System

Abstract

To provide a system that efficiently grasps the content of meeting videos and extracts key points.SOLUTION: A system according to the embodiment includes a video analysis unit, a key point extraction unit, a summary generation unit, and a clip generation unit. The video analysis unit analyzes meeting videos. The key point extraction unit extracts important topics or key points of discussions based on data converted into text by the video analysis unit. The summary generation unit generates a summary based on the information extracted by the key point extraction unit. The clip generation unit generates video clips of important portions based on the summary generated by the summary generation unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult to efficiently grasp the content of a meeting video and extract the key points.

[0005] The system according to the embodiment aims to efficiently grasp the contents of a meeting video and extract the main points. [Means for solving the problem]

[0006] The system according to the embodiment includes a video analysis unit, a main point extraction unit, a summary generation unit, and a clip generation unit. The video analysis unit analyzes meeting videos. The main point extraction unit extracts important topics or main points of discussions based on data converted into text by the video analysis unit. The summary generation unit generates a summary based on the information extracted by the main point extraction unit. The clip generation unit generates a video clip of important parts based on the summary generated by the summary generation unit. Effect of the Invention

[0007] The system according to the embodiment can efficiently grasp the contents of a meeting video and extract the main points. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The meeting video analysis system according to the embodiment of the present invention is a system that automatically analyzes meeting videos and accurately extracts important topics and key points of discussions. The system uses a generation AI to understand the content of the video and extract important topics and key points of discussions. For example, the system analyzes the speaker's voice and the content of the slides to identify the main points of the discussion. Then, a summary is instantly created based on the extracted information. The generation AI organizes the extracted topics and key points and generates a concise summary. This allows users to quickly access the information they need without watching long videos. In addition, the system not only provides summaries, but also automatically generates video clips of important parts. For example, it cuts out parts of specific discussions or presentations so that users can easily play them. This system not only saves time and effort, but also facilitates team communication and information sharing. For example, by quickly sharing the key points of a meeting, all members have the same information and can work efficiently. This allows the meeting video analysis system to quickly access the information they need without users having to watch long videos.

[0029] The meeting video analysis system according to the embodiment includes a video analysis unit, a main point extraction unit, a summary generation unit, and a clip generation unit. The video analysis unit uses a generation AI to understand the contents of the meeting video and converts the voice and slide contents into text. For example, the video analysis unit converts the speaker's voice into text data using voice recognition technology. The video analysis unit can also convert the contents of the slides into text data using OCR technology. For example, the video analysis unit analyzes the speaker's voice using highly accurate voice recognition technology and converts it into text data. The OCR technology recognizes the contents of the slides with high accuracy and converts them into text data. The main point extraction unit uses a generation AI to extract important topics and main points of discussion from the text data. For example, the main point extraction unit uses natural language processing technology to extract frequently occurring keywords and important phrases from the text data. The main point extraction unit can also analyze the speaker's emphasis points and the excitement of the discussion to identify important information. For example, the main point extraction unit uses morphological analysis to analyze the text data and extract important keywords. The speaker's emphasis points are identified using grammatical analysis. Using semantic analysis, the discussion is analyzed to extract important information. The summary generation unit uses a generation AI to organize the extracted topics and main points and generate a concise summary. For example, the summary generation unit uses a text generation AI (e.g., LLM) to generate a summary based on the extracted information. The summary generation unit can also use a multimodal generation AI to generate a summary that combines text data and image data. For example, the summary generation unit uses a text generation AI to concisely summarize the extracted information. The multimodal generation AI is used to generate a summary that combines text data and image data. The clip generation unit uses a generation AI to cut out specific parts of a discussion or presentation so that the user can easily play it back. For example, the clip generation unit analyzes the timing of the start and end of a discussion and cuts out important parts. The clip generation unit can also analyze the timing of slide switching and cut out important parts of a presentation. For example, the clip generation unit analyzes the timing of the start and end of a discussion and cuts out important parts.The timing of slide changes is analyzed and important parts of the presentation are cut out. This allows the meeting video analysis system according to the embodiment to efficiently analyze meeting videos, extract key points, generate summaries, and generate clips.

[0030] The video analysis unit uses generative AI to understand the contents of the meeting video and convert the audio and slide contents into text. Specifically, the video analysis unit uses highly accurate voice recognition technology to convert the speaker's voice into text data in real time. This voice recognition technology has noise removal and speaker separation functions, and can accurately convert the voice into text even when multiple speakers are speaking at the same time. In addition, the video analysis unit uses OCR technology to recognize the contents of slides with high accuracy and convert them into text data. OCR technology does not depend on the font or layout of the slides, and can accurately recognize handwritten characters and diagrams. Furthermore, the video analysis unit can integrate the contents of the audio and slides using generative AI and analyze the relationship between the remarks and the slides. For example, if a speaker is explaining a specific slide, linking the contents of the slide and the remarks makes it easier to search and refer to them later. This allows the video analysis unit to convert the contents of the meeting video into text in detail and accurately, providing a basis for subsequent analysis and summary generation.

[0031] The main point extraction unit uses generative AI to extract important topics and key points of discussions from the text data. Specifically, the main point extraction unit uses natural language processing technology to extract frequently occurring keywords and important phrases from the text data. For example, the main point extraction unit uses morphological analysis to break down the text data into small pieces and analyze the frequency of occurrence and co-occurrence of each word to identify important keywords. In addition, grammatical analysis can be used to identify points emphasized by speakers and important discussion flows. Furthermore, semantic analysis is used to extract the excitement of discussions and important information. For example, the speaker's emotions and intentions can be analyzed to identify particularly important parts of a discussion. The main point extraction unit combines these technologies to efficiently extract important information from text data and provide a foundation for subsequent summary and clip generation. This allows the main point extraction unit to quickly and accurately grasp the content of the meeting and extract important information.

[0032] The summary generation unit uses a generation AI to organize the extracted topics and main points and generate a concise summary. Specifically, the summary generation unit uses a text generation AI (e.g., LLM) to generate a summary based on the extracted information. The text generation AI has learned a large amount of text data and has the ability to generate natural sentences. For example, based on extracted keywords and phrases, it can generate a summary that concisely summarizes the main points of the meeting. The summary generation unit can also use a multimodal generation AI to generate a summary that combines text data and image data. For example, it combines slide images and remarks to generate a summary that is visually easy to understand. In this way, the summary generation unit summarizes the contents of the meeting concisely and clearly, allowing the user to quickly grasp important information. In addition, the summary generation unit can adjust the level of detail and format of the summary according to the user's needs. For example, if you want to grasp the overall main points in a short time, you can provide a concise summary, and if detailed information is required, you can provide a more detailed summary. In this way, the summary generation unit can respond to the diverse needs of users and provide information efficiently.

[0033] The clip generator uses generation AI to cut out parts of a particular discussion or presentation, allowing users to easily play them back. Specifically, the clip generator analyzes the timing of the start and end of a discussion and cuts out important parts. For example, it can accurately identify the timing when a speaker starts talking about a particular topic and the timing when the discussion ends, and cut out those parts as clips. The clip generator can also analyze the timing of slide changes and cut out important parts of a presentation. For example, it detects the timing of slide changes and identifies important parts of a presentation based on the remarks made before and after. Furthermore, the clip generator can generate clips customized according to the user's specifications. For example, it can generate clips that cut out only parts related to specific keywords or topics. This allows the clip generator to quickly play back the information the user needs, and efficiently grasp the contents of the meeting. Furthermore, the clip generator can tag the generated clips, making them easier to search and classify. This allows the user to quickly find and play the clips they need.

[0034] The video analysis unit can use the generation AI to understand the content of the video and convert the voice or the content of the slide into text. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI. The video analysis unit can convert the speaker's voice into text data using, for example, a voice recognition technology. For example, the video analysis unit can analyze the speaker's voice with high accuracy using voice recognition technology and convert it into text data. The video analysis unit can also convert the content of the slide into text data using OCR technology. For example, the video analysis unit can recognize the content of the slide with high accuracy using OCR technology and convert it into text data. Thereby, the content of the video can be accurately converted into text by using the generation AI. A part or all of the above-mentioned processing in the video analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the video analysis unit can convert the speaker's voice into text data using voice recognition technology, input the text data to the generation AI, and the generation AI can analyze the text data and extract the main points.

[0035] The gist extraction unit can extract important topics or key points of discussion from the text data using natural language processing technology. Natural language processing technology is, for example, morphological analysis, grammatical analysis, semantic analysis, etc. The gist extraction unit, for example, uses morphological analysis to analyze text data and extract important keywords. For example, the gist extraction unit uses morphological analysis to analyze text data and extract frequently occurring keywords. The gist extraction unit can also identify the speaker's emphasis using grammatical analysis. For example, the gist extraction unit uses grammatical analysis to identify the speaker's emphasis. Furthermore, the gist extraction unit can also analyze the excitement of the discussion using semantic analysis and extract important information. For example, the gist extraction unit uses semantic analysis to analyze the excitement of the discussion and extract important information. As a result, important information can be accurately extracted by using natural language processing technology. A part or all of the above-mentioned processing in the gist extraction unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the key point extraction unit can input text data into the generation AI, which can then analyze the text data to extract important topics or key points of discussion.

