System

Abstract

An object of a system according to an embodiment is to lower a hurdle for acquiring knowledge in a new field.SOLUTION: A system includes a reception part, an analysis part, and a follow-up part. The reception unit receives a question from a user. The analysis unit analyzes the question received by the reception unit and provides related information. The follow-up unit checks the understanding level of the user based on the information provided by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional techniques require joining online communities and forums to gain knowledge in new fields, which can be a hurdle.

[0005] The system according to the embodiment aims to lower the barrier to acquiring knowledge in a new field. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, and a follow-up unit. The reception unit receives questions from users. The analysis unit analyzes the questions received by the reception unit and provides related information. The follow-up unit checks the user's level of understanding based on the information provided by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can lower the barrier to acquiring knowledge in a new field. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) A knowledge acquisition support system according to an embodiment of the present invention allows a user to input questions or concerns about a new field into a generation AI, which then provides relevant information and confirms the user's level of understanding. In this knowledge acquisition support system, a user inputs a question about a new field, and the generation AI analyzes the question and provides relevant information. For example, when a user asks, "What is the basic knowledge in this field?", the generation AI provides an answer that explains the overview and key concepts of the field. Furthermore, in the knowledge acquisition support system, the generation AI asks follow-up questions to confirm the user's level of understanding. For example, the generation AI confirms the user's level of understanding through questions such as, "Did you understand this explanation?" or "Is there anything else you would like to know?" and provides additional information as needed. This allows the knowledge acquisition support system to efficiently acquire knowledge in a new field. Furthermore, through dialogue with the generation AI, users can obtain specific advice and know-how that will be useful in their actual work. For example, the generation AI can provide instructions, precautions, and success stories for specific tasks, allowing users to acquire practical knowledge. In this way, the knowledge acquisition support system lowers the barriers to entry into new fields and is an effective means for efficiently acquiring knowledge. This allows the knowledge acquisition support system to help users efficiently acquire knowledge in new fields and obtain specific advice and know-how that will be useful in their actual work. For example, the system can improve the effectiveness of users' learning by quickly and accurately analyzing questions written by users and providing related information.

[0029] A knowledge acquisition support system according to an embodiment includes a reception unit, an analysis unit, and a follow-up unit. The reception unit receives questions from users. Questions from users include, but are not limited to, text, audio, technical, and general questions. The reception unit receives, for example, text questions. The reception unit can also receive audio questions. The reception unit can also receive technical and general questions. For example, the reception unit analyzes text entered by a user and accepts the question. Audio questions are converted into text using speech recognition technology and accepted as questions. The analysis unit uses a generation AI to analyze the question and provide related information. The analysis is performed using, for example, natural language processing technology or a machine learning algorithm, but is not limited to, these examples. For example, the analysis unit allows the generation AI to analyze the question and provide related information. The analysis unit can also cause the generation AI to refer to a large amount of databases and literature to generate an optimal answer. The analysis unit can also cause the generation AI to refer to reliable academic papers, specialized books, official industry guidelines, etc. For example, the analysis unit causes the generation AI to refer to an academic database and generate an answer to a question. The follow-up unit uses the generation AI to check the user's level of understanding based on the information provided by the analysis unit. The check of understanding may be performed, for example, in the form of a quiz or feedback, but is not limited to these examples. For example, the follow-up unit causes the generation AI to ask a follow-up question to the user to check the user's level of understanding. The follow-up unit may also cause the generation AI to provide additional information based on the user's level of understanding. Furthermore, the follow-up unit may also incorporate a mechanism for the generation AI to learn and improve based on user feedback. For example, the follow-up unit causes the generation AI to analyze user feedback and improve the accuracy of the system. This allows the knowledge acquisition support system according to the embodiment to efficiently accept, analyze, and follow up on user questions. Some or all of the above-described processing in the follow-up unit may be performed, for example, using AI or without AI.For example, the follow-up unit can input user feedback into the generation AI and have the generation AI implement improvements to the system.

[0030] The analysis unit can refer to multiple databases and literature to generate an optimal answer to a user's question. Examples of multiple databases and literature include, but are not limited to, academic databases and official industry guidelines. For example, the analysis unit can refer to academic databases to generate an answer to a user's question. The analysis unit can also refer to official industry guidelines to generate an answer to a user's question. Furthermore, the analysis unit can refer to reliable academic papers and specialized books to generate an answer to a user's question. For example, the analysis unit can refer to peer-reviewed papers to generate an answer to a user's question. This allows the analysis unit to provide an optimal answer to a user's question by referring to a large number of databases and literature. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input information from databases and literature into a generation AI and cause the generation AI to generate an optimal answer.

[0031] The follow-up unit can ask follow-up questions to confirm the user's level of understanding. Examples of follow-up questions include, but are not limited to, multiple-choice questions and open-ended questions. For example, the follow-up unit can ask multiple-choice questions to confirm the user's level of understanding. The follow-up unit can also ask open-ended questions to confirm the user's level of understanding. Furthermore, the follow-up unit can ask quiz-style questions to confirm the user's level of understanding. For example, the follow-up unit has the generation AI ask multiple-choice follow-up questions to the user to confirm the user's level of understanding. Open-ended follow-up questions are in a format where the user can freely write their answers, and the generation AI analyzes the answers to confirm the user's level of understanding. Quiz-style follow-up questions are in a format where the user answers a quiz, and the generation AI analyzes the answers to confirm the user's level of understanding. In this way, the follow-up unit can deepen the user's understanding by asking follow-up questions to confirm the user's level of understanding. Some or all of the above-described processing in the follow-up unit may be performed, for example, using AI or without AI. For example, the follow-up unit can input the user's response data into the generation AI and have the generation AI check the user's level of understanding.

[0032] The follow-up unit can provide additional information according to the user's level of understanding. Examples of additional information include, but are not limited to, detailed explanations and related links. For example, the follow-up unit can provide detailed explanations to deepen the user's understanding. The follow-up unit can also provide related links to allow the user to obtain further information. Furthermore, the follow-up unit can provide specific examples and success stories to deepen the user's understanding. For example, the follow-up unit allows the generation AI to provide detailed explanations to the user to deepen their understanding. The related links are in a format that the user can click to obtain further information, and the generation AI provides the links. The specific examples and success stories are in a format that the user can use to obtain information useful for actual work, and the generation AI provides the information. This allows the follow-up unit to further deepen the user's understanding by providing additional information according to the user's level of understanding. Some or all of the above-described processing in the follow-up unit may be performed using AI, for example, or may be performed without using AI. For example, the follow-up unit can input the user's level of understanding data into the generation AI and cause the generation AI to provide additional information.

[0033] The analysis unit may refer to academic papers, specialized books, official industry guidelines, etc., whose reliability has been confirmed. Information sources whose reliability has been confirmed include, but are not limited to, peer-reviewed papers and official certifications. For example, the analysis unit may refer to peer-reviewed papers to generate answers to user questions. The analysis unit may also refer to official certifications to generate answers to user questions. Furthermore, the analysis unit may refer to official industry guidelines to generate answers to user questions. For example, the analysis unit may have a generation AI refer to peer-reviewed papers to generate answers to user questions. Official certifications are certified as reliable information sources, and the generation AI references the information. Official industry guidelines are certified as industry standards, and the generation AI references the information. By doing so, the analysis unit can increase the reliability of the information provided to the user by referring to reliable information sources. Some or all of the above-described processing by the analysis unit may be performed using AI, for example, or may be performed without AI. For example, the analysis unit may input information sources whose reliability has been confirmed into the generation AI and cause the generation AI to generate an optimal answer.

[0034] The follow-up unit can incorporate a mechanism for the generation AI to learn and improve based on user feedback. Examples of the generation AI include, but are not limited to, deep learning models and reinforcement learning models. The follow-up unit can, for example, use a deep learning model to learn and improve based on user feedback. The follow-up unit can also use a reinforcement learning model to learn and improve based on user feedback. Furthermore, the follow-up unit can have the generation AI analyze user feedback to improve the accuracy of the system. For example, in the follow-up unit, the generation AI inputs user feedback into a deep learning model to learn and improve. A reinforcement learning model is a model that learns optimal behavior based on user feedback, and the generation AI uses that model to learn and improve. The generation AI analyzes user feedback and uses it as data to improve the accuracy of the system. In this way, the follow-up unit can improve the accuracy of the system by having the generation AI learn and improve based on user feedback. Some or all of the above-described processing in the follow-up unit can be performed, for example, using AI or without AI. For example, the follow-up unit can input user feedback data into the generation AI and have the generation AI learn and improve.

