system

Abstract

The system according to the embodiment aims to efficiently extract key information from long videos and provide summaries. [Solution] A system according to an embodiment includes a reception unit, an analysis unit, a summarization unit, and a provision unit. The reception unit receives a video URL from a user. The analysis unit analyzes the audio or subtitles of the video received by the reception unit and extracts key topics or keywords. The summarization unit creates a summary based on the topics or keywords extracted by the analysis unit. The provision unit provides the summary created by the summarization unit to the user.

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the problem that it is difficult and time-consuming to efficiently extract necessary information from long videos.

[0005] The system according to the embodiment aims to efficiently extract key information from long videos and provide summaries. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a summarization unit, and a provision unit. The reception unit receives a video URL from a user. The analysis unit analyzes the audio or subtitles of the video received by the reception unit and extracts key topics or keywords. The summarization unit creates a summary based on the topics or keywords extracted by the analysis unit. The provision unit provides the summary created by the summarization unit to the user. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently extract key information from long videos and provide summaries. [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 video summarization system according to an embodiment of the present invention is a plug-in function called "Video Insights" that summarizes the content of videos, such as YouTube (registered trademark) videos. This video summarization system efficiently selects videos to watch by summarizing the content of 20-minute videos so that it can be understood in one minute. Furthermore, English videos are also summarized in Japanese, making it convenient for users who want to understand overseas cases or the latest news. For example, a user inputs the URL of a YouTube video. Next, a generation AI analyzes the content of the video and extracts key points. The generation AI analyzes the video's audio and subtitles to understand the content. For example, it extracts key topics and keywords discussed in the video and creates a summary based on them. The generated summary is provided to the user. By reading the summary, the user can quickly understand the content of the video. For example, a 20-minute video can be understood in about one minute. Furthermore, English videos are summarized in Japanese, making the content easy to understand even for users who are not good at English. This plug-in function allows users to efficiently select videos and quickly obtain the information they need. For example, it is very useful for business people to keep up with the latest industry news, or for students to use educational content from overseas. This allows users to quickly understand the content of videos and efficiently select videos.

[0029] A video summarization system according to an embodiment includes a receiving unit, an analysis unit, a summarization unit, and a providing unit. The receiving unit receives a video URL from a user. The user can input, for example, a YouTube video URL. The receiving unit passes the input video URL to the analysis unit. The analysis unit analyzes the audio or subtitles of the video and extracts key topics or keywords. The analysis unit converts the audio of the video into text using, for example, speech recognition technology and compares it with subtitle data. The analysis unit uses a generation AI to understand the content of the video and extract key topics and keywords. For example, the generation AI extracts key topics and keywords spoken in the video and creates a summary based on them. The summarization unit creates a summary based on the topics and keywords extracted by the analysis unit. The summarization unit uses the generation AI to extract key topics and keywords from text data and create a summary based on them. For example, the generation AI uses a text generation AI (e.g., LLM) to concisely summarize the content of the video. The providing unit provides the summary created by the summarization unit to the user. The providing unit provides the summary to the user in text format, for example. The providing unit can also translate the summary into Japanese using a generation AI. For example, for an English video, the providing unit is provided with a translation function for creating a summary in Japanese. This allows the video summarization system according to the embodiment to enable the user to quickly understand the content of the video and efficiently select videos. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the summary to a generation AI and cause the generation AI to provide the summary.

[0030] The analysis unit can convert the audio of a video into text and compare it with subtitle data. The analysis unit can convert the audio of a video into text, for example, using speech recognition technology. For example, the analysis unit can convert the audio of a video into text in real time using speech recognition software. The analysis unit can also record the audio of a video and later convert it into text using speech recognition technology. For example, the analysis unit can analyze an audio file and generate text data. The analysis unit can also convert audio data into text data using a generation AI. For example, the analysis unit can input audio data into a generation AI to generate text data. Next, the analysis unit can compare the generated text data with subtitle data. For example, the analysis unit can calculate the degree of similarity between the subtitle data and the text data and output the comparison result. The analysis unit can also compare the subtitle data with the text data using a generation AI. For example, the analysis unit can input subtitle data and text data into a generation AI and calculate the degree of similarity. This improves the accuracy of the analysis by comparing the audio and subtitle data. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input audio data and subtitle data into the generation AI and have the generation AI output the matching results.

[0031] The summarization unit can extract major topics and keywords from text data and create a summary based on them. The summarization unit extracts major topics and keywords from text data, for example, using a generation AI. For example, the summarization unit inputs text data into the generation AI and causes it to extract major topics and keywords. The summarization unit can also extract major topics and keywords from text data using natural language processing technology. For example, the summarization unit extracts major topics and keywords based on frequently occurring words and importance scores. Then, the summarization unit creates a summary based on the extracted topics and keywords. For example, the summarization unit uses the generation AI to create a summary based on the extracted topics and keywords. The summarization unit can also create a summary using a text generation AI (e.g., LLM). For example, the summarization unit inputs the extracted topics and keywords into the generation AI and causes it to generate a summary. This improves the accuracy of the summary by creating a summary based on the major topics and keywords. Some or all of the above-mentioned processing in the summarization unit may be performed, for example, using AI, or may be performed without using AI. For example, the summarization unit can input text data into the generation AI and have the generation AI create a summary.

[0032] The providing unit can provide the summary to the user in text format. For example, the providing unit can provide the summary to the user in plain text format. For example, the providing unit can cause the user to download the summary as a text file. The providing unit can also provide the summary in HTML format. For example, the providing unit can display the summary as a web page so that the user can view it in a browser. The providing unit can also send the summary to the user by email. For example, the providing unit can attach the summary in text format to an email and send it to the user. By providing the summary in text format, the user can easily understand the content. Some or all of the above-mentioned processing in the providing unit can be performed, for example, using AI or without AI. For example, the providing unit can input the summary to a generation AI and cause the generation AI to provide the summary in text format.

[0033] The summarization unit may have a translation function for creating summaries in Japanese for English videos. The summarization unit, for example, uses a generation AI to translate English videos into Japanese. For example, the summarization unit inputs English text data into the generation AI and causes it to generate Japanese text data. The summarization unit may also translate English videos into Japanese using a machine translation algorithm. For example, the summarization unit converts English text data into Japanese using a machine translation engine. Furthermore, the summarization unit may also translate English videos into Japanese in real time using a translation engine. For example, the summarization unit converts English audio data into Japanese text data in real time. By summarizing English videos in Japanese, even users who are not good at English can easily understand the content. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit may input English text data into the generation AI and cause the generation AI to create Japanese text data.

