Some or all of the above-mentioned processing in the search unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the search unit can input attribute information data of the submitter into the generation AI and perform a search.

[0057] The search unit can weight the search based on the submission frequency of the video during a search. The search unit, for example, uses a generation AI to weight the search based on the submission frequency of the video during a search. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit provides detailed search results for videos that are submitted frequently. The search unit can also provide concise search results for videos that are submitted infrequently. The search unit can also adjust the weighting of the search results based on the submission frequency. This enables a search based on the submission frequency. Some or all of the above-described processing in the search unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the search unit can input submission frequency data into the generation AI to weight the search.

[0058] The search unit can analyze the video viewing history during a search and customize search results based on the viewer's interests. The search unit can use, for example, a generation AI to analyze the video viewing history during a search and customize search results based on the viewer's interests. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit can include points of interest in the search results based on the user's viewing history. The search unit can also include related information from the viewing history in the search results. The search unit can also analyze the viewing history and provide optimal search results. This makes it possible to provide search results based on the viewer's interests. Some or all of the above-described processing in the search unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the search unit can input viewing history data into the generation AI to customize search results.

[0059] The search unit can adjust the display of search results according to the length of the video when searching. The search unit, for example, uses a generation AI to adjust the display of search results according to the length of the video when searching. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit provides detailed search results for long videos. The search unit can also provide concise search results for short videos. The search unit can also provide search results with an appropriate level of detail for videos of medium length. This makes it possible to provide search results according to the length of the video. Some or all of the above-mentioned processing in the search unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the search unit can input video length data into the generation AI and adjust the display of search results.

[0060] The search unit can perform a search taking into account the geographical distribution of videos. The search unit, for example, uses a generation AI to perform a search taking into account the geographical distribution of videos. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit prioritizes searching for geographically related parts. The search unit can also display search results by clearly dividing geographically distinct parts. The search unit can also analyze the geographical distribution and provide optimal search results. This enables a search based on geographical distribution. Some or all of the above-described processing in the search unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the search unit can input geographical distribution data into the generation AI and perform a search.

[0061] The search unit can improve search accuracy by referring to literature related to the video during a search. The search unit can improve search accuracy by referring to literature related to the video during a search, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit can include important points in search results based on related literature. The search unit can also complement the content of search results by referring to related literature. The search unit can also improve search accuracy by utilizing related literature. This makes it possible to perform searches by referring to related literature. Some or all of the above-mentioned processing in the search unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the search unit can input related literature data into the generation AI to improve search accuracy.

[0062] The search unit can perform a search taking into account the market value of a video when searching. The search unit, for example, uses a generation AI to perform a search taking into account the market value of a video when searching. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit provides detailed search results for videos with high market value. The search unit can also provide concise search results for videos with low market value. The search unit can also provide optimal search results based on market value. This enables a search based on market value. Some or all of the above-mentioned processing in the search unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the search unit can input market value data into the generation AI and perform a search.

[0063] The search unit can improve search results by reflecting feedback from viewers of the video at the time of a search. The search unit can improve search results by reflecting feedback from viewers of the video at the time of a search, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit performs a search by referring to search result styles that viewers have highly rated. The search unit can also improve the content of the search results based on viewer feedback. The search unit can also analyze viewer comments and reflect them in the content of the search results. This makes it possible to provide search results that reflect viewer feedback. Some or all of the above-mentioned processing in the search unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the search unit can input viewer feedback data into the generation AI to improve the search results.

[0064] The search unit can improve search accuracy by utilizing subtitle information of a video during a search. The search unit can improve search accuracy by utilizing subtitle information of a video during a search, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit can analyze subtitle information of a video and include important points in the search results. The search unit can also complement the content of the search results based on the subtitle information. The search unit can also improve search accuracy by utilizing the subtitle information. This improves the accuracy of searches that utilize subtitle information. Some or all of the above-mentioned processing in the search unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the search unit can input subtitle information of a video into the generation AI to improve search accuracy.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] The summarization unit can analyze the user's past viewing history and customize the content of the summary based on the viewing history. For example, the summarization unit can highlight relevant information based on the content of videos the user has previously viewed. The summarization unit can also include points that the user may be interested in from the user's viewing history in the summary. Furthermore, the summarization unit can analyze the user's viewing history and suggest the optimal summarization method. This makes it possible to provide summaries based on the viewer's interests.

[0067] The chapter section can improve the content of chapters by reflecting the feedback of viewers of the video. For example, the chapter section generates chapters by referring to chapter styles that viewers have given high ratings to. The chapter section can also improve the content of chapters based on the feedback of viewers. Furthermore, the chapter section can analyze the comments of viewers and reflect them in the content of chapters. This makes it possible to divide chapters in a way that reflects the feedback of viewers.

[0068] The summarizer can apply different summarization algorithms depending on the category of the video when generating a summary. For example, the summarizer can generate a summary that emphasizes learning points for an educational video. For an entertainment video, the summarizer can generate a summary that emphasizes key scenes. For a news video, the summarizer can generate a summary that emphasizes important news items. This allows for providing summaries according to the category of the video.