[0035] The analysis unit can periodically update the database to reflect the latest information. Periodically includes, but is not limited to, daily, weekly, monthly, etc. The analysis unit can, for example, update the database daily to reflect the latest information. The analysis unit can also update the database weekly to reflect the latest information. The analysis unit can also update the database monthly to reflect the latest information. For example, the analysis unit has the generation AI update the database daily to reflect the latest information. A weekly update is a format in which the generation AI updates the database weekly to reflect the latest information, and a monthly update is a format in which the generation AI updates the database monthly to reflect the latest information. In this way, the analysis unit can always provide the latest information by periodically updating the database. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can have the generation AI update the database.

[0036] The reception unit can analyze the user's past question history and select the optimal reception method. Optimal reception methods include, but are not limited to, chatbots and telephone support. For example, the reception unit prioritizes reception of topics that the user has frequently asked about in the past. The reception unit can also prioritize suggesting question formats (text, voice, etc.) that the user has used in the past. Furthermore, the reception unit can also suggest the optimal reception method for a specific time period based on the user's past question history. For example, the reception unit uses a generation AI to analyze the user's past question history and select the optimal reception method. A chatbot is a format in which the user inputs questions in text format, and the generation AI accepts the questions. A telephone support is a format in which the user inputs questions in voice format, and the generation AI accepts the questions. This allows the reception unit to select the optimal reception method by analyzing the user's past question history. Some or all of the above-described processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the user's question history data into the generation AI and have the generation AI select the optimal reception method.

[0037] When receiving a question, the reception unit can filter the questions based on the user's current areas of interest or projects. Examples of filtering include, but are not limited to, keyword matching and category classification. For example, the reception unit may preferentially receive questions related to a project the user is currently working on. The reception unit may also filter and receive related questions based on the user's areas of interest. Furthermore, the reception unit may suggest appropriate questions based on the user's project progress. For example, the reception unit may have a generation AI analyze the user's areas of interest and filter related questions. Keyword matching is a method of matching the user's input content with related keywords, and the generation AI performs the filtering. Category classification is a method of classifying the user's input content into specific categories, and the generation AI performs the filtering. This allows the reception unit to filter questions based on the user's current areas of interest or projects, thereby preferentially receiving highly relevant questions. Some or all of the above-described processing in the reception unit may be performed using AI, for example, or may be performed without AI. For example, the reception unit may input the user's area of ​​interest data into the generation AI and have the generation AI perform question filtering.

[0038] When receiving a question, the reception unit can select the optimal reception means depending on the user's input method. Examples of input methods include, but are not limited to, voice input, text input, and image input. For example, when a user inputs a question by voice, the reception unit uses voice recognition technology to receive the question. Furthermore, when a user inputs a question by text, the reception unit can also use text analysis technology to receive the question. Furthermore, when a user inputs a question using an image, the reception unit can also use image analysis technology to receive the question. For example, the reception unit converts the user's voice into text using voice recognition technology and receives the question. Text analysis technology analyzes the text entered by the user and accepts it as a question, and the generation AI performs the analysis. Image analysis technology analyzes the image entered by the user and accepts it as a question, and the generation AI performs the analysis. This allows the reception unit to select the optimal reception means depending on the user's input method, thereby smoothly receiving questions. Some or all of the above-described processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input user input data to the generation AI and cause the generation AI to select the optimal reception means.

[0039] When accepting questions, the reception unit can prioritize relevant questions by taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and IP addresses. For example, if the user is in a specific area, the reception unit can prioritize questions related to that area. Furthermore, if the user is traveling, the reception unit can prioritize questions related to the travel destination. Furthermore, if the user is participating in a specific event, the reception unit can prioritize questions related to the event. For example, in the reception unit, the generation AI analyzes the user's geographical location information and filters relevant questions. GPS data is data for identifying the user's current location, and the generation AI analyzes that data. IP address is data for identifying the user's Internet connection destination, and the generation AI analyzes that data. In this way, the reception unit can prioritize relevant questions by taking into account the user's geographical location information. Some or all of the above-described processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's geographical location data into the generation AI and have the generation AI perform question filtering.

[0040] When receiving a question, the reception unit can analyze the user's social media activity and receive related questions. Social media activity includes, but is not limited to, analysis of post content and follower analysis. For example, the reception unit preferentially receives questions related to topics in which the user has shown interest on social media. The reception unit can also analyze the user's social media posts and receive related questions. Furthermore, the reception unit can also receive related questions based on the activities of the user's friends on social media. For example, the reception unit uses a generation AI to analyze the user's social media activity and filter related questions. The analysis of post content involves analyzing content posted by the user on social media, and the generation AI performs this analysis. The analysis of followers involves analyzing the activities of the user's followers, and the generation AI performs this analysis. As a result, the reception unit can analyze the user's social media activity and preferentially receive highly relevant questions. Some or all of the above-described processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit can input the user's social media data into the generation AI and have the generation AI perform question filtering.

[0041] When receiving a question, the reception unit can customize the reception method by reflecting the user's past feedback. Examples of feedback include, but are not limited to, questionnaires and user reviews. The reception unit, for example, suggests an optimal reception method based on feedback provided by the user in the past. The reception unit can also preferentially receive specific question formats based on the user's past feedback. Furthermore, the reception unit can continuously improve the reception method by reflecting the user's feedback. For example, the reception unit uses a generation AI to analyze the user's past feedback and select an optimal reception method. A questionnaire is a format in which the user answers questions, and the generation AI analyzes the answers. A user review is a format in which reviews provided by the user are analyzed, and the generation AI performs the analysis. This allows the reception unit to provide an optimal reception method by reflecting the user's past feedback. Some or all of the above-described processing in the reception unit may be performed using, or without, an AI. For example, the reception unit can input user feedback data into the generation AI and have the generation AI customize the reception method.

[0042] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the question. The importance of the question includes, but is not limited to, the user's urgency and the question's impact. For example, the analysis unit allows the generation AI to provide detailed analysis results for questions with high importance. The analysis unit can also allow the generation AI to provide concise analysis results for questions with low importance. Furthermore, the analysis unit allows the generation AI to adjust the priority of the analysis based on the question's importance. For example, the analysis unit allows the generation AI to analyze the importance of the user's question and adjust the level of detail. The user's urgency is a criterion for evaluating the urgency of the question, and the generation AI uses this criterion to adjust the level of detail of the analysis. The question's impact is a criterion for evaluating the impact the question has on the user, and the generation AI uses this criterion to adjust the level of detail of the analysis. In this way, the analysis unit can provide detailed analysis results for important questions by adjusting the level of detail of the analysis based on the question's importance. Some or all of the above-described processing in the analysis unit may be performed, for example, using AI or without AI. For example, the analysis unit can input user question data into the generation AI and have the generation AI adjust the level of detail of the analysis.

[0043] During analysis, the analysis unit can apply different analysis algorithms depending on the question category. Examples of analysis algorithms include, but are not limited to, natural language processing algorithms and machine learning algorithms. For example, in the analysis unit, the generation AI applies a specialized analysis algorithm to technical questions. Furthermore, the analysis unit can also apply a business-oriented analysis algorithm to business-related questions. Furthermore, the analysis unit can also apply an analysis algorithm based on academic papers to academic questions. For example, the analysis unit applies a specialized natural language processing algorithm to technical questions. For business-related questions, the generation AI applies a business-oriented machine learning algorithm to perform analysis. For academic questions, the generation AI applies an analysis algorithm based on academic papers to perform analysis. This allows the analysis unit to provide more appropriate analysis results by applying different analysis algorithms depending on the question category. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user question data into the generation AI and have the generation AI apply the analysis algorithm.

