System

Abstract

To provide a system that extracts a keyword from a voice and immediately displays the meaning of the keyword.SOLUTION: A system according to an embodiment comprises a voice recognition unit, an extraction unit, an analysis unit, and a display unit. The voice recognition unit converts a voice into a text. The extraction unit extracts a keyword from the text obtained through the conversion performed by the voice recognition unit. The analysis unit analyzes the meaning of the keyword extracted by the extraction unit. The display unit displays a result of the analysis performed by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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] With conventional technology, there was a problem in that it was difficult to immediately grasp the meaning of unfamiliar keywords that appeared in presentations or lectures.

[0005] The system according to the embodiment aims to extract keywords from speech and instantly display their meanings. [Means for solving the problem]

[0006] The system according to the embodiment includes a speech recognition unit, an extraction unit, an analysis unit, and a display unit. The speech recognition unit converts speech into text. The extraction unit extracts keywords from the text converted by the speech recognition unit. The analysis unit analyzes the meaning of the keywords extracted by the extraction unit. The display unit displays the results of the analysis by the analysis unit. Effect of the Invention

[0007] The system according to the embodiment can extract keywords from speech and instantly display their meaning. [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, aperture, and 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 terminology understanding support system according to the embodiment of the present invention is a system that uses a smartphone to automatically display the meaning of a keyword that the user does not know when a presentation, study group, lecture, etc. is viewed and heard. This terminology understanding support system first accepts voice input through the smartphone's microphone. Next, it uses voice recognition technology to convert the voice into text and extracts keywords from the text. The extracted keywords are analyzed for meaning using a generation AI and displayed on the smartphone screen. This allows the user to easily understand the meaning of the term. For example, if the keyword "deep learning" appears during a presentation, the smartphone's microphone recognizes the voice and converts it into text. Next, the generation AI analyzes the meaning of "deep learning" and displays the result on the smartphone screen. The user can understand the meaning of "deep learning" just by looking at the smartphone screen. This system can convert voice into text in real time by using voice recognition technology. Next, it can quickly and accurately analyze the meaning of the keyword by using a generation AI. Furthermore, by displaying it on the smartphone screen, the user can easily check the meaning of the term. This system improves the viewing experience during presentations, study sessions, lectures, etc., and deepens understanding of keywords whose meanings are unknown. For example, even if a technical presentation contains a lot of technical terms, by using this system, users can understand the meaning of the terms on the spot and gain a deeper understanding of the content of the presentation. As a result, the terminology understanding support system can quickly and accurately understand the meaning of keywords whose meanings are unknown to users when viewing presentations, study sessions, lectures, etc.

[0029] The terminology understanding support system according to the embodiment includes a speech recognition unit, an extraction unit, an analysis unit, and a display unit. The speech recognition unit converts speech into text. The speech recognition unit converts speech into text using, for example, a speech recognition algorithm. The speech recognition unit can also convert speech into text using, for example, speech recognition software. The speech recognition unit can also convert speech into text using, for example, a speech recognition device. The extraction unit extracts keywords from the text converted by the speech recognition unit. The extraction unit extracts keywords using, for example, frequency analysis. The extraction unit can also extract keywords using, for example, natural language processing technology. The extraction unit can also extract keywords using, for example, a keyword extraction algorithm. The analysis unit analyzes the meaning of the keyword extracted by the extraction unit. The analysis unit analyzes the meaning of the keyword using, for example, a generation AI. The analysis unit can also analyze the meaning of the keyword using, for example, a semantic analysis algorithm. The analysis unit can also analyze the meaning of the keyword using, for example, a dictionary database. The display unit displays the result analyzed by the analysis unit. The display unit displays the analysis results using, for example, a text display. The display unit can also display the analysis results using, for example, a graphical display. The display unit can also display the analysis results using, for example, a smartphone screen. In this way, the terminology understanding support system according to the embodiment allows the user to quickly and accurately understand the meaning of keywords whose meanings are unknown when viewing a presentation, a study group, a lecture, or the like.

[0030] The speech recognition unit converts speech into text. The speech recognition unit converts speech into text using, for example, a speech recognition algorithm. Specifically, the speech recognition algorithm converts a speech signal into digital data and analyzes the data to identify phonemes and words. The speech recognition software implements these algorithms and can convert the words spoken by a user into text in real time. For example, the speech recognition software performs noise removal and speech normalization to improve the quality of the speech data. In addition, the speech recognition device uses a microphone or dedicated hardware to capture speech with high accuracy and input it to the speech recognition algorithm. This allows the speech recognition unit to convert speech into text with high accuracy even in various environments and situations. Furthermore, the speech recognition unit can support multiple languages ​​and dialects, and can meet the diverse needs of users. For example, the speech recognition unit can support not only major languages ​​such as English, Japanese, and Chinese, but also regional dialects and technical terms. This allows the speech recognition unit to provide consistent, high-quality speech recognition services to global users.

[0031] The extraction unit extracts keywords from the text converted by the speech recognition unit. The extraction unit extracts keywords using, for example, frequency analysis. Specifically, frequency analysis identifies words and phrases that frequently appear in the text and extracts them as keywords. When natural language processing technology is used, the context and meaning of the text can be analyzed to extract important keywords. For example, important keywords can be identified by dividing the text into words using morphological analysis and analyzing the parts of speech and meaning of each word. The keyword extraction algorithm combines these technologies to achieve more accurate keyword extraction. For example, TF-IDF (Term Frequency-Inverse Document Frequency) can be used to identify words that appear frequently in the text but are not often seen in other documents. This allows the extraction unit to quickly and accurately extract important keywords that interest the user. Furthermore, the extraction unit can also extract keywords specialized for a specific domain or field of expertise, allowing for flexible response according to the needs of the user. For example, high-precision keyword extraction can be performed even in fields with a lot of technical terms, such as the medical field and the legal field.

[0032] The analysis unit analyzes the meaning of the keyword extracted by the extraction unit. The analysis unit analyzes the meaning of the keyword using, for example, a generation AI. The generation AI has the ability to learn large amounts of text data and understand context and meaning. Specifically, the generation AI analyzes the surrounding context of the extracted keyword and infers its meaning. For example, if the keyword is "cloud computing", the generation AI can analyze the definition of cloud computing, related technologies, advantages, etc. from the context. The semantic analysis algorithm can use a thesaurus or semantic network to analyze the meaning of the keyword in more detail. For example, a semantic network such as WordNet can be used to identify synonyms and related words of the keyword and to understand its meaning more deeply. The dictionary database provides definitions and examples of the keyword, and helps the analysis unit to accurately understand the meaning of the keyword. This allows the analysis unit to analyze the meaning of the extracted keyword from multiple angles and provide accurate and detailed information to the user. Furthermore, the analysis unit can perform more personalized semantic analysis by taking into account the user's past search history and areas of interest. This allows the analysis unit to flexibly respond to the needs of the user and provide higher satisfaction.

[0033] The display unit displays the results of the analysis by the analysis unit. The display unit displays the analysis results using, for example, a text display. Specifically, the meanings of the analyzed keywords and related information are provided to the user in text format. When a graphical display is used, the analysis results can be displayed in a visually easy-to-understand manner. For example, a graph, chart, or mind map showing the relevance of keywords can be used to allow the user to intuitively understand. When the analysis results are displayed using a smartphone screen, the user can check the analysis results anytime and anywhere. For example, the analysis results can be received in real time through a smartphone app. This allows the display unit to provide the user with quick and accurate information and support the user's understanding. Furthermore, the display unit is capable of customizing the user interface, and a display format according to the user's preferences can be selected. For example, by adjusting the font size, color, layout, etc., the user can view information more comfortably. In addition, the display unit is equipped with a voice output and a notification function, and can reliably convey important information to the user. This allows the display unit to improve the user's convenience and maximize the effect of the term understanding support system.

[0034] The terminology understanding support system includes components for improving the accuracy of speech recognition. The components for improving the accuracy of speech recognition use, for example, noise canceling technology. The noise canceling technology removes ambient noise and improves the accuracy of speech recognition. For example, the noise canceling technology can remove noise in a presentation venue and recognize only the voice of the speaker. The components for improving the accuracy of speech recognition can also improve the acoustic model. The improvement of the acoustic model improves the accuracy of the speech recognition algorithm. For example, the improvement of the acoustic model can remove surrounding conversations in a study group and preferentially recognize the voice of the lecturer. Furthermore, the components for improving the accuracy of speech recognition can also improve the performance of the speech recognition device. The improvement of the performance of the speech recognition device improves the accuracy of speech recognition. For example, the improvement of the performance of the speech recognition device can remove applause and laughter in a lecture and accurately convert the speaker's voice into text. This improves the accuracy of speech recognition and enables more accurate text conversion.

[0035] The terminology understanding support system includes a providing unit that provides the analysis result of the generation AI to the user. The providing unit provides the analysis result of the generation AI to the user. The providing unit provides the analysis result in, for example, a text format. The text format allows the user to visually confirm the analysis result. For example, the providing unit can display the meaning of the keyword analyzed by the generation AI in a text format. The providing unit can also provide the analysis result in a graph format. The graph format makes it easier for the user to visually understand the analysis result. For example, the providing unit can display related information of the keyword analyzed by the generation AI in a graph format. Furthermore, the providing unit can also provide the analysis result based on the AI ​​model used. The AI ​​model generates the analysis result based on the algorithm or data set used by the generation AI. For example, the providing unit can analyze the meaning of the keyword based on the AI ​​model used by the generation AI and provide the result to the user. This makes it easier for the user to confirm the analysis result by providing the analysis result of the generation AI to the user.

[0036] The speech recognition unit can instantly convert speech into text. The speech recognition unit can instantly convert speech into text, for example, using a real-time speech recognition algorithm. The real-time speech recognition algorithm accepts speech input and simultaneously converts it into text. For example, the speech recognition unit can convert speech during a presentation into text in real time and quickly extract keywords. The speech recognition unit can also instantly convert speech into text using low-latency processing technology. The low-latency processing technology minimizes the delay from speech input to text conversion. For example, the speech recognition unit can convert the speech of a lecturer at a study group into text with low latency and quickly extract keywords. Furthermore, the speech recognition unit can also instantly convert speech into text using a real-time speech recognition device. The real-time speech recognition device processes speech input in real time and converts it into text. For example, the speech recognition unit can convert the speech of a speaker at a lecture into text in real time and quickly extract keywords. This makes it possible to instantly extract and analyze keywords by converting speech into text in real time.

