System

Abstract

To provide a system for understanding the contents and context of utterance during a meeting and displaying related words in real time.SOLUTION: A system includes a conversion section, an analysis section, and a display section. The conversion section converts the contents of utterance during a meeting into text data by using a voice recognition technique. The analysis section analyzes the text data obtained through the conversion performed by the conversion section, and extracts related words on the basis of the contents or context of the utterance. The display section displays the related words extracted by the analysis section in real time.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has the problem that it is difficult to understand what is being said during a meeting in real time and to instantly display related words.

[0005] The system according to the embodiment aims to understand the content and context of statements made during a meeting and display related words in real time. [Means for solving the problem]

[0006] The system according to the embodiment includes a conversion unit, an analysis unit, and a display unit. The conversion unit converts utterances made during a meeting into text data using voice recognition technology. The analysis unit analyzes the text data converted by the conversion unit and extracts related words based on the utterances or context. The display unit displays the related words extracted by the analysis unit in real time. Effect of the Invention

[0007] The system according to the embodiment can understand the content and context of statements made during a meeting and display related words in real time. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The meeting analysis system according to the embodiment of the present invention is a system that analyzes the contents of remarks made during a meeting in real time and displays related words. This meeting analysis system converts the contents of remarks made during a meeting into text data using voice recognition technology, and a generation AI analyzes the text data, extracts related words based on the contents of the remarks and the context, and displays them in real time. For example, if someone says "Let's discuss the marketing strategy for a new product" during a meeting, the voice recognition technology converts the remark into text data, and the generation AI extracts related words such as "new product," "marketing," and "strategy," and displays them on the screen. This allows meeting participants to understand the remarks more deeply and smoothly advance the discussion. This system not only improves the efficiency of meetings, but also helps record the remarks and refer to them later. For example, by searching for related words after the end of a meeting, it is easy to find remarks related to a specific topic. It is also possible to display the full text of remarks related to that word by clicking on a related word. This system can be used not only in corporate meetings, but also in various situations such as academic conferences and seminars. For example, at academic conferences, participants can deepen their understanding by displaying related research themes and keywords in real time based on the remarks made by the presenter. In addition, in seminars, participants can learn more effectively by displaying related topics and references based on what the lecturer has said. By combining speech recognition technology and generative AI, this system can analyze the content and context of comments in real time and display related words, greatly contributing to improving meeting efficiency and deepening understanding. This allows the meeting analysis system to analyze what is said during a meeting in real time and display related words.

[0029] The meeting analysis system according to the embodiment includes a conversion unit, an analysis unit, and a display unit. The conversion unit converts the content of a statement made during a meeting into text data using a voice recognition technology. The voice recognition technology includes, for example, deep learning-based voice recognition and HMM (Hidden Markov Model), but is not limited to such examples. For example, the conversion unit can convert the content of a statement into text data with high accuracy using the deep learning-based voice recognition technology. The conversion unit can also analyze a voice signal using HMM and convert it into text data. The analysis unit uses a generation AI to analyze the text data converted by the conversion unit and extracts related words based on the content of the statement and the context. The generation AI includes, for example, a text generation AI (for example, LLM) and a multimodal generation AI, but is not limited to such examples. For example, the analysis unit can analyze the content of a statement and extract related words using the text generation AI. The analysis unit can also analyze the content of a statement and the context and extract related words using the multimodal generation AI. The display unit displays the related words extracted by the analysis unit in real time. The display unit can, for example, display related words in a pop-up on the screen. The display unit can also display related words in a list in a specific area. Furthermore, the display unit can display the full text of a statement related to a word by a user clicking the related word. For example, the display unit displays related words in a list on the right side of the screen, and displays the full text of a related statement by a user clicking the word. Thereby, the meeting analysis system according to the embodiment can analyze the content of a statement made during a meeting in real time and display the related words. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can display the related words using an AI model that uses the related words extracted by the analysis unit as input and displays the related words. Thereby, the meeting analysis system can analyze the content of a statement made during a meeting in real time and display the related words.

[0030] The conversion unit converts the contents of speech during the meeting into text data using a voice recognition technology. Examples of voice recognition technology include, but are not limited to, deep learning-based voice recognition and HMM (hidden Markov model). Specifically, the deep learning-based voice recognition technology uses a neural network to analyze voice signals and convert the contents of speech into text data with high accuracy. This technology realizes accurate text conversion by learning a large amount of voice data, while taking into account subtle differences in pronunciation and background noise. On the other hand, the HMM models the voice signal as a temporal change and converts it into text data while taking into account the continuity of phonemes. The HMM is particularly good at capturing temporal patterns of speech, and can naturally convert the flow of speech into text. The conversion unit combines these technologies to realize highly accurate voice recognition that is compatible with various environments and speakers. For example, even if there is a lot of background noise in a conference room, the deep learning-based voice recognition technology can remove the noise and the HMM can capture the flow of speech, thereby generating accurate text data. Furthermore, the conversion unit can learn the technical terms of the conference and the characteristics of the participants' voices in advance in order to improve the accuracy of the voice recognition. This makes it possible to build speech recognition models specialized for specific industries or companies, achieving more accurate text conversion.

[0031] The analysis unit uses the generation AI to analyze the text data converted by the conversion unit and extracts related words based on the utterance content and context. The generation AI includes, but is not limited to, for example, a text generation AI (e.g., LLM) and a multimodal generation AI. Specifically, the text generation AI uses a large-scale language model to analyze the text data and understand the meaning and context of the utterance content. This AI can extract the intention of the utterance and important keywords by making full use of natural language processing technology. For example, it can identify related words such as "project progress" and "next meeting date" from utterances during a meeting. In addition, the multimodal generation AI can integrate and analyze multiple data modalities such as images and videos as well as voice and text. This makes it possible to analyze the contents of presentation materials and whiteboards used during the meeting and associate them with the utterance content. The analysis unit utilizes these generation AIs to deeply understand the context of the utterance content and extract related words with high accuracy. In addition, the analysis unit can complement the background and related information of the utterance content by referring to past meeting data and external information sources. For example, by referencing the contents of discussions in past meetings and related industry news, the analysis unit can more accurately grasp the intention and importance of statements. This allows the analysis unit to analyze the contents of statements made during meetings from multiple angles and extract related words, thereby providing a deeper understanding of the contents of the meeting.