[0044] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. Past analysis results include, but are not limited to, database references and analysis of historical data. For example, the analysis unit allows the generation AI to improve the accuracy of the analysis based on analysis results previously received by the user. The analysis unit can also extract specific patterns from the user's past analysis results and reflect them in the analysis. Furthermore, the analysis unit can analyze the user's past analysis results so that the generation AI can continuously learn and improve. For example, the analysis unit allows the generation AI to refer to a database of the user's past analysis results to improve the accuracy of the analysis. Analysis of historical data involves analyzing the user's past analysis results, and the generation AI performs the analysis. Extraction of specific patterns involves finding common patterns from the user's past analysis results, and the generation AI performs the extraction. In this way, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or without AI. For example, the analysis unit can input the user's past analysis result data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0045] During analysis, the analysis unit can determine the analysis priority based on the time of question submission. The submission time includes, but is not limited to, a record of the submission date and time, a timestamp, etc. For example, the analysis unit allows the generation AI to determine the analysis priority based on the time of day when the question was submitted. The analysis unit can also allow the generation AI to adjust the analysis schedule according to the time of question submission. Furthermore, the analysis unit can also allow the generation AI to optimally allocate analysis resources based on the time of question submission. For example, the analysis unit allows the generation AI to analyze the time of question submission and determine the priority. The submission date and time record is a record of the date and time when the question was submitted, and the generation AI analyzes the record. The timestamp is a record of the time when the question was submitted, and the generation AI analyzes the timestamp. This allows the analysis unit to determine the analysis priority based on the time of question submission, thereby providing analysis results at an appropriate time. Some or all of the above-described processing in the analysis unit may be performed, for example, using AI or without AI. For example, the analysis unit can input data on the time of question submission into the generation AI and have the generation AI determine the priority of the analysis.

[0046] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the questions. Relevance includes, but is not limited to, keyword similarity and topic similarity. For example, the analysis unit allows the generation AI to determine the order of analysis based on the relevance of the questions. The analysis unit can also allow the generation AI to adjust the analysis priority according to the relevance of the questions. Furthermore, the analysis unit can also allow the generation AI to optimally allocate analysis resources based on the relevance of the questions. For example, the analysis unit allows the generation AI to analyze the relevance of questions and adjust the order. Keyword similarity is a criterion for evaluating the degree of match between keywords related to a question, and the generation AI uses this criterion to adjust the order of analysis. Topic similarity is a criterion for evaluating the similarity between topics related to a question, and the generation AI uses this criterion to adjust the order of analysis. Thus, by adjusting the order of analysis based on the relevance of the questions, the analysis unit can prioritize the analysis of highly relevant questions. Some or all of the above-described processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input question relevance data to the generation AI and have the generation AI adjust the order of analysis.

[0047] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. Examples of technical terms include, but are not limited to, the user's occupation and past question content. For example, if the user is a beginner, the analysis unit can have the generation AI provide analysis results that avoid technical terms. For example, if the user is an intermediate user, the analysis unit can have the generation AI provide analysis results using appropriate technical terms. For example, if the user is an advanced user, the analysis unit can have the generation AI use more technical terms to provide detailed analysis results. For example, the analysis unit can have the generation AI analyze the user's occupation and estimate the user's level of expertise. The past question content is in the form of an analysis of the content of questions the user has previously asked, and the generation AI analyzes that content. This allows the analysis unit to adjust the use of technical terms in the analysis according to the user's level of expertise, thereby providing analysis results that are easier to understand. Some or all of the above-described processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input the user's level of expertise data into the generation AI and have the generation AI use technical terms.

[0048] During follow-up, the follow-up unit can analyze the user's past level of understanding and select the optimal follow-up method. Examples of past level of understanding include, but are not limited to, past test results and feedback content. For example, the follow-up unit allows the generation AI to perform detailed follow-up on topics that the user did not understand in the past. The follow-up unit can also allow the generation AI to suggest appropriate follow-up questions based on the user's past level of understanding. Furthermore, the follow-up unit can analyze the user's past level of understanding so that the generation AI can continuously learn and improve. For example, the follow-up unit allows the generation AI to analyze the user's past test results and select the optimal follow-up method. The feedback content is in the form of an analysis of feedback provided by the user in the past, and the generation AI analyzes that content. This allows the follow-up unit to analyze the user's past level of understanding and provide the optimal follow-up method. Some or all of the above-described processing in the follow-up unit may be performed using, for example, AI, or may be performed without AI. For example, the follow-up unit can input the user's past level of understanding data into the generation AI and have the generation AI select a follow-up method.

[0049] The follow-up unit can customize the follow-up method based on the user's current level of understanding during follow-up. Examples of the current level of understanding include, but are not limited to, real-time quiz results and immediate feedback. For example, if the user understands the current topic, the follow-up unit performs a follow-up in which the generation AI proceeds to the next step. Furthermore, if the user does not understand the current topic, the follow-up unit can perform a follow-up including a detailed explanation. Furthermore, the follow-up unit can suggest an appropriate follow-up method based on the user's current level of understanding. For example, the follow-up unit analyzes real-time quiz results and customizes the follow-up method. Immediate feedback is a form of providing feedback immediately after the user answers a question, and the generation AI provides that feedback. This allows the follow-up unit to customize the follow-up method based on the user's current level of understanding, thereby providing a more appropriate follow-up. Some or all of the above-described processing in the follow-up unit may be performed using, or without, an AI. For example, the follow-up unit can input the user's current level of understanding data into the generation AI and have the generation AI customize the follow-up method.

[0050] The follow-up unit can improve the follow-up method by reflecting user feedback during follow-up. Examples of follow-up methods include, but are not limited to, adjustments based on user feedback. For example, the follow-up unit causes the generation AI to improve the follow-up method based on feedback provided by the user. The follow-up unit can also preferentially suggest specific follow-up methods based on user feedback. Furthermore, the follow-up unit can continuously improve the follow-up method by reflecting user feedback. For example, the follow-up unit causes the generation AI to analyze user feedback and improve the follow-up method. User feedback is often provided in the form of a questionnaire or review, and the generation AI analyzes that feedback. This allows the follow-up unit to continuously improve the follow-up method by reflecting user feedback. Some or all of the above-described processing in the follow-up unit may be performed using AI, for example, or without AI. For example, the follow-up unit can input user feedback data into the generation AI and cause the generation AI to improve the follow-up method.

[0051] The follow-up unit can select the optimal follow-up method by taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and IP addresses. For example, if the user is in a specific area, the follow-up unit can provide information related to that area. Furthermore, if the user is traveling, the follow-up unit can also provide information related to the travel destination. Furthermore, if the user is participating in a specific event, the follow-up unit can also provide information related to the event. For example, the follow-up unit uses a generation AI to analyze the user's geographical location information and provide relevant information. GPS data is data for identifying the user's current location, and the generation AI analyzes that data. An IP address is data for identifying the user's Internet connection destination, and the generation AI analyzes that data. This allows the follow-up unit to provide highly relevant follow-up by taking the user's geographical location information into account. Some or all of the above-described processing in the follow-up unit may be performed, for example, using AI, or may be performed without using AI. For example, the follow-up unit can input the user's geographical location data into the generation AI and have the generation AI select a follow-up method.

[0052] The follow-up unit can analyze the user's social media activity during follow-up and suggest follow-up methods. Examples of social media activity include, but are not limited to, analysis of posted content and follower analysis. For example, the follow-up unit performs follow-up related to topics in which the user has shown interest on social media. The follow-up unit can also analyze the content of the user's social media posts and perform related follow-up. Furthermore, the follow-up unit can also perform related follow-up based on the activities of the user's friends on social media. For example, the follow-up unit analyzes the user's social media activity using a generation AI to suggest related follow-up. The analysis of posted content involves analyzing content posted by the user on social media, and the generation AI performs this analysis. The analysis of followers involves analyzing the activities of the user's followers, and the generation AI performs this analysis. This allows the follow-up unit to provide highly relevant follow-up by analyzing the user's social media activity. Some or all of the above-described processing in the follow-up unit may be performed using, for example, AI, or may be performed without using AI. For example, the follow-up unit can input the user's social media data into the generation AI and have the generation AI execute suggestions for follow-up measures.

[0053] The follow-up unit can customize the follow-up method by reflecting the user's past feedback during follow-up. Examples of past feedback include, but are not limited to, questionnaires and user reviews. The follow-up unit can, for example, suggest an optimal follow-up method based on feedback previously provided by the user. The follow-up unit can also prioritize specific follow-up methods based on the user's past feedback. Furthermore, the follow-up unit can continuously improve the follow-up method by reflecting the user's feedback. For example, the follow-up unit uses a generation AI to analyze the user's past feedback and select an optimal follow-up method. A questionnaire is a format in which the user answers questions, and the generation AI analyzes the answers. A user review is a format in which the user analyzes reviews provided by the user, and the generation AI performs the analysis. This allows the follow-up unit to provide an optimal follow-up method by reflecting the user's past feedback. Some or all of the above-described processing in the follow-up unit may be performed, for example, using AI or without AI. For example, the follow-up unit can input user feedback data into the generation AI and cause the generation AI to customize the follow-up method.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The reception unit can analyze the user's past question history and select the optimal reception method. For example, it can prioritize reception of topics that the user has frequently asked about in the past. The reception unit can also prioritize suggesting question formats (text, voice, etc.) that the user has used in the past. Furthermore, the reception unit can also suggest the optimal reception method for a specific time period based on the user's past question history. In this way, the reception unit can select the optimal reception method by analyzing the user's past question history.