[0037] The extraction unit can extract keywords from text at high speed. The extraction unit can extract keywords from text at high speed, for example, by using a high-speed natural language processing algorithm. The high-speed natural language processing algorithm quickly analyzes text data and extracts important keywords. For example, the extraction unit can quickly extract important keywords from text during a presentation. The extraction unit can also quickly extract keywords from text by using parallel processing technology. The parallel processing technology executes multiple processes simultaneously to improve processing speed. For example, the extraction unit can process text data at a study group in parallel and quickly extract important keywords. The extraction unit can also quickly extract keywords from text by using a high-speed keyword extraction algorithm. The high-speed keyword extraction algorithm efficiently analyzes text data and extracts important keywords. For example, the extraction unit can analyze text data at a lecture quickly and quickly extract important keywords. This quickly extracts keywords from text, thereby improving the analysis speed.

[0038] The analysis unit can analyze the meaning of keywords using the generation AI. The analysis unit, for example, analyzes the meaning of keywords using the generation AI. The generation AI learns a large amount of data and has advanced natural language processing capabilities. For example, the analysis unit can quickly and accurately analyze the meaning of keywords that appear during a presentation using the generation AI. The analysis unit can also analyze the meaning of technical terms used in a study group using the generation AI. The generation AI can understand the meaning of technical terms and explain them to users in an easy-to-understand manner. Furthermore, the analysis unit can also analyze the meaning of keywords used in a lecture using the generation AI. The generation AI can analyze the meaning of keywords based on the content of the lecture and provide it to the user. As a result, the meaning of keywords can be quickly and accurately analyzed by using the generation AI.

[0039] The display unit can display the analysis results on the smartphone screen. The display unit, for example, uses a text display to display the analysis results on the smartphone screen. The text display allows the user to visually confirm the analysis results. For example, the display unit can display the meaning of the keywords analyzed by the generation AI on the smartphone screen in text format. The display unit can also display the analysis results on the smartphone screen using a graphical display. The graphical display makes it easier for the user to visually understand the analysis results. For example, the display unit can display related information of the keywords analyzed by the generation AI on the smartphone screen in graphical format. Furthermore, the display unit can also display the analysis results using the smartphone screen. The smartphone screen allows the user to easily confirm the analysis results. For example, the display unit displays the meaning of the keywords analyzed by the generation AI on the smartphone screen, so that the user can confirm it on the spot. As a result, by displaying the analysis results on the smartphone screen, the user can easily confirm the results.

[0040] The voice recognition unit can automatically filter background noise during voice recognition. The voice recognition unit automatically filters background noise using, for example, a noise reduction algorithm. The noise reduction algorithm removes background noise from the voice signal and improves the accuracy of voice recognition. For example, the voice recognition unit can filter noise in a presentation venue and recognize only the voice of the speaker. The voice recognition unit can also automatically filter background noise using a filtering technique. The filtering technique removes unnecessary noise from the voice signal and improves the accuracy of voice recognition. For example, the voice recognition unit can remove surrounding conversations in a study group and preferentially recognize the voice of the lecturer. Furthermore, the voice recognition unit can automatically filter background noise using a noise canceling device. The noise canceling device removes background noise from the voice signal and improves the accuracy of voice recognition. For example, the voice recognition unit can filter applause and laughter at a lecture and accurately convert the speaker's voice into text. This improves the accuracy of voice recognition by filtering the background noise.

[0041] The speech recognition unit can learn the voice characteristics of the speaker during speech recognition and use an individually adjusted recognition model. The speech recognition unit can learn the voice characteristics of the speaker using, for example, acoustic feature extraction. The acoustic feature extraction extracts the speaker's characteristic acoustic pattern from the speech signal. For example, the speech recognition unit can learn the voice characteristics of a presenter and use a recognition model optimized for that voice. The speech recognition unit can also learn the voice characteristics of the speaker using training of an individual voice model. The training of an individual voice model optimizes the recognition model using the voice data of a specific speaker. For example, the speech recognition unit can learn the voice characteristics of a lecturer at a study group and accurately recognize the lecturer's voice. Furthermore, the speech recognition unit can learn the voice characteristics of the speaker using a speech recognition algorithm and use an individually adjusted recognition model. The speech recognition algorithm analyzes the speaker's voice data and optimizes the recognition model. For example, the speech recognition unit can learn the voice characteristics of a speaker at a lecture and quickly convert the speaker's voice into text. As a result, by learning the voice characteristics of the speaker, an individually optimized recognition model can be used, improving recognition accuracy.

[0042] The speech recognition unit can improve the recognition accuracy by reflecting the geographical accent or dialect of the speaker during speech recognition. The speech recognition unit, for example, uses a dialect database to reflect the geographical accent or dialect of the speaker. The dialect database includes data on regional accents and dialects. For example, the speech recognition unit can accurately recognize the speech of a speaker with a regional accent. The speech recognition unit can also reflect the geographical accent or dialect of the speaker using an accent recognition algorithm. The accent recognition algorithm identifies regional accents or dialects from a speech signal. For example, the speech recognition unit can accurately convert the speech of a lecturer who uses a dialect into text. Furthermore, the speech recognition unit can also reflect the geographical accent or dialect of the speaker using a speech recognition algorithm. The speech recognition algorithm analyzes the speech data of the speaker and identifies regional accents or dialects. For example, the speech recognition unit can quickly recognize the speech of a presenter with a geographical accent. As a result, the recognition accuracy is improved by taking into account the geographical accent or dialect.

[0043] The voice recognition unit can improve the recognition accuracy by referring to the speaker's past speech history during voice recognition. The voice recognition unit, for example, uses a speech history database to refer to the speaker's past speech history. The speech history database includes the speaker's past speech data. For example, the voice recognition unit can refer to the presenter's past speech history and preferentially recognize specific terms and phrases. The voice recognition unit can also refer to the speaker's past speech history using a history reference algorithm. The history reference algorithm analyzes past speech data and identifies specific terms and phrases. For example, the voice recognition unit can refer to the past speech history of a lecturer at a study group and accurately recognize technical terms. Furthermore, the voice recognition unit can also refer to the speaker's past speech history using a voice recognition algorithm. The voice recognition algorithm analyzes past speech data and identifies specific terms and phrases. For example, the voice recognition unit can refer to the speaker's past speech history at a lecture and quickly recognize terms related to a specific theme. As a result, the recognition accuracy is improved by referring to the past speech history.

[0044] The extraction unit can preferentially extract keywords with high importance based on context information when extracting keywords. The extraction unit, for example, uses a context analysis algorithm to consider context information when extracting keywords. The context analysis algorithm analyzes the context and relevance of text to extract keywords with high importance. For example, the extraction unit can consider the context of a presentation to extract important keywords. The extraction unit can also use importance scoring to consider context information when extracting keywords. Importance scoring evaluates the importance of keywords in text and preferentially extracts them. For example, the extraction unit can understand the content of a study session and preferentially extract related keywords. Furthermore, the extraction unit can use natural language processing technology to consider context information when extracting keywords. Natural language processing technology analyzes the meaning and context of text to extract keywords with high importance. For example, the extraction unit can quickly extract important keywords based on the theme of a lecture. As a result, by considering context information, keywords with high importance can be preferentially extracted.

[0045] The extraction unit can automatically identify and extract synonyms and similar words when extracting keywords. The extraction unit, for example, identifies synonyms and similar words using a thesaurus database. The thesaurus database includes data of synonyms and similar words. For example, the extraction unit can identify synonyms used in a presentation and extract related keywords. The extraction unit can also identify synonyms and similar words using a synonym identification algorithm. The synonym identification algorithm analyzes synonyms and similar words in a text and extracts related keywords. For example, the extraction unit can identify synonyms used in a study group and extract important keywords. Furthermore, the extraction unit can identify synonyms and similar words using a natural language processing technology. The natural language processing technology analyzes synonyms and similar words in a text and extracts related keywords. For example, the extraction unit can identify synonyms and similar words used in a lecture and quickly extract related keywords. This makes it possible to efficiently extract related keywords by identifying synonyms and similar words.

[0046] The extraction unit can apply a specific extraction algorithm according to the genre or category of the text when extracting keywords. The extraction unit, for example, uses a genre classification algorithm to identify the genre or category of the text. The genre classification algorithm analyzes the text data and classifies it into a specific genre or category. For example, the extraction unit can apply an algorithm that preferentially extracts technical terms in the case of a technical presentation. The extraction unit can also extract keywords according to the genre or category of the text using a category-specific extraction algorithm. The category-specific extraction algorithm extracts keywords based on a specific category. For example, the extraction unit can apply an algorithm that extracts related keywords according to the content of a study session. Furthermore, the extraction unit can also extract keywords according to the genre or category of the text using a natural language processing technology. The natural language processing technology analyzes the text data and extracts keywords based on a specific genre or category. For example, the extraction unit can apply an algorithm that extracts important keywords based on the theme of a lecture. As a result, the extraction algorithm is applied according to the genre or category of the text, thereby improving the extraction accuracy.

[0047] The extraction unit can improve the extraction accuracy by referring to the past extraction history when extracting keywords. The extraction unit, for example, refers to the past extraction history using an extraction history database. The extraction history database includes data of keywords extracted in the past. For example, the extraction unit can refer to the past extraction history of the presentation and extract related keywords. The extraction unit can also refer to the past extraction history using a history reference algorithm. The history reference algorithm analyzes the past extraction data and identifies related keywords. For example, the extraction unit can refer to the past extraction history of the study group and extract important keywords. Furthermore, the extraction unit can also refer to the past extraction history using a natural language processing technique. The natural language processing technique analyzes the past extraction data and identifies related keywords. For example, the extraction unit can refer to the past extraction history of the lecture and quickly extract related keywords. As a result, the extraction accuracy is improved by referring to the past extraction history.

[0048] The analysis unit can automatically collect keyword-related data during analysis to improve the analysis accuracy. The analysis unit automatically collects keyword-related data using, for example, web scraping. Web scraping automatically collects information on the Internet and uses it for analysis. For example, the analysis unit can collect information related to keywords used in presentations to improve the analysis accuracy. The analysis unit can also automatically collect keyword-related data using a data collection algorithm. The data collection algorithm efficiently collects information related to specific keywords. For example, the analysis unit can collect information related to keywords used in study sessions to improve the analysis accuracy. Furthermore, the analysis unit can automatically collect keyword-related data using natural language processing technology. The natural language processing technology analyzes text data and collects related information. For example, the analysis unit can collect information related to keywords used in lectures to improve the analysis accuracy. As a result, the analysis accuracy is improved by collecting keyword-related information.

