system

Abstract

The system according to this embodiment aims to understand the content of conversations in a specialized field and suggest appropriate questions. [Solution] The system according to the embodiment comprises a recording unit, a text conversion unit, an analysis unit, a judgment unit, and a proposal unit. The recording unit records the conversation. The text conversion unit converts the conversation recorded by the recording unit into text. The analysis unit analyzes the conversation converted into text by the text conversion unit. The judgment unit determines the validity of the statements in the conversation analyzed by the analysis unit. The proposal unit proposes questions based on the results determined by the judgment unit.

Description

Technical Field

[0006] , , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot; 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to understand the content of conversations in a specialized field and propose appropriate questions.

[0005] The system according to the embodiment aims to understand the content of conversations in a specialized field and propose appropriate questions.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a recording unit, a text conversion unit, an analysis unit, a judgment unit, and a proposal unit. The recording unit records the conversation. The text conversion unit converts the conversation recorded by the recording unit into text. The analysis unit analyzes the conversation converted into text by the text conversion unit. The judgment unit determines the validity of the statements in the conversation analyzed by the analysis unit. The proposal unit proposes questions based on the results determined by the judgment unit. [Effects of the Invention]

[0007] The system according to this embodiment can understand the content of a conversation in a specialized field and suggest appropriate questions. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 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". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

[0025] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The support system according to an embodiment of the present invention is a system that records, transcribes, analyzes, judges the validity of statements made, and suggests questions. The support system records, transcribes, and analyzes conversations with experts in a particular field to judge the validity of statements and suggests multiple questions based on the content of the conversation. For example, in conversations with a child's tutor or a doctor at a hospital, when technical terms are used or difficult judgments are required, having the support system by your side can provide great reassurance. Specifically, the support system operates in the following steps. First, it records and transcribes the conversation in real time. Next, it analyzes the transcribed conversation to judge the validity of statements. For example, if a tutor says, "This teaching material is very effective," the support system will verify the basis of that statement and, if necessary, suggest questions such as, "Do you have any data that shows the effectiveness of this teaching material?" The support system also suggests multiple questions based on the content of the conversation. For example, if a doctor at a hospital says, "This medicine has few side effects," the support system will suggest questions such as, "What other side effects are possible?" or "How long does it take for the effects of this medicine to appear?" Furthermore, the support system utilizes natural language processing to record and analyze each statement. It analyzes the recorded conversation and verifies the accuracy of key phrases. If inaccurate information or errors are present, it automatically detects them and makes appropriate statements at a time that does not disrupt the flow of the conversation. In addition, information regarding the child's academic performance and preferences is recorded and managed in a database via AI and used as needed. In this way, the support system assists conversations with experts in their respective fields, helping users make appropriate choices. For example, if it is difficult to decide what choices to make regarding a child's learning, the support system intervenes in conversations with school or tutors to support the decision. This allows users to appropriately grasp points that need to be confirmed and important information within the conversation. Thus, the support system can assist conversations with experts in their respective fields, helping users make appropriate choices.

[0029] The support system according to the embodiment comprises a recording unit, a text conversion unit, an analysis unit, a decision unit, and a proposal unit. The recording unit records conversations. The recording unit can record conversations by methods such as audio recording, video recording, and text recording. For example, the recording unit records conversations using audio recording. The recording unit can also record conversations as video using video recording. The recording unit can also record conversations as text information using text recording. For example, the recording unit records conversations using audio recording, and then analyzes the audio data to convert it into text data. The text conversion unit converts the conversations recorded by the recording unit into text. For example, the text conversion unit converts audio data into text data using speech recognition technology. The text conversion unit can also convert conversations into text using manual input. For example, the text conversion unit converts audio data into text data in real time using speech recognition technology. The text conversion unit can also convert conversations into text using manual input for later review. The analysis unit analyzes the conversations converted into text by the text conversion unit. The analysis unit analyzes the content of the conversation using, for example, natural language processing technology. The analysis unit can also extract important information from the conversation using keyword extraction technology. For example, the analysis unit analyzes the grammatical and semantic accuracy of the conversation using natural language processing technology. Furthermore, the analysis unit can pick out particularly important information from the conversation using keyword extraction technology. The judgment unit determines the validity of the statements in the conversation analyzed by the analysis unit. The judgment unit determines the validity of the statements based, for example, fact-checking and logical consistency. Furthermore, the judgment unit can verify the basis of the statements and provide additional information as needed. For example, the judgment unit performs fact-checking to confirm the accuracy of the statements. Furthermore, the judgment unit can determine the validity of the statements based on logical consistency and provide additional information as needed. The proposal unit proposes questions based on the results determined by the judgment unit. For example, the proposal unit proposes multiple questions based on the content of the conversation. Furthermore, the proposal unit can propose questions based on the user's interests. For example, the proposal unit proposes a question such as, "Is there any data demonstrating the effectiveness of this material?" based on the content of the conversation.Furthermore, the proposal function can also suggest questions based on the user's interests, such as "What other side effects might be possible?". This allows the support system according to the embodiment to facilitate conversations with experts in specific fields and assist users in making appropriate choices.

[0030] The recording unit records conversations. The recording unit can record conversations using methods such as audio recording, video recording, and text recording. For example, the recording unit can record conversations using audio recording. It can also record conversations as video using video recording. Furthermore, it can record conversations as text information using text recording. For example, the recording unit can record conversations using audio recording, and then analyze the audio data to convert it into text data. The recording unit is recommended to use high-quality microphones and cameras to accurately record the content of conversations. For audio recording, noise cancellation technology can be used to remove background noise and obtain clear audio data. For video recording, wide-angle lenses and high-resolution cameras can be used to capture the overall picture of the conversation. For text recording, keyboards or tablets that allow real-time input can be used to record conversation content quickly and accurately. The recording unit centrally manages this data and can collaborate with other departments and systems as needed. For example, recorded data can be stored in cloud storage and made accessible to the analysis and text conversion units. Furthermore, by optimizing data storage formats and compression methods, efficient data management becomes possible. This allows the recording unit to record conversations in a variety of ways, improving the overall system performance.

[0031] The text conversion unit converts conversations recorded by the recording unit into text. The text conversion unit can convert audio data into text data using, for example, speech recognition technology. The text conversion unit can also convert conversations into text using manual input. For example, the text conversion unit can convert audio data into text data in real time using speech recognition technology. Alternatively, the text conversion unit can convert conversations into text using manual input for later review. Speech recognition technology uses a deep learning model to analyze the features of audio data with high accuracy and convert them into text data. Specifically, it divides the audio data into short frames and identifies phonemes for each frame. This allows for accurate transcription of audio data into text. In the case of manual input, a professional operator can input the conversation content in real time and later review and correct it. The text conversion unit centrally manages this text data, making it accessible to the analysis and judgment units. Furthermore, by optimizing the format and tagging of the text data, subsequent analysis and judgment become easier. For example, tagging the speaker and time of speaking in a conversation allows for quick searching of specific statements. This allows the text conversion unit to efficiently and accurately transcribe conversations into text, improving the overall performance of the system.

[0032] The analysis unit analyzes the conversation that has been transcribed by the text conversion unit. The analysis unit analyzes the content of the conversation using, for example, natural language processing techniques. It can also extract important information from the conversation using keyword extraction techniques. For example, the analysis unit analyzes the grammatical and semantic accuracy of the conversation using natural language processing techniques. Furthermore, it can pick out particularly important information from the conversation using keyword extraction techniques. Natural language processing techniques include morphological analysis, syntactic analysis, and semantic analysis, which are combined to analyze the content of the conversation in detail. Morphological analysis divides the text into words and identifies the part of speech of each word. Syntactic analysis analyzes the structure of sentences and clarifies relationships such as subject, predicate, and object. Semantic analysis understands the meaning of sentences and provides appropriate interpretations based on context. Keyword extraction techniques automatically extract important words and phrases from the text to grasp the main points of the conversation. This allows the analysis unit to quickly and accurately analyze the content of the conversation and extract important information. Furthermore, the analysis unit can also utilize historical data and statistical information to analyze long-term trends and patterns. For example, by using past conversation data, it is possible to identify trends related to specific themes or topics and make future predictions. This allows the analysis unit to handle not only real-time analysis but also long-term analysis, improving the reliability and usefulness of the entire system.

[0033] The judgment unit determines the validity of statements in a conversation analyzed by the analysis unit. The judgment unit determines the validity of statements based, for example, on fact-checking and logical consistency. The judgment unit can also verify the basis of statements and provide additional information as needed. For example, the judgment unit performs fact-checking to confirm the accuracy of statements. Furthermore, the judgment unit can determine the validity of statements based on logical consistency and provide additional information as needed. The judgment unit automatically evaluates the validity of statements using AI. Specifically, the AI ​​performs fact-checking by comparing the content of statements with predefined rules and databases. For example, it checks whether statements are based on specific data or statistics and evaluates their accuracy. The AI ​​also evaluates the logical consistency of statements, checking for contradictions or errors. This allows the judgment unit to quickly and accurately determine the validity of statements. Furthermore, the judgment unit can collect feedback from users and continuously improve the accuracy and reliability of its judgments. For example, it can update the AI's evaluation model based on additional information and corrections provided by users to make more accurate judgments. The judgment unit can also integrate multiple information sources to perform a more comprehensive evaluation. This allows the decision-making unit to evaluate the validity of statements with high accuracy and provide users with reliable information.

[0034] The suggestion unit proposes questions based on the results determined by the judgment unit. For example, the suggestion unit proposes multiple questions based on the content of the conversation. It can also propose questions based on the user's interests. For example, based on the content of the conversation, the suggestion unit may propose a question such as, "Is there any data showing the effectiveness of this material?" It can also propose a question such as, "What other side effects are possible?" based on the user's interests. The suggestion unit uses AI to analyze the user's interests and the context of the conversation and automatically generates appropriate questions. Specifically, the AI ​​analyzes the content of the conversation and identifies relevant topics and themes. Next, it generates the most appropriate questions based on the user's past behavior and interests. For example, if the user has shown interest in a particular theme in the past, it will propose questions related to that theme. The suggestion unit can also collect user feedback and continuously improve the accuracy and usefulness of its suggestions. For example, it can record how the user reacted to the suggested questions and update the AI ​​model based on that data. This allows the suggestion unit to always propose the best questions to the user and improve the quality of the conversation. Furthermore, the proposal department enables more interactive conversations by simultaneously proposing multiple questions and allowing the user to select from them. This allows the proposal department to suggest questions that match the user's interests and needs, facilitating a smooth conversation.

[0035] The analysis unit can verify the accuracy of key phrases in a conversation. For example, the analysis unit extracts key phrases based on frequently occurring words and important phrases. For example, the analysis unit extracts words that frequently appear in a conversation as key phrases. The analysis unit can also extract important phrases as key phrases based on the context of the conversation. The analysis unit verifies the accuracy of key phrases based on grammatical and semantic accuracy. For example, the analysis unit checks whether the grammatical correctness is correct and determines the accuracy of the key phrase. The analysis unit can also check whether the semantic correctness is correct and determine the accuracy of the key phrase. This improves the accuracy of the analysis by verifying the accuracy of key phrases in a conversation. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the conversation text data into a generating AI and have the generating AI perform key phrase extraction and accuracy verification.