[0069] The search unit can improve search accuracy based on the interrelationships between videos during a search. For example, if the content of videos is continuous, the search unit will prioritize searching for related parts. Also, if the content of videos is different, the search unit can clearly separate and display search results. Furthermore, the search unit can analyze the interrelationships between videos and provide optimal search results. This enables searches that take into account the interrelationships between videos.

[0070] The chapter section can divide the video into chapters based on the attribute information of the person who submitted the video. For example, if the submitter is an expert, the chapter section can divide the video into detailed chapters. Also, if the submitter is a general user, the chapter section can divide the video into simple chapters. Furthermore, the chapter section can divide the video into optimal chapters based on the attribute information of the submitter. This makes it possible to divide the video into chapters based on the attribute information of the submitter.

[0071] When searching, the search unit can analyze the video viewing history and customize search results based on the viewer's interests. For example, the search unit can include points of interest that the user may have based on the user's viewing history in the search results. The search unit can also include related information from the viewing history in the search results. Furthermore, the search unit can analyze the viewing history and provide optimal search results. This allows the search results to be provided based on the viewer's interests.

[0072] When generating a summary, the summarization unit can adjust the level of detail of the summary based on the importance of the video. For example, the summarization unit generates a detailed summary for an important video. The summarization unit can also generate a concise summary for a general video. Furthermore, the summarization unit can generate a summary including details of a specific event for a video related to the event. This makes it possible to provide a summary according to the importance of the video.

[0073] The processing flow of the first embodiment will be briefly explained below.

[0074] Step 1: The summarization unit analyzes the content of the video and generates a summary. For example, the summarization unit uses a generation AI to analyze the content of the video, extract key points, and generate a summary. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. Step 2: The chaptering section divides the video into chapters based on the summary generated by the summarization section. The chaptering section analyzes the content of the video using, for example, a generation AI and displays the content of each chapter concisely. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. Step 3: When a user inputs a specific keyword, the search unit searches for parts of the video related to that keyword and plays the relevant parts. For example, when a user inputs a specific keyword, the search unit uses a generation AI to automatically search for parts of the video related to that keyword and play the relevant parts. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI.

[0075] (Example 2) A system according to an embodiment of the present invention utilizes a generation AI to summarize and divide videos into chapters and has a reverse search function. The system includes a summarization unit that analyzes the content of a video and automatically generates a summary; a chapter unit that divides the video into chapters based on the summary generated by the summarization unit; and a search unit that, when a user inputs a specific keyword, searches for parts of the video related to the keyword and plays the relevant parts. For example, the summarization unit uses a generation AI to analyze the content of the video, extracts important points, and generates a summary. Next, the chapter unit divides the video into chapters based on the summary generated by the summarization unit and concisely displays the content of each chapter. Furthermore, when a user inputs a specific keyword, the search unit automatically searches for parts of the video related to the keyword and plays the relevant parts. This allows users to quickly obtain necessary information. This makes the system an effective means for quickly obtaining necessary information in today's information-overloaded world. For example, by automatically summarizing meeting minutes and displaying key points divided into chapters, users can efficiently understand the content of the meeting. In addition, the video version of the instruction manual divides the chapters into individual steps and displays the contents of each step concisely, which helps to make work more efficient.

[0076] The information processing system according to the embodiment includes a summarization unit, a chapter unit, and a search unit. The summarization unit analyzes the content of a video and generates a summary. The summarization unit, for example, uses a generation AI to analyze the content of the video and extract important points to generate a summary. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI. For example, the generation AI analyzes the content of the video and extracts important points to generate a summary. The summarization unit can also use the generation AI to summarize the content of the video. The chapter unit divides the video into chapters based on the summary generated by the summarization unit. The chapter unit analyzes the content of the video using the generation AI and concisely displays the content of each chapter. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI. For example, the generation AI analyzes the content of the video and concisely displays the content of each chapter. The chapter unit can also use the generation AI to divide the content of the video into chapters. When a user inputs a specific keyword, the search unit searches for a portion of a video related to the keyword and plays the corresponding portion. When a user inputs a specific keyword, the search unit uses, for example, a generation AI to automatically search for a portion of a video related to the keyword and plays the corresponding portion. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, when a user inputs a specific keyword, the generation AI automatically searches for a portion of a video related to the keyword and plays the corresponding portion. This allows the information processing system according to the embodiment to obtain the information the user needs in a short period of time.

[0077] The summarization unit can analyze the content of the video using a generation AI, extract important points, and generate a summary. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI. The summarization unit can, for example, analyze the content of the video using a generation AI, extract important points, and generate a summary. For example, the generation AI can analyze the content of the video, extract important points, and generate a summary. The summarization unit can also summarize the content of the video using a generation AI. In this way, the accuracy of the summary can be improved by using the generation AI. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input the content of the video into the generation AI, extract important points, and generate a summary.

