System

Abstract

An object of the system according to the embodiment is to improve efficiency and accuracy of creating minutes of a meeting.SOLUTION: A system according to an embodiment includes a collection unit, an analysis unit, and a generation unit. The collection unit reads a voice of the meeting in real time and records the voice as voice data. The analysis unit analyzes the voice data recorded by the collection unit and summarizes the content of the conference. The generation unit creates a minutes based on the content summarized by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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 can make creating meeting minutes time-consuming, labor-intensive, and inaccurate.

[0005] The system according to the embodiment aims to improve the efficiency and accuracy of creating meeting minutes. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, and a generation unit. The collection unit reads the audio of the meeting in real time and records it as audio data. The analysis unit analyzes the audio data recorded by the collection unit and summarizes the content of the meeting. The generation unit creates minutes based on the content summarized by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can improve the efficiency and accuracy of creating meeting minutes. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A meeting summarization system according to an embodiment of the present invention reads meeting audio in real time, analyzes it using a generation AI, and automatically creates meeting minutes. The meeting summarization system reads meeting audio in real time and records it as audio data. Next, the generation AI analyzes the audio data and summarizes the meeting content. Finally, the generation AI creates meeting minutes based on the summarized content. For example, the meeting summarization system transcribes statements made during a meeting in real time and saves them as text data. Next, the generation AI analyzes the audio data and extracts important points and key points of discussion. For example, it summarizes the meeting agenda, decisions, action items, etc. Finally, the generation AI organizes the summarized content and outputs it as minutes. For example, it automatically creates minutes including the meeting start time, participants, agenda, decisions, action items, etc. This allows the meeting summarization system to significantly reduce the effort required to create meeting minutes and improve accuracy. This allows the meeting summarization system to significantly reduce the effort required to create meeting minutes and improve accuracy. For example, important statements and decisions made during a meeting are recorded without omission, making them useful for reviewing later. It also contributes to meeting efficiency, as audio is read in real time during the meeting and summarized by the AI ​​generator, helping the meeting proceed smoothly. For example, by checking the minutes during the meeting, participants can proceed without losing track of the direction of the discussion.

[0029] A meeting summarization system according to an embodiment includes a collection unit, an analysis unit, and a generation unit. The collection unit reads the audio of a meeting in real time and records it as audio data. The collection unit converts the content of statements made during the meeting into text data, for example, using speech recognition technology. The collection unit can also transcribe statements made during the meeting in real time and save the text data. For example, the collection unit accurately converts the content of statements made during the meeting into text data using speech recognition technology. The analysis unit uses a generation AI to analyze the audio data recorded by the collection unit and summarize the content of the meeting. For example, the analysis unit analyzes the audio data and extracts important points and key points of discussion. For example, the generation AI analyzes the audio data and summarizes the meeting agenda, decisions, action items, etc. The generation unit uses the generation AI to create minutes based on the content summarized by the analysis unit. For example, the generation unit organizes the summarized content and outputs the minutes. For example, the generation unit automatically creates minutes including the start time of the meeting, participants, agenda, decisions, action items, etc. As a result, the meeting summarization system of the embodiment can collect and analyze meeting audio in real time and automatically create minutes, thereby significantly reducing the amount of work required to create minutes and improving accuracy.

[0030] The collection unit can convert the contents of utterances made during a meeting into text data using speech recognition technology. The collection unit can convert the contents of utterances made during a meeting into text data using, for example, speech recognition technology. For example, the collection unit can use speech recognition technology that uses deep learning to convert the contents of utterances made during a meeting into text data with high accuracy. The collection unit can also use speech recognition technology that uses HMM (hidden Markov model) to convert the contents of utterances made during a meeting into text data. Furthermore, the collection unit can use speech recognition technology to transcribe the contents of utterances made during a meeting in real time and save the transcribed text as text data. For example, the collection unit can use speech recognition software to transcribe the contents of utterances made during a meeting in real time. In this way, the contents of utterances made during a meeting can be accurately converted into text data using speech recognition technology. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or can be performed without AI. For example, the collection unit can input speech data into a generation AI and cause the generation AI to generate text data from the speech data.

[0031] The analysis unit can analyze the audio data and extract important points and key points of the discussion. The analysis unit, for example, analyzes the audio data and extracts important points and key points of the discussion. For example, the analysis unit extracts important points based on frequently occurring keywords. The analysis unit can also extract important points based on emphasized parts of statements. Furthermore, the analysis unit can extract key points of the discussion based on the relevance of the topics. For example, the analysis unit analyzes the relevance of the content of statements and extracts key points of the discussion. In this way, the contents of the meeting can be efficiently summarized by extracting important points and key points of the discussion. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input audio data to a generation AI and have the generation AI extract important points and key points of the discussion.

[0032] The generation unit can automatically create minutes including the meeting start time, participants, agenda, decisions, and action items. The generation unit automatically creates minutes including, for example, the meeting start time, participants, agenda, decisions, and action items. For example, the generation unit records the meeting start time and includes it in the minutes. The generation unit can also list the meeting participants and include it in the minutes. The generation unit can also organize the meeting agenda and include it in the minutes. For example, the generation unit can summarize the meeting decisions and include them in the minutes. The generation unit can also list the meeting action items and include them in the minutes. This allows minutes including important meeting information to be automatically created, thereby improving the accuracy and efficiency of the minutes. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the summarized content into a generation AI and have the generation AI create the minutes.

[0033] The collection unit can analyze the speech frequency of meeting participants and prioritize collection of speech based on specific criteria. For example, the collection unit can prioritize collection of speech from participants who speak frequently to avoid missing important information. The collection unit can also pay particular attention to collecting speech from participants who speak infrequently to cover all opinions. Furthermore, the collection unit can analyze changes in speech frequency in real time to avoid missing the timing when important speech is made. In this way, by analyzing speech frequency, important speech can be collected without missing it. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input speech frequency data to a generation AI and cause the generation AI to prioritize collection of important speech.

