system

Abstract

The system according to this embodiment aims to respond quickly and accurately to the user's information needs. [Solution] The system according to the embodiment comprises a needs catching unit, an interviewing unit, a knowledge gathering unit, a knowledge verification unit, and an article generation unit. The needs catching unit catches the user's information needs. The interviewing unit conducts detailed interviews with excellent respondents on the Q&A site based on the information caught by the needs catching unit. The knowledge gathering unit collects the knowledge gathered by the interviewing unit from multiple experts. The knowledge verification unit verifies the accuracy of the knowledge gathered by the knowledge gathering unit. The article generation unit generates an article based on the knowledge verified by the knowledge verification unit.

Description

Technical Field

[0006] , , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there was a problem that it was difficult to quickly and accurately respond to the information needs of users.

[0005] The system according to the embodiment aims to quickly and accurately respond to the information needs of users.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a needs-catching unit, an interviewing unit, a knowledge-gathering unit, a knowledge-verification unit, and an article-generating unit. The needs-catching unit captures the user's information needs. The interviewing unit conducts detailed interviews with excellent respondents on the Q&A site based on the information captured by the needs-catching unit. The knowledge-gathering unit collects the knowledge gathered by the interviewing unit from multiple experts. The knowledge-verification unit verifies the accuracy of the knowledge gathered by the knowledge-gathering unit. The article-generating unit generates an article based on the knowledge verified by the knowledge-verification unit. [Effects of the Invention]

[0007] The system according to this embodiment can respond quickly and accurately to the user's information needs. [Brief explanation of the drawing]

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

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

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

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

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

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The InfoGenius system according to an embodiment of the present invention is a system for providing users with the information they seek quickly and reliably. This system captures users' information needs, conducts detailed interviews with users who have provided excellent answers in the past on Q&A sites, collects knowledge and opinions from multiple experts, and has other experts verify the accuracy of the content to aggregate highly reliable information, and a generating AI automatically generates articles for MyBest. For example, the InfoGenius system captures information that users are increasingly seeking through internet searches. Next, the generating AI conducts detailed interviews with users who have provided excellent answers in the past on Q&A sites via a messaging app. For example, regarding medical information, it asks detailed questions to doctors and experts to collect their knowledge. Subsequently, it collects knowledge and opinions from multiple experts, and has other experts verify the accuracy of the content. For example, it has other doctors and experts verify the collected medical information to ensure its accuracy. Finally, highly reliable information is aggregated, and based on the results, the generating AI automatically generates articles for MyBest. For example, the generating AI automatically creates an article about medical information and provides it to the user. This allows the InfoGenius system to quickly obtain reliable and high-quality information, supporting efficient decision-making. This process improves the quality and reliability of the information. As a result, the InfoGenius system can efficiently capture users' information needs and provide highly reliable information.

[0029] The InfoGenius system according to this embodiment comprises a needs catching unit, an interviewing unit, a knowledge gathering unit, a knowledge verification unit, and an article generation unit. The needs catching unit catches the user's information needs. For example, the needs catching unit can catch the user's need for information using internet search. For example, if there is a lot of searching for specific medical information or legal information, it will catch that information. The interviewing unit uses a generation AI to conduct detailed interviews with users who have provided excellent answers on Q&A sites, based on the information caught by the needs catching unit. For example, regarding medical information, it will ask detailed questions to doctors and experts and collect their knowledge. The interviewing unit can, for example, send questions to users via a messaging app and collect answers. The knowledge gathering unit collects the knowledge and opinions of multiple experts. For example, it will have the collected medical information checked by other doctors and experts to ensure its accuracy. The knowledge gathering unit can, for example, interview experts to collect knowledge. The knowledge verification unit verifies the accuracy of the collected knowledge. For example, the collected medical information can be verified by other doctors and specialists to ensure its accuracy. The knowledge verification unit can, for example, perform cross-checks to verify the accuracy of the knowledge. The article generation unit uses a generation AI to generate articles based on the verified knowledge. For example, the generation AI can automatically create articles about medical information and provide them to the user. The article generation unit can, for example, use a generation AI to generate articles based on the structure of the text and the algorithm used. As a result, the InfoGenius system according to this embodiment can efficiently capture the user's information needs and provide highly reliable information.

