system

Abstract

An object of the system according to the embodiment is to efficiently record the contents of the discussion of the MTG and to summarize the contents in a visually easy-to-understand manner.SOLUTION: A system according to an embodiment includes a collection unit, an analysis unit, an extraction unit, a generation unit, and a creation unit. The collection unit collects voice data of the MTG. The analysis unit analyzes the voice data collected by the collection unit and converts the discussion content into text. An extraction part extracts an important point based on the contents of the discussion converted into text by the analysis part. The generation unit generates an illustration corresponding to the important point extracted by the extraction unit. The creation unit creates a graphic record by combining the illustration and the text generated by the generation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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] With conventional technology, it was difficult to efficiently record the contents of meetings and summarize them in a visually easy-to-understand manner.

[0005] The system according to the embodiment aims to efficiently record the contents of discussions at meetings and summarize them in a visually easy-to-understand manner. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, an extraction unit, a generation unit, and a creation unit. The collection unit collects audio data from meetings. The analysis unit analyzes the audio data collected by the collection unit and converts the discussion content into text. The extraction unit extracts important points based on the discussion content converted into text by the analysis unit. The creation unit generates illustrations corresponding to the important points extracted by the extraction unit. The creation unit combines the illustrations and text generated by the creation unit to create a graphic record. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently record the contents of discussions at meetings and summarize them in a visually easy-to-understand manner. [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 graphic record generation system according to an embodiment of the present invention visually summarizes the contents of a meeting discussion. This system collects audio data from meetings, analyzes the audio data using AI to convert the discussion content into text, extracts key points, generates corresponding illustrations, and automatically creates a graphic record by combining the generated illustrations and text. For example, the graphic record generation system collects audio data using microphones installed in a conference room or participants' smartphones. Next, the graphic record generation system analyzes the audio data and converts the discussion content into text using AI. Furthermore, the graphic record generation system extracts key points from the text of the discussion, and the AI ​​generates corresponding illustrations. Finally, the graphic record generation system combines the generated illustrations and text to automatically create an easy-to-understand graphic record. This allows the graphic record generation system to visually summarize the contents of meetings, allowing all participants to easily understand the content of the discussion. This allows all participants to easily understand the content of the discussion. For example, important points, such as the progress of a project or next steps, can be seen at a glance. This improves the efficiency of meetings and maximizes the results of discussions.

[0029] A graphic record generation system according to an embodiment includes a collection unit, an analysis unit, an extraction unit, a generation unit, and a creation unit. The collection unit collects audio data from meetings. The collection unit can collect audio data using, for example, microphones installed in the conference room or participants' smartphones. For example, a microphone can be installed in the center of the conference room to record everyone's comments. The collection unit can also collect audio data using participants' smartphones. For example, the audio data can be collected using a dedicated app. The analysis unit analyzes the audio data collected by the collection unit and converts the discussion content into text. For example, the analysis unit converts the comments into text using, for example, speech recognition technology. For example, if a participant says, "Let's discuss the progress of the next project," the analysis unit records this as text. The extraction unit extracts important points from the discussion content converted into text by the analysis unit. For example, the extraction unit analyzes the text using natural language processing technology to identify important keywords and phrases. For example, the extraction unit extracts important points such as "project progress" and "next steps." The generation unit generates illustrations corresponding to the important points extracted by the extraction unit. The generation unit generates appropriate illustrations, for example, based on a database that has been learned in advance. For example, for "project progress," it generates illustrations of graphs or charts showing progress. The creation unit creates a graphic record by combining the illustrations generated by the generation unit with text. The creation unit, for example, appropriately arranges the text and illustrations to create an easy-to-read layout. For example, it arranges illustrations and text for each important point to make the overall flow easy to understand. As a result, the graphic record generation system according to the embodiment can visually summarize the contents of a meeting discussion in an easy-to-understand manner, allowing all participants to easily understand the contents of the discussion.

[0030] The collection unit can collect voice data using a microphone installed in the conference room or the participants' smartphones. For example, the collection unit installs a microphone in the center of the conference room and records everyone's speech. The collection unit can also collect voice data using the participants' smartphones. For example, the voice data is collected using a dedicated app. This allows voice data to be collected efficiently according to the environment of the conference room. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input voice data acquired by a microphone installed in the conference room into the generation AI and have the generation AI analyze the voice data.

[0031] The analysis unit can convert utterances into text using speech recognition technology. For example, if a user says, "Let's discuss the progress of the next project," the analysis unit records the utterance as text. The analysis unit can also use speech recognition technology that uses deep learning. For example, an acoustic model can be used to analyze speech data and convert the utterances into text. Furthermore, the analysis unit can also support multiple languages ​​using speech recognition technology. For example, speech in multiple languages, such as English, Japanese, and French, can be converted into text. This allows for accurate conversion of speech data into text. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or can be performed without AI. For example, the analysis unit can input speech data into a generation AI and have the generation AI convert the utterances into text.

[0032] The extraction unit can analyze text using natural language processing technology to identify important keywords and phrases. For example, the extraction unit can analyze text using natural language processing technology to identify important keywords and phrases. For example, the extraction unit can extract important points such as "project progress" and "next steps." The extraction unit can also analyze text using morphological analysis. For example, the extraction unit can extract nouns and verbs from the text and identify important keywords. The extraction unit can also analyze text using grammatical analysis. For example, the extraction unit can analyze sentence structure and identify important phrases. This allows the main points of the discussion to be clearly extracted. Some or all of the above-mentioned processing in the extraction unit can be performed using, for example, AI, or can be performed without using AI. For example, the extraction unit can input text data into a generation AI and have the generation AI extract important points.

[0033] The generation unit can generate illustrations based on a pre-trained database. The generation unit generates appropriate illustrations based on a pre-trained database, for example. For example, for "project progress," it generates illustrations of graphs and charts showing progress. The generation unit can also generate illustrations based on past meeting data. For example, it can generate new illustrations by referring to illustrations used in past meetings. The generation unit can also generate illustrations based on an image database. For example, it can select an appropriate image from the image database and generate an illustration based on that image. This makes it possible to automatically generate illustrations corresponding to the content of the discussion. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on important points into the generation AI and have the generation AI generate the illustrations.

[0034] The creation unit can appropriately arrange text and illustrations and organize them into an easy-to-read layout. For example, the creation unit can appropriately arrange text and illustrations and organize them into an easy-to-read layout. For example, illustrations and text can be arranged at each important point to make the overall flow easy to understand. The creation unit can also adjust the layout taking visual balance into consideration. For example, the creation unit can adjust the arrangement of text and illustrations to create a visually balanced layout. Furthermore, the creation unit can adjust the layout based on the importance of the information. For example, important information can be placed in a prominent position to visually emphasize it. This makes it possible to automatically create a visually easy-to-understand graphic record. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input data of the generated illustrations and text into a generation AI and have the generation AI adjust the layout.

[0035] The collection unit can change the range of audio data to be collected depending on the progress of the meeting. For example, the collection unit collects the overall discussion at the beginning of the meeting, and as the agenda becomes more specific, it focuses on collecting audio data from specific speakers. In addition, as the meeting progresses, the collection unit can prioritize collecting comments related to an important agenda item when that agenda item comes up. Furthermore, the collection unit can focus on collecting comments related to the conclusion or next steps towards the end of the meeting, thereby covering the entire discussion. This makes it possible to optimize the range of audio data collected depending on the progress 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 meeting progress data into the generation AI and have the generation AI adjust the collection range.

[0036] The collection unit can simultaneously collect speaker identification information when collecting audio data. For example, the collection unit can automatically identify the speaker's name and title when collecting audio data and tag the data. The collection unit can also analyze the speaker's voiceprint, identify individual speakers, and associate them with the audio data. Furthermore, the collection unit can compare the speaker's voiceprint with a meeting participant list and collect speaker identification information in real time. By simultaneously collecting speaker identification information, the content of the discussion can be more accurately understood. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input the audio data and speaker identification information into a generation AI and cause the generation AI to collect the identification information.