[0034] When collecting voice data, the collection unit can dynamically change the collection method depending on the progress of the conference. For example, if the conference is progressing quickly, the collection unit can increase the frequency of voice data collection to avoid missing important information. Also, if the conference is progressing slowly, the collection unit can decrease the frequency of voice data collection to reduce unnecessary data. Furthermore, if the conference is progressing irregularly, the collection unit can dynamically change the collection method depending on the progress to optimally collect data. This makes it possible to optimally collect data by dynamically changing the collection method depending on the progress of the conference. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input conference progress data to the generation AI and cause the generation AI to dynamically change the collection method.

[0035] The collection unit can apply filtering technology to remove background noise when collecting audio data. For example, the collection unit can remove background noise in a conference room in real time to collect clear audio data. The collection unit can also filter out sounds other than the participants' speech and collect only important speech. Furthermore, the collection unit can remove external noise to accurately collect the contents of the meeting. In this way, by removing background noise, clear audio data can be collected. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input audio data to a generation AI and have the generation AI remove background noise.

[0036] When collecting audio data, the collection unit can select an appropriate collection method depending on the location and environment of the meeting. For example, the collection unit adjusts the microphone placement depending on the size of the conference room to collect optimal audio data. The collection unit can also analyze the ambient sounds of the meeting and apply a noise canceling function to collect audio data. Furthermore, in the case of an online meeting, the collection unit can also collect the voices of participants individually to obtain clear audio data. This allows optimal audio data to be collected by selecting the optimal collection method depending on the location and environment of the meeting. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data about the location and environment of the meeting into the generation AI and cause the generation AI to select the optimal collection method.

[0037] When collecting audio data, the collection unit can customize the collected content based on the positions and expertise of the meeting participants. For example, the collection unit can prioritize collecting comments from participants with higher positions to avoid missing important decisions. The collection unit can also pay particular attention to collecting comments from participants with specialized knowledge to accurately record technical discussions. Furthermore, the collection unit can customize the collected content based on the positions and expertise of the participants to cover the key points of the meeting. In this way, by customizing the collected content based on the positions and expertise of the participants, important information can be collected without missing any important information. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the positions and expertise data of the participants into the generation AI and have the generation AI customize the collected content.

[0038] The collection unit can prioritize collecting keywords related to the meeting agenda when collecting audio data. For example, the collection unit can detect keywords related to the meeting agenda in real time and prioritize collecting important utterances. The collection unit can also pay particular attention to collecting utterances containing keywords related to the agenda so as not to miss the key points of the meeting. Furthermore, the collection unit can customize the collected content based on keywords related to the agenda to grasp the overall picture of the meeting. In this way, by prioritizing the collection of keywords related to the agenda, it is possible to collect the key points of the meeting without missing them. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input keyword data related to the agenda to a generation AI and cause the generation AI to customize the collected content based on the keywords.

[0039] When analyzing the audio data, the analysis unit can dynamically change the analysis algorithm depending on the progress of the conference. For example, if the conference is progressing quickly, the analysis unit can speed up the analysis algorithm and perform analysis in real time. Furthermore, if the conference is progressing slowly, the analysis unit can adjust the analysis algorithm and perform a more detailed analysis. Furthermore, if the conference is progressing irregularly, the analysis unit can dynamically change the analysis algorithm depending on the progress and perform an optimal analysis. This makes it possible to perform an optimal analysis by dynamically changing the analysis algorithm depending on the progress of the conference. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input conference progress data to the generation AI and cause the generation AI to dynamically change the analysis algorithm.

[0040] When analyzing the audio data, the analysis unit can classify the content of speech made by conference participants and determine the priority of analysis according to its importance. For example, the analysis unit can classify the content of speech in real time and prioritize analysis of important speech. The analysis unit can also analyze the importance of the content of speech so as not to miss important points. Furthermore, the analysis unit can classify the content of speech and dynamically change the priority of analysis according to its importance. In this way, by classifying the content of speech and determining the priority of analysis according to its importance, it is possible to analyze without missing important points. Some or all of the above-described processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input speech content data to a generation AI and have the generation AI determine the analysis priority based on the importance.

[0041] When analyzing the audio data, the analysis unit can apply different analysis methods to each agenda item of the meeting. For example, the analysis unit selects the optimal analysis method for each agenda item to ensure that important points are not missed. The analysis unit can also dynamically change the analysis method depending on the agenda item to perform optimal analysis. Furthermore, the analysis unit can apply different analysis methods to each agenda item to grasp the overall picture of the meeting. In this way, by applying different analysis methods to each agenda item, the overall picture of the meeting can be grasped. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input agenda data into the generation AI and have the generation AI apply different analysis methods to each agenda item.

[0042] When analyzing the audio data, the analysis unit can translate the speech content of the conference participants in real time and perform multilingual analysis. For example, the analysis unit can translate the speech content in real time so that participants who speak different languages ​​can understand it. The analysis unit can also display the speech content in multiple languages, making it possible to handle international conferences. Furthermore, the analysis unit can also translate the speech content in real time and provide the analysis results in multiple languages. This makes it possible to handle international conferences by translating the speech content in real time. Some or all of the above-mentioned processing in the analysis unit can be performed using, or without, a generation AI, for example. For example, the analysis unit can input speech content data to a generation AI and have the generation AI perform real-time translation and multilingual analysis.

[0043] When analyzing the audio data, the analysis unit can update the analysis results in real time according to the progress of the conference. For example, the analysis unit updates the analysis results in real time according to the progress of the conference to provide the latest information. The analysis unit can also analyze the progress of the conference and update important points in real time. Furthermore, the analysis unit can dynamically update the analysis results according to the progress of the conference to provide optimal information. In this way, the analysis results can be updated in real time according to the progress of the conference, thereby providing the latest information. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input conference progress data to the generation AI and cause the generation AI to perform real-time updates of the analysis results.