[0056] The analysis unit can adjust the use of technical terminology in the analysis according to the user's level of expertise. For example, if the user is a beginner, the generation AI can provide analysis results that avoid technical terminology. If the user is an intermediate user, the generation AI can provide analysis results using appropriate technical terminology. Furthermore, if the user is an advanced user, the generation AI can provide detailed analysis results using a lot of technical terminology. In this way, the analysis unit can provide analysis results that are easier to understand by adjusting the use of technical terminology in the analysis according to the user's level of expertise.

[0057] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the question. For example, the generation AI can provide detailed analysis results for questions with high importance. The generation AI can also provide concise analysis results for questions with low importance. Furthermore, the analysis unit can have the generation AI adjust the priority of the analysis according to the importance of the question. As a result, the analysis unit can provide detailed analysis results for important questions by adjusting the level of detail of the analysis based on the importance of the question.

[0058] When following up, the follow-up unit can analyze the user's past level of understanding and select the optimal follow-up method. For example, the generation AI can provide detailed follow-up on topics that the user was unable to understand in the past. The follow-up unit can also suggest appropriate follow-up questions based on the user's past level of understanding. Furthermore, the follow-up unit can analyze the user's past level of understanding, allowing the generation AI to continuously learn and improve. This allows the follow-up unit to provide the optimal follow-up method by analyzing the user's past level of understanding.

[0059] During analysis, the analysis unit can apply different analysis algorithms depending on the question category. For example, for technical questions, the generation AI can apply a specialized analysis algorithm. For business-related questions, the generation AI can also apply a business-oriented analysis algorithm. Furthermore, for academic questions, the generation AI can apply an analysis algorithm based on academic papers. In this way, the analysis unit can provide more appropriate analysis results by applying different analysis algorithms depending on the question category.

[0060] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the generation AI improves the accuracy of the analysis based on the analysis results the user received in the past. The analysis unit can also extract specific patterns from the user's past analysis results and reflect them in the analysis. Furthermore, the analysis unit can analyze the user's past analysis results, allowing the generation AI to continuously learn and improve. In this way, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results.

[0061] The processing flow of the first embodiment will be briefly explained below.

[0062] Step 1: The reception unit receives questions from users. Questions from users may be in text format, voice format, technical questions, general questions, etc. For example, the reception unit analyzes text entered by the user and accepts it as a question. Voice-format questions are converted into text using voice recognition technology and accepted as questions. Step 2: The analysis unit uses the generation AI to analyze the question received by the reception unit and provide relevant information. The analysis is carried out using natural language processing technology and machine learning algorithms. For example, the generation AI may refer to a large amount of databases and literature to generate the optimal answer. It may also refer to reliable academic papers, specialist books, official industry guidelines, etc. Step 3: The follow-up unit uses the generation AI to check the user's level of understanding based on the information provided by the analysis unit. The check of understanding is done in the form of a quiz or feedback. For example, the generation AI may ask the user follow-up questions to check the user's level of understanding. It may also provide additional information depending on the user's level of understanding. Furthermore, it may also introduce a mechanism for learning and improving based on user feedback.

[0063] (Example 2) A knowledge acquisition support system according to an embodiment of the present invention allows a user to input questions or concerns about a new field into a generation AI, which then provides relevant information and confirms the user's level of understanding. In this knowledge acquisition support system, a user inputs a question about a new field, and the generation AI analyzes the question and provides relevant information. For example, when a user asks, "What is the basic knowledge in this field?", the generation AI provides an answer that explains the overview and key concepts of the field. Furthermore, in the knowledge acquisition support system, the generation AI asks follow-up questions to confirm the user's level of understanding. For example, the generation AI confirms the user's level of understanding through questions such as, "Did you understand this explanation?" or "Is there anything else you would like to know?" and provides additional information as needed. This allows the knowledge acquisition support system to efficiently acquire knowledge in a new field. Furthermore, through dialogue with the generation AI, users can obtain specific advice and know-how that will be useful in their actual work. For example, the generation AI can provide instructions, precautions, and success stories for specific tasks, allowing users to acquire practical knowledge. In this way, the knowledge acquisition support system lowers the barriers to entry into new fields and is an effective means for efficiently acquiring knowledge. This allows the knowledge acquisition support system to help users efficiently acquire knowledge in new fields and obtain specific advice and know-how that will be useful in their actual work. For example, the system can improve the effectiveness of users' learning by quickly and accurately analyzing questions written by users and providing related information.

[0064] A knowledge acquisition support system according to an embodiment includes a reception unit, an analysis unit, and a follow-up unit. The reception unit receives questions from users. Questions from users include, but are not limited to, text, audio, technical, and general questions. The reception unit receives, for example, text questions. The reception unit can also receive audio questions. The reception unit can also receive technical and general questions. For example, the reception unit analyzes text entered by a user and accepts the question. Audio questions are converted into text using speech recognition technology and accepted as questions. The analysis unit uses a generation AI to analyze the question and provide related information. The analysis is performed using, for example, natural language processing technology or a machine learning algorithm, but is not limited to, these examples. For example, the analysis unit allows the generation AI to analyze the question and provide related information. The analysis unit can also cause the generation AI to refer to a large amount of databases and literature to generate an optimal answer. The analysis unit can also cause the generation AI to refer to reliable academic papers, specialized books, official industry guidelines, etc. For example, the analysis unit causes the generation AI to refer to an academic database and generate an answer to a question. The follow-up unit uses the generation AI to check the user's level of understanding based on the information provided by the analysis unit. The check of understanding may be performed, for example, in the form of a quiz or feedback, but is not limited to these examples. For example, the follow-up unit causes the generation AI to ask a follow-up question to the user to check the user's level of understanding. The follow-up unit may also cause the generation AI to provide additional information based on the user's level of understanding. Furthermore, the follow-up unit may also incorporate a mechanism for the generation AI to learn and improve based on user feedback. For example, the follow-up unit causes the generation AI to analyze user feedback and improve the accuracy of the system. This allows the knowledge acquisition support system according to the embodiment to efficiently accept, analyze, and follow up on user questions. Some or all of the above-described processing in the follow-up unit may be performed, for example, using AI or without AI.For example, the follow-up unit can input user feedback into the generation AI and have the generation AI implement improvements to the system.

[0065] The analysis unit can refer to multiple databases and literature to generate an optimal answer to a user's question. Examples of multiple databases and literature include, but are not limited to, academic databases and official industry guidelines. For example, the analysis unit can refer to academic databases to generate an answer to a user's question. The analysis unit can also refer to official industry guidelines to generate an answer to a user's question. Furthermore, the analysis unit can refer to reliable academic papers and specialized books to generate an answer to a user's question. For example, the analysis unit can refer to peer-reviewed papers to generate an answer to a user's question. This allows the analysis unit to provide an optimal answer to a user's question by referring to a large number of databases and literature. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input information from databases and literature into a generation AI and cause the generation AI to generate an optimal answer.

[0066] The follow-up unit can ask follow-up questions to confirm the user's level of understanding. Examples of follow-up questions include, but are not limited to, multiple-choice questions and open-ended questions. For example, the follow-up unit can ask multiple-choice questions to confirm the user's level of understanding. The follow-up unit can also ask open-ended questions to confirm the user's level of understanding. Furthermore, the follow-up unit can ask quiz-style questions to confirm the user's level of understanding. For example, the follow-up unit has the generation AI ask multiple-choice follow-up questions to the user to confirm the user's level of understanding. Open-ended follow-up questions are in a format where the user can freely write their answers, and the generation AI analyzes the answers to confirm the user's level of understanding. Quiz-style follow-up questions are in a format where the user answers a quiz, and the generation AI analyzes the answers to confirm the user's level of understanding. In this way, the follow-up unit can deepen the user's understanding by asking follow-up questions to confirm the user's level of understanding. Some or all of the above-described processing in the follow-up unit may be performed, for example, using AI or without AI. For example, the follow-up unit can input the user's response data into the generation AI and have the generation AI check the user's level of understanding.