[0037] When collecting voice data, the collection unit can set the collection order based on the agenda of the meeting. For example, if the agenda of the meeting is important, the collection unit prioritizes collection of utterances related to that agenda. In addition, if there are multiple agendas, the collection unit can also collect voice data based on a pre-set priority. Furthermore, the collection unit can dynamically change the collection priority based on the importance of the agenda as the meeting progresses. This makes it possible to optimize the collection of voice data based on the agenda 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 meeting agenda data to a generation AI and have the generation AI set the collection order.

[0038] When collecting audio data, the collection unit can change the collection method based on the location and time of the meeting. For example, the collection unit collects audio data by applying noise canceling, taking into account the environmental sounds of the conference room. The collection unit can also adjust the audio data collection sensitivity for nighttime meetings, assuming a quiet environment. Furthermore, the collection unit can optimize the audio data collection method by taking into account network delays for online meetings. This makes it possible to optimize the audio data collection method depending on the location and time of the meeting. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input data on the location and time of the meeting into the generation AI and cause the generation AI to change the collection method.

[0039] When collecting voice data, the collection unit can adjust the accuracy of collection based on the positions and fields of expertise of the participants in the meeting. For example, the collection unit can prioritize collecting comments from participants with important positions to increase accuracy. In addition, when a discussion specialized in a specialized field is taking place, the collection unit can accurately collect technical terms in that field. Furthermore, the collection unit can dynamically adjust the accuracy of collection based on the positions and fields of expertise of the participants as the meeting progresses. This makes it possible to optimize the accuracy of voice data collection depending on the positions and fields of expertise of the participants. 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 on the positions and fields of expertise of the participants into the generation AI and cause the generation AI to adjust the collection accuracy.

[0040] The collection unit can monitor the progress of the meeting in real time when collecting audio data and optimize the collection method. For example, the collection unit can monitor the progress of the meeting in real time and strengthen the collection method when an important topic comes up. The collection unit can also dynamically adjust the range and accuracy of the audio data to be collected according to the progress of the meeting. Furthermore, the collection unit can focus on collecting comments related to conclusions and next steps towards the end of the meeting to cover the entire discussion. This makes it possible to optimize the audio data collection method according to the progress 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 meeting progress data to the generation AI and have the generation AI optimize the collection method.

[0041] When analyzing voice data, the analysis unit can convert the speech data into text taking into account the speaker's emotions and tone. For example, the analysis unit can convert the speech data into text by bolding or changing the color of parts emphasized by the speaker. Furthermore, if the speaker is relaxed, the analysis unit can convert the speech data into text in a calm tone. Furthermore, if the speaker is excited, the analysis unit can convert the speech data into text in an expression method that reflects the speaker's emotions. This enables the speech data to reflect the speaker's emotions and tone. Emotion estimation is achieved using an emotion estimation function, for example, with 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 such examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the speaker's emotion data into the generation AI and have the generation AI adjust the expression method for the text data.

[0042] When analyzing the audio data, the analysis unit can set a priority for text conversion based on the agenda of the meeting. For example, the analysis unit can prioritize text conversion of statements related to important agenda items. The analysis unit can also dynamically change the priority for text conversion based on the importance of the agenda items as the meeting progresses. Furthermore, the analysis unit can prioritize text conversion of statements related to conclusions and next steps toward the end of the meeting. This makes it possible to optimize the priority for text conversion based on the agenda of the meeting. Some or all of the above-described processing by the analysis unit may be performed using, or without, AI, for example. For example, the analysis unit can input meeting agenda data into a generation AI and cause the generation AI to set the priority for text conversion.

[0043] When analyzing audio data, the analysis unit can improve the accuracy of the text conversion by taking into account the context of the utterance. For example, the analysis unit analyzes the context before and after the utterance and converts it into text using an appropriate expression method. The analysis unit can also convert the text in accordance with the context by taking into account the intention of the utterance. Furthermore, the analysis unit can dynamically adjust the accuracy of the text conversion by taking into account the context of the utterance according to the progress of the meeting. This makes it possible to convert the text into text taking into account the context of the utterance. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input context data of the utterance into the generation AI and cause the generation AI to improve the accuracy of the text conversion.

[0044] When analyzing the audio data, the analysis unit can automatically recognize the speaker's technical terms and industry jargon and convert them into text. For example, the analysis unit can automatically recognize technical terms used by the speaker and convert them into text accurately. The analysis unit can also automatically recognize industry-specific terms and convert them into text using an appropriate expression method. Furthermore, the analysis unit can dynamically recognize and convert technical terms and industry jargon into text as the meeting progresses. This allows the technical terms and industry jargon to be accurately converted into text. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on technical terms and industry jargon into a generation AI and have the generation AI perform the recognition and conversion into text.

[0045] When analyzing the audio data, the analysis unit can adjust the order of transcription based on the progress of the meeting. For example, the analysis unit can prioritize transcription of statements related to important agenda items according to the progress of the meeting. The analysis unit can also dynamically change the order of transcription based on the importance of the agenda items as the meeting progresses. Furthermore, the analysis unit can prioritize transcription of statements related to conclusions and next steps toward the end of the meeting. This makes it possible to optimize the order of transcription according to the progress of the meeting. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, AI, for example. For example, the analysis unit can input data on the progress of the meeting into the generation AI and cause the generation AI to adjust the order of transcription.

[0046] When analyzing audio data, the analysis unit can improve the accuracy of the text by taking into account the speaker's attribute information. The analysis unit can convert the speech into text using an appropriate expression method, for example, taking into account the speaker's position and field of expertise. The analysis unit can also improve the accuracy of the text by referring to the speaker's past speech history. Furthermore, the analysis unit can dynamically consider the speaker's attribute information and adjust the accuracy of the text as the meeting progresses. This makes it possible to convert the speech into text taking into account the speaker's attribute information. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the speaker's attribute information data into the generation AI and cause the generation AI to improve the accuracy of the text.

[0047] The extraction unit can extract important points from the text-converted discussion content, taking into account the speaker's intention and purpose. The extraction unit, for example, analyzes the speaker's intention and extracts important points. The extraction unit can also extract important points using appropriate criteria, taking into account the speaker's purpose. Furthermore, the extraction unit can extract important points by dynamically taking into account the speaker's intention and purpose as the meeting progresses. This makes it possible to extract important points taking into account the speaker's intention and purpose. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input data on the speaker's intention and purpose into the generation AI and cause the generation AI to extract important points.

[0048] The extraction unit can extract important points from the text-converted discussion content based on the meeting agenda. The extraction unit extracts important points based on, for example, keywords related to the meeting agenda. The extraction unit can also dynamically extract important points based on the importance of the agenda as the meeting progresses. Furthermore, the extraction unit can prioritize extracting important points related to conclusions and next steps toward the end of the meeting. This makes it possible to extract important points based on the meeting agenda. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input meeting agenda data into a generation AI and cause the generation AI to extract important points.

[0049] The extraction unit can extract important points from the text-converted discussion content, taking into account the frequency of comments and emphasized parts. For example, the extraction unit extracts important points based on frequently-commented parts. The extraction unit can also analyze emphasized parts and extract them as important points. Furthermore, the extraction unit can extract important points by dynamically taking into account the frequency of comments and emphasized parts as the meeting progresses. This makes it possible to extract important points taking into account the frequency of comments and emphasized parts. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input data on the frequency of comments and emphasized parts into the generation AI and cause the generation AI to extract important points.

[0050] The extraction unit can extract important points from the text-converted discussion content based on the speaker's field of expertise and position. The extraction unit extracts important points based on, for example, keywords related to the speaker's field of expertise. The extraction unit can also preferentially extract important points based on the speaker's position. Furthermore, the extraction unit can extract important points by dynamically considering the speaker's field of expertise and position as the meeting progresses. This makes it possible to extract important points based on the speaker's field of expertise and position. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input data on the speaker's field of expertise and position into the generation AI and cause the generation AI to extract important points.