[0044] When analyzing the audio data, the analysis unit can summarize the speech content of the meeting participants and emphasize important points. For example, the analysis unit can summarize the speech content and display it with important points emphasized. The analysis unit can also summarize the speech content in real time to ensure that important points are not overlooked. Furthermore, the analysis unit can summarize the speech content and display it with important points emphasized visually. In this way, by summarizing the speech content and emphasizing important points, the gist of the meeting can be grasped without missing anything. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input speech content data into a generation AI and have the generation AI perform the summarization and emphasize important points.

[0045] The generation unit can dynamically change the structure of the minutes based on the summarized content in accordance with the progress of the meeting. For example, the generation unit dynamically changes the structure of the minutes in accordance with the progress of the meeting to emphasize important points. The generation unit can also analyze the progress of the meeting and optimize the structure of the minutes. Furthermore, the generation unit can dynamically change the structure of the minutes in accordance with the progress of the meeting, taking into account the overall balance. In this way, important points can be emphasized by dynamically changing the structure of the minutes in accordance with the progress of the meeting. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input summarized content data into the generation AI and cause the generation AI to dynamically change the structure of the minutes.

[0046] The generation unit can create different minutes for each participant of the meeting based on the summarized content. For example, the generation unit can create minutes from different perspectives for each participant to meet individual needs. The generation unit can also customize the content of the minutes according to the participant's position or expertise. Furthermore, the generation unit can create different minutes for each participant and provide them in a format that is easy for everyone to understand. This makes it possible to meet individual needs by creating different minutes for each participant. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input summarized content data into a generation AI and have the generation AI create different minutes for each participant.

[0047] The generation unit can create different minutes for each meeting agenda based on the summarized content. For example, the generation unit can create different minutes for each agenda and emphasize important points. The generation unit can also change the structure of the minutes depending on the agenda and provide them in the optimal format. Furthermore, the generation unit can create different minutes for each agenda and consider the overall balance. This allows the overall picture of the meeting to be grasped by creating different minutes for each agenda. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the summarized content data into a generation AI and have the generation AI create different minutes for each agenda.

[0048] The generation unit can determine the priority of the minutes based on the summarized content in accordance with the progress of the meeting. For example, the generation unit prioritizes recording important topics in the minutes as the meeting progresses. The generation unit can also analyze the progress of the meeting and prioritize reflecting important points in the minutes. Furthermore, the generation unit can dynamically change the priority of the minutes as the meeting progresses and provide optimal information. This allows important information to be recorded preferentially by determining the priority of the minutes in accordance with the progress of the meeting. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input summarized content data into the generation AI and have the generation AI determine the priority of the minutes.

[0049] The generation unit can customize the content of the minutes based on the summarized content according to the positions and expertise of the meeting participants. For example, the generation unit can create minutes that emphasize important decisions for participants with higher positions. The generation unit can also create minutes that include technical details for participants with specialized knowledge. Furthermore, the generation unit can customize the content of the minutes according to the positions and expertise and provide them in a format that is easy for everyone to understand. In this way, the content of the minutes can be customized according to the positions and expertise of the participants, so that they can be provided in a format that is easy for everyone to understand. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input summarized content data into a generation AI and have the generation AI customize the minutes based on the positions and expertise.

[0050] The generation unit can highlight keywords related to the meeting agenda based on the summarized content. For example, the generation unit can highlight keywords related to the agenda to visually highlight important points. The generation unit can also organize the content of the minutes based on keywords related to the agenda and provide them in an easy-to-understand format. Furthermore, the generation unit can highlight keywords related to the agenda to prevent important information from being overlooked. By highlighting keywords related to the agenda, important information can be understood without missing anything. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the generation unit can input summarized content data to a generation AI and have the generation AI perform keyword highlighting.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The collection unit can translate the speech content of conference participants in real time and perform multilingual collection. For example, the collection unit can translate the speech content in real time so that it can be understood by participants who speak different languages. The collection unit can also display the speech content in multiple languages ​​and support international conferences. Furthermore, the collection unit can translate the speech content in real time and provide collected data in multiple languages. This makes it possible to support international conferences by translating the speech content in real time. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the collection unit can input speech content data to a generation AI and have the generation AI perform real-time translation and multilingual collection.

[0053] The generation unit can dynamically change the structure of the minutes according to the progress of the meeting. For example, the generation unit can dynamically change the structure of the minutes according to the progress of the meeting to emphasize important points. The generation unit can also analyze the progress of the meeting and optimize the structure of the minutes. Furthermore, the generation unit can dynamically change the structure of the minutes according to the progress of the meeting and take the overall balance into consideration. In this way, important points can be emphasized by dynamically changing the structure of the minutes according to the progress of the meeting. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input summarized content data into the generation AI and cause the generation AI to dynamically change the structure of the minutes.

[0054] The collection unit can customize the collected content based on the positions and expertise of the meeting participants. For example, the collection unit can prioritize collecting comments from participants with higher positions to avoid missing important decisions. The collection unit can also pay particular attention to collecting comments from participants with specialized knowledge to accurately record technical discussions. Furthermore, the collection unit can customize the collected content based on the positions and expertise of the participants to cover all key points of the meeting. In this way, by customizing the collected content based on the positions and expertise of the participants, important information can be collected without missing any important information. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the positions and specialized knowledge data of the participants into the generation AI and have the generation AI customize the collected content.