[0036] The suggestion unit can suggest multiple questions based on the content of the conversation. For example, the suggestion unit can analyze the content of the conversation and suggest relevant questions. For example, the suggestion unit can suggest a question such as, "Is there any data showing the effectiveness of this material?" based on the content of the conversation. The suggestion unit can also suggest a question such as, "What other side effects are possible?" based on the content of the conversation. The suggestion unit can suggest open-ended and closed-ended questions, for example. For example, the suggestion unit can suggest an open-ended question based on the content of the conversation. The suggestion unit can also suggest a closed-ended question based on the content of the conversation. By suggesting multiple questions based on the content of the conversation, it helps the user to ask appropriate questions. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or not using AI. For example, the suggestion unit can input the text data of the conversation into a generating AI and have the generating AI suggest questions.

[0037] The recording unit can record conversations in real time. For example, the recording unit can record conversations in real time using voice recording. For example, the recording unit can start recording at the same time as the conversation begins and stop recording at the same time as the conversation ends. The recording unit can also record conversations as video in real time using video recording. For example, the recording unit can start video recording at the same time as the conversation begins and stop video recording at the same time as the conversation ends. The recording unit can also record conversations as text information in real time using text recording. For example, the recording unit can transcribe the content of the conversation into text in real time and record it. This allows for accurate recording by recording conversations in real time. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input the audio data of the conversation into a generating AI and have the generating AI perform real-time audio recording.

[0038] The text conversion unit can convert recorded conversations into text. The text conversion unit can convert audio data into text data using, for example, speech recognition technology. The text conversion unit can convert audio data into text data in real time using, for example, speech recognition technology. The text conversion unit can also convert conversations into text using manual input. The text conversion unit can also convert conversations into text using, for example, manual input and review them later. This makes it easier to refer to recorded conversations later by converting them into text. Some or all of the above-described processes in the text conversion unit may be performed using, for example, AI, or without AI. For example, the text conversion unit can input audio data into a generating AI and have the generating AI perform the conversion to text data.

[0039] The judgment unit can determine the validity of a statement. The judgment unit determines the validity of a statement based, for example, on fact-checking and logical consistency. The judgment unit, for example, performs fact-checking to confirm the accuracy of the statement. The judgment unit can also determine the validity of a statement based on logical consistency and provide additional information as needed. This makes it possible to provide accurate information by determining the validity of a statement. Some or all of the above processing in the judgment unit may be performed using, for example, AI, or without AI. For example, the judgment unit can input the text data of the conversation into a generating AI and have the generating AI perform the judgment on the validity of the statement.

[0040] The suggestion unit can make statements at times that do not disrupt the flow of conversation. For example, the suggestion unit can make statements at appropriate times based on the interval between statements and natural pauses in the conversation. For example, the suggestion unit can analyze the flow of conversation and make statements at appropriate times. The suggestion unit can also make statements based on natural pauses in the conversation. This enables smooth conversation by making appropriate statements at times that do not disrupt the flow of conversation. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input conversation text data into a generating AI and have the generating AI execute the timing of statements.

[0041] A management department is provided, which records and manages information about children's academic performance and intentions in a database, and can use it as needed. For example, the management department records children's test scores and assignment evaluations in the database. For example, the management department records children's test scores in the database and can refer to them later. The management department can also record children's assignment evaluations in the database and use them as needed. For example, the management department records children's aspirations for higher education and careers in the database. For example, the management department can record children's aspirations for higher education in the database and use it to select schools. The management department can also record children's career aspirations in the database and use it for future career guidance. In this way, information about children's academic performance and intentions is recorded and managed in a database and can be used as needed. Some or all of the above processing in the management department may be performed using AI, for example, or not using AI. For example, the management department can input information about children's academic performance and intentions into a generating AI and have the generating AI perform the recording and management in the database.

[0042] The recording unit can remove background noise and other unwanted sounds when recording conversations. For example, the recording unit can analyze background noise during a conversation in real time and remove the noise. For example, the recording unit can analyze background noise during a conversation in real time and apply a noise reduction algorithm to remove the noise. The recording unit can also filter out noise in specific frequency bands when recording conversations. For example, the recording unit can filter out noise in specific frequency bands when recording conversations to record clear audio. The recording unit can also remove background noise after recording a conversation by applying a noise reduction algorithm. For example, the recording unit can remove background noise after recording a conversation by applying a noise reduction algorithm to provide clear audio. This makes it possible to record conversations clearly by removing background noise and other unwanted sounds. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input conversation audio data into a generating AI and have the generating AI perform noise reduction.

[0043] The recording unit can automatically highlight specific keywords when they appear during conversation recording. For example, the recording unit can automatically highlight keywords such as "important" or "confirm" when they appear in a conversation, making them easier to review later. The recording unit can also search for and highlight specific keywords after the conversation has been recorded, ensuring that important information is not missed. The recording unit can also automatically highlight custom keywords set by the user when they appear in a conversation, ensuring that important information is not missed. This ensures that important information is not missed by highlighting specific keywords. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input the conversation text data into a generating AI and have the generating AI perform keyword highlighting.

[0044] The recording unit can prioritize recording conversations that are highly relevant based on the user's geographical location information when recording conversations. For example, if the user is in a specific location, the recording unit will prioritize recording conversations related to that location, which can then be referenced later. The recording unit can also prioritize recording conversations related to the user's destination if the user is on the move, which can then be reviewed later. Furthermore, if the user is participating in a specific event, the recording unit can prioritize recording conversations related to that event, which can then be referenced later. This allows for the prioritization of recording highly relevant conversations by considering geographical location information. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input the user's geographical location information into a generating AI and have the generating AI prioritize the recording of conversations.

[0045] The recording unit can analyze the user's social media activity and record relevant conversations when recording a conversation. For example, the recording unit can record relevant conversations based on information the user has shared on social media. The recording unit can record relevant conversations based on information the user has shared on social media and refer to them later. The recording unit can also analyze the content of the user's social media posts and record relevant conversations. The recording unit can analyze the content of the user's social media posts, record relevant conversations and refer to them later. The recording unit can also record relevant conversations based on accounts the user follows on social media. The recording unit can record relevant conversations based on accounts the user follows on social media and refer to them later. This allows for efficient recording of relevant conversations by analyzing social media activity. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input the user's social media data into a generating AI and have the generating AI record relevant conversations.

[0046] The text conversion unit can interpret technical terms and abbreviations during the text conversion process and convert them into more understandable expressions. For example, the text conversion unit can convert medical terms into more general expressions to generate easily understandable text. The text conversion unit can also convert educational terms into more understandable expressions to make conversations easier to understand. The text conversion unit can also convert technical terms into more general expressions to make conversations easier to understand. In this way, by converting technical terms and abbreviations into appropriate expressions, easily understandable text is possible. Some or all of the above-described processes in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input technical terms and abbreviations into a generating AI and have the generating AI perform the conversion into appropriate expressions.

[0047] The text conversion unit can insert punctuation marks based on the context of the conversation during the text conversion process. For example, the text conversion unit can insert appropriate punctuation marks based on the flow of the conversation. The text conversion unit can, for example, insert appropriate punctuation marks based on the flow of the conversation to generate easy-to-read text. The text conversion unit can also analyze the context and insert punctuation marks in appropriate places. For example, the text conversion unit can analyze the context and insert punctuation marks in appropriate places to clarify the content of the conversation. The text conversion unit can also consider the meaning of the conversation and insert appropriate punctuation marks. For example, the text conversion unit can consider the meaning of the conversation and insert appropriate punctuation marks to make the content of the conversation easier to understand. This makes it possible to create easy-to-read text by inserting punctuation marks while considering the context. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input the conversation text data into a generating AI and have the generating AI perform the insertion of punctuation marks.

[0048] The text conversion unit can determine the order of text conversion based on the importance of the conversations. For example, the text conversion unit can prioritize the text conversion of important conversations. For example, the text conversion unit can prioritize the text conversion of important conversations based on their importance so that they can be referenced later. The text conversion unit can also determine the order of text conversion based on the importance of the conversations. For example, the text conversion unit can analyze the importance of the conversations, determine the order of text conversion, and prioritize the recording of important conversations. The text conversion unit can also analyze the importance of the conversations and determine the priority order. For example, the text conversion unit can analyze the importance of the conversations, determine the priority order, and prioritize the text conversion of important conversations. In this way, by determining the priority order of text conversion based on the importance of the conversations, important conversations can be prioritized for text conversion. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input the conversation text data into a generating AI and have the generating AI perform the determination of the text conversion order.

[0049] The text conversion unit can determine the order of text conversion based on the relevance of the conversations. For example, the text conversion unit can prioritize the text conversion of conversations that are highly relevant. For example, the text conversion unit can prioritize the text conversion of conversations that are highly relevant based on their relevance, allowing for later reference. The text conversion unit can also determine the order of text conversion based on the relevance of the conversations. For example, the text conversion unit can analyze the relevance of the conversations, determine the order of text conversion, and prioritize the recording of conversations that are highly relevant. The text conversion unit can also analyze the relevance of the conversations and adjust the order. For example, the text conversion unit can analyze the relevance of the conversations, adjust the order, and prioritize the text conversion of conversations that are highly relevant. In this way, by adjusting the order of text conversion based on the relevance of the conversations, conversations that are highly relevant can be prioritized for text conversion. Some or all of the above-described processes in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input the conversation text data into a generating AI and have the generating AI determine the order of text conversion.

[0050] The analysis unit can improve the accuracy of its analysis based on the relationships between conversations during the analysis process. For example, the analysis unit can improve accuracy by analyzing the context of the conversation. For example, the analysis unit can improve accuracy by analyzing the context of the conversation and clarify the content of the conversation. The analysis unit can also provide analysis results while considering the relationships between conversations. For example, the analysis unit can provide analysis results while considering the relationships between conversations and analyze the content of the conversation in detail. The analysis unit can also improve accuracy by analyzing the flow of the conversation. For example, the analysis unit can improve accuracy by analyzing the flow of the conversation and clarify the content of the conversation. This improves the accuracy of the analysis by considering the relationships between conversations. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the conversation text data into a generating AI and have the generating AI perform the relationship analysis.

[0051] The analysis unit can perform analysis based on the attribute information of the speakers in a conversation. The analysis unit can, for example, perform analysis considering the speaker's level of expertise. The analysis unit can, for example, perform analysis considering the speaker's level of expertise to clarify the content of the conversation. The analysis unit can also perform analysis considering the speaker's past speaking history. The analysis unit can, for example, perform analysis considering the speaker's past speaking history to analyze the content of the conversation in detail. The analysis unit can also provide analysis results based on the speaker's attribute information. The analysis unit can, for example, provide analysis results based on the speaker's attribute information to clarify the content of the conversation. This allows for more accurate analysis results by considering the speaker's attribute information. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the speaker's attribute information into a generating AI and have the generating AI perform the analysis.

[0052] The analysis unit can perform analysis based on the geographical distribution of conversations. For example, the analysis unit can analyze the geographical distribution of conversations to improve accuracy. For example, the analysis unit can analyze the geographical distribution of conversations to improve accuracy and clarify the content of the conversations. The analysis unit can also provide analysis results based on geographical distribution. For example, the analysis unit can provide analysis results based on geographical distribution and analyze the content of the conversations in detail. The analysis unit can also perform analysis considering the geographical background of conversations. For example, the analysis unit can perform analysis considering the geographical background of conversations to clarify the content of the conversations. This allows for more accurate analysis results by considering geographical distribution. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input geographical data of conversations into a generating AI and have the generating AI perform the analysis.