[0051] The extraction unit can extract important points from the text-converted discussion content, taking into account the progress of the meeting. For example, the extraction unit prioritizes extraction of comments related to important topics according to the progress of the meeting. The extraction unit can also dynamically extract important points based on the importance of the topics as the meeting progresses. Furthermore, the extraction unit can prioritize extraction of important points related to conclusions and next steps towards the end of the meeting. This makes it possible to extract important points according to the progress of the meeting. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input data on the progress of the meeting into the generation AI and cause the generation AI to extract important points.

[0052] The extraction unit can extract important points from the text-converted discussion content while taking into account the speaker's attribute information. The extraction unit extracts important points while taking into account, for example, the speaker's position or field of expertise. The extraction unit can also extract important points while referring to the speaker's past speech history. Furthermore, the extraction unit can extract important points while dynamically taking into account the speaker's attribute information as the meeting progresses. This makes it possible to extract important points while taking into account the speaker's attribute information. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the speaker's attribute information data into the generation AI and cause the generation AI to extract important points.

[0053] The generation unit can generate an illustration that reflects the speaker's intention and purpose based on the extracted important points. The generation unit, for example, analyzes the speaker's intention and generates an illustration based on that. The generation unit can also generate an appropriate illustration by taking the speaker's purpose into consideration. Furthermore, the generation unit can generate an illustration by dynamically taking the speaker's intention and purpose into consideration as the meeting progresses. This makes it possible to generate an illustration that reflects the speaker's intention and purpose. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on the speaker's intention and purpose into the generation AI and have the generation AI generate an illustration.

[0054] The generation unit can generate illustrations related to the meeting agenda based on the extracted important points. The generation unit generates appropriate illustrations based on, for example, keywords related to the meeting agenda. The generation unit can also dynamically generate illustrations based on the importance of the agenda as the meeting progresses. Furthermore, the generation unit can prioritize generating illustrations related to conclusions and next steps toward the end of the meeting. This makes it possible to generate illustrations related to the meeting agenda. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input meeting agenda data into a generation AI and cause the generation AI to generate illustrations.

[0055] The generation unit can generate an illustration that takes into account the context of the utterance based on the extracted important points. The generation unit, for example, analyzes the context before and after the utterance and generates an appropriate illustration. The generation unit can also generate an illustration that is in line with the context by taking into account the intention of the utterance. Furthermore, the generation unit can dynamically generate an illustration by taking into account the context of the utterance according to the progress of the meeting. This makes it possible to generate an illustration that takes into account the context of the utterance. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input context data of the utterance into a generation AI and cause the generation AI to generate an illustration.

[0056] The generation unit can generate illustrations related to the speaker's field of expertise and position based on the extracted important points. The generation unit generates appropriate illustrations based on, for example, keywords related to the speaker's field of expertise. The generation unit can also generate related illustrations based on the speaker's position. Furthermore, the generation unit can dynamically generate illustrations taking into account the speaker's field of expertise and position as the meeting progresses. This makes it possible to generate illustrations related to the speaker's field of expertise and position. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on the speaker's field of expertise and position into the generation AI and cause the generation AI to generate illustrations.

[0057] The generation unit can generate illustrations that take into account the progress of the meeting based on the extracted important points. For example, the generation unit prioritizes generating illustrations related to important agenda items according to the progress of the meeting. The generation unit can also dynamically generate illustrations based on the importance of the agenda items as the meeting progresses. Furthermore, the generation unit can prioritize generating illustrations related to conclusions and next steps toward the end of the meeting. This makes it possible to generate illustrations 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, AI, or may be performed without using AI. For example, the generation unit can input data on the progress of the meeting into the generation AI and cause the generation AI to generate illustrations.

[0058] The generation unit can generate illustrations that reflect the speaker's attribute information based on the extracted important points. The generation unit generates appropriate illustrations, for example, by taking into account the speaker's job title and field of expertise. The generation unit can also generate related illustrations by referring to the speaker's past speech history. Furthermore, the generation unit can generate illustrations by dynamically taking into account the speaker's attribute information as the meeting progresses. This makes it possible to generate illustrations that reflect the speaker's attribute information. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the speaker's attribute information data into the generation AI and cause the generation AI to generate an illustration.

[0059] The creation unit can combine the generated illustrations and text in a layout that reflects the speaker's intention and purpose. For example, the creation unit can analyze the speaker's intention and combine the illustrations and text in a layout based on that analysis. The creation unit can also combine the illustrations and text in an appropriate layout, taking into account the speaker's purpose. Furthermore, the creation unit can adjust the layout dynamically taking into account the speaker's intention and purpose as the meeting progresses. This enables graphic recording of a layout that reflects the speaker's intention and purpose. Some or all of the above-mentioned processing in the creation unit may be performed using, or without, AI. For example, the creation unit can input data on the speaker's intention and purpose into the generation AI and have the generation AI adjust the layout.

[0060] The creation unit can appropriately arrange the generated illustrations and text based on the meeting agenda. For example, the creation unit arranges the illustrations and text in an appropriate layout based on keywords related to the meeting agenda. The creation unit can also dynamically adjust the layout based on the importance of the agenda as the meeting progresses. Furthermore, the creation unit can prioritize the arrangement of illustrations and text related to conclusions and next steps toward the end of the meeting. This enables a graphic record with an appropriate arrangement based on the meeting agenda. Some or all of the above-mentioned processing in the creation unit may be performed using, or without, AI, for example. For example, the creation unit can input meeting agenda data into the generation AI and have the generation AI adjust the layout.

[0061] The creation unit can organize the generated illustrations and text into an easy-to-read layout taking into account the context of the utterance. For example, the creation unit analyzes the context before and after the utterance and arranges the illustrations and text in an appropriate layout. The creation unit can also arrange the illustrations and text in a layout that matches the context taking into account the intention of the utterance. Furthermore, the creation unit can dynamically adjust the layout taking into account the context of the utterance as the meeting progresses. This enables graphic recording with an easy-to-read layout that takes into account the context of the utterance. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input context data of the utterance into the generation AI and have the generation AI adjust the layout.

[0062] The creation unit can appropriately arrange the generated illustrations and text based on the speaker's field of expertise and position. For example, the creation unit arranges illustrations and text in an appropriate layout based on keywords related to the speaker's field of expertise. The creation unit can also prioritize the arrangement of related illustrations and text based on the speaker's position. Furthermore, the creation unit can dynamically adjust the layout taking into account the speaker's field of expertise and position as the meeting progresses. This enables a graphic record with an appropriate arrangement based on the speaker's field of expertise and position. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input data on the speaker's field of expertise and position into the generation AI and have the generation AI adjust the layout.

[0063] The creation unit can organize the generated illustrations and text into a layout based on the progress of the meeting. For example, the creation unit can prioritize the placement of illustrations and text related to important agenda items according to the progress of the meeting. The creation unit can also dynamically adjust the layout based on the importance of the agenda items as the meeting progresses. Furthermore, the creation unit can prioritize the placement of illustrations and text related to conclusions and next steps toward the end of the meeting. This enables a graphic record with an optimal layout according to the progress of the meeting. Some or all of the above-mentioned processing in the creation unit may be performed using, or without, AI, for example. For example, the creation unit can input meeting progress data into the generation AI and have the generation AI adjust the layout.

[0064] The creation unit can organize the generated illustrations and text into an easy-to-read layout that reflects the speaker's attribute information. The creation unit arranges the illustrations and text in an appropriate layout, taking into account, for example, the speaker's position and field of expertise. The creation unit can also arrange related illustrations and text by referring to the speaker's past speech history. Furthermore, the creation unit can adjust the layout by dynamically considering the speaker's attribute information as the meeting progresses. This enables a graphic record with an easy-to-read layout that reflects the speaker's attribute information. Some or all of the above-mentioned processing in the creation unit may be performed, for example, using AI, or may be performed without using AI. For example, the creation unit can input the speaker's attribute information data into the generation AI and have the generation AI adjust the layout.