[0055] The analysis unit can classify the content of statements made by meeting participants in real time and determine the priority of analysis according to their importance. For example, the analysis unit can classify the content of statements in real time and prioritize analysis of important statements. The analysis unit can also analyze the importance of the content of statements and perform analysis so as not to miss important points. Furthermore, the analysis unit can classify the content of statements and dynamically change the priority of analysis according to their importance. In this way, by classifying the content of statements and determining the priority of analysis according to their importance, it is possible to analyze without missing important points. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the content data of statements to a generation AI and have the generation AI determine the analysis priority based on the importance.

[0056] The generation unit can create different minutes for each participant in the meeting based on the summarized content. For example, minutes can be created from different perspectives for each participant to meet their individual needs. The generation unit can also customize the content of the minutes according to the participant's position or expertise. Furthermore, the generation unit can create different minutes for each participant and provide them in a format that is easy for everyone to understand. This allows individual needs to be met by creating different minutes for each participant. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the summarized content data into the generation AI and have the generation AI create different minutes for each participant.

[0057] When collecting audio data, the collection unit can select an appropriate collection method depending on the location and environment of the meeting. For example, the collection unit adjusts the microphone placement depending on the size of the conference room to collect optimal audio data. The collection unit can also analyze the ambient sounds of the meeting and apply a noise canceling function to collect audio data. Furthermore, in the case of an online meeting, the collection unit can also collect the voices of participants individually to obtain clear audio data. This allows optimal audio data to be collected by selecting the optimal collection method depending on the location and environment of the meeting. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data about the location and environment of the meeting into the generation AI and have the generation AI select the optimal collection method.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The collection unit reads the audio of the meeting in real time and records it as audio data. The collection unit uses speech recognition technology to convert what is said in the meeting into text data. The collection unit can also transcribe what is said during the meeting in real time and save it as text data. Step 2: The analysis unit uses the generation AI to analyze the audio data recorded by the collection unit and summarize the contents of the meeting. The analysis unit analyzes the audio data and extracts important points and key points of discussion. For example, the generation AI analyzes the audio data and summarizes the meeting agenda, decisions, action items, etc. Step 3: The generation unit uses the generation AI to create minutes based on the content summarized by the analysis unit. The generation unit organizes the summarized content and outputs it as minutes. For example, the generation unit automatically creates minutes that include the meeting start time, participants, agenda, decisions, action items, etc.

[0060] (Example 2) A meeting summarization system according to an embodiment of the present invention reads meeting audio in real time, analyzes it using a generation AI, and automatically creates meeting minutes. The meeting summarization system reads meeting audio in real time and records it as audio data. Next, the generation AI analyzes the audio data and summarizes the meeting content. Finally, the generation AI creates meeting minutes based on the summarized content. For example, the meeting summarization system transcribes statements made during a meeting in real time and saves them as text data. Next, the generation AI analyzes the audio data and extracts important points and key points of discussion. For example, it summarizes the meeting agenda, decisions, action items, etc. Finally, the generation AI organizes the summarized content and outputs it as minutes. For example, it automatically creates minutes including the meeting start time, participants, agenda, decisions, action items, etc. This allows the meeting summarization system to significantly reduce the effort required to create meeting minutes and improve accuracy. This allows the meeting summarization system to significantly reduce the effort required to create meeting minutes and improve accuracy. For example, important statements and decisions made during a meeting are recorded without omission, making them useful for reviewing later. It also contributes to meeting efficiency, as audio is read in real time during the meeting and summarized by the AI ​​generator, helping the meeting proceed smoothly. For example, by checking the minutes during the meeting, participants can proceed without losing track of the direction of the discussion.

[0061] A meeting summarization system according to an embodiment includes a collection unit, an analysis unit, and a generation unit. The collection unit reads the audio of a meeting in real time and records it as audio data. The collection unit converts the content of statements made during the meeting into text data, for example, using speech recognition technology. The collection unit can also transcribe statements made during the meeting in real time and save the text data. For example, the collection unit accurately converts the content of statements made during the meeting into text data using speech recognition technology. The analysis unit uses a generation AI to analyze the audio data recorded by the collection unit and summarize the content of the meeting. For example, the analysis unit analyzes the audio data and extracts important points and key points of discussion. For example, the generation AI analyzes the audio data and summarizes the meeting agenda, decisions, action items, etc. The generation unit uses the generation AI to create minutes based on the content summarized by the analysis unit. For example, the generation unit organizes the summarized content and outputs the minutes. For example, the generation unit automatically creates minutes including the start time of the meeting, participants, agenda, decisions, action items, etc. As a result, the meeting summarization system of the embodiment can collect and analyze meeting audio in real time and automatically create minutes, thereby significantly reducing the amount of work required to create minutes and improving accuracy.

[0062] The collection unit can convert the contents of utterances made during a meeting into text data using speech recognition technology. The collection unit can convert the contents of utterances made during a meeting into text data using, for example, speech recognition technology. For example, the collection unit can use speech recognition technology that uses deep learning to convert the contents of utterances made during a meeting into text data with high accuracy. The collection unit can also use speech recognition technology that uses HMM (hidden Markov model) to convert the contents of utterances made during a meeting into text data. Furthermore, the collection unit can use speech recognition technology to transcribe the contents of utterances made during a meeting in real time and save the transcribed text as text data. For example, the collection unit can use speech recognition software to transcribe the contents of utterances made during a meeting in real time. In this way, the contents of utterances made during a meeting can be accurately converted into text data using speech recognition technology. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or can be performed without AI. For example, the collection unit can input speech data into a generation AI and cause the generation AI to generate text data from the speech data.

[0063] The analysis unit can analyze the audio data and extract important points and key points of the discussion. The analysis unit, for example, analyzes the audio data and extracts important points and key points of the discussion. For example, the analysis unit extracts important points based on frequently occurring keywords. The analysis unit can also extract important points based on emphasized parts of statements. Furthermore, the analysis unit can extract key points of the discussion based on the relevance of the topics. For example, the analysis unit analyzes the relevance of the content of statements and extracts key points of the discussion. In this way, the contents of the meeting can be efficiently summarized by extracting important points and key points of the discussion. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input audio data to a generation AI and have the generation AI extract important points and key points of the discussion.

