system

Abstract

The system according to the embodiment aims to automatically generate accurate summaries from recorded video and audio. [Solution] A system according to an embodiment includes an analysis unit, a recognition unit, an extraction unit, a generation unit, and a provision unit. The analysis unit analyzes recorded video and audio. The recognition unit recognizes the audio data analyzed by the analysis unit. The extraction unit extracts important points from the text data recognized by the recognition unit. The generation unit generates a summary based on the points extracted by the extraction unit. The provision unit provides the summary generated by the generation unit.

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the drawback of making it difficult to automatically generate accurate summaries from recorded video and audio, requiring manual correction.

[0005] The system according to the embodiment aims to automatically generate accurate summaries from recorded video and audio. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a recognition unit, an extraction unit, a generation unit, and a provision unit. The analysis unit analyzes recorded video and audio. The recognition unit recognizes the audio data analyzed by the analysis unit. The extraction unit extracts important points from the text data recognized by the recognition unit. The generation unit generates a summary based on the points extracted by the extraction unit. The provision unit provides the summary generated by the generation unit. [Effects of the Invention]

[0007] An embodiment of the system can automatically generate accurate summaries from recorded video and audio. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0028] (Example 1) An automatic minutes generation system according to an embodiment of the present invention automatically creates a summary of meeting minutes using Zoom recordings. This system records a Zoom meeting, analyzes the recorded video and audio, and generates a summary of the meeting minutes. Specifically, the Zoom meeting is first recorded. The recorded video and audio are then input to an analysis unit, which uses a noise canceling unit and a speaker separation unit to improve the quality of the audio data. The analyzed audio data is then input to a recognition unit, which converts the audio data into text using a speech recognition model based on generative AI. The converted text data is then input to an extraction unit, which extracts key points using a keyword extraction unit and a topic modeling unit. The extracted points are then input to a generation unit, which generates a summary of the meeting minutes using a summary generation model based on generative AI. Finally, the generated summary is input to a provision unit and provided to the user. This mechanism significantly reduces the need for revisions to the meeting minutes. This allows the automatic minutes generation system to automatically create a summary of the meeting minutes using Zoom recordings.

[0029] An automatic minutes generation system according to an embodiment includes an analysis unit, a recognition unit, an extraction unit, a generation unit, and a provision unit. The analysis unit analyzes recorded video and audio. The analysis unit improves the quality of the audio data using a noise canceling unit and a speaker separation unit. For example, the noise canceling unit removes background noise and increases the clarity of the audio data. The speaker separation unit separates the audio of multiple speakers and extracts the audio data of each speaker. The recognition unit converts the audio data into text data using a speech recognition model based on a generative AI. For example, the generative AI receives audio data and outputs text data. The generative AI has trained on a large amount of audio data and is capable of highly accurate speech recognition. The extraction unit extracts important points from the text data using a keyword extraction unit and a topic modeling unit. For example, the keyword extraction unit extracts frequently occurring keywords from the text data. The topic modeling unit classifies the text data by topic and extracts important topics. The generation unit generates a summary of the minutes using a summary generation model based on the generative AI. For example, the generation AI takes the extracted points as input and outputs a summary. The generation AI has learned from a large amount of text data and is capable of generating summaries with high accuracy. The providing unit provides the generated summary to a user. For example, the providing unit displays the summary through a web application or a mobile application. The providing unit can also send the summary by email. As a result, the automatic minutes generation system according to the embodiment can automatically create a summary of minutes using Zoom recordings and provide it to a user.

[0030] The automatic minutes generation system includes a noise canceling unit that performs noise canceling. The noise canceling unit removes background noise from recorded audio data. For example, the noise canceling unit receives audio data as input and outputs audio data from which noise has been removed. The noise canceling unit removes noise from the audio data using a noise reduction algorithm. For example, the noise canceling unit removes noise from the audio data using a spectral subtraction method. The noise canceling unit can also remove noise from the audio data using adaptive filtering. Furthermore, the noise canceling unit can remove noise from the audio data using a machine learning algorithm. For example, the noise canceling unit removes noise from the audio data using a machine learning model. In this way, the noise canceling unit can improve the quality of the audio data.

[0031] The automatic minutes generation system includes a speaker separation unit that performs speaker separation. The speaker separation unit separates the voices of multiple speakers from recorded audio data. For example, the speaker separation unit receives audio data as input and outputs audio data of each speaker. The speaker separation unit uses a speaker identification algorithm to identify speakers from the audio data. For example, the speaker separation unit uses audio features to identify speakers from the audio data. The speaker separation unit can also use a machine learning algorithm to identify speakers from the audio data. Furthermore, the speaker separation unit can also use a deep learning algorithm to identify speakers from the audio data. For example, the speaker separation unit uses a deep neural network to identify speakers from the audio data. This allows the speaker separation unit to improve the quality of the audio data.

[0032] The automatic minutes generation system includes a keyword extraction unit that extracts keywords. The keyword extraction unit extracts important keywords from text data. For example, the keyword extraction unit receives text data as input and outputs important keywords. The keyword extraction unit uses a keyword extraction algorithm to extract keywords from the text data. For example, the keyword extraction unit uses TF-IDF (Term Frequency-Inverse Document Frequency) to extract keywords from the text data. The keyword extraction unit can also use co-occurrence network analysis to extract keywords from the text data. Furthermore, the keyword extraction unit can also use a machine learning algorithm to extract keywords from the text data. For example, the keyword extraction unit uses a machine learning model to extract keywords from the text data. This allows the keyword extraction unit to efficiently extract important points.

[0033] The automatic minutes generation system includes a topic modeling unit that performs topic modeling. The topic modeling unit classifies text data by topic and extracts important topics. For example, the topic modeling unit receives text data as input and outputs topics. The topic modeling unit uses a topic modeling algorithm to classify the text data by topic. For example, the topic modeling unit uses LDA (Latent Dirichlet Allocation) to classify the text data by topic. The topic modeling unit can also use non-negative matrix factorization to classify the text data by topic. Furthermore, the topic modeling unit can also use topic clustering to classify the text data by topic. For example, the topic modeling unit uses a clustering algorithm to classify the text data by topic. This allows the topic modeling unit to efficiently extract important points.

[0034] The recognition unit can convert voice data into text data using a voice recognition model that uses generative AI. The generative AI takes voice data as input and outputs text data. For example, the generative AI converts voice data into text data using a voice recognition algorithm. The generative AI has learned a large amount of voice data and is capable of highly accurate voice recognition. For example, the generative AI converts voice data into text data using a deep learning algorithm. The generative AI can also convert voice data into text data using a recurrent neural network (RNN). Furthermore, the generative AI can convert voice data into text data using a Transformer model. For example, the generative AI converts voice data into text data using a Transformer model. This improves the accuracy of voice recognition by using generative AI.

[0035] The generation unit can generate a summary of the minutes using a summary generation model that uses generative AI. The generative AI takes the extracted points as input and outputs a summary. For example, the generative AI uses a summary generation algorithm to generate a summary based on the extracted points. The generative AI has learned from large amounts of text data and is capable of generating summaries with high accuracy. For example, the generative AI generates a summary using a deep learning algorithm. The generative AI can also generate a summary using a Transformer model. Furthermore, the generative AI can generate a summary using a recurrent neural network (RNN). For example, the generative AI generates a summary using a Transformer model. This improves the accuracy of summary generation by using generative AI.

[0036] During analysis, the analysis unit can apply different analysis algorithms depending on the content of the meeting. The analysis unit applies different analysis algorithms depending on the content of the meeting. For example, in the case of a technical meeting, the analysis unit applies an analysis algorithm that emphasizes technical terms. In addition, in the case of a business meeting, the analysis unit can also apply an analysis algorithm that emphasizes points related to decision-making. Furthermore, in the case of an educational meeting, the analysis unit can apply an analysis algorithm that emphasizes learning content. In this way, by applying an analysis algorithm depending on the content of the meeting, the accuracy of the analysis is improved.