[0036] The summary generation unit can organize the extracted topics or main points and generate a concise summary. The summary generation unit generates a summary based on the extracted information, for example, using a text generation AI (for example, LLM). For example, the summary generation unit uses a text generation AI to concisely summarize the extracted information. The summary generation unit can also generate a summary that combines text data and image data using a multimodal generation AI. For example, the summary generation unit uses a multimodal generation AI to generate a summary that combines text data and image data. This allows a concise summary to be generated based on the extracted information. Some or all of the above-mentioned processing in the summary generation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the summary generation unit can input the extracted information to the generation AI, which then organizes the information to generate a summary.

[0037] The clip generation unit can cut out a part of a particular discussion or presentation so that the user can easily play it back. The clip generation unit can, for example, use a generation AI to analyze the timing of the start and end of a discussion and cut out important parts. For example, the clip generation unit can use a generation AI to analyze the timing of the start and end of a discussion and cut out important parts. The clip generation unit can also analyze the timing of slide switching and cut out important parts of a presentation. For example, the clip generation unit can use a generation AI to analyze the timing of slide switching and cut out important parts of a presentation. This makes it possible to automatically generate video clips of important parts. Some or all of the above-mentioned processing in the clip generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the clip generation unit can use a generation AI to analyze the timing of the start and end of a discussion and cut out important parts.

[0038] The video analysis unit can analyze the facial expression and gestures of the speaker and evaluate the importance of the discussion. The video analysis unit can analyze the facial expression and gestures of the speaker using, for example, a generation AI. For example, the video analysis unit can analyze the facial expression of the speaker using face recognition technology to capture changes in emotions. The video analysis unit can also analyze the gestures of the speaker using motion analysis technology to evaluate the heat of the discussion. For example, the video analysis unit can analyze the facial expression of the speaker using face recognition technology to capture changes in emotions. The gestures of the speaker can be analyzed using motion analysis technology to evaluate the heat of the discussion. In this way, the importance of the discussion can be evaluated by analyzing the facial expression and gestures of the speaker. Part or all of the above-mentioned processing in the video analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the video analysis unit can input the facial expression and gestures of the speaker to the generation AI, which can analyze and evaluate the importance of the discussion.

[0039] The video analysis unit can remove background sounds and noise from the conference and improve the clarity of the voice. The video analysis unit can remove background sounds and noise from the conference, for example, using a generation AI. For example, the video analysis unit can filter background sounds using a noise reduction filter to make the speaker's voice clear. The video analysis unit can also use noise reduction technology to make the voice of the conference clear. For example, the video analysis unit can use noise reduction technology to make the voice of the conference clear. Furthermore, the video analysis unit can also emphasize a specific frequency band to highlight important remarks. For example, the video analysis unit emphasizes a specific frequency band to highlight important remarks. This improves the clarity of the voice by removing the background sounds and noise. Some or all of the above-mentioned processing in the video analysis unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the video analysis unit can input background sounds and noise from the conference into the generation AI, which can analyze the sound to improve the clarity of the voice.

[0040] The video analysis unit can improve the accuracy of the analysis by considering the positions and fields of expertise of the participants in the meeting. The video analysis unit can improve the accuracy of the analysis by considering the positions and fields of expertise of the participants in the meeting, for example, using a generation AI. For example, the video analysis unit evaluates the importance of remarks based on the positions of the participants. The video analysis unit can also evaluate the importance of technical discussions based on the fields of expertise of the participants. For example, the video analysis unit can evaluate the importance of technical discussions based on the fields of expertise of the participants. Furthermore, the video analysis unit can improve the accuracy of the analysis by combining the positions and fields of expertise of the participants. For example, the video analysis unit improves the accuracy of the analysis by combining the positions and fields of expertise of the participants. As a result, the accuracy of the analysis is improved by considering the positions and fields of expertise of the participants. Some or all of the above-mentioned processing in the video analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the video analysis unit can input the positions and fields of expertise of the participants to the generation AI, and the generation AI can analyze and improve the accuracy of the analysis.

[0041] The video analysis unit can adjust the analysis method taking into consideration the location and time of the meeting. The video analysis unit adjusts the analysis method taking into consideration the location and time of the meeting, for example, using a generation AI. For example, the video analysis unit adjusts the filtering of background sound based on the location of the meeting. The video analysis unit can also adjust the timing of the analysis based on the time period. For example, the video analysis unit adjusts the timing of the analysis based on the time period. Furthermore, the video analysis unit can select the optimal analysis method by combining the location of the meeting and the time period. For example, the video analysis unit selects the optimal analysis method by combining the location of the meeting and the time period. In this way, the optimal analysis method can be selected by taking into consideration the location of the meeting and the time period. Some or all of the above-mentioned processing in the video analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the video analysis unit inputs the location of the meeting and the time period into the generation AI, which can analyze and select the optimal analysis method.

[0042] The gist extraction unit can identify important topics by referring to the speaker's past speech history. The gist extraction unit can identify important topics by referring to the speaker's past speech history, for example, using a generation AI. For example, the gist extraction unit can refer to the speaker's past speech history using a database. The gist extraction unit can also refer to the speaker's past speech history using a speech recording method. For example, the gist extraction unit can refer to the speaker's past speech history using a database. Furthermore, the gist extraction unit can analyze the speaker's past speech pattern and predict important topics. For example, the gist extraction unit can analyze the speaker's past speech pattern and predict important topics. As a result, important topics can be identified by referring to the speaker's past speech history. Part or all of the above-mentioned processing in the gist extraction unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the gist extraction unit can input the speaker's past speech history to the generation AI, which can analyze and identify important topics.

[0043] The gist extraction unit can analyze the progress of the discussion in real time and instantly extract important points. The gist extraction unit can analyze the progress of the discussion in real time, for example, using a generation AI. For example, the gist extraction unit can analyze the timing of remarks and instantly extract important points. The gist extraction unit can also analyze the flow of the discussion and predict the timing at which an important topic will appear. For example, the gist extraction unit can analyze the flow of the discussion and predict the timing at which an important topic will appear. Furthermore, the gist extraction unit can also monitor the progress of the discussion in real time and instantly extract important points. For example, the gist extraction unit can monitor the progress of the discussion in real time and instantly extract important points. As a result, by analyzing the progress of the discussion in real time, important points can be instantly extracted. A part or all of the above-mentioned processing in the gist extraction unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the gist extraction unit can input the progress of the discussion to the generation AI, which can analyze and instantly extract important points.

[0044] The main point extraction unit can improve the accuracy of extraction by considering the agenda and purpose of the meeting. The main point extraction unit improves the accuracy of extraction by considering the agenda and purpose of the meeting, for example, using a generation AI. For example, the main point extraction unit identifies the agenda of the meeting using a prior agenda. The main point extraction unit can also improve the accuracy of extraction based on the goal of the meeting. For example, the main point extraction unit improves the accuracy of extraction based on the goal of the meeting. Furthermore, the main point extraction unit can combine the agenda and purpose of the meeting to extract the optimal main points. For example, the main point extraction unit combines the agenda and purpose of the meeting to extract the optimal main points. As a result, the accuracy of extraction is improved by considering the agenda and purpose. Some or all of the above-mentioned processing in the main point extraction unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the main point extraction unit can input the agenda and purpose of the meeting to the generation AI, which analyzes the agenda and purpose to improve the accuracy of extraction.

[0045] The main point extraction unit can identify important topics by considering the speech frequency and speech time of the meeting participants. The main point extraction unit can identify important topics by using, for example, a generation AI, by considering the speech frequency and speech time of the meeting participants. For example, the main point extraction unit measures the speech frequency using a speech counting method. The main point extraction unit can also measure the speech time using a time measuring method. For example, the main point extraction unit measures the speech frequency using a speech counting method. Furthermore, the main point extraction unit can combine the speech frequency and the speech time to extract optimal main points. For example, the main point extraction unit combines the speech frequency and the speech time to extract optimal main points. In this way, important topics can be identified by considering the speech frequency and the speech time. Part or all of the above-mentioned processing in the main point extraction unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the main point extraction unit can input the speech frequency and speech time to the generation AI, which can analyze and identify important topics.

[0046] The summary generation unit can adjust the level of detail of the summary based on the importance of the discussion. The summary generation unit adjusts the level of detail of the summary based on the importance of the discussion, for example, using a generation AI. For example, the summary generation unit evaluates the importance of the discussion based on the frequency of remarks. The summary generation unit can also evaluate the importance of the discussion based on the emphasized points. For example, the summary generation unit evaluates the importance of the discussion based on the emphasized points. Furthermore, the summary generation unit can adjust the level of detail of the summary according to the importance of the discussion. For example, the summary generation unit adjusts the level of detail of the summary according to the importance of the discussion. This makes it possible to adjust the level of detail of the summary according to the importance of the discussion. Part or all of the above-mentioned processing in the summary generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the summary generation unit can input the importance of the discussion to the generation AI, which can analyze and adjust the level of detail of the summary.