[0078] The chapter section can analyze the content of the video using a generation AI and concisely display the content of each chapter. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI. The chapter section can analyze the content of the video using a generation AI and concisely display the content of each chapter. For example, the generation AI can analyze the content of the video and concisely display the content of each chapter. The chapter section can also divide the content of the video into chapters using a generation AI. This improves the accuracy of chapter division. Some or all of the above-mentioned processing in the chapter section can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chapter section can input the content of the video into a generation AI and concisely display the content of each chapter.

[0079] When a user inputs a specific keyword using the generation AI, the search unit can automatically search for parts of a video related to the keyword and play the relevant parts. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI. When a user inputs a specific keyword using the generation AI, the search unit can automatically search for parts of a video related to the keyword and play the relevant parts. For example, when a user inputs a specific keyword, the generation AI can automatically search for parts of a video related to the keyword and play the relevant parts. In this way, using the generation AI improves search accuracy. Some or all of the above-mentioned processing in the search unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the search unit can input a keyword entered by a user into the generation AI, automatically search for parts of a video related to the keyword, and play the relevant parts.

[0080] The chapter section can summarize the minutes of a meeting and display important points by dividing them into chapters. The minutes of a meeting may be in, for example, text or audio format. The chapter section can, for example, use a generation AI to summarize the minutes of a meeting and display important points by dividing them into chapters. For example, the generation AI can analyze the minutes of a meeting, extract important points, generate a summary, and display the summary by dividing them into chapters. The chapter section can also summarize the minutes of a meeting and display important points by dividing them into chapters. This allows the content of the meeting to be efficiently understood. Some or all of the above-described processing in the chapter section can be performed by, for example, a generation AI, or can be performed without using a generation AI. For example, the chapter section can input the minutes of a meeting into a generation AI, extract important points, generate a summary, and display the summary by dividing it into chapters.

[0081] The chapter section can divide a video instruction manual into chapters by procedure and concisely display the content of each procedure. The video instruction manual can include, for example, the type of procedure and the level of detail of the procedure. The chapter section can, for example, analyze the video instruction manual using a generation AI, divide the chapters by procedure, and concisely display the content of each procedure. For example, the generation AI can analyze the video instruction manual, divide the chapters by procedure, and concisely display the content of each procedure. The chapter section can also use the generation AI to divide the video instruction manual into chapters by procedure and concisely display the content of each procedure. This can improve work efficiency. Some or all of the above-mentioned processing in the chapter section can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the chapter section can input the video instruction manual into the generation AI, divide the chapters by procedure, and concisely display the content of each procedure.

[0082] The summarization unit can estimate the user's emotions and adjust the presentation style of the summary based on the estimated user emotions. The summarization unit can estimate the user's emotions using, for example, a generation AI and adjust the presentation style of the summary based on the estimated user emotions. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, if the user is stressed, the summarization unit can simplify the summary and emphasize only the important points. If the user is relaxed, the summarization unit can also provide a summary with detailed explanations. If the user is in a hurry, the summarization unit can shorten the summary and quickly convey the main points. This allows a summary to be provided that matches the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, a generation AI, or without a generation AI. For example, the summarization unit can input user emotion data into the generation AI and adjust the way the summary is expressed based on the estimated user emotion.

[0083] The summarization unit can adjust the level of detail of the summary based on the importance of the video when generating a summary. The summarization unit can adjust the level of detail of the summary based on the importance of the video when generating a summary using, for example, a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit generates a detailed summary for an important video. The summarization unit can also generate a concise summary for a general video. The summarization unit can also generate a summary including details of the event for a video related to a specific event. This makes it possible to provide a summary based on the importance of the video. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input video importance data into the generation AI and adjust the level of detail of the summary.

[0084] The summarization unit can apply different summarization algorithms depending on the category of the video when generating a summary. The summarization unit, for example, uses a generation AI to apply different summarization algorithms depending on the category of the video when generating a summary. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit can generate a summary that emphasizes learning points in the case of an educational video. The summarization unit can also generate a summary that emphasizes key scenes in the case of an entertainment video. The summarization unit can also generate a summary that emphasizes important news items in the case of a news video. This makes it possible to provide a summary according to the category of the video. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input video category data into the generation AI and apply different summarization algorithms.

[0085] The summarization unit can improve the accuracy of the summary by referring to the user's past summarization results when generating a summary. For example, the summarization unit can improve the accuracy of the summary by referring to the user's past summarization results when generating a summary using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit generates a summary by referring to the user's preferred summarization style in the past. The summarization unit can also highlight related information based on the content of summaries the user has viewed in the past. The summarization unit can also analyze the user's past summarization results and suggest an optimal summarization method. This improves the accuracy of the summary by referring to the user's past summarization results. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the summarization unit can input the user's past summarization result data into the generation AI to improve the accuracy of the summary.