[0037] The analysis unit can perform analysis taking into account the attribute information of the meeting participants. The analysis unit performs analysis taking into account the attribute information of the meeting participants. For example, the analysis unit prioritizes analysis of important comments based on the participant's job position. The analysis unit can also analyze by placing emphasis on related comments based on the participant's field of expertise. Furthermore, the analysis unit can analyze in detail the content of participants who frequently speak based on the frequency of their comments. In this way, by taking into account the participant's attribute information, more accurate analysis results can be provided.

[0038] The analysis unit can take into account the geographical distribution of the conference when performing the analysis. The analysis unit performs the analysis while taking into account the geographical distribution of the conference. For example, if participants are from different regions, the analysis unit will place emphasis on comments made by each region. The analysis unit can also analyze the nuances of comments while taking into account the cultural background of each region. Furthermore, the analysis unit can adjust the importance of comments while taking into account the time zone of each region. In this way, by taking geographical distribution into account, more accurate analysis results can be provided.

[0039] During analysis, the analysis unit can improve the accuracy of the analysis by referring to literature related to the conference. The analysis unit improves the accuracy of the analysis by referring to literature related to the conference. For example, the analysis unit automatically refers to literature related to the theme of the conference and reflects this in the analysis results. The analysis unit can also incorporate literature cited by participants into the analysis to improve accuracy. Furthermore, the analysis unit can refer to the latest research results related to the content of the conference and reflect this in the analysis results. In this way, the accuracy of the analysis is improved by referring to related literature.

[0040] The recognition unit can apply different speech recognition algorithms depending on the content of the meeting during recognition. The recognition unit applies different speech recognition algorithms depending on the content of the meeting. For example, in the case of a technical meeting, the recognition unit applies a speech recognition algorithm that emphasizes technical terms. In addition, in the case of a business meeting, the recognition unit can apply a speech recognition algorithm that emphasizes points related to decision-making. Furthermore, in the case of an educational meeting, the recognition unit can apply a speech recognition algorithm that emphasizes learning content. In this way, by applying a speech recognition algorithm depending on the content of the meeting, the accuracy of speech recognition is improved.

[0041] The recognition unit can perform recognition taking into consideration the speech frequency of the conference participants during recognition. The recognition unit performs recognition taking into consideration the speech frequency of the conference participants. For example, the recognition unit prioritizes recognition of the voices of participants who speak frequently. The recognition unit can also recognize the voices of participants who speak infrequently without omission. Furthermore, the recognition unit can also prioritize recognition of important statements based on speech frequency. In this way, important statements can be recognized with priority by taking speech frequency into consideration.

[0042] During recognition, the recognition unit can determine the priority of speech recognition based on the time period of the meeting. The recognition unit determines the priority of speech recognition based on the time period of the meeting. For example, the recognition unit may prioritize recognition of important utterances based on the start time of the meeting. The recognition unit may also emphasize recognition of key points as the end of the meeting approaches. Furthermore, the recognition unit may recognize speech in the middle of the meeting while taking into account the overall balance. In this way, by determining the priority of speech recognition based on the time period, important utterances can be prioritized.

[0043] The recognition unit can improve the accuracy of speech recognition by referring to data related to the conference during recognition. The recognition unit improves the accuracy of speech recognition by referring to data related to the conference. For example, the recognition unit improves the accuracy of speech recognition by referring to data related to the topic of the conference. The recognition unit can also incorporate data cited by participants into the recognition to improve accuracy. Furthermore, the recognition unit can improve the accuracy of speech recognition by referring to the latest data related to the content of the conference. In this way, the accuracy of speech recognition is improved by referring to related data.

[0044] During extraction, the extraction unit can apply different extraction algorithms depending on the content of the meeting. The extraction unit applies different extraction algorithms depending on the content of the meeting. For example, in the case of a technical meeting, the extraction unit applies an extraction algorithm that emphasizes technical terms. In addition, in the case of a business meeting, the extraction unit can also apply an extraction algorithm that emphasizes points related to decision-making. Furthermore, in the case of an educational meeting, the extraction unit can apply an extraction algorithm that emphasizes learning content. In this way, by applying an extraction algorithm depending on the content of the meeting, the accuracy of extraction is improved.

[0045] The extraction unit can perform extraction while taking into consideration the content of statements made by the meeting participants. The extraction unit performs extraction while taking into consideration the content of statements made by the meeting participants. For example, the extraction unit prioritizes extraction of important statements based on the participants' job positions. The extraction unit can also prioritize extraction of relevant statements based on the participants' fields of expertise. Furthermore, the extraction unit can extract detailed content from participants who frequently make statements based on the frequency of their statements. This allows important points to be extracted efficiently by taking into consideration the content of the participants' statements.

[0046] During extraction, the extraction unit can determine the priority of important points based on the time period of the meeting. The extraction unit determines the priority of important points based on the time period of the meeting. For example, the extraction unit may preferentially extract important points based on the start time of the meeting. The extraction unit may also prioritize extraction of key points as the end of the meeting approaches. Furthermore, the extraction unit may extract important points in the middle of the meeting, taking into account the overall balance. This allows for efficient extraction by determining the priority of important points based on the time period.

[0047] The extraction unit can improve the accuracy of extraction by referring to data related to the meeting during extraction. The extraction unit improves the accuracy of extraction by referring to data related to the meeting. For example, the extraction unit improves the accuracy of extraction by referring to data related to the theme of the meeting. The extraction unit can also improve the accuracy by incorporating data cited by participants into the extraction. Furthermore, the extraction unit can improve the accuracy of extraction by referring to the latest data related to the content of the meeting. In this way, the accuracy of extraction is improved by referring to related data.

[0048] The generation unit can apply different summary generation algorithms depending on the content of the conference during generation. The generation unit applies different summary generation algorithms depending on the content of the conference. For example, in the case of a technical conference, the generation unit applies a summary generation algorithm that emphasizes technical terms. In addition, in the case of a business conference, the generation unit can also apply a summary generation algorithm that emphasizes points related to decision-making. Furthermore, in the case of an educational conference, the generation unit can apply a summary generation algorithm that emphasizes learning content. In this way, by applying a summary generation algorithm depending on the content of the conference, the accuracy of the summary is improved.

[0049] The generation unit can generate a summary taking into consideration the content of statements made by the meeting participants when generating the summary. The generation unit generates a summary taking into consideration the content of statements made by the meeting participants. For example, the generation unit prioritizes summarizing important statements based on the participants' job positions. The generation unit can also emphasize and summarize relevant statements based on the participants' fields of expertise. Furthermore, the generation unit can summarize in detail the content of participants who frequently speak based on the frequency of their statements. This allows important points to be efficiently summarized by taking into consideration the content of participants' statements.

[0050] The generation unit can determine the priority of summaries based on the time slot of the meeting when generating the summaries. The generation unit determines the priority of summaries based on the time slot of the meeting. For example, the generation unit prioritizes summarizing important points based on the start time of the meeting. The generation unit can also emphasize the main points when summarizing as the end time of the meeting approaches. Furthermore, the generation unit can summarize in the middle of the meeting while taking into account the overall balance. In this way, efficient summarization is possible by determining the priority of summaries based on the time slot.

[0051] The generation unit can improve the accuracy of the summary by referring to data related to the conference when generating the summary. The generation unit improves the accuracy of the summary by referring to data related to the conference. For example, the generation unit improves the accuracy of the summary by referring to data related to the theme of the conference. The generation unit can also improve the accuracy by incorporating data cited by participants into the summary. Furthermore, the generation unit can improve the accuracy of the summary by referring to the latest data related to the content of the conference. In this way, the accuracy of the summary is improved by referring to the related data.