[0047] The summary generation unit can apply different summarization algorithms depending on the category of the discussion. The summary generation unit applies different summarization algorithms depending on the category of the discussion, for example, using a generation AI. For example, the summary generation unit applies a specialized summarization algorithm to a technical discussion. The summary generation unit can also apply a business-oriented summarization algorithm to a business discussion. For example, the summary generation unit applies a business-oriented summarization algorithm to a business discussion. Furthermore, the summary generation unit can also select an optimal summarization algorithm depending on the category. For example, the summary generation unit selects an optimal summarization algorithm depending on the category. This makes it possible to apply an optimal summarization algorithm depending on the category. A part or all of the above-mentioned processing in the summary generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the summary generation unit can input the category of the discussion to the generation AI, which analyzes the category and applies the optimal summarization algorithm.

[0048] The summary generation unit can determine the priority of summaries based on the progress of the discussion. The summary generation unit determines the priority of summaries based on the progress of the discussion, for example, using a generation AI. For example, the summary generation unit analyzes the timing of remarks and prioritizes summarizing important topics. The summary generation unit can also analyze the flow of the discussion in real time and determine the priority of summaries. For example, the summary generation unit analyzes the flow of the discussion in real time and determine the priority of summaries. Furthermore, the summary generation unit can adjust the priority of summaries according to the progress of the discussion. For example, the summary generation unit adjusts the priority of summaries according to the progress of the discussion. This makes it possible to determine the priority of summaries according to the progress of the discussion. Part or all of the above-mentioned processing in the summary generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the summary generation unit can input the progress of the discussion to the generation AI, which can analyze and determine the priority of summaries.

[0049] The summary generation unit can adjust the order of summaries based on the relevance of the discussion. The summary generation unit adjusts the order of summaries based on the relevance of the discussion, for example, using a generation AI. For example, the summary generation unit analyzes commonalities of topics and prioritizes summarizing topics with high relevance. The summary generation unit can also analyze the continuity of comments and determine the optimal order of summaries. For example, the summary generation unit analyzes the continuity of comments and determines the optimal order of summaries. Furthermore, the summary generation unit can analyze the relevance of the discussion and adjust the order of summaries. For example, the summary generation unit analyzes the relevance of the discussion and adjusts the order of summaries. This makes it possible to adjust the order of summaries according to the relevance of the discussion. A part or all of the above-mentioned processing in the summary generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the summary generation unit can input the relevance of the discussion to the generation AI, which can analyze and adjust the order of summaries.

[0050] The clip generation unit can adjust the length of the clip based on the importance of the discussion. The clip generation unit adjusts the length of the clip based on the importance of the discussion, for example, using a generation AI. For example, the clip generation unit evaluates the importance of the discussion based on the frequency of remarks. The clip generation unit can also evaluate the importance of the discussion based on the emphasized points. For example, the clip generation unit evaluates the importance of the discussion based on the emphasized points. Furthermore, the clip generation unit can adjust the length of the clip according to the importance of the discussion. For example, the clip generation unit adjusts the length of the clip according to the importance of the discussion. This makes it possible to adjust the length of the clip according to the importance of the discussion. A part or all of the above-mentioned processing in the clip generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the clip generation unit can input the importance of the discussion to the generation AI, which analyzes and adjusts the length of the clip.

[0051] The clip generation unit can apply different clip generation algorithms depending on the category of the discussion. The clip generation unit applies different clip generation algorithms depending on the category of the discussion, for example, using a generation AI. For example, the clip generation unit applies a specialized clip generation algorithm to a technical discussion. The clip generation unit can also apply a business-oriented clip generation algorithm to a business discussion. For example, the clip generation unit applies a business-oriented clip generation algorithm to a business discussion. Furthermore, the clip generation unit can also select an optimal clip generation algorithm depending on the category. For example, the clip generation unit selects an optimal clip generation algorithm depending on the category. This makes it possible to apply an optimal clip generation algorithm depending on the category. A part or all of the above-mentioned processing in the clip generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the clip generation unit can input the category of the discussion to the generation AI, which analyzes the category and applies the optimal clip generation algorithm.

[0052] The clip generation unit can determine the priority of the clips based on the progress of the discussion. The clip generation unit, for example, uses a generation AI to determine the priority of the clips based on the progress of the discussion. For example, the clip generation unit analyzes the timing of remarks and prioritizes clipping of important topics. The clip generation unit can also analyze the flow of the discussion in real time and determine the priority of the clips. For example, the clip generation unit analyzes the flow of the discussion in real time and determines the priority of the clips. Furthermore, the clip generation unit can adjust the priority of the clips according to the progress of the discussion. For example, the clip generation unit adjusts the priority of the clips according to the progress of the discussion. This makes it possible to determine the priority of the clips according to the progress of the discussion. A part or all of the above-mentioned processing in the clip generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the clip generation unit inputs the progress of the discussion to the generation AI, which can analyze and determine the priority of the clips.

[0053] The clip generation unit can adjust the order of clips based on the relevance of the discussion. The clip generation unit adjusts the order of clips based on the relevance of the discussion, for example, using a generation AI. For example, the clip generation unit analyzes commonalities between topics and prioritizes clipping of topics with high relevance. The clip generation unit can also analyze the continuity of comments and determine the optimal order of clips. For example, the clip generation unit analyzes the continuity of comments and determines the optimal order of clips. Furthermore, the clip generation unit can analyze the relevance of the discussion and adjust the order of clips. For example, the clip generation unit analyzes the relevance of the discussion and adjusts the order of clips. This makes it possible to adjust the order of clips according to the relevance of the discussion. A part or all of the above-mentioned processing in the clip generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the clip generation unit can input the relevance of the discussion to the generation AI, which then analyzes and adjusts the order of clips.

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

[0055] The meeting video analysis system may further include a real-time translation unit. The real-time translation unit translates the data converted into text by the video analysis unit into multiple languages, allowing users to understand the contents of the meeting in different languages. For example, a meeting held in English may be translated into Japanese and Japanese subtitles may be generated. The real-time translation unit may also directly translate the speaker's voice and output the voice in real time. This facilitates communication between participants who speak different languages.

[0056] The meeting video analysis system may further include an interactive question-answering unit. When a user inputs a question about the meeting content, the interactive question-answering unit generates an answer based on the data converted to text by the video analysis unit. For example, when a user asks, "What is the conclusion of this discussion?", the interactive question-answering unit refers to the summary generated by the summary generation unit and provides an appropriate answer. The interactive question-answering unit may also present video clips related to the user's question. This allows the user to have a deeper understanding of the meeting content.

[0057] The meeting video analysis system can further include a minutes generation unit. The minutes generation unit automatically generates minutes based on the data converted to text by the video analysis unit. For example, it organizes important topics and key points of discussions extracted by the key point extraction unit and compiles them as minutes. The minutes generation unit can also reflect comments and notes added by the user. This eliminates the need to create minutes after a meeting and allows them to be shared quickly.

[0058] The meeting video analysis system can further include a context analysis unit for understanding the context of the discussion. The context analysis unit analyzes information before and after the meeting and related documents to understand the background and purpose of the discussion. For example, it refers to materials distributed before the meeting and minutes of past meetings to grasp the position of the current discussion. The context analysis unit can also refer to related external databases to provide information that complements the content of the discussion. This enables deeper understanding and more effective discussion.

[0059] The meeting video analysis system can further include a visual timeline unit for visualizing the progress of the discussion. The visual timeline unit displays the progress of the meeting in a timeline format, allowing the user to grasp the flow of the discussion at a glance. For example, important topics and key points of the discussion can be marked on the timeline so that the user can easily access them. The visual timeline unit also provides a function for the user to jump to a specific time period and play it back. This makes it easier to grasp the overall picture of the meeting.

[0060] The meeting video analysis system can further include an interaction analysis unit for analyzing interactions between meeting participants. The interaction analysis unit analyzes the frequency of exchanges between speakers and question-and-answer sessions to grasp the dynamics of the meeting. For example, if a particular participant frequently speaks, it evaluates the importance of those comments. The interaction analysis unit can also analyze the relationships between participants and evaluate the influence of the discussion. This makes it possible to visualize the progress of the meeting and the contributions of the participants.

[0061] The process flow of the first embodiment will be briefly described below.

[0062] Step 1: The video analysis unit uses generative AI to understand the contents of the meeting video and convert the audio and slides into text. For example, the video analysis unit uses voice recognition technology to convert the speaker's voice into text data. The video analysis unit can also use OCR technology to convert the contents of slides into text data. Step 2: The main point extraction unit uses generative AI to extract important topics and key points of discussion from the text data. For example, the main point extraction unit uses natural language processing technology to extract frequently occurring keywords and important phrases from the text data. The main point extraction unit can also analyze the speaker's emphasis and the excitement of the discussion to identify important information. Step 3: The summary generator uses a generation AI to organize the extracted topics and key points and generate a concise summary. For example, the summary generator may use a text generation AI (e.g., LLM) to generate a summary based on the extracted information. The summary generator may also use a multimodal generation AI to generate a summary that combines text data and image data. Step 4: The clip generator uses AI to cut out specific parts of a discussion or presentation, making it easy for users to play. For example, the clip generator can analyze the timing of the start and end of a discussion and cut out important parts. The clip generator can also analyze the timing of slide changes and cut out important parts of a presentation.