[0049] The analysis unit can determine the priority of the analysis based on the frequency of use and importance of the keywords during the analysis. The analysis unit, for example, uses frequency analysis to evaluate the frequency of use of the keywords. The frequency analysis analyzes the frequency of appearance of the keywords in the text and evaluates the importance. For example, the analysis unit can preferentially analyze keywords that are frequently used in presentations. The analysis unit can also evaluate the importance of the keywords using importance scoring. The importance scoring evaluates the importance of the keywords in the text and analyzes them preferentially. For example, the analysis unit can preferentially analyze important keywords in a study group. Furthermore, the analysis unit can also evaluate the frequency of use and importance of the keywords using natural language processing technology. The natural language processing technology analyzes text data and evaluates the frequency of use and importance of the keywords. For example, the analysis unit can preferentially analyze keywords that are frequently used in a lecture. As a result, by determining the priority of the analysis based on the frequency of use and importance of the keywords, important keywords can be preferentially analyzed.

[0050] The analysis unit can improve the analysis accuracy by referring to the related materials and databases of the keywords during the analysis. The analysis unit, for example, refers to the related materials of the keywords using a literature database. The literature database includes literature information related to the keywords. For example, the analysis unit can improve the analysis accuracy by referring to the related literature of the keywords used in the presentation. The analysis unit can also refer to the related materials of the keywords using a database reference algorithm. The database reference algorithm efficiently refers to materials related to a specific keyword. For example, the analysis unit can improve the analysis accuracy by referring to a related database of the keywords used in the study group. Furthermore, the analysis unit can also refer to the related materials of the keywords using a natural language processing technology. The natural language processing technology analyzes text data and refers to the related materials. For example, the analysis unit can improve the analysis accuracy by referring to the related literature and databases of the keywords used in the lecture. As a result, the analysis accuracy is improved by referring to the related literature and database.

[0051] The analysis unit can perform the analysis while taking into consideration the historical background and development history of the keyword. The analysis unit, for example, refers to the historical background of the keyword using a history database. The history database includes historical information related to the keyword. For example, the analysis unit can perform the analysis while taking into consideration the historical background of the keyword used in the presentation. The analysis unit can also analyze the development history of the keyword using a development history analysis algorithm. The development history analysis algorithm analyzes the development process of the keyword and provides related information. For example, the analysis unit can perform the analysis while taking into consideration the development history of the keyword used in the study group. Furthermore, the analysis unit can also analyze the historical background and development history of the keyword using natural language processing technology. The natural language processing technology analyzes text data and takes into consideration the historical background and development history of the keyword. For example, the analysis unit can perform the analysis while taking into consideration the historical background and development history of the keyword used in the lecture. This enables a deeper analysis by taking into consideration the historical background and development history of the keyword.

[0052] The display unit can provide a display method customized according to the visual settings of the user at the time of display. The display unit customizes the display content using, for example, a user setting option. The user setting option includes settings such as a color tone and a font preferred by the user. For example, the display unit can customize the display content using a color tone and a font preferred by the user. The display unit can also adjust the display content using a customization algorithm. The customization algorithm adjusts the display content based on the visual preferences of the user. For example, the display unit can adjust the layout and design according to the visual preferences of the user. Furthermore, the display unit can also customize the display content using a natural language processing technology. The natural language processing technology adjusts the display content based on the visual preferences of the user. For example, the display unit can customize the display content based on a theme selected by the user. This improves the satisfaction of the user by customizing the display method according to the visual preferences of the user.

[0053] The display unit can automatically display related additional information and links when displaying. The display unit collects related additional information using, for example, a related information collection algorithm. The related information collection algorithm efficiently collects information related to a specific keyword. For example, the display unit can display additional information related to the keyword so that the user can check the details. The display unit can also automatically display related links using a link generation technology. The link generation technology generates and displays links related to a specific keyword. For example, the display unit can display links related to the keyword so that the user can access the related information. Furthermore, the display unit can also display related additional information and links using a natural language processing technology. The natural language processing technology analyzes text data and displays related information and links. For example, the display unit can display videos and images related to the keyword so that the user can visually understand. This makes it easier for the user to access detailed information by displaying related additional information and links.

[0054] The display unit can select an appropriate display method based on the device information of the user at the time of display. The display unit detects the device information of the user using, for example, a device detection algorithm. The device detection algorithm identifies the type and characteristics of the device used by the user. For example, when the user is using a smartphone, the display unit can provide a display method that matches the screen size. The display unit can also adjust the display method based on the device information of the user using responsive design. The responsive design optimizes the display content according to the screen size and resolution of the device. For example, when the user is using a tablet, the display unit can provide a display method optimized for a large screen. Furthermore, the display unit can also select a display method based on the device information of the user using natural language processing technology. The natural language processing technology analyzes the device information of the user and provides the optimal display method. For example, when the user is using a smart watch, the display unit can provide a simple and highly visible display method. This makes it possible to provide the optimal display method by taking into account the device information of the user.

[0055] The display unit can customize the display contents by referring to the user's past browsing history when displaying. The display unit, for example, refers to the user's past browsing history using a browsing history database. The browsing history database includes information that the user has browsed in the past. For example, the display unit can refer to the user's past browsing history and preferentially display related information. The display unit can also refer to the user's past browsing history using a history reference algorithm. The history reference algorithm analyzes past browsing data and identifies related information. For example, the display unit can display related information based on keywords that the user has browsed in the past. Furthermore, the display unit can also refer to the user's past browsing history using natural language processing technology. The natural language processing technology analyzes past browsing data and identifies related information. For example, the display unit can analyze the user's past browsing history and provide optimal display content. As a result, information that is highly relevant to the user can be displayed by referring to the past browsing history.

[0056] The accuracy improvement unit can optimize the algorithm by referring to past recognition data when improving the accuracy. The accuracy improvement unit, for example, refers to past recognition data using a recognition database. The recognition database includes data that has been recognized in the past. For example, the accuracy improvement unit can optimize the algorithm by referring to past voice recognition data. The accuracy improvement unit can also refer to past recognition data using a history reference algorithm. The history reference algorithm analyzes past recognition data and optimizes the algorithm. For example, the accuracy improvement unit can optimize the algorithm by referring to past keyword extraction data. Furthermore, the accuracy improvement unit can also refer to past recognition data using natural language processing technology. The natural language processing technology analyzes past recognition data and optimizes the algorithm. For example, the accuracy improvement unit can optimize the algorithm by referring to past analysis data. This makes it possible to optimize the algorithm by referring to past recognition data.

[0057] The accuracy improvement unit can select optimal data by considering the environmental conditions of the voice recognition when improving the accuracy. The accuracy improvement unit, for example, uses an environmental sound database to consider the environmental conditions of the voice recognition. The environmental sound database includes voice data related to specific environmental conditions. For example, the accuracy improvement unit can select optimal data by considering the environmental conditions of a presentation venue. The accuracy improvement unit can also consider the environmental conditions of the voice recognition by using an environmental condition detection algorithm. The environmental condition detection algorithm detects specific environmental conditions and selects optimal data. For example, the accuracy improvement unit can consider the environmental conditions of a study group and select optimal data. Furthermore, the accuracy improvement unit can consider the environmental conditions of the voice recognition by using natural language processing technology. The natural language processing technology analyzes the environmental conditions and selects optimal data. For example, the accuracy improvement unit can consider the environmental conditions of a lecture and select optimal data. As a result, optimal data can be selected by considering the environmental conditions of the voice recognition, and accuracy improvement can be effectively performed.

[0058] The providing unit can provide optimal information by referring to the user's past usage history at the time of providing. The providing unit, for example, uses a usage history database to refer to the user's past usage history. The usage history database includes information used by the user in the past. For example, the providing unit can refer to the user's past usage history and provide related information. The providing unit can also refer to the user's past usage history using a history reference algorithm. The history reference algorithm analyzes past usage data and identifies related information. For example, the providing unit can provide related information based on keywords used by the user in the past. Furthermore, the providing unit can also refer to the user's past usage history using natural language processing technology. The natural language processing technology analyzes past usage data and identifies related information. For example, the providing unit can analyze the user's past usage history and provide optimal information. As a result, information highly relevant to the user can be provided by referring to the past usage history.

[0059] The providing unit can select an appropriate information providing method based on the device information of the user at the time of providing. The providing unit detects the device information of the user using, for example, a device detection algorithm. The device detection algorithm identifies the type and characteristics of the device used by the user. For example, when the user is using a smartphone, the providing unit can provide an information providing method that matches the screen size. The providing unit can also adjust the information providing method based on the device information of the user using responsive design. The responsive design optimizes the information content according to the screen size and resolution of the device. For example, when the user is using a tablet, the providing unit can provide an information providing method that is optimized for a large screen. Furthermore, the providing unit can also select the information providing method based on the device information of the user using natural language processing technology. The natural language processing technology analyzes the device information of the user and provides the optimal information providing method. For example, when the user is using a smart watch, the providing unit can provide a concise and highly visible information providing method. This makes it possible to provide the optimal information providing method by taking into account the device information of the user.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] The terminology understanding support system can refer to the user's learning history and provide the meaning of keywords based on what the user has learned in the past. For example, the content that the user has learned in the past is stored in a database, and the analysis unit can refer to the database to provide the meaning of new keywords taking into account what the user already understands. In addition, based on the learning history, it can also prioritize the display of related keywords and topics. Furthermore, based on the learning history, it can also focus on analyzing keywords related to areas that the user had difficulty in the past and provide detailed explanations. In this way, more effective learning support can be provided by utilizing the user's learning history.

[0062] The terminology understanding support system can monitor the user's current learning progress in real time and provide the meanings of keywords according to that progress. For example, if a user is studying a particular topic, it can preferentially analyze and display keywords related to that topic. It can also provide explanations of different levels of difficulty according to the user's learning progress. For example, it can provide basic explanations to beginners and detailed technical explanations to advanced users. It can also suggest keywords and topics that the user should study next based on the user's learning progress. This makes it possible to provide flexible support according to the user's learning progress.

[0063] The terminology understanding support system can provide the meaning of keywords according to the user's learning style. For example, explanations using diagrams and graphs can be provided to visual learners, and explanations using audio and video can be provided to auditory learners. In addition, a function for checking the meaning of keywords in the form of a quiz can be provided to users who prefer interactive learning. Furthermore, the system can suggest the most suitable learning method based on the user's learning style. For example, visual notes can be suggested to visual learners, and podcasts can be suggested to auditory learners. This makes it possible to provide effective support according to the user's learning style.