[0052] The providing unit can select the optimal providing method by referring to the user's past usage history when providing the data. The providing unit selects the optimal providing method by referring to the user's past usage history. For example, the providing unit selects the optimal providing method based on the summary format used by the user in the past. The providing unit can also predict and provide a preferred summary format from the user's past usage history. Furthermore, the providing unit can analyze the user's past usage history and select the most efficient providing method. In this way, the optimal providing method can be selected by referring to the past usage history.

[0053] The providing unit can select the optimal providing method by taking into consideration the device information of the user when providing the summary. The providing unit selects the optimal providing method by taking into consideration the device information of the user. For example, if the user is using a smartphone, the providing unit can provide a summary that is tailored to the screen size. Also, if the user is using a tablet, the providing unit can provide a summary that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the providing unit can provide a concise and highly visible summary. In this way, the optimal providing method can be selected by taking into consideration the device information.

[0054] The noise canceling unit can apply different noise canceling algorithms depending on the content of the meeting during noise cancellation. The noise canceling unit applies different noise canceling algorithms depending on the content of the meeting. For example, in a technical meeting, the noise canceling unit applies a noise canceling algorithm that emphasizes technical terms. In addition, in a business meeting, the noise canceling unit can apply a noise canceling algorithm that emphasizes points related to decision-making. Furthermore, in an educational meeting, the noise canceling unit can apply a noise canceling algorithm that emphasizes learning content. In this way, by applying a noise canceling algorithm depending on the content of the meeting, the accuracy of noise canceling is improved.

[0055] The noise canceling unit can select the optimal noise canceling method by taking into account the environmental sounds of the meeting when performing noise cancellation. The noise canceling unit selects the optimal noise canceling method by taking into account the environmental sounds of the meeting. For example, the noise canceling unit analyzes the environmental sounds of the meeting room and selects the optimal noise canceling method. In addition, the noise canceling unit can perform noise cancellation by taking into account background sounds in the case of an online meeting. Furthermore, the noise canceling unit can perform noise cancellation by taking into account wind and traffic sounds in the case of an outdoor meeting. In this way, the optimal noise canceling method can be selected by taking into account the environmental sounds.

[0056] The speaker separation unit can apply different speaker separation algorithms depending on the content of the conference when separating speakers. The speaker separation unit applies different speaker separation algorithms depending on the content of the conference. For example, in the case of a technical conference, the speaker separation unit applies a speaker separation algorithm that emphasizes technical terms. In addition, in the case of a business conference, the speaker separation unit can also apply a speaker separation algorithm that emphasizes points related to decision-making. Furthermore, in the case of an educational conference, the speaker separation unit can apply a speaker separation algorithm that emphasizes learning content. In this way, by applying a speaker separation algorithm depending on the content of the conference, the accuracy of speaker separation is improved.

[0057] The speaker separation unit can perform speaker separation by taking into account attribute information of the conference participants. The speaker separation unit performs speaker separation by taking into account attribute information of the conference participants. For example, the speaker separation unit prioritizes separation of important utterances based on the participants' job positions. The speaker separation unit can also prioritize separation of related utterances based on the participants' fields of expertise. Furthermore, the speaker separation unit can separate the content of frequently uttered participants in detail based on the frequency of their utterances. In this way, important utterances can be efficiently separated by taking into account the participants' attribute information.

[0058] The keyword extraction unit can apply different keyword extraction algorithms depending on the content of the meeting when extracting keywords. The keyword extraction unit applies different keyword extraction algorithms depending on the content of the meeting. For example, in the case of a technical meeting, the keyword extraction unit applies a keyword extraction algorithm that emphasizes technical terms. In addition, in the case of a business meeting, the keyword extraction unit can also apply a keyword extraction algorithm that emphasizes points related to decision-making. Furthermore, in the case of an educational meeting, the keyword extraction unit can apply a keyword extraction algorithm that emphasizes learning content. In this way, by applying a keyword extraction algorithm depending on the content of the meeting, the accuracy of keyword extraction is improved.

[0059] The keyword extraction unit can improve the accuracy of keyword extraction by referring to data related to the meeting when extracting keywords. The keyword extraction unit improves the accuracy of keyword extraction by referring to data related to the meeting. For example, the keyword extraction unit improves the accuracy of keyword extraction by referring to data related to the theme of the meeting. The keyword extraction unit can also improve accuracy by incorporating data cited by participants into the extraction. Furthermore, the keyword extraction unit can improve the accuracy of keyword extraction by referring to the latest data related to the content of the meeting. In this way, the accuracy of keyword extraction is improved by referring to related data.

[0060] During topic modeling, the topic modeling unit can apply different topic modeling algorithms depending on the content of the meeting. The topic modeling unit applies different topic modeling algorithms depending on the content of the meeting. For example, in the case of a technical meeting, the topic modeling unit applies a topic modeling algorithm that emphasizes technical terms. In addition, in the case of a business meeting, the topic modeling unit can apply a topic modeling algorithm that emphasizes points related to decision-making. Furthermore, in the case of an educational meeting, the topic modeling unit can apply a topic modeling algorithm that emphasizes learning content. In this way, by applying a topic modeling algorithm depending on the content of the meeting, the accuracy of topic modeling is improved.

[0061] During topic modeling, the topic modeling unit can improve the accuracy of topic modeling by referring to data related to the conference. The topic modeling unit improves the accuracy of topic modeling by referring to data related to the conference. For example, the topic modeling unit improves the accuracy of topic modeling by referring to data related to the theme of the conference. The topic modeling unit can also incorporate data cited by participants into the modeling to improve accuracy. Furthermore, the topic modeling unit can improve the accuracy of topic modeling by referring to the latest data related to the content of the conference. In this way, the accuracy of topic modeling is improved by referring to related data.

[0062] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0063] The recognition unit can analyze the content of speech made by meeting participants and infer the intention of the speech. For example, the recognition unit can classify the intention of speech, such as a question, suggestion, or opinion, based on the content of speech. The recognition unit can also support the progress of the meeting based on the intention of the speech. Furthermore, the recognition unit can automatically provide related information based on the intention of the speech. This helps the meeting proceed smoothly and deepens participants' understanding.

[0064] The extraction unit can analyze the content of comments made by meeting participants and evaluate the importance of the comments. For example, the extraction unit can extract important keywords and phrases from the content of the comments and score the importance of the comments. The extraction unit can also generate a summary of the meeting based on the importance of the comments. Furthermore, the extraction unit can support the progress of the meeting based on the importance of the comments. This allows you to efficiently grasp the main points of the meeting and not miss any important information.

[0065] The providing unit can analyze the content of statements made by meeting participants and provide a summary based on the intent of the statements. For example, the providing unit can provide a summary that focuses on answers to questions. The providing unit can also provide a summary that includes opinions on proposals. Furthermore, the providing unit can also provide a summary that reflects the content of the exchange of opinions. This makes it easier to understand the content of the meeting.

[0066] The recognition unit can analyze the content of speech made by meeting participants and provide relevant information based on the intent of the speech. For example, the recognition unit can automatically provide answers to questions, provide relevant information for suggestions, and provide information related to the exchange of opinions. This helps the meeting proceed smoothly and deepens participants' understanding.

[0067] The generation unit can analyze the content of statements made by meeting participants and generate summaries based on the intent of those statements. For example, it can generate summaries that focus on answers to questions. It can also generate summaries that include opinions on proposals. It can also generate summaries that reflect the content of the exchange of opinions. This makes the content of the meeting easier to understand.

[0068] The processing flow of the first embodiment will be briefly explained below.