[0032] The display unit displays the related words extracted by the analysis unit in real time. For example, the display unit can display the related words in a pop-up on the screen. The display unit can also display the related words in a list in a specific area. Specifically, the related words extracted during the meeting are displayed in a list on the right side of the screen, and the full text of the related remarks is displayed when the user clicks on the word. This allows the user to quickly grasp the important points of the meeting. Furthermore, the display unit can adjust the display priority based on the importance and frequency of the related words. For example, frequently mentioned words and important keywords are displayed in prominent positions. Furthermore, the display unit can customize the display content based on user feedback. For example, when a user judges a specific word to be important, a function is provided to highlight the word. Furthermore, the display unit can improve the user's convenience by diversifying the display method of the related words. For example, different categories and importance can be visually distinguished by displaying the related words in different colors. Furthermore, the related words can be displayed in a timeline format to grasp the flow of remarks in chronological order. This allows the display unit to provide a variety of display methods that allow the user to easily and intuitively understand the contents of the conference.

[0033] The display unit can display the related words in a pop-up on the screen. The pop-up display includes, for example, a display position, a display time, a display format, and the like, but is not limited to such examples. The display unit can display, for example, the related words in a pop-up in the center of the screen. The display unit can also set the related words to be displayed for a certain period of time and then to disappear automatically. Furthermore, the display unit can display the related words in a specific font or color. For example, the display unit can display the related words in bold to improve visibility. As a result, the visibility is improved by displaying the related words in a pop-up. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can perform the pop-up display using an AI model that adjusts the display position and display time of the related words.

[0034] The display unit can display the related words in a list in a specific area. The specific area includes, for example, the right side and the top of the screen, but is not limited to such examples. The display unit can display the related words in a list on the right side of the screen, for example. The display unit can also display the related words in a list on the top of the screen. Furthermore, the display unit can display the related words in a list in a specific order. For example, the display unit displays the related words in a list in order of importance, so that the user can check important words preferentially. This makes it possible to provide organized information by displaying the related words in a list. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can display the list using an AI model that adjusts the list display position and order of the related words.

[0035] The display unit can display all the contents of the utterance related to a related word by the user clicking the related word. The full text includes, for example, all the contents from the start to the end of the utterance, but is not limited to such an example. The display unit can display the full text of the utterance related to the word by the user clicking the related word, for example. The display unit can also display the full text of the utterance in a separate window by clicking the related word. Furthermore, the display unit can display the full text of the utterance in a specific format by clicking the related word. For example, the display unit can display the full text of the utterance in paragraphs to improve readability. This allows detailed information to be accessed by clicking the related word. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can display the full text using an AI model that generates the full text of the utterance to be displayed when the related word is clicked.

[0036] The display unit can have a function of searching for related words after the end of the meeting. The search includes, for example, a keyword search, a full-text search, and the like, but is not limited to such examples. The display unit can have, for example, a function of searching for related words by keyword after the end of the meeting. The display unit can also have a function of searching for related words in full text after the end of the meeting. Furthermore, the display unit can have a function of searching for related words under specific conditions after the end of the meeting. For example, the display unit can search for related words under conditions such as date and time and speaker after the end of the meeting. This makes it easy to refer to the contents of remarks by searching for related words after the end of the meeting. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can provide a search function using an AI model that adjusts the search conditions for related words.

[0037] The conversion unit can filter background sounds during a meeting and improve the recognition accuracy of the speech content. The conversion unit can, for example, remove noise in the meeting room and emphasize only the speaker's voice. The conversion unit can also filter keyboard sounds and paper sounds during a meeting to clarify the speech content. Furthermore, the conversion unit can remove noise outside the meeting room and clearly recognize the speaker's voice. For example, the conversion unit uses noise canceling technology to remove noise in the meeting room and emphasize the speaker's voice. This improves the recognition accuracy of the speech content by filtering the background sound. Part or all of the above-mentioned processing in the conversion unit may be performed, for example, using AI or may be performed without using AI. For example, the conversion unit can improve the recognition accuracy of the speech content by using an AI model that filters background sound.

[0038] The conversion unit can improve the recognition accuracy by learning the characteristics of the speaker's voice and creating an individual voice profile. The conversion unit can, for example, learn the tone and pitch of each speaker's voice and create an individual voice profile. The conversion unit can also improve the accuracy of voice recognition based on the characteristics of the speaker's voice. Furthermore, the conversion unit can dynamically update the voice profile in response to changes in the speaker's voice. For example, the conversion unit learns the tone and pitch of the speaker's voice and creates an individual voice profile. As a result, the recognition accuracy is improved by learning the characteristics of the speaker's voice. A part or all of the above-mentioned processing in the conversion unit may be performed, for example, using AI, or may be performed without using AI. For example, the conversion unit can create an individual voice profile using an AI model that learns the characteristics of the speaker's voice.

[0039] The conversion unit can translate the contents of remarks made during a conference in real time and generate text data in multiple languages. For example, the conversion unit can translate the contents of remarks into English in real time and generate English text data. The conversion unit can also translate the contents of remarks into Chinese in real time and generate Chinese text data. The conversion unit can also translate the contents of remarks into Spanish in real time and generate Spanish text data. For example, the conversion unit translates the contents of remarks in real time and generates text data in multiple languages. This makes it possible to support multiple languages ​​by translating the contents of remarks in real time. A part or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can generate text data in multiple languages ​​using an AI model that translates the contents of remarks.

[0040] The conversion unit can summarize the utterance contents in real time and generate a summary text. For example, the conversion unit can summarize the utterance contents in real time and extract only important points to generate text data. The conversion unit can also summarize the utterance contents in real time and generate concise text data. Furthermore, the conversion unit can summarize the utterance contents in real time and generate a summary text that matches the progress of the meeting. For example, the conversion unit summarizes the utterance contents in real time and extracts only important points to generate text data. As a result, by summarizing the utterance contents, the important points can be grasped concisely. A part or all of the above-mentioned processing in the conversion unit may be performed, for example, using AI, or may be performed without using AI. For example, the conversion unit can generate a summary text using an AI model that summarizes the utterance contents.

[0041] The analysis unit can analyze the context of the remarks in detail and evaluate the importance of the related words. The analysis unit can, for example, analyze the context of the remarks and evaluate important keywords as having high importance. The analysis unit can also analyze the context of the remarks and evaluate the importance based on the frequency of appearance of related words. The analysis unit can also analyze the context of the remarks and evaluate the importance based on the correlation of related words. For example, the analysis unit analyzes the context of the remarks and evaluates important keywords as having high importance. This allows the importance of related words to be accurately evaluated by deeply analyzing the context. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can evaluate the importance of related words using an AI model that analyzes the context of the remarks.

[0042] The analysis unit can apply different analysis algorithms depending on the category of the comment content. For example, the analysis unit can apply an analysis algorithm specialized in technical terms to technical comment content. In addition, the analysis unit can apply an analysis algorithm specialized in marketing terms to marketing comment content. In addition, the analysis unit can apply an analysis algorithm specialized in management terms to management comment content. For example, the analysis unit applies an analysis algorithm specialized in technical terms to technical comment content. Thereby, by applying an analysis algorithm according to the category, the analysis accuracy is improved. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can improve the analysis accuracy by using an AI model that applies an analysis algorithm according to the category of the comment content.