[0064] The terminology understanding support system can provide the meaning of keywords according to the user's learning goals. For example, for a user studying for a specific exam, it can prioritize the analysis and display of keywords related to that exam. It can also provide the latest industry trends and technical terms to users who are aiming to advance their careers. It can also suggest specific steps and study plans that the user should achieve based on their learning goals. This makes it possible to provide effective support according to the user's learning goals.

[0065] The terminology understanding support system can provide the meaning of keywords according to the user's learning environment. For example, it can provide detailed text explanations to users who are learning in a quiet environment, and explanations using audio or video to users who are learning in a noisy environment. It can also provide summaries that can be understood in a short time to users who are on the move. It can also suggest optimal learning tools and resources based on the learning environment. This makes it possible to provide flexible support according to the user's learning environment.

[0066] The process flow of the first embodiment will be briefly described below.

[0067] Step 1: The speech recognition unit converts speech to text. The speech recognition unit can convert speech to text using, for example, a speech recognition algorithm, speech recognition software, or a speech recognition device. Step 2: The extraction unit extracts keywords from the text converted by the speech recognition unit. The extraction unit can extract keywords using, for example, frequency analysis, natural language processing techniques, or keyword extraction algorithms. Step 3: The analysis unit analyzes the meaning of the keywords extracted by the extraction unit. The analysis unit can analyze the meaning of the keywords using, for example, a generation AI, a semantic analysis algorithm, or a dictionary database. Step 4: The display unit displays the results analyzed by the analysis unit. The display unit can display the analysis results using, for example, a text display, a graphical display, or a smartphone screen.

[0068] (Example 2) The terminology understanding support system according to the embodiment of the present invention is a system that uses a smartphone to automatically display the meaning of a keyword that the user does not know when a presentation, study group, lecture, etc. is viewed and heard. This terminology understanding support system first accepts voice input through the smartphone's microphone. Next, it uses voice recognition technology to convert the voice into text and extracts keywords from the text. The extracted keywords are analyzed for meaning using a generation AI and displayed on the smartphone screen. This allows the user to easily understand the meaning of the term. For example, if the keyword "deep learning" appears during a presentation, the smartphone's microphone recognizes the voice and converts it into text. Next, the generation AI analyzes the meaning of "deep learning" and displays the result on the smartphone screen. The user can understand the meaning of "deep learning" just by looking at the smartphone screen. This system can convert voice into text in real time by using voice recognition technology. Next, it can quickly and accurately analyze the meaning of the keyword by using a generation AI. Furthermore, by displaying it on the smartphone screen, the user can easily check the meaning of the term. This system improves the viewing experience during presentations, study sessions, lectures, etc., and deepens understanding of keywords whose meanings are unknown. For example, even if a technical presentation contains a lot of technical terms, by using this system, users can understand the meaning of the terms on the spot and gain a deeper understanding of the content of the presentation. As a result, the terminology understanding support system can quickly and accurately understand the meaning of keywords whose meanings are unknown to users when viewing presentations, study sessions, lectures, etc.

[0069] The terminology understanding support system according to the embodiment includes a speech recognition unit, an extraction unit, an analysis unit, and a display unit. The speech recognition unit converts speech into text. The speech recognition unit converts speech into text using, for example, a speech recognition algorithm. The speech recognition unit can also convert speech into text using, for example, speech recognition software. The speech recognition unit can also convert speech into text using, for example, a speech recognition device. The extraction unit extracts keywords from the text converted by the speech recognition unit. The extraction unit extracts keywords using, for example, frequency analysis. The extraction unit can also extract keywords using, for example, natural language processing technology. The extraction unit can also extract keywords using, for example, a keyword extraction algorithm. The analysis unit analyzes the meaning of the keyword extracted by the extraction unit. The analysis unit analyzes the meaning of the keyword using, for example, a generation AI. The analysis unit can also analyze the meaning of the keyword using, for example, a semantic analysis algorithm. The analysis unit can also analyze the meaning of the keyword using, for example, a dictionary database. The display unit displays the result analyzed by the analysis unit. The display unit displays the analysis results using, for example, a text display. The display unit can also display the analysis results using, for example, a graphical display. The display unit can also display the analysis results using, for example, a smartphone screen. In this way, the terminology understanding support system according to the embodiment allows the user to quickly and accurately understand the meaning of keywords whose meanings are unknown when viewing a presentation, a study group, a lecture, or the like.

[0070] The speech recognition unit converts speech into text. The speech recognition unit converts speech into text using, for example, a speech recognition algorithm. Specifically, the speech recognition algorithm converts a speech signal into digital data and analyzes the data to identify phonemes and words. The speech recognition software implements these algorithms and can convert the words spoken by a user into text in real time. For example, the speech recognition software performs noise removal and speech normalization to improve the quality of the speech data. In addition, the speech recognition device uses a microphone or dedicated hardware to capture speech with high accuracy and input it to the speech recognition algorithm. This allows the speech recognition unit to convert speech into text with high accuracy even in various environments and situations. Furthermore, the speech recognition unit can support multiple languages ​​and dialects, and can meet the diverse needs of users. For example, the speech recognition unit can support not only major languages ​​such as English, Japanese, and Chinese, but also regional dialects and technical terms. This allows the speech recognition unit to provide consistent, high-quality speech recognition services to global users.

[0071] The extraction unit extracts keywords from the text converted by the speech recognition unit. The extraction unit extracts keywords using, for example, frequency analysis. Specifically, frequency analysis identifies words and phrases that frequently appear in the text and extracts them as keywords. When natural language processing technology is used, the context and meaning of the text can be analyzed to extract important keywords. For example, important keywords can be identified by dividing the text into words using morphological analysis and analyzing the parts of speech and meaning of each word. The keyword extraction algorithm combines these technologies to achieve more accurate keyword extraction. For example, TF-IDF (Term Frequency-Inverse Document Frequency) can be used to identify words that appear frequently in the text but are not often seen in other documents. This allows the extraction unit to quickly and accurately extract important keywords that interest the user. Furthermore, the extraction unit can also extract keywords specialized for a specific domain or field of expertise, allowing for flexible response according to the needs of the user. For example, high-precision keyword extraction can be performed even in fields with a lot of technical terms, such as the medical field and the legal field.

[0072] The analysis unit analyzes the meaning of the keyword extracted by the extraction unit. The analysis unit analyzes the meaning of the keyword using, for example, a generation AI. The generation AI has the ability to learn large amounts of text data and understand context and meaning. Specifically, the generation AI analyzes the surrounding context of the extracted keyword and infers its meaning. For example, if the keyword is "cloud computing", the generation AI can analyze the definition of cloud computing, related technologies, advantages, etc. from the context. The semantic analysis algorithm can use a thesaurus or semantic network to analyze the meaning of the keyword in more detail. For example, a semantic network such as WordNet can be used to identify synonyms and related words of the keyword and to understand its meaning more deeply. The dictionary database provides definitions and examples of the keyword, and helps the analysis unit to accurately understand the meaning of the keyword. This allows the analysis unit to analyze the meaning of the extracted keyword from multiple angles and provide accurate and detailed information to the user. Furthermore, the analysis unit can perform more personalized semantic analysis by taking into account the user's past search history and areas of interest. This allows the analysis unit to flexibly respond to the needs of the user and provide higher satisfaction.

[0073] The display unit displays the results of the analysis by the analysis unit. The display unit displays the analysis results using, for example, a text display. Specifically, the meanings of the analyzed keywords and related information are provided to the user in text format. When a graphical display is used, the analysis results can be displayed in a visually easy-to-understand manner. For example, a graph, chart, or mind map showing the relevance of keywords can be used to allow the user to intuitively understand. When the analysis results are displayed using a smartphone screen, the user can check the analysis results anytime and anywhere. For example, the analysis results can be received in real time through a smartphone app. This allows the display unit to provide the user with quick and accurate information and support the user's understanding. Furthermore, the display unit is capable of customizing the user interface, and a display format according to the user's preferences can be selected. For example, by adjusting the font size, color, layout, etc., the user can view information more comfortably. In addition, the display unit is equipped with a voice output and a notification function, and can reliably convey important information to the user. This allows the display unit to improve the user's convenience and maximize the effect of the term understanding support system.

[0074] The terminology understanding support system includes components for improving the accuracy of speech recognition. The components for improving the accuracy of speech recognition use, for example, noise canceling technology. The noise canceling technology removes ambient noise and improves the accuracy of speech recognition. For example, the noise canceling technology can remove noise in a presentation venue and recognize only the voice of the speaker. The components for improving the accuracy of speech recognition can also improve the acoustic model. The improvement of the acoustic model improves the accuracy of the speech recognition algorithm. For example, the improvement of the acoustic model can remove surrounding conversations in a study group and preferentially recognize the voice of the lecturer. Furthermore, the components for improving the accuracy of speech recognition can also improve the performance of the speech recognition device. The improvement of the performance of the speech recognition device improves the accuracy of speech recognition. For example, the improvement of the performance of the speech recognition device can remove applause and laughter in a lecture and accurately convert the speaker's voice into text. This improves the accuracy of speech recognition and enables more accurate text conversion.

[0075] The terminology understanding support system includes a providing unit that provides the analysis result of the generation AI to the user. The providing unit provides the analysis result of the generation AI to the user. The providing unit provides the analysis result in, for example, a text format. The text format allows the user to visually confirm the analysis result. For example, the providing unit can display the meaning of the keyword analyzed by the generation AI in a text format. The providing unit can also provide the analysis result in a graph format. The graph format makes it easier for the user to visually understand the analysis result. For example, the providing unit can display related information of the keyword analyzed by the generation AI in a graph format. Furthermore, the providing unit can also provide the analysis result based on the AI ​​model used. The AI ​​model generates the analysis result based on the algorithm or data set used by the generation AI. For example, the providing unit can analyze the meaning of the keyword based on the AI ​​model used by the generation AI and provide the result to the user. This makes it easier for the user to confirm the analysis result by providing the analysis result of the generation AI to the user.

[0076] The speech recognition unit can instantly convert speech into text. The speech recognition unit can instantly convert speech into text, for example, using a real-time speech recognition algorithm. The real-time speech recognition algorithm accepts speech input and simultaneously converts it into text. For example, the speech recognition unit can convert speech during a presentation into text in real time and quickly extract keywords. The speech recognition unit can also instantly convert speech into text using low-latency processing technology. The low-latency processing technology minimizes the delay from speech input to text conversion. For example, the speech recognition unit can convert the speech of a lecturer at a study group into text with low latency and quickly extract keywords. Furthermore, the speech recognition unit can also instantly convert speech into text using a real-time speech recognition device. The real-time speech recognition device processes speech input in real time and converts it into text. For example, the speech recognition unit can convert the speech of a speaker at a lecture into text in real time and quickly extract keywords. This makes it possible to instantly extract and analyze keywords by converting speech into text in real time.