[0069] Step 1: The analysis unit analyzes the recorded video and audio. The analysis unit improves the quality of the audio data using a noise canceling unit and a speaker separation unit. For example, the noise canceling unit removes background noise and improves the clarity of the audio data. The speaker separation unit separates the audio from multiple speakers and extracts the audio data of each speaker. Step 2: The recognition unit converts the voice data into text data using a voice recognition model that uses the generation AI. For example, the generation AI takes voice data as input and outputs text data. The generation AI has learned a large amount of voice data and is capable of highly accurate voice recognition. Step 3: The extraction unit uses the keyword extraction unit and topic modeling unit to extract important points from the text data. For example, the keyword extraction unit extracts frequently occurring keywords from the text data. The topic modeling unit classifies the text data by topic and extracts important topics. Step 4: The generation unit uses a summary generation model with generative AI to generate a summary of the minutes. For example, the generative AI takes the extracted points as input and outputs a summary. The generative AI has learned from a large amount of text data, enabling it to generate summaries with high accuracy. Step 5: The providing unit provides the generated summary to the user. For example, the providing unit may display the summary through a web application or a mobile application. The providing unit may also send the summary by email.

[0070] (Example 2) An automatic minutes generation system according to an embodiment of the present invention automatically creates a summary of meeting minutes using Zoom recordings. This system records a Zoom meeting, analyzes the recorded video and audio, and generates a summary of the meeting minutes. Specifically, the Zoom meeting is first recorded. The recorded video and audio are then input to an analysis unit, which uses a noise canceling unit and a speaker separation unit to improve the quality of the audio data. The analyzed audio data is then input to a recognition unit, which converts the audio data into text using a speech recognition model based on generative AI. The converted text data is then input to an extraction unit, which extracts key points using a keyword extraction unit and a topic modeling unit. The extracted points are then input to a generation unit, which generates a summary of the meeting minutes using a summary generation model based on generative AI. Finally, the generated summary is input to a provision unit and provided to the user. This mechanism significantly reduces the need for revisions to the meeting minutes. This allows the automatic minutes generation system to automatically create a summary of the meeting minutes using Zoom recordings.

[0071] An automatic minutes generation system according to an embodiment includes an analysis unit, a recognition unit, an extraction unit, a generation unit, and a provision unit. The analysis unit analyzes recorded video and audio. The analysis unit improves the quality of the audio data using a noise canceling unit and a speaker separation unit. For example, the noise canceling unit removes background noise and increases the clarity of the audio data. The speaker separation unit separates the audio of multiple speakers and extracts the audio data of each speaker. The recognition unit converts the audio data into text data using a speech recognition model based on a generative AI. For example, the generative AI receives audio data and outputs text data. The generative AI has trained on a large amount of audio data and is capable of highly accurate speech recognition. The extraction unit extracts important points from the text data using a keyword extraction unit and a topic modeling unit. For example, the keyword extraction unit extracts frequently occurring keywords from the text data. The topic modeling unit classifies the text data by topic and extracts important topics. The generation unit generates a summary of the minutes using a summary generation model based on the generative AI. For example, the generation AI takes the extracted points as input and outputs a summary. The generation AI has learned from a large amount of text data and is capable of generating summaries with high accuracy. The providing unit provides the generated summary to a user. For example, the providing unit displays the summary through a web application or a mobile application. The providing unit can also send the summary by email. As a result, the automatic minutes generation system according to the embodiment can automatically create a summary of minutes using Zoom recordings and provide it to a user.

[0072] The automatic minutes generation system includes a noise canceling unit that performs noise canceling. The noise canceling unit removes background noise from recorded audio data. For example, the noise canceling unit receives audio data as input and outputs audio data from which noise has been removed. The noise canceling unit removes noise from the audio data using a noise reduction algorithm. For example, the noise canceling unit removes noise from the audio data using a spectral subtraction method. The noise canceling unit can also remove noise from the audio data using adaptive filtering. Furthermore, the noise canceling unit can remove noise from the audio data using a machine learning algorithm. For example, the noise canceling unit removes noise from the audio data using a machine learning model. In this way, the noise canceling unit can improve the quality of the audio data.

[0073] The automatic minutes generation system includes a speaker separation unit that performs speaker separation. The speaker separation unit separates the voices of multiple speakers from recorded audio data. For example, the speaker separation unit receives audio data as input and outputs audio data of each speaker. The speaker separation unit uses a speaker identification algorithm to identify speakers from the audio data. For example, the speaker separation unit uses audio features to identify speakers from the audio data. The speaker separation unit can also use a machine learning algorithm to identify speakers from the audio data. Furthermore, the speaker separation unit can also use a deep learning algorithm to identify speakers from the audio data. For example, the speaker separation unit uses a deep neural network to identify speakers from the audio data. This allows the speaker separation unit to improve the quality of the audio data.

[0074] The automatic minutes generation system includes a keyword extraction unit that extracts keywords. The keyword extraction unit extracts important keywords from text data. For example, the keyword extraction unit receives text data as input and outputs important keywords. The keyword extraction unit uses a keyword extraction algorithm to extract keywords from the text data. For example, the keyword extraction unit uses TF-IDF (Term Frequency-Inverse Document Frequency) to extract keywords from the text data. The keyword extraction unit can also use co-occurrence network analysis to extract keywords from the text data. Furthermore, the keyword extraction unit can also use a machine learning algorithm to extract keywords from the text data. For example, the keyword extraction unit uses a machine learning model to extract keywords from the text data. This allows the keyword extraction unit to efficiently extract important points.

[0075] The automatic minutes generation system includes a topic modeling unit that performs topic modeling. The topic modeling unit classifies text data by topic and extracts important topics. For example, the topic modeling unit receives text data as input and outputs topics. The topic modeling unit uses a topic modeling algorithm to classify the text data by topic. For example, the topic modeling unit uses LDA (Latent Dirichlet Allocation) to classify the text data by topic. The topic modeling unit can also use non-negative matrix factorization to classify the text data by topic. Furthermore, the topic modeling unit can also use topic clustering to classify the text data by topic. For example, the topic modeling unit uses a clustering algorithm to classify the text data by topic. This allows the topic modeling unit to efficiently extract important points.

[0076] The recognition unit can convert voice data into text data using a voice recognition model that uses generative AI. The generative AI takes voice data as input and outputs text data. For example, the generative AI converts voice data into text data using a voice recognition algorithm. The generative AI has learned a large amount of voice data and is capable of highly accurate voice recognition. For example, the generative AI converts voice data into text data using a deep learning algorithm. The generative AI can also convert voice data into text data using a recurrent neural network (RNN). Furthermore, the generative AI can convert voice data into text data using a Transformer model. For example, the generative AI converts voice data into text data using a Transformer model. This improves the accuracy of voice recognition by using generative AI.

[0077] The generation unit can generate a summary of the minutes using a summary generation model that uses generative AI. The generative AI takes the extracted points as input and outputs a summary. For example, the generative AI uses a summary generation algorithm to generate a summary based on the extracted points. The generative AI has learned from large amounts of text data and is capable of generating summaries with high accuracy. For example, the generative AI generates a summary using a deep learning algorithm. The generative AI can also generate a summary using a Transformer model. Furthermore, the generative AI can generate a summary using a recurrent neural network (RNN). For example, the generative AI generates a summary using a Transformer model. This improves the accuracy of summary generation by using generative AI.

[0078] In the automatic minutes generation system, the analysis unit can estimate the user's emotions and adjust the analysis priority based on the estimated user emotions. The analysis unit estimates the user's emotions and adjusts the analysis priority based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit can prioritize analysis of important points and provide results quickly. In addition, if the user is relaxed, the analysis unit can perform a detailed analysis and provide comprehensive results. Furthermore, if the user is in a hurry, the analysis unit can complete the analysis in a short time and extract only the main points. In this way, by adjusting the analysis priority according to the user's emotions, more appropriate analysis results can be provided.