[0053] The analysis unit can improve the accuracy of its analysis based on relevant literature related to the conversation during the analysis process. For example, the analysis unit can refer to relevant literature to improve the accuracy of the analysis results. For example, the analysis unit can refer to relevant literature to improve the accuracy of the analysis results and clarify the content of the conversation. The analysis unit can also search for relevant literature based on the content of the conversation and incorporate it into the analysis. For example, the analysis unit can search for relevant literature based on the content of the conversation, incorporate it into the analysis, and analyze the content of the conversation in detail. The analysis unit can also provide analysis results based on relevant literature. For example, the analysis unit provides analysis results based on relevant literature and clarifies the content of the conversation. This improves the accuracy of the analysis by referring to relevant literature. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the conversation text data into a generating AI and have the generating AI perform the referencing and analysis of relevant literature.

[0054] The judgment unit can improve the accuracy of its judgment when determining the validity of a statement by referencing data of similar past statements. For example, the judgment unit can refer to similar past statements to determine validity. For example, the judgment unit can refer to similar past statements to determine validity and confirm the accuracy of the statement. The judgment unit can also improve the accuracy of its judgment based on data of similar statements. For example, the judgment unit can improve the accuracy of its judgment based on data of similar statements and make a detailed judgment on the validity of the statement. The judgment unit can also analyze past statement history to determine validity. For example, the judgment unit can analyze past statement history to determine validity and confirm the accuracy of the statement. This improves the accuracy of the judgment by referring to data of similar past statements. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without using AI. For example, the judgment unit can input data of similar past statements into a generating AI and have the generating AI perform the judgment on validity.

[0055] The judgment unit can make a judgment on the validity of a statement based on the speaker's level of expertise. For example, the judgment unit can make a judgment on validity based on the speaker's level of expertise. For example, the judgment unit can make a judgment on validity based on the speaker's level of expertise and confirm the accuracy of the statement. The judgment unit can also make a judgment on validity by considering the speaker's past statement history. For example, the judgment unit can make a judgment on validity by considering the speaker's past statement history and confirm the accuracy of the statement. The judgment unit can also make a judgment on validity based on the speaker's attribute information. For example, the judgment unit can make a judgment on validity based on the speaker's attribute information and confirm the accuracy of the statement. This makes it possible to make a more accurate judgment by considering the speaker's level of expertise. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input the speaker's level of expertise into a generating AI and have the generating AI perform the judgment on validity.

[0056] The decision-making unit can determine the priority of judgments based on the context of the conversation when determining the validity of a statement. For example, the decision-making unit can analyze the context of the conversation and prioritize important statements. For example, the decision-making unit can analyze the context of the conversation, prioritize important statements, and verify the accuracy of the statements. The decision-making unit can also determine the priority of judgments by considering the flow of the conversation. For example, the decision-making unit can consider the flow of the conversation, determine the priority of judgments, and quickly determine the validity of statements. The decision-making unit can also analyze the context of the conversation and determine the priority. For example, the decision-making unit can analyze the context of the conversation, determine the priority, and make a detailed judgment on the validity of statements. This allows important statements to be prioritized by considering the context of the conversation. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input conversational context data into a generating AI and have the generating AI perform the determination of the priority of judgments.

[0057] The judgment unit can improve the accuracy of its judgment when determining the validity of a statement by referencing an external database. For example, the judgment unit may refer to an external database to determine the validity of a statement. The judgment unit may refer to an external database to determine the validity of a statement and confirm its accuracy. The judgment unit can also improve the accuracy of its judgment by referencing an external database. For example, the judgment unit may improve the accuracy of its judgment by referencing an external database and make a detailed judgment on the validity of a statement. The judgment unit can also analyze information from an external database to determine validity. For example, the judgment unit may analyze information from an external database to determine validity and confirm the accuracy of the statement. As a result, the accuracy of the judgment is improved by referring to an external database. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit may input information from an external database into a generating AI and have the generating AI perform the validity judgment.

[0058] The suggestion unit can update the content of the suggested questions in real time according to the progress of the conversation. For example, the suggestion unit updates the questions at the appropriate time according to the progress of the conversation. For example, the suggestion unit updates the questions at the appropriate time according to the progress of the conversation to clarify the content of the conversation. The suggestion unit can also adjust the questions in real time based on the content of the conversation. For example, the suggestion unit adjusts the questions in real time based on the content of the conversation to prioritize confirmation of important parts of the conversation. The suggestion unit can also analyze the flow of the conversation and suggest the most appropriate questions in real time. For example, the suggestion unit analyzes the flow of the conversation and suggests the most appropriate questions in real time to clarify the content of the conversation. As a result, more appropriate questions are suggested by updating the questions in real time according to the progress of the conversation. Some or all of the above processes in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input the text data of the conversation into a generating AI and have the generating AI perform the question updates.

[0059] The suggestion unit can optimize the content of the questions it proposes based on past conversation history. For example, the suggestion unit can propose the most appropriate questions based on past conversation history. For example, the suggestion unit can propose the most appropriate questions based on past conversation history and clarify the content of the conversation. The suggestion unit can also analyze the conversation history and propose appropriate questions. For example, the suggestion unit can analyze the conversation history, propose appropriate questions, and prioritize confirming important parts of the conversation. The suggestion unit can also optimize questions by considering past statements. For example, the suggestion unit can optimize questions by considering past statements and clarify the content of the conversation. As a result, more appropriate questions are proposed by referring to past conversation history. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input past conversation history into a generating AI and have the generating AI perform question optimization.

[0060] The suggestion unit can adjust the content of the questions it proposes based on the geographical context of the conversation. For example, the suggestion unit can propose appropriate questions considering the geographical context of the conversation. For example, the suggestion unit can propose appropriate questions considering the geographical context of the conversation to clarify the content of the conversation. The suggestion unit can also adjust the content of the questions based on geographical information. For example, the suggestion unit can adjust the content of the questions based on geographical information to prioritize confirmation of important parts of the conversation. The suggestion unit can also propose questions related to the location of the conversation. For example, the suggestion unit can propose questions related to the location of the conversation to clarify the content of the conversation. This allows for the proposal of more appropriate questions by considering the geographical context. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or not using AI. For example, the suggestion unit can input the geographical data of the conversation into a generating AI and have the generating AI perform the question adjustments.

[0061] The suggestion unit can optimize the content of the questions it proposes based on relevant external databases. For example, the suggestion unit can refer to external databases and propose appropriate questions. For example, the suggestion unit can refer to external databases and propose appropriate questions to clarify the content of the conversation. The suggestion unit can also optimize the content of questions based on relevant databases. For example, the suggestion unit can optimize the content of questions based on relevant databases and prioritize confirming important parts of the conversation. The suggestion unit can also analyze information from external databases and propose questions. For example, the suggestion unit can analyze information from external databases, propose questions, and clarify the content of the conversation. This allows for the proposal of more appropriate questions by referring to external databases. Some or all of the above processes in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input information from external databases into a generating AI and have the generating AI perform question optimization.

[0062] The management department can select a management method by comparing the information recorded in the database with past data. For example, the management department can select the optimal management method based on past data. For example, the management department can select the optimal management method based on past data and clarify the contents of the database. The management department can also analyze the history of the data and provide an appropriate management method. For example, the management department can analyze the history of the data, provide an appropriate management method and manage the contents of the database in detail. The management department can also select the optimal method by referring to past management methods. For example, the management department can select the optimal method by referring to past management methods and prioritize the management of important parts of the database. This allows the optimal management method to be selected by comparing it with past data. Some or all of the above processes in the management department may be performed using AI, for example, or without AI. For example, the management department can input past data into a generating AI and have the generating AI perform the selection of a management method.

[0063] The management department can adjust the information recorded in the database based on user attribute information. For example, the management department can customize the database management method based on user attribute information. For example, the management department can customize the database management method based on user attribute information and clarify the contents of the database. The management department can also adjust the management method considering the user's past usage history. For example, the management department can adjust the management method considering the user's past usage history and prioritize the management of important parts of the database. The management department can also analyze user attribute information and provide the optimal management method. For example, the management department can analyze user attribute information, provide the optimal management method and manage the contents of the database in detail. This makes it possible to manage the database more appropriately by customizing it based on user attribute information. Some or all of the above processes in the management department may be performed using AI, for example, or not using AI. For example, the management department can input user attribute information into a generating AI and have the generating AI perform the adjustment of the management method.

[0064] The management department can select a management method for the information recorded in the database based on geographical context. For example, the management department can select an appropriate management method considering geographical context. For example, the management department can select an appropriate management method considering geographical context and clarify the contents of the database. The management department can also adjust the database management method based on geographical information. For example, the management department can adjust the database management method based on geographical information and prioritize the management of important parts of the database. The management department can also analyze geographical context and provide the optimal management method. For example, the management department can analyze geographical context, provide the optimal management method, and manage the contents of the database in detail. This makes it possible to manage the database more appropriately by considering geographical context. Some or all of the above processes in the management department may be performed using AI, for example, or not using AI. For example, the management department can input geographical information into a generating AI and have the generating AI perform the selection of a management method.

[0065] The management department can manage the information recorded in the database in conjunction with related external databases. For example, the management department can manage information in conjunction with external databases. For example, the management department can manage information in conjunction with external databases and clarify the contents of the database. The management department can also adjust management methods based on related databases. For example, the management department can adjust management methods based on related databases and prioritize the management of important parts of the database. The management department can also analyze information in external databases and provide optimal management methods. For example, the management department can analyze information in external databases, provide optimal management methods, and manage the contents of the database in detail. This enables more appropriate database management by linking with external databases. Some or all of the above processes in the management department may be performed using AI, for example, or not. For example, the management department can input information from external databases into a generating AI and have the generating AI perform adjustments to the management methods.

[0066] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0067] The support system can refer to relevant external databases based on the content of a conversation to determine the validity of the statement. For example, in a conversation about medicine, the system can refer to a medical database to verify the accuracy of the statement. Similarly, in a conversation about education, it can refer to an education database to determine the validity of the statement. Furthermore, in a conversation about technology, it can refer to a technology database to verify the accuracy of the statement. This allows for a more accurate determination of the validity of statements by referring to external databases.

[0068] The support system can search for relevant literature based on the content of a conversation and determine the validity of the statements. For example, in a conversation about medicine, the system can search for relevant medical literature to verify the accuracy of the statements. In a conversation about education, it can search for relevant educational literature to determine the validity of the statements. Furthermore, in a conversation about technology, it can search for relevant technical literature to verify the accuracy of the statements. This allows for a more accurate determination of the validity of statements by referring to relevant literature.

[0069] The support system can refer to relevant geographical information based on the content of a conversation to determine the appropriateness of the statement. For example, in a conversation about local healthcare, the system can refer to local healthcare information to verify the accuracy of the statement. Similarly, in a conversation about local education, it can refer to local education information to determine the appropriateness of the statement. Furthermore, in a conversation about local technology, it can refer to local technology information to verify the accuracy of the statement. This allows for a more accurate determination of the appropriateness of statements by referring to geographical information.

[0070] The support system can refer to relevant social media information based on the content of a conversation to determine the appropriateness of the statement. For example, in a conversation about medicine, the system can refer to relevant social media posts to verify the accuracy of the statement. Similarly, in a conversation about education, it can refer to relevant social media posts to determine the appropriateness of the statement. Furthermore, in a conversation about technology, it can refer to relevant social media posts to verify the accuracy of the statement. This allows for a more accurate determination of the appropriateness of a statement by referring to social media information.