[0030] The Needs Catching Unit captures users' information needs. Specifically, it analyzes trend data from internet search engines and social media to understand what kind of information users are seeking. For example, by collecting search engine query data and analyzing how often specific keywords and phrases are searched, it identifies user interests. It can also analyze social media posts and comments to understand what topics users are discussing. This allows the Needs Catching Unit to quickly capture users' fluctuating information needs in real time and improve the accuracy of information provision throughout the system. Furthermore, the Needs Catching Unit uses natural language processing technology to analyze users' search queries and posts to extract specific information needs. For example, if there is an increase in search queries related to medical information, it can analyze the content of those queries in detail to identify the specific information users are seeking (e.g., treatments or preventive measures for specific diseases). This allows the Needs Catching Unit to more accurately understand users' information needs and smoothly provide information to the next step, the Hearing Unit.

[0031] The Hearing Department uses a generative AI to conduct detailed interviews with users who have provided excellent answers on the Q&A platform, based on information gathered by the Needs Gathering Department. Specifically, the generative AI automatically generates appropriate questions based on the user's information needs and sends them to knowledgeable users. For example, regarding medical information, the generative AI creates detailed questions for doctors and specialists and sends them via messaging apps or email. This allows the Hearing Department to collect detailed answers from specialists and gather foundational data to meet the user's information needs. Furthermore, the generative AI analyzes the collected answers and extracts important information and insights. For example, it can analyze answers from doctors and extract key points regarding treatments and preventive measures for specific diseases. This allows the Hearing Department to efficiently organize the collected information and smoothly provide it to the Knowledge Gathering Department, which is the next step.

[0032] The Knowledge Gathering Department collects knowledge and opinions from multiple experts. Specifically, it ensures the accuracy of collected medical information by having it verified by other doctors and experts. For example, based on information provided by the Interviewing Department, it conducts interviews with other doctors and experts to gather additional knowledge and opinions. This allows the Knowledge Gathering Department to integrate the opinions of multiple experts and improve the accuracy and reliability of the information. Furthermore, the Knowledge Gathering Department stores the collected information in a database, making it accessible to other departments. For example, it stores collected medical information in a database, allowing the Article Generation Department to create articles based on that information. This allows the Knowledge Gathering Department to improve the accuracy and reliability of information provided throughout the entire system.

[0033] The Knowledge Verification Department verifies the accuracy of the collected knowledge. Specifically, it ensures the accuracy of the collected medical information by having other doctors and specialists verify it. For example, it performs cross-checks, ensuring that multiple specialists confirm the same information and guarantee its accuracy. This allows the Knowledge Verification Department to enhance the reliability of the collected information and improve the quality of the information provided to users. Furthermore, the Knowledge Verification Department can regularly update the collected information to provide the latest information. For example, if there are results from new medical research or changes in guidelines, it will quickly reflect this information and keep the information provided to users up-to-date. This allows the Knowledge Verification Department to always provide the latest and most accurate information and gain the trust of users.

[0034] The article generation unit uses a generation AI to generate articles based on verified knowledge. Specifically, the generation AI automatically generates articles in a user-friendly format based on collected information. For example, the generation AI automatically creates articles on medical information and provides them to users. The generation AI can organize information and create easy-to-understand articles based on the structure of the text and the algorithms used. This allows the article generation unit to quickly provide high-quality information to users. Furthermore, the article generation unit can regularly update the generated articles to provide the latest information. For example, if there are results from new medical research or changes in guidelines, the article will be updated to reflect that information quickly. This allows the article generation unit to always provide the latest and most accurate information and gain the trust of users.

[0035] The needs-catching unit can capture users' information needs through internet searches. For example, the needs-catching unit uses internet searches to capture users' needs for information. For instance, if there are many searches for specific medical information or legal information, it will capture that information. This allows for the rapid capture of users' information needs by utilizing internet searches. Some or all of the above-described processing in the needs-catching unit may be performed using AI, for example, or without AI. For example, the needs-catching unit can input internet search queries into AI, which will analyze the search queries and capture the user's information needs.