[0079] During analysis, the analysis unit can apply different analysis algorithms depending on the content of the meeting. The analysis unit applies different analysis algorithms depending on the content of the meeting. For example, in the case of a technical meeting, the analysis unit applies an analysis algorithm that emphasizes technical terms. In addition, in the case of a business meeting, the analysis unit can also apply an analysis algorithm that emphasizes points related to decision-making. Furthermore, in the case of an educational meeting, the analysis unit can apply an analysis algorithm that emphasizes learning content. In this way, by applying an analysis algorithm depending on the content of the meeting, the accuracy of the analysis is improved.

[0080] The analysis unit can perform analysis taking into account the attribute information of the meeting participants. The analysis unit performs analysis taking into account the attribute information of the meeting participants. For example, the analysis unit prioritizes analysis of important comments based on the participant's job position. The analysis unit can also analyze by placing emphasis on related comments based on the participant's field of expertise. Furthermore, the analysis unit can analyze in detail the content of participants who frequently speak based on the frequency of their comments. In this way, by taking into account the participant's attribute information, more accurate analysis results can be provided.

[0081] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the analysis unit can provide a simple, highly visible display method. If the user is relaxed, the analysis unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the analysis unit can also provide a display method that focuses on the main points. This makes it possible to adjust the display method of the analysis results according to the user's emotions, thereby enabling more appropriate display.

[0082] The analysis unit can take into account the geographical distribution of the conference when performing the analysis. The analysis unit performs the analysis while taking into account the geographical distribution of the conference. For example, if participants are from different regions, the analysis unit will place emphasis on comments made by each region. The analysis unit can also analyze the nuances of comments while taking into account the cultural background of each region. Furthermore, the analysis unit can adjust the importance of comments while taking into account the time zone of each region. In this way, by taking geographical distribution into account, more accurate analysis results can be provided.

[0083] During analysis, the analysis unit can improve the accuracy of the analysis by referring to literature related to the conference. The analysis unit improves the accuracy of the analysis by referring to literature related to the conference. For example, the analysis unit automatically refers to literature related to the theme of the conference and reflects this in the analysis results. The analysis unit can also incorporate literature cited by participants into the analysis to improve accuracy. Furthermore, the analysis unit can refer to the latest research results related to the content of the conference and reflect this in the analysis results. In this way, the accuracy of the analysis is improved by referring to related literature.

[0084] The recognition unit can estimate the user's emotion and adjust the accuracy of speech recognition based on the estimated user's emotion. The recognition unit can estimate the user's emotion and adjust the accuracy of speech recognition based on the estimated user's emotion. For example, if the user is feeling stressed, the recognition unit can increase the accuracy of speech recognition to reduce erroneous recognition. Also, if the user is relaxed, the recognition unit can perform processing with normal speech recognition accuracy. Furthermore, if the user is in a hurry, the recognition unit can quickly perform speech recognition and provide a result. In this way, by adjusting the accuracy of speech recognition according to the user's emotion, more appropriate speech recognition results can be provided.

[0085] The recognition unit can apply different speech recognition algorithms depending on the content of the meeting during recognition. The recognition unit applies different speech recognition algorithms depending on the content of the meeting. For example, in the case of a technical meeting, the recognition unit applies a speech recognition algorithm that emphasizes technical terms. In addition, in the case of a business meeting, the recognition unit can apply a speech recognition algorithm that emphasizes points related to decision-making. Furthermore, in the case of an educational meeting, the recognition unit can apply a speech recognition algorithm that emphasizes learning content. In this way, by applying a speech recognition algorithm depending on the content of the meeting, the accuracy of speech recognition is improved.

[0086] The recognition unit can perform recognition taking into consideration the speech frequency of the conference participants during recognition. The recognition unit performs recognition taking into consideration the speech frequency of the conference participants. For example, the recognition unit prioritizes recognition of the voices of participants who speak frequently. The recognition unit can also recognize the voices of participants who speak infrequently without omission. Furthermore, the recognition unit can also prioritize recognition of important statements based on speech frequency. In this way, important statements can be recognized with priority by taking speech frequency into consideration.

[0087] The recognition unit can estimate the user's emotion and adjust the display method of the recognition result based on the estimated user's emotion. The recognition unit can estimate the user's emotion and adjust the display method of the recognition result based on the estimated user's emotion. For example, if the user is nervous, the recognition unit can provide a simple, highly visible display method. If the user is relaxed, the recognition unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the recognition unit can also provide a display method that focuses on the main points. This makes it possible to adjust the display method of the recognition result according to the user's emotion, thereby enabling a more appropriate display.

[0088] During recognition, the recognition unit can determine the priority of speech recognition based on the time period of the meeting. The recognition unit determines the priority of speech recognition based on the time period of the meeting. For example, the recognition unit may prioritize recognition of important utterances based on the start time of the meeting. The recognition unit may also emphasize recognition of key points as the end of the meeting approaches. Furthermore, the recognition unit may recognize speech in the middle of the meeting while taking into account the overall balance. In this way, by determining the priority of speech recognition based on the time period, important utterances can be prioritized.

[0089] The recognition unit can improve the accuracy of speech recognition by referring to data related to the conference during recognition. The recognition unit improves the accuracy of speech recognition by referring to data related to the conference. For example, the recognition unit improves the accuracy of speech recognition by referring to data related to the topic of the conference. The recognition unit can also incorporate data cited by participants into the recognition to improve accuracy. Furthermore, the recognition unit can improve the accuracy of speech recognition by referring to the latest data related to the content of the conference. In this way, the accuracy of speech recognition is improved by referring to related data.

[0090] The extraction unit can estimate the user's emotions and adjust the extraction method of important points based on the estimated user's emotions. The extraction unit can estimate the user's emotions and adjust the extraction method of important points based on the estimated user's emotions. For example, if the user is feeling stressed, the extraction unit can prioritize extracting important points. Also, if the user is relaxed, the extraction unit can extract detailed points. Furthermore, if the user is in a hurry, the extraction unit can extract only the main points. In this way, by adjusting the extraction method according to the user's emotions, more appropriate points can be extracted.

[0091] During extraction, the extraction unit can apply different extraction algorithms depending on the content of the meeting. The extraction unit applies different extraction algorithms depending on the content of the meeting. For example, in the case of a technical meeting, the extraction unit applies an extraction algorithm that emphasizes technical terms. In addition, in the case of a business meeting, the extraction unit can also apply an extraction algorithm that emphasizes points related to decision-making. Furthermore, in the case of an educational meeting, the extraction unit can apply an extraction algorithm that emphasizes learning content. In this way, by applying an extraction algorithm depending on the content of the meeting, the accuracy of extraction is improved.

[0092] The extraction unit can perform extraction while taking into consideration the content of statements made by the meeting participants. The extraction unit performs extraction while taking into consideration the content of statements made by the meeting participants. For example, the extraction unit prioritizes extraction of important statements based on the participants' job positions. The extraction unit can also prioritize extraction of relevant statements based on the participants' fields of expertise. Furthermore, the extraction unit can extract detailed content from participants who frequently make statements based on the frequency of their statements. This allows important points to be extracted efficiently by taking into consideration the content of the participants' statements.

[0093] The extraction unit can estimate the user's emotion and adjust the display method of the extraction results based on the estimated user's emotion. The extraction unit can estimate the user's emotion and adjust the display method of the extraction results based on the estimated user's emotion. For example, if the user is nervous, the extraction unit can provide a simple, highly visible display method. If the user is relaxed, the extraction unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the extraction unit can also provide a display method that focuses on the main points. This makes it possible to adjust the display method of the extraction results according to the user's emotion, thereby enabling more appropriate display.