[0086] The summarization unit can analyze the video viewing history when generating a summary and customize the summary based on the viewer's interests. The summarization unit can, for example, use a generation AI to analyze the video viewing history and customize the summary based on the viewer's interests when generating a summary. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit can highlight relevant information based on the content of videos the user has previously watched. The summarization unit can also include points of interest from the user's viewing history in the summary. The summarization unit can also analyze the user's viewing history and suggest an optimal summarization method. This makes it possible to provide a summary based on the viewer's interests. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input the user's viewing history data into the generation AI to customize the summary.

[0087] The summarization unit can adjust the length of the summary according to the length of the video when generating a summary. The summarization unit can adjust the length of the summary according to the length of the video when generating a summary using, for example, a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit can generate a detailed summary for a long video. The summarization unit can also generate a concise summary for a short video. The summarization unit can also generate a summary with an appropriate level of detail for a medium-length video. This makes it possible to provide a summary according to the length of the video. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input video length data into the generation AI and adjust the length of the summary.

[0088] The summarization unit can estimate the user's emotion and adjust the length of the summary based on the estimated user emotion. The summarization unit can estimate the user's emotion using, for example, a generation AI and adjust the length of the summary based on the estimated user emotion. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, if the user is stressed, the summarization unit can shorten the summary and emphasize only the important points. If the user is relaxed, the summarization unit can also provide a summary with detailed explanations. If the user is in a hurry, the summarization unit can shorten the summary and quickly convey the main points. This allows the length of the summary to be tailored to the user's emotion. Emotion estimation is achieved using, for example, an emotion engine or a generation AI with an emotion estimation function. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the summarization unit can be performed using, for example, a generation AI, or without a generation AI. For example, the summarization unit can input user emotion data into the generation AI and adjust the length of the summary based on the estimated user emotion.

[0089] The summarization unit can determine the priority of summaries based on the upload date of the video when generating summaries. The summarization unit can determine the priority of summaries based on the upload date of the video when generating summaries using, for example, a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit prioritizes the generation of summaries for the latest videos. The summarization unit can also postpone the generation of summaries for older videos. For videos related to a specific event, the summarization unit can also determine the priority of summaries based on the time of the event. This makes it possible to provide summary priorities according to the upload date of the video. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input video upload date data into the generation AI to determine the priority of summaries.

[0090] The summarization unit can adjust the order of summaries based on the relevance of the videos when generating summaries. The summarization unit adjusts the order of summaries based on the relevance of the videos when generating summaries using, for example, a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit prioritizes generating summaries for highly relevant videos. The summarization unit can also postpone generating summaries for less relevant videos. The summarization unit can also adjust the order of summaries based on the importance of the topic for videos related to a specific topic. This makes it possible to provide an order of summaries according to the relevance of the videos. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input video relevance data into the generation AI and adjust the order of summaries.

[0091] The summarization unit can adjust the use of technical terms in the summary according to the user's level of expertise when generating a summary. For example, the summarization unit can adjust the use of technical terms in the summary according to the user's level of expertise when generating a summary using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit can generate a summary that uses a lot of technical terms for a user with high expertise. For a user with low expertise, the summarization unit can also generate a summary that explains things in simple terms. For a user with medium expertise, the summarization unit can also generate a summary that uses appropriate technical terms. This allows a summary to be provided that is appropriate for the user's level of expertise. Some or all of the above-described processing in the summarization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input the user's level of expertise data into the generation AI to adjust the use of technical terms in the summary.

[0092] The summarization unit can improve the content of the summary by reflecting feedback from viewers of the video when generating a summary. The summarization unit can improve the content of the summary by reflecting feedback from viewers of the video when generating a summary, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit generates a summary by referring to a summary style that viewers have highly rated. The summarization unit can also improve the content of the summary based on viewer feedback. The summarization unit can also analyze viewer comments and reflect them in the content of the summary. This makes it possible to provide a summary that reflects viewer feedback. Some or all of the above-mentioned processing in the summarization unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input viewer feedback data into the generation AI to improve the content of the summary.

[0093] The summarization unit can improve the accuracy of the summary by utilizing subtitle information of the video when generating a summary. The summarization unit can improve the accuracy of the summary by utilizing subtitle information of the video when generating a summary using, for example, a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the summarization unit can analyze the subtitle information of the video and extract important points to generate a summary. The summarization unit can also complement the content of the summary based on the subtitle information. The summarization unit can also improve the accuracy of the summary by utilizing the subtitle information. This improves the accuracy of the summary using the subtitle information. Some or all of the above-mentioned processing in the summarization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the summarization unit can input subtitle information of the video into the generation AI to improve the accuracy of the summary.

[0094] The chapter section can estimate a user's emotion and adjust the display method of the chapter based on the estimated user's emotion. The chapter section can estimate a user's emotion using, for example, a generation AI and adjust the display method of the chapter based on the estimated user's emotion. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the chapter section can provide a simple chapter display when the user is stressed. The chapter section can also provide a detailed chapter display when the user is relaxed. The chapter section can also provide a chapter display that focuses on the main points when the user is in a hurry. This allows the chapter display to be provided according to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the chapter section can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the chapter section can input user emotion data into the generation AI and adjust the way chapters are displayed based on the estimated user emotion.