[0034] The reception unit can analyze the user's past video viewing history and select an appropriate video URL input method. The reception unit, for example, collects and analyzes the user's past video viewing history. For example, the reception unit can analyze the genre of videos the user has previously viewed and prompt the user to input a related video URL. The reception unit can also analyze the length of videos the user has previously viewed and suggest the user to input an appropriate video URL. Furthermore, the reception unit can analyze the ratings of videos the user has previously viewed and prompt the user to input a highly rated video URL. In this way, by analyzing the past viewing history, the optimal video URL input method can be provided to the user. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's viewing history data into a generation AI and have the generation AI select the optimal input method.

[0035] The reception unit can filter video URLs based on the user's current areas of interest when the video URLs are input. The reception unit can, for example, analyze the user's search history and social media activity to identify the user's current areas of interest. For example, the reception unit can input relevant video URLs based on keywords recently searched by the user. The reception unit can also preferentially input new video URLs from channels the user follows. Furthermore, the reception unit can also preferentially input video URLs related to topics in which the user is currently interested. This allows highly relevant video URLs to be input by filtering based on the user's areas of interest. Some or all of the above-described processing by the reception unit can be performed using, for example, AI, or without AI. For example, the reception unit can input the user's area of ​​interest data to a generation AI and have the generation AI perform filtering.

[0036] When inputting a video URL, the reception unit can prioritize inputting a highly relevant video URL based on the user's geographical location information. The reception unit, for example, collects and analyzes the user's geographical location information. For example, the reception unit can identify the user's current location using GPS data. The reception unit can also obtain the user's geographical location information using a location information service. Next, the reception unit prioritizes inputting a highly relevant video URL based on the user's geographical location information. For example, if the user is in a specific area, the reception unit can prioritize video URLs related to that area. If the user is traveling, the reception unit can prioritize video URLs related to the travel destination. Furthermore, if the user is participating in a specific event, the reception unit can prioritize video URLs related to the event. In this way, by taking the geographical location information into consideration, highly relevant video URLs can be prioritized. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's geographical location information data to a generation AI and cause the generation AI to select highly relevant video URLs.

[0037] When a video URL is input, the reception unit can analyze the user's social media activity and input related video URLs. The reception unit, for example, collects and analyzes the user's social media activity. For example, the reception unit inputs video URLs related to content shared by the user on social media. The reception unit can also input video URLs introduced by influencers the user follows. Furthermore, the reception unit can input video URLs related to topics in groups the user participates in. In this way, related video URLs can be input by analyzing social media activity. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's social media activity data to the generation AI and cause the generation AI to select related video URLs.

[0038] When analyzing audio or subtitles, the analysis unit can adjust the level of detail of the analysis based on the importance of the video. The analysis unit, for example, analyzes the number of views and user ratings to evaluate the importance of the video. For example, the analysis unit determines that a video with a high number of views is an important video and performs a detailed analysis. The analysis unit can also determine that a video with a high user rating is an important video and perform a detailed analysis. Furthermore, the analysis unit can determine that a video related to a specific event is an important video and perform a detailed analysis. Next, the analysis unit adjusts the level of detail of the analysis based on the importance of the video. For example, the analysis unit performs a detailed analysis for an important video. The analysis unit can also perform a standard analysis for a general video. Furthermore, the analysis unit can perform a simplified analysis for a video with low importance. In this way, adjusting the level of detail of the analysis based on the importance of the video enables efficient analysis. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input video importance data to a generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0039] When analyzing audio and subtitles, the analysis unit can apply different analysis algorithms depending on the category of the video. For example, the analysis unit analyzes video metadata to identify the category of the video. For example, the analysis unit analyzes the title and description of the video to identify the category. The analysis unit can also analyze the content of the video to identify the category. Next, the analysis unit applies different analysis algorithms depending on the category of the video. For example, the analysis unit applies a terminology analysis algorithm to educational videos. The analysis unit can also apply a sentiment analysis algorithm to entertainment videos. Furthermore, the analysis unit can apply a keyword extraction algorithm to business videos. In this way, by applying an analysis algorithm depending on the video category, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input video category data to the generation AI and cause the generation AI to apply the analysis algorithm.

[0040] When analyzing audio and subtitles, the analysis unit can determine analysis priorities based on the time the video was submitted. The analysis unit, for example, collects and analyzes the time the video was submitted. For example, the analysis unit records the submission date and time of the video and sets priorities based on the time of submission. The analysis unit can also prioritize analysis of videos within a period specified by the user. Furthermore, the analysis unit can also prioritize analysis of videos related to a specific event. Next, the analysis unit determines analysis priorities based on the time the video was submitted. For example, the analysis unit prioritizes analysis of the most recent video. The analysis unit can also prioritize analysis of videos within a period specified by the user. Furthermore, the analysis unit can also prioritize analysis of videos related to a specific event. In this way, determining analysis priorities based on the time the video was submitted enables efficient analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input video submission date data to a generation AI and have the generation AI determine the analysis priorities.

[0041] When analyzing audio and subtitles, the analysis unit can adjust the order of analysis based on the relevance of the videos. For example, the analysis unit analyzes content similarity and viewing history to evaluate the relevance of the videos. For example, the analysis unit prioritizes analyzing videos related to topics in which the user is interested. The analysis unit can also prioritize analyzing videos from channels the user follows. Furthermore, the analysis unit can also prioritize analyzing videos that the user has given high ratings. Next, the analysis unit adjusts the order of analysis based on the relevance of the videos. For example, the analysis unit prioritizes analyzing videos related to topics in which the user is interested. The analysis unit can also prioritize analyzing videos from channels the user follows. Furthermore, the analysis unit can also prioritize analyzing videos that the user has given high ratings. In this way, adjusting the order of analysis based on the relevance of the videos enables efficient analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input video relevance data to a generation AI and cause the generation AI to adjust the order of analysis.

[0042] 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 analyzes the number of views and user ratings to evaluate the importance of the video. For example, the summarization unit determines that a video with a high number of views is an important video and provides a detailed summary. The summarization unit can also determine that a video with a high user rating is an important video and provide a detailed summary. Furthermore, the summarization unit can determine that a video related to a specific event is an important video and provide a detailed summary. Next, the summarization unit adjusts the level of detail of the summary based on the importance of the video. For example, the summarization unit provides a detailed summary for an important video. The summarization unit can also provide a standard summary for a general video. Furthermore, the summarization unit can provide a simplified summary for a video with low importance. In this way, adjusting the level of detail of the summary based on the importance of the video enables efficient summarization. Some or all of the above-mentioned processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input video importance data to the generation AI and cause the generation AI to adjust the level of detail of the summary.

[0043] When generating a summary, the summarization unit can apply different summarization algorithms depending on the category of the video. For example, the summarization unit analyzes video metadata to identify the category of the video. For example, the summarization unit analyzes the title and description of the video to identify the category. The summarization unit can also analyze the content of the video to identify the category. Next, the summarization unit applies different summarization algorithms depending on the category of the video. For example, the summarization unit applies a summarization algorithm that includes technical terms to educational videos. The summarization unit can also apply a summarization algorithm that reflects emotions to entertainment videos. Furthermore, the summarization unit can apply a summarization algorithm that emphasizes keywords to business videos. In this way, applying a summarization algorithm depending on the category of the video improves the accuracy of the summary. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input video category data to the generation AI and cause the generation AI to apply the summarization algorithm.