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

[0066] The collection unit can also adjust the method of collecting voice data depending on the type of device used by the meeting participants. For example, if a participant is using a laptop, the built-in microphone can be used to collect voice data. If a participant is using a tablet, an external microphone can be connected to collect voice data. Furthermore, if a participant is using a wearable device, the device's sensors can be used to collect voice data. This allows the collection unit to provide the optimal method of collecting voice data depending on the participant's device.

[0067] When analyzing audio data, the analysis unit can improve the accuracy of the text conversion by taking into account the speaker's speaking speed and tone of voice. For example, if the speaker speaks quickly, the analysis unit can adjust the speaking speed before converting to text. Also, if the speaker speaks in a low voice, the analysis unit can adjust the volume of the audio data before converting to text. Furthermore, if the speaker is speaking emotionally, the analysis unit can convert to text using an expression method that reflects that emotion. This enables the analysis unit to convert to text while taking into account the speaker's speaking speed and tone of voice.

[0068] The extraction unit can extract important points from the text-converted discussion content, taking into account the speaker's past speech history. For example, if a speaker has made an important proposal in the past, important points can be extracted based on that speech history. Also, if a speaker has previously determined the direction of a discussion, important points can be extracted by referring to that speech history. Furthermore, if a speaker has previously reached a conclusion in a discussion, important points can be extracted by taking into account that speech history. This enables the extraction unit to extract important points by taking into account the speaker's past speech history.

[0069] The generation unit can generate illustrations that reflect the progress of the meeting in real time based on the extracted important points. For example, illustrations can be dynamically generated based on the importance of the agenda items as the meeting progresses. Also, towards the end of the meeting, illustrations related to the conclusion or next steps can be generated preferentially. Furthermore, if a new agenda item is added while the meeting is in progress, an illustration corresponding to that agenda item can be instantly generated. This enables the generation unit to generate illustrations that reflect the progress of the meeting in real time.

[0070] The creation unit can appropriately arrange the generated illustrations and text based on the job titles and areas of expertise of the meeting participants. For example, if the speaker is a project manager, illustrations and text related to that statement can be placed in a prominent position. Also, if the speaker is a technical expert, technical illustrations and text related to that statement can be appropriately placed. Furthermore, if the speaker is a marketing specialist, illustrations and text containing marketing materials related to that statement can be placed. This enables the creation unit to create a graphic record with appropriate placement based on the job titles and areas of expertise of the meeting participants.

[0071] The processing flow of the first embodiment will be briefly explained below.

[0072] Step 1: The collection unit collects audio data from the meeting. The collection unit can collect audio data, for example, using microphones installed in the conference room or participants' smartphones. For example, a microphone can be installed in the center of the conference room and everyone's comments recorded. The collection unit can also collect audio data using participants' smartphones. For example, audio data can be collected using a dedicated app. Step 2: The analysis unit analyzes the voice data collected by the collection unit and converts the content of the discussion into text. For example, the analysis unit converts the utterances into text using voice recognition technology. For example, if someone says, "Let's discuss the progress of the next project," it will record this as text. Step 3: The extraction unit extracts key points from the discussion content converted into text by the analysis unit. For example, the extraction unit uses natural language processing technology to analyze the text and identify important keywords and phrases. For example, it extracts key points such as "project progress" and "next steps." Step 4: The generator generates illustrations corresponding to the key points extracted by the extractor. For example, the generator generates appropriate illustrations based on a pre-trained database. For example, for "Project Progress," it generates illustrations of graphs and charts showing progress. Step 5: The creation unit creates a graphic record by combining the illustrations and text generated by the generation unit. For example, the creation unit arranges the text and illustrations appropriately and creates an easy-to-read layout. For example, the creation unit arranges illustrations and text at each important point to make the overall flow easy to understand.

[0073] (Example 2) A graphic record generation system according to an embodiment of the present invention visually summarizes the contents of a meeting discussion. This system collects audio data from meetings, analyzes the audio data using AI to convert the discussion content into text, extracts key points, generates corresponding illustrations, and automatically creates a graphic record by combining the generated illustrations and text. For example, the graphic record generation system collects audio data using microphones installed in a conference room or participants' smartphones. Next, the graphic record generation system analyzes the audio data and converts the discussion content into text using AI. Furthermore, the graphic record generation system extracts key points from the text of the discussion, and the AI ​​generates corresponding illustrations. Finally, the graphic record generation system combines the generated illustrations and text to automatically create an easy-to-understand graphic record. This allows the graphic record generation system to visually summarize the contents of meetings, allowing all participants to easily understand the content of the discussion. This allows all participants to easily understand the content of the discussion. For example, important points, such as the progress of a project or next steps, can be seen at a glance. This improves the efficiency of meetings and maximizes the results of discussions.

[0074] A graphic record generation system according to an embodiment includes a collection unit, an analysis unit, an extraction unit, a generation unit, and a creation unit. The collection unit collects audio data from meetings. The collection unit can collect audio data using, for example, microphones installed in the conference room or participants' smartphones. For example, a microphone can be installed in the center of the conference room to record everyone's comments. The collection unit can also collect audio data using participants' smartphones. For example, the audio data can be collected using a dedicated app. The analysis unit analyzes the audio data collected by the collection unit and converts the discussion content into text. For example, the analysis unit converts the comments into text using, for example, speech recognition technology. For example, if a participant says, "Let's discuss the progress of the next project," the analysis unit records this as text. The extraction unit extracts important points from the discussion content converted into text by the analysis unit. For example, the extraction unit analyzes the text using natural language processing technology to identify important keywords and phrases. For example, the extraction unit extracts important points such as "project progress" and "next steps." The generation unit generates illustrations corresponding to the important points extracted by the extraction unit. The generation unit generates appropriate illustrations, for example, based on a database that has been learned in advance. For example, for "project progress," it generates illustrations of graphs or charts showing progress. The creation unit creates a graphic record by combining the illustrations generated by the generation unit with text. The creation unit, for example, appropriately arranges the text and illustrations to create an easy-to-read layout. For example, it arranges illustrations and text for each important point to make the overall flow easy to understand. As a result, the graphic record generation system according to the embodiment can visually summarize the contents of a meeting discussion in an easy-to-understand manner, allowing all participants to easily understand the contents of the discussion.

[0075] The collection unit can collect voice data using a microphone installed in the conference room or the participants' smartphones. For example, the collection unit installs a microphone in the center of the conference room and records everyone's speech. The collection unit can also collect voice data using the participants' smartphones. For example, the voice data is collected using a dedicated app. This allows voice data to be collected efficiently according to the environment of the conference room. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input voice data acquired by a microphone installed in the conference room into the generation AI and have the generation AI analyze the voice data.

[0076] The analysis unit can convert utterances into text using speech recognition technology. For example, if a user says, "Let's discuss the progress of the next project," the analysis unit records the utterance as text. The analysis unit can also use speech recognition technology that uses deep learning. For example, an acoustic model can be used to analyze speech data and convert the utterances into text. Furthermore, the analysis unit can also support multiple languages ​​using speech recognition technology. For example, speech in multiple languages, such as English, Japanese, and French, can be converted into text. This allows for accurate conversion of speech data into text. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or can be performed without AI. For example, the analysis unit can input speech data into a generation AI and have the generation AI convert the utterances into text.

[0077] The extraction unit can analyze text using natural language processing technology to identify important keywords and phrases. For example, the extraction unit can analyze text using natural language processing technology to identify important keywords and phrases. For example, the extraction unit can extract important points such as "project progress" and "next steps." The extraction unit can also analyze text using morphological analysis. For example, the extraction unit can extract nouns and verbs from the text and identify important keywords. The extraction unit can also analyze text using grammatical analysis. For example, the extraction unit can analyze sentence structure and identify important phrases. This allows the main points of the discussion to be clearly extracted. Some or all of the above-mentioned processing in the extraction unit can be performed using, for example, AI, or can be performed without using AI. For example, the extraction unit can input text data into a generation AI and have the generation AI extract important points.