[0063] (Example 2) The meeting video analysis system according to the embodiment of the present invention is a system that automatically analyzes meeting videos and accurately extracts important topics and key points of discussions. The system uses a generation AI to understand the content of the video and extract important topics and key points of discussions. For example, the system analyzes the speaker's voice and the content of the slides to identify the main points of the discussion. Then, a summary is instantly created based on the extracted information. The generation AI organizes the extracted topics and key points and generates a concise summary. This allows users to quickly access the information they need without watching long videos. In addition, the system not only provides summaries, but also automatically generates video clips of important parts. For example, it cuts out parts of specific discussions or presentations so that users can easily play them. This system not only saves time and effort, but also facilitates team communication and information sharing. For example, by quickly sharing the key points of a meeting, all members have the same information and can work efficiently. This allows the meeting video analysis system to quickly access the information they need without users having to watch long videos.

[0064] The meeting video analysis system according to the embodiment includes a video analysis unit, a main point extraction unit, a summary generation unit, and a clip generation unit. The video analysis unit uses a generation AI to understand the contents of the meeting video and converts the voice and slide contents into text. For example, the video analysis unit converts the speaker's voice into text data using voice recognition technology. The video analysis unit can also convert the contents of the slides into text data using OCR technology. For example, the video analysis unit analyzes the speaker's voice using highly accurate voice recognition technology and converts it into text data. The OCR technology recognizes the contents of the slides with high accuracy and converts them into text data. The main point extraction unit uses a generation AI to extract important topics and main points of discussion from the text data. For example, the main point extraction unit uses natural language processing technology to extract frequently occurring keywords and important phrases from the text data. The main point extraction unit can also analyze the speaker's emphasis points and the excitement of the discussion to identify important information. For example, the main point extraction unit uses morphological analysis to analyze the text data and extract important keywords. The speaker's emphasis points are identified using grammatical analysis. Using semantic analysis, the discussion is analyzed to extract important information. The summary generation unit uses a generation AI to organize the extracted topics and main points and generate a concise summary. For example, the summary generation unit uses a text generation AI (e.g., LLM) to generate a summary based on the extracted information. The summary generation unit can also use a multimodal generation AI to generate a summary that combines text data and image data. For example, the summary generation unit uses a text generation AI to concisely summarize the extracted information. The multimodal generation AI is used to generate a summary that combines text data and image data. The clip generation unit uses a generation AI to cut out specific parts of a discussion or presentation so that the user can easily play it back. For example, the clip generation unit analyzes the timing of the start and end of a discussion and cuts out important parts. The clip generation unit can also analyze the timing of slide switching and cut out important parts of a presentation. For example, the clip generation unit analyzes the timing of the start and end of a discussion and cuts out important parts.The timing of slide changes is analyzed and important parts of the presentation are cut out. This allows the meeting video analysis system according to the embodiment to efficiently analyze meeting videos, extract key points, generate summaries, and generate clips.

[0065] The video analysis unit uses generative AI to understand the contents of the meeting video and convert the audio and slide contents into text. Specifically, the video analysis unit uses highly accurate voice recognition technology to convert the speaker's voice into text data in real time. This voice recognition technology has noise removal and speaker separation functions, and can accurately convert the voice into text even when multiple speakers are speaking at the same time. In addition, the video analysis unit uses OCR technology to recognize the contents of slides with high accuracy and convert them into text data. OCR technology does not depend on the font or layout of the slides, and can accurately recognize handwritten characters and diagrams. Furthermore, the video analysis unit can integrate the contents of the audio and slides using generative AI and analyze the relationship between the remarks and the slides. For example, if a speaker is explaining a specific slide, linking the contents of the slide and the remarks makes it easier to search and refer to them later. This allows the video analysis unit to convert the contents of the meeting video into text in detail and accurately, providing a basis for subsequent analysis and summary generation.

[0066] The main point extraction unit uses generative AI to extract important topics and key points of discussions from the text data. Specifically, the main point extraction unit uses natural language processing technology to extract frequently occurring keywords and important phrases from the text data. For example, the main point extraction unit uses morphological analysis to break down the text data into small pieces and analyze the frequency of occurrence and co-occurrence of each word to identify important keywords. In addition, grammatical analysis can be used to identify points emphasized by speakers and important discussion flows. Furthermore, semantic analysis is used to extract the excitement of discussions and important information. For example, the speaker's emotions and intentions can be analyzed to identify particularly important parts of a discussion. The main point extraction unit combines these technologies to efficiently extract important information from text data and provide a foundation for subsequent summary and clip generation. This allows the main point extraction unit to quickly and accurately grasp the content of the meeting and extract important information.

[0067] The summary generation unit uses a generation AI to organize the extracted topics and main points and generate a concise summary. Specifically, the summary generation unit uses a text generation AI (e.g., LLM) to generate a summary based on the extracted information. The text generation AI has learned a large amount of text data and has the ability to generate natural sentences. For example, based on extracted keywords and phrases, it can generate a summary that concisely summarizes the main points of the meeting. The summary generation unit can also use a multimodal generation AI to generate a summary that combines text data and image data. For example, it combines slide images and remarks to generate a summary that is visually easy to understand. In this way, the summary generation unit summarizes the contents of the meeting concisely and clearly, allowing the user to quickly grasp important information. In addition, the summary generation unit can adjust the level of detail and format of the summary according to the user's needs. For example, if you want to grasp the overall main points in a short time, you can provide a concise summary, and if detailed information is required, you can provide a more detailed summary. In this way, the summary generation unit can respond to the diverse needs of users and provide information efficiently.

[0068] The clip generator uses generation AI to cut out parts of a particular discussion or presentation, allowing users to easily play them back. Specifically, the clip generator analyzes the timing of the start and end of a discussion and cuts out important parts. For example, it can accurately identify the timing when a speaker starts talking about a particular topic and the timing when the discussion ends, and cut out those parts as clips. The clip generator can also analyze the timing of slide changes and cut out important parts of a presentation. For example, it detects the timing of slide changes and identifies important parts of a presentation based on the remarks made before and after. Furthermore, the clip generator can generate clips customized according to the user's specifications. For example, it can generate clips that cut out only parts related to specific keywords or topics. This allows the clip generator to quickly play back the information the user needs, and efficiently grasp the contents of the meeting. Furthermore, the clip generator can tag the generated clips, making them easier to search and classify. This allows the user to quickly find and play the clips they need.

[0069] The video analysis unit can use the generation AI to understand the content of the video and convert the voice or the content of the slide into text. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI. The video analysis unit can convert the speaker's voice into text data using, for example, a voice recognition technology. For example, the video analysis unit can analyze the speaker's voice with high accuracy using voice recognition technology and convert it into text data. The video analysis unit can also convert the content of the slide into text data using OCR technology. For example, the video analysis unit can recognize the content of the slide with high accuracy using OCR technology and convert it into text data. Thereby, the content of the video can be accurately converted into text by using the generation AI. A part or all of the above-mentioned processing in the video analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the video analysis unit can convert the speaker's voice into text data using voice recognition technology, input the text data to the generation AI, and the generation AI can analyze the text data and extract the main points.

[0070] The gist extraction unit can extract important topics or key points of discussion from the text data using natural language processing technology. Natural language processing technology is, for example, morphological analysis, grammatical analysis, semantic analysis, etc. The gist extraction unit, for example, uses morphological analysis to analyze text data and extract important keywords. For example, the gist extraction unit uses morphological analysis to analyze text data and extract frequently occurring keywords. The gist extraction unit can also identify the speaker's emphasis using grammatical analysis. For example, the gist extraction unit uses grammatical analysis to identify the speaker's emphasis. Furthermore, the gist extraction unit can also analyze the excitement of the discussion using semantic analysis and extract important information. For example, the gist extraction unit uses semantic analysis to analyze the excitement of the discussion and extract important information. As a result, important information can be accurately extracted by using natural language processing technology. A part or all of the above-mentioned processing in the gist extraction unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the key point extraction unit can input text data into the generation AI, which can then analyze the text data to extract important topics or key points of discussion.

[0071] The summary generation unit can organize the extracted topics or main points and generate a concise summary. The summary generation unit generates a summary based on the extracted information, for example, using a text generation AI (for example, LLM). For example, the summary generation unit uses a text generation AI to concisely summarize the extracted information. The summary generation unit can also generate a summary that combines text data and image data using a multimodal generation AI. For example, the summary generation unit uses a multimodal generation AI to generate a summary that combines text data and image data. This allows a concise summary to be generated based on the extracted information. Some or all of the above-mentioned processing in the summary generation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the summary generation unit can input the extracted information to the generation AI, which then organizes the information to generate a summary.