[0044] When generating summaries, the summarization unit can determine the priority of summaries based on the time of video submission. The summarization unit, for example, collects and analyzes the time of video submission. For example, the summarization unit records the submission date and time of videos and sets the priority based on the time of submission. The summarization unit can also prioritize summarizing videos within a period specified by a user. Furthermore, the summarization unit can also prioritize summarizing videos related to a specific event. Next, the summarization unit determines the priority of summaries based on the time of video submission. For example, the summarization unit prioritizes summarizing the most recent videos. The summarization unit can also prioritize summarizing videos within a period specified by a user. Furthermore, the summarization unit can also prioritize summarizing videos related to a specific event. In this way, by determining the priority of summaries based on the time of video submission, efficient summarization can be achieved. Some or all of the above-described processing in the summarization unit may be performed using, for example, AI, or may be performed without AI. For example, the summarization unit can input video submission date data to a generation AI and have the generation AI determine the priority of summaries.

[0045] When generating summaries, the summarization unit can adjust the order of summaries based on the relevance of the videos. For example, the summarization unit analyzes content similarity and viewing history to evaluate the relevance of the videos. For example, the summarization unit prioritizes summarizing videos related to topics in which the user is interested. The summarization unit can also prioritize summarizing videos from channels the user follows. Furthermore, the summarization unit can also prioritize summarizing videos that the user has given a high rating. Next, the summarization unit adjusts the order of summaries based on the relevance of the videos. For example, the summarization unit prioritizes summarizing videos related to topics in which the user is interested. The summarization unit can also prioritize summarizing videos from channels the user follows. Furthermore, the summarization unit can also prioritize summarizing videos that the user has given a high rating. In this way, adjusting the order of summaries based on the relevance of the videos enables efficient summarization. Some or all of the above-described processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit may input video relevance data to a generation AI and cause the generation AI to adjust the order of summaries.

[0046] When providing a summary, the providing unit can select an appropriate delivery method by referring to the user's past viewing history. The providing unit, for example, collects and analyzes the user's past viewing history. For example, the providing unit can provide a summary based on the genre of videos the user has previously viewed. The providing unit can also provide a summary based on the length of videos the user has previously viewed. Furthermore, the providing unit can also provide a summary based on the user's rating of videos the user has previously viewed. In this way, by referring to the past viewing history, the optimal summary delivery method can be provided to the user. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's viewing history data into a generation AI and cause the generation AI to select the optimal delivery method.

[0047] When providing a summary, the providing unit can customize the content provided based on the user's current areas of interest. For example, the providing unit can analyze the user's search history and social media activity to identify the user's current areas of interest. For example, the providing unit can provide a summary based on keywords recently searched by the user. The providing unit can also provide summaries of new videos on channels the user follows. Furthermore, the providing unit can provide summaries related to topics in which the user is currently interested. This allows the user to be provided with the most suitable summary by customizing the content provided based on the user's current areas of interest. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input the user's area of ​​interest data into a generating AI and have the generating AI customize the content provided.

[0048] The providing unit can select the optimal delivery method by taking into account the user's geographical location information when providing a summary. The providing unit, for example, collects and analyzes the user's geographical location information. For example, the providing unit can identify the user's current location using GPS data. The providing unit can also obtain the user's geographical location information using a location information service. Next, the providing unit selects the optimal delivery method based on the user's geographical location information. For example, if the user is in a specific area, the providing unit can provide a summary related to that area. If the user is traveling, the providing unit can also provide a summary related to the travel destination. Furthermore, if the user is participating in a specific event, the providing unit can also provide a summary related to the event. In this way, the optimal summary delivery method can be provided to the user by taking into account the geographical location information. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's geographical location information data to a generation AI and cause the generation AI to select the optimal delivery method.

[0049] When providing a summary, the providing unit can customize the content to be provided by analyzing the user's social media activity. The providing unit, for example, collects and analyzes the user's social media activity. For example, the providing unit can provide a summary related to content shared by the user on social media. The providing unit can also provide summaries of videos introduced by influencers the user follows. Furthermore, the providing unit can also provide summaries related to topics of groups the user participates in. In this way, by analyzing social media activity, the most suitable summary can be provided to the user. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's social media activity data into a generation AI and cause the generation AI to customize the content to be provided.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The reception unit can analyze the user's past viewing history and suggest input of related video URLs based on the viewing history. For example, the reception unit can analyze the genre of videos the user has viewed in the past and suggest URLs of videos of the same genre. The reception unit can also analyze the length of videos the user has viewed in the past and suggest URLs of videos of similar length. Furthermore, the reception unit can analyze the genre of videos the user has previously given high ratings to and suggest URLs of videos of the same genre. In this way, by suggesting related video URLs based on the user's viewing history, it is possible to efficiently find videos that are likely to interest the user.

[0052] When analyzing the audio and subtitles of a video, the analysis unit can determine the priority of the analysis based on the number of views and ratings of the video. For example, the analysis unit prioritizes the analysis of videos with a large number of views. The analysis unit can also prioritize the analysis of videos with high user ratings. Furthermore, the analysis unit can also prioritize the analysis of videos related to a specific event. In this way, by determining the priority of the analysis based on the number of views and ratings, important videos can be analyzed efficiently.

[0053] The summarization unit can apply different summarization algorithms depending on the category of the video. For example, the summarization unit can apply a summarization algorithm that includes technical terms to educational videos. The summarization unit can also apply a summarization algorithm that reflects emotions to entertainment videos. Furthermore, the summarization unit can apply a summarization algorithm that emphasizes keywords to business videos. In this way, applying a summarization algorithm depending on the category of the video improves the accuracy of the summary.

[0054] The providing unit can preferentially input highly relevant video URLs based on the user's geographical location information. For example, if the user is in a specific area, the providing unit can prioritize video URLs related to that area. Also, if the user is traveling, the providing unit can prioritize video URLs related to the travel destination. Furthermore, if the user is participating in a specific event, the providing unit can prioritize video URLs related to the event. In this way, highly relevant video URLs can be preferentially input by taking geographical location information into consideration.

