System

Abstract

An object of the system according to the embodiment is to search for necessary information in real time during a meeting and automatically generate materials.SOLUTION: A system according to an embodiment includes an analysis unit, a search unit, and a generation unit. The analysis unit analyzes the conversation during the conference in real time. The search unit searches the database based on the keyword extracted by the analysis unit. The generation unit automatically generates the material based on the information retrieved by the retrieval unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem that it is difficult to quickly search for necessary information during a meeting and automatically generate materials.

[0005] The system according to the embodiment aims to search for necessary information in real time during a meeting and automatically generate materials. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a search unit, and a generation unit. The analysis unit analyzes conversations during a meeting in real time. The search unit searches a database based on keywords extracted by the analysis unit. The generation unit automatically generates materials based on the information searched by the search unit. [Effects of the Invention]

[0007] The system according to the embodiment can search for necessary information during a meeting in real time and automatically generate materials. [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 conference support system according to an embodiment of the present invention analyzes conversations during a conference in real time, searches for relevant information, and automatically generates materials. The conference support system analyzes conversations during a conference in real time, extracts important keywords and phrases, and searches for related information from a database. Furthermore, the conference support system automatically generates materials based on the searched information. For example, if a participant says, "I feel like I've heard a similar case before. Is there a history of that?" during a conference, the conference support system analyzes the conversation and searches for relevant information from a database. Furthermore, if a participant asks, "Where is that document?", the conference support system searches for the relevant document from the database and instantly displays it. Furthermore, if the contents of a conference need to be shared in another conference, the participant can request, "Please document this conference." Materials are automatically generated. This allows the conference support system to instantly provide necessary information during a conference, improving the efficiency of the conference. For example, even if a participant forgets what that was during a conference, the conference support system can provide real-time support and instantly provide the necessary information. This allows the conference to proceed smoothly and efficiently.

[0029] A conference support system according to an embodiment includes an analysis unit, a search unit, and a generation unit. The analysis unit analyzes conversations during a conference in real time. For example, the analysis unit converts the conversation into text data using speech recognition technology and extracts important keywords and phrases. The analysis unit can also understand the context of the conversation and extract related information using natural language processing technology. For example, the analysis unit analyzes statements made during a conference in real time and extracts important keywords. The search unit searches a database based on the keywords extracted by the analysis unit. The search unit quickly searches for related information using, for example, an SQL database or a NoSQL database. The search unit can also search for highly relevant information using keyword matching or context analysis. For example, the search unit searches a database based on the extracted keywords to obtain related materials or minutes of past meetings. The generation unit automatically generates materials based on the information retrieved by the search unit. For example, the generation unit automatically generates minutes or presentation materials using a text generation AI (e.g., LLM). The generation unit can also use multimodal generation AI to generate materials that include not only text data but also images and graphs. For example, the generation unit automatically generates meeting minutes based on the searched information. This allows the meeting support system according to the embodiment to analyze conversations during meetings in real time, search for related information, and automatically generate materials. This improves the efficiency of meetings and enables them to proceed smoothly.

[0030] The analysis unit can analyze conversations during meetings in real time and extract important keywords and phrases. The analysis unit can convert the conversation into text data using, for example, speech recognition technology. For example, the analysis unit can recognize speech spoken during meetings in real time and save it as text data. The analysis unit can also understand the context of the conversation and extract important keywords and phrases using natural language processing technology. For example, the analysis unit can extract keywords that appear frequently in the conversation and evaluate their importance. The analysis unit can also extract important phrases based on the context of the conversation. For example, the analysis unit can analyze the flow of the conversation and identify important statements. This allows the content of the meeting to be efficiently understood by extracting important keywords and phrases during the meeting in real time. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input the audio data of the conversation into a generation AI and have the generation AI extract important keywords and phrases.

[0031] The search unit can search for related information from a database. The search unit can search for related information using, for example, an SQL database. For example, the search unit can search for related materials in a database based on extracted keywords. The search unit can also perform flexible searches using a NoSQL database. For example, the search unit can search for highly relevant information using keyword matching. The search unit can also search for context-based information using context analysis. For example, the search unit can understand the context of a conversation and search for relevant minutes of past meetings or email exchanges. This allows necessary information to be quickly obtained by searching for related information from a database. Some or all of the above-mentioned processing in the search unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the search unit can input the extracted keywords into a generation AI and cause the generation AI to search for related information.

[0032] The generation unit can generate minutes and presentation materials based on the content of remarks or discussions made during a meeting. The generation unit automatically generates minutes and presentation materials, for example, using a text generation AI (e.g., LLM). For example, the generation unit automatically generates minutes based on remarks made during a meeting. The generation unit can also generate materials including not only text data but also images and graphs using a multimodal generation AI. For example, the generation unit automatically generates presentation materials based on the content of discussions made during a meeting. The generation unit can also automatically generate materials based on searched information. For example, the generation unit generates new materials based on minutes and related materials of past meetings searched by the search unit. This allows for efficient creation of meeting records by automatically generating materials based on the content of remarks and discussions made during a meeting. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can input data of remarks made during a meeting into the generation AI and cause the generation AI to generate minutes and presentation materials.

[0033] The search unit can search a database for minutes of past meetings or related materials, and email exchanges. The search unit, for example, searches a database for minutes of past meetings. For example, the search unit searches for minutes used in past meetings and acquires related information. The search unit can also search a database for related materials. For example, the search unit searches for presentation materials used in past meetings. The search unit can also search a database for email exchanges. For example, the search unit searches for email exchanges related to past meetings and acquires related information. This allows the contents of past meetings to be quickly referenced by searching for minutes and related materials of past meetings. Some or all of the above-mentioned processing in the search unit may be performed using, or without, a generation AI. For example, the search unit can input minutes and related materials of past meetings into the generation AI and cause the generation AI to search for related information.

[0034] The generation unit can automatically generate materials based on the searched information. The generation unit automatically generates materials based on the searched information, for example, using a text generation AI (e.g., LLM). For example, the generation unit automatically generates minutes based on the information searched by the search unit. The generation unit can also generate materials including not only text data but also images and graphs using a multimodal generation AI. For example, the generation unit automatically generates presentation materials based on the searched information. The generation unit can also generate detailed reports based on the searched information. For example, the generation unit generates a report summarizing the contents of a meeting based on the searched information. In this way, necessary materials can be quickly created by automatically generating materials based on the searched information. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can input the searched information into the generation AI and cause the generation AI to generate materials.