[0043] The analysis unit can analyze the time flow of the statement contents and evaluate the appearance frequency of the related words. The analysis unit can, for example, analyze the time flow of the statement contents and highly evaluate related words that appear frequently. The analysis unit can also analyze the time flow of the statement contents and highly evaluate related words that appear at important timing. Furthermore, the analysis unit can analyze the time flow of the statement contents and evaluate based on the appearance pattern of the related words. For example, the analysis unit analyzes the time flow of the statement contents and highly evaluates related words that appear frequently. In this way, the appearance frequency of the related words can be accurately evaluated by analyzing the time flow. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can evaluate the appearance frequency of the related words using an AI model that analyzes the time flow of the statement contents.

[0044] The analysis unit can evaluate the relevance of the statement contents and perform clustering of related words. The analysis unit can, for example, evaluate the relevance of the statement contents and cluster the related words by theme. The analysis unit can also evaluate the relevance of the statement contents and cluster the related words by importance. The analysis unit can also evaluate the relevance of the statement contents and cluster the related words by frequency of appearance. For example, the analysis unit evaluates the relevance of the statement contents and clusters the related words by theme. In this way, the related words can be effectively clustered by evaluating the relevance. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can perform clustering of related words using an AI model that evaluates the relevance of the statement contents.

[0045] When displaying the related words, the display unit can select the optimal display method by referring to the user's past operation history. For example, the display unit can provide a display method that the user has used in the past with preference. The display unit can also suggest the optimal display method based on the user's past operation history. Furthermore, the display unit can automatically select a specific display method from the user's past operation history. For example, the display unit can provide a frequently used display method with preference by referring to the user's past operation history. In this way, the optimal display method can be provided by referring to the past operation history. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can select the optimal display method by using an AI model that analyzes the user's operation history.

[0046] The display unit can adjust the display position by using the user's gaze tracking data when displaying the related words. The display unit can display the related words at the center of the user's gaze based on the user's gaze tracking data, for example. The display unit can also dynamically adjust the display position of the related words based on the user's gaze tracking data. Furthermore, the display unit can display the related words at the most visible position based on the user's gaze tracking data. For example, the display unit displays the related words at the center of the user's gaze based on the user's gaze tracking data. This makes it possible to optimize the display position of the related words by using the gaze tracking data. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can adjust the display position of the related words by using an AI model that analyzes the gaze tracking data.

[0047] The display unit can select an optimal display method based on the user's device information when displaying related words. For example, when the user is using a smartphone, the display unit can provide a display method that matches the screen size. In addition, when the user is using a tablet, the display unit can also provide a display method optimized for a large screen. In addition, when the user is using a desktop, the display unit can also provide a method for displaying a wide range of information. For example, the display unit provides a display method that matches the screen size when using a smartphone based on the user's device information. This improves visibility by providing an optimal display method based on the device information. Part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can select an optimal display method using an AI model that analyzes the user's device information.

[0048] The display unit can analyze the operation history of the user and adjust the display order of the related words when displaying the related words. The display unit can, for example, display frequently used related words with priority based on the operation history of the user. The display unit can also display important related words with priority based on the operation history of the user. Furthermore, the display unit can dynamically adjust the display order of the related words based on the operation history of the user. For example, the display unit analyzes the operation history of the user and displays frequently used related words with priority. Thereby, the display order of the related words can be optimized by analyzing the operation history. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can adjust the display order of the related words using an AI model that analyzes the operation history of the user.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] When displaying related words, the display unit can select the optimal display method by referring to the content of past comments made by the user. For example, related words that the user has frequently used in the past can be preferentially displayed. The display unit can also adjust the display order of related words based on the content of past comments made by the user. Furthermore, the display unit can automatically select a specific display method from the content of past comments made by the user. This makes it possible to provide an optimal display method by referring to the content of past comments. A part or all of the above-mentioned processing in the display unit may be performed using AI, or may be performed without using AI. For example, the display unit can select the optimal display method by using an AI model that analyzes the content of user comments.

[0051] When displaying the related words, the display unit can adjust the display method taking into account the remaining battery level of the user's device. For example, when the battery level is low, the display unit can display the related words in a power-saving mode. Also, when the battery level is sufficient, the display unit can provide a normal display method. Furthermore, when the battery level is very low, the display unit can reduce the frequency of displaying the related words. This allows for efficient display by adjusting the display method according to the remaining battery level of the device. Some or all of the above-mentioned processing in the display unit may be performed using AI or may be performed without using AI. For example, the display unit can adjust the display method using an AI model that analyzes battery information of the device.

[0052] When displaying the related words, the display unit can adjust the display method taking into account the presence or absence of a visual impairment of the user. For example, for a user with a visual impairment, the related words can be displayed in a large font. Also, for a user with color vision deficiency, the color contrast can be adjusted and displayed. Furthermore, for a user without a visual impairment, a normal display method can be provided. This improves visibility by adjusting the display method depending on the presence or absence of a visual impairment. A part or all of the above-mentioned processing in the display unit may be performed using AI, or may be performed without using AI. For example, the display unit can adjust the display method using an AI model that analyzes the visual information of the user.

[0053] The display unit can adjust the display method by receiving a voice command from the user when displaying the related words. For example, when the user issues a voice command of "larger display", the related words can be displayed in a larger font. Also, when the user issues a voice command of "change color", the display color of the related words can be changed. Furthermore, when the user issues a voice command of "list display", the related words can be displayed in list format. In this way, by receiving a voice command, a display method according to the user's instructions can be provided. A part or all of the above-mentioned processing in the display unit may be performed using AI, or may be performed without using AI. For example, the display unit can adjust the display method using an AI model that analyzes the voice command.

[0054] The display unit can detect a user's gesture when displaying the related words and adjust the display method. For example, when the user makes a gesture of waving, the related words can be erased. Also, when the user makes a gesture of pointing, the related words can be highlighted. Furthermore, when the user makes a gesture of spreading his / her hand, the related words can be enlarged. In this way, by detecting the gesture, a display method according to the user's instruction can be provided. A part or all of the above-mentioned processing in the display unit may be performed using AI, or may be performed without using AI. For example, the display unit can adjust the display method using an AI model that analyzes gestures.

[0055] The process flow of the first embodiment will be briefly described below.