[0078] The generation unit can generate illustrations based on a pre-trained database. The generation unit generates appropriate illustrations based on a pre-trained database, for example. For example, for "project progress," it generates illustrations of graphs and charts showing progress. The generation unit can also generate illustrations based on past meeting data. For example, it can generate new illustrations by referring to illustrations used in past meetings. The generation unit can also generate illustrations based on an image database. For example, it can select an appropriate image from the image database and generate an illustration based on that image. This makes it possible to automatically generate illustrations corresponding to the content of the discussion. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on important points into the generation AI and have the generation AI generate the illustrations.

[0079] The creation unit can appropriately arrange text and illustrations and organize them into an easy-to-read layout. For example, the creation unit can appropriately arrange text and illustrations and organize them into an easy-to-read layout. For example, illustrations and text can be arranged at each important point to make the overall flow easy to understand. The creation unit can also adjust the layout taking visual balance into consideration. For example, the creation unit can adjust the arrangement of text and illustrations to create a visually balanced layout. Furthermore, the creation unit can adjust the layout based on the importance of the information. For example, important information can be placed in a prominent position to visually emphasize it. This makes it possible to automatically create a visually easy-to-understand graphic record. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input data of the generated illustrations and text into a generation AI and have the generation AI adjust the layout.

[0080] The collection unit can estimate the user's emotions and adjust the timing of voice data collection based on the emotion data. For example, if the user is nervous, the collection unit starts collecting voice data immediately after the meeting starts and pauses collection when the user relaxes. Furthermore, if the user is relaxed, the collection unit can continue collecting voice data as the meeting progresses and increase collection before an important discussion begins. Furthermore, if the user is excited, the collection unit can increase collection of voice data when the discussion becomes heated and pause collection when the user calms down. This allows the timing of voice data collection to be optimized 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 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 have the generation AI adjust the collection timing.

[0081] The collection unit can change the range of audio data to be collected depending on the progress of the meeting. For example, the collection unit collects the overall discussion at the beginning of the meeting, and as the agenda becomes more specific, it focuses on collecting audio data from specific speakers. In addition, as the meeting progresses, the collection unit can prioritize collecting comments related to an important agenda item when that agenda item comes up. Furthermore, the collection unit can focus on collecting comments related to the conclusion or next steps towards the end of the meeting, thereby covering the entire discussion. This makes it possible to optimize the range of audio data collected depending on the progress 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 meeting progress data into the generation AI and have the generation AI adjust the collection range.

[0082] The collection unit can simultaneously collect speaker identification information when collecting audio data. For example, the collection unit can automatically identify the speaker's name and title when collecting audio data and tag the data. The collection unit can also analyze the speaker's voiceprint, identify individual speakers, and associate them with the audio data. Furthermore, the collection unit can compare the speaker's voiceprint with a meeting participant list and collect speaker identification information in real time. By simultaneously collecting speaker identification information, the content of the discussion can be more accurately understood. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input the audio data and speaker identification information into a generation AI and cause the generation AI to collect the identification information.

[0083] When collecting voice data, the collection unit can set the collection order based on the agenda of the meeting. For example, if the agenda of the meeting is important, the collection unit prioritizes collection of utterances related to that agenda. In addition, if there are multiple agendas, the collection unit can also collect voice data based on a pre-set priority. Furthermore, the collection unit can dynamically change the collection priority based on the importance of the agenda as the meeting progresses. This makes it possible to optimize the collection of voice data based on the agenda 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 meeting agenda data to a generation AI and have the generation AI set the collection order.

[0084] 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's emotions. For example, if the user is nervous, the collection unit can prioritize collecting relaxed utterances to relieve the tension. Furthermore, if the user is relaxed, the collection unit can prioritize collecting important discussions and proposals. Furthermore, if the user is excited, the collection unit can prioritize collecting utterances made during heated discussions. This allows the voice data collection priority to be optimized according to the user's emotions. 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, or without an AI. For example, the collection unit can input the user's emotion data into the generation AI and have the generation AI determine the collection priority.

[0085] When collecting audio data, the collection unit can change the collection method based on the location and time of the meeting. For example, the collection unit collects audio data by applying noise canceling, taking into account the environmental sounds of the conference room. The collection unit can also adjust the audio data collection sensitivity for nighttime meetings, assuming a quiet environment. Furthermore, the collection unit can optimize the audio data collection method by taking into account network delays for online meetings. This makes it possible to optimize the audio data collection method depending on the location and time of the meeting. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input data on the location and time of the meeting into the generation AI and cause the generation AI to change the collection method.

[0086] When collecting voice data, the collection unit can adjust the accuracy of collection based on the positions and fields of expertise of the participants in the meeting. For example, the collection unit can prioritize collecting comments from participants with important positions to increase accuracy. In addition, when a discussion specialized in a specialized field is taking place, the collection unit can accurately collect technical terms in that field. Furthermore, the collection unit can dynamically adjust the accuracy of collection based on the positions and fields of expertise of the participants as the meeting progresses. This makes it possible to optimize the accuracy of voice data collection depending on the positions and fields of expertise of the participants. 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 on the positions and fields of expertise of the participants into the generation AI and cause the generation AI to adjust the collection accuracy.

[0087] The collection unit can monitor the progress of the meeting in real time when collecting audio data and optimize the collection method. For example, the collection unit can monitor the progress of the meeting in real time and strengthen the collection method when an important topic comes up. The collection unit can also dynamically adjust the range and accuracy of the audio data to be collected according to the progress of the meeting. Furthermore, the collection unit can focus on collecting comments related to conclusions and next steps towards the end of the meeting to cover the entire discussion. This makes it possible to optimize the audio data collection method according to the progress 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 meeting progress data to the generation AI and have the generation AI optimize the collection method.

[0088] The analysis unit can estimate the user's emotions and adjust the expression method for the text based on the estimated user emotions. For example, if the user is nervous, the analysis unit can use a simple and easy-to-understand expression method for text generation. Furthermore, if the user is relaxed, the analysis unit can also use an expression method that includes detailed information for text generation. Furthermore, if the user is excited, the analysis unit can also use an emphasized expression method for text generation. This allows the expression method for the text generation to be optimized according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI adjust the expression method for the text generation.

[0089] When analyzing voice data, the analysis unit can convert the speech data into text taking into account the speaker's emotions and tone. For example, the analysis unit can convert the speech data into text by bolding or changing the color of parts emphasized by the speaker. Furthermore, if the speaker is relaxed, the analysis unit can convert the speech data into text in a calm tone. Furthermore, if the speaker is excited, the analysis unit can convert the speech data into text in an expression method that reflects the speaker's emotions. This enables the speech data to reflect the speaker's emotions and tone. Emotion estimation is achieved using an emotion estimation function, for example, with 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 such examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the speaker's emotion data into the generation AI and have the generation AI adjust the expression method for the text data.

[0090] When analyzing the audio data, the analysis unit can set a priority for text conversion based on the agenda of the meeting. For example, the analysis unit can prioritize text conversion of statements related to important agenda items. The analysis unit can also dynamically change the priority for text conversion based on the importance of the agenda items as the meeting progresses. Furthermore, the analysis unit can prioritize text conversion of statements related to conclusions and next steps toward the end of the meeting. This makes it possible to optimize the priority for text conversion based on the agenda of the meeting. Some or all of the above-described processing by the analysis unit may be performed using, or without, AI, for example. For example, the analysis unit can input meeting agenda data into a generation AI and cause the generation AI to set the priority for text conversion.

[0091] When analyzing audio data, the analysis unit can improve the accuracy of the text conversion by taking into account the context of the utterance. For example, the analysis unit analyzes the context before and after the utterance and converts it into text using an appropriate expression method. The analysis unit can also convert the text in accordance with the context by taking into account the intention of the utterance. Furthermore, the analysis unit can dynamically adjust the accuracy of the text conversion by taking into account the context of the utterance according to the progress of the meeting. This makes it possible to convert the text into text taking into account the context of the utterance. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input context data of the utterance into the generation AI and cause the generation AI to improve the accuracy of the text conversion.