[0035] The analysis unit can analyze the tone and speed of speech made during a meeting and prioritize extraction of highly important speech. The analysis unit, for example, analyzes the tone of speech made during a meeting. For example, the analysis unit analyzes the audio waveform of the speech and evaluates the pitch of the tone. The analysis unit can also analyze the speed of speech. For example, the analysis unit measures the speed of speech and evaluates its importance. The analysis unit can also analyze changes in the tone and speed of speech to identify highly important speech. For example, if the tone and speed of a speech are high, the analysis unit determines that the speech is highly important and prioritizes extraction. If the tone and speed of a speech are low and the speed is slow, the analysis unit can determine that the speech is low in importance and postpone it. Furthermore, if the tone or speed of a speech suddenly changes, the analysis unit can determine that the speech requires attention and prioritize extraction. In this way, highly important speech can be efficiently extracted by analyzing the tone and speed of speech. Some or all of the above-described processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit may input speech data to the generation AI and have the generation AI analyze the tone and speed.

[0036] The analysis unit can analyze the context of statements made during a meeting and automatically link related past statements and materials. The analysis unit, for example, analyzes the context of statements made during a meeting. For example, the analysis unit analyzes the content before and after a statement to understand the context. The analysis unit can also identify related topics and link past statements and materials. For example, the analysis unit automatically links related statements made in past meetings from the context of a statement. The analysis unit can also automatically link related materials from the context of a statement. Furthermore, the analysis unit can automatically link related email exchanges from the context of a statement. In this way, by analyzing the context of a statement, related past statements and materials can be efficiently linked. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input text data of a statement into a generation AI and have the generation AI analyze the context and generate links.

[0037] The analysis unit can analyze the frequency and patterns of utterances made during a meeting and extract important keywords related to a specific theme. The analysis unit, for example, analyzes the frequency of utterances made during a meeting. For example, the analysis unit measures the frequency of utterances and identifies important keywords. The analysis unit can also analyze utterance patterns. For example, the analysis unit analyzes the temporal pattern of utterances and extracts keywords related to a specific theme. The analysis unit can also analyze the frequency and patterns of utterances and identify keywords important for the progress of the meeting. For example, the analysis unit determines and extracts keywords that are frequently uttered as important. The analysis unit can also extract keywords related to a specific theme from the utterance patterns. Furthermore, the analysis unit can analyze the frequency and patterns of utterances and identify keywords important for the progress of the meeting. In this way, by analyzing the frequency and patterns of utterances, important keywords related to a specific theme can be efficiently extracted. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input text data of utterances into the generation AI and have the generation AI perform frequency and pattern analysis.

[0038] The analysis unit can automatically translate the language of speech made during a meeting and perform multilingual analysis. The analysis unit, for example, automatically translates the language of speech made during a meeting. For example, the analysis unit translates speech audio data in real time and saves it as text data. The analysis unit can also automatically detect the language of speech and translate it into an appropriate language. For example, the analysis unit automatically detects the language of speech and translates it into an appropriate language using a generation AI. The analysis unit can also provide multilingual analysis results and display them to meeting participants. For example, the analysis unit generates multilingual analysis results based on the translated text data and displays them to meeting participants. This enables multilingual analysis by automatically translating the language of speech. Some or all of the above-described processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input speech audio data of speech into a generation AI and have the generation AI perform translation and analysis.

[0039] The analysis unit can analyze audio data of speech made during a meeting and provide feedback to improve speech recognition accuracy. The analysis unit, for example, analyzes audio data of speech made during a meeting. For example, the analysis unit can remove noise from the audio data to improve speech recognition accuracy. The analysis unit can also analyze features of the audio data and suggest improvements to the speech recognition. For example, the analysis unit can analyze the audio data of speech and provide feedback to improve speech recognition accuracy using a generation AI. The analysis unit can also remove noise from the audio data to improve speech recognition accuracy using a generation AI. The analysis unit can also analyze the audio data of speech and suggest improvements to speech recognition using a generation AI. In this way, feedback to improve speech recognition accuracy can be provided by analyzing the audio data. Some or all of the above-described processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input the audio data of speech to the generation AI and cause the generation AI to provide feedback to improve speech recognition accuracy.

[0040] The analysis unit can remove background noise from speech during a meeting to improve analysis accuracy. The analysis unit, for example, removes background noise from speech during a meeting. For example, the analysis unit can use noise filtering technology to remove background noise from speech audio data. The analysis unit can also use a noise reduction algorithm to clear speech audio data. For example, the analysis unit can remove background noise from speech in real time and improve analysis accuracy using a generation AI. The analysis unit can also use noise removal technology to clear speech audio data using a generation AI. Furthermore, the analysis unit can remove background noise from speech in real time and improve analysis accuracy using a generation AI. In this way, removing background noise can improve analysis accuracy. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input speech audio data to a generation AI and have the generation AI remove background noise.

[0041] The search unit can evaluate the reliability of information in the database and prioritize searching for highly reliable information. The search unit, for example, evaluates the reliability of information in the database. For example, the search unit evaluates the reliability of information based on the reliability of the information source. The search unit can also evaluate the consistency of information. For example, the search unit evaluates whether the content of the information is consistent with other highly reliable information. The search unit can also evaluate the update frequency of information and prioritize searching for the latest information. For example, the search unit prioritizes displaying the latest information based on the update date and time of the information. In this way, by evaluating the reliability of the information, highly reliable information can be prioritized and searched for. Some or all of the above-mentioned processing in the search unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the search unit can input information in the database into a generation AI and have the generation AI perform the reliability evaluation and search.

[0042] The search unit can prioritize searching for the most recent information by taking into account the update frequency of the information in the database. The search unit, for example, evaluates the update frequency of the information in the database. For example, the search unit prioritizes displaying the most recent information based on the update date and time of the information. The search unit can also evaluate the number of times the information has been updated and prioritize searching for information that has been updated more frequently. For example, the search unit prioritizes searching and displaying information that has been updated more frequently. This allows the most recent information to be prioritized by taking into account the update frequency of the information. Some or all of the above-described processing in the search unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the search unit can input information in the database into the generation AI and have the generation AI evaluate the update frequency and perform the search.

[0043] The search unit can evaluate the relevance of information in the database and prioritize searching for highly relevant information. The search unit, for example, evaluates the relevance of information in the database. For example, the search unit uses keyword matching to search for highly relevant information. The search unit can also use context analysis to search for context-based information. For example, the search unit can prioritize displaying highly relevant information based on the degree of match of keywords in the information. The search unit can also analyze the context of the information and prioritize searching for the most relevant information. In this way, by evaluating the relevance of the information, highly relevant information can be prioritized for search. Some or all of the above-mentioned processing in the search unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the search unit can input information in the database into a generation AI and have the generation AI perform the relevance evaluation and search.