[0072] The clip generation unit can cut out a part of a particular discussion or presentation so that the user can easily play it back. The clip generation unit can, for example, use a generation AI to analyze the timing of the start and end of a discussion and cut out important parts. For example, the clip generation unit can use a generation AI to analyze the timing of the start and end of a discussion and cut out important parts. The clip generation unit can also analyze the timing of slide switching and cut out important parts of a presentation. For example, the clip generation unit can use a generation AI to analyze the timing of slide switching and cut out important parts of a presentation. This makes it possible to automatically generate video clips of important parts. Some or all of the above-mentioned processing in the clip generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the clip generation unit can use a generation AI to analyze the timing of the start and end of a discussion and cut out important parts.

[0073] The video analysis unit can estimate the user's emotions and adjust the timing of the video analysis based on the estimated user's emotions. The video analysis unit estimates the user's emotions using an emotion estimation function, for example, using an emotion engine or a generation AI. For example, the video analysis unit uses a facial expression recognition technology to analyze the user's facial expression and estimate the emotions. The video analysis unit can also analyze the user's voice and estimate the emotions using an audio tone analysis technology. For example, the video analysis unit uses an audio tone analysis technology to analyze the user's voice and estimate the emotions. Furthermore, the video analysis unit adjusts the timing of the video analysis based on the user's emotions. For example, when the user is concentrating, the video analysis is performed in real time and the results are provided immediately. Also, when the user is tired, the video analysis can be paused and resumed after the user is refreshed. For example, when the user is tired, the video analysis unit pauses the video analysis and resumes it after the user is refreshed. This makes it possible to adjust the timing of the video analysis according to the user's emotions. Some or all of the above-mentioned processing in the video analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the video analysis unit can input the user's emotions into the generation AI, which can then analyze the emotions and adjust the timing of the video analysis.

[0074] The video analysis unit can analyze the facial expression and gestures of the speaker and evaluate the importance of the discussion. The video analysis unit can analyze the facial expression and gestures of the speaker using, for example, a generation AI. For example, the video analysis unit can analyze the facial expression of the speaker using face recognition technology to capture changes in emotions. The video analysis unit can also analyze the gestures of the speaker using motion analysis technology to evaluate the heat of the discussion. For example, the video analysis unit can analyze the facial expression of the speaker using face recognition technology to capture changes in emotions. The gestures of the speaker can be analyzed using motion analysis technology to evaluate the heat of the discussion. In this way, the importance of the discussion can be evaluated by analyzing the facial expression and gestures of the speaker. Part or all of the above-mentioned processing in the video analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the video analysis unit can input the facial expression and gestures of the speaker to the generation AI, which can analyze and evaluate the importance of the discussion.

[0075] The video analysis unit can remove background sounds and noise from the conference and improve the clarity of the voice. The video analysis unit can remove background sounds and noise from the conference, for example, using a generation AI. For example, the video analysis unit can filter background sounds using a noise reduction filter to make the speaker's voice clear. The video analysis unit can also use noise reduction technology to make the voice of the conference clear. For example, the video analysis unit can use noise reduction technology to make the voice of the conference clear. Furthermore, the video analysis unit can also emphasize a specific frequency band to highlight important remarks. For example, the video analysis unit emphasizes a specific frequency band to highlight important remarks. This improves the clarity of the voice by removing the background sounds and noise. Some or all of the above-mentioned processing in the video analysis unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the video analysis unit can input background sounds and noise from the conference into the generation AI, which can analyze the sound to improve the clarity of the voice.

[0076] The video analysis unit can estimate the user's emotions and determine the priority of videos to be analyzed based on the estimated user's emotions. The video analysis unit estimates the user's emotions using an emotion estimation function, for example, using an emotion engine or a generation AI. For example, the video analysis unit analyzes the user's facial expression using a facial expression recognition technology to estimate the emotion. The video analysis unit can also analyze the user's voice using an audio tone analysis technology to estimate the emotion. For example, the video analysis unit analyzes the user's voice using an audio tone analysis technology to estimate the emotion. Furthermore, the video analysis unit determines the priority of videos to be analyzed based on the estimated user's emotions. For example, when the user is excited, videos including important topics are preferentially analyzed. Also, when the user is relaxed, videos covering the overall content can be preferentially analyzed. For example, when the user is relaxed, the video analysis unit preferentially analyzes videos covering the overall content. This makes it possible to determine the priority of videos to be analyzed according to the user's emotions. A part or all of the above-mentioned processing in the video analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the video analysis unit can input a user's emotions into the generation AI, which can then analyze the emotions and determine the priority of the videos.

[0077] The video analysis unit can improve the accuracy of the analysis by considering the positions and fields of expertise of the participants in the meeting. The video analysis unit can improve the accuracy of the analysis by considering the positions and fields of expertise of the participants in the meeting, for example, using a generation AI. For example, the video analysis unit evaluates the importance of remarks based on the positions of the participants. The video analysis unit can also evaluate the importance of technical discussions based on the fields of expertise of the participants. For example, the video analysis unit can evaluate the importance of technical discussions based on the fields of expertise of the participants. Furthermore, the video analysis unit can improve the accuracy of the analysis by combining the positions and fields of expertise of the participants. For example, the video analysis unit improves the accuracy of the analysis by combining the positions and fields of expertise of the participants. As a result, the accuracy of the analysis is improved by considering the positions and fields of expertise of the participants. Some or all of the above-mentioned processing in the video analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the video analysis unit can input the positions and fields of expertise of the participants to the generation AI, and the generation AI can analyze and improve the accuracy of the analysis.

[0078] The video analysis unit can adjust the analysis method taking into consideration the location and time of the meeting. The video analysis unit adjusts the analysis method taking into consideration the location and time of the meeting, for example, using a generation AI. For example, the video analysis unit adjusts the filtering of background sound based on the location of the meeting. The video analysis unit can also adjust the timing of the analysis based on the time period. For example, the video analysis unit adjusts the timing of the analysis based on the time period. Furthermore, the video analysis unit can select the optimal analysis method by combining the location of the meeting and the time period. For example, the video analysis unit selects the optimal analysis method by combining the location of the meeting and the time period. In this way, the optimal analysis method can be selected by taking into consideration the location of the meeting and the time period. Some or all of the above-mentioned processing in the video analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the video analysis unit inputs the location of the meeting and the time period into the generation AI, which can analyze and select the optimal analysis method.

[0079] The main point extraction unit can estimate the user's emotion and determine the priority of the main points to be extracted based on the estimated user's emotion. The main point extraction unit estimates the user's emotion using an emotion estimation function, for example, using an emotion engine or a generation AI. For example, the main point extraction unit can analyze the user's facial expression using a facial expression recognition technology to estimate the emotion. The main point extraction unit can also analyze the user's voice using a voice tone analysis technology to estimate the emotion. For example, the main point extraction unit can analyze the user's voice using a voice tone analysis technology to estimate the emotion. Furthermore, the main point extraction unit determines the priority of the main points to be extracted based on the estimated user's emotion. For example, when the user is excited, important topics are preferentially extracted. Also, when the user is relaxed, overall main points can be extracted in a balanced manner. For example, when the user is relaxed, the main point extraction unit extracts overall main points in a balanced manner. This makes it possible to determine the priority of the main points according to the user's emotion. A part or all of the above-mentioned processing in the main point extraction unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the key point extraction unit can input the user's emotions into the generation AI, which can then analyze the emotions and determine the priority of the key points.

[0080] The gist extraction unit can identify important topics by referring to the speaker's past speech history. The gist extraction unit can identify important topics by referring to the speaker's past speech history, for example, using a generation AI. For example, the gist extraction unit can refer to the speaker's past speech history using a database. The gist extraction unit can also refer to the speaker's past speech history using a speech recording method. For example, the gist extraction unit can refer to the speaker's past speech history using a database. Furthermore, the gist extraction unit can analyze the speaker's past speech pattern and predict important topics. For example, the gist extraction unit can analyze the speaker's past speech pattern and predict important topics. As a result, important topics can be identified by referring to the speaker's past speech history. Part or all of the above-mentioned processing in the gist extraction unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the gist extraction unit can input the speaker's past speech history to the generation AI, which can analyze and identify important topics.

[0081] The gist extraction unit can analyze the progress of the discussion in real time and instantly extract important points. The gist extraction unit can analyze the progress of the discussion in real time, for example, using a generation AI. For example, the gist extraction unit can analyze the timing of remarks and instantly extract important points. The gist extraction unit can also analyze the flow of the discussion and predict the timing at which an important topic will appear. For example, the gist extraction unit can analyze the flow of the discussion and predict the timing at which an important topic will appear. Furthermore, the gist extraction unit can also monitor the progress of the discussion in real time and instantly extract important points. For example, the gist extraction unit can monitor the progress of the discussion in real time and instantly extract important points. As a result, by analyzing the progress of the discussion in real time, important points can be instantly extracted. A part or all of the above-mentioned processing in the gist extraction unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the gist extraction unit can input the progress of the discussion to the generation AI, which can analyze and instantly extract important points.