[0092] The analysis unit can estimate the user's emotions and adjust the length of the text based on the estimated user emotions. For example, if the user is in a hurry, the analysis unit can generate a short, to-the-point text. Furthermore, if the user is relaxed, the analysis unit can generate a longer text that includes detailed information. Furthermore, if the user is excited, the analysis unit can generate a text in an expression that reflects the user's emotions. This allows the length of the text to be optimized 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, an AI, or without an AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI adjust the length of the text.

[0093] When analyzing the audio data, the analysis unit can automatically recognize the speaker's technical terms and industry jargon and convert them into text. For example, the analysis unit can automatically recognize technical terms used by the speaker and convert them into text accurately. The analysis unit can also automatically recognize industry-specific terms and convert them into text using an appropriate expression method. Furthermore, the analysis unit can dynamically recognize and convert technical terms and industry jargon into text as the meeting progresses. This allows the technical terms and industry jargon to be accurately converted into text. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on technical terms and industry jargon into a generation AI and have the generation AI perform the recognition and conversion into text.

[0094] When analyzing the audio data, the analysis unit can adjust the order of transcription based on the progress of the meeting. For example, the analysis unit can prioritize transcription of statements related to important agenda items according to the progress of the meeting. The analysis unit can also dynamically change the order of transcription based on the importance of the agenda items as the meeting progresses. Furthermore, the analysis unit can prioritize transcription of statements related to conclusions and next steps toward the end of the meeting. This makes it possible to optimize the order of transcription according to the progress of the meeting. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, AI, for example. For example, the analysis unit can input data on the progress of the meeting into the generation AI and cause the generation AI to adjust the order of transcription.

[0095] When analyzing audio data, the analysis unit can improve the accuracy of the text by taking into account the speaker's attribute information. The analysis unit can convert the speech into text using an appropriate expression method, for example, taking into account the speaker's position and field of expertise. The analysis unit can also improve the accuracy of the text by referring to the speaker's past speech history. Furthermore, the analysis unit can dynamically consider the speaker's attribute information and adjust the accuracy of the text as the meeting progresses. This makes it possible to convert the speech into text taking into account the speaker's attribute information. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the speaker's attribute information data into the generation AI and cause the generation AI to improve the accuracy of the text.

[0096] The extraction unit can estimate the user's emotions and adjust the extraction criteria for key points based on the estimated user emotions. For example, if the user is nervous, the extraction unit can extract key points using simple and easy-to-understand criteria. Furthermore, if the user is relaxed, the extraction unit can extract key points using criteria that include detailed information. Furthermore, if the user is excited, the extraction unit can extract key points using emphasized criteria. This allows the extraction criteria for key points to be optimized 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 extraction unit can be performed using, for example, an AI, or without an AI. For example, the extraction unit can input the user's emotion data into the generation AI and have the generation AI adjust the extraction criteria.

[0097] The extraction unit can extract important points from the text-converted discussion content, taking into account the speaker's intention and purpose. The extraction unit, for example, analyzes the speaker's intention and extracts important points. The extraction unit can also extract important points using appropriate criteria, taking into account the speaker's purpose. Furthermore, the extraction unit can extract important points by dynamically taking into account the speaker's intention and purpose as the meeting progresses. This makes it possible to extract important points taking into account the speaker's intention and purpose. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input data on the speaker's intention and purpose into the generation AI and cause the generation AI to extract important points.

[0098] The extraction unit can extract important points from the text-converted discussion content based on the meeting agenda. The extraction unit extracts important points based on, for example, keywords related to the meeting agenda. The extraction unit can also dynamically extract important points based on the importance of the agenda as the meeting progresses. Furthermore, the extraction unit can prioritize extracting important points related to conclusions and next steps toward the end of the meeting. This makes it possible to extract important points based on the meeting agenda. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input meeting agenda data into a generation AI and cause the generation AI to extract important points.

[0099] The extraction unit can extract important points from the text-converted discussion content, taking into account the frequency of comments and emphasized parts. For example, the extraction unit extracts important points based on frequently-commented parts. The extraction unit can also analyze emphasized parts and extract them as important points. Furthermore, the extraction unit can extract important points by dynamically taking into account the frequency of comments and emphasized parts as the meeting progresses. This makes it possible to extract important points taking into account the frequency of comments and emphasized parts. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input data on the frequency of comments and emphasized parts into the generation AI and cause the generation AI to extract important points.

[0100] The extraction unit can estimate the user's emotions and determine the priority of points to be extracted based on the estimated user emotions. For example, if the user is nervous, the extraction unit can prioritize extracting relaxed utterances. Furthermore, if the user is relaxed, the extraction unit can also prioritize extracting important discussions and proposals. Furthermore, if the user is excited, the extraction unit can prioritize extracting utterances made at the height of a heated discussion. This allows the priority of points to be extracted to be optimized 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 extraction unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the extraction unit can input the user's emotion data into the generation AI and have the generation AI determine the priority of points to be extracted.

[0101] The extraction unit can extract important points from the text-converted discussion content based on the speaker's field of expertise and position. The extraction unit extracts important points based on, for example, keywords related to the speaker's field of expertise. The extraction unit can also preferentially extract important points based on the speaker's position. Furthermore, the extraction unit can extract important points by dynamically considering the speaker's field of expertise and position as the meeting progresses. This makes it possible to extract important points based on the speaker's field of expertise and position. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input data on the speaker's field of expertise and position into the generation AI and cause the generation AI to extract important points.

[0102] The extraction unit can extract important points from the text-converted discussion content, taking into account the progress of the meeting. For example, the extraction unit prioritizes extraction of comments related to important topics according to the progress of the meeting. The extraction unit can also dynamically extract important points based on the importance of the topics as the meeting progresses. Furthermore, the extraction unit can prioritize extraction of important points related to conclusions and next steps towards the end of the meeting. This makes it possible to extract important points according to the progress of the meeting. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input data on the progress of the meeting into the generation AI and cause the generation AI to extract important points.

[0103] The extraction unit can extract important points from the text-converted discussion content while taking into account the speaker's attribute information. The extraction unit extracts important points while taking into account, for example, the speaker's position or field of expertise. The extraction unit can also extract important points while referring to the speaker's past speech history. Furthermore, the extraction unit can extract important points while dynamically taking into account the speaker's attribute information as the meeting progresses. This makes it possible to extract important points while taking into account the speaker's attribute information. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the speaker's attribute information data into the generation AI and cause the generation AI to extract important points.

[0104] The generation unit can estimate the user's emotions and adjust the way the illustration is expressed based on the estimated user's emotions. For example, if the user is nervous, the generation unit generates a simple and easy-to-understand illustration. Furthermore, if the user is relaxed, the generation unit can generate an illustration containing detailed information. Furthermore, if the user is excited, the generation unit can generate an illustration with an emphasized expression. This allows the way the illustration is expressed to be optimized according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using, for example, an AI, or may be performed without using an 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 way the illustration is expressed.

[0105] The generation unit can generate an illustration that reflects the speaker's intention and purpose based on the extracted important points. The generation unit, for example, analyzes the speaker's intention and generates an illustration based on that. The generation unit can also generate an appropriate illustration by taking the speaker's purpose into consideration. Furthermore, the generation unit can generate an illustration by dynamically taking the speaker's intention and purpose into consideration as the meeting progresses. This makes it possible to generate an illustration that reflects the speaker's intention and purpose. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on the speaker's intention and purpose into the generation AI and have the generation AI generate an illustration.

[0106] The generation unit can generate illustrations related to the meeting agenda based on the extracted important points. The generation unit generates appropriate illustrations based on, for example, keywords related to the meeting agenda. The generation unit can also dynamically generate illustrations based on the importance of the agenda as the meeting progresses. Furthermore, the generation unit can prioritize generating illustrations related to conclusions and next steps toward the end of the meeting. This makes it possible to generate illustrations related to the meeting agenda. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input meeting agenda data into a generation AI and cause the generation AI to generate illustrations.