[0064] The generation unit can automatically create minutes including the meeting start time, participants, agenda, decisions, and action items. The generation unit automatically creates minutes including, for example, the meeting start time, participants, agenda, decisions, and action items. For example, the generation unit records the meeting start time and includes it in the minutes. The generation unit can also list the meeting participants and include it in the minutes. The generation unit can also organize the meeting agenda and include it in the minutes. For example, the generation unit can summarize the meeting decisions and include them in the minutes. The generation unit can also list the meeting action items and include them in the minutes. This allows minutes including important meeting information to be automatically created, thereby improving the accuracy and efficiency of the minutes. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the summarized content into a generation AI and have the generation AI create the minutes.

[0065] The collection unit can estimate the user's emotions and adjust the timing of voice data collection based on the estimated user emotions. For example, if the user is nervous, the collection unit can start collecting voice data immediately after the start of a meeting to avoid missing important comments. Alternatively, if the user is relaxed, the collection unit can gradually collect voice data as the meeting progresses. Furthermore, if the user is in a hurry, the collection unit can start collecting voice data when an important topic of the meeting begins. This allows the timing of voice data collection to be adjusted according to the user's emotions, preventing important comments from being missed. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit can be performed using, for example, an AI, or without an AI. For example, the collection unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the collection timing based on the emotion.

[0066] The collection unit can analyze the speech frequency of meeting participants and prioritize collection of speech based on specific criteria. For example, the collection unit can prioritize collection of speech from participants who speak frequently to avoid missing important information. The collection unit can also pay particular attention to collecting speech from participants who speak infrequently to cover all opinions. Furthermore, the collection unit can analyze changes in speech frequency in real time to avoid missing the timing when important speech is made. In this way, by analyzing speech frequency, important speech can be collected without missing it. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input speech frequency data to a generation AI and cause the generation AI to prioritize collection of important speech.

[0067] When collecting voice data, the collection unit can dynamically change the collection method depending on the progress of the conference. For example, if the conference is progressing quickly, the collection unit can increase the frequency of voice data collection to avoid missing important information. Also, if the conference is progressing slowly, the collection unit can decrease the frequency of voice data collection to reduce unnecessary data. Furthermore, if the conference is progressing irregularly, the collection unit can dynamically change the collection method depending on the progress to optimally collect data. This makes it possible to optimally collect data by dynamically changing the collection method depending on the progress of the conference. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input conference progress data to the generation AI and cause the generation AI to dynamically change the collection method.

[0068] The collection unit can apply filtering technology to remove background noise when collecting audio data. For example, the collection unit can remove background noise in a conference room in real time to collect clear audio data. The collection unit can also filter out sounds other than the participants' speech and collect only important speech. Furthermore, the collection unit can remove external noise to accurately collect the contents of the meeting. In this way, by removing background noise, clear audio data can be collected. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input audio data to a generation AI and have the generation AI remove background noise.

[0069] The collection unit can estimate the user's emotions and determine the priority of the voice data to be collected based on the estimated user emotions. For example, if the user is nervous, the collection unit can prioritize collecting important utterances to avoid missing the key points of the meeting. Furthermore, if the user is relaxed, the collection unit can collect all utterances in a balanced manner to grasp the overall picture of the meeting. Furthermore, if the user is in a hurry, the collection unit can prioritize collecting utterances related to important topics of the meeting. Thus, by determining the priority of the voice data according to the user's emotions, important information can be collected preferentially. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit can be performed using, for example, an AI. For example, the collection unit can input the user's emotion data into the generation AI and cause the generation AI to determine the collection priority based on the emotion.

[0070] When collecting audio data, the collection unit can select an appropriate collection method depending on the location and environment of the meeting. For example, the collection unit adjusts the microphone placement depending on the size of the conference room to collect optimal audio data. The collection unit can also analyze the ambient sounds of the meeting and apply a noise canceling function to collect audio data. Furthermore, in the case of an online meeting, the collection unit can also collect the voices of participants individually to obtain clear audio data. This allows optimal audio data to be collected by selecting the optimal collection method depending on the location and environment of the meeting. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data about the location and environment of the meeting into the generation AI and cause the generation AI to select the optimal collection method.

[0071] When collecting audio data, the collection unit can customize the collected content based on the positions and expertise of the meeting participants. For example, the collection unit can prioritize collecting comments from participants with higher positions to avoid missing important decisions. The collection unit can also pay particular attention to collecting comments from participants with specialized knowledge to accurately record technical discussions. Furthermore, the collection unit can customize the collected content based on the positions and expertise of the participants to cover the key points of the meeting. In this way, by customizing the collected content based on the positions and expertise of the participants, important information can be collected without missing any important information. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the positions and expertise data of the participants into the generation AI and have the generation AI customize the collected content.

[0072] The collection unit can prioritize collecting keywords related to the meeting agenda when collecting audio data. For example, the collection unit can detect keywords related to the meeting agenda in real time and prioritize collecting important utterances. The collection unit can also pay particular attention to collecting utterances containing keywords related to the agenda so as not to miss the key points of the meeting. Furthermore, the collection unit can customize the collected content based on keywords related to the agenda to grasp the overall picture of the meeting. In this way, by prioritizing the collection of keywords related to the agenda, it is possible to collect the key points of the meeting without missing them. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input keyword data related to the agenda to a generation AI and cause the generation AI to customize the collected content based on the keywords.