[0071] The support system can refer to relevant past conversation history based on the content of the conversation to determine the appropriateness of the statement. For example, in the case of a medical conversation, the system can refer to past medical conversation history to verify the accuracy of the statement. Similarly, in the case of an educational conversation, it can refer to past educational conversation history to determine the appropriateness of the statement. Furthermore, in the case of a technical conversation, it can refer to past technical conversation history to verify the accuracy of the statement. This allows for a more accurate determination of the appropriateness of a statement by referring to past conversation history.

[0072] The following briefly describes the processing flow for example form 1.

[0073] Step 1: The recording unit records the conversation. The recording unit can record the conversation using methods such as audio recording, video recording, and text recording. For example, it can record the conversation using audio recording, record the conversation as video using video recording, and record the conversation as written information using text recording. Step 2: The text conversion unit converts the conversation recorded by the recording unit into text. The text conversion unit can convert audio data into text data using speech recognition technology. It can also convert conversations into text using manual input. For example, it is possible to convert audio data into text data in real time using speech recognition technology, and to convert conversations into text using manual input for later review. Step 3: The analysis unit analyzes the conversation that has been transcribed by the text conversion unit. The analysis unit can analyze the content of the conversation using natural language processing techniques and extract important information from the conversation using keyword extraction techniques. For example, it can analyze the grammatical and semantic accuracy of the conversation using natural language processing techniques and pick out particularly important information from the conversation using keyword extraction techniques. Step 4: The judgment unit determines the validity of the statements in the conversation analyzed by the analysis unit. The judgment unit can determine the validity of the statements based on fact-checking and logical consistency, verify the basis for the statements, and provide additional information as needed. For example, it can perform fact-checking, verify the accuracy of the statements, determine the validity of the statements based on logical consistency, and provide additional information as needed. Step 5: The suggestion unit proposes questions based on the results determined by the judgment unit. The suggestion unit can propose multiple questions based on the content of the conversation and questions based on the user's interests. For example, based on the content of the conversation, it can propose a question such as "Is there any data showing the effectiveness of this material?" and based on the user's interests, it can propose a question such as "What other side effects are possible?"

[0074] (Example of form 2) The support system according to an embodiment of the present invention is a system that records, transcribes, analyzes, judges the validity of statements made, and suggests questions. The support system records, transcribes, and analyzes conversations with experts in a particular field to judge the validity of statements and suggests multiple questions based on the content of the conversation. For example, in conversations with a child's tutor or a doctor at a hospital, when technical terms are used or difficult judgments are required, having the support system by your side can provide great reassurance. Specifically, the support system operates in the following steps. First, it records and transcribes the conversation in real time. Next, it analyzes the transcribed conversation to judge the validity of statements. For example, if a tutor says, "This teaching material is very effective," the support system will verify the basis of that statement and, if necessary, suggest questions such as, "Do you have any data that shows the effectiveness of this teaching material?" The support system also suggests multiple questions based on the content of the conversation. For example, if a doctor at a hospital says, "This medicine has few side effects," the support system will suggest questions such as, "What other side effects are possible?" or "How long does it take for the effects of this medicine to appear?" Furthermore, the support system utilizes natural language processing to record and analyze each statement. It analyzes the recorded conversation and verifies the accuracy of key phrases. If inaccurate information or errors are present, it automatically detects them and makes appropriate statements at a time that does not disrupt the flow of the conversation. In addition, information regarding the child's academic performance and preferences is recorded and managed in a database via AI and used as needed. In this way, the support system assists conversations with experts in their respective fields, helping users make appropriate choices. For example, if it is difficult to decide what choices to make regarding a child's learning, the support system intervenes in conversations with school or tutors to support the decision. This allows users to appropriately grasp points that need to be confirmed and important information within the conversation. Thus, the support system can assist conversations with experts in their respective fields, helping users make appropriate choices.

[0075] The support system according to the embodiment comprises a recording unit, a text conversion unit, an analysis unit, a decision unit, and a proposal unit. The recording unit records conversations. The recording unit can record conversations by methods such as audio recording, video recording, and text recording. For example, the recording unit records conversations using audio recording. The recording unit can also record conversations as video using video recording. The recording unit can also record conversations as text information using text recording. For example, the recording unit records conversations using audio recording, and then analyzes the audio data to convert it into text data. The text conversion unit converts the conversations recorded by the recording unit into text. For example, the text conversion unit converts audio data into text data using speech recognition technology. The text conversion unit can also convert conversations into text using manual input. For example, the text conversion unit converts audio data into text data in real time using speech recognition technology. The text conversion unit can also convert conversations into text using manual input for later review. The analysis unit analyzes the conversations converted into text by the text conversion unit. The analysis unit analyzes the content of the conversation using, for example, natural language processing technology. The analysis unit can also extract important information from the conversation using keyword extraction technology. For example, the analysis unit analyzes the grammatical and semantic accuracy of the conversation using natural language processing technology. Furthermore, the analysis unit can pick out particularly important information from the conversation using keyword extraction technology. The judgment unit determines the validity of the statements in the conversation analyzed by the analysis unit. The judgment unit determines the validity of the statements based, for example, fact-checking and logical consistency. Furthermore, the judgment unit can verify the basis of the statements and provide additional information as needed. For example, the judgment unit performs fact-checking to confirm the accuracy of the statements. Furthermore, the judgment unit can determine the validity of the statements based on logical consistency and provide additional information as needed. The proposal unit proposes questions based on the results determined by the judgment unit. For example, the proposal unit proposes multiple questions based on the content of the conversation. Furthermore, the proposal unit can propose questions based on the user's interests. For example, the proposal unit proposes a question such as, "Is there any data demonstrating the effectiveness of this material?" based on the content of the conversation.Furthermore, the proposal function can also suggest questions based on the user's interests, such as "What other side effects might be possible?". This allows the support system according to the embodiment to facilitate conversations with experts in specific fields and assist users in making appropriate choices.

[0076] The recording unit records conversations. The recording unit can record conversations using methods such as audio recording, video recording, and text recording. For example, the recording unit can record conversations using audio recording. It can also record conversations as video using video recording. Furthermore, it can record conversations as text information using text recording. For example, the recording unit can record conversations using audio recording, and then analyze the audio data to convert it into text data. The recording unit is recommended to use high-quality microphones and cameras to accurately record the content of conversations. For audio recording, noise cancellation technology can be used to remove background noise and obtain clear audio data. For video recording, wide-angle lenses and high-resolution cameras can be used to capture the overall picture of the conversation. For text recording, keyboards or tablets that allow real-time input can be used to record conversation content quickly and accurately. The recording unit centrally manages this data and can collaborate with other departments and systems as needed. For example, recorded data can be stored in cloud storage and made accessible to the analysis and text conversion units. Furthermore, by optimizing data storage formats and compression methods, efficient data management becomes possible. This allows the recording unit to record conversations in a variety of ways, improving the overall system performance.

[0077] The text conversion unit converts conversations recorded by the recording unit into text. The text conversion unit can convert audio data into text data using, for example, speech recognition technology. The text conversion unit can also convert conversations into text using manual input. For example, the text conversion unit can convert audio data into text data in real time using speech recognition technology. Alternatively, the text conversion unit can convert conversations into text using manual input for later review. Speech recognition technology uses a deep learning model to analyze the features of audio data with high accuracy and convert them into text data. Specifically, it divides the audio data into short frames and identifies phonemes for each frame. This allows for accurate transcription of audio data into text. In the case of manual input, a professional operator can input the conversation content in real time and later review and correct it. The text conversion unit centrally manages this text data, making it accessible to the analysis and judgment units. Furthermore, by optimizing the format and tagging of the text data, subsequent analysis and judgment become easier. For example, tagging the speaker and time of speaking in a conversation allows for quick searching of specific statements. This allows the text conversion unit to efficiently and accurately transcribe conversations into text, improving the overall performance of the system.

[0078] The analysis unit analyzes the conversation that has been transcribed by the text conversion unit. The analysis unit analyzes the content of the conversation using, for example, natural language processing techniques. It can also extract important information from the conversation using keyword extraction techniques. For example, the analysis unit analyzes the grammatical and semantic accuracy of the conversation using natural language processing techniques. Furthermore, it can pick out particularly important information from the conversation using keyword extraction techniques. Natural language processing techniques include morphological analysis, syntactic analysis, and semantic analysis, which are combined to analyze the content of the conversation in detail. Morphological analysis divides the text into words and identifies the part of speech of each word. Syntactic analysis analyzes the structure of sentences and clarifies relationships such as subject, predicate, and object. Semantic analysis understands the meaning of sentences and provides appropriate interpretations based on context. Keyword extraction techniques automatically extract important words and phrases from the text to grasp the main points of the conversation. This allows the analysis unit to quickly and accurately analyze the content of the conversation and extract important information. Furthermore, the analysis unit can also utilize historical data and statistical information to analyze long-term trends and patterns. For example, by using past conversation data, it is possible to identify trends related to specific themes or topics and make future predictions. This allows the analysis unit to handle not only real-time analysis but also long-term analysis, improving the reliability and usefulness of the entire system.

[0079] The judgment unit determines the validity of statements in a conversation analyzed by the analysis unit. The judgment unit determines the validity of statements based, for example, on fact-checking and logical consistency. The judgment unit can also verify the basis of statements and provide additional information as needed. For example, the judgment unit performs fact-checking to confirm the accuracy of statements. Furthermore, the judgment unit can determine the validity of statements based on logical consistency and provide additional information as needed. The judgment unit automatically evaluates the validity of statements using AI. Specifically, the AI ​​performs fact-checking by comparing the content of statements with predefined rules and databases. For example, it checks whether statements are based on specific data or statistics and evaluates their accuracy. The AI ​​also evaluates the logical consistency of statements, checking for contradictions or errors. This allows the judgment unit to quickly and accurately determine the validity of statements. Furthermore, the judgment unit can collect feedback from users and continuously improve the accuracy and reliability of its judgments. For example, it can update the AI's evaluation model based on additional information and corrections provided by users to make more accurate judgments. The judgment unit can also integrate multiple information sources to perform a more comprehensive evaluation. This allows the decision-making unit to evaluate the validity of statements with high accuracy and provide users with reliable information.

[0080] The suggestion unit proposes questions based on the results determined by the judgment unit. For example, the suggestion unit proposes multiple questions based on the content of the conversation. It can also propose questions based on the user's interests. For example, based on the content of the conversation, the suggestion unit may propose a question such as, "Is there any data showing the effectiveness of this material?" It can also propose a question such as, "What other side effects are possible?" based on the user's interests. The suggestion unit uses AI to analyze the user's interests and the context of the conversation and automatically generates appropriate questions. Specifically, the AI ​​analyzes the content of the conversation and identifies relevant topics and themes. Next, it generates the most appropriate questions based on the user's past behavior and interests. For example, if the user has shown interest in a particular theme in the past, it will propose questions related to that theme. The suggestion unit can also collect user feedback and continuously improve the accuracy and usefulness of its suggestions. For example, it can record how the user reacted to the suggested questions and update the AI ​​model based on that data. This allows the suggestion unit to always propose the best questions to the user and improve the quality of the conversation. Furthermore, the proposal department enables more interactive conversations by simultaneously proposing multiple questions and allowing the user to select from them. This allows the proposal department to suggest questions that match the user's interests and needs, facilitating a smooth conversation.