[0095] The chapter section can improve the accuracy of chapters based on the interrelationships between videos when dividing a video into chapters. The chapter section can improve the accuracy of chapters based on the interrelationships between videos when dividing a video into chapters, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, when the content of videos is continuous, the chapter section can group related parts into one chapter. Furthermore, when the content of videos is different, the chapter section can clearly divide and generate chapters. Furthermore, the chapter section can analyze the interrelationships between videos and perform optimal chapter division. This enables chapter division that takes into account the interrelationships between videos. Some or all of the above-mentioned processing in the chapter section can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chapter section can input interrelationship data between videos into the generation AI to improve the accuracy of chapters.

[0096] The chapter section can divide the video into chapters based on the attribute information of the person who submitted the video. For example, the chapter section uses a generation AI to divide the video into chapters based on the attribute information of the person who submitted the video. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, if the submitter is an expert, the chapter section can divide the video into detailed chapters. Also, if the submitter is a general user, the chapter section can divide the video into simple chapters. Also, the chapter section can divide the video into optimal chapters based on the attribute information of the submitter. This enables chapter division based on the attribute information of the submitter. Some or all of the above-mentioned processing in the chapter section can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chapter section can input attribute information data of the submitter into the generation AI to perform chaptering.

[0097] The chapter section can weight chapters based on the frequency of submission of videos when dividing the chapters. The chapter section, for example, uses a generation AI to weight chapters based on the frequency of submission of videos when dividing the chapters. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the chapter section can divide videos that are submitted frequently into detailed chapters. The chapter section can also divide videos that are submitted infrequently into simple chapters. The chapter section can also adjust the weighting of chapters based on the submission frequency. This enables chapter division based on the submission frequency. Some or all of the above-mentioned processing in the chapter section can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chapter section can input submission frequency data into the generation AI and weight the chapters.

[0098] The chapter unit can analyze the viewing history of the video when dividing the video into chapters and customize the chapters based on the viewer's interests. The chapter unit can, for example, use a generation AI to analyze the viewing history of the video when dividing the video into chapters and customize the chapters based on the viewer's interests. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the chapter unit can include points of interest in chapters based on the user's viewing history. The chapter unit can also include related information from the viewing history in the chapters. The chapter unit can also analyze the viewing history and divide the chapters optimally. This enables chapter division based on the viewer's interests. Some or all of the above-mentioned processing in the chapter unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chapter unit can input viewing history data into the generation AI to customize the chapters.

[0099] The chapter section can adjust the length of the chapters according to the length of the video when dividing the video into chapters. The chapter section adjusts the length of the chapters according to the length of the video when dividing the video into chapters, for example, using a generation AI. The generation AI can be a text generation AI (for example, LLM) or a multimodal generation AI. For example, the chapter section can divide a long video into detailed chapters. Furthermore, the chapter section can divide a short video into concise chapters. Furthermore, the chapter section can divide a medium-length video into chapters with an appropriate level of detail. This enables chapter division according to the length of the video. Some or all of the above-mentioned processing in the chapter section can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chapter section can input video length data into the generation AI and adjust the chapter length.

[0100] The chapter section can estimate a user's emotions and adjust the display order of chapters based on the estimated user emotions. The chapter section, for example, uses a generation AI to estimate a user's emotions and adjust the display order of chapters based on the estimated user emotions. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the chapter section can display important chapters first when the user is stressed. The chapter section can also display detailed chapters in order when the user is relaxed. The chapter section can also display chapters that highlight the main points first when the user is in a hurry. This makes it possible to provide a chapter display order that corresponds to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the chapter section can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the chapter section can input user emotion data into the generation AI and adjust the display order of chapters based on the estimated user emotion.

[0101] The chapter section can divide a video into chapters taking into account the geographical distribution of the video. For example, the chapter section uses a generation AI to divide the video into chapters taking into account the geographical distribution of the video. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the chapter section groups geographically related parts into one chapter. The chapter section can also clearly divide geographically different parts to generate chapters. The chapter section can also analyze the geographical distribution and divide the video into optimal chapters. This enables chapter division based on the geographical distribution. Some or all of the above-described processing in the chapter section can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the chapter section can input geographical distribution data into the generation AI to generate chapters.

[0102] The chapter section can improve the accuracy of chapters by referring to related literature of the video when dividing the chapters. The chapter section can improve the accuracy of chapters by referring to related literature of the video when dividing the chapters, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the chapter section can include important points in chapters based on related literature. The chapter section can also complement the content of the chapters by referring to related literature. The chapter section can also improve the accuracy of chapters by utilizing related literature. This makes it possible to divide the chapters by referring to related literature. Some or all of the above-mentioned processing in the chapter section can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chapter section can input related literature data into the generation AI to improve the accuracy of the chapters.