[0073] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated user emotions. For example, if the user is nervous, the analysis unit increases the accuracy of the analysis to avoid missing important points. The analysis unit can also adjust the accuracy of the analysis to consider overall balance when the user is relaxed. Furthermore, if the user is in a hurry, the analysis unit can increase the accuracy of the analysis and quickly summarize. This allows the analysis to be performed without missing important points by adjusting the accuracy of the analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, the generation AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI adjust the analysis accuracy based on the emotion.

[0074] When analyzing the audio data, the analysis unit can dynamically change the analysis algorithm depending on the progress of the conference. For example, if the conference is progressing quickly, the analysis unit can speed up the analysis algorithm and perform analysis in real time. Furthermore, if the conference is progressing slowly, the analysis unit can adjust the analysis algorithm and perform a more detailed analysis. Furthermore, if the conference is progressing irregularly, the analysis unit can dynamically change the analysis algorithm depending on the progress and perform an optimal analysis. This makes it possible to perform an optimal analysis by dynamically changing the analysis algorithm depending on the progress of the conference. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input conference progress data to the generation AI and cause the generation AI to dynamically change the analysis algorithm.

[0075] When analyzing the audio data, the analysis unit can classify the content of speech made by conference participants and determine the priority of analysis according to its importance. For example, the analysis unit can classify the content of speech in real time and prioritize analysis of important speech. The analysis unit can also analyze the importance of the content of speech so as not to miss important points. Furthermore, the analysis unit can classify the content of speech and dynamically change the priority of analysis according to its importance. In this way, by classifying the content of speech and determining the priority of analysis according to its importance, it is possible to analyze without missing important points. Some or all of the above-described processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input speech content data to a generation AI and have the generation AI determine the analysis priority based on the importance.

[0076] When analyzing the audio data, the analysis unit can apply different analysis methods to each agenda item of the meeting. For example, the analysis unit selects the optimal analysis method for each agenda item to ensure that important points are not missed. The analysis unit can also dynamically change the analysis method depending on the agenda item to perform optimal analysis. Furthermore, the analysis unit can apply different analysis methods to each agenda item to grasp the overall picture of the meeting. In this way, by applying different analysis methods to each agenda item, the overall picture of the meeting can be grasped. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input agenda data into the generation AI and have the generation AI apply different analysis methods to each agenda item.

[0077] 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 display the analysis results simply to reduce visual stress. Furthermore, if the user is relaxed, the analysis unit can display detailed analysis results while taking overall balance into consideration. Furthermore, if the user is in a hurry, the analysis unit can quickly display analysis results that focus on the main points. This allows visual stress to be reduced by adjusting the display method of the analysis results according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, the generation AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI adjust the display method based on the emotion.

[0078] When analyzing the audio data, the analysis unit can translate the speech content of the conference participants in real time and perform multilingual analysis. For example, the analysis unit can translate the speech content in real time so that participants who speak different languages ​​can understand it. The analysis unit can also display the speech content in multiple languages, making it possible to handle international conferences. Furthermore, the analysis unit can also translate the speech content in real time and provide the analysis results in multiple languages. This makes it possible to handle international conferences by translating the speech content in real time. Some or all of the above-mentioned processing in the analysis unit can be performed using, or without, a generation AI, for example. For example, the analysis unit can input speech content data to a generation AI and have the generation AI perform real-time translation and multilingual analysis.

[0079] When analyzing the audio data, the analysis unit can update the analysis results in real time according to the progress of the conference. For example, the analysis unit updates the analysis results in real time according to the progress of the conference to provide the latest information. The analysis unit can also analyze the progress of the conference and update important points in real time. Furthermore, the analysis unit can dynamically update the analysis results according to the progress of the conference to provide optimal information. In this way, the analysis results can be updated in real time according to the progress of the conference, thereby providing the latest information. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input conference progress data to the generation AI and cause the generation AI to perform real-time updates of the analysis results.

[0080] When analyzing the audio data, the analysis unit can summarize the speech content of the meeting participants and emphasize important points. For example, the analysis unit can summarize the speech content and display it with important points emphasized. The analysis unit can also summarize the speech content in real time to ensure that important points are not overlooked. Furthermore, the analysis unit can summarize the speech content and display it with important points emphasized visually. In this way, by summarizing the speech content and emphasizing important points, the gist of the meeting can be grasped without missing anything. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input speech content data into a generation AI and have the generation AI perform the summarization and emphasize important points.

[0081] The generation unit can estimate the user's emotions and adjust the presentation style of the minutes based on the estimated user emotions. For example, if the user is nervous, the generation unit can create simple, highly visible minutes. Furthermore, if the user is relaxed, the generation unit can also create minutes that include detailed information. Furthermore, if the user is in a hurry, the generation unit can create concise minutes that focus on the main points. By adjusting the presentation style of the minutes according to the user's emotions, highly visible minutes can be created. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the generation unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the presentation style based on the emotion.

[0082] The generation unit can dynamically change the structure of the minutes based on the summarized content in accordance with the progress of the meeting. For example, the generation unit dynamically changes the structure of the minutes in accordance with the progress of the meeting to emphasize important points. The generation unit can also analyze the progress of the meeting and optimize the structure of the minutes. Furthermore, the generation unit can dynamically change the structure of the minutes in accordance with the progress of the meeting, taking into account the overall balance. In this way, important points can be emphasized by dynamically changing the structure of the minutes in accordance with the progress of the meeting. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input summarized content data into the generation AI and cause the generation AI to dynamically change the structure of the minutes.

[0083] The generation unit can create different minutes for each participant of the meeting based on the summarized content. For example, the generation unit can create minutes from different perspectives for each participant to meet individual needs. The generation unit can also customize the content of the minutes according to the participant's position or expertise. Furthermore, the generation unit can create different minutes for each participant and provide them in a format that is easy for everyone to understand. This makes it possible to meet individual needs by creating different minutes for each participant. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input summarized content data into a generation AI and have the generation AI create different minutes for each participant.