[0055] The providing unit can analyze the user's social media activity and input related video URLs. For example, the providing unit can input video URLs related to content shared by the user on social media. The providing unit can also input video URLs introduced by influencers the user follows. Furthermore, the providing unit can input video URLs related to topics in groups the user participates in. In this way, related video URLs can be input by analyzing social media activity.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The reception unit receives input of a video URL from the user. The user can input, for example, a YouTube video URL. The reception unit passes the input video URL to the analysis unit. Step 2: The analysis unit analyzes the video's audio or subtitles and extracts key topics or keywords. For example, the analysis unit uses speech recognition technology to convert the video's audio into text and compare it with the subtitle data. The analysis unit uses generative AI to understand the content of the video and extract key topics and keywords. Step 3: The summarization unit creates a summary based on the topics and keywords extracted by the analysis unit. The summarization unit uses a generation AI to extract key topics and keywords from the text data and create a summary based on them. For example, the generation AI uses a text generation AI (e.g., LLM) to concisely summarize the content of the video. Step 4: The providing unit provides the summary created by the summarizing unit to the user. The providing unit may provide the summary to the user in text format, for example. The providing unit may also use a generation AI to translate the summary into Japanese. For example, for an English video, the providing unit may have a translation function to create a summary in Japanese.

[0058] (Example 2) A video summarization system according to an embodiment of the present invention is a plug-in function called "Video Insights" that summarizes the content of videos, such as YouTube videos. This video summarization system efficiently selects videos to watch by summarizing the content of 20-minute videos so that they can be understood in one minute. Furthermore, English videos are summarized in Japanese, making it convenient for users who want to understand overseas cases or the latest news. For example, a user inputs the URL of a YouTube video. Next, a generation AI analyzes the content of the video and extracts key points. The generation AI analyzes the video's audio and subtitles to understand the content. For example, it extracts key topics and keywords discussed in the video and creates a summary based on them. The generated summary is provided to the user. By reading the summary, the user can quickly understand the content of the video. For example, a 20-minute video can be understood in about one minute. Furthermore, English videos are summarized in Japanese, making the content easy to understand even for users who are not good at English. This plug-in function allows users to efficiently select videos and quickly obtain the information they need. For example, it is very useful for business people to keep up with the latest industry news, or for students to use educational content from overseas. This allows users to quickly understand the content of videos and efficiently select videos.

[0059] A video summarization system according to an embodiment includes a receiving unit, an analysis unit, a summarization unit, and a providing unit. The receiving unit receives a video URL from a user. The user can input, for example, a YouTube video URL. The receiving unit passes the input video URL to the analysis unit. The analysis unit analyzes the audio or subtitles of the video and extracts key topics or keywords. The analysis unit converts the audio of the video into text using, for example, speech recognition technology and compares it with subtitle data. The analysis unit uses a generation AI to understand the content of the video and extract key topics and keywords. For example, the generation AI extracts key topics and keywords spoken in the video and creates a summary based on them. The summarization unit creates a summary based on the topics and keywords extracted by the analysis unit. The summarization unit uses the generation AI to extract key topics and keywords from text data and create a summary based on them. For example, the generation AI uses a text generation AI (e.g., LLM) to concisely summarize the content of the video. The providing unit provides the summary created by the summarization unit to the user. The providing unit provides the summary to the user in text format, for example. The providing unit can also translate the summary into Japanese using a generation AI. For example, for an English video, the providing unit is provided with a translation function for creating a summary in Japanese. This allows the video summarization system according to the embodiment to enable the user to quickly understand the content of the video and efficiently select videos. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the summary to a generation AI and cause the generation AI to provide the summary.

[0060] The analysis unit can convert the audio of a video into text and compare it with subtitle data. The analysis unit can convert the audio of a video into text, for example, using speech recognition technology. For example, the analysis unit can convert the audio of a video into text in real time using speech recognition software. The analysis unit can also record the audio of a video and later convert it into text using speech recognition technology. For example, the analysis unit can analyze an audio file and generate text data. The analysis unit can also convert audio data into text data using a generation AI. For example, the analysis unit can input audio data into a generation AI to generate text data. Next, the analysis unit can compare the generated text data with subtitle data. For example, the analysis unit can calculate the degree of similarity between the subtitle data and the text data and output the comparison result. The analysis unit can also compare the subtitle data with the text data using a generation AI. For example, the analysis unit can input subtitle data and text data into a generation AI and calculate the degree of similarity. This improves the accuracy of the analysis by comparing the audio and subtitle data. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input audio data and subtitle data into the generation AI and have the generation AI output the matching results.

[0061] The summarization unit can extract major topics and keywords from text data and create a summary based on them. The summarization unit extracts major topics and keywords from text data, for example, using a generation AI. For example, the summarization unit inputs text data into the generation AI and causes it to extract major topics and keywords. The summarization unit can also extract major topics and keywords from text data using natural language processing technology. For example, the summarization unit extracts major topics and keywords based on frequently occurring words and importance scores. Then, the summarization unit creates a summary based on the extracted topics and keywords. For example, the summarization unit uses the generation AI to create a summary based on the extracted topics and keywords. The summarization unit can also create a summary using a text generation AI (e.g., LLM). For example, the summarization unit inputs the extracted topics and keywords into the generation AI and causes it to generate a summary. This improves the accuracy of the summary by creating a summary based on the major topics and keywords. Some or all of the above-mentioned processing in the summarization unit may be performed, for example, using AI, or may be performed without using AI. For example, the summarization unit can input text data into the generation AI and have the generation AI create a summary.

[0062] The providing unit can provide the summary to the user in text format. For example, the providing unit can provide the summary to the user in plain text format. For example, the providing unit can cause the user to download the summary as a text file. The providing unit can also provide the summary in HTML format. For example, the providing unit can display the summary as a web page so that the user can view it in a browser. The providing unit can also send the summary to the user by email. For example, the providing unit can attach the summary in text format to an email and send it to the user. By providing the summary in text format, the user can easily understand the content. Some or all of the above-mentioned processing in the providing unit can be performed, for example, using AI or without AI. For example, the providing unit can input the summary to a generation AI and cause the generation AI to provide the summary in text format.

[0063] The summarization unit may have a translation function for creating summaries in Japanese for English videos. The summarization unit, for example, uses a generation AI to translate English videos into Japanese. For example, the summarization unit inputs English text data into the generation AI and causes it to generate Japanese text data. The summarization unit may also translate English videos into Japanese using a machine translation algorithm. For example, the summarization unit converts English text data into Japanese using a machine translation engine. Furthermore, the summarization unit may also translate English videos into Japanese in real time using a translation engine. For example, the summarization unit converts English audio data into Japanese text data in real time. By summarizing English videos in Japanese, even users who are not good at English can easily understand the content. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit may input English text data into the generation AI and cause the generation AI to create Japanese text data.