[0077] The extraction unit can extract keywords from text at high speed. The extraction unit can extract keywords from text at high speed, for example, by using a high-speed natural language processing algorithm. The high-speed natural language processing algorithm quickly analyzes text data and extracts important keywords. For example, the extraction unit can quickly extract important keywords from text during a presentation. The extraction unit can also quickly extract keywords from text by using parallel processing technology. The parallel processing technology executes multiple processes simultaneously to improve processing speed. For example, the extraction unit can process text data at a study group in parallel and quickly extract important keywords. The extraction unit can also quickly extract keywords from text by using a high-speed keyword extraction algorithm. The high-speed keyword extraction algorithm efficiently analyzes text data and extracts important keywords. For example, the extraction unit can analyze text data at a lecture quickly and quickly extract important keywords. This quickly extracts keywords from text, thereby improving the analysis speed.

[0078] The analysis unit can analyze the meaning of keywords using the generation AI. The analysis unit, for example, analyzes the meaning of keywords using the generation AI. The generation AI learns a large amount of data and has advanced natural language processing capabilities. For example, the analysis unit can quickly and accurately analyze the meaning of keywords that appear during a presentation using the generation AI. The analysis unit can also analyze the meaning of technical terms used in a study group using the generation AI. The generation AI can understand the meaning of technical terms and explain them to users in an easy-to-understand manner. Furthermore, the analysis unit can also analyze the meaning of keywords used in a lecture using the generation AI. The generation AI can analyze the meaning of keywords based on the content of the lecture and provide it to the user. As a result, the meaning of keywords can be quickly and accurately analyzed by using the generation AI.

[0079] The display unit can display the analysis results on the smartphone screen. The display unit, for example, uses a text display to display the analysis results on the smartphone screen. The text display allows the user to visually confirm the analysis results. For example, the display unit can display the meaning of the keywords analyzed by the generation AI on the smartphone screen in text format. The display unit can also display the analysis results on the smartphone screen using a graphical display. The graphical display makes it easier for the user to visually understand the analysis results. For example, the display unit can display related information of the keywords analyzed by the generation AI on the smartphone screen in graphical format. Furthermore, the display unit can also display the analysis results using the smartphone screen. The smartphone screen allows the user to easily confirm the analysis results. For example, the display unit displays the meaning of the keywords analyzed by the generation AI on the smartphone screen, so that the user can confirm it on the spot. As a result, by displaying the analysis results on the smartphone screen, the user can easily confirm the results.

[0080] The voice recognition unit can estimate the user's emotion and adjust the voice recognition parameters based on the estimated user's emotion. The voice recognition unit estimates the user's emotion using, for example, a machine learning algorithm. The machine learning algorithm analyzes data such as the user's facial expression and voice to estimate the emotion. For example, the voice recognition unit can increase the sensitivity of voice recognition and convert the voice into text more accurately when the user is nervous. Also, when the user is relaxed, the voice recognition unit can set the sensitivity of voice recognition to normal and accept natural voice input. Furthermore, when the user is in a hurry, the voice recognition unit can prioritize the speed of voice recognition and convert the voice into text quickly. Thereby, by adjusting the voice recognition parameters according to the user's emotion, the recognition accuracy is improved. 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.

[0081] The voice recognition unit can automatically filter background noise during voice recognition. The voice recognition unit automatically filters background noise using, for example, a noise reduction algorithm. The noise reduction algorithm removes background noise from the voice signal and improves the accuracy of voice recognition. For example, the voice recognition unit can filter noise in a presentation venue and recognize only the voice of the speaker. The voice recognition unit can also automatically filter background noise using a filtering technique. The filtering technique removes unnecessary noise from the voice signal and improves the accuracy of voice recognition. For example, the voice recognition unit can remove surrounding conversations in a study group and preferentially recognize the voice of the lecturer. Furthermore, the voice recognition unit can automatically filter background noise using a noise canceling device. The noise canceling device removes background noise from the voice signal and improves the accuracy of voice recognition. For example, the voice recognition unit can filter applause and laughter at a lecture and accurately convert the speaker's voice into text. This improves the accuracy of voice recognition by filtering the background noise.

[0082] The speech recognition unit can learn the voice characteristics of the speaker during speech recognition and use an individually adjusted recognition model. The speech recognition unit can learn the voice characteristics of the speaker using, for example, acoustic feature extraction. The acoustic feature extraction extracts the speaker's characteristic acoustic pattern from the speech signal. For example, the speech recognition unit can learn the voice characteristics of a presenter and use a recognition model optimized for that voice. The speech recognition unit can also learn the voice characteristics of the speaker using training of an individual voice model. The training of an individual voice model optimizes the recognition model using the voice data of a specific speaker. For example, the speech recognition unit can learn the voice characteristics of a lecturer at a study group and accurately recognize the lecturer's voice. Furthermore, the speech recognition unit can learn the voice characteristics of the speaker using a speech recognition algorithm and use an individually adjusted recognition model. The speech recognition algorithm analyzes the speaker's voice data and optimizes the recognition model. For example, the speech recognition unit can learn the voice characteristics of a speaker at a lecture and quickly convert the speaker's voice into text. As a result, by learning the voice characteristics of the speaker, an individually optimized recognition model can be used, improving recognition accuracy.

[0083] The voice recognition unit can estimate the user's emotion and determine the priority of voice recognition based on the estimated user's emotion. The voice recognition unit estimates the user's emotion using, for example, a machine learning algorithm. The machine learning algorithm analyzes data such as the user's facial expression and voice to estimate the emotion. For example, the voice recognition unit can preferentially recognize important keywords when the user is nervous. Also, the voice recognition unit can evenly recognize the entire voice when the user is relaxed. Furthermore, the voice recognition unit can preferentially recognize short phrases and words when the user is in a hurry. As a result, important voice can be preferentially recognized by determining the priority of voice recognition 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.

[0084] The speech recognition unit can improve the recognition accuracy by reflecting the geographical accent or dialect of the speaker during speech recognition. The speech recognition unit, for example, uses a dialect database to reflect the geographical accent or dialect of the speaker. The dialect database includes data on regional accents and dialects. For example, the speech recognition unit can accurately recognize the speech of a speaker with a regional accent. The speech recognition unit can also reflect the geographical accent or dialect of the speaker using an accent recognition algorithm. The accent recognition algorithm identifies regional accents or dialects from a speech signal. For example, the speech recognition unit can accurately convert the speech of a lecturer who uses a dialect into text. Furthermore, the speech recognition unit can also reflect the geographical accent or dialect of the speaker using a speech recognition algorithm. The speech recognition algorithm analyzes the speech data of the speaker and identifies regional accents or dialects. For example, the speech recognition unit can quickly recognize the speech of a presenter with a geographical accent. As a result, the recognition accuracy is improved by taking into account the geographical accent or dialect.

[0085] The voice recognition unit can improve the recognition accuracy by referring to the speaker's past speech history during voice recognition. The voice recognition unit, for example, uses a speech history database to refer to the speaker's past speech history. The speech history database includes the speaker's past speech data. For example, the voice recognition unit can refer to the presenter's past speech history and preferentially recognize specific terms and phrases. The voice recognition unit can also refer to the speaker's past speech history using a history reference algorithm. The history reference algorithm analyzes past speech data and identifies specific terms and phrases. For example, the voice recognition unit can refer to the past speech history of a lecturer at a study group and accurately recognize technical terms. Furthermore, the voice recognition unit can also refer to the speaker's past speech history using a voice recognition algorithm. The voice recognition algorithm analyzes past speech data and identifies specific terms and phrases. For example, the voice recognition unit can refer to the speaker's past speech history at a lecture and quickly recognize terms related to a specific theme. As a result, the recognition accuracy is improved by referring to the past speech history.

[0086] The extraction unit can estimate the user's emotion and adjust the keyword extraction algorithm based on the estimated user's emotion. The extraction unit estimates the user's emotion using, for example, a machine learning algorithm. The machine learning algorithm analyzes data such as the user's facial expression and voice to estimate the emotion. For example, the extraction unit can preferentially extract important keywords when the user is nervous. Also, the extraction unit can extract keywords evenly from the entire text when the user is relaxed. Furthermore, the extraction unit can preferentially extract short phrases and words when the user is in a hurry. This improves the extraction accuracy by adjusting the keyword extraction algorithm 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.

[0087] The extraction unit can preferentially extract keywords with high importance based on context information when extracting keywords. The extraction unit, for example, uses a context analysis algorithm to consider context information when extracting keywords. The context analysis algorithm analyzes the context and relevance of text to extract keywords with high importance. For example, the extraction unit can consider the context of a presentation to extract important keywords. The extraction unit can also use importance scoring to consider context information when extracting keywords. Importance scoring evaluates the importance of keywords in text and preferentially extracts them. For example, the extraction unit can understand the content of a study session and preferentially extract related keywords. Furthermore, the extraction unit can use natural language processing technology to consider context information when extracting keywords. Natural language processing technology analyzes the meaning and context of text to extract keywords with high importance. For example, the extraction unit can quickly extract important keywords based on the theme of a lecture. As a result, by considering context information, keywords with high importance can be preferentially extracted.

[0088] The extraction unit can automatically identify and extract synonyms and similar words when extracting keywords. The extraction unit, for example, identifies synonyms and similar words using a thesaurus database. The thesaurus database includes data of synonyms and similar words. For example, the extraction unit can identify synonyms used in a presentation and extract related keywords. The extraction unit can also identify synonyms and similar words using a synonym identification algorithm. The synonym identification algorithm analyzes synonyms and similar words in a text and extracts related keywords. For example, the extraction unit can identify synonyms used in a study group and extract important keywords. Furthermore, the extraction unit can identify synonyms and similar words using a natural language processing technology. The natural language processing technology analyzes synonyms and similar words in a text and extracts related keywords. For example, the extraction unit can identify synonyms and similar words used in a lecture and quickly extract related keywords. This makes it possible to efficiently extract related keywords by identifying synonyms and similar words.

[0089] The extraction unit can estimate the user's emotion and determine the priority of keywords to be extracted based on the estimated user's emotion. The extraction unit estimates the user's emotion using, for example, a machine learning algorithm. The machine learning algorithm analyzes data such as the user's facial expression and voice to estimate the emotion. For example, the extraction unit can preferentially extract important keywords when the user is nervous. Also, the extraction unit can extract keywords evenly from the entire text when the user is relaxed. Furthermore, the extraction unit can preferentially extract short phrases or words when the user is in a hurry. As a result, by determining the priority of keywords according to the user's emotion, important keywords can be preferentially extracted. 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.