[0044] The search unit can organize information in the database by category, enabling searches by category. For example, the search unit organizes information in the database by category. For example, the search unit can classify information by topic and provide searches by category. The search unit can also classify information by time and provide searches by category. For example, the search unit can organize information by date and display search results by category. The search unit can also classify information by theme and provide search results by category. For example, the search unit can classify information based on a specific theme and display search results by category. In this way, organizing information by category enables searches by category. Some or all of the above-described processing in the search unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the search unit can input information in the database into a generation AI and have the generation AI organize and search by category.

[0045] The search unit can tag information in the database and filter search results based on the tags. The search unit, for example, tags information in the database. For example, the search unit can tag the information with keyword tags and filter search results based on the tags. The search unit can also tag category tags to the information and filter search results based on the tags. For example, the search unit can tag keyword tags related to the information and display search results based on the tags. The search unit can also tag category tags related to the information and display search results based on the tags. In this way, tagging the information makes it possible to filter search results based on the tags. Some or all of the above-described processing in the search unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the search unit can input information in the database to a generation AI and have the generation AI perform tagging and filtering.

[0046] The search unit organizes information in the database in chronological order and can search for past information in chronological order. The search unit, for example, organizes information in the database in chronological order. For example, the search unit organizes information in date order and searches for past information in chronological order. The search unit can also organize information in chronological order and search for past information in chronological order. For example, the search unit organizes information in date order and displays search results in chronological order. The search unit can also organize information in chronological order and display search results in chronological order. In this way, by organizing information in chronological order, past information can be searched in chronological order. Some or all of the above-described processing in the search unit may be performed using, or without, a generation AI. For example, the search unit can input information in the database to a generation AI and have the generation AI organize and search in chronological order.

[0047] The generation unit can prioritize the content of the generated materials based on the importance of statements made during the meeting. The generation unit, for example, evaluates the importance of statements made during the meeting. For example, the generation unit evaluates the importance based on the frequency of statements. The generation unit can also evaluate the importance based on the speaker's position. For example, the generation unit preferentially reflects content that is spoken frequently in the materials. Furthermore, if the speaker has a high position, the generation unit can determine that the statement is of high importance and reflect it preferentially in the materials. In this way, by prioritizing the content of the materials based on the importance of the statements, important content can be preferentially reflected. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input data of statements made during the meeting into the generation AI and have the generation AI evaluate the importance and prioritize the materials.

[0048] The generation unit can generate materials using different templates depending on the category of utterances made during the meeting. The generation unit, for example, identifies the category of utterances made during the meeting. For example, the generation unit analyzes the content of the utterances and identifies the category. The generation unit can also select an appropriate template depending on the identified category. For example, the generation unit selects an appropriate template depending on the category of the utterance to generate materials. The generation unit can also provide different templates for each category and generate materials. For example, the generation unit selects an optimal template based on the category of the utterance and generates materials. In this way, optimal materials can be generated by using different templates depending on the category of the utterance. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input utterance data made during the meeting into the generation AI and cause the generation AI to identify the category and select a template.

[0049] The generation unit can analyze the frequency and patterns of utterances made during a meeting and generate detailed materials on a specific topic. The generation unit, for example, analyzes the frequency of utterances made during a meeting. For example, the generation unit measures the frequency of utterances and generates materials related to a specific topic. The generation unit can also analyze utterance patterns. For example, the generation unit can analyze the temporal pattern of utterances and generate detailed materials on a specific topic. The generation unit can also analyze the utterance frequency and patterns to identify topics important to the progress of the meeting. For example, the generation unit generates detailed materials on a topic with a high utterance frequency. The generation unit can also analyze utterance patterns and generate materials on a specific topic. In this way, detailed materials on a specific topic can be generated by analyzing the utterance frequency and patterns. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input utterance data made during a meeting into the generation AI and cause the generation AI to analyze the frequency and pattern and generate materials.

[0050] The generation unit can automatically translate the language of speech made during a meeting and generate multilingual materials. The generation unit, for example, automatically translates the language of speech made during a meeting. For example, the generation unit translates audio data of speech in real time and saves it as text data. The generation unit can also automatically detect the language of speech and translate it into an appropriate language. For example, the generation unit automatically detects the language of speech and translates it into an appropriate language using a generation AI. The generation unit can also provide multilingual materials and display them to meeting participants. For example, the generation unit generates multilingual materials based on the translated text data and displays them to the meeting participants. In this way, multilingual materials can be generated by automatically translating the language of speech. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input audio data of speech to a generation AI and have the generation AI perform translation and generate materials.

[0051] The generation unit can convert audio data of speech made during a meeting into text and generate materials based on the speech recognition results. The generation unit, for example, converts audio data of speech made during a meeting into text. For example, the generation unit converts the audio data of speech made into text data using speech recognition technology. The generation unit can also remove noise from the audio data and generate materials based on the speech recognition results. For example, the generation unit can remove noise from the audio data and generate materials based on the speech recognition results using a generation AI. The generation unit can also analyze the audio data of speech made and generate materials based on the speech recognition results using a generation AI. In this way, materials can be generated based on the speech recognition results by converting the audio data into text. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the generation unit can input the audio data of speech made into a generation AI and have the generation AI perform text conversion and material generation.

[0052] The generation unit can add background information of utterances made during a meeting to generate more detailed materials. The generation unit, for example, adds background information of utterances made during a meeting. For example, the generation unit understands the context of the utterance and adds relevant background information. The generation unit can also add background information of the utterance based on related literature or past utterances. For example, the generation unit generates detailed materials based on the background information of the utterance. The generation unit can also supplement the context of the utterance and generate materials based on the background information. For example, the generation unit analyzes the background information of the utterance and adds relevant information to generate materials. In this way, by adding background information of the utterance, more detailed materials can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input text data of the utterance into the generation AI and cause the generation AI to add background information and generate materials.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] The analysis unit can analyze the tone and speed of speech during a meeting and prioritize extraction of highly important speech. For example, the analysis unit can analyze the speech waveform and evaluate the pitch of the tone. The analysis unit can also measure the speed of speech and evaluate its importance. Furthermore, the analysis unit can analyze changes in the tone and speed of speech and identify highly important speech. In this way, by analyzing the tone and speed of speech, highly important speech can be efficiently extracted.