[0056] Step 1: The conversion unit converts what is said during the meeting into text data using speech recognition technology. Speech recognition technology includes deep learning-based speech recognition and HMM (hidden Markov model). For example, the conversion unit can convert what is said into text data with high accuracy using deep learning-based speech recognition technology. It can also analyze speech signals using HMM and convert them into text data. Step 2: The analysis unit uses the generation AI to analyze the text data converted by the conversion unit, and extracts related words based on the utterance content and context. The generation AI includes text generation AI (e.g., LLM) and multimodal generation AI. For example, the analysis unit can use the text generation AI to analyze the utterance content and extract related words. It can also use the multimodal generation AI to analyze the utterance content and context and extract related words. Step 3: The display unit displays the related words extracted by the analysis unit in real time. The display unit can display the related words as a pop-up on the screen or as a list in a specific area. Furthermore, the user can click on a related word to display the full text of the comment related to that word. For example, the display unit displays the related words in a list on the right side of the screen, and the user can click on the word to display the full text of the related comment.

[0057] (Example 2) The meeting analysis system according to the embodiment of the present invention is a system that analyzes the contents of remarks made during a meeting in real time and displays related words. This meeting analysis system converts the contents of remarks made during a meeting into text data using voice recognition technology, and a generation AI analyzes the text data, extracts related words based on the contents of the remarks and the context, and displays them in real time. For example, if someone says "Let's discuss the marketing strategy for a new product" during a meeting, the voice recognition technology converts the remark into text data, and the generation AI extracts related words such as "new product," "marketing," and "strategy," and displays them on the screen. This allows meeting participants to understand the remarks more deeply and smoothly advance the discussion. This system not only improves the efficiency of meetings, but also helps record the remarks and refer to them later. For example, by searching for related words after the end of a meeting, it is easy to find remarks related to a specific topic. It is also possible to display the full text of remarks related to that word by clicking on a related word. This system can be used not only in corporate meetings, but also in various situations such as academic conferences and seminars. For example, at academic conferences, participants can deepen their understanding by displaying related research themes and keywords in real time based on the remarks made by the presenter. In addition, in seminars, participants can learn more effectively by displaying related topics and references based on what the lecturer has said. By combining speech recognition technology and generative AI, this system can analyze the content and context of comments in real time and display related words, greatly contributing to improving meeting efficiency and deepening understanding. This allows the meeting analysis system to analyze what is said during a meeting in real time and display related words.

[0058] The meeting analysis system according to the embodiment includes a conversion unit, an analysis unit, and a display unit. The conversion unit converts the content of a statement made during a meeting into text data using a voice recognition technology. The voice recognition technology includes, for example, deep learning-based voice recognition and HMM (Hidden Markov Model), but is not limited to such examples. For example, the conversion unit can convert the content of a statement into text data with high accuracy using the deep learning-based voice recognition technology. The conversion unit can also analyze a voice signal using HMM and convert it into text data. The analysis unit uses a generation AI to analyze the text data converted by the conversion unit and extracts related words based on the content of the statement and the context. The generation AI includes, for example, a text generation AI (for example, LLM) and a multimodal generation AI, but is not limited to such examples. For example, the analysis unit can analyze the content of a statement and extract related words using the text generation AI. The analysis unit can also analyze the content of a statement and the context and extract related words using the multimodal generation AI. The display unit displays the related words extracted by the analysis unit in real time. The display unit can, for example, display related words in a pop-up on the screen. The display unit can also display related words in a list in a specific area. Furthermore, the display unit can display the full text of a statement related to a word by a user clicking the related word. For example, the display unit displays related words in a list on the right side of the screen, and displays the full text of a related statement by a user clicking the word. Thereby, the meeting analysis system according to the embodiment can analyze the content of a statement made during a meeting in real time and display the related words. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can display the related words using an AI model that uses the related words extracted by the analysis unit as input and displays the related words. Thereby, the meeting analysis system can analyze the content of a statement made during a meeting in real time and display the related words.

[0059] The conversion unit converts the contents of speech during the meeting into text data using a voice recognition technology. Examples of voice recognition technology include, but are not limited to, deep learning-based voice recognition and HMM (hidden Markov model). Specifically, the deep learning-based voice recognition technology uses a neural network to analyze voice signals and convert the contents of speech into text data with high accuracy. This technology realizes accurate text conversion by learning a large amount of voice data, while taking into account subtle differences in pronunciation and background noise. On the other hand, the HMM models the voice signal as a temporal change and converts it into text data while taking into account the continuity of phonemes. The HMM is particularly good at capturing temporal patterns of speech, and can naturally convert the flow of speech into text. The conversion unit combines these technologies to realize highly accurate voice recognition that is compatible with various environments and speakers. For example, even if there is a lot of background noise in a conference room, the deep learning-based voice recognition technology can remove the noise and the HMM can capture the flow of speech, thereby generating accurate text data. Furthermore, the conversion unit can learn the technical terms of the conference and the characteristics of the participants' voices in advance in order to improve the accuracy of the voice recognition. This makes it possible to build speech recognition models specialized for specific industries or companies, achieving more accurate text conversion.

[0060] The analysis unit uses the generation AI to analyze the text data converted by the conversion unit and extracts related words based on the utterance content and context. The generation AI includes, but is not limited to, for example, a text generation AI (e.g., LLM) and a multimodal generation AI. Specifically, the text generation AI uses a large-scale language model to analyze the text data and understand the meaning and context of the utterance content. This AI can extract the intention of the utterance and important keywords by making full use of natural language processing technology. For example, it can identify related words such as "project progress" and "next meeting date" from utterances during a meeting. In addition, the multimodal generation AI can integrate and analyze multiple data modalities such as images and videos as well as voice and text. This makes it possible to analyze the contents of presentation materials and whiteboards used during the meeting and associate them with the utterance content. The analysis unit utilizes these generation AIs to deeply understand the context of the utterance content and extract related words with high accuracy. In addition, the analysis unit can complement the background and related information of the utterance content by referring to past meeting data and external information sources. For example, by referencing the contents of discussions in past meetings and related industry news, the analysis unit can more accurately grasp the intention and importance of statements. This allows the analysis unit to analyze the contents of statements made during meetings from multiple angles and extract related words, thereby providing a deeper understanding of the contents of the meeting.

[0061] The display unit displays the related words extracted by the analysis unit in real time. For example, the display unit can display the related words in a pop-up on the screen. The display unit can also display the related words in a list in a specific area. Specifically, the related words extracted during the meeting are displayed in a list on the right side of the screen, and the full text of the related remarks is displayed when the user clicks on the word. This allows the user to quickly grasp the important points of the meeting. Furthermore, the display unit can adjust the display priority based on the importance and frequency of the related words. For example, frequently mentioned words and important keywords are displayed in prominent positions. Furthermore, the display unit can customize the display content based on user feedback. For example, when a user judges a specific word to be important, a function is provided to highlight the word. Furthermore, the display unit can improve the user's convenience by diversifying the display method of the related words. For example, different categories and importance can be visually distinguished by displaying the related words in different colors. Furthermore, the related words can be displayed in a timeline format to grasp the flow of remarks in chronological order. This allows the display unit to provide a variety of display methods that allow the user to easily and intuitively understand the contents of the conference.