[0090] The extraction unit can apply a specific extraction algorithm according to the genre or category of the text when extracting keywords. The extraction unit, for example, uses a genre classification algorithm to identify the genre or category of the text. The genre classification algorithm analyzes the text data and classifies it into a specific genre or category. For example, the extraction unit can apply an algorithm that preferentially extracts technical terms in the case of a technical presentation. The extraction unit can also extract keywords according to the genre or category of the text using a category-specific extraction algorithm. The category-specific extraction algorithm extracts keywords based on a specific category. For example, the extraction unit can apply an algorithm that extracts related keywords according to the content of a study session. Furthermore, the extraction unit can also extract keywords according to the genre or category of the text using a natural language processing technology. The natural language processing technology analyzes the text data and extracts keywords based on a specific genre or category. For example, the extraction unit can apply an algorithm that extracts important keywords based on the theme of a lecture. As a result, the extraction algorithm is applied according to the genre or category of the text, thereby improving the extraction accuracy.

[0091] The extraction unit can improve the extraction accuracy by referring to the past extraction history when extracting keywords. The extraction unit, for example, refers to the past extraction history using an extraction history database. The extraction history database includes data of keywords extracted in the past. For example, the extraction unit can refer to the past extraction history of the presentation and extract related keywords. The extraction unit can also refer to the past extraction history using a history reference algorithm. The history reference algorithm analyzes the past extraction data and identifies related keywords. For example, the extraction unit can refer to the past extraction history of the study group and extract important keywords. Furthermore, the extraction unit can also refer to the past extraction history using a natural language processing technique. The natural language processing technique analyzes the past extraction data and identifies related keywords. For example, the extraction unit can refer to the past extraction history of the lecture and quickly extract related keywords. As a result, the extraction accuracy is improved by referring to the past extraction history.

[0092] The analysis unit can estimate the user's emotion and adjust the expression method of the analysis result based on the estimated user's emotion. The analysis unit estimates the user's emotion using, for example, a machine learning algorithm. The machine learning algorithm analyzes data such as the user's facial expression and voice to estimate the emotion. For example, the analysis unit can display a simple and highly visible analysis result when the user is nervous. Furthermore, the analysis unit can display an analysis result including detailed information when the user is relaxed. Furthermore, the analysis unit can display an analysis result that focuses on the main points when the user is in a hurry. This makes it possible to provide an analysis result that is easy for the user to understand by adjusting the expression method of the analysis result according to the user's emotion. The emotion estimation is realized using, for example, an emotion estimation function using 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.

[0093] The analysis unit can automatically collect keyword-related data during analysis to improve the analysis accuracy. The analysis unit automatically collects keyword-related data using, for example, web scraping. Web scraping automatically collects information on the Internet and uses it for analysis. For example, the analysis unit can collect information related to keywords used in presentations to improve the analysis accuracy. The analysis unit can also automatically collect keyword-related data using a data collection algorithm. The data collection algorithm efficiently collects information related to specific keywords. For example, the analysis unit can collect information related to keywords used in study sessions to improve the analysis accuracy. Furthermore, the analysis unit can automatically collect keyword-related data using natural language processing technology. The natural language processing technology analyzes text data and collects related information. For example, the analysis unit can collect information related to keywords used in lectures to improve the analysis accuracy. As a result, the analysis accuracy is improved by collecting keyword-related information.

[0094] The analysis unit can determine the priority of the analysis based on the frequency of use and importance of the keywords during the analysis. The analysis unit, for example, uses frequency analysis to evaluate the frequency of use of the keywords. The frequency analysis analyzes the frequency of appearance of the keywords in the text and evaluates the importance. For example, the analysis unit can preferentially analyze keywords that are frequently used in presentations. The analysis unit can also evaluate the importance of the keywords using importance scoring. The importance scoring evaluates the importance of the keywords in the text and analyzes them preferentially. For example, the analysis unit can preferentially analyze important keywords in a study group. Furthermore, the analysis unit can also evaluate the frequency of use and importance of the keywords using natural language processing technology. The natural language processing technology analyzes text data and evaluates the frequency of use and importance of the keywords. For example, the analysis unit can preferentially analyze keywords that are frequently used in a lecture. As a result, by determining the priority of the analysis based on the frequency of use and importance of the keywords, important keywords can be preferentially analyzed.

[0095] The analysis unit can estimate the user's emotion and adjust the display order of the analysis results based on the estimated user's emotion. The analysis unit estimates the user's emotion using, for example, a machine learning algorithm. The machine learning algorithm analyzes data such as the user's facial expression and voice to estimate the emotion. For example, the analysis unit can preferentially display important analysis results when the user is nervous. Furthermore, the analysis unit can evenly display the entire analysis results when the user is relaxed. Furthermore, the analysis unit can preferentially display analysis results that focus on the main points when the user is in a hurry. This allows important information to be preferentially displayed by adjusting the display order of the analysis results according to the user's emotion. The emotion estimation is realized using, for example, an emotion estimation function using 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.

[0096] The analysis unit can improve the analysis accuracy by referring to the related materials and databases of the keywords during the analysis. The analysis unit, for example, refers to the related materials of the keywords using a literature database. The literature database includes literature information related to the keywords. For example, the analysis unit can improve the analysis accuracy by referring to the related literature of the keywords used in the presentation. The analysis unit can also refer to the related materials of the keywords using a database reference algorithm. The database reference algorithm efficiently refers to materials related to a specific keyword. For example, the analysis unit can improve the analysis accuracy by referring to a related database of the keywords used in the study group. Furthermore, the analysis unit can also refer to the related materials of the keywords using a natural language processing technology. The natural language processing technology analyzes text data and refers to the related materials. For example, the analysis unit can improve the analysis accuracy by referring to the related literature and databases of the keywords used in the lecture. As a result, the analysis accuracy is improved by referring to the related literature and database.

[0097] The analysis unit can perform the analysis while taking into consideration the historical background and development history of the keyword. The analysis unit, for example, refers to the historical background of the keyword using a history database. The history database includes historical information related to the keyword. For example, the analysis unit can perform the analysis while taking into consideration the historical background of the keyword used in the presentation. The analysis unit can also analyze the development history of the keyword using a development history analysis algorithm. The development history analysis algorithm analyzes the development process of the keyword and provides related information. For example, the analysis unit can perform the analysis while taking into consideration the development history of the keyword used in the study group. Furthermore, the analysis unit can also analyze the historical background and development history of the keyword using natural language processing technology. The natural language processing technology analyzes text data and takes into consideration the historical background and development history of the keyword. For example, the analysis unit can perform the analysis while taking into consideration the historical background and development history of the keyword used in the lecture. This enables a deeper analysis by taking into consideration the historical background and development history of the keyword.

[0098] The display unit can estimate the user's emotion and adjust the format of the display content based on the estimated user's emotion. The display unit estimates the user's emotion using, for example, a machine learning algorithm. The machine learning algorithm analyzes data such as the user's facial expression and voice to estimate the emotion. For example, the display unit can provide a simple, highly visible format when the user is nervous. Also, the display unit can provide a format including detailed information when the user is relaxed. Furthermore, the display unit can provide a format that focuses on the main points when the user is in a hurry. This improves visibility by adjusting the format of the display content 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.

[0099] The display unit can provide a display method customized according to the visual settings of the user at the time of display. The display unit customizes the display content using, for example, a user setting option. The user setting option includes settings such as a color tone and a font preferred by the user. For example, the display unit can customize the display content using a color tone and a font preferred by the user. The display unit can also adjust the display content using a customization algorithm. The customization algorithm adjusts the display content based on the visual preferences of the user. For example, the display unit can adjust the layout and design according to the visual preferences of the user. Furthermore, the display unit can also customize the display content using a natural language processing technology. The natural language processing technology adjusts the display content based on the visual preferences of the user. For example, the display unit can customize the display content based on a theme selected by the user. This improves the satisfaction of the user by customizing the display method according to the visual preferences of the user.

[0100] The display unit can automatically display related additional information and links when displaying. The display unit collects related additional information using, for example, a related information collection algorithm. The related information collection algorithm efficiently collects information related to a specific keyword. For example, the display unit can display additional information related to the keyword so that the user can check the details. The display unit can also automatically display related links using a link generation technology. The link generation technology generates and displays links related to a specific keyword. For example, the display unit can display links related to the keyword so that the user can access the related information. Furthermore, the display unit can also display related additional information and links using a natural language processing technology. The natural language processing technology analyzes text data and displays related information and links. For example, the display unit can display videos and images related to the keyword so that the user can visually understand. This makes it easier for the user to access detailed information by displaying related additional information and links.

[0101] The display unit can estimate the user's emotion and determine the priority of the display contents based on the estimated user's emotion. The display unit estimates the user's emotion using, for example, a machine learning algorithm. The machine learning algorithm analyzes data such as the user's facial expression and voice to estimate the emotion. For example, the display unit can display important information preferentially when the user is nervous. Also, the display unit can display the entire information evenly when the user is relaxed. Furthermore, the display unit can display information with a focus on the main points preferentially when the user is in a hurry. As a result, important information can be displayed preferentially by determining the priority of the display contents 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.

[0102] The display unit can select an appropriate display method based on the device information of the user at the time of display. The display unit detects the device information of the user using, for example, a device detection algorithm. The device detection algorithm identifies the type and characteristics of the device used by the user. For example, when the user is using a smartphone, the display unit can provide a display method that matches the screen size. The display unit can also adjust the display method based on the device information of the user using responsive design. The responsive design optimizes the display content according to the screen size and resolution of the device. For example, when the user is using a tablet, the display unit can provide a display method optimized for a large screen. Furthermore, the display unit can also select a display method based on the device information of the user using natural language processing technology. The natural language processing technology analyzes the device information of the user and provides the optimal display method. For example, when the user is using a smart watch, the display unit can provide a simple and highly visible display method. This makes it possible to provide the optimal display method by taking into account the device information of the user.

[0103] The display unit can customize the display contents by referring to the user's past browsing history when displaying. The display unit, for example, refers to the user's past browsing history using a browsing history database. The browsing history database includes information that the user has browsed in the past. For example, the display unit can refer to the user's past browsing history and preferentially display related information. The display unit can also refer to the user's past browsing history using a history reference algorithm. The history reference algorithm analyzes past browsing data and identifies related information. For example, the display unit can display related information based on keywords that the user has browsed in the past. Furthermore, the display unit can also refer to the user's past browsing history using natural language processing technology. The natural language processing technology analyzes past browsing data and identifies related information. For example, the display unit can analyze the user's past browsing history and provide optimal display content. As a result, information that is highly relevant to the user can be displayed by referring to the past browsing history.