[0082] The main point extraction unit can estimate the user's emotion and adjust the display method of the extracted main points based on the estimated user's emotion. The main point extraction unit estimates the user's emotion using an emotion estimation function, for example, using an emotion engine or a generation AI. For example, the main point extraction unit analyzes the user's facial expression using a facial expression recognition technology to estimate the emotion. The main point extraction unit can also analyze the user's voice using a voice tone analysis technology to estimate the emotion. For example, the main point extraction unit analyzes the user's voice using a voice tone analysis technology to estimate the emotion. Furthermore, the main point extraction unit adjusts the display method of the extracted main points based on the estimated user's emotion. For example, when the user is nervous, a simple and highly visible display method is provided. Also, when the user is relaxed, a display method including detailed information can be provided. For example, when the user is relaxed, the main point extraction unit provides a display method including detailed information. This makes it possible to adjust the display method of the main points according to the user's emotion. A part or all of the above-mentioned processing in the main point extraction unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the key point extraction unit can input the user's emotions into the generation AI, which can then analyze the emotions and adjust the way the key points are displayed.

[0083] The main point extraction unit can improve the accuracy of extraction by considering the agenda and purpose of the meeting. The main point extraction unit improves the accuracy of extraction by considering the agenda and purpose of the meeting, for example, using a generation AI. For example, the main point extraction unit identifies the agenda of the meeting using a prior agenda. The main point extraction unit can also improve the accuracy of extraction based on the goal of the meeting. For example, the main point extraction unit improves the accuracy of extraction based on the goal of the meeting. Furthermore, the main point extraction unit can combine the agenda and purpose of the meeting to extract the optimal main points. For example, the main point extraction unit combines the agenda and purpose of the meeting to extract the optimal main points. As a result, the accuracy of extraction is improved by considering the agenda and purpose. Some or all of the above-mentioned processing in the main point extraction unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the main point extraction unit can input the agenda and purpose of the meeting to the generation AI, which analyzes the agenda and purpose to improve the accuracy of extraction.

[0084] The main point extraction unit can identify important topics by considering the speech frequency and speech time of the meeting participants. The main point extraction unit can identify important topics by using, for example, a generation AI, by considering the speech frequency and speech time of the meeting participants. For example, the main point extraction unit measures the speech frequency using a speech counting method. The main point extraction unit can also measure the speech time using a time measuring method. For example, the main point extraction unit measures the speech frequency using a speech counting method. Furthermore, the main point extraction unit can combine the speech frequency and the speech time to extract optimal main points. For example, the main point extraction unit combines the speech frequency and the speech time to extract optimal main points. In this way, important topics can be identified by considering the speech frequency and the speech time. Part or all of the above-mentioned processing in the main point extraction unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the main point extraction unit can input the speech frequency and speech time to the generation AI, which can analyze and identify important topics.

[0085] The summary generation unit can estimate the user's emotion and adjust the expression method of the summary based on the estimated user's emotion. The summary generation unit estimates the user's emotion using an emotion estimation function, for example, using an emotion engine or a generation AI. For example, the summary generation unit analyzes the user's facial expression using a facial expression recognition technology to estimate the emotion. The summary generation unit can also analyze the user's voice using a voice tone analysis technology to estimate the emotion. For example, the summary generation unit analyzes the user's voice using a voice tone analysis technology to estimate the emotion. Furthermore, the summary generation unit adjusts the expression method of the summary based on the estimated user's emotion. For example, when the user is nervous, a simple and highly visible summary is provided. Also, when the user is relaxed, a summary including detailed information can be provided. For example, when the user is relaxed, the summary generation unit provides a summary including detailed information. This makes it possible to adjust the expression method of the summary according to the user's emotion. A part or all of the above-mentioned processing in the summary generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the summary generation unit can input the user's emotions into the generation AI, which can then analyze the emotions and adjust the way the summary is expressed.

[0086] The summary generation unit can adjust the level of detail of the summary based on the importance of the discussion. The summary generation unit adjusts the level of detail of the summary based on the importance of the discussion, for example, using a generation AI. For example, the summary generation unit evaluates the importance of the discussion based on the frequency of remarks. The summary generation unit can also evaluate the importance of the discussion based on the emphasized points. For example, the summary generation unit evaluates the importance of the discussion based on the emphasized points. Furthermore, the summary generation unit can adjust the level of detail of the summary according to the importance of the discussion. For example, the summary generation unit adjusts the level of detail of the summary according to the importance of the discussion. This makes it possible to adjust the level of detail of the summary according to the importance of the discussion. Part or all of the above-mentioned processing in the summary generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the summary generation unit can input the importance of the discussion to the generation AI, which can analyze and adjust the level of detail of the summary.

[0087] The summary generation unit can apply different summarization algorithms depending on the category of the discussion. The summary generation unit applies different summarization algorithms depending on the category of the discussion, for example, using a generation AI. For example, the summary generation unit applies a specialized summarization algorithm to a technical discussion. The summary generation unit can also apply a business-oriented summarization algorithm to a business discussion. For example, the summary generation unit applies a business-oriented summarization algorithm to a business discussion. Furthermore, the summary generation unit can also select an optimal summarization algorithm depending on the category. For example, the summary generation unit selects an optimal summarization algorithm depending on the category. This makes it possible to apply an optimal summarization algorithm depending on the category. A part or all of the above-mentioned processing in the summary generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the summary generation unit can input the category of the discussion to the generation AI, which analyzes the category and applies the optimal summarization algorithm.

[0088] The summary generation unit can estimate the user's emotion and adjust the length of the summary based on the estimated user's emotion. The summary generation unit estimates the user's emotion using an emotion estimation function, for example, using an emotion engine or a generation AI. For example, the summary generation unit uses a facial expression recognition technology to analyze the user's facial expression and estimate the emotion. The summary generation unit can also analyze the user's voice using a voice tone analysis technology to estimate the emotion. For example, the summary generation unit uses a voice tone analysis technology to analyze the user's voice and estimate the emotion. Furthermore, the summary generation unit adjusts the length of the summary based on the estimated user's emotion. For example, if the user is in a hurry, a short summary that covers the main points is provided. Also, if the user is relaxed, a longer summary including detailed explanations can be provided. For example, if the user is relaxed, the summary generation unit provides a longer summary including detailed explanations. This allows the length of the summary to be adjusted according to the user's emotion. A part or all of the above-mentioned processing in the summary generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the summary generation unit can input the user's emotions into the generation AI, which can then analyze the emotions and adjust the length of the summary.

[0089] The summary generation unit can determine the priority of summaries based on the progress of the discussion. The summary generation unit determines the priority of summaries based on the progress of the discussion, for example, using a generation AI. For example, the summary generation unit analyzes the timing of remarks and prioritizes summarizing important topics. The summary generation unit can also analyze the flow of the discussion in real time and determine the priority of summaries. For example, the summary generation unit analyzes the flow of the discussion in real time and determine the priority of summaries. Furthermore, the summary generation unit can adjust the priority of summaries according to the progress of the discussion. For example, the summary generation unit adjusts the priority of summaries according to the progress of the discussion. This makes it possible to determine the priority of summaries according to the progress of the discussion. Part or all of the above-mentioned processing in the summary generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the summary generation unit can input the progress of the discussion to the generation AI, which can analyze and determine the priority of summaries.

[0090] The summary generation unit can adjust the order of summaries based on the relevance of the discussion. The summary generation unit adjusts the order of summaries based on the relevance of the discussion, for example, using a generation AI. For example, the summary generation unit analyzes commonalities of topics and prioritizes summarizing topics with high relevance. The summary generation unit can also analyze the continuity of comments and determine the optimal order of summaries. For example, the summary generation unit analyzes the continuity of comments and determines the optimal order of summaries. Furthermore, the summary generation unit can analyze the relevance of the discussion and adjust the order of summaries. For example, the summary generation unit analyzes the relevance of the discussion and adjusts the order of summaries. This makes it possible to adjust the order of summaries according to the relevance of the discussion. A part or all of the above-mentioned processing in the summary generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the summary generation unit can input the relevance of the discussion to the generation AI, which can analyze and adjust the order of summaries.

[0091] The clip generation unit can estimate the user's emotion and adjust the generation method of the clip based on the estimated user's emotion. The clip generation unit estimates the user's emotion using an emotion estimation function, for example, using an emotion engine or a generation AI. For example, the clip generation unit analyzes the user's facial expression using a facial expression recognition technology to estimate the emotion. The clip generation unit can also analyze the user's voice using an audio tone analysis technology to estimate the emotion. For example, the clip generation unit analyzes the user's voice using an audio tone analysis technology to estimate the emotion. Furthermore, the clip generation unit adjusts the generation method of the clip based on the estimated user's emotion. For example, when the user is excited, a clip with a visually stimulating effect is generated. Also, when the user is relaxed, a clip with a calm tone can be generated. For example, when the user is relaxed, the clip generation unit generates a clip with a calm tone. This makes it possible to adjust the generation method of the clip according to the user's emotion. A part or all of the above-mentioned processing in the clip generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the clip generation unit can input the user's emotions into the generation AI, which can then analyze the emotions and adjust the way the clip is generated.