[0084] The generation unit can create different minutes for each meeting agenda based on the summarized content. For example, the generation unit can create different minutes for each agenda and emphasize important points. The generation unit can also change the structure of the minutes depending on the agenda and provide them in the optimal format. Furthermore, the generation unit can create different minutes for each agenda and consider the overall balance. This allows the overall picture of the meeting to be grasped by creating different minutes for each agenda. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the summarized content data into a generation AI and have the generation AI create different minutes for each agenda.

[0085] The generation unit can estimate the user's emotions and adjust the length of the minutes based on the estimated user emotions. For example, if the user is nervous, the generation unit can create short, concise minutes that are concise and easy to read if the user is relaxed. Furthermore, if the user is in a hurry, the generation unit can create longer minutes that include detailed information. This allows minutes with an appropriate amount of information to be created by adjusting the length of the minutes according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the generation unit can be performed using, for example, the generation AI. For example, the generation unit can input user emotion data into the generation AI and cause the generation AI to adjust the length of the minutes based on the emotion.

[0086] The generation unit can determine the priority of the minutes based on the summarized content in accordance with the progress of the meeting. For example, the generation unit prioritizes recording important topics in the minutes as the meeting progresses. The generation unit can also analyze the progress of the meeting and prioritize reflecting important points in the minutes. Furthermore, the generation unit can dynamically change the priority of the minutes as the meeting progresses and provide optimal information. This allows important information to be recorded preferentially by determining the priority of the minutes in accordance with the progress of the meeting. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input summarized content data into the generation AI and have the generation AI determine the priority of the minutes.

[0087] The generation unit can customize the content of the minutes based on the summarized content according to the positions and expertise of the meeting participants. For example, the generation unit can create minutes that emphasize important decisions for participants with higher positions. The generation unit can also create minutes that include technical details for participants with specialized knowledge. Furthermore, the generation unit can customize the content of the minutes according to the positions and expertise and provide them in a format that is easy for everyone to understand. In this way, the content of the minutes can be customized according to the positions and expertise of the participants, so that they can be provided in a format that is easy for everyone to understand. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input summarized content data into a generation AI and have the generation AI customize the minutes based on the positions and expertise.

[0088] The generation unit can highlight keywords related to the meeting agenda based on the summarized content. For example, the generation unit can highlight keywords related to the agenda to visually highlight important points. The generation unit can also organize the content of the minutes based on keywords related to the agenda and provide them in an easy-to-understand format. Furthermore, the generation unit can highlight keywords related to the agenda to prevent important information from being overlooked. By highlighting keywords related to the agenda, important information can be understood without missing anything. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the generation unit can input summarized content data to a generation AI and have the generation AI perform keyword highlighting. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, and generation unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit reads the audio of a meeting in real time using the microphone 38B of the smart device 14 and records it as audio data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the audio data using a generation AI, and summarizes the content of the meeting. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and creates minutes based on the summarized content. The generation unit may be realized, for example, by the control unit 46A of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, and generation unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit reads the audio of a meeting in real time using the microphone 238 of the smart glasses 214 and records it as audio data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the audio data using a generation AI to summarize the content of the meeting. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and creates minutes based on the summarized content. The generation unit may be realized, for example, by the control unit 46A of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, analysis unit, and generation unit described above is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit reads the audio of the conference in real time using the microphone 238 of the headset-type terminal 314 and records it as audio data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the audio data using a generation AI to summarize the contents of the conference. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and creates minutes based on the summarized contents. The generation unit may be realized, for example, by the control unit 46A of the headset-type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, analysis unit, and generation unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit reads the audio of a meeting in real time using the microphone 238 of the robot 414 and records it as audio data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the audio data using a generation AI, and summarizes the content of the meeting. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and creates minutes based on the summarized content. The generation unit may be realized, for example, by the control unit 46A of the robot 414.

[0089] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0090] The collection unit can translate the speech content of conference participants in real time and perform multilingual collection. For example, the collection unit can translate the speech content in real time so that it can be understood by participants who speak different languages. The collection unit can also display the speech content in multiple languages ​​and support international conferences. Furthermore, the collection unit can translate the speech content in real time and provide collected data in multiple languages. This makes it possible to support international conferences by translating the speech content in real time. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the collection unit can input speech content data to a generation AI and have the generation AI perform real-time translation and multilingual collection.

[0091] The analysis unit can perform real-time emotional analysis of the speech content of meeting participants and determine analysis priorities based on the emotions. For example, the analysis unit can perform real-time emotional analysis of speech content and prioritize analysis of emotionally charged speech. The analysis unit can also postpone emotionally charged speech to avoid missing important points. Furthermore, the analysis unit can dynamically change the analysis priorities based on the emotional analysis to perform optimal analysis. This allows for analysis without missing important points by determining the analysis priorities based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, the generation AI, or without the generation AI. For example, the analysis unit can input emotion data into the generation AI and have the generation AI determine the analysis priorities based on emotions.

[0092] The generation unit can dynamically change the structure of the minutes according to the progress of the meeting. For example, the generation unit can dynamically change the structure of the minutes according to the progress of the meeting to emphasize important points. The generation unit can also analyze the progress of the meeting and optimize the structure of the minutes. Furthermore, the generation unit can dynamically change the structure of the minutes according to the progress of the meeting and take the overall balance into consideration. In this way, important points can be emphasized by dynamically changing the structure of the minutes according to the progress of the meeting. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input summarized content data into the generation AI and cause the generation AI to dynamically change the structure of the minutes.