[0081] The analysis unit can verify the accuracy of key phrases in a conversation. For example, the analysis unit extracts key phrases based on frequently occurring words and important phrases. For example, the analysis unit extracts words that frequently appear in a conversation as key phrases. The analysis unit can also extract important phrases as key phrases based on the context of the conversation. The analysis unit verifies the accuracy of key phrases based on grammatical and semantic accuracy. For example, the analysis unit checks whether the grammatical correctness is correct and determines the accuracy of the key phrase. The analysis unit can also check whether the semantic correctness is correct and determine the accuracy of the key phrase. This improves the accuracy of the analysis by verifying the accuracy of key phrases in a conversation. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the conversation text data into a generating AI and have the generating AI perform key phrase extraction and accuracy verification.

[0082] The suggestion unit can suggest multiple questions based on the content of the conversation. For example, the suggestion unit can analyze the content of the conversation and suggest relevant questions. For example, the suggestion unit can suggest a question such as, "Is there any data showing the effectiveness of this material?" based on the content of the conversation. The suggestion unit can also suggest a question such as, "What other side effects are possible?" based on the content of the conversation. The suggestion unit can suggest open-ended and closed-ended questions, for example. For example, the suggestion unit can suggest an open-ended question based on the content of the conversation. The suggestion unit can also suggest a closed-ended question based on the content of the conversation. By suggesting multiple questions based on the content of the conversation, it helps the user to ask appropriate questions. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input the text data of the conversation into a generating AI and have the generating AI suggest questions.

[0083] The recording unit can record conversations in real time. For example, the recording unit can record conversations in real time using voice recording. For example, the recording unit can start recording at the same time as the conversation begins and stop recording at the same time as the conversation ends. The recording unit can also record conversations as video in real time using video recording. For example, the recording unit can start video recording at the same time as the conversation begins and stop video recording at the same time as the conversation ends. The recording unit can also record conversations as text information in real time using text recording. For example, the recording unit can transcribe the content of the conversation into text in real time and record it. This allows for accurate recording by recording conversations in real time. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input the audio data of the conversation into a generating AI and have the generating AI perform real-time audio recording.

[0084] The text conversion unit can convert recorded conversations into text. The text conversion unit can convert audio data into text data using, for example, speech recognition technology. The text conversion unit can convert audio data into text data in real time using, for example, speech recognition technology. The text conversion unit can also convert conversations into text using manual input. The text conversion unit can also convert conversations into text using, for example, manual input and review them later. This makes it easier to refer to recorded conversations later by converting them into text. Some or all of the above-described processes in the text conversion unit may be performed using, for example, AI, or without AI. For example, the text conversion unit can input audio data into a generating AI and have the generating AI perform the conversion to text data.

[0085] The judgment unit can determine the validity of a statement. The judgment unit determines the validity of a statement based, for example, on fact-checking and logical consistency. The judgment unit, for example, performs fact-checking to confirm the accuracy of the statement. The judgment unit can also determine the validity of a statement based on logical consistency and provide additional information as needed. This makes it possible to provide accurate information by determining the validity of a statement. Some or all of the above processing in the judgment unit may be performed using, for example, AI, or without AI. For example, the judgment unit can input the text data of the conversation into a generating AI and have the generating AI perform the judgment on the validity of the statement.

[0086] The suggestion unit can make statements at times that do not disrupt the flow of conversation. For example, the suggestion unit can make statements at appropriate times based on the interval between statements and natural pauses in the conversation. For example, the suggestion unit can analyze the flow of conversation and make statements at appropriate times. The suggestion unit can also make statements based on natural pauses in the conversation. This enables smooth conversation by making appropriate statements at times that do not disrupt the flow of conversation. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input conversation text data into a generating AI and have the generating AI execute the timing of statements.

[0087] A management department is provided, which records and manages information about children's academic performance and intentions in a database, and can use it as needed. For example, the management department records children's test scores and assignment evaluations in the database. For example, the management department records children's test scores in the database and can refer to them later. The management department can also record children's assignment evaluations in the database and use them as needed. For example, the management department records children's aspirations for higher education and careers in the database. For example, the management department can record children's aspirations for higher education in the database and use it to select schools. The management department can also record children's career aspirations in the database and use it for future career guidance. In this way, information about children's academic performance and intentions is recorded and managed in a database and can be used as needed. Some or all of the above processing in the management department may be performed using AI, for example, or not using AI. For example, the management department can input information about children's academic performance and intentions into a generating AI and have the generating AI perform the recording and management in the database.

[0088] The recording unit can estimate the user's emotions and adjust the timing of conversation recording based on the estimated emotions. For example, if the user is nervous, the recording unit can adjust to record only the most important parts of the conversation. The recording unit can also adjust to record the entire conversation in detail if the user is relaxed, allowing for later reference. The recording unit can also adjust to record only the essential parts if the user is in a hurry, allowing for later review. By adjusting the timing of conversation recording based on the user's emotions, more appropriate recordings are possible. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input user emotion data into a generating AI and have the generating AI adjust the timing of conversation recording.

[0089] The recording unit can remove background noise and other unwanted sounds when recording conversations. For example, the recording unit can analyze background noise during a conversation in real time and remove the noise. For example, the recording unit can analyze background noise during a conversation in real time and apply a noise reduction algorithm to remove the noise. The recording unit can also filter out noise in specific frequency bands when recording conversations. For example, the recording unit can filter out noise in specific frequency bands when recording conversations to record clear audio. The recording unit can also remove background noise after recording a conversation by applying a noise reduction algorithm. For example, the recording unit can remove background noise after recording a conversation by applying a noise reduction algorithm to provide clear audio. This makes it possible to record conversations clearly by removing background noise and other unwanted sounds. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input conversation audio data into a generating AI and have the generating AI perform noise reduction.

[0090] The recording unit can automatically highlight specific keywords when they appear during conversation recording. For example, the recording unit can automatically highlight keywords such as "important" or "confirm" when they appear in a conversation, making them easier to review later. The recording unit can also search for and highlight specific keywords after the conversation has been recorded, ensuring that important information is not missed. The recording unit can also automatically highlight custom keywords set by the user when they appear in a conversation, ensuring that important information is not missed. This ensures that important information is not missed by highlighting specific keywords. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input the conversation text data into a generating AI and have the generating AI perform keyword highlighting.

[0091] The recording unit can estimate the user's emotions and determine the priority of conversations to record based on the estimated emotions. For example, if the user is nervous, the recording unit will prioritize recording important conversations. If the user is relaxed, the recording unit can record the entire conversation evenly for later reference. If the user is in a hurry, the recording unit can prioritize recording the most important parts of the conversation for later review. This allows for the prioritization of important conversations by determining the priority of conversations based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input user emotion data into a generating AI and have the generating AI determine the priority of conversations.

[0092] The recording unit can prioritize recording conversations that are highly relevant based on the user's geographical location information when recording conversations. For example, if the user is in a specific location, the recording unit will prioritize recording conversations related to that location, which can then be referenced later. The recording unit can also prioritize recording conversations related to the user's destination if the user is on the move, which can then be reviewed later. Furthermore, if the user is participating in a specific event, the recording unit can prioritize recording conversations related to that event, which can then be referenced later. This allows for the prioritization of recording highly relevant conversations by considering geographical location information. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input the user's geographical location information into a generating AI and have the generating AI prioritize the recording of conversations.

[0093] The recording unit can analyze the user's social media activity and record relevant conversations when recording a conversation. For example, the recording unit can record relevant conversations based on information the user has shared on social media. The recording unit can record relevant conversations based on information the user has shared on social media and refer to them later. The recording unit can also analyze the content of the user's social media posts and record relevant conversations. The recording unit can analyze the content of the user's social media posts, record relevant conversations and refer to them later. The recording unit can also record relevant conversations based on accounts the user follows on social media. The recording unit can record relevant conversations based on accounts the user follows on social media and refer to them later. This allows for efficient recording of relevant conversations by analyzing social media activity. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input the user's social media data into a generating AI and have the generating AI record relevant conversations.

[0094] The text generation unit can estimate the user's emotions and adjust the textual expression based on the estimated emotions. For example, if the user is nervous, the text generation unit will use concise and easy-to-understand language. The text generation unit will use concise and easy-to-understand language to make it easier to review later. The text generation unit can also use detailed language if the user is relaxed. The text generation unit will use detailed language to record the content of the conversation in detail. The text generation unit can also use concise language if the user is in a hurry. The text generation unit will use concise language to prioritize recording the important parts of the conversation. This allows for more appropriate text generation by adjusting the textual expression based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input user emotion data into a generating AI and have the generating AI adjust the way the text is expressed.

[0095] The text conversion unit can interpret technical terms and abbreviations during the text conversion process and convert them into more understandable expressions. For example, the text conversion unit can convert medical terms into more general expressions to generate easily understandable text. The text conversion unit can also convert educational terms into more understandable expressions to make conversations easier to understand. The text conversion unit can also convert technical terms into more general expressions to make conversations easier to understand. In this way, by converting technical terms and abbreviations into appropriate expressions, easily understandable text is possible. Some or all of the above-described processes in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input technical terms and abbreviations into a generating AI and have the generating AI perform the conversion into appropriate expressions.

[0096] The text conversion unit can insert punctuation marks based on the context of the conversation during the text conversion process. For example, the text conversion unit can insert appropriate punctuation marks based on the flow of the conversation. The text conversion unit can, for example, insert appropriate punctuation marks based on the flow of the conversation to generate easy-to-read text. The text conversion unit can also analyze the context and insert punctuation marks in appropriate places. For example, the text conversion unit can analyze the context and insert punctuation marks in appropriate places to clarify the content of the conversation. The text conversion unit can also consider the meaning of the conversation and insert appropriate punctuation marks. For example, the text conversion unit can consider the meaning of the conversation and insert appropriate punctuation marks to make the content of the conversation easier to understand. This makes it possible to create easy-to-read text by inserting punctuation marks while considering the context. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input the conversation text data into a generating AI and have the generating AI perform the insertion of punctuation marks.

[0097] The text generation unit can estimate the user's emotions and adjust the length of the text based on the estimated emotions. For example, if the user is nervous, the text generation unit will generate short, concise text, prioritizing the recording of important parts of the conversation. The text generation unit can also generate detailed text if the user is relaxed, recording the conversation in detail. The text generation unit can also generate concise text if the user is in a hurry, prioritizing the recording of key points of the conversation. This allows for text of appropriate length by adjusting the length of the text based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input user emotion data into a generating AI and have the generating AI adjust the length of the text.

[0098] The text conversion unit can determine the order of text conversion based on the importance of the conversations. For example, the text conversion unit can prioritize the text conversion of important conversations. For example, the text conversion unit can prioritize the text conversion of important conversations based on their importance so that they can be referenced later. The text conversion unit can also determine the order of text conversion based on the importance of the conversations. For example, the text conversion unit can analyze the importance of the conversations, determine the order of text conversion, and prioritize the recording of important conversations. The text conversion unit can also analyze the importance of the conversations and determine the priority order. For example, the text conversion unit can analyze the importance of the conversations, determine the priority order, and prioritize the text conversion of important conversations. In this way, by determining the priority order of text conversion based on the importance of the conversations, important conversations can be prioritized for text conversion. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input the conversation text data into a generating AI and have the generating AI perform the determination of the text conversion order.