[0104] The accuracy improvement unit can estimate the user's emotion and select data for accuracy improvement based on the estimated user's emotion. The accuracy improvement unit estimates the user's emotion using, for example, a machine learning algorithm. The machine learning algorithm analyzes data such as the user's facial expression and voice to estimate the emotion. For example, the accuracy improvement unit can preferentially select important data when the user is nervous. Also, the accuracy improvement unit can select all data evenly when the user is relaxed. Furthermore, the accuracy improvement unit can preferentially select data that can be used quickly when the user is in a hurry. In this way, accuracy improvement can be effectively performed by selecting data for accuracy improvement 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.

[0105] The accuracy improvement unit can optimize the algorithm by referring to past recognition data when improving the accuracy. The accuracy improvement unit, for example, refers to past recognition data using a recognition database. The recognition database includes data that has been recognized in the past. For example, the accuracy improvement unit can optimize the algorithm by referring to past voice recognition data. The accuracy improvement unit can also refer to past recognition data using a history reference algorithm. The history reference algorithm analyzes past recognition data and optimizes the algorithm. For example, the accuracy improvement unit can optimize the algorithm by referring to past keyword extraction data. Furthermore, the accuracy improvement unit can also refer to past recognition data using natural language processing technology. The natural language processing technology analyzes past recognition data and optimizes the algorithm. For example, the accuracy improvement unit can optimize the algorithm by referring to past analysis data. This makes it possible to optimize the algorithm by referring to past recognition data.

[0106] The accuracy improvement unit can estimate the user's emotion and adjust the frequency of accuracy improvement based on the estimated user's emotion. The accuracy improvement unit estimates the user's emotion using, for example, a machine learning algorithm. The machine learning algorithm analyzes data such as the user's facial expression and voice to estimate the emotion. For example, the accuracy improvement unit can frequently improve the accuracy when the user is nervous. Also, the accuracy improvement unit can improve the accuracy at a normal frequency when the user is relaxed. Furthermore, the accuracy improvement unit can quickly improve the accuracy when the user is in a hurry. This allows effective accuracy improvement by adjusting the frequency of accuracy improvement 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.

[0107] The accuracy improvement unit can select optimal data by considering the environmental conditions of the voice recognition when improving the accuracy. The accuracy improvement unit, for example, uses an environmental sound database to consider the environmental conditions of the voice recognition. The environmental sound database includes voice data related to specific environmental conditions. For example, the accuracy improvement unit can select optimal data by considering the environmental conditions of a presentation venue. The accuracy improvement unit can also consider the environmental conditions of the voice recognition by using an environmental condition detection algorithm. The environmental condition detection algorithm detects specific environmental conditions and selects optimal data. For example, the accuracy improvement unit can consider the environmental conditions of a study group and select optimal data. Furthermore, the accuracy improvement unit can consider the environmental conditions of the voice recognition by using natural language processing technology. The natural language processing technology analyzes the environmental conditions and selects optimal data. For example, the accuracy improvement unit can consider the environmental conditions of a lecture and select optimal data. As a result, optimal data can be selected by considering the environmental conditions of the voice recognition, and accuracy improvement can be effectively performed.

[0108] The providing unit can estimate the user's emotion using a machine learning algorithm and adjust the format of the information to be provided based on the estimated emotion of the user. The providing unit, for example, estimates the user's emotion using a machine learning algorithm. The machine learning algorithm analyzes data such as the user's facial expression and voice to estimate the emotion. For example, the providing unit can provide information in a simple and highly visible format when the user is nervous. Also, the providing unit can provide information in a format including detailed information when the user is relaxed. Furthermore, the providing unit can provide information in a format that focuses on the main points when the user is in a hurry. Thereby, the visibility is improved by adjusting the format of the information according to the emotion of the user. 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.

[0109] The providing unit can provide optimal information by referring to the user's past usage history at the time of providing. The providing unit, for example, uses a usage history database to refer to the user's past usage history. The usage history database includes information used by the user in the past. For example, the providing unit can refer to the user's past usage history and provide related information. The providing unit can also refer to the user's past usage history using a history reference algorithm. The history reference algorithm analyzes past usage data and identifies related information. For example, the providing unit can provide related information based on keywords used by the user in the past. Furthermore, the providing unit can also refer to the user's past usage history using natural language processing technology. The natural language processing technology analyzes past usage data and identifies related information. For example, the providing unit can analyze the user's past usage history and provide optimal information. As a result, information highly relevant to the user can be provided by referring to the past usage history.

[0110] The providing unit can estimate the user's emotion and determine the priority of information to be provided based on the estimated user's emotion. The providing unit, for example, uses a machine learning algorithm to estimate the user's emotion. The machine learning algorithm analyzes data such as the user's facial expression and voice to estimate the emotion. For example, the providing unit can provide important information preferentially when the user is nervous. Furthermore, the providing unit can provide the entire information evenly when the user is relaxed. Furthermore, the providing unit can provide information with a focus on the main points preferentially when the user is in a hurry. As a result, important information can be provided preferentially by determining the priority of information 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.

[0111] The providing unit can select an appropriate information providing method based on the device information of the user at the time of providing. The providing unit detects the device information of the user using, for example, a device detection algorithm. The device detection algorithm identifies the type and characteristics of the device used by the user. For example, when the user is using a smartphone, the providing unit can provide an information providing method that matches the screen size. The providing unit can also adjust the information providing method based on the device information of the user using responsive design. The responsive design optimizes the information content according to the screen size and resolution of the device. For example, when the user is using a tablet, the providing unit can provide an information providing method that is optimized for a large screen. Furthermore, the providing unit can also select the information providing method based on the device information of the user using natural language processing technology. The natural language processing technology analyzes the device information of the user and provides the optimal information providing method. For example, when the user is using a smart watch, the providing unit can provide a concise and highly visible information providing method. This makes it possible to provide the optimal information providing method by taking into account the device information of the user.

[0112] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0113] The terminology understanding support system can refer to the user's learning history and provide the meaning of keywords based on what the user has learned in the past. For example, the content that the user has learned in the past is stored in a database, and the analysis unit can refer to the database to provide the meaning of new keywords taking into account what the user already understands. In addition, based on the learning history, it can also prioritize the display of related keywords and topics. Furthermore, based on the learning history, it can also focus on analyzing keywords related to areas that the user had difficulty in the past and provide detailed explanations. In this way, more effective learning support can be provided by utilizing the user's learning history.

[0114] The terminology understanding support system can monitor the user's current learning progress in real time and provide the meanings of keywords according to that progress. For example, if a user is studying a particular topic, it can preferentially analyze and display keywords related to that topic. It can also provide explanations of different levels of difficulty according to the user's learning progress. For example, it can provide basic explanations to beginners and detailed technical explanations to advanced users. It can also suggest keywords and topics that the user should study next based on the user's learning progress. This makes it possible to provide flexible support according to the user's learning progress.

[0115] The terminology understanding support system can provide the meaning of keywords according to the user's learning style. For example, explanations using diagrams and graphs can be provided to visual learners, and explanations using audio and video can be provided to auditory learners. In addition, a function for checking the meaning of keywords in the form of a quiz can be provided to users who prefer interactive learning. Furthermore, the system can suggest the most suitable learning method based on the user's learning style. For example, visual notes can be suggested to visual learners, and podcasts can be suggested to auditory learners. This makes it possible to provide effective support according to the user's learning style.

[0116] The terminology understanding support system can provide the meaning of keywords according to the user's learning goals. For example, for a user studying for a specific exam, it can prioritize the analysis and display of keywords related to that exam. It can also provide the latest industry trends and technical terms to users who are aiming to advance their careers. It can also suggest specific steps and study plans that the user should achieve based on their learning goals. This makes it possible to provide effective support according to the user's learning goals.

[0117] The terminology understanding support system can provide the meaning of keywords according to the user's learning environment. For example, it can provide detailed text explanations to users who are learning in a quiet environment, and explanations using audio or video to users who are learning in a noisy environment. It can also provide summaries that can be understood in a short time to users who are on the move. It can also suggest optimal learning tools and resources based on the learning environment. This makes it possible to provide flexible support according to the user's learning environment.

[0118] The terminology understanding support system can estimate the user's emotions and provide the meaning of keywords based on the estimated emotions. For example, if the user is excited, a detailed explanation can be provided to keep the user interested. If the user is tired, a concise explanation that gets to the point can be provided. Furthermore, if the user is anxious, an explanation can be provided in a gentle tone that gives a sense of security. This makes it possible to provide flexible support according to the user's emotions.

[0119] The terminology understanding support system can estimate the user's emotions and adjust the order in which the meanings of keywords are presented based on the estimated emotions. For example, if the user is nervous, important keywords can be provided preferentially, and if the user is relaxed, they can be provided in an order that follows the overall flow. Also, if the user is in a hurry, keywords that capture the main points can be provided preferentially. Furthermore, if the user is excited, related keywords can be provided one after another to increase the user's motivation to learn. This makes it possible to provide flexible support according to the user's emotions.

[0120] The terminology understanding support system can estimate the user's emotions and adjust the format of providing the meaning of keywords based on the estimated emotions. For example, if the user is relaxed, a detailed text explanation can be provided, and if the user is nervous, a concise visual explanation can be provided. If the user is excited, an explanation can be provided in an interactive format. Furthermore, if the user is tired, an explanation using audio and video can be provided. This enables flexible support according to the user's emotions.

[0121] The terminology understanding support system can estimate the user's emotions and adjust the timing of providing keyword meanings based on the estimated emotions. For example, when the user is concentrating, the meanings of keywords can be provided in real time, and when the user is tired, they can be provided after a break. Also, when the user is tense, important keywords can be provided early, and when the user is relaxed, they can be provided at a timing that matches the overall flow. Furthermore, when the user is excited, related keywords can be provided one after another to increase the user's motivation to learn. This enables flexible support according to the user's emotions.

[0122] The terminology understanding support system can estimate the user's emotions and adjust the way it provides keyword meanings based on the estimated emotions. For example, if the user is relaxed, a detailed text explanation can be provided, and if the user is nervous, a concise visual explanation can be provided. If the user is excited, an explanation can be provided in an interactive format. Furthermore, if the user is tired, an explanation using audio and video can be provided. This allows for flexible support according to the user's emotions.

[0123] The process flow of the second embodiment will be briefly described below.