[0064] The reception unit can estimate the user's emotion and adjust the timing of inputting the video URL based on the estimated user's emotion. The reception unit can estimate the user's emotion using, for example, facial expression recognition technology. For example, the reception unit can analyze the user's facial expression captured by a camera and calculate an emotion score. The reception unit can also estimate the user's emotion using voice analysis technology. For example, the reception unit can analyze the tone and speed of the user's voice and calculate an emotion score. The reception unit can also estimate the user's emotion using text analysis technology. For example, the reception unit can analyze text data entered by the user and calculate an emotion score. Next, the reception unit adjusts the timing of inputting the video URL based on the estimated user's emotion. For example, if the user is feeling stressed, the reception unit can prompt the user to input the video URL at a time when the user can relax. If the user is concentrating, the reception unit can prompt the user to input the video URL immediately. If the user is tired, the reception unit can prompt the user to input the video URL after a break. In this way, by adjusting the timing of inputting the video URL according to the user's emotion, the video URL can be input at a more appropriate time. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI may 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 reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit may input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0065] The reception unit can analyze the user's past video viewing history and select an appropriate video URL input method. The reception unit, for example, collects and analyzes the user's past video viewing history. For example, the reception unit can analyze the genre of videos the user has previously viewed and prompt the user to input a related video URL. The reception unit can also analyze the length of videos the user has previously viewed and suggest the user to input an appropriate video URL. Furthermore, the reception unit can analyze the ratings of videos the user has previously viewed and prompt the user to input a highly rated video URL. In this way, by analyzing the past viewing history, the optimal video URL input method can be provided to the user. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's viewing history data into a generation AI and have the generation AI select the optimal input method.

[0066] The reception unit can filter video URLs based on the user's current areas of interest when the video URLs are input. The reception unit can, for example, analyze the user's search history and social media activity to identify the user's current areas of interest. For example, the reception unit can input relevant video URLs based on keywords recently searched by the user. The reception unit can also preferentially input new video URLs from channels the user follows. Furthermore, the reception unit can also preferentially input video URLs related to topics in which the user is currently interested. This allows highly relevant video URLs to be input by filtering based on the user's areas of interest. Some or all of the above-described processing by the reception unit can be performed using, for example, AI, or without AI. For example, the reception unit can input the user's area of ​​interest data to a generation AI and have the generation AI perform filtering.

[0067] The reception unit can estimate the user's emotion and prioritize the input video URLs based on the estimated user's emotion. The reception unit can estimate the user's emotion using, for example, facial expression recognition technology. For example, the reception unit can analyze the user's facial expression captured by a camera and calculate an emotion score. The reception unit can also estimate the user's emotion using voice analysis technology. For example, the reception unit can analyze the tone and speed of the user's voice and calculate an emotion score. The reception unit can also estimate the user's emotion using text analysis technology. For example, the reception unit can analyze text data input by the user and calculate an emotion score. Next, the reception unit prioritizes the input video URLs based on the estimated user's emotion. For example, if the user is excited, the reception unit can prioritize entertainment video URLs. If the user is relaxed, the reception unit can prioritize educational video URLs. If the user is focused, the reception unit can prioritize business video URLs. In this way, by prioritizing video URLs according to the user's emotion, more appropriate videos can be processed preferentially. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI may 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 reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit may input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0068] When inputting a video URL, the reception unit can prioritize inputting a highly relevant video URL based on the user's geographical location information. The reception unit, for example, collects and analyzes the user's geographical location information. For example, the reception unit can identify the user's current location using GPS data. The reception unit can also obtain the user's geographical location information using a location information service. Next, the reception unit prioritizes inputting a highly relevant video URL based on the user's geographical location information. For example, if the user is in a specific area, the reception unit can prioritize video URLs related to that area. If the user is traveling, the reception unit can prioritize video URLs related to the travel destination. Furthermore, if the user is participating in a specific event, the reception unit can prioritize video URLs related to the event. In this way, by taking the geographical location information into consideration, highly relevant video URLs can be prioritized. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's geographical location information data to a generation AI and cause the generation AI to select highly relevant video URLs.

[0069] When a video URL is input, the reception unit can analyze the user's social media activity and input related video URLs. The reception unit, for example, collects and analyzes the user's social media activity. For example, the reception unit inputs video URLs related to content shared by the user on social media. The reception unit can also input video URLs introduced by influencers the user follows. Furthermore, the reception unit can input video URLs related to topics in groups the user participates in. In this way, related video URLs can be input by analyzing social media activity. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's social media activity data to the generation AI and cause the generation AI to select related video URLs.

[0070] The analysis unit can estimate the user's emotion and adjust the audio or subtitle analysis method based on the estimated user's emotion. The analysis unit can estimate the user's emotion using, for example, facial expression recognition technology. For example, the analysis unit can analyze the user's facial expression captured by a camera and calculate an emotion score. The analysis unit can also estimate the user's emotion using voice analysis technology. For example, the analysis unit can analyze the tone and speed of the user's voice and calculate an emotion score. Furthermore, the analysis unit can estimate the user's emotion using text analysis technology. For example, the analysis unit can analyze text data entered by the user and calculate an emotion score. Next, the analysis unit adjusts the audio or subtitle analysis method based on the estimated user's emotion. For example, the analysis unit can perform a detailed analysis if the user is relaxed. The analysis unit can also perform a simplified analysis if the user is in a hurry. Furthermore, the analysis unit can perform a visually stimulating analysis if the user is excited. This allows for more appropriate analysis by adjusting the analysis method according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit may input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0071] When analyzing audio or subtitles, the analysis unit can adjust the level of detail of the analysis based on the importance of the video. The analysis unit, for example, analyzes the number of views and user ratings to evaluate the importance of the video. For example, the analysis unit determines that a video with a high number of views is an important video and performs a detailed analysis. The analysis unit can also determine that a video with a high user rating is an important video and perform a detailed analysis. Furthermore, the analysis unit can determine that a video related to a specific event is an important video and perform a detailed analysis. Next, the analysis unit adjusts the level of detail of the analysis based on the importance of the video. For example, the analysis unit performs a detailed analysis for an important video. The analysis unit can also perform a standard analysis for a general video. Furthermore, the analysis unit can perform a simplified analysis for a video with low importance. In this way, adjusting the level of detail of the analysis based on the importance of the video enables efficient analysis. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input video importance data to a generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0072] When analyzing audio and subtitles, the analysis unit can apply different analysis algorithms depending on the category of the video. For example, the analysis unit analyzes video metadata to identify the category of the video. For example, the analysis unit analyzes the title and description of the video to identify the category. The analysis unit can also analyze the content of the video to identify the category. Next, the analysis unit applies different analysis algorithms depending on the category of the video. For example, the analysis unit applies a terminology analysis algorithm to educational videos. The analysis unit can also apply a sentiment analysis algorithm to entertainment videos. Furthermore, the analysis unit can apply a keyword extraction algorithm to business videos. In this way, by applying an analysis algorithm depending on the video category, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input video category data to the generation AI and cause the generation AI to apply the analysis algorithm.