[0107] The generation unit can generate an illustration that takes into account the context of the utterance based on the extracted important points. The generation unit, for example, analyzes the context before and after the utterance and generates an appropriate illustration. The generation unit can also generate an illustration that is in line with the context by taking into account the intention of the utterance. Furthermore, the generation unit can dynamically generate an illustration by taking into account the context of the utterance according to the progress of the meeting. This makes it possible to generate an illustration that takes into account the context of the utterance. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input context data of the utterance into a generation AI and cause the generation AI to generate an illustration.

[0108] The generation unit can estimate the user's emotions and adjust the style of the illustration based on the estimated user's emotions. For example, if the user is nervous, the generation unit can generate an illustration in a simple and calm style. If the user is relaxed, the generation unit can also generate an illustration in a detailed and colorful style. If the user is excited, the generation unit can also generate an illustration in an emphasized style. This allows the style of the illustration to be optimized according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the generation unit can be performed using AI, for example, or without 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 style of the illustration.

[0109] The generation unit can generate illustrations related to the speaker's field of expertise and position based on the extracted important points. The generation unit generates appropriate illustrations based on, for example, keywords related to the speaker's field of expertise. The generation unit can also generate related illustrations based on the speaker's position. Furthermore, the generation unit can dynamically generate illustrations taking into account the speaker's field of expertise and position as the meeting progresses. This makes it possible to generate illustrations related to the speaker's field of expertise and position. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input data on the speaker's field of expertise and position into the generation AI and cause the generation AI to generate illustrations.

[0110] The generation unit can generate illustrations that take into account the progress of the meeting based on the extracted important points. For example, the generation unit prioritizes generating illustrations related to important agenda items according to the progress of the meeting. The generation unit can also dynamically generate illustrations based on the importance of the agenda items as the meeting progresses. Furthermore, the generation unit can prioritize generating illustrations related to conclusions and next steps toward the end of the meeting. This makes it possible to generate illustrations 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, AI, or may be performed without using AI. For example, the generation unit can input data on the progress of the meeting into the generation AI and cause the generation AI to generate illustrations.

[0111] The generation unit can generate illustrations that reflect the speaker's attribute information based on the extracted important points. The generation unit generates appropriate illustrations, for example, by taking into account the speaker's job title and field of expertise. The generation unit can also generate related illustrations by referring to the speaker's past speech history. Furthermore, the generation unit can generate illustrations by dynamically taking into account the speaker's attribute information as the meeting progresses. This makes it possible to generate illustrations that reflect the speaker's attribute information. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the speaker's attribute information data into the generation AI and cause the generation AI to generate an illustration.

[0112] The creation unit can estimate the user's emotions and adjust the layout of the graphic record based on the estimated user emotions. For example, if the user is nervous, the creation unit can provide a simple and easy-to-understand layout. Furthermore, if the user is relaxed, the creation unit can provide a layout that includes detailed information. Furthermore, if the user is excited, the creation unit can provide an emphasized layout. This allows the layout of the graphic record to be optimized according to the user's emotions. 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 creation unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the creation unit can input the user's emotion data into the generation AI and have the generation AI adjust the layout.

[0113] The creation unit can combine the generated illustrations and text in a layout that reflects the speaker's intention and purpose. For example, the creation unit can analyze the speaker's intention and combine the illustrations and text in a layout based on that analysis. The creation unit can also combine the illustrations and text in an appropriate layout, taking into account the speaker's purpose. Furthermore, the creation unit can adjust the layout dynamically taking into account the speaker's intention and purpose as the meeting progresses. This enables graphic recording of a layout that reflects the speaker's intention and purpose. Some or all of the above-mentioned processing in the creation unit may be performed using, or without, AI. For example, the creation unit can input data on the speaker's intention and purpose into the generation AI and have the generation AI adjust the layout.

[0114] The creation unit can appropriately arrange the generated illustrations and text based on the meeting agenda. For example, the creation unit arranges the illustrations and text in an appropriate layout based on keywords related to the meeting agenda. The creation unit can also dynamically adjust the layout based on the importance of the agenda as the meeting progresses. Furthermore, the creation unit can prioritize the arrangement of illustrations and text related to conclusions and next steps toward the end of the meeting. This enables a graphic record with an appropriate arrangement based on the meeting agenda. Some or all of the above-mentioned processing in the creation unit may be performed using, or without, AI, for example. For example, the creation unit can input meeting agenda data into the generation AI and have the generation AI adjust the layout.

[0115] The creation unit can organize the generated illustrations and text into an easy-to-read layout taking into account the context of the utterance. For example, the creation unit analyzes the context before and after the utterance and arranges the illustrations and text in an appropriate layout. The creation unit can also arrange the illustrations and text in a layout that matches the context taking into account the intention of the utterance. Furthermore, the creation unit can dynamically adjust the layout taking into account the context of the utterance as the meeting progresses. This enables graphic recording with an easy-to-read layout that takes into account the context of the utterance. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input context data of the utterance into the generation AI and have the generation AI adjust the layout.

[0116] The creation unit can estimate the user's emotions and adjust the display method of the graphic record based on the estimated user emotions. For example, if the user is nervous, the creation unit can provide a simple and easy-to-understand display method. Furthermore, if the user is relaxed, the creation unit can provide a display method including detailed information. Furthermore, if the user is excited, the creation unit can provide an emphasized display method. This allows the display method of the graphic record to be optimized according to the user's emotions. 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 creation unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the creation unit can input the user's emotion data into the generation AI and have the generation AI adjust the display method.

[0117] The creation unit can appropriately arrange the generated illustrations and text based on the speaker's field of expertise and position. For example, the creation unit arranges illustrations and text in an appropriate layout based on keywords related to the speaker's field of expertise. The creation unit can also prioritize the arrangement of related illustrations and text based on the speaker's position. Furthermore, the creation unit can dynamically adjust the layout taking into account the speaker's field of expertise and position as the meeting progresses. This enables a graphic record with an appropriate arrangement based on the speaker's field of expertise and position. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input data on the speaker's field of expertise and position into the generation AI and have the generation AI adjust the layout.

[0118] The creation unit can organize the generated illustrations and text into a layout based on the progress of the meeting. For example, the creation unit can prioritize the placement of illustrations and text related to important agenda items according to the progress of the meeting. The creation unit can also dynamically adjust the layout based on the importance of the agenda items as the meeting progresses. Furthermore, the creation unit can prioritize the placement of illustrations and text related to conclusions and next steps toward the end of the meeting. This enables a graphic record with an optimal layout according to the progress of the meeting. Some or all of the above-mentioned processing in the creation unit may be performed using, or without, AI, for example. For example, the creation unit can input meeting progress data into the generation AI and have the generation AI adjust the layout.

[0119] The creation unit can organize the generated illustrations and text into an easy-to-read layout that reflects the speaker's attribute information. The creation unit arranges the illustrations and text in an appropriate layout, taking into account, for example, the speaker's position and field of expertise. The creation unit can also arrange related illustrations and text by referring to the speaker's past speech history. Furthermore, the creation unit can adjust the layout by dynamically considering the speaker's attribute information as the meeting progresses. This enables a graphic record with an easy-to-read layout that reflects the speaker's attribute information. Some or all of the above-mentioned processing in the creation unit may be performed, for example, using AI, or may be performed without using AI. For example, the creation unit can input the speaker's attribute information data into the generation AI and have the generation AI adjust the layout. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, extraction unit, generation unit, and creation unit, described above, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects audio data using the microphone 38B of the smart device 14 or a microphone installed in the conference room. The analysis unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, converts the audio data into text. The extraction unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, extracts important points from the converted text of the discussion. The creation unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, generates illustrations corresponding to the extracted important points. The creation unit, implemented, for example, by the control unit 46A of the smart device 14, combines the generated illustrations and text to create a graphic record. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, extraction unit, generation unit, and creation unit, described above, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects audio data using the microphone 238 of the smart glasses 214 or a microphone installed in the conference room. The analysis unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, converts the audio data into text. The extraction unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, extracts important points from the converted text of the discussion. The creation unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, generates illustrations corresponding to the extracted important points. The creation unit, implemented, for example, by the control unit 46A of the smart glasses 214, combines the generated illustrations and text to create a graphic record. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, analysis unit, extraction unit, generation unit, and creation 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 collects audio data using the microphone 238 of the headset-type terminal 314 or a microphone installed in the conference room. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, converts the audio data into text. The extraction unit, realized, for example, by the specific processing unit 290 of the data processing device 12, extracts important points from the converted text of the discussion. The creation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, generates illustrations corresponding to the extracted important points. The creation unit, realized, for example, by the control unit 46A of the headset-type terminal 314, combines the generated illustrations and text to create a graphic record. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, analysis unit, extraction unit, generation unit, and creation 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 collects audio data using the microphone 238 of the robot 414 or a microphone installed in the conference room. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, converts the audio data into text. The extraction unit, realized, for example, by the specific processing unit 290 of the data processing device 12, extracts important points from the converted text of the discussion. The creation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, generates illustrations corresponding to the extracted important points. The creation unit, realized, for example, by the control unit 46A of the robot 414, combines the generated illustrations and text to create a graphic record.