[0067] The follow-up unit can provide additional information according to the user's level of understanding. Examples of additional information include, but are not limited to, detailed explanations and related links. For example, the follow-up unit can provide detailed explanations to deepen the user's understanding. The follow-up unit can also provide related links to allow the user to obtain further information. Furthermore, the follow-up unit can provide specific examples and success stories to deepen the user's understanding. For example, the follow-up unit allows the generation AI to provide detailed explanations to the user to deepen their understanding. The related links are in a format that the user can click to obtain further information, and the generation AI provides the links. The specific examples and success stories are in a format that the user can use to obtain information useful for actual work, and the generation AI provides the information. This allows the follow-up unit to further deepen the user's understanding by providing additional information according to the user's level of understanding. Some or all of the above-described processing in the follow-up unit may be performed using AI, for example, or may be performed without using AI. For example, the follow-up unit can input the user's level of understanding data into the generation AI and cause the generation AI to provide additional information.

[0068] The analysis unit may refer to academic papers, specialized books, official industry guidelines, etc., whose reliability has been confirmed. Information sources whose reliability has been confirmed include, but are not limited to, peer-reviewed papers and official certifications. For example, the analysis unit may refer to peer-reviewed papers to generate answers to user questions. The analysis unit may also refer to official certifications to generate answers to user questions. Furthermore, the analysis unit may refer to official industry guidelines to generate answers to user questions. For example, the analysis unit may have a generation AI refer to peer-reviewed papers to generate answers to user questions. Official certifications are certified as reliable information sources, and the generation AI references the information. Official industry guidelines are certified as industry standards, and the generation AI references the information. By doing so, the analysis unit can increase the reliability of the information provided to the user by referring to reliable information sources. Some or all of the above-described processing by the analysis unit may be performed using AI, for example, or may be performed without AI. For example, the analysis unit may input information sources whose reliability has been confirmed into the generation AI and cause the generation AI to generate an optimal answer.

[0069] The follow-up unit can incorporate a mechanism for the generation AI to learn and improve based on user feedback. Examples of the generation AI include, but are not limited to, deep learning models and reinforcement learning models. The follow-up unit can, for example, use a deep learning model to learn and improve based on user feedback. The follow-up unit can also use a reinforcement learning model to learn and improve based on user feedback. Furthermore, the follow-up unit can have the generation AI analyze user feedback to improve the accuracy of the system. For example, in the follow-up unit, the generation AI inputs user feedback into a deep learning model to learn and improve. A reinforcement learning model is a model that learns optimal behavior based on user feedback, and the generation AI uses that model to learn and improve. The generation AI analyzes user feedback and uses it as data to improve the accuracy of the system. In this way, the follow-up unit can improve the accuracy of the system by having the generation AI learn and improve based on user feedback. Some or all of the above-described processing in the follow-up unit can be performed, for example, using AI or without AI. For example, the follow-up unit can input user feedback data into the generation AI and have the generation AI learn and improve.

[0070] The analysis unit can periodically update the database to reflect the latest information. Periodically includes, but is not limited to, daily, weekly, monthly, etc. The analysis unit can, for example, update the database daily to reflect the latest information. The analysis unit can also update the database weekly to reflect the latest information. The analysis unit can also update the database monthly to reflect the latest information. For example, the analysis unit has the generation AI update the database daily to reflect the latest information. A weekly update is a format in which the generation AI updates the database weekly to reflect the latest information, and a monthly update is a format in which the generation AI updates the database monthly to reflect the latest information. In this way, the analysis unit can always provide the latest information by periodically updating the database. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can have the generation AI update the database.

[0071] The reception unit can estimate the user's emotions and adjust the timing of question acceptance based on the estimated user emotions. For example, if the user is feeling stressed, the reception unit can cause the generation AI to temporarily delay accepting questions and provide advice to relax. Furthermore, if the user is excited, the reception unit can cause the generation AI to immediately accept questions and provide answers quickly. Furthermore, if the user is tired, the reception unit can cause the generation AI to simplify the question acceptance process, enabling answers to be obtained in a short time. For example, the reception unit can have the generation AI analyze the user's facial expressions to estimate emotions. It can also use voice analysis technology to analyze the tone and speed of the user's voice to estimate emotions. It can also use text analysis technology to analyze the user's input content to estimate emotions. This allows the reception unit to adjust the timing of question acceptance according to the user's emotions, thereby accepting questions at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input user emotion data to the generation AI and cause the generation AI to adjust the timing of receiving questions.

[0072] The reception unit can analyze the user's past question history and select the optimal reception method. Optimal reception methods include, but are not limited to, chatbots and telephone support. For example, the reception unit prioritizes reception of topics that the user has frequently asked about in the past. The reception unit can also prioritize suggesting question formats (text, voice, etc.) that the user has used in the past. Furthermore, the reception unit can also suggest the optimal reception method for a specific time period based on the user's past question history. For example, the reception unit uses a generation AI to analyze the user's past question history and select the optimal reception method. A chatbot is a format in which the user inputs questions in text format, and the generation AI accepts the questions. A telephone support is a format in which the user inputs questions in voice format, and the generation AI accepts the questions. This allows the reception unit to select the optimal reception method by analyzing the user's past question history. Some or all of the above-described processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the user's question history data into the generation AI and have the generation AI select the optimal reception method.

[0073] When receiving a question, the reception unit can filter the questions based on the user's current areas of interest or projects. Examples of filtering include, but are not limited to, keyword matching and category classification. For example, the reception unit may preferentially receive questions related to a project the user is currently working on. The reception unit may also filter and receive related questions based on the user's areas of interest. Furthermore, the reception unit may suggest appropriate questions based on the user's project progress. For example, the reception unit may have a generation AI analyze the user's areas of interest and filter related questions. Keyword matching is a method of matching the user's input content with related keywords, and the generation AI performs the filtering. Category classification is a method of classifying the user's input content into specific categories, and the generation AI performs the filtering. This allows the reception unit to filter questions based on the user's current areas of interest or projects, thereby preferentially receiving highly relevant questions. Some or all of the above-described processing in the reception unit may be performed using AI, for example, or may be performed without AI. For example, the reception unit may input the user's area of ​​interest data into the generation AI and have the generation AI perform question filtering.

[0074] When receiving a question, the reception unit can select the optimal reception means depending on the user's input method. Examples of input methods include, but are not limited to, voice input, text input, and image input. For example, when a user inputs a question by voice, the reception unit uses voice recognition technology to receive the question. Furthermore, when a user inputs a question by text, the reception unit can also use text analysis technology to receive the question. Furthermore, when a user inputs a question using an image, the reception unit can also use image analysis technology to receive the question. For example, the reception unit converts the user's voice into text using voice recognition technology and receives the question. Text analysis technology analyzes the text entered by the user and accepts it as a question, and the generation AI performs the analysis. Image analysis technology analyzes the image entered by the user and accepts it as a question, and the generation AI performs the analysis. This allows the reception unit to select the optimal reception means depending on the user's input method, thereby smoothly receiving questions. Some or all of the above-described processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input user input data to the generation AI and cause the generation AI to select the optimal reception means.

[0075] The reception unit can estimate the user's emotions and prioritize questions based on the estimated user emotions. Examples of prioritization include, but are not limited to, urgency and importance. For example, when the user is stressed, the reception unit allows the generation AI to prioritize questions of high importance. Furthermore, when the user is relaxed, the reception unit can also prioritize detailed questions. Furthermore, when the user is in a hurry, the reception unit can prioritize questions that the generation AI can answer quickly. For example, the reception unit allows the generation AI to analyze the user's facial expressions and estimate emotions. Voice analysis technology can also be used to analyze the tone and speed of the user's voice and estimate emotions. Text analysis technology can also be used to analyze the user's input and estimate emotions. This allows the reception unit to prioritize questions based on the user's emotions, thereby prioritizing important questions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit may input user emotion data into the generation AI and have the generation AI determine the priority of questions.

[0076] When accepting questions, the reception unit can prioritize relevant questions by taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and IP addresses. For example, if the user is in a specific area, the reception unit can prioritize questions related to that area. Furthermore, if the user is traveling, the reception unit can prioritize questions related to the travel destination. Furthermore, if the user is participating in a specific event, the reception unit can prioritize questions related to the event. For example, in the reception unit, the generation AI analyzes the user's geographical location information and filters relevant questions. GPS data is data for identifying the user's current location, and the generation AI analyzes that data. IP address is data for identifying the user's Internet connection destination, and the generation AI analyzes that data. In this way, the reception unit can prioritize relevant questions by taking into account the user's geographical location information. Some or all of the above-described processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's geographical location data into the generation AI and have the generation AI perform question filtering.