[0124] Step 1: The speech recognition unit converts speech to text. The speech recognition unit can convert speech to text using, for example, a speech recognition algorithm, speech recognition software, or a speech recognition device. Step 2: The extraction unit extracts keywords from the text converted by the speech recognition unit. The extraction unit can extract keywords using, for example, frequency analysis, natural language processing techniques, or keyword extraction algorithms. Step 3: The analysis unit analyzes the meaning of the keywords extracted by the extraction unit. The analysis unit can analyze the meaning of the keywords using, for example, a generation AI, a semantic analysis algorithm, or a dictionary database. Step 4: The display unit displays the results analyzed by the analysis unit. The display unit can display the analysis results using, for example, a text display, a graphical display, or a smartphone screen.

[0125] 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.

[0126] 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 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.

[0127] 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.

[0128] Each of the multiple elements including the above-mentioned voice recognition unit, extraction unit, analysis unit, display unit, and provision unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the voice recognition unit acquires voice using the microphone 38B of the smart device 14, and converts the voice into text by the control unit 46A. The extraction unit extracts keywords from the text, for example, by the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the meaning of the keyword using a generation AI, for example, by the specific processing unit 290 of the data processing device 12. The display unit displays the analysis result using the display 40A of the smart device 14. The provision unit provides the analysis result to the user, for example, by the control unit 46A of the smart device 14. The parts for improving the accuracy of voice recognition are realized, for example, by using the noise canceling technology of the smart device 14. The emotion estimation function is realized, for example, by the specific processing unit 290 of the data processing device 12, and adjusts the parameters of the voice recognition based on the emotion of the user. The correspondence relationship between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0129] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] Each of the multiple elements including the above-mentioned voice recognition unit, extraction unit, analysis unit, display unit, and provision unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the voice recognition unit acquires voice using the microphone 238 of the smart glasses 214, and converts the voice into text by the control unit 46A. The extraction unit extracts keywords from the text, for example, by the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the meaning of the keyword using a generation AI, for example, by the specific processing unit 290 of the data processing device 12. The display unit displays the analysis result using the display of the smart glasses 214. The provision unit provides the analysis result to the user, for example, by the control unit 46A of the smart glasses 214. The components for improving the accuracy of voice recognition are realized, for example, by using the noise canceling technology of the smart glasses 214. The emotion estimation function is realized, for example, by the specific processing unit 290 of the data processing device 12, and adjusts the parameters of voice recognition based on the user's emotion. The correspondence between each part and the device or control part is not limited to the above-mentioned example, and various modifications are possible.

[0145] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] Each of the multiple elements including the above-mentioned voice recognition unit, extraction unit, analysis unit, display unit, and provision unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the voice recognition unit acquires voice using the microphone 238 of the headset type terminal 314, and converts the voice into text by the control unit 46A. The extraction unit extracts keywords from the text, for example, by the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the meaning of the keyword using a generation AI by the specific processing unit 290 of the data processing device 12. The display unit displays the analysis result using the display 343 of the headset type terminal 314. The provision unit provides the analysis result to the user, for example, by the control unit 46A of the headset type terminal 314. The parts for improving the accuracy of voice recognition are realized, for example, by using the noise canceling technology of the headset type terminal 314. The emotion estimation function is realized, for example, by the specific processing unit 290 of the data processing device 12, and adjusts the parameters of the voice recognition based on the emotion of the user. The correspondence between each part and the device or control part is not limited to the above-mentioned example, and various modifications are possible.

[0161] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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).

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] Each of the multiple elements including the above-mentioned voice recognition unit, extraction unit, analysis unit, display unit, and provision unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the voice recognition unit acquires voice using the microphone 238 of the robot 414, and converts the voice into text by the control unit 46A. The extraction unit extracts keywords from the text, for example, by the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the meaning of the keyword using a generation AI, for example, by the specific processing unit 290 of the data processing device 12. The display unit displays the analysis result using the display of the robot 414. The provision unit provides the analysis result to the user, for example, by the control unit 46A of the robot 414. The parts for improving the accuracy of the voice recognition are realized, for example, by using the noise canceling technology of the robot 414. The emotion estimation function is realized, for example, by the specific processing unit 290 of the data processing device 12, and adjusts the parameters of the voice recognition based on the emotion of the user. The correspondence relationship between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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).

[0182] 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.

[0183] 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."

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] (Appendix 1) a speech recognition unit that converts speech into text; an extraction unit that extracts keywords from the text converted by the speech recognition unit; an analysis unit that analyzes the meaning of the keyword extracted by the extraction unit; A display unit that displays the results of the analysis by the analysis unit. A system characterized by: (Appendix 2) Equipped with components to improve the accuracy of voice recognition 2. The system of claim 1, (Appendix 3) Equipped with a provision section that provides the analysis results of the generative AI to users 2. The system of claim 1, (Appendix 4) The voice recognition unit Instantly convert speech to text 2. The system of claim 1, (Appendix 5) The extraction unit is Quickly extract keywords from text 2. The system of claim 1, (Appendix 6) The analysis unit is Analyzing keyword meanings using generative AI 2. The system of claim 1, (Appendix 7) The display unit is Display analysis results on your smartphone screen 2. The system of claim 1, (Appendix 8) The voice recognition unit The user's emotions are estimated using a machine learning algorithm, and the voice recognition parameters are adjusted based on the estimated user's emotions. 2. The system of claim 1, (Appendix 9) The voice recognition unit Automatically filter background noise during speech recognition 2. The system of claim 1, (Appendix 10) The voice recognition unit Learns the characteristics of a speaker's voice and uses individually tuned recognition models during speech recognition 2. The system of claim 1, (Appendix 11) The voice recognition unit Estimating a user's emotion and determining a priority of speech recognition based on the estimated user's emotion 2. The system of claim 1, (Appendix 12) The voice recognition unit Improve speech recognition accuracy by taking into account the speaker's geographical accent and dialect 2. The system of claim 1, (Appendix 13) The voice recognition unit Improve speech recognition accuracy by referring to the speaker's past utterance history during speech recognition 2. The system of claim 1, (Appendix 14) The extraction unit is Infer user sentiment and adjust keyword extraction algorithms based on the estimated user sentiment 2. The system of claim 1, (Appendix 15) The extraction unit is When extracting keywords, prioritize extraction of important keywords based on context information 2. The system of claim 1, (Appendix 16) The extraction unit is Automatically identify and extract synonyms and related terms during keyword extraction 2. The system of claim 1, (Appendix 17) The extraction unit is Estimate user sentiment and prioritize keywords to be extracted based on the estimated user sentiment. 2. The system of claim 1, (Appendix 18) The extraction unit is Applying specific extraction algorithms during keyword extraction depending on the genre or category of the text 2. The system of claim 1, (Appendix 19) The extraction unit is Improve extraction accuracy by referring to past extraction history when extracting keywords 2. The system of claim 1, (Appendix 20) The analysis unit is Infer user emotions and adjust the presentation of analysis results based on the inferred user emotions 2. The system of claim 1, (Appendix 21) The analysis unit is During analysis, keyword-related data is automatically collected to improve analysis accuracy. 2. The system of claim 1, (Appendix 22) The analysis unit is During analysis, prioritize analysis based on keyword frequency and importance 2. The system of claim 1, (Appendix 23) The analysis unit is Infer user emotions and adjust the display order of analysis results based on the estimated user emotions 2. The system of claim 1, (Appendix 24) The analysis unit is During analysis, refer to related materials and databases for keywords to improve analysis accuracy. 2. The system of claim 1, (Appendix 25) The analysis unit is When analyzing, take into account the historical background and development history of the keywords. 2. The system of claim 1, (Appendix 26) The display unit is Inferring user emotion and adjusting the format of the displayed content based on the estimated user emotion 2. The system of claim 1, (Appendix 27) The display unit is When displayed, it provides a customized display based on the user's visual preferences. 2. The system of claim 1, (Appendix 28) The display unit is Automatically display additional related information and links when viewed 2. The system of claim 1, (Appendix 29) The display unit is Estimate the user's emotions and prioritize the content to be displayed based on the estimated user's emotions. 2. The system of claim 1, (Appendix 30) The display unit is When displaying, select the appropriate display method based on the user's device information 2. The system of claim 1, (Appendix 31) The display unit is When displaying, customize the display content by referring to the user's past browsing history. 2. The system of claim 1, (Appendix 32) The accuracy improvement unit is The user's emotions are estimated, and data for improving accuracy is selected based on the estimated user's emotions. 3. The system of claim 2, (Appendix 33) The accuracy improvement unit is When improving accuracy, the algorithm is adjusted by referring to past recognition data. 3. The system of claim 2, (Appendix 34) The accuracy improvement unit is Estimate the user's emotions and adjust the frequency of accuracy improvements based on the estimated user's emotions. 3. The system of claim 2, (Appendix 35) The accuracy improvement unit is When improving accuracy, select the most suitable data taking into account the environmental conditions of voice recognition. 3. The system of claim 2, (Appendix 36) The providing unit is The user's emotions are estimated using a machine learning algorithm, and the format of information provided is adjusted based on the estimated user's emotions. 4. The system of claim 3. (Appendix 37) The providing unit is When providing information, the most appropriate information is provided by referring to the user's past usage history. 4. The system of claim 3. (Appendix 38) The providing unit is Estimate the user's emotions and prioritize the information to be provided based on the estimated user's emotions. 4. The system of claim 3. (Appendix 39) The providing unit is When providing information, the appropriate information provision method is selected based on the user's device information. 4. The system of claim 3. [Explanation of symbols]

[0197] 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 speech recognition unit that converts speech into text; an extraction unit that extracts keywords from the text converted by the speech recognition unit; an analysis unit that analyzes the meaning of the keyword extracted by the extraction unit; A display unit that displays the results of the analysis by the analysis unit. A system characterized by:

2. Equipped with components to improve the accuracy of voice recognition 2. The system of claim 1 .

3. Equipped with a providing unit that provides the analysis results of the generation AI to the user 2. The system of claim 1 .

4. The voice recognition unit Instantly convert speech to text 2. The system of claim 1 .

5. The extraction unit is Quickly extract keywords from text 2. The system of claim 1 .

6. The analysis unit is Analyzing the meaning of keywords using generative AI 2. The system of claim 1 .

7. The display unit is Display analysis results on your smartphone screen 2. The system of claim 1 .

8. The voice recognition unit The user's emotions are estimated using a machine learning algorithm, and the voice recognition parameters are adjusted based on the estimated user's emotions.

2. The system of claim 1 .

9. The voice recognition unit Automatically filter background noise during speech recognition 2. The system of claim 1 .

Images