[0094] During extraction, the extraction unit can determine the priority of important points based on the time period of the meeting. The extraction unit determines the priority of important points based on the time period of the meeting. For example, the extraction unit may preferentially extract important points based on the start time of the meeting. The extraction unit may also prioritize extraction of key points as the end of the meeting approaches. Furthermore, the extraction unit may extract important points in the middle of the meeting, taking into account the overall balance. This allows for efficient extraction by determining the priority of important points based on the time period.

[0095] The extraction unit can improve the accuracy of extraction by referring to data related to the meeting during extraction. The extraction unit improves the accuracy of extraction by referring to data related to the meeting. For example, the extraction unit improves the accuracy of extraction by referring to data related to the theme of the meeting. The extraction unit can also improve the accuracy by incorporating data cited by participants into the extraction. Furthermore, the extraction unit can improve the accuracy of extraction by referring to the latest data related to the content of the meeting. In this way, the accuracy of extraction is improved by referring to related data.

[0096] The generation unit can estimate the user's emotion and adjust the summary generation method based on the estimated user's emotion. The generation unit can estimate the user's emotion and adjust the summary generation method based on the estimated user's emotion. For example, if the user is feeling stressed, the generation unit can generate a concise summary that is concise and to the point. Also, if the user is relaxed, the generation unit can generate a summary that includes detailed information. Furthermore, if the user is in a hurry, the generation unit can quickly generate a summary and provide the result. In this way, by adjusting the summary generation method according to the user's emotion, a more appropriate summary can be generated.

[0097] The generation unit can apply different summary generation algorithms depending on the content of the conference during generation. The generation unit applies different summary generation algorithms depending on the content of the conference. For example, in the case of a technical conference, the generation unit applies a summary generation algorithm that emphasizes technical terms. In addition, in the case of a business conference, the generation unit can also apply a summary generation algorithm that emphasizes points related to decision-making. Furthermore, in the case of an educational conference, the generation unit can apply a summary generation algorithm that emphasizes learning content. In this way, by applying a summary generation algorithm depending on the content of the conference, the accuracy of the summary is improved.

[0098] The generation unit can generate a summary taking into consideration the content of statements made by the meeting participants when generating the summary. The generation unit generates a summary taking into consideration the content of statements made by the meeting participants. For example, the generation unit prioritizes summarizing important statements based on the participants' job positions. The generation unit can also emphasize and summarize relevant statements based on the participants' fields of expertise. Furthermore, the generation unit can summarize in detail the content of participants who frequently speak based on the frequency of their statements. This allows important points to be efficiently summarized by taking into consideration the content of participants' statements.

[0099] The generation unit can estimate the user's emotion and adjust the summary display method based on the estimated user's emotion. The generation unit can estimate the user's emotion and adjust the summary display method based on the estimated user's emotion. For example, if the user is nervous, the generation unit can provide a simple, highly visible display method. If the user is relaxed, the generation unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the generation unit can also provide a display method that focuses on the main points. This allows for a more appropriate display by adjusting the summary display method according to the user's emotion.

[0100] The generation unit can determine the priority of summaries based on the time slot of the meeting when generating the summaries. The generation unit determines the priority of summaries based on the time slot of the meeting. For example, the generation unit prioritizes summarizing important points based on the start time of the meeting. The generation unit can also emphasize the main points when summarizing as the end time of the meeting approaches. Furthermore, the generation unit can summarize in the middle of the meeting while taking into account the overall balance. In this way, efficient summarization is possible by determining the priority of summaries based on the time slot.

[0101] The generation unit can improve the accuracy of the summary by referring to data related to the conference when generating the summary. The generation unit improves the accuracy of the summary by referring to data related to the conference. For example, the generation unit improves the accuracy of the summary by referring to data related to the theme of the conference. The generation unit can also improve the accuracy by incorporating data cited by participants into the summary. Furthermore, the generation unit can improve the accuracy of the summary by referring to the latest data related to the content of the conference. In this way, the accuracy of the summary is improved by referring to the related data.

[0102] The providing unit can estimate the user's emotion and adjust the method of providing a summary based on the estimated user's emotion. The providing unit can estimate the user's emotion and adjust the method of providing a summary based on the estimated user's emotion. For example, if the user is feeling stressed, the providing unit can provide a concise summary that covers the main points. Also, if the user is relaxed, the providing unit can provide a summary that includes detailed information. Furthermore, if the user is in a hurry, the providing unit can provide a summary quickly. In this way, by adjusting the method of providing a summary according to the user's emotion, more appropriate provision is possible.

[0103] The providing unit can select the optimal providing method by referring to the user's past usage history when providing the data. The providing unit selects the optimal providing method by referring to the user's past usage history. For example, the providing unit selects the optimal providing method based on the summary format used by the user in the past. The providing unit can also predict and provide a preferred summary format from the user's past usage history. Furthermore, the providing unit can analyze the user's past usage history and select the most efficient providing method. In this way, the optimal providing method can be selected by referring to the past usage history.

[0104] The providing unit can estimate the user's emotion and adjust the timing of providing the summary based on the estimated user's emotion. The providing unit can estimate the user's emotion and adjust the timing of providing the summary based on the estimated user's emotion. For example, the providing unit can provide the summary quickly when the user is nervous. The providing unit can also provide the summary at an appropriate time when the user is relaxed. Furthermore, the providing unit can also provide the summary immediately when the user is in a hurry. In this way, by adjusting the timing of providing the summary according to the user's emotion, it is possible to provide the summary at a more appropriate time.

[0105] The providing unit can select the optimal providing method by taking into consideration the device information of the user when providing the summary. The providing unit selects the optimal providing method by taking into consideration the device information of the user. For example, if the user is using a smartphone, the providing unit can provide a summary that is tailored to the screen size. Also, if the user is using a tablet, the providing unit can provide a summary that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the providing unit can provide a concise and highly visible summary. In this way, the optimal providing method can be selected by taking into consideration the device information.

[0106] The noise canceling unit can estimate the user's emotions and adjust the noise canceling intensity based on the estimated user's emotions. The noise canceling unit can estimate the user's emotions and adjust the noise canceling intensity based on the estimated user's emotions. For example, if the user is feeling stressed, the noise canceling unit can increase the noise canceling intensity to block out external sounds. Also, if the user is relaxed, the noise canceling unit can perform processing at normal noise canceling intensity. Furthermore, if the user is in a hurry, the noise canceling unit can quickly perform noise canceling and provide the results. This allows for more appropriate noise canceling by adjusting the noise canceling intensity according to the user's emotions.

[0107] The noise canceling unit can apply different noise canceling algorithms depending on the content of the meeting during noise cancellation. The noise canceling unit applies different noise canceling algorithms depending on the content of the meeting. For example, in a technical meeting, the noise canceling unit applies a noise canceling algorithm that emphasizes technical terms. In addition, in a business meeting, the noise canceling unit can apply a noise canceling algorithm that emphasizes points related to decision-making. Furthermore, in an educational meeting, the noise canceling unit can apply a noise canceling algorithm that emphasizes learning content. In this way, by applying a noise canceling algorithm depending on the content of the meeting, the accuracy of noise canceling is improved.

[0108] The noise canceling unit can estimate the user's emotions and adjust the timing of noise canceling based on the estimated user's emotions. The noise canceling unit estimates the user's emotions and adjusts the timing of noise canceling based on the estimated user's emotions. For example, the noise canceling unit performs noise canceling quickly when the user is nervous. The noise canceling unit can also perform noise canceling at an appropriate timing when the user is relaxed. Furthermore, the noise canceling unit can also perform noise canceling immediately when the user is in a hurry. In this way, more appropriate noise canceling is possible by adjusting the timing of noise canceling according to the user's emotions.