[0077] When receiving a question, the reception unit can analyze the user's social media activity and receive related questions. Social media activity includes, but is not limited to, analysis of post content and follower analysis. For example, the reception unit preferentially receives questions related to topics in which the user has shown interest on social media. The reception unit can also analyze the user's social media posts and receive related questions. Furthermore, the reception unit can also receive related questions based on the activities of the user's friends on social media. For example, the reception unit uses a generation AI to analyze the user's social media activity and filter related questions. The analysis of post content involves analyzing content posted by the user on social media, and the generation AI performs this analysis. The analysis of followers involves analyzing the activities of the user's followers, and the generation AI performs this analysis. As a result, the reception unit can analyze the user's social media activity and preferentially receive highly relevant questions. Some or all of the above-described processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit can input the user's social media data into the generation AI and have the generation AI perform question filtering.

[0078] When receiving a question, the reception unit can customize the reception method by reflecting the user's past feedback. Examples of feedback include, but are not limited to, questionnaires and user reviews. The reception unit, for example, suggests an optimal reception method based on feedback provided by the user in the past. The reception unit can also preferentially receive specific question formats based on the user's past feedback. Furthermore, the reception unit can continuously improve the reception method by reflecting the user's feedback. For example, the reception unit uses a generation AI to analyze the user's past feedback and select an optimal reception method. A questionnaire is a format in which the user answers questions, and the generation AI analyzes the answers. A user review is a format in which reviews provided by the user are analyzed, and the generation AI performs the analysis. This allows the reception unit to provide an optimal reception method by reflecting the user's past feedback. Some or all of the above-described processing in the reception unit may be performed using, or without, an AI. For example, the reception unit can input user feedback data into the generation AI and have the generation AI customize the reception method.

[0079] The analysis unit can estimate the user's emotions and adjust the presentation method of the analysis based on the estimated user's emotions. Examples of presentation methods for the analysis include, but are not limited to, text format and graph format. For example, if the user is relaxed, the generation AI can provide analysis results with detailed explanations. Furthermore, if the user is in a hurry, the analysis unit can provide analysis results that are concise and to the point. Furthermore, if the user is excited, the generation AI can provide analysis results that are visually appealing. For example, the analysis unit can have the generation AI analyze the user's facial expressions to estimate emotions. Voice analysis technology can also be used to analyze the tone and speed of the user's voice to estimate emotions. Text analysis technology can also be used to analyze the user's input content to estimate emotions. This allows the analysis unit to adjust the presentation method of the analysis according to the user's emotions, thereby providing more appropriate analysis results. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit may input user emotion data into the generation AI and cause the generation AI to adjust the method of expression of the analysis.

[0080] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the question. The importance of the question includes, but is not limited to, the user's urgency and the question's impact. For example, the analysis unit allows the generation AI to provide detailed analysis results for questions with high importance. The analysis unit can also allow the generation AI to provide concise analysis results for questions with low importance. Furthermore, the analysis unit allows the generation AI to adjust the priority of the analysis based on the question's importance. For example, the analysis unit allows the generation AI to analyze the importance of the user's question and adjust the level of detail. The user's urgency is a criterion for evaluating the urgency of the question, and the generation AI uses this criterion to adjust the level of detail of the analysis. The question's impact is a criterion for evaluating the impact the question has on the user, and the generation AI uses this criterion to adjust the level of detail of the analysis. In this way, the analysis unit can provide detailed analysis results for important questions by adjusting the level of detail of the analysis based on the question's importance. Some or all of the above-described processing in the analysis unit may be performed, for example, using AI or without AI. For example, the analysis unit can input user question data into the generation AI and have the generation AI adjust the level of detail of the analysis.

[0081] During analysis, the analysis unit can apply different analysis algorithms depending on the question category. Examples of analysis algorithms include, but are not limited to, natural language processing algorithms and machine learning algorithms. For example, in the analysis unit, the generation AI applies a specialized analysis algorithm to technical questions. Furthermore, the analysis unit can also apply a business-oriented analysis algorithm to business-related questions. Furthermore, the analysis unit can also apply an analysis algorithm based on academic papers to academic questions. For example, the analysis unit applies a specialized natural language processing algorithm to technical questions. For business-related questions, the generation AI applies a business-oriented machine learning algorithm to perform analysis. For academic questions, the generation AI applies an analysis algorithm based on academic papers to perform analysis. This allows the analysis unit to provide more appropriate analysis results by applying different analysis algorithms depending on the question category. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user question data into the generation AI and have the generation AI apply the analysis algorithm.

[0082] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. Past analysis results include, but are not limited to, database references and analysis of historical data. For example, the analysis unit allows the generation AI to improve the accuracy of the analysis based on analysis results previously received by the user. The analysis unit can also extract specific patterns from the user's past analysis results and reflect them in the analysis. Furthermore, the analysis unit can analyze the user's past analysis results so that the generation AI can continuously learn and improve. For example, the analysis unit allows the generation AI to refer to a database of the user's past analysis results to improve the accuracy of the analysis. Analysis of historical data involves analyzing the user's past analysis results, and the generation AI performs the analysis. Extraction of specific patterns involves finding common patterns from the user's past analysis results, and the generation AI performs the extraction. In this way, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or without AI. For example, the analysis unit can input the user's past analysis result data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0083] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. Examples of the length of the analysis include, but are not limited to, adjusting the length of the analysis based on the user's level of concentration. For example, if the user is in a hurry, the generation AI can provide a short, concise analysis result. Alternatively, if the user is relaxed, the generation AI can provide a longer analysis result with detailed explanations. Furthermore, if the user is excited, the generation AI can provide an analysis result with visually stimulating effects. For example, the analysis unit uses the generation AI to analyze the user's facial expressions and estimate emotions. Voice analysis technology can also be used to analyze the tone and speed of the user's voice and estimate emotions. Text analysis technology can also be used to analyze the user's input and estimate emotions. This allows the analysis unit to adjust the length of the analysis based on the user's emotions, thereby providing more appropriate analysis results. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit may input user emotion data into the generation AI and cause the generation AI to adjust the length of the analysis.

[0084] During analysis, the analysis unit can determine the analysis priority based on the time of question submission. The submission time includes, but is not limited to, a record of the submission date and time, a timestamp, etc. For example, the analysis unit allows the generation AI to determine the analysis priority based on the time of day when the question was submitted. The analysis unit can also allow the generation AI to adjust the analysis schedule according to the time of question submission. Furthermore, the analysis unit can also allow the generation AI to optimally allocate analysis resources based on the time of question submission. For example, the analysis unit allows the generation AI to analyze the time of question submission and determine the priority. The submission date and time record is a record of the date and time when the question was submitted, and the generation AI analyzes the record. The timestamp is a record of the time when the question was submitted, and the generation AI analyzes the timestamp. This allows the analysis unit to determine the analysis priority based on the time of question submission, thereby providing analysis results at an appropriate time. Some or all of the above-described processing in the analysis unit may be performed, for example, using AI or without AI. For example, the analysis unit can input data on the time of question submission into the generation AI and have the generation AI determine the priority of the analysis.

[0085] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the questions. Relevance includes, but is not limited to, keyword similarity and topic similarity. For example, the analysis unit allows the generation AI to determine the order of analysis based on the relevance of the questions. The analysis unit can also allow the generation AI to adjust the analysis priority according to the relevance of the questions. Furthermore, the analysis unit can also allow the generation AI to optimally allocate analysis resources based on the relevance of the questions. For example, the analysis unit allows the generation AI to analyze the relevance of questions and adjust the order. Keyword similarity is a criterion for evaluating the degree of match between keywords related to a question, and the generation AI uses this criterion to adjust the order of analysis. Topic similarity is a criterion for evaluating the similarity between topics related to a question, and the generation AI uses this criterion to adjust the order of analysis. Thus, by adjusting the order of analysis based on the relevance of the questions, the analysis unit can prioritize the analysis of highly relevant questions. Some or all of the above-described processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input question relevance data to the generation AI and have the generation AI adjust the order of analysis.