[0055] The search unit can evaluate the reliability of information in the database and prioritize searching for highly reliable information. For example, the search unit evaluates the reliability of information based on the reliability of the information source. The search unit can also evaluate the consistency of the information. Furthermore, the search unit can evaluate the update frequency of the information and prioritize searching for the most recent information. In this way, by evaluating the reliability of information, highly reliable information can be prioritized for search.

[0056] The generation unit can generate materials using different templates depending on the category of utterances made during a meeting. For example, the generation unit can analyze the content of utterances and identify the category. The generation unit can also select an appropriate template depending on the identified category. Furthermore, the generation unit can provide different templates for each category and generate materials. This allows optimal materials to be generated by using different templates depending on the category of utterances.

[0057] The analysis unit can analyze the context of statements made during a meeting and automatically link related past statements and materials. For example, the analysis unit analyzes the content before and after a statement to understand the context. The analysis unit can also identify related topics and link past statements and materials. Furthermore, the analysis unit can automatically link related email exchanges from the context of a statement. This makes it possible to efficiently link related past statements and materials by analyzing the context of a statement.

[0058] The generation unit can add background information for utterances made during a meeting and generate more detailed materials. For example, the generation unit can understand the context of a utterance and add related background information. The generation unit can also add background information for utterances based on related literature or past utterances. Furthermore, the generation unit can supplement the context of utterances based on background information and generate materials. In this way, by adding background information for utterances, more detailed materials can be generated.

[0059] The generation unit can automatically translate the language of speech during a meeting and generate multilingual materials. For example, the generation unit translates speech audio data in real time and saves it as text data. The generation unit can also automatically detect the language of speech and translate it into an appropriate language. Furthermore, the generation unit can provide multilingual materials and display them to meeting participants. In this way, multilingual materials can be generated by automatically translating the language of speech.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The analysis unit analyzes the conversation during the meeting in real time. The analysis unit uses speech recognition technology to convert the conversation into text data and extract important keywords and phrases. It can also use natural language processing technology to understand the context of the conversation and extract relevant information. Step 2: The search unit searches the database based on the keywords extracted by the analysis unit. The search unit uses SQL databases and NoSQL databases to quickly search for relevant information. It can also use keyword matching and context analysis to search for highly relevant information. Step 3: The generation unit automatically generates materials based on the information retrieved by the search unit. The generation unit uses text generation AI (e.g., LLM) to automatically generate minutes and presentation materials. It can also use multimodal generation AI to generate materials that include not only text data but also images and graphs.

[0062] (Example 2) A conference support system according to an embodiment of the present invention analyzes conversations during a conference in real time, searches for relevant information, and automatically generates materials. The conference support system analyzes conversations during a conference in real time, extracts important keywords and phrases, and searches for related information from a database. Furthermore, the conference support system automatically generates materials based on the searched information. For example, if a participant says, "I feel like I've heard a similar case before. Is there a history of that?" during a conference, the conference support system analyzes the conversation and searches for relevant information from a database. Furthermore, if a participant asks, "Where is that document?", the conference support system searches for the relevant document from the database and instantly displays it. Furthermore, if the contents of a conference need to be shared in another conference, the participant can request, "Please document this conference." Materials are automatically generated. This allows the conference support system to instantly provide necessary information during a conference, improving the efficiency of the conference. For example, even if a participant forgets what that was during a conference, the conference support system can provide real-time support and instantly provide the necessary information. This allows the conference to proceed smoothly and efficiently.

[0063] A conference support system according to an embodiment includes an analysis unit, a search unit, and a generation unit. The analysis unit analyzes conversations during a conference in real time. For example, the analysis unit converts the conversation into text data using speech recognition technology and extracts important keywords and phrases. The analysis unit can also understand the context of the conversation and extract related information using natural language processing technology. For example, the analysis unit analyzes statements made during a conference in real time and extracts important keywords. The search unit searches a database based on the keywords extracted by the analysis unit. The search unit quickly searches for related information using, for example, an SQL database or a NoSQL database. The search unit can also search for highly relevant information using keyword matching or context analysis. For example, the search unit searches a database based on the extracted keywords to obtain related materials or minutes of past meetings. The generation unit automatically generates materials based on the information retrieved by the search unit. For example, the generation unit automatically generates minutes or presentation materials using a text generation AI (e.g., LLM). The generation unit can also use multimodal generation AI to generate materials that include not only text data but also images and graphs. For example, the generation unit automatically generates meeting minutes based on the searched information. This allows the meeting support system according to the embodiment to analyze conversations during meetings in real time, search for related information, and automatically generate materials. This improves the efficiency of meetings and enables them to proceed smoothly.

[0064] The analysis unit can analyze conversations during meetings in real time and extract important keywords and phrases. The analysis unit can convert the conversation into text data using, for example, speech recognition technology. For example, the analysis unit can recognize speech spoken during meetings in real time and save it as text data. The analysis unit can also understand the context of the conversation and extract important keywords and phrases using natural language processing technology. For example, the analysis unit can extract keywords that appear frequently in the conversation and evaluate their importance. The analysis unit can also extract important phrases based on the context of the conversation. For example, the analysis unit can analyze the flow of the conversation and identify important statements. This allows the content of the meeting to be efficiently understood by extracting important keywords and phrases during the meeting in real time. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input the audio data of the conversation into a generation AI and have the generation AI extract important keywords and phrases.

[0065] The search unit can search for related information from a database. The search unit can search for related information using, for example, an SQL database. For example, the search unit can search for related materials in a database based on extracted keywords. The search unit can also perform flexible searches using a NoSQL database. For example, the search unit can search for highly relevant information using keyword matching. The search unit can also search for context-based information using context analysis. For example, the search unit can understand the context of a conversation and search for relevant minutes of past meetings or email exchanges. This allows necessary information to be quickly obtained by searching for related information from a database. Some or all of the above-mentioned processing in the search unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the search unit can input the extracted keywords into a generation AI and cause the generation AI to search for related information.

[0066] The generation unit can generate minutes and presentation materials based on the content of remarks or discussions made during a meeting. The generation unit automatically generates minutes and presentation materials, for example, using a text generation AI (e.g., LLM). For example, the generation unit automatically generates minutes based on remarks made during a meeting. The generation unit can also generate materials including not only text data but also images and graphs using a multimodal generation AI. For example, the generation unit automatically generates presentation materials based on the content of discussions made during a meeting. The generation unit can also automatically generate materials based on searched information. For example, the generation unit generates new materials based on minutes and related materials of past meetings searched by the search unit. This allows for efficient creation of meeting records by automatically generating materials based on the content of remarks and discussions made during a meeting. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can input data of remarks made during a meeting into the generation AI and cause the generation AI to generate minutes and presentation materials.