[0099] The text conversion unit can determine the order of text conversion based on the relevance of the conversations. For example, the text conversion unit can prioritize the text conversion of conversations that are highly relevant. For example, the text conversion unit can prioritize the text conversion of conversations that are highly relevant based on their relevance, allowing for later reference. The text conversion unit can also determine the order of text conversion based on the relevance of the conversations. For example, the text conversion unit can analyze the relevance of the conversations, determine the order of text conversion, and prioritize the recording of conversations that are highly relevant. The text conversion unit can also analyze the relevance of the conversations and adjust the order. For example, the text conversion unit can analyze the relevance of the conversations, adjust the order, and prioritize the text conversion of conversations that are highly relevant. In this way, by adjusting the order of text conversion based on the relevance of the conversations, conversations that are highly relevant can be prioritized for text conversion. Some or all of the above-described processes in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input the conversation text data into a generating AI and have the generating AI determine the order of text conversion.

[0100] The analysis unit can estimate the user's emotions and adjust the analysis criteria based on the estimated emotions. For example, if the user is nervous, the analysis unit provides concise and easy-to-understand analysis results, clarifying the content of the conversation. The analysis unit can also provide detailed analysis results if the user is relaxed, analyzing the content of the conversation in detail. The analysis unit can also provide concise analysis results if the user is in a hurry, prioritizing the analysis of the most important parts of the conversation. By adjusting the analysis criteria based on the user's emotions, more appropriate analysis results can be obtained. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generating AI and have the generating AI adjust the analysis criteria.

[0101] The analysis unit can improve the accuracy of its analysis based on the relationships between conversations during the analysis process. For example, the analysis unit can improve accuracy by analyzing the context of the conversation. For example, the analysis unit can improve accuracy by analyzing the context of the conversation and clarify the content of the conversation. The analysis unit can also provide analysis results while considering the relationships between conversations. For example, the analysis unit can provide analysis results while considering the relationships between conversations and analyze the content of the conversation in detail. The analysis unit can also improve accuracy by analyzing the flow of the conversation. For example, the analysis unit can improve accuracy by analyzing the flow of the conversation and clarify the content of the conversation. This improves the accuracy of the analysis by considering the relationships between conversations. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the conversation text data into a generating AI and have the generating AI perform the relationship analysis.

[0102] The analysis unit can perform analysis based on the attribute information of the speakers in a conversation. The analysis unit can, for example, perform analysis considering the speaker's level of expertise. The analysis unit can, for example, perform analysis considering the speaker's level of expertise to clarify the content of the conversation. The analysis unit can also perform analysis considering the speaker's past speaking history. The analysis unit can, for example, perform analysis considering the speaker's past speaking history to analyze the content of the conversation in detail. The analysis unit can also provide analysis results based on the speaker's attribute information. The analysis unit can, for example, provide analysis results based on the speaker's attribute information to clarify the content of the conversation. This allows for more accurate analysis results by considering the speaker's attribute information. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the speaker's attribute information into a generating AI and have the generating AI perform the analysis.

[0103] The analysis unit can estimate the user's emotions and adjust the display order of the analysis results based on the estimated emotions. For example, if the user is nervous, the analysis unit will prioritize displaying important analysis results to clarify the content of the conversation. The analysis unit can also display detailed analysis results if the user is relaxed to analyze the content of the conversation in detail. The analysis unit can also prioritize displaying concise analysis results if the user is in a hurry to clarify the important parts of the conversation. In this way, by adjusting the display order of the analysis results based on the user's emotions, important information can be prioritized. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generating AI and have the generating AI adjust the display order of the analysis results.

[0104] The analysis unit can perform analysis based on the geographical distribution of conversations. For example, the analysis unit can analyze the geographical distribution of conversations to improve accuracy. For example, the analysis unit can analyze the geographical distribution of conversations to improve accuracy and clarify the content of the conversations. The analysis unit can also provide analysis results based on geographical distribution. For example, the analysis unit can provide analysis results based on geographical distribution and analyze the content of the conversations in detail. The analysis unit can also perform analysis considering the geographical background of conversations. For example, the analysis unit can perform analysis considering the geographical background of conversations to clarify the content of the conversations. This allows for more accurate analysis results by considering geographical distribution. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input geographical data of conversations into a generating AI and have the generating AI perform the analysis.

[0105] The analysis unit can improve the accuracy of its analysis based on relevant literature related to the conversation during the analysis process. For example, the analysis unit can refer to relevant literature to improve the accuracy of the analysis results. For example, the analysis unit can refer to relevant literature to improve the accuracy of the analysis results and clarify the content of the conversation. The analysis unit can also search for relevant literature based on the content of the conversation and incorporate it into the analysis. For example, the analysis unit can search for relevant literature based on the content of the conversation, incorporate it into the analysis, and analyze the content of the conversation in detail. The analysis unit can also provide analysis results based on relevant literature. For example, the analysis unit provides analysis results based on relevant literature and clarifies the content of the conversation. This improves the accuracy of the analysis by referring to relevant literature. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the conversation text data into a generating AI and have the generating AI perform the referencing and analysis of relevant literature.

[0106] The decision-making unit can estimate the user's emotions and adjust the criteria for judging the appropriateness of a statement based on the estimated emotions. For example, if the user is nervous, the decision-making unit uses concise and easy-to-understand criteria to determine the appropriateness of the statement. The decision-making unit can also use detailed criteria if the user is relaxed. For example, if the user is relaxed, the decision-making unit uses detailed criteria to determine the appropriateness of the statement in detail. The decision-making unit can also use concise criteria if the user is in a hurry. For example, if the user is in a hurry, the decision-making unit uses concise criteria to quickly determine the appropriateness of the statement. This allows for more appropriate judgments by adjusting the criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input user emotion data into a generating AI and have the generating AI adjust the decision criteria.

[0107] The judgment unit can improve the accuracy of its judgment when determining the validity of a statement by referencing data of similar past statements. For example, the judgment unit can refer to similar past statements to determine validity. For example, the judgment unit can refer to similar past statements to determine validity and confirm the accuracy of the statement. The judgment unit can also improve the accuracy of its judgment based on data of similar statements. For example, the judgment unit can improve the accuracy of its judgment based on data of similar statements and make a detailed judgment on the validity of the statement. The judgment unit can also analyze past statement history to determine validity. For example, the judgment unit can analyze past statement history to determine validity and confirm the accuracy of the statement. This improves the accuracy of the judgment by referring to data of similar past statements. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without using AI. For example, the judgment unit can input data of similar past statements into a generating AI and have the generating AI perform the judgment on validity.

[0108] The judgment unit can make a judgment on the validity of a statement based on the speaker's level of expertise. For example, the judgment unit can make a judgment on validity based on the speaker's level of expertise. For example, the judgment unit can make a judgment on validity based on the speaker's level of expertise and confirm the accuracy of the statement. The judgment unit can also make a judgment on validity by considering the speaker's past statement history. For example, the judgment unit can make a judgment on validity by considering the speaker's past statement history and confirm the accuracy of the statement. The judgment unit can also make a judgment on validity based on the speaker's attribute information. For example, the judgment unit can make a judgment on validity based on the speaker's attribute information and confirm the accuracy of the statement. This makes it possible to make a more accurate judgment by considering the speaker's level of expertise. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input the speaker's level of expertise into a generating AI and have the generating AI perform the judgment on validity.

[0109] The decision-making unit can estimate the user's emotions and adjust the display method for the appropriateness of the statement based on the estimated user emotions. For example, if the user is nervous, the decision-making unit provides a concise and easy-to-understand display method to clarify the appropriateness of the statement. The decision-making unit can also provide a detailed display method if the user is relaxed. For example, if the user is relaxed, the decision-making unit provides a detailed display method to show the appropriateness of the statement in detail. The decision-making unit can also provide a concise display method if the user is in a hurry. For example, if the user is in a hurry, the decision-making unit provides a concise display method to quickly show the appropriateness of the statement. By adjusting the display method based on the user's emotions, a more easily understandable display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input user emotion data into a generating AI and have the generating AI adjust the display method.

[0110] The decision-making unit can determine the priority of judgments based on the context of the conversation when determining the validity of a statement. For example, the decision-making unit can analyze the context of the conversation and prioritize important statements. For example, the decision-making unit can analyze the context of the conversation, prioritize important statements, and verify the accuracy of the statements. The decision-making unit can also determine the priority of judgments by considering the flow of the conversation. For example, the decision-making unit can consider the flow of the conversation, determine the priority of judgments, and quickly determine the validity of statements. The decision-making unit can also analyze the context of the conversation and determine the priority. For example, the decision-making unit can analyze the context of the conversation, determine the priority, and make a detailed judgment on the validity of statements. This allows important statements to be prioritized by considering the context of the conversation. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input conversational context data into a generating AI and have the generating AI perform the determination of the priority of judgments.

[0111] The judgment unit can improve the accuracy of its judgment when determining the validity of a statement by referencing an external database. For example, the judgment unit may refer to an external database to determine the validity of a statement. The judgment unit may refer to an external database to determine the validity of a statement and confirm its accuracy. The judgment unit can also improve the accuracy of its judgment by referencing an external database. For example, the judgment unit may improve the accuracy of its judgment by referencing an external database and make a detailed judgment on the validity of a statement. The judgment unit can also analyze information from an external database to determine validity. For example, the judgment unit may analyze information from an external database to determine validity and confirm the accuracy of the statement. As a result, the accuracy of the judgment is improved by referring to an external database. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit may input information from an external database into a generating AI and have the generating AI perform the validity judgment.

[0112] The suggestion unit can estimate the user's emotions and adjust the wording of suggested questions based on the estimated emotions. For example, if the user is nervous, the suggestion unit can suggest concise and easy-to-understand questions to clarify the content of the conversation. The suggestion unit can also suggest detailed questions if the user is relaxed to confirm the content of the conversation in detail. The suggestion unit can also suggest concise questions if the user is in a hurry to confirm the important parts of the conversation. By adjusting the wording of questions based on the user's emotions, more appropriate questions are suggested. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the proposal department can input user emotion data into a generating AI and have the AI ​​adjust the way questions are phrased.

[0113] The suggestion unit can update the content of the suggested questions in real time according to the progress of the conversation. For example, the suggestion unit updates the questions at the appropriate time according to the progress of the conversation. For example, the suggestion unit updates the questions at the appropriate time according to the progress of the conversation to clarify the content of the conversation. The suggestion unit can also adjust the questions in real time based on the content of the conversation. For example, the suggestion unit adjusts the questions in real time based on the content of the conversation to prioritize confirmation of important parts of the conversation. The suggestion unit can also analyze the flow of the conversation and suggest the most appropriate questions in real time. For example, the suggestion unit analyzes the flow of the conversation and suggests the most appropriate questions in real time to clarify the content of the conversation. As a result, more appropriate questions are suggested by updating the questions in real time according to the progress of the conversation. Some or all of the above processes in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input the text data of the conversation into a generating AI and have the generating AI perform the question updates.