[0092] The clip generation unit can adjust the length of the clip based on the importance of the discussion. The clip generation unit adjusts the length of the clip based on the importance of the discussion, for example, using a generation AI. For example, the clip generation unit evaluates the importance of the discussion based on the frequency of remarks. The clip generation unit can also evaluate the importance of the discussion based on the emphasized points. For example, the clip generation unit evaluates the importance of the discussion based on the emphasized points. Furthermore, the clip generation unit can adjust the length of the clip according to the importance of the discussion. For example, the clip generation unit adjusts the length of the clip according to the importance of the discussion. This makes it possible to adjust the length of the clip according to the importance of the discussion. A part or all of the above-mentioned processing in the clip generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the clip generation unit can input the importance of the discussion to the generation AI, which analyzes and adjusts the length of the clip.

[0093] The clip generation unit can apply different clip generation algorithms depending on the category of the discussion. The clip generation unit applies different clip generation algorithms depending on the category of the discussion, for example, using a generation AI. For example, the clip generation unit applies a specialized clip generation algorithm to a technical discussion. The clip generation unit can also apply a business-oriented clip generation algorithm to a business discussion. For example, the clip generation unit applies a business-oriented clip generation algorithm to a business discussion. Furthermore, the clip generation unit can also select an optimal clip generation algorithm depending on the category. For example, the clip generation unit selects an optimal clip generation algorithm depending on the category. This makes it possible to apply an optimal clip generation algorithm depending on the category. A part or all of the above-mentioned processing in the clip generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the clip generation unit can input the category of the discussion to the generation AI, which analyzes the category and applies the optimal clip generation algorithm.

[0094] The clip generation unit can estimate the user's emotion and adjust the display method of the clip based on the estimated user's emotion. The clip generation unit estimates the user's emotion using an emotion estimation function, for example, using an emotion engine or a generation AI. For example, the clip generation unit uses a facial expression recognition technology to analyze the user's facial expression and estimate the emotion. The clip generation unit can also analyze the user's voice using an audio tone analysis technology to estimate the emotion. For example, the clip generation unit uses an audio tone analysis technology to analyze the user's voice and estimate the emotion. Furthermore, the clip generation unit adjusts the display method of the clip based on the estimated user's emotion. For example, when the user is nervous, a simple and highly visible display method is provided. Also, when the user is relaxed, a display method including detailed information can be provided. For example, when the user is relaxed, the clip generation unit provides a display method including detailed information. This makes it possible to adjust the display method of the clip according to the user's emotion. A part or all of the above-mentioned processing in the clip generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the clip generation unit can input the user's emotions into a generation AI, which can then analyze the emotions and adjust the way the clip is displayed.

[0095] The clip generation unit can determine the priority of the clips based on the progress of the discussion. The clip generation unit, for example, uses a generation AI to determine the priority of the clips based on the progress of the discussion. For example, the clip generation unit analyzes the timing of remarks and prioritizes clipping of important topics. The clip generation unit can also analyze the flow of the discussion in real time and determine the priority of the clips. For example, the clip generation unit analyzes the flow of the discussion in real time and determines the priority of the clips. Furthermore, the clip generation unit can adjust the priority of the clips according to the progress of the discussion. For example, the clip generation unit adjusts the priority of the clips according to the progress of the discussion. This makes it possible to determine the priority of the clips according to the progress of the discussion. A part or all of the above-mentioned processing in the clip generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the clip generation unit inputs the progress of the discussion to the generation AI, which can analyze and determine the priority of the clips.

[0096] The clip generation unit can adjust the order of clips based on the relevance of the discussion. The clip generation unit adjusts the order of clips based on the relevance of the discussion, for example, using a generation AI. For example, the clip generation unit analyzes commonalities between topics and prioritizes clipping of topics with high relevance. The clip generation unit can also analyze the continuity of comments and determine the optimal order of clips. For example, the clip generation unit analyzes the continuity of comments and determines the optimal order of clips. Furthermore, the clip generation unit can analyze the relevance of the discussion and adjust the order of clips. For example, the clip generation unit analyzes the relevance of the discussion and adjusts the order of clips. This makes it possible to adjust the order of clips according to the relevance of the discussion. A part or all of the above-mentioned processing in the clip generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the clip generation unit can input the relevance of the discussion to the generation AI, which then analyzes and adjusts the order of clips.

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

[0098] The meeting video analysis system may further include a real-time translation unit. The real-time translation unit translates the data converted into text by the video analysis unit into multiple languages, allowing users to understand the contents of the meeting in different languages. For example, a meeting held in English may be translated into Japanese and Japanese subtitles may be generated. The real-time translation unit may also directly translate the speaker's voice and output the voice in real time. This facilitates communication between participants who speak different languages.

[0099] The meeting video analysis system may further include an interactive question-answering unit. When a user inputs a question about the meeting content, the interactive question-answering unit generates an answer based on the data converted to text by the video analysis unit. For example, when a user asks, "What is the conclusion of this discussion?", the interactive question-answering unit refers to the summary generated by the summary generation unit and provides an appropriate answer. The interactive question-answering unit may also present video clips related to the user's question. This allows the user to have a deeper understanding of the meeting content.

[0100] The meeting video analysis system may further include an emotion feedback unit. The emotion feedback unit provides a function of feeding back the emotion felt by the user regarding the content of the meeting. For example, when a user inputs emotion such as "excited" or "bored" regarding a particular discussion, the emotion feedback unit collects the information and reflects it in the next meeting analysis. The emotion feedback unit may also adjust the method of generating summaries and clips based on the user's emotion. This makes it possible to provide optimal information according to the user's emotion.

[0101] The meeting video analysis system can further include a minutes generation unit. The minutes generation unit automatically generates minutes based on the data converted to text by the video analysis unit. For example, it organizes important topics and key points of discussions extracted by the key point extraction unit and compiles them as minutes. The minutes generation unit can also reflect comments and notes added by the user. This eliminates the need to create minutes after a meeting and allows them to be shared quickly.

[0102] The meeting video analysis system can further use the emotion estimation function to adjust the progress of the meeting in real time based on the user's emotions. For example, if the system estimates that the user is tired, it can pause the meeting and suggest a break. Also, if the user is excited, it can encourage the user to continue important discussions. This allows for flexible meeting progress according to the user's emotions.

[0103] The meeting video analysis system can further include a context analysis unit for understanding the context of the discussion. The context analysis unit analyzes information before and after the meeting and related documents to understand the background and purpose of the discussion. For example, it refers to materials distributed before the meeting and minutes of past meetings to grasp the position of the current discussion. The context analysis unit can also refer to related external databases to provide information that complements the content of the discussion. This enables deeper understanding and more effective discussion.

[0104] The meeting video analysis system can further use the emotion estimation function to highlight key points of a meeting based on the user's emotions. For example, if the user is excited, important topics and key points of discussion can be highlighted to make them visually prominent. Also, if the user is relaxed, the overall content can be displayed in a balanced manner. This makes it possible to provide optimal information according to the user's emotions.

[0105] The meeting video analysis system can further include a visual timeline unit for visualizing the progress of the discussion. The visual timeline unit displays the progress of the meeting in a timeline format, allowing the user to grasp the flow of the discussion at a glance. For example, important topics and key points of the discussion can be marked on the timeline so that the user can easily access them. The visual timeline unit also provides a function for the user to jump to a specific time period and play it back. This makes it easier to grasp the overall picture of the meeting.

[0106] The meeting video analysis system can further use the emotion estimation function to customize a summary of the meeting based on the user's emotions. For example, if the user is nervous, a simple and highly visible summary can be provided. On the other hand, if the user is relaxed, a summary including detailed information can be provided. In this way, an optimal summary according to the user's emotions can be provided.

[0107] The meeting video analysis system can further include an interaction analysis unit for analyzing interactions between meeting participants. The interaction analysis unit analyzes the frequency of exchanges between speakers and question-and-answer sessions to grasp the dynamics of the meeting. For example, if a particular participant frequently speaks, it evaluates the importance of those comments. The interaction analysis unit can also analyze the relationships between participants and evaluate the influence of the discussion. This makes it possible to visualize the progress of the meeting and the contributions of the participants.

[0108] The process flow of the second embodiment will be briefly described below.