[0093] The collection unit can customize the collected content based on the positions and expertise of the meeting participants. For example, the collection unit can prioritize collecting comments from participants with higher positions to avoid missing important decisions. The collection unit can also pay particular attention to collecting comments from participants with specialized knowledge to accurately record technical discussions. Furthermore, the collection unit can customize the collected content based on the positions and expertise of the participants to cover all key points of the meeting. In this way, by customizing the collected content based on the positions and expertise of the participants, important information can be collected without missing any important information. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the positions and specialized knowledge data of the participants into the generation AI and have the generation AI customize the collected content.

[0094] The analysis unit can classify the content of statements made by meeting participants in real time and determine the priority of analysis according to their importance. For example, the analysis unit can classify the content of statements in real time and prioritize analysis of important statements. The analysis unit can also analyze the importance of the content of statements and perform analysis so as not to miss important points. Furthermore, the analysis unit can classify the content of statements and dynamically change the priority of analysis according to their importance. In this way, by classifying the content of statements and determining the priority of analysis according to their importance, it is possible to analyze without missing important points. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the content data of statements to a generation AI and have the generation AI determine the analysis priority based on the importance.

[0095] The collection unit can estimate the user's emotions and prioritize the voice data to be collected based on the estimated user emotions. For example, if the user is nervous, the collection unit can prioritize collecting important comments to avoid missing the key points of the meeting. Furthermore, if the user is relaxed, the collection unit can collect all comments in a balanced manner to grasp the overall picture of the meeting. Furthermore, if the user is in a hurry, the collection unit can prioritize collecting comments related to important topics of the meeting. Thus, by prioritizing the voice data according to the user's emotions, important information can be collected preferentially. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit can be performed using, for example, an AI. For example, the collection unit can input the user's emotion data into the generation AI and cause the generation AI to determine the collection priority based on the emotion.

[0096] The generation unit can create different minutes for each participant in the meeting based on the summarized content. For example, minutes can be created from different perspectives for each participant to meet their individual needs. The generation unit can also customize the content of the minutes according to the participant's position or expertise. Furthermore, the generation unit can create different minutes for each participant and provide them in a format that is easy for everyone to understand. This allows individual needs to be met by creating different minutes for each participant. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the summarized content data into the generation AI and have the generation AI create different minutes for each participant.

[0097] 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 display the analysis results simply to reduce visual stress. Furthermore, if the user is relaxed, the analysis unit can display detailed analysis results while taking overall balance into consideration. Furthermore, if the user is in a hurry, the analysis unit can quickly display analysis results that focus on the main points. This allows visual stress to be reduced by adjusting the display method of the analysis results according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, the generation AI, or without the generation AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI adjust the display method based on the emotion.

[0098] When collecting audio data, the collection unit can select an appropriate collection method depending on the location and environment of the meeting. For example, the collection unit adjusts the microphone placement depending on the size of the conference room to collect optimal audio data. The collection unit can also analyze the ambient sounds of the meeting and apply a noise canceling function to collect audio data. Furthermore, in the case of an online meeting, the collection unit can also collect the voices of participants individually to obtain clear audio data. This allows optimal audio data to be collected by selecting the optimal collection method depending on the location and environment of the meeting. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data about the location and environment of the meeting into the generation AI and have the generation AI select the optimal collection method.

[0099] The generation unit can estimate the user's emotions and adjust the presentation style of the minutes based on the estimated user emotions. For example, if the user is nervous, the generation unit can create simple, highly readable minutes. Furthermore, if the user is relaxed, the generation unit can create minutes that include detailed information. Furthermore, if the user is in a hurry, the generation unit can create concise minutes that focus on the main points. By adjusting the presentation style of the minutes based on the user's emotions, highly readable minutes can be created. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the generation unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the presentation style based on the emotion.

[0100] The processing flow of the second embodiment will be briefly explained below.

[0101] Step 1: The collection unit reads the audio of the meeting in real time and records it as audio data. The collection unit uses speech recognition technology to convert what is said in the meeting into text data. The collection unit can also transcribe what is said during the meeting in real time and save it as text data. Step 2: The analysis unit uses the generation AI to analyze the audio data recorded by the collection unit and summarize the contents of the meeting. The analysis unit analyzes the audio data and extracts important points and key points of discussion. For example, the generation AI analyzes the audio data and summarizes the meeting agenda, decisions, action items, etc. Step 3: The generation unit uses the generation AI to create minutes based on the content summarized by the analysis unit. The generation unit organizes the summarized content and outputs it as minutes. For example, the generation unit automatically creates minutes that include the meeting start time, participants, agenda, decisions, action items, etc.

[0102] 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.

[0103] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0104] 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.

[0105] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] 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.

[0121] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0136] 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.

[0137] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0138] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0139] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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).

[0144] 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.

[0145] 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.

[0146] 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.

[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 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.

[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 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.

[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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0153] 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.

[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] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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."

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] [Explanation of symbols]

[0174] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection unit that reads the audio of the meeting in real time and records it as audio data; an analysis unit that analyzes the audio data recorded by the collection unit and summarizes the contents of the conference; a generation unit that generates minutes based on the content summarized by the analysis unit. A system characterized by:

2. The collecting unit Converting meeting content into text data using speech recognition technology 2. The system of claim 1.

3. The analysis unit Analyze audio data to extract key points and key discussion points 2. The system of claim 1.

4. The generation unit Automatically create meeting minutes with meeting start time, participants, agenda, decisions, and action items 2. The system of claim 1.

5. The collecting unit The user's emotions are estimated, and the timing of collecting voice data is adjusted based on the estimated user's emotions.

2. The system of claim 1.

6. The collecting unit Analyze the frequency of speech by meeting participants and prioritize collection of speech based on specific criteria 2. The system of claim 1.

7. The collecting unit Dynamically change the collection method for audio data collection depending on the progress of the meeting.

2. The system of claim 1.

8. The collecting unit When collecting audio data, apply filtering techniques to remove background noise.

2. The system of claim 1.

Images