[0109] The noise canceling unit can select the optimal noise canceling method by taking into account the environmental sounds of the meeting when performing noise cancellation. The noise canceling unit selects the optimal noise canceling method by taking into account the environmental sounds of the meeting. For example, the noise canceling unit analyzes the environmental sounds of the meeting room and selects the optimal noise canceling method. In addition, the noise canceling unit can perform noise cancellation by taking into account background sounds in the case of an online meeting. Furthermore, the noise canceling unit can perform noise cancellation by taking into account wind and traffic sounds in the case of an outdoor meeting. In this way, the optimal noise canceling method can be selected by taking into account the environmental sounds.

[0110] The speaker separation unit can estimate the user's emotion and adjust the accuracy of speaker separation based on the estimated user's emotion. The speaker separation unit can estimate the user's emotion and adjust the accuracy of speaker separation based on the estimated user's emotion. For example, if the user is feeling stressed, the speaker separation unit can increase the accuracy of speaker separation to reduce misrecognition. Furthermore, if the user is relaxed, the speaker separation unit can perform processing with normal speaker separation accuracy. Furthermore, if the user is in a hurry, the speaker separation unit can quickly perform speaker separation and provide the results. In this way, more appropriate speaker separation is possible by adjusting the accuracy of speaker separation according to the user's emotion.

[0111] The speaker separation unit can apply different speaker separation algorithms depending on the content of the conference when separating speakers. The speaker separation unit applies different speaker separation algorithms depending on the content of the conference. For example, in the case of a technical conference, the speaker separation unit applies a speaker separation algorithm that emphasizes technical terms. In addition, in the case of a business conference, the speaker separation unit can also apply a speaker separation algorithm that emphasizes points related to decision-making. Furthermore, in the case of an educational conference, the speaker separation unit can apply a speaker separation algorithm that emphasizes learning content. In this way, by applying a speaker separation algorithm depending on the content of the conference, the accuracy of speaker separation is improved.

[0112] The speaker separation unit can estimate the user's emotion and adjust the order in which speaker separation results are displayed based on the estimated user's emotion. The speaker separation unit estimates the user's emotion and adjusts the order in which speaker separation results are displayed based on the estimated user's emotion. For example, if the user is nervous, the speaker separation unit can prioritize displaying important utterances. Furthermore, if the user is relaxed, the speaker separation unit can also display detailed utterance content. Furthermore, if the user is in a hurry, the speaker separation unit can display utterance content that focuses on the main points. In this way, by adjusting the order in which speaker separation results are displayed based on the user's emotion, more appropriate display is possible.

[0113] The speaker separation unit can perform speaker separation by taking into account attribute information of the conference participants. The speaker separation unit performs speaker separation by taking into account attribute information of the conference participants. For example, the speaker separation unit prioritizes separation of important utterances based on the participants' job positions. The speaker separation unit can also prioritize separation of related utterances based on the participants' fields of expertise. Furthermore, the speaker separation unit can separate the content of frequently uttered participants in detail based on the frequency of their utterances. In this way, important utterances can be efficiently separated by taking into account the participants' attribute information.

[0114] The keyword extraction unit can estimate the user's emotions and adjust the keyword extraction method based on the estimated user's emotions. The keyword extraction unit can estimate the user's emotions and adjust the keyword extraction method based on the estimated user's emotions. For example, if the user is feeling stressed, the keyword extraction unit can prioritize extracting important keywords. Also, if the user is relaxed, the keyword extraction unit can extract detailed keywords. Furthermore, if the user is in a hurry, the keyword extraction unit can extract only the main points. In this way, by adjusting the keyword extraction method according to the user's emotions, more appropriate keywords can be extracted.

[0115] The keyword extraction unit can apply different keyword extraction algorithms depending on the content of the meeting when extracting keywords. The keyword extraction unit applies different keyword extraction algorithms depending on the content of the meeting. For example, in the case of a technical meeting, the keyword extraction unit applies a keyword extraction algorithm that emphasizes technical terms. In addition, in the case of a business meeting, the keyword extraction unit can also apply a keyword extraction algorithm that emphasizes points related to decision-making. Furthermore, in the case of an educational meeting, the keyword extraction unit can apply a keyword extraction algorithm that emphasizes learning content. In this way, by applying a keyword extraction algorithm depending on the content of the meeting, the accuracy of keyword extraction is improved.

[0116] The keyword extraction unit can estimate the user's emotions and adjust the order in which the keyword extraction results are displayed based on the estimated user emotions. The keyword extraction unit estimates the user's emotions and adjusts the order in which the keyword extraction results are displayed based on the estimated user emotions. For example, if the user is nervous, the keyword extraction unit can prioritize displaying important keywords. Furthermore, if the user is relaxed, the keyword extraction unit can also display detailed keywords. Furthermore, if the user is in a hurry, the keyword extraction unit can display keywords that focus on the main points. In this way, by adjusting the order in which the keyword extraction results are displayed based on the user's emotions, more appropriate display is possible.

[0117] The keyword extraction unit can improve the accuracy of keyword extraction by referring to data related to the meeting when extracting keywords. The keyword extraction unit improves the accuracy of keyword extraction by referring to data related to the meeting. For example, the keyword extraction unit improves the accuracy of keyword extraction by referring to data related to the theme of the meeting. The keyword extraction unit can also improve accuracy by incorporating data cited by participants into the extraction. Furthermore, the keyword extraction unit can improve the accuracy of keyword extraction by referring to the latest data related to the content of the meeting. In this way, the accuracy of keyword extraction is improved by referring to related data.

[0118] The topic modeling unit can estimate the user's emotions and adjust the topic modeling method based on the estimated user's emotions. The topic modeling unit estimates the user's emotions and adjusts the topic modeling method based on the estimated user's emotions. For example, when the user is feeling stressed, the topic modeling unit prioritizes modeling of important topics. Furthermore, when the user is relaxed, the topic modeling unit can also model detailed topics. Furthermore, when the user is in a hurry, the topic modeling unit can model only the main points. In this way, by adjusting the topic modeling method according to the user's emotions, more appropriate topics can be modeled.

[0119] During topic modeling, the topic modeling unit can apply different topic modeling algorithms depending on the content of the meeting. The topic modeling unit applies different topic modeling algorithms depending on the content of the meeting. For example, in the case of a technical meeting, the topic modeling unit applies a topic modeling algorithm that emphasizes technical terms. In addition, in the case of a business meeting, the topic modeling unit can apply a topic modeling algorithm that emphasizes points related to decision-making. Furthermore, in the case of an educational meeting, the topic modeling unit can apply a topic modeling algorithm that emphasizes learning content. In this way, by applying a topic modeling algorithm depending on the content of the meeting, the accuracy of topic modeling is improved.

[0120] The topic modeling unit can estimate the user's emotions and adjust the order in which the topic modeling results are displayed based on the estimated user's emotions. The topic modeling unit estimates the user's emotions and adjusts the order in which the topic modeling results are displayed based on the estimated user's emotions. For example, if the user is nervous, the topic modeling unit can prioritize displaying important topics. Also, if the user is relaxed, the topic modeling unit can display detailed topics. Furthermore, if the user is in a hurry, the topic modeling unit can display topics that focus on the main points. In this way, by adjusting the order in which the topic modeling results are displayed according to the user's emotions, more appropriate display is possible.