[0067] The search unit can search a database for minutes of past meetings or related materials, and email exchanges. The search unit, for example, searches a database for minutes of past meetings. For example, the search unit searches for minutes used in past meetings and acquires related information. The search unit can also search a database for related materials. For example, the search unit searches for presentation materials used in past meetings. The search unit can also search a database for email exchanges. For example, the search unit searches for email exchanges related to past meetings and acquires related information. This allows the contents of past meetings to be quickly referenced by searching for minutes and related materials of past meetings. Some or all of the above-mentioned processing in the search unit may be performed using, or without, a generation AI. For example, the search unit can input minutes and related materials of past meetings into the generation AI and cause the generation AI to search for related information.

[0068] The generation unit can automatically generate materials based on the searched information. The generation unit automatically generates materials based on the searched information, for example, using a text generation AI (e.g., LLM). For example, the generation unit automatically generates minutes based on the information searched by the search unit. The generation unit can also generate materials including not only text data but also images and graphs using a multimodal generation AI. For example, the generation unit automatically generates presentation materials based on the searched information. The generation unit can also generate detailed reports based on the searched information. For example, the generation unit generates a report summarizing the contents of a meeting based on the searched information. In this way, necessary materials can be quickly created by automatically generating materials based on the searched information. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can input the searched information into the generation AI and cause the generation AI to generate materials.

[0069] The analysis unit can estimate the emotions of the conference participants and adjust the priority of analysis based on the estimated emotions. For example, the analysis unit captures the facial expressions of the conference participants with a camera and estimates their emotions using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on changes in facial expressions. The analysis unit can also record the voices of the conference participants and estimate their emotions using voice analysis technology. For example, the analysis unit analyzes the tone and speed of their voices and calculates an emotion score. The analysis unit can also collect biometric data (heart rate and electrodermal activity) of the conference participants with a sensor and estimate their emotions using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on heart rate fluctuations. This enables more appropriate analysis by adjusting the priority of analysis based on the emotions of the conference participants. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative 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 may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit may input emotion data of the conference participants into the generation AI and have the generation AI adjust the analysis priority.

[0070] The analysis unit can analyze the tone and speed of speech made during a meeting and prioritize extraction of highly important speech. The analysis unit, for example, analyzes the tone of speech made during a meeting. For example, the analysis unit analyzes the audio waveform of the speech and evaluates the pitch of the tone. The analysis unit can also analyze the speed of speech. For example, the analysis unit measures the speed of speech and evaluates its importance. The analysis unit can also analyze changes in the tone and speed of speech to identify highly important speech. For example, if the tone and speed of a speech are high, the analysis unit determines that the speech is highly important and prioritizes extraction. If the tone and speed of a speech are low and the speed is slow, the analysis unit can determine that the speech is low in importance and postpone it. Furthermore, if the tone or speed of a speech suddenly changes, the analysis unit can determine that the speech requires attention and prioritize extraction. In this way, highly important speech can be efficiently extracted by analyzing the tone and speed of speech. Some or all of the above-described processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit may input speech data to the generation AI and have the generation AI analyze the tone and speed.

[0071] The analysis unit can analyze the context of statements made during a meeting and automatically link related past statements and materials. The analysis unit, for example, analyzes the context of statements made during a meeting. For example, the analysis unit analyzes the content before and after a statement to understand the context. The analysis unit can also identify related topics and link past statements and materials. For example, the analysis unit automatically links related statements made in past meetings from the context of a statement. The analysis unit can also automatically link related materials from the context of a statement. Furthermore, the analysis unit can automatically link related email exchanges from the context of a statement. In this way, by analyzing the context of a statement, related past statements and materials can be efficiently linked. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input text data of a statement into a generation AI and have the generation AI analyze the context and generate links.

[0072] The analysis unit can analyze the frequency and patterns of utterances made during a meeting and extract important keywords related to a specific theme. The analysis unit, for example, analyzes the frequency of utterances made during a meeting. For example, the analysis unit measures the frequency of utterances and identifies important keywords. The analysis unit can also analyze utterance patterns. For example, the analysis unit analyzes the temporal pattern of utterances and extracts keywords related to a specific theme. The analysis unit can also analyze the frequency and patterns of utterances and identify keywords important for the progress of the meeting. For example, the analysis unit determines and extracts keywords that are frequently uttered as important. The analysis unit can also extract keywords related to a specific theme from the utterance patterns. Furthermore, the analysis unit can analyze the frequency and patterns of utterances and identify keywords important for the progress of the meeting. In this way, by analyzing the frequency and patterns of utterances, important keywords related to a specific theme can be efficiently extracted. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input text data of utterances into the generation AI and have the generation AI perform frequency and pattern analysis.

[0073] The analysis unit can estimate the emotions of the conference participants and adjust the display method of the analysis results based on the estimated emotions. For example, the analysis unit captures the facial expressions of the conference participants with a camera and estimates their emotions using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on changes in facial expressions. The analysis unit can also record the conference participants' voices and estimate their emotions using voice analysis technology. For example, the analysis unit analyzes the tone and speed of the voices and calculates an emotion score. The analysis unit can also collect the conference participants' biometric data (heart rate and electrodermal activity) with a sensor and estimate their emotions using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on heart rate fluctuations. This enables more appropriate display by adjusting the display method of the analysis results based on the conference participants' emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative 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 may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit may input emotion data of the conference participants into the generation AI and have the generation AI adjust the display method of the analysis results.

[0074] The analysis unit can automatically translate the language of speech made during a meeting and perform multilingual analysis. The analysis unit, for example, automatically translates the language of speech made during a meeting. For example, the analysis unit translates speech audio data in real time and saves it as text data. The analysis unit can also automatically detect the language of speech and translate it into an appropriate language. For example, the analysis unit automatically detects the language of speech and translates it into an appropriate language using a generation AI. The analysis unit can also provide multilingual analysis results and display them to meeting participants. For example, the analysis unit generates multilingual analysis results based on the translated text data and displays them to meeting participants. This enables multilingual analysis by automatically translating the language of speech. Some or all of the above-described processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input speech audio data of speech into a generation AI and have the generation AI perform translation and analysis.

[0075] The analysis unit can analyze audio data of speech made during a meeting and provide feedback to improve speech recognition accuracy. The analysis unit, for example, analyzes audio data of speech made during a meeting. For example, the analysis unit can remove noise from the audio data to improve speech recognition accuracy. The analysis unit can also analyze features of the audio data and suggest improvements to the speech recognition. For example, the analysis unit can analyze the audio data of speech and provide feedback to improve speech recognition accuracy using a generation AI. The analysis unit can also remove noise from the audio data to improve speech recognition accuracy using a generation AI. The analysis unit can also analyze the audio data of speech and suggest improvements to speech recognition using a generation AI. In this way, feedback to improve speech recognition accuracy can be provided by analyzing the audio data. Some or all of the above-described processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input the audio data of speech to the generation AI and cause the generation AI to provide feedback to improve speech recognition accuracy.