[0073] The analysis unit can estimate the user's emotion and adjust the display method of the analysis results based on the estimated user's emotion. The analysis unit can estimate the user's emotion using, for example, facial expression recognition technology. For example, the analysis unit can analyze the user's facial expression captured by a camera and calculate an emotion score. The analysis unit can also estimate the user's emotion using voice analysis technology. For example, the analysis unit can analyze the tone and speed of the user's voice and calculate an emotion score. Furthermore, the analysis unit can estimate the user's emotion using text analysis technology. For example, the analysis unit can analyze text data entered by the user and calculate an emotion score. Next, the analysis unit adjusts the display method of the analysis results based on the estimated user's emotion. For example, the analysis unit can provide a simple, highly visible display method when the user is nervous. Furthermore, the analysis unit can provide a display method including detailed information when the user is relaxed. Furthermore, the analysis unit can provide a display method that focuses on the main points when the user is in a hurry. This allows the display method of the analysis results to be adjusted according to the user's emotion, resulting in a more appropriate display. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit may input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0074] When analyzing audio and subtitles, the analysis unit can determine analysis priorities based on the time the video was submitted. The analysis unit, for example, collects and analyzes the time the video was submitted. For example, the analysis unit records the submission date and time of the video and sets priorities based on the time of submission. The analysis unit can also prioritize analysis of videos within a period specified by the user. Furthermore, the analysis unit can also prioritize analysis of videos related to a specific event. Next, the analysis unit determines analysis priorities based on the time the video was submitted. For example, the analysis unit prioritizes analysis of the most recent video. The analysis unit can also prioritize analysis of videos within a period specified by the user. Furthermore, the analysis unit can also prioritize analysis of videos related to a specific event. In this way, determining analysis priorities based on the time the video was submitted enables efficient analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input video submission date data to a generation AI and have the generation AI determine the analysis priorities.

[0075] When analyzing audio and subtitles, the analysis unit can adjust the order of analysis based on the relevance of the videos. For example, the analysis unit analyzes content similarity and viewing history to evaluate the relevance of the videos. For example, the analysis unit prioritizes analyzing videos related to topics in which the user is interested. The analysis unit can also prioritize analyzing videos from channels the user follows. Furthermore, the analysis unit can also prioritize analyzing videos that the user has given high ratings. Next, the analysis unit adjusts the order of analysis based on the relevance of the videos. For example, the analysis unit prioritizes analyzing videos related to topics in which the user is interested. The analysis unit can also prioritize analyzing videos from channels the user follows. Furthermore, the analysis unit can also prioritize analyzing videos that the user has given high ratings. In this way, adjusting the order of analysis based on the relevance of the videos enables efficient analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input video relevance data to a generation AI and cause the generation AI to adjust the order of analysis.

[0076] The summarization unit can estimate the user's emotion and adjust the presentation style of the summary based on the estimated user's emotion. The summarization unit can estimate the user's emotion using, for example, facial expression recognition technology. For example, the summarization unit can analyze the user's facial expression captured by a camera and calculate an emotion score. The summarization unit can also estimate the user's emotion using voice analysis technology. For example, the summarization unit can analyze the tone and speed of the user's voice and calculate an emotion score. The summarization unit can also estimate the user's emotion using text analysis technology. For example, the summarization unit can analyze text data entered by the user and calculate an emotion score. Next, the summarization unit adjusts the presentation style of the summary based on the estimated user's emotion. For example, the summarization unit can provide a detailed summary when the user is relaxed. The summarization unit can also provide a concise summary when the user is in a hurry. The summarization unit can also provide a visually stimulating summary when the user is excited. In this way, by adjusting the presentation style of the summary according to the user's emotion, a more appropriate summary can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the summarization unit may be performed using, or without, an AI. For example, the summarization unit may input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0077] 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 analyzes the number of views and user ratings to evaluate the importance of the video. For example, the summarization unit determines that a video with a high number of views is an important video and provides a detailed summary. The summarization unit can also determine that a video with a high user rating is an important video and provide a detailed summary. Furthermore, the summarization unit can determine that a video related to a specific event is an important video and provide a detailed summary. Next, the summarization unit adjusts the level of detail of the summary based on the importance of the video. For example, the summarization unit provides a detailed summary for an important video. The summarization unit can also provide a standard summary for a general video. Furthermore, the summarization unit can provide a simplified summary for a video with low importance. In this way, adjusting the level of detail of the summary based on the importance of the video enables efficient summarization. Some or all of the above-mentioned processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input video importance data to the generation AI and cause the generation AI to adjust the level of detail of the summary.

[0078] When generating a summary, the summarization unit can apply different summarization algorithms depending on the category of the video. For example, the summarization unit analyzes video metadata to identify the category of the video. For example, the summarization unit analyzes the title and description of the video to identify the category. The summarization unit can also analyze the content of the video to identify the category. Next, the summarization unit applies different summarization algorithms depending on the category of the video. For example, the summarization unit applies a summarization algorithm that includes technical terms to educational videos. The summarization unit can also apply a summarization algorithm that reflects emotions to entertainment videos. Furthermore, the summarization unit can apply a summarization algorithm that emphasizes keywords to business videos. In this way, applying a summarization algorithm depending on the category of the video improves the accuracy of the summary. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input video category data to the generation AI and cause the generation AI to apply the summarization algorithm.

[0079] The summarization unit can estimate the user's emotion and adjust the length of the summary based on the estimated user's emotion. The summarization unit can estimate the user's emotion using, for example, facial expression recognition technology. For example, the summarization unit can analyze the user's facial expression captured with a camera and calculate an emotion score. The summarization unit can also estimate the user's emotion using voice analysis technology. For example, the summarization unit can analyze the tone and speed of the user's voice and calculate an emotion score. Furthermore, the summarization unit can estimate the user's emotion using text analysis technology. For example, the summarization unit can analyze text data entered by the user and calculate an emotion score. Next, the summarization unit adjusts the length of the summary based on the estimated user's emotion. For example, the summarization unit can provide a short summary if the user is in a hurry. The summarization unit can also provide a longer summary if the user is relaxed. Furthermore, the summarization unit can provide a visually stimulating summary if the user is excited. This allows the length of the summary to be adjusted according to the user's emotion, thereby providing a more appropriate summary. Emotion estimation is achieved using, for example, an emotion estimation function using an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the summarization unit may be performed using AI, or may be performed without using AI. For example, the summarization unit may input user facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0080] When generating summaries, the summarization unit can determine the priority of summaries based on the time of video submission. The summarization unit, for example, collects and analyzes the time of video submission. For example, the summarization unit records the submission date and time of videos and sets the priority based on the time of submission. The summarization unit can also prioritize summarizing videos within a period specified by a user. Furthermore, the summarization unit can also prioritize summarizing videos related to a specific event. Next, the summarization unit determines the priority of summaries based on the time of video submission. For example, the summarization unit prioritizes summarizing the most recent videos. The summarization unit can also prioritize summarizing videos within a period specified by a user. Furthermore, the summarization unit can also prioritize summarizing videos related to a specific event. In this way, by determining the priority of summaries based on the time of video submission, efficient summarization can be achieved. Some or all of the above-described processing in the summarization unit may be performed using, for example, AI, or may be performed without AI. For example, the summarization unit can input video submission date data to a generation AI and have the generation AI determine the priority of summaries.