[0114] The suggestion unit can optimize the content of the questions it proposes based on past conversation history. For example, the suggestion unit can propose the most appropriate questions based on past conversation history. For example, the suggestion unit can propose the most appropriate questions based on past conversation history and clarify the content of the conversation. The suggestion unit can also analyze the conversation history and propose appropriate questions. For example, the suggestion unit can analyze the conversation history, propose appropriate questions, and prioritize confirming important parts of the conversation. The suggestion unit can also optimize questions by considering past statements. For example, the suggestion unit can optimize questions by considering past statements and clarify the content of the conversation. As a result, more appropriate questions are proposed by referring to past conversation history. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input past conversation history into a generating AI and have the generating AI perform question optimization.

[0115] The suggestion function can estimate the user's emotions and prioritize the questions it suggests based on those emotions. For example, if the user is nervous, the suggestion function will prioritize suggesting important questions to clarify the content of the conversation. The suggestion function can also suggest detailed questions if the user is relaxed to confirm the content of the conversation in detail. The suggestion function can also prioritize suggesting concise questions if the user is in a hurry to confirm the important parts of the conversation. This allows the system to prioritize suggesting important questions by determining the priority of questions based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input user emotion data into a generating AI and have the generating AI determine the priority of questions.

[0116] The suggestion unit can adjust the content of the questions it proposes based on the geographical context of the conversation. For example, the suggestion unit can propose appropriate questions considering the geographical context of the conversation. For example, the suggestion unit can propose appropriate questions considering the geographical context of the conversation to clarify the content of the conversation. The suggestion unit can also adjust the content of the questions based on geographical information. For example, the suggestion unit can adjust the content of the questions based on geographical information to prioritize confirmation of important parts of the conversation. The suggestion unit can also propose questions related to the location of the conversation. For example, the suggestion unit can propose questions related to the location of the conversation to clarify the content of the conversation. This allows for the proposal of more appropriate questions by considering the geographical context. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or not using AI. For example, the suggestion unit can input the geographical data of the conversation into a generating AI and have the generating AI perform the question adjustments.

[0117] The suggestion unit can optimize the content of the questions it proposes based on relevant external databases. For example, the suggestion unit can refer to external databases and propose appropriate questions. For example, the suggestion unit can refer to external databases and propose appropriate questions to clarify the content of the conversation. The suggestion unit can also optimize the content of questions based on relevant databases. For example, the suggestion unit can optimize the content of questions based on relevant databases and prioritize confirming important parts of the conversation. The suggestion unit can also analyze information from external databases and propose questions. For example, the suggestion unit can analyze information from external databases, propose questions, and clarify the content of the conversation. This allows for the proposal of more appropriate questions by referring to external databases. Some or all of the above processes in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input information from external databases into a generating AI and have the generating AI perform question optimization.

[0118] The management unit can estimate the user's emotions and adjust the database management method based on the estimated user emotions. For example, if the user is nervous, the management unit can provide a concise and easy-to-understand management method, clarifying the contents of the database. The management unit can also provide a detailed management method, for example, if the user is relaxed, managing the contents of the database in detail. The management unit can also provide a concise management method, for example, if the user is in a hurry, prioritizing the management of important parts of the database. This allows for more appropriate database management by adjusting the management method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the management unit may be performed using AI, for example, or without AI. For example, the management department can input user emotion data into a generating AI and have the AI ​​adjust the management methods.

[0119] The management department can select a management method by comparing the information recorded in the database with past data. For example, the management department can select the optimal management method based on past data. For example, the management department can select the optimal management method based on past data and clarify the contents of the database. The management department can also analyze the history of the data and provide an appropriate management method. For example, the management department can analyze the history of the data, provide an appropriate management method and manage the contents of the database in detail. The management department can also select the optimal method by referring to past management methods. For example, the management department can select the optimal method by referring to past management methods and prioritize the management of important parts of the database. This allows the optimal management method to be selected by comparing it with past data. Some or all of the above processes in the management department may be performed using AI, for example, or without AI. For example, the management department can input past data into a generating AI and have the generating AI perform the selection of a management method.

[0120] The management department can adjust the information recorded in the database based on user attribute information. For example, the management department can customize the database management method based on user attribute information. For example, the management department can customize the database management method based on user attribute information and clarify the contents of the database. The management department can also adjust the management method considering the user's past usage history. For example, the management department can adjust the management method considering the user's past usage history and prioritize the management of important parts of the database. The management department can also analyze user attribute information and provide the optimal management method. For example, the management department can analyze user attribute information, provide the optimal management method and manage the contents of the database in detail. This makes it possible to manage the database more appropriately by customizing it based on user attribute information. Some or all of the above processes in the management department may be performed using AI, for example, or not using AI. For example, the management department can input user attribute information into a generating AI and have the generating AI perform the adjustment of the management method.

[0121] The management department can estimate the user's emotions and adjust the database update frequency based on the estimated emotions. For example, if the user is stressed, the management department can set a lower update frequency to clarify the database content. The management department can also set a higher update frequency if the user is relaxed to manage the database content in detail. The management department can also set a more concise update frequency if the user is in a hurry to prioritize the management of important parts of the database. This allows for more appropriate database management by adjusting the update frequency based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the management department may be performed using AI, for example, or without AI. For example, the management department can input user sentiment data into a generating AI and have the generating AI adjust the update frequency.

[0122] The management department can select a management method for the information recorded in the database based on geographical context. For example, the management department can select an appropriate management method considering geographical context. For example, the management department can select an appropriate management method considering geographical context and clarify the contents of the database. The management department can also adjust the database management method based on geographical information. For example, the management department can adjust the database management method based on geographical information and prioritize the management of important parts of the database. The management department can also analyze geographical context and provide the optimal management method. For example, the management department can analyze geographical context, provide the optimal management method, and manage the contents of the database in detail. This makes it possible to manage the database more appropriately by considering geographical context. Some or all of the above processes in the management department may be performed using AI, for example, or not using AI. For example, the management department can input geographical information into a generating AI and have the generating AI perform the selection of a management method.

[0123] The management department can manage the information recorded in the database in conjunction with related external databases. For example, the management department can manage information in conjunction with external databases. For example, the management department can manage information in conjunction with external databases and clarify the contents of the database. The management department can also adjust management methods based on related databases. For example, the management department can adjust management methods based on related databases and prioritize the management of important parts of the database. The management department can also analyze information in external databases and provide optimal management methods. For example, the management department can analyze information in external databases, provide optimal management methods, and manage the contents of the database in detail. This enables more appropriate database management by linking with external databases. Some or all of the above processes in the management department may be performed using AI, for example, or not. For example, the management department can input information from external databases into a generating AI and have the generating AI perform adjustments to the management methods.

[0124] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0125] The support system can estimate the user's emotions and adjust how the conversation is recorded based on those emotions. For example, if the user is nervous, the system can adjust to record only the most important parts of the conversation. If the user is relaxed, it can record the entire conversation in detail. Furthermore, if the user is in a hurry, it can adjust to record only the essential points. By adjusting the conversation recording method based on the user's emotions, more appropriate recordings can be made.

[0126] The support system can refer to relevant external databases based on the content of a conversation to determine the validity of the statement. For example, in a conversation about medicine, the system can refer to a medical database to verify the accuracy of the statement. Similarly, in a conversation about education, it can refer to an education database to determine the validity of the statement. Furthermore, in a conversation about technology, it can refer to a technology database to verify the accuracy of the statement. This allows for a more accurate determination of the validity of statements by referring to external databases.

[0127] The support system can estimate the user's emotions and adjust the wording of suggested questions based on those emotions. For example, if the user is nervous, the system can suggest concise and easy-to-understand questions. If the user is relaxed, it can suggest more detailed questions. Furthermore, if the user is in a hurry, it can suggest questions that get straight to the point. In this way, by adjusting the wording of questions based on the user's emotions, more appropriate questions are suggested.

[0128] The support system can search for relevant literature based on the content of a conversation and determine the validity of the statements. For example, in a conversation about medicine, the system can search for relevant medical literature to verify the accuracy of the statements. In a conversation about education, it can search for relevant educational literature to determine the validity of the statements. Furthermore, in a conversation about technology, it can search for relevant technical literature to verify the accuracy of the statements. This allows for a more accurate determination of the validity of statements by referring to relevant literature.

[0129] The support system can estimate the user's emotions and adjust how the analysis results are displayed based on those emotions. For example, if the user is nervous, the system can provide a concise and easy-to-understand display. If the user is relaxed, it can provide a more detailed display. Furthermore, if the user is in a hurry, it can provide a concise and to-the-point display. By adjusting the display method based on the user's emotions, the system provides more easily understandable analysis results.

[0130] The support system can refer to relevant geographical information based on the content of a conversation to determine the appropriateness of the statement. For example, in a conversation about local healthcare, the system can refer to local healthcare information to verify the accuracy of the statement. Similarly, in a conversation about local education, it can refer to local education information to determine the appropriateness of the statement. Furthermore, in a conversation about local technology, it can refer to local technology information to verify the accuracy of the statement. This allows for a more accurate determination of the appropriateness of statements by referring to geographical information.

[0131] The support system can estimate the user's emotions and adjust the conversation analysis criteria based on those emotions. For example, if the user is nervous, the system can provide concise and easy-to-understand analysis results. If the user is relaxed, it can provide detailed analysis results. Furthermore, if the user is in a hurry, it can provide concise analysis results. By adjusting the analysis criteria based on the user's emotions, more appropriate analysis results can be obtained.

[0132] The support system can refer to relevant social media information based on the content of a conversation to determine the appropriateness of the statement. For example, in a conversation about medicine, the system can refer to relevant social media posts to verify the accuracy of the statement. Similarly, in a conversation about education, it can refer to relevant social media posts to determine the appropriateness of the statement. Furthermore, in a conversation about technology, it can refer to relevant social media posts to verify the accuracy of the statement. This allows for a more accurate determination of the appropriateness of a statement by referring to social media information.

[0133] The support system can estimate the user's emotions and prioritize conversations based on those emotions. For example, if the user is nervous, the system can prioritize recording important conversations. If the user is relaxed, it can record all conversations evenly. Furthermore, if the user is in a hurry, it can prioritize recording only the most concise conversations. In this way, by prioritizing conversations based on the user's emotions, important conversations can be recorded preferentially.

[0134] The support system can refer to relevant past conversation history based on the content of the conversation to determine the appropriateness of the statement. For example, in the case of a medical conversation, the system can refer to past medical conversation history to verify the accuracy of the statement. Similarly, in the case of an educational conversation, it can refer to past educational conversation history to determine the appropriateness of the statement. Furthermore, in the case of a technical conversation, it can refer to past technical conversation history to verify the accuracy of the statement. This allows for a more accurate determination of the appropriateness of a statement by referring to past conversation history.

[0135] The following briefly describes the processing flow for example form 2.