[0076] The analysis unit can remove background noise from speech during a meeting to improve analysis accuracy. The analysis unit, for example, removes background noise from speech during a meeting. For example, the analysis unit can use noise filtering technology to remove background noise from speech audio data. The analysis unit can also use a noise reduction algorithm to clear speech audio data. For example, the analysis unit can remove background noise from speech in real time and improve analysis accuracy using a generation AI. The analysis unit can also use noise removal technology to clear speech audio data using a generation AI. Furthermore, the analysis unit can remove background noise from speech in real time and improve analysis accuracy using a generation AI. In this way, removing background noise can improve analysis accuracy. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input speech audio data to a generation AI and have the generation AI remove background noise.

[0077] The search unit can estimate the emotions of the conference participants and adjust the priority of search results based on the estimated emotions. For example, the search unit captures the facial expressions of the conference participants with a camera and estimates their emotions using an emotion estimation algorithm. For example, the search unit calculates an emotion score based on changes in facial expressions. The search unit can also record the voices of the conference participants and estimate their emotions using voice analysis technology. For example, the search unit analyzes the tone and speed of the voices and calculates an emotion score. The search unit can also collect biometric data of the conference participants (heart rate and electrodermal activity) with a sensor and estimate their emotions using an emotion estimation algorithm. For example, the search unit calculates an emotion score based on heart rate fluctuations. This allows the prioritization of search results based on the emotions of the conference participants to provide more appropriate search results. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative 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 search unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the search unit may input emotion data of the conference participants into the generation AI and have the generation AI adjust the priority of the search results.

[0078] The search unit can evaluate the reliability of information in the database and prioritize searching for highly reliable information. The search unit, for example, evaluates the reliability of information in the database. For example, the search unit evaluates the reliability of information based on the reliability of the information source. The search unit can also evaluate the consistency of information. For example, the search unit evaluates whether the content of the information is consistent with other highly reliable information. The search unit can also evaluate the update frequency of information and prioritize searching for the latest information. For example, the search unit prioritizes displaying the latest information based on the update date and time of the information. In this way, by evaluating the reliability of the information, highly reliable information can be prioritized and searched for. Some or all of the above-mentioned processing in the search unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the search unit can input information in the database into a generation AI and have the generation AI perform the reliability evaluation and search.

[0079] The search unit can prioritize searching for the most recent information by taking into account the update frequency of the information in the database. The search unit, for example, evaluates the update frequency of the information in the database. For example, the search unit prioritizes displaying the most recent information based on the update date and time of the information. The search unit can also evaluate the number of times the information has been updated and prioritize searching for information that has been updated more frequently. For example, the search unit prioritizes searching and displaying information that has been updated more frequently. This allows the most recent information to be prioritized by taking into account the update frequency of the information. Some or all of the above-described processing in the search unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the search unit can input information in the database into the generation AI and have the generation AI evaluate the update frequency and perform the search.

[0080] The search unit can evaluate the relevance of information in the database and prioritize searching for highly relevant information. The search unit, for example, evaluates the relevance of information in the database. For example, the search unit uses keyword matching to search for highly relevant information. The search unit can also use context analysis to search for context-based information. For example, the search unit can prioritize displaying highly relevant information based on the degree of match of keywords in the information. The search unit can also analyze the context of the information and prioritize searching for the most relevant information. In this way, by evaluating the relevance of the information, highly relevant information can be prioritized for search. Some or all of the above-mentioned processing in the search unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the search unit can input information in the database into a generation AI and have the generation AI perform the relevance evaluation and search.

[0081] The search unit can estimate the emotions of the conference participants and adjust the display method of search results based on the estimated emotions. For example, the search unit captures the facial expressions of the conference participants with a camera and estimates their emotions using an emotion estimation algorithm. For example, the search unit calculates an emotion score based on changes in facial expressions. The search unit can also record the voices of the conference participants and estimate their emotions using voice analysis technology. For example, the search unit analyzes the tone and speed of the voices and calculates an emotion score. The search unit can also collect biometric data of the conference participants (heart rate and electrodermal activity) using a sensor and estimate their emotions using an emotion estimation algorithm. For example, the search unit calculates an emotion score based on heart rate fluctuations. This allows for more appropriate display by adjusting the display method of the search results based on the emotions of the conference participants. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative 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 search unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the search unit may input emotion data of conference participants into the generation AI and have the generation AI adjust the display method of the search results.

[0082] The search unit can organize information in the database by category, enabling searches by category. For example, the search unit organizes information in the database by category. For example, the search unit can classify information by topic and provide searches by category. The search unit can also classify information by time and provide searches by category. For example, the search unit can organize information by date and display search results by category. The search unit can also classify information by theme and provide search results by category. For example, the search unit can classify information based on a specific theme and display search results by category. In this way, organizing information by category enables searches by category. Some or all of the above-described processing in the search unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the search unit can input information in the database into a generation AI and have the generation AI organize and search by category.

[0083] The search unit can tag information in the database and filter search results based on the tags. The search unit, for example, tags information in the database. For example, the search unit can tag the information with keyword tags and filter search results based on the tags. The search unit can also tag category tags to the information and filter search results based on the tags. For example, the search unit can tag keyword tags related to the information and display search results based on the tags. The search unit can also tag category tags related to the information and display search results based on the tags. In this way, tagging the information makes it possible to filter search results based on the tags. Some or all of the above-described processing in the search unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the search unit can input information in the database to a generation AI and have the generation AI perform tagging and filtering.

[0084] The search unit organizes information in the database in chronological order and can search for past information in chronological order. The search unit, for example, organizes information in the database in chronological order. For example, the search unit organizes information in date order and searches for past information in chronological order. The search unit can also organize information in chronological order and search for past information in chronological order. For example, the search unit organizes information in date order and displays search results in chronological order. The search unit can also organize information in chronological order and display search results in chronological order. In this way, by organizing information in chronological order, past information can be searched in chronological order. Some or all of the above-described processing in the search unit may be performed using, or without, a generation AI. For example, the search unit can input information in the database to a generation AI and have the generation AI organize and search in chronological order.