[0036] The interviewing unit can conduct detailed interviews via a messaging app with users who have provided excellent answers on the Q&A site. For example, the interviewing unit can send questions to users via the messaging app and collect answers. For example, regarding medical information, it can ask detailed questions to doctors and specialists and collect their knowledge. This allows for efficient collection of user knowledge through detailed interviews via the messaging app. Some or all of the above-described processes in the interviewing unit may be performed using, for example, a generative AI, or not. For example, the interviewing unit can input the content of the questions to be sent via the messaging app into a generative AI, which can then generate the questions.

[0037] The knowledge gathering unit can collect knowledge and opinions from multiple experts. For example, the knowledge gathering unit can collect knowledge by interviewing experts. For example, it can have the collected medical information verified by other doctors and experts to ensure its accuracy. By collecting knowledge from multiple experts, the reliability of the information can be increased. Some or all of the above processes in the knowledge gathering unit may be performed using AI, for example, or not using AI. For example, the knowledge gathering unit can input the knowledge collected from experts into AI, which can then organize and analyze the knowledge.

[0038] The knowledge verification unit allows other experts to verify the accuracy of the collected knowledge. For example, the knowledge verification unit can perform cross-checks to verify the accuracy of the knowledge. For example, it can have other doctors or experts verify the collected medical information to ensure its accuracy. This ensures the accuracy of the information through verification by other experts. Some or all of the above processes in the knowledge verification unit may be performed using AI, or not using AI. For example, the knowledge verification unit can input the collected knowledge into an AI, which can then verify the accuracy of the knowledge.

[0039] The article generation unit can automatically generate articles for MyBest based on verified knowledge. For example, the article generation unit uses a generation AI to generate articles based on the structure of the text and the algorithm used. For example, the generation AI can automatically create articles on medical information and provide them to users. This allows users to quickly obtain reliable information through automatically generated articles. Some or all of the above-described processes in the article generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the article generation unit can input verified knowledge into a generation AI, and the generation AI can generate an article.

[0040] The needs-catching unit can identify the optimal information needs by analyzing the user's past search history during needs detection. For example, the needs-catching unit can identify relevant information needs based on keywords the user has searched for in the past. For example, it can prioritize capturing frequently searched topics from the user's past search history. For example, it can analyze the user's search history to identify information needs related to seasons and events. In this way, the optimal information needs can be identified by analyzing the user's past search history. Some or all of the above processing in the needs-catching unit may be performed using AI, for example, or without AI. For example, the needs-catching unit can input the user's search history data into AI, which can analyze the search history and identify the optimal information needs.

[0041] The needs detection unit can filter information based on the user's current areas of interest when detecting needs. For example, the needs detection unit prioritizes capturing information related to topics the user is currently interested in. For example, it filters and provides relevant information based on the user's areas of interest. For example, it analyzes the user's areas of interest and captures the most relevant information. This allows the system to provide highly relevant information by filtering it based on the user's areas of interest. Some or all of the above processing in the needs detection unit may be performed using AI, or not. For example, the needs detection unit can input user area of ​​interest data into an AI, which can then analyze the areas of interest and filter the information.

[0042] The needs-catching unit can prioritize capturing highly relevant information by considering the user's geographical location information when capturing needs. For example, the needs-catching unit can prioritize capturing region-related information based on the user's current location. For example, it can analyze the user's geographical location information and provide the most relevant information. For example, it can capture local events and news based on the user's location information. In this way, by considering the user's geographical location information, it can provide highly relevant information. Some or all of the above processing in the needs-catching unit may be performed using AI, for example, or without AI. For example, the needs-catching unit can input the user's geographical location information data into AI, which can analyze the location information and capture highly relevant information.

[0043] The needs-catching unit can analyze a user's social media activity and identify relevant information needs when identifying needs. For example, the needs-catching unit can analyze the content of a user's social media posts to identify relevant information needs. For example, it can identify topics of high interest from the user's social media activity. For example, it can identify relevant information based on the content of posts by the user's followers and friends on social media. In this way, relevant information needs can be identified by analyzing the user's social media activity. Some or all of the above processing in the needs-catching unit may be performed using AI, for example, or without AI. For example, the needs-catching unit can input the user's social media data into AI, which can analyze social media activity and identify relevant information needs.