[0062] The display unit can display the related words in a pop-up on the screen. The pop-up display includes, for example, a display position, a display time, a display format, and the like, but is not limited to such examples. The display unit can display, for example, the related words in a pop-up in the center of the screen. The display unit can also set the related words to be displayed for a certain period of time and then to disappear automatically. Furthermore, the display unit can display the related words in a specific font or color. For example, the display unit can display the related words in bold to improve visibility. As a result, the visibility is improved by displaying the related words in a pop-up. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can perform the pop-up display using an AI model that adjusts the display position and display time of the related words.

[0063] The display unit can display the related words in a list in a specific area. The specific area includes, for example, the right side and the top of the screen, but is not limited to such examples. The display unit can display the related words in a list on the right side of the screen, for example. The display unit can also display the related words in a list on the top of the screen. Furthermore, the display unit can display the related words in a list in a specific order. For example, the display unit displays the related words in a list in order of importance, so that the user can check important words preferentially. This makes it possible to provide organized information by displaying the related words in a list. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can display the list using an AI model that adjusts the list display position and order of the related words.

[0064] The display unit can display all the contents of the utterance related to a related word by the user clicking the related word. The full text includes, for example, all the contents from the start to the end of the utterance, but is not limited to such an example. The display unit can display the full text of the utterance related to the word by the user clicking the related word, for example. The display unit can also display the full text of the utterance in a separate window by clicking the related word. Furthermore, the display unit can display the full text of the utterance in a specific format by clicking the related word. For example, the display unit can display the full text of the utterance in paragraphs to improve readability. This allows detailed information to be accessed by clicking the related word. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can display the full text using an AI model that generates the full text of the utterance to be displayed when the related word is clicked.

[0065] The display unit can have a function of searching for related words after the end of the meeting. The search includes, for example, a keyword search, a full-text search, and the like, but is not limited to such examples. The display unit can have, for example, a function of searching for related words by keyword after the end of the meeting. The display unit can also have a function of searching for related words in full text after the end of the meeting. Furthermore, the display unit can have a function of searching for related words under specific conditions after the end of the meeting. For example, the display unit can search for related words under conditions such as date and time and speaker after the end of the meeting. This makes it easy to refer to the contents of remarks by searching for related words after the end of the meeting. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can provide a search function using an AI model that adjusts the search conditions for related words.

[0066] The conversion unit can estimate the user's emotion and adjust the accuracy of the voice recognition based on the estimated user's emotion. For example, when the user is nervous, the conversion unit can increase the sensitivity of the voice recognition to accurately capture the speech. Also, when the user is relaxed, the conversion unit can set the sensitivity of the voice recognition to normal and capture natural speech. Furthermore, when the user is in a hurry, the conversion unit can increase the speed of the voice recognition to quickly convert the voice into text data. For example, the conversion unit estimates the user's emotion, and increases the sensitivity of the voice recognition when the user is nervous, and sets the sensitivity to normal when the user is relaxed. This improves the recognition accuracy by adjusting the accuracy of the voice recognition according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the conversion unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the conversion unit can input a user's emotional data into the generation AI and have the generation AI adjust the accuracy of voice recognition.

[0067] The conversion unit can filter background sounds during a meeting and improve the recognition accuracy of the speech content. The conversion unit can, for example, remove noise in the meeting room and emphasize only the speaker's voice. The conversion unit can also filter keyboard sounds and paper sounds during a meeting to clarify the speech content. Furthermore, the conversion unit can remove noise outside the meeting room and clearly recognize the speaker's voice. For example, the conversion unit uses noise canceling technology to remove noise in the meeting room and emphasize the speaker's voice. This improves the recognition accuracy of the speech content by filtering the background sound. Part or all of the above-mentioned processing in the conversion unit may be performed, for example, using AI or may be performed without using AI. For example, the conversion unit can improve the recognition accuracy of the speech content by using an AI model that filters background sound.

[0068] The conversion unit can improve the recognition accuracy by learning the characteristics of the speaker's voice and creating an individual voice profile. The conversion unit can, for example, learn the tone and pitch of each speaker's voice and create an individual voice profile. The conversion unit can also improve the accuracy of voice recognition based on the characteristics of the speaker's voice. Furthermore, the conversion unit can dynamically update the voice profile in response to changes in the speaker's voice. For example, the conversion unit learns the tone and pitch of the speaker's voice and creates an individual voice profile. As a result, the recognition accuracy is improved by learning the characteristics of the speaker's voice. A part or all of the above-mentioned processing in the conversion unit may be performed, for example, using AI, or may be performed without using AI. For example, the conversion unit can create an individual voice profile using an AI model that learns the characteristics of the speaker's voice.

[0069] The conversion unit can estimate the user's emotion and adjust the timing of the voice recognition based on the estimated user's emotion. For example, when the user is nervous, the conversion unit can shorten the interval between speeches to perform voice recognition quickly. Also, when the user is relaxed, the conversion unit can set the interval between speeches to normal to perform voice recognition. Furthermore, when the user is in a hurry, the conversion unit can minimize the interval between speeches to perform voice recognition quickly. For example, the conversion unit estimates the user's emotion, shortens the interval between speeches when the user is nervous, and sets it to normal intervals when the user is relaxed. This improves the recognition accuracy by adjusting the timing of voice recognition according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the conversion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the conversion unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the timing of voice recognition.

[0070] The conversion unit can translate the contents of remarks made during a conference in real time and generate text data in multiple languages. For example, the conversion unit can translate the contents of remarks into English in real time and generate English text data. The conversion unit can also translate the contents of remarks into Chinese in real time and generate Chinese text data. The conversion unit can also translate the contents of remarks into Spanish in real time and generate Spanish text data. For example, the conversion unit translates the contents of remarks in real time and generates text data in multiple languages. This makes it possible to support multiple languages ​​by translating the contents of remarks in real time. A part or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can generate text data in multiple languages ​​using an AI model that translates the contents of remarks.