[0081] When generating summaries, the summarization unit can adjust the order of summaries based on the relevance of the videos. For example, the summarization unit analyzes content similarity and viewing history to evaluate the relevance of the videos. For example, the summarization unit prioritizes summarizing videos related to topics in which the user is interested. The summarization unit can also prioritize summarizing videos from channels the user follows. Furthermore, the summarization unit can also prioritize summarizing videos that the user has given a high rating. Next, the summarization unit adjusts the order of summaries based on the relevance of the videos. For example, the summarization unit prioritizes summarizing videos related to topics in which the user is interested. The summarization unit can also prioritize summarizing videos from channels the user follows. Furthermore, the summarization unit can also prioritize summarizing videos that the user has given a high rating. In this way, adjusting the order of summaries based on the relevance of the videos enables efficient summarization. Some or all of the above-described processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit may input video relevance data to a generation AI and cause the generation AI to adjust the order of summaries.

[0082] The providing unit can estimate the user's emotion and adjust the summary provision method based on the estimated user's emotion. The providing unit can estimate the user's emotion using, for example, facial expression recognition technology. For example, the providing unit can analyze the user's facial expression captured with a camera and calculate an emotion score. The providing unit can also estimate the user's emotion using voice analysis technology. For example, the providing unit can analyze the tone and speed of the user's voice and calculate an emotion score. Furthermore, the providing unit can estimate the user's emotion using text analysis technology. For example, the providing unit can analyze text data entered by the user and calculate an emotion score. Next, the providing unit adjusts the summary provision method based on the estimated user's emotion. For example, the providing unit can provide a detailed summary if the user is relaxed. Furthermore, the providing unit can provide a concise summary if the user is in a hurry. Furthermore, the providing unit can provide a visually stimulating summary if the user is excited. This allows the summary provision method to be adjusted according to the user's emotion, thereby providing a more appropriate summary. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit may be performed using AI, or may be performed without using AI. For example, the providing unit may input the user's facial expression data to the generation AI and cause the generation AI to estimate emotions.

[0083] When providing a summary, the providing unit can select an appropriate delivery method by referring to the user's past viewing history. The providing unit, for example, collects and analyzes the user's past viewing history. For example, the providing unit can provide a summary based on the genre of videos the user has previously viewed. The providing unit can also provide a summary based on the length of videos the user has previously viewed. Furthermore, the providing unit can also provide a summary based on the user's rating of videos the user has previously viewed. In this way, by referring to the past viewing history, the optimal summary delivery method can be provided to the user. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's viewing history data into a generation AI and cause the generation AI to select the optimal delivery method.

[0084] When providing a summary, the providing unit can customize the content provided based on the user's current areas of interest. For example, the providing unit can analyze the user's search history and social media activity to identify the user's current areas of interest. For example, the providing unit can provide a summary based on keywords recently searched by the user. The providing unit can also provide summaries of new videos on channels the user follows. Furthermore, the providing unit can provide summaries related to topics in which the user is currently interested. This allows the user to be provided with the most suitable summary by customizing the content provided based on the user's current areas of interest. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input the user's area of ​​interest data into a generating AI and have the generating AI customize the content provided.

[0085] The providing unit can estimate the user's emotion and adjust the timing of providing the summary based on the estimated user's emotion. The providing unit can estimate the user's emotion using, for example, facial expression recognition technology. For example, the providing unit can analyze the user's facial expression captured by a camera and calculate an emotion score. The providing unit can also estimate the user's emotion using voice analysis technology. For example, the providing unit can analyze the tone and speed of the user's voice and calculate an emotion score. Furthermore, the providing unit can estimate the user's emotion using text analysis technology. For example, the providing unit can analyze text data entered by the user and calculate an emotion score. Next, the providing unit adjusts the timing of providing the summary based on the estimated user's emotion. For example, the providing unit can provide the summary immediately if the user is relaxed. Alternatively, the providing unit can provide the summary later if the user is in a hurry. Furthermore, the providing unit can provide the summary at an appropriate time if the user is excited. In this way, by adjusting the timing of providing the summary according to the user's emotion, the summary can be provided at a more appropriate time. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit may be performed using AI, or may be performed without using AI. For example, the providing unit may input the user's facial expression data to the generation AI and cause the generation AI to estimate emotions.

[0086] The providing unit can select the optimal delivery method by taking into account the user's geographical location information when providing a summary. The providing unit, for example, collects and analyzes the user's geographical location information. For example, the providing unit can identify the user's current location using GPS data. The providing unit can also obtain the user's geographical location information using a location information service. Next, the providing unit selects the optimal delivery method based on the user's geographical location information. For example, if the user is in a specific area, the providing unit can provide a summary related to that area. If the user is traveling, the providing unit can also provide a summary related to the travel destination. Furthermore, if the user is participating in a specific event, the providing unit can also provide a summary related to the event. In this way, the optimal summary delivery method can be provided to the user by taking into account the geographical location information. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's geographical location information data to a generation AI and cause the generation AI to select the optimal delivery method.

[0087] When providing a summary, the providing unit can customize the content to be provided by analyzing the user's social media activity. The providing unit, for example, collects and analyzes the user's social media activity. For example, the providing unit can provide a summary related to content shared by the user on social media. The providing unit can also provide summaries of videos introduced by influencers the user follows. Furthermore, the providing unit can also provide summaries related to topics of groups the user participates in. In this way, by analyzing social media activity, the most suitable summary can be provided to the user. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's social media activity data into a generation AI and cause the generation AI to customize the content to be provided. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, summarization unit, and provision unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and receives input of a video URL from a user. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the audio or subtitles of the video and extracts major topics or keywords. The summarization unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and creates a summary based on the extracted topics and keywords. The provision unit is realized, for example, by the control unit 46A of the smart device 14 and provides the summary to the user. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, summarization unit, and provision unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and receives input of a video URL from a user. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the audio or subtitles of the video and extracts main topics or keywords. The summarization unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and creates a summary based on the extracted topics and keywords. The provision unit is realized, for example, by the control unit 46A of the smart glasses 214 and provides the summary to the user. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, summarization unit, and provision unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314 and receives input of a video URL from a user. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the audio or subtitles of the video and extracts main topics or keywords. The summarization unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and creates a summary based on the extracted topics and keywords. The provision unit is realized, for example, by the control unit 46A of the headset type terminal 314 and provides the summary to the user. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, summarization unit, and provision unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and receives input of a video URL from a user. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the audio or subtitles of the video and extracts main topics or keywords. The summarization unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and creates a summary based on the extracted topics and keywords. The provision unit is realized, for example, by the control unit 46A of the robot 414 and provides the summary to the user.