[0044] The interviewing unit can analyze the history of past excellent respondents during the interview process and select the most appropriate questions. For example, the interviewing unit can analyze the answers of users who have provided excellent answers in the past and select relevant questions. For example, it can select the most effective questions from the history of excellent respondents. For example, it can select the most appropriate questions based on past response history. In this way, the most appropriate questions can be selected by analyzing the history of past respondents. Some or all of the above processing in the interviewing unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the interviewing unit can input past respondent history data into a generative AI, which can then analyze the history and select the most appropriate questions.

[0045] The interviewing unit can apply different question algorithms during the interview depending on the respondent's area of ​​expertise. For example, the interviewing unit will ask detailed questions about medicine to medical professionals, specific questions about law to legal professionals, and specialized questions about technology to technology experts. This allows for the collection of more specialized knowledge by asking questions tailored to the respondent's area of ​​expertise. Some or all of the above processing in the interviewing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interviewing unit can input the respondent's area of ​​expertise data into a generative AI, which can then apply a question algorithm to generate the questions.

[0046] The interviewing unit can prioritize asking highly relevant questions during the interview, taking into account the respondent's geographical location. For example, the interviewing unit can prioritize asking region-related questions based on the respondent's current location. For example, it can analyze the respondent's geographical location and ask the most relevant questions. For example, it can ask questions related to local events or news based on the respondent's location. In this way, highly relevant questions can be asked by considering the respondent's geographical location. Some or all of the above processing in the interviewing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interviewing unit can input the respondent's geographical location data into a generative AI, which can analyze the location information and generate highly relevant questions.

[0047] The interviewing unit can analyze the respondent's social media activity during the interview and ask relevant questions. For example, the interviewing unit can analyze the content of the respondent's social media posts and ask relevant questions. For example, it can ask questions about topics of high interest based on the respondent's social media activity. For example, it can ask relevant questions based on the content of posts by the respondent's followers and friends on social media. In this way, relevant questions can be asked by analyzing the respondent's social media activity. Some or all of the above processing in the interviewing unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the interviewing unit can input the respondent's social media data into a generative AI, which can analyze the social media activity and generate relevant questions.

[0048] The knowledge acquisition unit can analyze the knowledge of past experts and select the most suitable knowledge during the knowledge acquisition process. For example, the knowledge acquisition unit can analyze the knowledge of experts who have provided excellent knowledge in the past and select relevant knowledge. For example, it can select the most effective knowledge from the past knowledge of experts. For example, it can select the most suitable knowledge based on the knowledge of past experts. In this way, the most suitable knowledge can be selected by analyzing the knowledge of past experts. Some or all of the above-described processes in the knowledge acquisition unit may be performed using AI, for example, or without AI. For example, the knowledge acquisition unit can input past expert knowledge data into AI, which can then analyze the knowledge and select the most suitable knowledge.

[0049] The knowledge acquisition unit can apply different acquisition algorithms based on the expert's attribute information when acquiring knowledge. For example, the knowledge acquisition unit prioritizes acquiring medical knowledge for medical professionals, legal knowledge for legal professionals, and technical knowledge for technical professionals. By acquiring knowledge based on the expert's attribute information, more relevant knowledge can be obtained. Some or all of the above processing in the knowledge acquisition unit may be performed using AI, for example, or without AI. For example, the knowledge acquisition unit can input expert attribute information data into AI, which can analyze the attribute information and apply an acquisition algorithm to acquire knowledge.

[0050] The knowledge acquisition unit can prioritize the collection of highly relevant knowledge by considering the geographical location information of experts during the knowledge acquisition process. For example, the knowledge acquisition unit can prioritize the collection of region-related knowledge based on the expert's current location. For example, it can analyze the expert's geographical location information and collect the most relevant knowledge. For example, it can collect knowledge related to local events and news based on the expert's location information. In this way, highly relevant knowledge can be collected by considering the expert's geographical location information. Some or all of the above processing in the knowledge acquisition unit may be performed using AI, for example, or without AI. For example, the knowledge acquisition unit can input the expert's geographical location information data into AI, which can analyze the location information and collect highly relevant knowledge.