[0103] The chapter section can divide the video into chapters based on the market value of the video. For example, the chapter section uses a generation AI to divide the video into chapters based on the market value of the video. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the chapter section can divide the video into detailed chapters for a video with high market value. Also, the chapter section can divide the video into simple chapters for a video with low market value. Also, the chapter section can divide the video into optimal chapters based on the market value. This enables chapter division based on market value. Some or all of the above-mentioned processing in the chapter section can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the chapter section can input market value data into the generation AI and perform chaptering.

[0104] The chapter section can improve the content of the chapters by reflecting the feedback of viewers of the video when dividing the chapters. The chapter section can improve the content of the chapters by using, for example, a generation AI when dividing the chapters. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the chapter section can generate chapters by referring to chapter styles that viewers have highly rated. The chapter section can also improve the content of the chapters based on the viewer feedback. The chapter section can also analyze viewer comments and reflect them in the content of the chapters. This enables chapter division that reflects viewer feedback. Some or all of the above-mentioned processing in the chapter section can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the chapter section can input viewer feedback data into the generation AI to improve the content of the chapters.

[0105] The chapter section can improve the accuracy of chapters by utilizing subtitle information of the video when dividing the video into chapters. For example, the chapter section can improve the accuracy of chapters by utilizing subtitle information of the video when dividing the video into chapters using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the chapter section can analyze subtitle information of the video and include important points in the chapters. The chapter section can also complement the content of the chapters based on the subtitle information. The chapter section can also improve the accuracy of chapters by utilizing the subtitle information. This enables chapter division using subtitle information. Some or all of the above-mentioned processing in the chapter section can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chapter section can input subtitle information of the video into the generation AI to improve the accuracy of chapters.

[0106] The search unit can estimate a user's emotion and adjust the display method of search results based on the estimated user emotion. The search unit can estimate a user's emotion using, for example, a generation AI and adjust the display method of search results based on the estimated user emotion. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit can provide a simple search result display when the user is stressed. The search unit can also provide a detailed search result display when the user is relaxed. The search unit can also provide a search result display that focuses on the main points when the user is in a hurry. This makes it possible to provide a search result display that corresponds to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the search unit can be performed using, for example, a generation AI. For example, the search unit can input user emotion data into the generation AI and adjust the display method of search results based on the estimated user emotion.

[0107] The search unit can improve search accuracy based on the interrelationships between videos during a search. The search unit can improve search accuracy based on the interrelationships between videos during a search, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, if the content of videos is continuous, the search unit prioritizes searching for related parts. Furthermore, if the content of videos is different, the search unit can clearly divide the videos and display search results. Furthermore, the search unit can analyze the interrelationships between videos and provide optimal search results. This enables searches that take into account the interrelationships between videos. Some or all of the above-described processing in the search unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the search unit can input video interrelationship data into the generation AI to improve search accuracy.

[0108] The search unit can perform a search taking into account the attribute information of the video submitter when searching. The search unit can perform a search taking into account the attribute information of the video submitter when searching, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit provides detailed search results when the submitter is an expert. The search unit can also provide concise search results when the submitter is a general user. The search unit can also provide optimal search results based on the attribute information of the submitter. This enables a search based on the attribute information of the submitter. Some or all of the above-mentioned processing in the search unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the search unit can input attribute information data of the submitter into the generation AI and perform a search.

[0109] The search unit can weight the search based on the submission frequency of the video during a search. The search unit, for example, uses a generation AI to weight the search based on the submission frequency of the video during a search. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit provides detailed search results for videos that are submitted frequently. The search unit can also provide concise search results for videos that are submitted infrequently. The search unit can also adjust the weighting of the search results based on the submission frequency. This enables a search based on the submission frequency. Some or all of the above-described processing in the search unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the search unit can input submission frequency data into the generation AI to weight the search.

[0110] The search unit can analyze the video viewing history during a search and customize search results based on the viewer's interests. The search unit can use, for example, a generation AI to analyze the video viewing history during a search and customize search results based on the viewer's interests. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit can include points of interest in the search results based on the user's viewing history. The search unit can also include related information from the viewing history in the search results. The search unit can also analyze the viewing history and provide optimal search results. This makes it possible to provide search results based on the viewer's interests. Some or all of the above-described processing in the search unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the search unit can input viewing history data into the generation AI to customize search results.

[0111] The search unit can adjust the display of search results according to the length of the video when searching. The search unit, for example, uses a generation AI to adjust the display of search results according to the length of the video when searching. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit provides detailed search results for long videos. The search unit can also provide concise search results for short videos. The search unit can also provide search results with an appropriate level of detail for videos of medium length. This makes it possible to provide search results according to the length of the video. Some or all of the above-mentioned processing in the search unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the search unit can input video length data into the generation AI and adjust the display of search results.

[0112] The search unit can estimate the user's emotions and adjust the display order of search results based on the estimated user emotions. The search unit can estimate the user's emotions using, for example, a generation AI and adjust the display order of search results based on the estimated user emotions. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, if the user is feeling stressed, the search unit can display important search results first. Also, if the user is relaxed, the search unit can display detailed search results in order. Also, if the user is in a hurry, the search unit can display search results that highlight the main points first. This makes it possible to provide a search result display order that corresponds to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the search unit can be performed using, for example, a generation AI, or without a generation AI. For example, the search unit can input user emotion data into the generation AI and adjust the display order of search results based on the estimated user emotion.