[0086] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. Examples of technical terms include, but are not limited to, the user's occupation and past question content. For example, if the user is a beginner, the analysis unit can have the generation AI provide analysis results that avoid technical terms. For example, if the user is an intermediate user, the analysis unit can have the generation AI provide analysis results using appropriate technical terms. For example, if the user is an advanced user, the analysis unit can have the generation AI use more technical terms to provide detailed analysis results. For example, the analysis unit can have the generation AI analyze the user's occupation and estimate the user's level of expertise. The past question content is in the form of an analysis of the content of questions the user has previously asked, and the generation AI analyzes that content. This allows the analysis unit to adjust the use of technical terms in the analysis according to the user's level of expertise, thereby providing analysis results that are easier to understand. Some or all of the above-described processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input the user's level of expertise data into the generation AI and have the generation AI use technical terms.

[0087] The follow-up unit can estimate the user's emotions and adjust the follow-up method based on the estimated user emotions. Examples of follow-up methods include, but are not limited to, email follow-up and telephone follow-up. For example, if the user is feeling stressed, the generation AI can provide relaxation advice. If the user is relaxed, the follow-up unit can also ask detailed follow-up questions. If the user is in a hurry, the follow-up unit can also ask concise follow-up questions. For example, the follow-up unit can analyze the user's facial expressions and estimate emotions. Voice analysis technology can also be used to analyze the tone and speed of the user's voice and estimate emotions. Text analysis technology can also be used to analyze the user's input and estimate emotions. This allows the follow-up unit to adjust the follow-up method according to the user's emotions, thereby providing more appropriate follow-up. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the follow-up unit may be performed using AI, or may be performed without using AI. For example, the follow-up unit may input user emotion data into the generation AI and cause the generation AI to adjust the follow-up method.

[0088] During follow-up, the follow-up unit can analyze the user's past level of understanding and select the optimal follow-up method. Examples of past level of understanding include, but are not limited to, past test results and feedback content. For example, the follow-up unit allows the generation AI to perform detailed follow-up on topics that the user did not understand in the past. The follow-up unit can also allow the generation AI to suggest appropriate follow-up questions based on the user's past level of understanding. Furthermore, the follow-up unit can analyze the user's past level of understanding so that the generation AI can continuously learn and improve. For example, the follow-up unit allows the generation AI to analyze the user's past test results and select the optimal follow-up method. The feedback content is in the form of an analysis of feedback provided by the user in the past, and the generation AI analyzes that content. This allows the follow-up unit to analyze the user's past level of understanding and provide the optimal follow-up method. Some or all of the above-described processing in the follow-up unit may be performed using, for example, AI, or may be performed without AI. For example, the follow-up unit can input the user's past level of understanding data into the generation AI and have the generation AI select a follow-up method.

[0089] The follow-up unit can customize the follow-up method based on the user's current level of understanding during follow-up. Examples of the current level of understanding include, but are not limited to, real-time quiz results and immediate feedback. For example, if the user understands the current topic, the follow-up unit performs a follow-up in which the generation AI proceeds to the next step. Furthermore, if the user does not understand the current topic, the follow-up unit can perform a follow-up including a detailed explanation. Furthermore, the follow-up unit can suggest an appropriate follow-up method based on the user's current level of understanding. For example, the follow-up unit analyzes real-time quiz results and customizes the follow-up method. Immediate feedback is a form of providing feedback immediately after the user answers a question, and the generation AI provides that feedback. This allows the follow-up unit to customize the follow-up method based on the user's current level of understanding, thereby providing a more appropriate follow-up. Some or all of the above-described processing in the follow-up unit may be performed using, or without, an AI. For example, the follow-up unit can input the user's current level of understanding data into the generation AI and have the generation AI customize the follow-up method.

[0090] The follow-up unit can improve the follow-up method by reflecting user feedback during follow-up. Examples of follow-up methods include, but are not limited to, adjustments based on user feedback. For example, the follow-up unit causes the generation AI to improve the follow-up method based on feedback provided by the user. The follow-up unit can also preferentially suggest specific follow-up methods based on user feedback. Furthermore, the follow-up unit can continuously improve the follow-up method by reflecting user feedback. For example, the follow-up unit causes the generation AI to analyze user feedback and improve the follow-up method. User feedback is often provided in the form of a questionnaire or review, and the generation AI analyzes that feedback. This allows the follow-up unit to continuously improve the follow-up method by reflecting user feedback. Some or all of the above-described processing in the follow-up unit may be performed using AI, for example, or without AI. For example, the follow-up unit can input user feedback data into the generation AI and cause the generation AI to improve the follow-up method.

[0091] The follow-up unit can estimate the user's emotions and determine the priority of follow-ups based on the estimated user emotions. Examples of follow-up priorities include, but are not limited to, the user's urgency and importance. For example, if the user is stressed, the generation AI can prioritize follow-ups with higher importance. Furthermore, if the user is relaxed, the follow-up unit can prioritize detailed follow-ups. Furthermore, if the user is in a hurry, the follow-up unit can prioritize follow-ups that the generation AI can respond to quickly. For example, the follow-up unit uses the generation AI to analyze the user's facial expressions and estimate emotions. Voice analysis technology can also be used to analyze the tone and speed of the user's voice and estimate emotions. Text analysis technology can also be used to analyze the user's input and estimate emotions. This allows the follow-up unit to prioritize follow-ups based on the user's emotions, thereby prioritizing important follow-ups. Emotion estimation is achieved, for example, using an emotion estimation function using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the follow-up unit may be performed using AI, or may be performed without using AI. For example, the follow-up unit may input user emotion data into the generation AI and have the generation AI determine the priority of follow-up.

[0092] The follow-up unit can select the optimal follow-up method by taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and IP addresses. For example, if the user is in a specific area, the follow-up unit can provide information related to that area. Furthermore, if the user is traveling, the follow-up unit can also provide information related to the travel destination. Furthermore, if the user is participating in a specific event, the follow-up unit can also provide information related to the event. For example, the follow-up unit uses a generation AI to analyze the user's geographical location information and provide relevant information. GPS data is data for identifying the user's current location, and the generation AI analyzes that data. An IP address is data for identifying the user's Internet connection destination, and the generation AI analyzes that data. This allows the follow-up unit to provide highly relevant follow-up by taking the user's geographical location information into account. Some or all of the above-described processing in the follow-up unit may be performed, for example, using AI, or may be performed without using AI. For example, the follow-up unit can input the user's geographical location data into the generation AI and have the generation AI select a follow-up method.

[0093] The follow-up unit can analyze the user's social media activity during follow-up and suggest follow-up methods. Examples of social media activity include, but are not limited to, analysis of posted content and follower analysis. For example, the follow-up unit performs follow-up related to topics in which the user has shown interest on social media. The follow-up unit can also analyze the content of the user's social media posts and perform related follow-up. Furthermore, the follow-up unit can also perform related follow-up based on the activities of the user's friends on social media. For example, the follow-up unit analyzes the user's social media activity using a generation AI to suggest related follow-up. The analysis of posted content involves analyzing content posted by the user on social media, and the generation AI performs this analysis. The analysis of followers involves analyzing the activities of the user's followers, and the generation AI performs this analysis. This allows the follow-up unit to provide highly relevant follow-up by analyzing the user's social media activity. Some or all of the above-described processing in the follow-up unit may be performed using, for example, AI, or may be performed without using AI. For example, the follow-up unit can input the user's social media data into the generation AI and have the generation AI execute suggestions for follow-up measures.

[0094] The follow-up unit can customize the follow-up method by reflecting the user's past feedback during follow-up. Examples of past feedback include, but are not limited to, questionnaires and user reviews. The follow-up unit can, for example, suggest an optimal follow-up method based on feedback previously provided by the user. The follow-up unit can also prioritize specific follow-up methods based on the user's past feedback. Furthermore, the follow-up unit can continuously improve the follow-up method by reflecting the user's feedback. For example, the follow-up unit uses a generation AI to analyze the user's past feedback and select an optimal follow-up method. A questionnaire is a format in which the user answers questions, and the generation AI analyzes the answers. A user review is a format in which the user analyzes reviews provided by the user, and the generation AI performs the analysis. This allows the follow-up unit to provide an optimal follow-up method by reflecting the user's past feedback. Some or all of the above-described processing in the follow-up unit may be performed, for example, using AI or without AI. For example, the follow-up unit can input user feedback data into the generation AI and cause the generation AI to customize the follow-up method. === Hard Collateral 1-1 === Each of the multiple elements, including the reception unit, analysis unit, and follow-up unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the camera 42 and microphone 38B of the smart device 14 can be used to analyze the user's facial expressions and voice to estimate emotions. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the question using a generation AI and provides related information. The follow-up unit is realized, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and uses a generation AI to check the user's understanding and provide additional information as needed. === Hard Collateral 1-2 === Each of the multiple elements, including the reception unit, analysis unit, and follow-up unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the camera 42 and microphone 238 of the smart glasses 214 can be used to analyze the user's facial expressions and voice and estimate their emotions. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the question using a generation AI and provides related information. The follow-up unit is realized, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and uses a generation AI to check the user's understanding and provide additional information as needed. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, and follow-up unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset-type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the camera 42 and the microphone 238 of the headset-type terminal 314 can be used to analyze the user's facial expressions and voice to estimate emotions. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the question using a generation AI and provides related information. The follow-up unit is realized, for example, by the control unit 46A of the headset-type terminal 314 or the specific processing unit 290 of the data processing device 12, and uses a generation AI to check the user's understanding and provide additional information as necessary. === Hard Collateral 1-4 === Each of the multiple elements, including the reception unit, analysis unit, and follow-up unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the camera 42 and microphone 238 of the robot 414 can be used to analyze the user's facial expressions and voice to estimate their emotions. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the question using a generation AI and provides related information. The follow-up unit is realized, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and uses a generation AI to check the user's understanding and provide additional information as needed.