[0085] The generation unit can estimate the emotions of the meeting participants and adjust the tone and style of the generated materials based on the estimated emotions. For example, the generation unit captures the facial expressions of the meeting participants with a camera and estimates their emotions using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on changes in facial expressions. The generation unit can also record the voices of the meeting participants and estimate their emotions using voice analysis technology. For example, the generation unit analyzes the tone and speed of the voices and calculates an emotion score. The generation unit can also collect biometric data (heart rate and electrodermal activity) of the meeting participants with a sensor and estimate their emotions using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on heart rate fluctuations. This allows the generation of more appropriate materials by adjusting the tone and style of the materials based on the emotions of the meeting participants. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the generation unit may input emotional data of the meeting participants into the generation AI and have the generation AI adjust the tone and style of the materials.

[0086] The generation unit can prioritize the content of the generated materials based on the importance of statements made during the meeting. The generation unit, for example, evaluates the importance of statements made during the meeting. For example, the generation unit evaluates the importance based on the frequency of statements. The generation unit can also evaluate the importance based on the speaker's position. For example, the generation unit preferentially reflects content that is spoken frequently in the materials. Furthermore, if the speaker has a high position, the generation unit can determine that the statement is of high importance and reflect it preferentially in the materials. In this way, by prioritizing the content of the materials based on the importance of the statements, important content can be preferentially reflected. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input data of statements made during the meeting into the generation AI and have the generation AI evaluate the importance and prioritize the materials.

[0087] The generation unit can generate materials using different templates depending on the category of utterances made during the meeting. The generation unit, for example, identifies the category of utterances made during the meeting. For example, the generation unit analyzes the content of the utterances and identifies the category. The generation unit can also select an appropriate template depending on the identified category. For example, the generation unit selects an appropriate template depending on the category of the utterance to generate materials. The generation unit can also provide different templates for each category and generate materials. For example, the generation unit selects an optimal template based on the category of the utterance and generates materials. In this way, optimal materials can be generated by using different templates depending on the category of the utterance. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input utterance data made during the meeting into the generation AI and cause the generation AI to identify the category and select a template.

[0088] The generation unit can analyze the frequency and patterns of utterances made during a meeting and generate detailed materials on a specific topic. The generation unit, for example, analyzes the frequency of utterances made during a meeting. For example, the generation unit measures the frequency of utterances and generates materials related to a specific topic. The generation unit can also analyze utterance patterns. For example, the generation unit can analyze the temporal pattern of utterances and generate detailed materials on a specific topic. The generation unit can also analyze the utterance frequency and patterns to identify topics important to the progress of the meeting. For example, the generation unit generates detailed materials on a topic with a high utterance frequency. The generation unit can also analyze utterance patterns and generate materials on a specific topic. In this way, detailed materials on a specific topic can be generated by analyzing the utterance frequency and patterns. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input utterance data made during a meeting into the generation AI and cause the generation AI to analyze the frequency and pattern and generate materials.

[0089] The generation unit can estimate the emotions of the meeting participants and adjust the layout of the generated materials based on the estimated emotions. For example, the generation unit captures the facial expressions of the meeting participants with a camera and estimates their emotions using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on changes in facial expressions. The generation unit can also record the voices of the meeting participants and estimate their emotions using voice analysis technology. For example, the generation unit analyzes the tone and speed of the voices and calculates an emotion score. The generation unit can also collect biometric data (heart rate and electrodermal activity) of the meeting participants with a sensor and estimate their emotions using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on heart rate fluctuations. This allows the generation of more appropriate materials by adjusting the layout of the materials based on the emotions of the meeting participants. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the generation unit may input emotion data of the meeting participants into the generation AI and have the generation AI adjust the layout of the materials.

[0090] The generation unit can automatically translate the language of speech made during a meeting and generate multilingual materials. The generation unit, for example, automatically translates the language of speech made during a meeting. For example, the generation unit translates audio data of speech in real time and saves it as text data. The generation unit can also automatically detect the language of speech and translate it into an appropriate language. For example, the generation unit automatically detects the language of speech and translates it into an appropriate language using a generation AI. The generation unit can also provide multilingual materials and display them to meeting participants. For example, the generation unit generates multilingual materials based on the translated text data and displays them to the meeting participants. In this way, multilingual materials can be generated by automatically translating the language of speech. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input audio data of speech to a generation AI and have the generation AI perform translation and generate materials.

[0091] The generation unit can convert audio data of speech made during a meeting into text and generate materials based on the speech recognition results. The generation unit, for example, converts audio data of speech made during a meeting into text. For example, the generation unit converts the audio data of speech made into text data using speech recognition technology. The generation unit can also remove noise from the audio data and generate materials based on the speech recognition results. For example, the generation unit can remove noise from the audio data and generate materials based on the speech recognition results using a generation AI. The generation unit can also analyze the audio data of speech made and generate materials based on the speech recognition results using a generation AI. In this way, materials can be generated based on the speech recognition results by converting the audio data into text. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the generation unit can input the audio data of speech made into a generation AI and have the generation AI perform text conversion and material generation.

[0092] The generation unit can add background information of utterances made during a meeting to generate more detailed materials. The generation unit, for example, adds background information of utterances made during a meeting. For example, the generation unit understands the context of the utterance and adds relevant background information. The generation unit can also add background information of the utterance based on related literature or past utterances. For example, the generation unit generates detailed materials based on the background information of the utterance. The generation unit can also supplement the context of the utterance and generate materials based on the background information. For example, the generation unit analyzes the background information of the utterance and adds relevant information to generate materials. In this way, by adding background information of the utterance, more detailed materials can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input text data of the utterance into the generation AI and cause the generation AI to add background information and generate materials. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned analysis unit, search unit, and generation unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart device 14 and analyzes conversations during a meeting in real time to extract important keywords and phrases. The search unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and searches the database 24 based on the extracted keywords. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates materials based on the searched information. The analysis unit, search unit, and generation unit may also be realized, for example, by the control unit 46A of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned analysis unit, search unit, and generation unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart glasses 214 and analyzes conversations during a meeting in real time to extract important keywords and phrases. The search unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and searches the database 24 based on the extracted keywords. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates materials based on the searched information. The analysis unit, search unit, and generation unit may also be realized, for example, by the control unit 46A of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, search unit, and generation unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the headset type terminal 314 and analyzes conversations during a conference in real time to extract important keywords and phrases. The search unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and searches the database 24 based on the extracted keywords. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates materials based on the searched information. The analysis unit, search unit, and generation unit may also be realized, for example, by the control unit 46A of the headset type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, search unit, and generation unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the robot 414 and analyzes conversations during meetings in real time to extract important keywords and phrases. The search unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and searches the database 24 based on the extracted keywords. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates materials based on the searched information. The analysis unit, search unit, and generation unit may also be realized, for example, by the control unit 46A of the robot 414.