[0071] The conversion unit can summarize the utterance contents in real time and generate a summary text. For example, the conversion unit can summarize the utterance contents in real time and extract only important points to generate text data. The conversion unit can also summarize the utterance contents in real time and generate concise text data. Furthermore, the conversion unit can summarize the utterance contents in real time and generate a summary text that matches the progress of the meeting. For example, the conversion unit summarizes the utterance contents in real time and extracts only important points to generate text data. As a result, by summarizing the utterance contents, the important points can be grasped concisely. A part or all of the above-mentioned processing in the conversion unit may be performed, for example, using AI, or may be performed without using AI. For example, the conversion unit can generate a summary text using an AI model that summarizes the utterance contents.

[0072] The analysis unit can estimate the user's emotion and adjust the extraction criteria of related words based on the estimated user's emotion. For example, when the user is nervous, the analysis unit can prioritize and extract important keywords. In addition, when the user is relaxed, the analysis unit can also extract a wide range of related words. In addition, when the user is in a hurry, the analysis unit can extract related words that focus on the main points. For example, the analysis unit estimates the user's emotion, and when the user is nervous, it prioritizes and extracts important keywords, and when the user is relaxed, it extracts a wide range of related words. In this way, by adjusting the extraction criteria of related words according to the user's emotion, more appropriate related words can be extracted. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the extraction criteria of related words.

[0073] The analysis unit can analyze the context of the remarks in detail and evaluate the importance of the related words. The analysis unit can, for example, analyze the context of the remarks and evaluate important keywords as having high importance. The analysis unit can also analyze the context of the remarks and evaluate the importance based on the frequency of appearance of related words. The analysis unit can also analyze the context of the remarks and evaluate the importance based on the correlation of related words. For example, the analysis unit analyzes the context of the remarks and evaluates important keywords as having high importance. This allows the importance of related words to be accurately evaluated by deeply analyzing the context. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can evaluate the importance of related words using an AI model that analyzes the context of the remarks.

[0074] The analysis unit can apply different analysis algorithms depending on the category of the comment content. For example, the analysis unit can apply an analysis algorithm specialized in technical terms to technical comment content. In addition, the analysis unit can apply an analysis algorithm specialized in marketing terms to marketing comment content. In addition, the analysis unit can apply an analysis algorithm specialized in management terms to management comment content. For example, the analysis unit applies an analysis algorithm specialized in technical terms to technical comment content. Thereby, by applying an analysis algorithm according to the category, the analysis accuracy is improved. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can improve the analysis accuracy by using an AI model that applies an analysis algorithm according to the category of the comment content.

[0075] The analysis unit can estimate the user's emotion and adjust the display order of related words based on the estimated user's emotion. For example, when the user is nervous, the analysis unit can prioritize and display important related words. In addition, when the user is relaxed, the analysis unit can also display a wide range of related words. In addition, when the user is in a hurry, the analysis unit can prioritize and display related words that cover the main points. For example, the analysis unit estimates the user's emotion and prioritizes and displays important related words when the user is nervous, and displays a wide range of related words when the user is relaxed. Thereby, the display order of related words is adjusted according to the user's emotion, thereby improving visibility. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display order of related words.

[0076] The analysis unit can analyze the time flow of the statement contents and evaluate the appearance frequency of the related words. The analysis unit can, for example, analyze the time flow of the statement contents and highly evaluate related words that appear frequently. The analysis unit can also analyze the time flow of the statement contents and highly evaluate related words that appear at important timing. Furthermore, the analysis unit can analyze the time flow of the statement contents and evaluate based on the appearance pattern of the related words. For example, the analysis unit analyzes the time flow of the statement contents and highly evaluates related words that appear frequently. In this way, the appearance frequency of the related words can be accurately evaluated by analyzing the time flow. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can evaluate the appearance frequency of the related words using an AI model that analyzes the time flow of the statement contents.

[0077] The analysis unit can evaluate the relevance of the statement contents and perform clustering of related words. The analysis unit can, for example, evaluate the relevance of the statement contents and cluster the related words by theme. The analysis unit can also evaluate the relevance of the statement contents and cluster the related words by importance. The analysis unit can also evaluate the relevance of the statement contents and cluster the related words by frequency of appearance. For example, the analysis unit evaluates the relevance of the statement contents and clusters the related words by theme. In this way, the related words can be effectively clustered by evaluating the relevance. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can perform clustering of related words using an AI model that evaluates the relevance of the statement contents.

[0078] The display unit can estimate the user's emotion and adjust the display method of the related words based on the estimated user's emotion. For example, when the user is nervous, the display unit can provide a simple and highly visible display method. Also, when the user is relaxed, the display unit can provide a display method including detailed information. Furthermore, when the user is in a hurry, the display unit can provide a display method that focuses on the main points. For example, the display unit estimates the user's emotion and provides a simple and highly visible display method when the user is nervous, and provides a display method including detailed information when the user is relaxed. Thereby, the visibility is improved by adjusting the display method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the display unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the display unit can input the user's emotion data to the generation AI and cause the generation AI to execute the adjustment of the display method of the related words.

[0079] When displaying the related words, the display unit can select the optimal display method by referring to the user's past operation history. For example, the display unit can provide a display method that the user has used in the past with preference. The display unit can also suggest the optimal display method based on the user's past operation history. Furthermore, the display unit can automatically select a specific display method from the user's past operation history. For example, the display unit can provide a frequently used display method with preference by referring to the user's past operation history. In this way, the optimal display method can be provided by referring to the past operation history. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can select the optimal display method by using an AI model that analyzes the user's operation history.

[0080] The display unit can adjust the display position by using the user's gaze tracking data when displaying the related words. The display unit can display the related words at the center of the user's gaze based on the user's gaze tracking data, for example. The display unit can also dynamically adjust the display position of the related words based on the user's gaze tracking data. Furthermore, the display unit can display the related words at the most visible position based on the user's gaze tracking data. For example, the display unit displays the related words at the center of the user's gaze based on the user's gaze tracking data. This makes it possible to optimize the display position of the related words by using the gaze tracking data. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can adjust the display position of the related words by using an AI model that analyzes the gaze tracking data.

[0081] The display unit can estimate the user's emotion and adjust the display frequency of related words based on the estimated user's emotion. For example, when the user is nervous, the display unit can frequently display important related words. Also, when the user is relaxed, the display unit can display a wide range of related words. Furthermore, when the user is in a hurry, the display unit can frequently display related words that cover the main points. For example, the display unit estimates the user's emotion and frequently displays important related words when the user is nervous, and displays a wide range of related words when the user is relaxed. Thereby, the visibility is improved by adjusting the display frequency according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the display unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the display unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display frequency of related words.