[0113] The search unit can perform a search taking into account the geographical distribution of videos. The search unit, for example, uses a generation AI to perform a search taking into account the geographical distribution of videos. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit prioritizes searching for geographically related parts. The search unit can also display search results by clearly dividing geographically distinct parts. The search unit can also analyze the geographical distribution and provide optimal search results. This enables a search based on geographical distribution. Some or all of the above-described processing in the search unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the search unit can input geographical distribution data into the generation AI and perform a search.

[0114] The search unit can improve search accuracy by referring to literature related to the video during a search. The search unit can improve search accuracy by referring to literature related to the video during a search, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit can include important points in search results based on related literature. The search unit can also complement the content of search results by referring to related literature. The search unit can also improve search accuracy by utilizing related literature. This makes it possible to perform searches by referring to related literature. Some or all of the above-mentioned processing in the search unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the search unit can input related literature data into the generation AI to improve search accuracy.

[0115] The search unit can perform a search taking into account the market value of a video when searching. The search unit, for example, uses a generation AI to perform a search taking into account the market value of a video when searching. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit provides detailed search results for videos with high market value. The search unit can also provide concise search results for videos with low market value. The search unit can also provide optimal search results based on market value. This enables a search based on market value. Some or all of the above-mentioned processing in the search unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the search unit can input market value data into the generation AI and perform a search.

[0116] The search unit can improve search results by reflecting feedback from viewers of the video at the time of a search. The search unit can improve search results by reflecting feedback from viewers of the video at the time of a search, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit performs a search by referring to search result styles that viewers have highly rated. The search unit can also improve the content of the search results based on viewer feedback. The search unit can also analyze viewer comments and reflect them in the content of the search results. This makes it possible to provide search results that reflect viewer feedback. Some or all of the above-mentioned processing in the search unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the search unit can input viewer feedback data into the generation AI to improve the search results.

[0117] The search unit can improve search accuracy by utilizing subtitle information of a video during a search. The search unit can improve search accuracy by utilizing subtitle information of a video during a search, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the search unit can analyze subtitle information of a video and include important points in the search results. The search unit can also complement the content of the search results based on the subtitle information. The search unit can also improve search accuracy by utilizing the subtitle information. This improves the accuracy of searches that utilize subtitle information. Some or all of the above-mentioned processing in the search unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the search unit can input subtitle information of a video into the generation AI to improve search accuracy. === Hard Collateral 1-1 === Each of the multiple elements, including the summary section, chapter section, and search section, described above, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the summary section is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the summary section analyzes the content of a video using a generation AI, extracts important points, and generates a summary. The chapter section is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and divides the video into chapters based on the summary. The search section is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and when a user inputs a specific keyword, searches for a portion of the video related to the keyword and plays the relevant portion. === Hard Collateral 1-2 === Each of the multiple elements, including the summary section, chapter section, and search section, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the summary section is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the summary section analyzes the content of the video using a generation AI, extracts important points, and generates a summary. The chapter section is realized, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and divides the video into chapters based on the summary. The search section is realized, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and when a user inputs a specific keyword, searches for a part of the video related to the keyword and plays the relevant part. === Hard Collateral 1-3 === Each of the multiple elements including the summary section, chapter section, and search section described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the summary section is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, a generation AI is used to analyze the content of a video, extract important points, and generate a summary. The chapter section is realized, for example, by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and divides the video into chapters based on the summary. The search section is realized, for example, by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and when a user inputs a specific keyword, searches for parts of the video related to the keyword and plays the relevant parts. === Hard Collateral 1-4 === Each of the multiple elements including the summary section, chapter section, and search section described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the summary section is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the summary section analyzes the content of the video using a generation AI, extracts important points, and generates a summary. The chapter section is realized, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and divides the video into chapters based on the summary. The search section is realized, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and when a user inputs a specific keyword, searches for parts of the video related to the keyword and plays the relevant parts.

[0118] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0119] The summarization unit can analyze the user's past viewing history and customize the content of the summary based on the viewing history. For example, the summarization unit can highlight relevant information based on the content of videos the user has previously viewed. The summarization unit can also include points that the user may be interested in from the user's viewing history in the summary. Furthermore, the summarization unit can analyze the user's viewing history and suggest the optimal summarization method. This makes it possible to provide summaries based on the viewer's interests.

[0120] The chapter section can improve the content of chapters by reflecting the feedback of viewers of the video. For example, the chapter section generates chapters by referring to chapter styles that viewers have given high ratings to. The chapter section can also improve the content of chapters based on the feedback of viewers. Furthermore, the chapter section can analyze the comments of viewers and reflect them in the content of chapters. This makes it possible to divide chapters in a way that reflects the feedback of viewers.