[0088] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0089] The reception unit can analyze the user's past viewing history and suggest input of related video URLs based on the viewing history. For example, the reception unit can analyze the genre of videos the user has viewed in the past and suggest URLs of videos of the same genre. The reception unit can also analyze the length of videos the user has viewed in the past and suggest URLs of videos of similar length. Furthermore, the reception unit can analyze the genre of videos the user has previously given high ratings to and suggest URLs of videos of the same genre. In this way, by suggesting related video URLs based on the user's viewing history, it is possible to efficiently find videos that are likely to interest the user.

[0090] When analyzing the audio and subtitles of a video, the analysis unit can determine the priority of the analysis based on the number of views and ratings of the video. For example, the analysis unit prioritizes the analysis of videos with a large number of views. The analysis unit can also prioritize the analysis of videos with high user ratings. Furthermore, the analysis unit can also prioritize the analysis of videos related to a specific event. In this way, by determining the priority of the analysis based on the number of views and ratings, important videos can be analyzed efficiently.

[0091] The summarization unit can apply different summarization algorithms depending on the category of the video. For example, the summarization unit can apply a summarization algorithm that includes technical terms to educational videos. The summarization unit can also apply a summarization algorithm that reflects emotions to entertainment videos. Furthermore, the summarization unit can apply a summarization algorithm that emphasizes keywords to business videos. In this way, applying a summarization algorithm depending on the category of the video improves the accuracy of the summary.

[0092] The providing unit can preferentially input highly relevant video URLs based on the user's geographical location information. For example, if the user is in a specific area, the providing unit can prioritize video URLs related to that area. Also, if the user is traveling, the providing unit can prioritize video URLs related to the travel destination. Furthermore, if the user is participating in a specific event, the providing unit can prioritize video URLs related to the event. In this way, highly relevant video URLs can be preferentially input by taking geographical location information into consideration.

[0093] The providing unit can analyze the user's social media activity and input related video URLs. For example, the providing unit can input video URLs related to content shared by the user on social media. The providing unit can also input video URLs introduced by influencers the user follows. Furthermore, the providing unit can input video URLs related to topics in groups the user participates in. In this way, related video URLs can be input by analyzing social media activity.

[0094] The reception unit can estimate the user's emotions and adjust the timing of inputting a video URL based on the estimated user's emotions. For example, if the user is feeling stressed, the reception unit can prompt the user to input a video URL at a time when the user can relax. Also, if the user is concentrating, the reception unit can prompt the user to input a video URL immediately. Furthermore, if the user is tired, the reception unit can prompt the user to input a video URL after a break. In this way, by adjusting the timing of inputting a video URL according to the user's emotions, the video URL can be input at a more appropriate time.

[0095] The analysis unit can estimate the user's emotions and adjust the analysis method of the audio or subtitles based on the estimated user's emotions. For example, the analysis unit can perform a detailed analysis when the user is relaxed. The analysis unit can also perform a simplified analysis when the user is in a hurry. Furthermore, the analysis unit can perform a visually stimulating analysis when the user is excited. This allows for more appropriate analysis by adjusting the analysis method according to the user's emotions.

[0096] The summarization unit can estimate the user's emotion and adjust the summary presentation method based on the estimated user's emotion. For example, the summarization unit can provide a detailed summary when the user is relaxed. The summarization unit can also provide a concise summary when the user is in a hurry. Furthermore, the summarization unit can provide a visually stimulating summary when the user is excited. In this way, by adjusting the summary presentation method according to the user's emotion, a more appropriate summary can be provided.

[0097] The providing unit can estimate the user's emotion and adjust the summary providing method based on the estimated user's emotion. For example, the providing unit can provide a detailed summary when the user is relaxed. The providing unit can also provide a concise summary when the user is in a hurry. Furthermore, the providing unit can provide a visually stimulating summary when the user is excited. In this way, by adjusting the summary providing method according to the user's emotion, a more appropriate summary can be provided.

[0098] The providing unit can estimate the user's emotion and adjust the timing of providing the summary based on the estimated user's emotion. For example, if the user is relaxed, the providing unit can provide the summary immediately. Alternatively, if the user is in a hurry, the providing unit can provide the summary later. Furthermore, if the user is excited, the providing unit can provide the summary at an appropriate timing. In this way, by adjusting the timing of providing the summary according to the user's emotion, the summary can be provided at a more appropriate timing.

[0099] The processing flow of the second embodiment will be briefly explained below.

[0100] Step 1: The reception unit receives input of a video URL from the user. The user can input, for example, a YouTube video URL. The reception unit passes the input video URL to the analysis unit. Step 2: The analysis unit analyzes the video's audio or subtitles and extracts key topics or keywords. For example, the analysis unit uses speech recognition technology to convert the video's audio into text and compare it with the subtitle data. The analysis unit uses generative AI to understand the content of the video and extract key topics and keywords. Step 3: The summarization unit creates a summary based on the topics and keywords extracted by the analysis unit. The summarization unit uses a generation AI to extract key topics and keywords from the text data and create a summary based on them. For example, the generation AI uses a text generation AI (e.g., LLM) to concisely summarize the content of the video. Step 4: The providing unit provides the summary created by the summarizing unit to the user. The providing unit may provide the summary to the user in text format, for example. The providing unit may also use a generation AI to translate the summary into Japanese. For example, for an English video, the providing unit may have a translation function to create a summary in Japanese.

[0101] 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.

[0102] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0103] 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.

[0104] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0105] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0106] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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).

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0119] 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.

[0120] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0135] 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.

[0136] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0137] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0138] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0152] 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.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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).

[0158] 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 indicated, and when they approach the ideal, a state of pleasure is indicated. 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 indicated, and when they approach the ideal, a state of pleasure is indicated. 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.

[0159] 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."

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] [Explanation of symbols]

[0173] 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 reception unit that receives an input of a video URL from a user; an analysis unit that analyzes the audio or subtitles of the video received by the reception unit and extracts main topics or keywords; a summarization unit that creates a summary based on the topics or keywords extracted by the analysis unit; a providing unit that provides the summary created by the summarizing unit to a user. A system characterized by:

2. The analysis unit Converts video audio into text and matches it with subtitle data 2. The system of claim 1.

3. The summary section Extracting key topics and keywords from text data and creating summaries based on them 2. The system of claim 1.

4. The providing unit Provides a summary to the user in text format 2. The system of claim 1.

5. The summary section Includes a translation function that can be used to create summaries in Japanese for English videos 2. The system of claim 1.

6. The reception unit By estimating the user's emotions, the timing of inputting the video URL is adjusted based on the estimated user emotions.

2. The system of claim 1.

7. The reception unit Analyze the user's past video viewing history and select the appropriate method for entering the video URL.

2. The system of claim 1.

8. The reception unit Filtering video URLs based on the user's current interests 2. The system of claim 1.

Images