[0082] The display unit can select an optimal display method based on the user's device information when displaying related words. For example, when the user is using a smartphone, the display unit can provide a display method that matches the screen size. In addition, when the user is using a tablet, the display unit can also provide a display method optimized for a large screen. In addition, when the user is using a desktop, the display unit can also provide a method for displaying a wide range of information. For example, the display unit provides a display method that matches the screen size when using a smartphone based on the user's device information. This improves visibility by providing an optimal display method based on the device information. Part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can select an optimal display method using an AI model that analyzes the user's device information.

[0083] The display unit can analyze the operation history of the user and adjust the display order of the related words when displaying the related words. The display unit can, for example, display frequently used related words with priority based on the operation history of the user. The display unit can also display important related words with priority based on the operation history of the user. Furthermore, the display unit can dynamically adjust the display order of the related words based on the operation history of the user. For example, the display unit analyzes the operation history of the user and displays frequently used related words with priority. Thereby, the display order of the related words can be optimized by analyzing the operation history. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can adjust the display order of the related words using an AI model that analyzes the operation history of the user.

[0084] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0085] The analysis unit can estimate the user's emotion and adjust the display color of the related words based on the estimated user's emotion. For example, if the user is nervous, the related words can be displayed in a calm color. Also, if the user is relaxed, the related words can be displayed in a bright color. Furthermore, if the user is in a hurry, the related words can be displayed in a conspicuous color. Thereby, the display color of the related words is adjusted according to the user's emotion, thereby improving visibility. The estimation of the emotion is realized using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display color of the related words.

[0086] When displaying related words, the display unit can select the optimal display method by referring to the content of past comments made by the user. For example, related words that the user has frequently used in the past can be preferentially displayed. The display unit can also adjust the display order of related words based on the content of past comments made by the user. Furthermore, the display unit can automatically select a specific display method from the content of past comments made by the user. This makes it possible to provide an optimal display method by referring to the content of past comments. A part or all of the above-mentioned processing in the display unit may be performed using AI, or may be performed without using AI. For example, the display unit can select the optimal display method by using an AI model that analyzes the content of user comments.

[0087] The analysis unit can estimate the user's emotion and adjust the importance of related words based on the estimated user's emotion. For example, if the user is nervous, important related words can be evaluated as having high importance. Also, if the user is relaxed, a wide range of related words can be evaluated. Furthermore, if the user is in a hurry, related words that cover the main points can be evaluated as having high importance. In this way, more appropriate related words can be extracted by adjusting the importance of related words according to the user's emotion. The estimation of emotion is realized using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the importance of the related words.

[0088] When displaying the related words, the display unit can adjust the display method taking into account the remaining battery level of the user's device. For example, when the battery level is low, the display unit can display the related words in a power-saving mode. Also, when the battery level is sufficient, the display unit can provide a normal display method. Furthermore, when the battery level is very low, the display unit can reduce the frequency of displaying the related words. This allows for efficient display by adjusting the display method according to the remaining battery level of the device. Some or all of the above-mentioned processing in the display unit may be performed using AI or may be performed without using AI. For example, the display unit can adjust the display method using an AI model that analyzes battery information of the device.

[0089] The analysis unit can estimate the user's emotion and adjust the display timing of the related words based on the estimated user's emotion. For example, if the user is nervous, the related words can be displayed earlier. Also, if the user is relaxed, the related words can be displayed at a normal timing. Furthermore, if the user is in a hurry, the related words can be displayed quickly. This improves visibility by adjusting the display timing of the related words according to the user's emotion. The emotion estimation is realized using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using an AI or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display timing of the related words.

[0090] When displaying the related words, the display unit can adjust the display method taking into account the presence or absence of a visual impairment of the user. For example, for a user with a visual impairment, the related words can be displayed in a large font. Also, for a user with color vision deficiency, the color contrast can be adjusted and displayed. Furthermore, for a user without a visual impairment, a normal display method can be provided. This improves visibility by adjusting the display method depending on the presence or absence of a visual impairment. A part or all of the above-mentioned processing in the display unit may be performed using AI, or may be performed without using AI. For example, the display unit can adjust the display method using an AI model that analyzes the visual information of the user.

[0091] The analysis unit can estimate the user's emotion and adjust the display format of the related words based on the estimated user's emotion. For example, if the user is nervous, the related words can be displayed in a simple format. Also, if the user is relaxed, the related words can be displayed in a detailed format. Furthermore, if the user is in a hurry, the related words can be displayed in only the main points. This improves visibility by adjusting the display format of the related words according to the user's emotion. The estimation of the emotion is realized using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using an AI or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display format of the related words.

[0092] The display unit can adjust the display method by receiving a voice command from the user when displaying the related words. For example, when the user issues a voice command of "larger display", the related words can be displayed in a larger font. Also, when the user issues a voice command of "change color", the display color of the related words can be changed. Furthermore, when the user issues a voice command of "list display", the related words can be displayed in list format. In this way, by receiving a voice command, a display method according to the user's instructions can be provided. A part or all of the above-mentioned processing in the display unit may be performed using AI, or may be performed without using AI. For example, the display unit can adjust the display method using an AI model that analyzes the voice command.

[0093] The analysis unit can estimate the user's emotions and adjust the display frequency of related words based on the estimated user's emotions. For example, if the user is nervous, important related words can be displayed frequently. Also, if the user is relaxed, a wide range of related words can be displayed. Furthermore, if the user is in a hurry, related words that focus on the main points can be displayed frequently. This improves visibility by adjusting the display frequency according to the user's emotions. The estimation of emotions is realized using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display frequency of related words.

[0094] The display unit can detect a user's gesture when displaying the related words and adjust the display method. For example, when the user makes a gesture of waving, the related words can be erased. Also, when the user makes a gesture of pointing, the related words can be highlighted. Furthermore, when the user makes a gesture of spreading his / her hand, the related words can be enlarged. In this way, by detecting the gesture, a display method according to the user's instruction can be provided. A part or all of the above-mentioned processing in the display unit may be performed using AI, or may be performed without using AI. For example, the display unit can adjust the display method using an AI model that analyzes gestures.

[0095] The process flow of the second embodiment will be briefly described below.

[0096] Step 1: The conversion unit converts what is said during the meeting into text data using speech recognition technology. Speech recognition technology includes deep learning-based speech recognition and HMM (hidden Markov model). For example, the conversion unit can convert what is said into text data with high accuracy using deep learning-based speech recognition technology. It can also analyze speech signals using HMM and convert them into text data. Step 2: The analysis unit uses the generation AI to analyze the text data converted by the conversion unit, and extracts related words based on the utterance content and context. The generation AI includes text generation AI (e.g., LLM) and multimodal generation AI. For example, the analysis unit can use the text generation AI to analyze the utterance content and extract related words. It can also use the multimodal generation AI to analyze the utterance content and context and extract related words. Step 3: The display unit displays the related words extracted by the analysis unit in real time. The display unit can display the related words as a pop-up on the screen or as a list in a specific area. Furthermore, the user can click on a related word to display the full text of the comment related to that word. For example, the display unit displays the related words in a list on the right side of the screen, and the user can click on the word to display the full text of the related comment.