[0121] During topic modeling, the topic modeling unit can improve the accuracy of topic modeling by referring to data related to the conference. The topic modeling unit improves the accuracy of topic modeling by referring to data related to the conference. For example, the topic modeling unit improves the accuracy of topic modeling by referring to data related to the theme of the conference. The topic modeling unit can also incorporate data cited by participants into the modeling to improve accuracy. Furthermore, the topic modeling unit can improve the accuracy of topic modeling by referring to the latest data related to the content of the conference. In this way, the accuracy of topic modeling is improved by referring to related data. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned analysis unit, recognition unit, extraction unit, generation unit, and provision unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The recognition unit is realized, for example, by the specific processing unit 290 of the data processing device 12. The extraction unit is realized, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12. The provision unit is realized, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned analysis unit, recognition unit, extraction unit, generation unit, and provision unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The recognition unit is realized, for example, by the specific processing unit 290 of the data processing device 12. The extraction unit is realized, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12. The provision unit is realized, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, recognition unit, extraction unit, generation unit, and provision unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The recognition unit is realized, for example, by the specific processing unit 290 of the data processing device 12. The extraction unit is realized, for example, by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12. The provision unit is realized, for example, by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, recognition unit, extraction unit, generation unit, and provision unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The recognition unit is realized, for example, by the specific processing unit 290 of the data processing device 12. The extraction unit is realized, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12. The provision unit is realized, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12.

[0122] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0123] The analysis unit can analyze the content of speech made by meeting participants in real time and estimate the emotional tone of the speech. For example, the analysis unit can classify the emotions of speech into positive, negative, and neutral, and grasp the progress of the meeting. The analysis unit can also visualize the atmosphere of the meeting in real time based on the emotional tone of the speech. Furthermore, the analysis unit can detect changes in the emotional tone and identify important turning points in the meeting. This allows for a more detailed understanding of the progress of the meeting and enables appropriate responses.

[0124] The recognition unit can analyze the content of speech made by meeting participants and infer the intention of the speech. For example, the recognition unit can classify the intention of speech, such as a question, suggestion, or opinion, based on the content of speech. The recognition unit can also support the progress of the meeting based on the intention of the speech. Furthermore, the recognition unit can automatically provide related information based on the intention of the speech. This helps the meeting proceed smoothly and deepens participants' understanding.

[0125] The extraction unit can analyze the content of comments made by meeting participants and evaluate the importance of the comments. For example, the extraction unit can extract important keywords and phrases from the content of the comments and score the importance of the comments. The extraction unit can also generate a summary of the meeting based on the importance of the comments. Furthermore, the extraction unit can support the progress of the meeting based on the importance of the comments. This allows you to efficiently grasp the main points of the meeting and not miss any important information.

[0126] The generation unit can analyze the content of statements made by meeting participants and generate summaries based on the emotional tone of the statements. For example, the generation unit can generate summaries that emphasize positive statements. The generation unit can also generate summaries that include negative statements. Furthermore, the generation unit can also generate summaries that focus on neutral statements. This makes it possible to provide summaries that reflect the atmosphere of the meeting.

[0127] The providing unit can analyze the content of statements made by meeting participants and provide a summary based on the intent of the statements. For example, the providing unit can provide a summary that focuses on answers to questions. The providing unit can also provide a summary that includes opinions on proposals. Furthermore, the providing unit can also provide a summary that reflects the content of the exchange of opinions. This makes it easier to understand the content of the meeting.

[0128] The analysis unit can analyze the content of comments made by meeting participants and support the progress of the meeting based on the emotional tone of the comments. For example, if there are a lot of positive comments, the analysis unit can make suggestions to make the meeting progress smoothly. Also, if there are a lot of negative comments, the analysis unit can make suggestions to improve the atmosphere of the meeting. Furthermore, if there are a lot of neutral comments, the analysis unit can make suggestions to maintain the progress of the meeting. This makes it possible to more effectively support the progress of the meeting.

[0129] The recognition unit can analyze the content of speech made by meeting participants and provide relevant information based on the intent of the speech. For example, the recognition unit can automatically provide answers to questions, provide relevant information for suggestions, and provide information related to the exchange of opinions. This helps the meeting proceed smoothly and deepens participants' understanding.

[0130] The extraction unit can analyze the content of statements made by meeting participants and extract key points based on the emotional tone of the statements. For example, it can prioritize extraction of positive statements. It can also extract key points that include negative statements. It can also extract key points that mainly focus on neutral statements. This makes it possible to provide key points that reflect the atmosphere of the meeting.

[0131] The generation unit can analyze the content of statements made by meeting participants and generate summaries based on the intent of those statements. For example, it can generate summaries that focus on answers to questions. It can also generate summaries that include opinions on proposals. It can also generate summaries that reflect the content of the exchange of opinions. This makes the content of the meeting easier to understand.

[0132] The providing unit can analyze the content of speeches made by meeting participants and provide summaries based on the emotional tone of the speeches. For example, it can provide summaries that emphasize positive speeches, summaries that include negative speeches, or summaries that focus on neutral speeches. This makes it possible to provide summaries that reflect the atmosphere of the meeting.

[0133] The processing flow of the second embodiment will be briefly explained below.

[0134] Step 1: The analysis unit analyzes the recorded video and audio. The analysis unit improves the quality of the audio data using a noise canceling unit and a speaker separation unit. For example, the noise canceling unit removes background noise and improves the clarity of the audio data. The speaker separation unit separates the audio from multiple speakers and extracts the audio data of each speaker. Step 2: The recognition unit converts the voice data into text data using a voice recognition model that uses the generation AI. For example, the generation AI takes voice data as input and outputs text data. The generation AI has learned a large amount of voice data and is capable of highly accurate voice recognition. Step 3: The extraction unit uses the keyword extraction unit and topic modeling unit to extract important points from the text data. For example, the keyword extraction unit extracts frequently occurring keywords from the text data. The topic modeling unit classifies the text data by topic and extracts important topics. Step 4: The generation unit uses a summary generation model with generative AI to generate a summary of the minutes. For example, the generative AI takes the extracted points as input and outputs a summary. The generative AI has learned from a large amount of text data, enabling it to generate summaries with high accuracy. Step 5: The providing unit provides the generated summary to the user. For example, the providing unit may display the summary through a web application or a mobile application. The providing unit may also send the summary by email.

[0135] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0136] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0137] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0138] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0139] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0140] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0141] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0142] 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.

[0143] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0145] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0146] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0147] 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.

[0148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0149] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0150] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0151] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0153] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0154] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0155] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0156] 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.

[0157] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0158] 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.

[0159] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0160] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0161] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0162] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0163] 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.

[0164] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0165] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0166] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0167] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0168] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0169] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0170] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0171] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0172] 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.

[0173] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0174] 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.

[0175] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0176] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0177] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0178] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0179] 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.

[0180] 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.

[0181] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0182] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0183] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0184] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0185] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0186] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0187] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0188] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0189] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0190] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0191] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0192] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0193] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0194] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0195] 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.

[0196] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0197] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0198] 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.

[0199] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0200] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0201] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0202] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0203] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0204] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0205] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0206] [Explanation of symbols]

[0207] 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. an analysis unit that analyzes the recorded video and audio; a recognition unit that recognizes the voice data analyzed by the analysis unit; an extraction unit that extracts important points from the text data recognized by the recognition unit; a generation unit that generates a summary based on the points extracted by the extraction unit; a providing unit that provides the summary generated by the generating unit. A system characterized by:

2. Equipped with a noise canceling unit that performs noise cancellation 2. The system of claim 1.

3. Equipped with a speaker separation unit that performs speaker separation 2. The system of claim 1.

4. Equipped with a keyword extraction unit that extracts keywords 2. The system of claim 1.

5. Equipped with a topic modeling section that performs topic modeling 2. The system of claim 1.

6. The recognition unit Converting voice data into text data using a speech recognition model with generative AI 2. The system of claim 1.

7. The generation unit Generate a summary of meeting minutes using a summary generation model using generative AI 2. The system of claim 1.

8. The analysis unit Estimate user emotions and adjust analysis priorities based on the estimated user emotions 2. The system of claim 1.

9. The analysis unit During analysis, different analysis algorithms are applied depending on the content of the meeting.

2. The system of claim 1.

Images