[0121] The search unit can estimate the user's emotions and adjust the display method of search results based on the estimated user's emotions. For example, the search unit can provide a simple search result display when the user is stressed. The search unit can also provide a detailed search result display when the user is relaxed. Furthermore, the search unit can provide a search result display that focuses on the main points when the user is in a hurry. In this way, it is possible to provide a search result display that corresponds to the user's emotions.

[0122] The summarizer can apply different summarization algorithms depending on the category of the video when generating a summary. For example, the summarizer can generate a summary that emphasizes learning points for an educational video. For an entertainment video, the summarizer can generate a summary that emphasizes key scenes. For a news video, the summarizer can generate a summary that emphasizes important news items. This allows for providing summaries according to the category of the video.

[0123] The chapter section can estimate the user's emotions and adjust the way the chapters are displayed based on the estimated user's emotions. For example, the chapter section can provide a simple chapter display when the user is stressed. The chapter section can also provide a detailed chapter display when the user is relaxed. Furthermore, the chapter section can provide a concise chapter display when the user is in a hurry. This allows the chapter display to be provided according to the user's emotions.

[0124] The search unit can improve search accuracy based on the interrelationships between videos during a search. For example, if the content of videos is continuous, the search unit will prioritize searching for related parts. Also, if the content of videos is different, the search unit can clearly separate and display search results. Furthermore, the search unit can analyze the interrelationships between videos and provide optimal search results. This enables searches that take into account the interrelationships between videos.

[0125] The summarization unit can estimate the user's emotions and adjust the presentation of the summary based on the estimated user's emotions. For example, if the user is feeling stressed, the summarization unit can make the summary concise and emphasize only the important points. Alternatively, if the user is relaxed, the summarization unit can provide a summary with detailed explanations. Furthermore, if the user is in a hurry, the summarization unit can shorten the summary and quickly convey the main points. In this way, a summary can be provided that corresponds to the user's emotions.

[0126] The chapter section can divide the video into chapters based on the attribute information of the person who submitted the video. For example, if the submitter is an expert, the chapter section can divide the video into detailed chapters. Also, if the submitter is a general user, the chapter section can divide the video into simple chapters. Furthermore, the chapter section can divide the video into optimal chapters based on the attribute information of the submitter. This makes it possible to divide the video into chapters based on the attribute information of the submitter.

[0127] When searching, the search unit can analyze the video viewing history and customize search results based on the viewer's interests. For example, the search unit can include points of interest that the user may have based on the user's viewing history in the search results. The search unit can also include related information from the viewing history in the search results. Furthermore, the search unit can analyze the viewing history and provide optimal search results. This allows the search results to be provided based on the viewer's interests.

[0128] When generating a summary, the summarization unit can adjust the level of detail of the summary based on the importance of the video. For example, the summarization unit generates a detailed summary for an important video. The summarization unit can also generate a concise summary for a general video. Furthermore, the summarization unit can generate a summary including details of a specific event for a video related to the event. This makes it possible to provide a summary according to the importance of the video.

[0129] The processing flow of the second embodiment will be briefly explained below.

[0130] Step 1: The summarization unit analyzes the content of the video and generates a summary. For example, the summarization unit uses a generation AI to analyze the content of the video, extract key points, and generate a summary. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. Step 2: The chaptering section divides the video into chapters based on the summary generated by the summarization section. The chaptering section analyzes the content of the video using, for example, a generation AI and displays the content of each chapter concisely. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. Step 3: When a user inputs a specific keyword, the search unit searches for parts of the video related to that keyword and plays the relevant parts. For example, when a user inputs a specific keyword, the search unit uses a generation AI to automatically search for parts of the video related to that keyword and play the relevant parts. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI.

[0131] 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.

[0132] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<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.

[0133] 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.

[0134] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0135] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0145] 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. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0151] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0161] 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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0167] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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).

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0178] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. 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 the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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).

[0188] 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.

[0189] 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."

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] [Explanation of symbols]

[0203] 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 summarization unit that analyzes the content of the video and generates a summary; a chapter section for dividing a video into chapters based on the summary generated by the summarization section; A search unit that, when a user inputs a specific keyword, searches for a part of a video related to the keyword and plays the relevant part. A system characterized by:

2. The summary section Generative AI analyzes the content of the video, extracts key points, and generates a summary 2. The system of claim 1.

3. The chapter part includes: Analyze the video content using generative AI and display the contents of each chapter concisely.

2. The system of claim 1.

4. The search unit When a user enters a specific keyword, the AI ​​automatically searches for the part of the video related to that keyword and plays that part.

2. The system of claim 1.

5. The chapter part includes: Summarize meeting minutes and display key points divided into chapters 2. The system of claim 1.

6. The chapter part includes: In the video version of the manual, the chapters are divided into steps, and the content of each step is displayed concisely.

2. The system of claim 1.

7. The summary section Estimate the user's emotions and adjust the way summaries are presented based on the estimated user emotions.

2. The system of claim 1.

8. The summary section When generating summaries, adjust the level of detail in the summary based on the importance of the video.

2. The system of claim 1.

Images