[0097] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0098] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0099] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0100] Each of the multiple elements including the above-mentioned conversion unit, analysis unit, and display unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the conversion unit is realized by the processor 46 of the smart device 14, and converts the contents of remarks made during a meeting into text data using voice recognition technology. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the text data using a generation AI and extracts related words. The display unit is realized, for example, by the display 40A of the smart device 14, and displays the extracted related words in real time. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0101] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0102] 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.

[0103] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0104] 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.

[0105] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0106] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0107] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0108] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0109] 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.

[0110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0111] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0112] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0114] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0115] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0116] Each of the multiple elements including the above-mentioned conversion unit, analysis unit, and display unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the conversion unit is realized by the processor 46 of the smart glasses 214, and converts the contents of remarks made during a meeting into text data using voice recognition technology. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the text data using a generation AI and extracts related words. The display unit is realized, for example, by the display of the smart glasses 214, and displays the extracted related words in real time. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0117] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0118] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0119] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0120] 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.

[0121] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0123] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0124] 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.

[0125] 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.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0127] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0129] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0131] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0132] Each of the multiple elements including the above-mentioned conversion unit, analysis unit, and display unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the conversion unit is realized by the processor 46 of the headset type terminal 314, and converts the contents of remarks made during the conference into text data using voice recognition technology. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the text data using a generation AI and extracts related words. The display unit is realized, for example, by the display 343 of the headset type terminal 314, and displays the extracted related words in real time. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0133] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0134] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0135] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0136] 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.

[0137] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0140] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0141] 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.

[0142] 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.

[0143] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0144] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0145] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0146] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0147] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0148] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0149] Each of the multiple elements including the above-mentioned conversion unit, analysis unit, and display unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the conversion unit is realized by the processor 46 of the robot 414, and converts the contents of remarks made during a meeting into text data using voice recognition technology. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the text data using a generation AI and extracts related words. The display unit is realized, for example, by the display of the robot 414, and displays the extracted related words in real time. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0150] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0151] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0152] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0153] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0154] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0155] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0156] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0157] 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.

[0158] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0159] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0160] 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.

[0161] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0162] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0163] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0164] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0165] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0166] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0167] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0168] (Appendix 1) A conversion unit that converts the contents of statements made during a meeting into text data using voice recognition technology; an analysis unit that analyzes the text data converted by the conversion unit and extracts related words based on the content or context of the comment; A display unit that displays the related words extracted by the analysis unit in real time. A system characterized by: (Appendix 2) The display unit is Related words pop up on the screen 2. The system of claim 1, (Appendix 3) The display unit is Display a list of related words in a specific area 2. The system of claim 1, (Appendix 4) The display unit is When a user clicks on a related word, the system displays all the posts related to that word. 2. The system of claim 1, (Appendix 5) The display unit is Equipped with a function to search for related words after the meeting ends 2. The system of claim 1, (Appendix 6) The conversion unit is Estimating a user's emotion and adjusting the accuracy of speech recognition based on the estimated user's emotion 2. The system of claim 1, (Appendix 7) The conversion unit is Filter background noise during meetings to improve recognition of what is being said 2. The system of claim 1, (Appendix 8) The conversion unit is Learns the speaker's vocal characteristics and creates a personalized voice profile to improve recognition accuracy 2. The system of claim 1, (Appendix 9) The conversion unit is To estimate a user's emotion and adjust the timing of speech recognition based on the estimated user's emotion. 2. The system of claim 1, (Appendix 10) The conversion unit is Translate what is said during a meeting in real time and generate text data in multiple languages 2. The system of claim 1, (Appendix 11) The conversion unit is Summarize speech in real time and generate summary text 2. The system of claim 1, (Appendix 12) The analysis unit is The user's sentiment is estimated, and the criteria for extracting related words are adjusted based on the estimated user's sentiment. 2. The system of claim 1, (Appendix 13) The analysis unit is Analyze the context of what is said in detail and evaluate the importance of related words 2. The system of claim 1, (Appendix 14) The analysis unit is Apply different analysis algorithms depending on the category of speech 2. The system of claim 1, (Appendix 15) The analysis unit is Infer user sentiment and adjust the display order of related words based on the estimated user sentiment 2. The system of claim 1, (Appendix 16) The analysis unit is Analyze the timeline of comments and evaluate the frequency of related words 2. The system of claim 1, (Appendix 17) The analysis unit is Evaluate the relevance of the content of comments and cluster related words 2. The system of claim 1, (Appendix 18) The display unit is Infer user sentiment and adjust how related words are displayed based on the estimated user sentiment 2. The system of claim 1, (Appendix 19) The display unit is When displaying related words, the system selects the optimal display method by referring to the user's past operation history. 2. The system of claim 1, (Appendix 20) The display unit is When displaying related words, adjust the display position using user eye tracking data 2. The system of claim 1, (Appendix 21) The display unit is Infer user sentiment and adjust the frequency of related words based on the estimated sentiment 2. The system of claim 1, (Appendix 22) The display unit is When displaying related words, the optimal display method is selected based on the user's device information. 2. The system of claim 1, (Appendix 23) The display unit is When displaying related words, analyze the user's operation history and adjust the display order of related words. 2. The system of claim 1, [Explanation of symbols]

[0169] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A conversion unit that converts the contents of statements made during a meeting into text data using voice recognition technology; an analysis unit that analyzes the text data converted by the conversion unit and extracts related words based on the content or context of the comment; A display unit that displays the related words extracted by the analysis unit in real time. A system characterized by:

2. The display unit is Related words pop up on the screen 2. The system of claim 1 .

3. The display unit is Display a list of related words in a specific area 2. The system of claim 1 .

4. The display unit is When a user clicks on a related word, the system displays all the posts related to that word.

2. The system of claim 1 .

5. The display unit is Equipped with a function to search for related words after the meeting ends 2. The system of claim 1 .

6. The conversion unit is Estimating a user's emotion and adjusting the accuracy of speech recognition based on the estimated user's emotion 2. The system of claim 1 .

7. The conversion unit is Filter background noise during meetings to improve recognition of what is being said 2. The system of claim 1 .

8. The conversion unit is Learns the speaker's vocal characteristics and creates a personalized voice profile to improve recognition accuracy 2. The system of claim 1 .

9. The conversion unit is To estimate a user's emotion and adjust the timing of speech recognition based on the estimated user's emotion.

2. The system of claim 1 .

Images