[0095] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0096] The reception unit can analyze the user's past question history and select the optimal reception method. For example, it can prioritize reception of topics that the user has frequently asked about in the past. The reception unit can also prioritize suggesting question formats (text, voice, etc.) that the user has used in the past. Furthermore, the reception unit can also suggest the optimal reception method for a specific time period based on the user's past question history. In this way, the reception unit can select the optimal reception method by analyzing the user's past question history.

[0097] The analysis unit can adjust the use of technical terminology in the analysis according to the user's level of expertise. For example, if the user is a beginner, the generation AI can provide analysis results that avoid technical terminology. If the user is an intermediate user, the generation AI can provide analysis results using appropriate technical terminology. Furthermore, if the user is an advanced user, the generation AI can provide detailed analysis results using a lot of technical terminology. In this way, the analysis unit can provide analysis results that are easier to understand by adjusting the use of technical terminology in the analysis according to the user's level of expertise.

[0098] The follow-up unit can estimate the user's emotions and adjust the follow-up method based on the estimated user's emotions. For example, if the user is feeling stressed, the generation AI can provide advice to relax. Also, if the user is relaxed, the generation AI can ask detailed follow-up questions. Furthermore, if the user is in a hurry, the generation AI can ask concise follow-up questions. This allows the follow-up unit to provide more appropriate follow-up by adjusting the follow-up method according to the user's emotions.

[0099] The analysis unit can estimate the user's emotions and adjust the way the analysis is presented based on the estimated user emotions. For example, if the user is relaxed, the generation AI can provide analysis results with detailed explanations. If the user is in a hurry, the generation AI can provide analysis results that are concise and to the point. Furthermore, if the user is excited, the generation AI can provide analysis results that are visually appealing. This allows the analysis unit to provide more appropriate analysis results by adjusting the way the analysis is presented according to the user's emotions.

[0100] The reception unit can estimate the user's emotions and adjust the timing of question reception based on the estimated user emotions. For example, if the user is feeling stressed, the generation AI can temporarily delay the reception of questions and provide advice on how to relax. Also, if the user is excited, the generation AI can immediately accept questions and provide answers quickly. Furthermore, if the user is tired, the generation AI can simplify the reception of questions so that answers can be obtained in a short time. In this way, the reception unit can adjust the timing of question reception according to the user's emotions, allowing questions to be received at a more appropriate time.

[0101] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the question. For example, the generation AI can provide detailed analysis results for questions with high importance. The generation AI can also provide concise analysis results for questions with low importance. Furthermore, the analysis unit can have the generation AI adjust the priority of the analysis according to the importance of the question. As a result, the analysis unit can provide detailed analysis results for important questions by adjusting the level of detail of the analysis based on the importance of the question.

[0102] When following up, the follow-up unit can analyze the user's past level of understanding and select the optimal follow-up method. For example, the generation AI can provide detailed follow-up on topics that the user was unable to understand in the past. The follow-up unit can also suggest appropriate follow-up questions based on the user's past level of understanding. Furthermore, the follow-up unit can analyze the user's past level of understanding, allowing the generation AI to continuously learn and improve. This allows the follow-up unit to provide the optimal follow-up method by analyzing the user's past level of understanding.

[0103] During analysis, the analysis unit can apply different analysis algorithms depending on the question category. For example, for technical questions, the generation AI can apply a specialized analysis algorithm. For business-related questions, the generation AI can also apply a business-oriented analysis algorithm. Furthermore, for academic questions, the generation AI can apply an analysis algorithm based on academic papers. In this way, the analysis unit can provide more appropriate analysis results by applying different analysis algorithms depending on the question category.

[0104] The follow-up unit can estimate the user's emotions and determine the priority of follow-ups based on the estimated user's emotions. For example, if the user is feeling stressed, the generation AI can prioritize follow-ups with high importance. Also, if the user is relaxed, the generation AI can prioritize detailed follow-ups. Furthermore, if the user is in a hurry, the generation AI can prioritize follow-ups that can be handled quickly. In this way, the follow-up unit can prioritize important follow-ups by determining the priority of follow-ups according to the user's emotions.

[0105] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the generation AI improves the accuracy of the analysis based on the analysis results the user received in the past. The analysis unit can also extract specific patterns from the user's past analysis results and reflect them in the analysis. Furthermore, the analysis unit can analyze the user's past analysis results, allowing the generation AI to continuously learn and improve. In this way, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results.

[0106] The processing flow of the second embodiment will be briefly explained below.

[0107] Step 1: The reception unit receives questions from users. Questions from users may be in text format, voice format, technical questions, general questions, etc. For example, the reception unit analyzes text entered by the user and accepts it as a question. Voice-format questions are converted into text using voice recognition technology and accepted as questions. Step 2: The analysis unit uses the generation AI to analyze the question received by the reception unit and provide relevant information. The analysis is carried out using natural language processing technology and machine learning algorithms. For example, the generation AI may refer to a large amount of databases and literature to generate the optimal answer. It may also refer to reliable academic papers, specialist books, official industry guidelines, etc. Step 3: The follow-up unit uses the generation AI to check the user's level of understanding based on the information provided by the analysis unit. The check of understanding is done in the form of a quiz or feedback. For example, the generation AI may ask the user follow-up questions to check the user's level of understanding. It may also provide additional information depending on the user's level of understanding. Furthermore, it may also introduce a mechanism for learning and improving based on user feedback.

[0108] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0109] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0110] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0111] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0112] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0113] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0114] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0115] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0116] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0117] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0118] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0119] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0120] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0121] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0122] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0123] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0124] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0125] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0126] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0127] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0128] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0129] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0130] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0131] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0132] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0133] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0134] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0135] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0136] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0137] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0138] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0139] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0140] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0141] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0142] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0143] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0144] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0145] 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.

[0146] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0147] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0148] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0149] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0150] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0151] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0152] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0153] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0154] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0155] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0156] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0157] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0158] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0159] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0160] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0161] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0162] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0163] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0164] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0165] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0166] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0167] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0168] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0169] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0170] 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.

[0171] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0172] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0173] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0174] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0175] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0176] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0177] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0178] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0179] [Explanation of symbols]

[0180] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit that receives questions from users; an analysis unit that analyzes the question received by the reception unit and provides related information; a follow-up unit that confirms the user's level of understanding based on the information provided by the analysis unit. A system characterized by:

2. The analysis unit Referencing multiple databases and literature to generate the best answer to a user's question 2. The system of claim 1.

3. The follow-up unit Ask follow-up questions to check user understanding 2. The system of claim 1.

4. The follow-up unit Providing additional information based on the user's level of understanding 2. The system of claim 1.

5. The analysis unit Refer to reliable academic papers, specialist books, official industry guidelines, etc.

2. The system of claim 1.

6. The follow-up unit Introducing a mechanism for generative AI to learn and improve based on user feedback 2. The system of claim 1.

7. The analysis unit Regularly update the database to reflect the latest information 2. The system of claim 1.

8. The reception unit Estimates the user's emotions and adjusts the timing of accepting questions based on the estimated user emotions.

2. The system of claim 1.

9. The reception unit Analyze the user's past question history and select the optimal reception method 2. The system of claim 1.

10. The reception unit Filter questions based on your current interests and projects 2. The system of claim 1.

Images