[0120] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0121] The collection unit can also adjust the method of collecting voice data depending on the type of device used by the meeting participants. For example, if a participant is using a laptop, the built-in microphone can be used to collect voice data. If a participant is using a tablet, an external microphone can be connected to collect voice data. Furthermore, if a participant is using a wearable device, the device's sensors can be used to collect voice data. This allows the collection unit to provide the optimal method of collecting voice data depending on the participant's device.

[0122] When analyzing audio data, the analysis unit can improve the accuracy of the text conversion by taking into account the speaker's speaking speed and tone of voice. For example, if the speaker speaks quickly, the analysis unit can adjust the speaking speed before converting to text. Also, if the speaker speaks in a low voice, the analysis unit can adjust the volume of the audio data before converting to text. Furthermore, if the speaker is speaking emotionally, the analysis unit can convert to text using an expression method that reflects that emotion. This enables the analysis unit to convert to text while taking into account the speaker's speaking speed and tone of voice.

[0123] The extraction unit can extract important points from the text-converted discussion content, taking into account the speaker's past speech history. For example, if a speaker has made an important proposal in the past, important points can be extracted based on that speech history. Also, if a speaker has previously determined the direction of a discussion, important points can be extracted by referring to that speech history. Furthermore, if a speaker has previously reached a conclusion in a discussion, important points can be extracted by taking into account that speech history. This enables the extraction unit to extract important points by taking into account the speaker's past speech history.

[0124] The generation unit can generate illustrations that reflect the progress of the meeting in real time based on the extracted important points. For example, illustrations can be dynamically generated based on the importance of the agenda items as the meeting progresses. Also, towards the end of the meeting, illustrations related to the conclusion or next steps can be generated preferentially. Furthermore, if a new agenda item is added while the meeting is in progress, an illustration corresponding to that agenda item can be instantly generated. This enables the generation unit to generate illustrations that reflect the progress of the meeting in real time.

[0125] The creation unit can appropriately arrange the generated illustrations and text based on the job titles and areas of expertise of the meeting participants. For example, if the speaker is a project manager, illustrations and text related to that statement can be placed in a prominent position. Also, if the speaker is a technical expert, technical illustrations and text related to that statement can be appropriately placed. Furthermore, if the speaker is a marketing specialist, illustrations and text containing marketing materials related to that statement can be placed. This enables the creation unit to create a graphic record with appropriate placement based on the job titles and areas of expertise of the meeting participants.

[0126] The collection unit can estimate the user's emotions and filter the collected voice data based on the estimated user's emotions. For example, if the user is nervous, relaxed utterances can be preferentially collected to relieve the tension. Also, if the user is relaxed, important discussions and proposals can be preferentially collected. Furthermore, if the user is excited, utterances made at the time of the heated discussion can be preferentially collected. This makes it possible to optimize the filtering of voice data according to the user's emotions.

[0127] The analysis unit can estimate the user's emotions and adjust the expression method for converting to text based on the estimated user emotions. For example, if the user is nervous, a simple and easy-to-understand expression method can be used for converting to text. If the user is relaxed, an expression method including detailed information can be used for converting to text. Furthermore, if the user is excited, an emphasized expression method can be used for converting to text. This makes it possible to optimize the expression method for converting to text according to the user's emotions.

[0128] The extraction unit can estimate the user's emotions and adjust the extraction criteria for important points based on the estimated user emotions. For example, if the user is nervous, simple and easy-to-understand criteria can be used to extract important points. If the user is relaxed, important points can be extracted using criteria that include detailed information. Furthermore, if the user is excited, important points can be extracted using emphasized criteria. This makes it possible to optimize the extraction criteria for important points according to the user's emotions.

[0129] The generation unit can estimate the user's emotions and adjust the way the illustration is expressed based on the estimated user's emotions. For example, if the user is nervous, a simple and easy-to-understand illustration can be generated. If the user is relaxed, an illustration containing detailed information can be generated. Furthermore, if the user is excited, an illustration can be generated with an emphasized expression. This makes it possible to optimize the way the illustration is expressed according to the user's emotions.

[0130] The creation unit can estimate the user's emotion and adjust the layout of the graphic record based on the estimated user's emotion. For example, if the user is nervous, a simple and easy-to-understand layout can be provided. If the user is relaxed, a layout including detailed information can be provided. Furthermore, if the user is excited, an emphasized layout can be provided. In this way, the layout of the graphic record can be optimized according to the user's emotion.

[0131] The processing flow of the second embodiment will be briefly explained below.

[0132] Step 1: The collection unit collects audio data from the meeting. The collection unit can collect audio data, for example, using microphones installed in the conference room or participants' smartphones. For example, a microphone can be installed in the center of the conference room and everyone's comments recorded. The collection unit can also collect audio data using participants' smartphones. For example, audio data can be collected using a dedicated app. Step 2: The analysis unit analyzes the voice data collected by the collection unit and converts the content of the discussion into text. For example, the analysis unit converts the utterances into text using voice recognition technology. For example, if someone says, "Let's discuss the progress of the next project," it will record this as text. Step 3: The extraction unit extracts key points from the discussion content converted into text by the analysis unit. For example, the extraction unit uses natural language processing technology to analyze the text and identify important keywords and phrases. For example, it extracts key points such as "project progress" and "next steps." Step 4: The generator generates illustrations corresponding to the key points extracted by the extractor. For example, the generator generates appropriate illustrations based on a pre-trained database. For example, for "Project Progress," it generates illustrations of graphs and charts showing progress. Step 5: The creation unit creates a graphic record by combining the illustrations and text generated by the generation unit. For example, the creation unit arranges the text and illustrations appropriately and creates an easy-to-read layout. For example, the creation unit arranges illustrations and text at each important point to make the overall flow easy to understand.

[0133] 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.

[0134] 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.

[0135] 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.

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

[0137] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0138] 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.

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] The 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.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (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).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0169] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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).

[0190] 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.

[0191] 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."

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] [Explanation of symbols]

[0205] 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 collects MTG audio data; an analysis unit that analyzes the voice data collected by the collection unit and converts the content of the discussion into text; an extraction unit that extracts important points based on the discussion content converted into text by the analysis unit; a generating unit that generates an illustration corresponding to the important points extracted by the extracting unit; a creation unit that creates a graphic record by combining the illustration and text generated by the creation unit. A system characterized by:

2. The collecting unit Audio data is collected using microphones installed in the conference room or participants' smartphones.

2. The system of claim 1.

3. The analysis unit Convert what is said into text using speech recognition technology 2. The system of claim 1.

4. The extraction unit Analyze text using natural language processing techniques to identify important keywords and phrases 2. The system of claim 1.

5. The generation unit Generate illustrations based on a pre-trained database 2. The system of claim 1.

6. The creation unit Arrange text and illustrations appropriately to create an easy-to-read layout 2. The system of claim 1.

7. 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.

8. The collecting unit Change the scope of audio data collected as the meeting progresses 2. The system of claim 1.

Images