[0136] Step 1: The recording unit records the conversation. The recording unit can record the conversation using methods such as audio recording, video recording, and text recording. For example, it can record the conversation using audio recording, record the conversation as video using video recording, and record the conversation as written information using text recording. Step 2: The text conversion unit converts the conversation recorded by the recording unit into text. The text conversion unit can convert audio data into text data using speech recognition technology. It can also convert conversations into text using manual input. For example, it is possible to convert audio data into text data in real time using speech recognition technology, and to convert conversations into text using manual input for later review. Step 3: The analysis unit analyzes the conversation that has been transcribed by the text conversion unit. The analysis unit can analyze the content of the conversation using natural language processing techniques and extract important information from the conversation using keyword extraction techniques. For example, it can analyze the grammatical and semantic accuracy of the conversation using natural language processing techniques and pick out particularly important information from the conversation using keyword extraction techniques. Step 4: The judgment unit determines the validity of the statements in the conversation analyzed by the analysis unit. The judgment unit can determine the validity of the statements based on fact-checking and logical consistency, verify the basis for the statements, and provide additional information as needed. For example, it can perform fact-checking, verify the accuracy of the statements, determine the validity of the statements based on logical consistency, and provide additional information as needed. Step 5: The suggestion unit proposes questions based on the results determined by the judgment unit. The suggestion unit can propose multiple questions based on the content of the conversation and questions based on the user's interests. For example, based on the content of the conversation, it can propose a question such as "Is there any data showing the effectiveness of this material?" and based on the user's interests, it can propose a question such as "What other side effects are possible?"

[0137] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0138] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0139] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0140] Each of the multiple elements described above, including the recording unit, text conversion unit, analysis unit, judgment unit, proposal unit, management unit, and emotion estimation function, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the recording unit records conversations using the camera 42 and microphone 38B of the smart device 14 and converts the audio data into text data by the control unit 46A. The text conversion unit is implemented in the specific processing unit 290 of the data processing unit 12 and converts the audio data into text data using speech recognition technology. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the content of the conversation using natural language processing technology. The judgment unit is implemented in the specific processing unit 290 of the data processing unit 12 and determines the validity of the statements. The proposal unit is implemented in the specific processing unit 290 of the data processing unit 12 and proposes questions based on the content of the conversation. The management unit records and manages information about the child's learning performance and intentions in the database 24 of the data processing unit 12. The emotion estimation function is implemented, for example, by the specific processing unit 290 of the data processing device 12, which estimates the user's emotions and adjusts the recording timing. The correspondence between each part and the device or control unit is not limited to the example described above and can be modified in various ways.

[0141] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0142] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0143] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0144] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0145] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0147] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0148] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0149] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0150] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0151] In the smart glasses 214, 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0152] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0153] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0154] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0155] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed 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 necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0156] Each of the multiple elements described above, including the recording unit, text conversion unit, analysis unit, judgment unit, proposal unit, management unit, and emotion estimation function, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the recording unit records conversations using the camera 42 and microphone 238 of the smart glasses 214 and converts the audio data into text data by the control unit 46A. The text conversion unit is implemented in the specific processing unit 290 of the data processing unit 12 and converts the audio data into text data using speech recognition technology. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the content of the conversation using natural language processing technology. The judgment unit is implemented in the specific processing unit 290 of the data processing unit 12 and determines the validity of the statements. The proposal unit is implemented in the specific processing unit 290 of the data processing unit 12 and proposes questions based on the content of the conversation. The management unit records and manages information about the child's learning performance and intentions in the database 24 of the data processing unit 12. The emotion estimation function is implemented, for example, by the specific processing unit 290 of the data processing device 12, which estimates the user's emotions and adjusts the recording timing. The correspondence between each part and the device or control unit is not limited to the example described above and can be modified in various ways.

[0157] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0158] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0159] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0160] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0161] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0162] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0163] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0164] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0165] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0166] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0167] In the headset terminal 314, 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 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0168] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0169] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0170] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0171] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0172] Each of the multiple elements described above, including the recording unit, text conversion unit, analysis unit, judgment unit, proposal unit, management unit, and emotion estimation function, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the recording unit records conversations using the camera 42 and microphone 238 of the headset terminal 314 and converts the audio data into text data by the control unit 46A. The text conversion unit is implemented in the specific processing unit 290 of the data processing unit 12 and converts the audio data into text data using speech recognition technology. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the content of the conversation using natural language processing technology. The judgment unit is implemented in the specific processing unit 290 of the data processing unit 12 and determines the validity of the statements. The proposal unit is implemented in the specific processing unit 290 of the data processing unit 12 and proposes questions based on the content of the conversation. The management unit records and manages information regarding the child's learning performance and intentions in the database 24 of the data processing unit 12. The emotion estimation function is implemented, for example, by the specific processing unit 290 of the data processing device 12, which estimates the user's emotions and adjusts the recording timing. The correspondence between each part and the device or control unit is not limited to the example described above and can be modified in various ways.

[0173] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0174] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0175] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0176] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0177] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0178] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0179] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0180] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0181] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0182] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0183] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0184] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0185] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0186] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0187] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0188] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed 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 necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0189] Each of the multiple elements described above, including the recording unit, text conversion unit, analysis unit, judgment unit, proposal unit, management unit, and emotion estimation function, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the recording unit records conversations using the camera 42 and microphone 238 of the robot 414 and converts the audio data into text data by the control unit 46A. The text conversion unit is implemented in the specific processing unit 290 of the data processing unit 12 and converts the audio data into text data using speech recognition technology. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the content of the conversation using natural language processing technology. The judgment unit is implemented in the specific processing unit 290 of the data processing unit 12 and determines the validity of the statements. The proposal unit is implemented in the specific processing unit 290 of the data processing unit 12 and proposes questions based on the content of the conversation. The management unit records and manages information regarding the child's learning performance and intentions in the database 24 of the data processing unit 12. The emotion estimation function is implemented, for example, by the specific processing unit 290 of the data processing device 12, which estimates the user's emotions and adjusts the recording timing. The correspondence between each part and the device or control unit is not limited to the example described above and can be modified in various ways.

[0190] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0191] Figure 9 shows the emotion map 400, in 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 the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0192] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0193] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0194] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0195] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it 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 emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0196] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0197] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0198] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0199] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0200] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0201] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0202] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0203] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0204] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0205] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0206] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0207] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0208] (Note 1) A recording unit for recording conversations, A text conversion unit that converts the conversation recorded by the recording unit into text, An analysis unit analyzes the conversation converted into text by the text conversion unit, A judgment unit that determines the validity of the statements in the conversation analyzed by the aforementioned analysis unit, The system comprises a proposal unit that proposes questions based on the results determined by the aforementioned determination unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Check the accuracy of key phrases in the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned proposal section is, Suggest multiple questions based on the content of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 4) The recording unit is, Record conversations in real time. The system described in Appendix 1, characterized by the features described herein. (Note 5) The text conversion unit, Convert recorded conversations into text. The system described in Appendix 1, characterized by the features described herein. (Note 6) The unit that makes the determination said, To judge the appropriateness of the statement The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned proposal section is, Speak at a time that doesn't disrupt the flow of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 8) Equipped with an administrative department, The aforementioned management department, Information regarding children's academic performance and preferences is recorded and managed in a database and used as needed. The system described in Appendix 1, characterized by the features described herein. (Note 9) The recording unit is, It estimates the user's emotions and adjusts the timing of conversation recording based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The recording unit is, Remove background noise and other sounds when recording conversations. The system described in Appendix 1, characterized by the features described herein. (Note 11) The recording unit is, When recording a conversation, highlight specific keywords when they appear. The system described in Appendix 1, characterized by the features described herein. (Note 12) The recording unit is, It estimates the user's emotions and determines the priority of conversations to record based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The recording unit is, When recording conversations, the system prioritizes recording conversations that are highly relevant based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 14) The recording unit is, When recording conversations, the system analyzes the user's social media activity and records relevant conversations. The system described in Appendix 1, characterized by the features described herein. (Note 15) The text conversion unit, It estimates the user's emotions and adjusts the textual expression based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The text conversion unit, During the text conversion process, technical terms and abbreviations are interpreted and converted into more concrete expressions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The text conversion unit, When transcribing, punctuation is inserted based on the context of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 18) The text conversion unit, It estimates the user's emotions and adjusts the length of the text based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The text conversion unit, When transcribing, the order in which conversations are transcribed is determined based on their importance. The system described in Appendix 1, characterized by the features described herein. (Note 20) The text conversion unit, When transcribing, the order of transcription is determined based on the relevance of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned analysis unit, We estimate the user's emotions and adjust the analysis criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned analysis unit, During analysis, the accuracy of the analysis is improved based on the relationships between conversations. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned analysis unit, During analysis, the analysis is performed based on the attribute information of the speakers in the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned analysis unit, It estimates the user's emotions and adjusts the display order of the analysis results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned analysis unit, During the analysis, the analysis will be based on the geographical distribution of the conversations. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned analysis unit, During analysis, we improve the accuracy of the analysis based on relevant literature related to the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 27) The unit that makes the determination said, The system estimates the user's emotions and adjusts the criteria for judging the appropriateness of statements based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The unit that makes the determination said, When judging the validity of a statement, we improve the accuracy of the judgment by using data on similar past statements. The system described in Appendix 1, characterized by the features described herein. (Note 29) The unit that makes the determination said, When judging the validity of a statement, the judgment is based on the speaker's level of expertise. The system described in Appendix 1, characterized by the features described herein. (Note 30) The unit that makes the determination said, The system estimates the user's emotions and adjusts how the appropriateness of a statement is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The unit that makes the determination said, When judging the appropriateness of a statement, the context of the conversation is used to determine the priority of the judgment. The system described in Appendix 1, characterized by the features described herein. (Note 32) The unit that makes the determination said, When judging the validity of a statement, we improve the accuracy of the judgment by using relevant external databases. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned proposal section is, We estimate the user's emotions and adjust the wording of the questions we suggest based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned proposal section is, The content of the proposed questions will be updated according to the progress of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned proposal section is, The content of the suggested questions is optimized based on past conversation history. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned proposal section is, It estimates the user's emotions and determines the priority of suggested questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned proposal section is, Adjust the content of the proposed questions based on the geographical context of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned proposal section is, The content of the proposed questions will be optimized based on relevant external databases. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned management department, It estimates user sentiment and adjusts how the database is managed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned management department, The information recorded in the database is compared with past data to select a management method. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned management department, The information recorded in the database is adjusted based on the user's attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned management department, The system estimates user sentiment and adjusts the database update frequency based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 43) The aforementioned management department, The management method for the information recorded in the database is selected based on its geographical context. The system described in Appendix 1, characterized by the features described herein. (Note 44) The aforementioned management department, The information recorded in the database is managed in conjunction with related external databases. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0209] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A recording unit for recording conversations, A text conversion unit that converts the conversation recorded by the recording unit into text, An analysis unit analyzes the conversation that has been converted into text by the text conversion unit, A judgment unit that determines the validity of the statements in the conversation analyzed by the aforementioned analysis unit, The system comprises a proposal unit that proposes questions based on the results determined by the aforementioned determination unit. A system characterized by the following features.

2. The aforementioned analysis unit, Check the accuracy of key phrases in the conversation. The system according to feature 1.

3. The aforementioned proposal section is, Suggest multiple questions based on the content of the conversation. The system according to feature 1.

4. The aforementioned recording unit is Record conversations in real time. The system according to feature 1.

5. The text conversion unit, Convert recorded conversations into text. The system according to feature 1.

6. The unit that makes the determination said, To judge the appropriateness of the statement The system according to feature 1.

7. The aforementioned proposal section is, Speak at a time that doesn't disrupt the flow of the conversation. The system according to feature 1.

8. Equipped with an administrative department, The aforementioned management department, Information regarding children's academic performance and preferences is recorded and managed in a database and used as needed. The system according to feature 1.

9. The aforementioned recording unit is It estimates the user's emotions and adjusts the timing of conversation recording based on the estimated emotions. The system according to feature 1.

Images