[0093] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0094] The analysis unit can estimate the emotions of the speech of the meeting participants and evaluate the importance of the speech based on the estimated emotions. For example, the analysis unit can analyze the tone and speed of the speech of the meeting participants and calculate an emotion score. The analysis unit can also capture the facial expressions of the meeting participants with a camera and estimate their emotions using an emotion estimation algorithm. Furthermore, the analysis unit can collect biometric data of the meeting participants (heart rate and electrodermal activity) with a sensor and calculate an emotion score. This enables more appropriate analysis by evaluating the importance of speech based on the emotions of the meeting participants.

[0095] The search unit can estimate the emotions of the meeting participants and adjust the display method of search results based on the estimated emotions. For example, the search unit can capture the facial expressions of the meeting participants with a camera and estimate their emotions using an emotion estimation algorithm. The search unit can also record the voices of the meeting participants and estimate their emotions using voice analysis technology. Furthermore, the search unit can collect biometric data (heart rate and electrodermal activity) of the meeting participants with a sensor and calculate an emotion score. This allows for more appropriate display by adjusting the display method of search results based on the emotions of the meeting participants.

[0096] The generation unit can estimate the emotions of the meeting participants and adjust the tone and style of the generated materials based on the estimated emotions. For example, the generation unit can capture the facial expressions of the meeting participants with a camera and estimate their emotions using an emotion estimation algorithm. The generation unit can also record the voices of the meeting participants and estimate their emotions using voice analysis technology. Furthermore, the generation unit can collect biometric data (heart rate and electrodermal activity) of the meeting participants with a sensor and calculate an emotion score. This makes it possible to generate more appropriate materials by adjusting the tone and style of the materials based on the emotions of the meeting participants.

[0097] The analysis unit can analyze the tone and speed of speech during a meeting and prioritize extraction of highly important speech. For example, the analysis unit can analyze the speech waveform and evaluate the pitch of the tone. The analysis unit can also measure the speed of speech and evaluate its importance. Furthermore, the analysis unit can analyze changes in the tone and speed of speech and identify highly important speech. In this way, by analyzing the tone and speed of speech, highly important speech can be efficiently extracted.

[0098] The search unit can evaluate the reliability of information in the database and prioritize searching for highly reliable information. For example, the search unit evaluates the reliability of information based on the reliability of the information source. The search unit can also evaluate the consistency of the information. Furthermore, the search unit can evaluate the update frequency of the information and prioritize searching for the most recent information. In this way, by evaluating the reliability of information, highly reliable information can be prioritized for search.

[0099] The generation unit can generate materials using different templates depending on the category of utterances made during a meeting. For example, the generation unit can analyze the content of utterances and identify the category. The generation unit can also select an appropriate template depending on the identified category. Furthermore, the generation unit can provide different templates for each category and generate materials. This allows optimal materials to be generated by using different templates depending on the category of utterances.

[0100] The analysis unit can analyze the context of statements made during a meeting and automatically link related past statements and materials. For example, the analysis unit analyzes the content before and after a statement to understand the context. The analysis unit can also identify related topics and link past statements and materials. Furthermore, the analysis unit can automatically link related email exchanges from the context of a statement. This makes it possible to efficiently link related past statements and materials by analyzing the context of a statement.

[0101] The generation unit can add background information for utterances made during a meeting and generate more detailed materials. For example, the generation unit can understand the context of a utterance and add related background information. The generation unit can also add background information for utterances based on related literature or past utterances. Furthermore, the generation unit can supplement the context of utterances based on background information and generate materials. In this way, by adding background information for utterances, more detailed materials can be generated.

[0102] The analysis unit can estimate the emotions of the meeting participants and adjust the display method of the analysis results based on the estimated emotions. For example, the analysis unit can capture the facial expressions of the meeting participants with a camera and estimate their emotions using an emotion estimation algorithm. The analysis unit can also record the voices of the meeting participants and estimate their emotions using voice analysis technology. Furthermore, the analysis unit can collect biometric data (heart rate and electrodermal activity) of the meeting participants with a sensor and calculate an emotion score. This allows for a more appropriate display by adjusting the display method of the analysis results based on the emotions of the meeting participants.

[0103] The generation unit can automatically translate the language of speech during a meeting and generate multilingual materials. For example, the generation unit translates speech audio data in real time and saves it as text data. The generation unit can also automatically detect the language of speech and translate it into an appropriate language. Furthermore, the generation unit can provide multilingual materials and display them to meeting participants. In this way, multilingual materials can be generated by automatically translating the language of speech.

[0104] The processing flow of the second embodiment will be briefly explained below.

[0105] Step 1: The analysis unit analyzes the conversation during the meeting in real time. The analysis unit uses speech recognition technology to convert the conversation into text data and extract important keywords and phrases. It can also use natural language processing technology to understand the context of the conversation and extract relevant information. Step 2: The search unit searches the database based on the keywords extracted by the analysis unit. The search unit uses SQL databases and NoSQL databases to quickly search for relevant information. It can also use keyword matching and context analysis to search for highly relevant information. Step 3: The generation unit automatically generates materials based on the information retrieved by the search unit. The generation unit uses text generation AI (e.g., LLM) to automatically generate minutes and presentation materials. It can also use multimodal generation AI to generate materials that include not only text data but also images and graphs.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0110] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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).

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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).

[0163] 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.

[0164] 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."

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] [Explanation of symbols]

[0178] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. An analysis unit that analyzes conversations during meetings in real time, a search unit that searches a database based on the keywords extracted by the analysis unit; a generation unit that automatically generates materials based on the information searched by the search unit; Equipped with A system characterized by:

2. The analysis unit Analyzes meeting conversations in real time and extracts important keywords and phrases 2. The system of claim 1.

3. The search unit Searching for relevant information in databases 2. The system of claim 1.

4. The generation unit Generate minutes and presentation materials based on what is said or discussed during a meeting 2. The system of claim 1.

5. The search unit Search the database for past meeting minutes or related materials, email correspondence 2. The system of claim 1.

6. The generation unit Automatically generate documents based on searched information 2. The system of claim 1.

7. The analysis unit Estimate the emotions of meeting participants and adjust analysis priorities based on the estimated emotions 2. The system of claim 1.

8. The analysis unit Analyzes the tone and speed of speech during meetings and prioritizes the most important statements.

2. The system of claim 1.

Images