[0109] Step 1: The video analysis unit uses generative AI to understand the contents of the meeting video and convert the audio and slides into text. For example, the video analysis unit uses voice recognition technology to convert the speaker's voice into text data. The video analysis unit can also use OCR technology to convert the contents of slides into text data. Step 2: The main point extraction unit uses generative AI to extract important topics and key points of discussion from the text data. For example, the main point extraction unit uses natural language processing technology to extract frequently occurring keywords and important phrases from the text data. The main point extraction unit can also analyze the speaker's emphasis and the excitement of the discussion to identify important information. Step 3: The summary generator uses a generation AI to organize the extracted topics and key points and generate a concise summary. For example, the summary generator may use a text generation AI (e.g., LLM) to generate a summary based on the extracted information. The summary generator may also use a multimodal generation AI to generate a summary that combines text data and image data. Step 4: The clip generator uses AI to cut out specific parts of a discussion or presentation, making it easy for users to play. For example, the clip generator can analyze the timing of the start and end of a discussion and cut out important parts. The clip generator can also analyze the timing of slide changes and cut out important parts of a presentation.

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

[0111] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0112] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0113] Each of the multiple elements including the video analysis unit, the main point extraction unit, the summary generation unit, and the clip generation unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the video analysis unit is realized by the processor 46 of the smart device 14, and converts the contents of the meeting video into text using voice recognition technology or OCR technology. The main point extraction unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and extracts important topics and the main points of discussions using natural language processing technology. The summary generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a summary based on information extracted using a generation AI. The clip generation unit is realized, for example, by the control unit 46A of the smart device 14, and cuts out a part of a specific discussion or presentation so that the user can easily play it. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

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

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

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

[0117] The 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.

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

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0120] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0121] Fig. 4 shows an example of 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.

[0122] 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.

[0123] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0124] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0125] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

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

[0127] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

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

[0129] Each of the multiple elements including the video analysis unit, the main point extraction unit, the summary generation unit, and the clip generation unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the video analysis unit is realized by the processor 46 of the smart glasses 214, and converts the contents of the meeting video into text using voice recognition technology or OCR technology. The main point extraction unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and extracts important topics and discussion main points using natural language processing technology. The summary generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a summary based on information extracted using a generation AI. The clip generation unit is realized, for example, by the control unit 46A of the smart glasses 214, and cuts out a part of a specific discussion or presentation so that the user can easily play it. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

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

[0131] 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.

[0132] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0133] 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.

[0134] 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 the voice according to instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0136] 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 performed in a secure state.

[0137] 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.

[0138] 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.

[0139] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0140] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific 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.

[0141] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0142] 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 voice indicating a user input for 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.

[0143] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0144] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0145] Each of the multiple elements including the video analysis unit, the main point extraction unit, the summary generation unit, and the clip generation unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the video analysis unit is realized by the processor 46 of the headset type terminal 314, and converts the contents of the meeting video into text using voice recognition technology or OCR technology. The main point extraction unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and extracts important topics and the main points of discussions using natural language processing technology. The summary generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a summary based on information extracted using a generation AI. The clip generation unit is realized, for example, by the control unit 46A of the headset type terminal 314, and cuts out a part of a specific discussion or presentation so that the user can easily play it. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

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

[0147] 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.

[0148] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0149] 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.

[0150] 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 the voice according to instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0152] 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 performed in a secure state.

[0153] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0154] 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.

[0155] 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.

[0156] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0157] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[0158] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0159] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for 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.

[0160] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

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

[0162] Each of the multiple elements including the video analysis unit, the main point extraction unit, the summary generation unit, and the clip generation unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the video analysis unit is realized by the processor 46 of the robot 414, and converts the contents of the meeting video into text using voice recognition technology or OCR technology. The main point extraction unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and extracts important topics and the main points of discussions using natural language processing technology. The summary generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a summary based on information extracted using a generation AI. The clip generation unit is realized, for example, by the control unit 46A of the robot 414, and cuts out a part of a specific discussion or presentation so that the user can easily play it. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

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

[0164] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0165] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0166] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0167] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

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

[0169] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0170] 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.

[0171] 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 Universal Serial Bus (USB) 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.

[0172] In addition, 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 upon request from the data processing device 12.

[0173] 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.

[0174] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0175] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0176] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0177] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0178] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0179] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0180] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0181] (Appendix 1) A video analysis unit that analyzes meeting videos; a main point extraction unit that extracts important topics or main points of discussion based on the data converted into text by the video analysis unit; a summary generation unit that generates a summary based on the information extracted by the gist extraction unit; a clip generator that generates a video clip of an important portion based on the summary generated by the summary generator. A system characterized by: (Appendix 2) The video analysis unit is Uses generative AI to understand the content of videos and convert audio or slides into text 2. The system of claim 1, (Appendix 3) The gist extraction unit Use natural language processing techniques to extract key topics or discussion points from textual data 2. The system of claim 1, (Appendix 4) The summary generation unit Organize the extracted topics or main points and generate a concise summary 2. The system of claim 1, (Appendix 5) The clip generation unit Cut out specific parts of a discussion or presentation so that users can easily replay them 2. The system of claim 1, (Appendix 6) The video analysis unit is Estimate user emotions and adjust the timing of video analysis based on the estimated user emotions 2. The system of claim 1, (Appendix 7) The video analysis unit is Analyzing the speaker's facial expressions and gestures to evaluate the importance of the discussion 2. The system of claim 1, (Appendix 8) The video analysis unit is Eliminate background noise and improve voice clarity in meetings 2. The system of claim 1, (Appendix 9) The video analysis unit is Estimate user emotions and prioritize videos to be analyzed based on the estimated user emotions. 2. The system of claim 1, (Appendix 10) The video analysis unit is Improve analysis accuracy by considering meeting participants' job titles and areas of expertise 2. The system of claim 1, (Appendix 11) The video analysis unit is Tailor your analysis to take into account meeting location and time of day 2. The system of claim 1, (Appendix 12) The gist extraction unit Estimate the user's emotions and prioritize the key points to be extracted based on the estimated user emotions. 2. The system of claim 1, (Appendix 13) The gist extraction unit Identify important topics by looking at the speaker's past speech history 2. The system of claim 1, (Appendix 14) The gist extraction unit Analyze the progress of discussions in real time and instantly extract important points 2. The system of claim 1, (Appendix 15) The gist extraction unit Infer the user's emotions and adjust the display method of extracted points based on the estimated user emotions. 2. The system of claim 1, (Appendix 16) The gist extraction unit Improve extraction accuracy by considering meeting agenda and purpose 2. The system of claim 1, (Appendix 17) The gist extraction unit Identify important topics by considering the frequency and duration of speech by meeting participants 2. The system of claim 1, (Appendix 18) The summary generation unit Estimate the user's emotions and adjust the way summaries are presented based on the estimated user emotions. 2. The system of claim 1, (Appendix 19) The summary generation unit Adjust the detail of your summary based on the importance of the discussion 2. The system of claim 1, (Appendix 20) The summary generation unit Apply different summarization algorithms depending on the category of discussion 2. The system of claim 1, (Appendix 21) The summary generation unit Estimating user sentiment and adjusting the length of a summary based on the estimated user sentiment 2. The system of claim 1, (Appendix 22) The summary generation unit Prioritize summaries based on discussion progress 2. The system of claim 1, (Appendix 23) The summary generation unit Adjust the order of summaries based on the relevance of the discussion 2. The system of claim 1, (Appendix 24) The clip generation unit A user's emotion is estimated, and a clip generation method is adjusted based on the estimated user's emotion. 2. The system of claim 1, (Appendix 25) The clip generation unit Adjust clip length based on the importance of the discussion 2. The system of claim 1, (Appendix 26) The clip generation unit Apply different clip generation algorithms depending on the category of discussion 2. The system of claim 1, (Appendix 27) The clip generation unit Inferring a user's emotion and adjusting how a clip is displayed based on the estimated user's emotion 2. The system of claim 1, (Appendix 28) The clip generation unit Prioritize clips based on discussion progress 2. The system of claim 1, (Appendix 29) The clip generation unit Adjust the order of clips based on the relevance of the discussion 2. The system of claim 1, [Explanation of symbols]

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

Claims

1. A video analysis unit that analyzes meeting videos; a main point extraction unit that extracts important topics or main points of discussion based on the data converted into text by the video analysis unit; a summary generation unit that generates a summary based on the information extracted by the gist extraction unit; a clip generator that generates a video clip of an important portion based on the summary generated by the summary generator. A system characterized by:

2. The video analysis unit is Using generative AI to understand the content of videos and convert audio or slide content into text 2. The system of claim 1 .

3. The gist extraction unit Use natural language processing techniques to extract key topics or discussion points from textual data 2. The system of claim 1 .

4. The summary generation unit Organize the extracted topics or main points and generate a concise summary 2. The system of claim 1 .

5. The clip generation unit Cut out specific parts of a discussion or presentation so that users can easily replay them 2. The system of claim 1 .

6. The video analysis unit is Estimate user emotions and adjust the timing of video analysis based on the estimated user emotions 2. The system of claim 1 .

7. The video analysis unit is Analyzing the speaker's facial expressions and gestures to evaluate the importance of the discussion 2. The system of claim 1 .

8. The video analysis unit is Eliminate background noise and improve voice clarity in meetings 2. The system of claim 1 .

Images