[0051] The knowledge gathering unit can analyze experts' social media activities and collect relevant knowledge during the knowledge gathering process. For example, the knowledge gathering unit can analyze the content of experts' social media posts and collect relevant knowledge. For example, it can collect knowledge on topics of high interest from experts' social media activities. For example, it can collect relevant knowledge based on the content of posts by experts' followers and friends on social media. In this way, relevant knowledge can be collected by analyzing experts' social media activities. Some or all of the above processing in the knowledge gathering unit may be performed using AI, for example, or without AI. For example, the knowledge gathering unit can input experts' social media data into AI, which can then analyze social media activities and collect relevant knowledge.

[0052] The knowledge verification unit can analyze past verification history and select the optimal verification method during knowledge verification. For example, the knowledge verification unit can select the optimal verification method based on verification methods that have been effective in the past. For example, it can analyze the verification history and select the most reliable verification method. For example, it can select the optimal verification method based on past verification history. In this way, the optimal verification method can be selected by analyzing past verification history. Some or all of the above processing in the knowledge verification unit may be performed using AI, for example, or without using AI. For example, the knowledge verification unit can input past verification history data into AI, which can analyze the verification history and select the optimal verification method.

[0053] The knowledge verification unit can apply different verification algorithms depending on the verifier's area of ​​expertise during knowledge verification. For example, the knowledge verification unit can apply a method for verifying medical knowledge to a medical professional, a method for verifying legal knowledge to a legal professional, and a method for verifying technical knowledge to a technical professional. This allows for more accurate knowledge verification by performing verification according to the verifier's area of ​​expertise. Some or all of the above-described processes in the knowledge verification unit may be performed using AI, for example, or without AI. For example, the knowledge verification unit can input the verifier's area of ​​expertise data into an AI, which can then analyze the area of ​​expertise and apply a verification algorithm to verify the knowledge.

[0054] The knowledge verification unit can prioritize verifying highly relevant knowledge by considering the geographical location information of the verifier during knowledge verification. For example, the knowledge verification unit can prioritize verifying knowledge related to a region based on the verifier's current location. For example, it can analyze the verifier's geographical location information and verify the most relevant knowledge. For example, it can verify knowledge related to local events and news based on the verifier's location information. In this way, highly relevant knowledge can be verified by considering the verifier's geographical location information. Some or all of the above processing in the knowledge verification unit may be performed using AI, for example, or without using AI. For example, the knowledge verification unit can input the verifier's geographical location information data into AI, which can analyze the location information and verify highly relevant knowledge.

[0055] The knowledge verification unit can analyze the verifier's social media activity and verify relevant knowledge during knowledge verification. For example, the knowledge verification unit can analyze the content of the verifier's social media posts and verify relevant knowledge. For example, it can verify knowledge about topics of high interest from the verifier's social media activity. For example, it can verify relevant knowledge based on the content of posts by the verifier's followers and friends on social media. In this way, relevant knowledge can be verified by analyzing the verifier's social media activity. Some or all of the above processing in the knowledge verification unit may be performed using AI, for example, or without AI. For example, the knowledge verification unit can input the verifier's social media data into AI, which can analyze social media activity and verify relevant knowledge.

[0056] The article generation unit can adjust the level of detail in an article based on the importance of the collected knowledge during article generation. For example, the article generation unit can generate a detailed article based on highly important knowledge, or a concise article based on less important knowledge. For example, it can adjust the level of detail in an article according to the importance of the knowledge. This allows for the generation of more appropriate articles by adjusting the level of detail based on the importance of the collected knowledge. Some or all of the above-described processes in the article generation unit may be performed using a generation AI, or without a generation AI. For example, the article generation unit can input the importance data of the collected knowledge into a generation AI, which can then analyze the importance of the knowledge and adjust the level of detail in the article.

[0057] The article generation unit can apply different generation algorithms depending on the article category when generating an article. For example, for articles in the medical category, the article generation unit applies a generation algorithm related to medicine. For example, for articles in the legal category, it applies a generation algorithm related to law. For example, for articles in the technology category, it applies a generation algorithm related to technology. By applying a generation algorithm appropriate to the article category, more appropriate articles can be generated. Some or all of the above processing in the article generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the article generation unit can input article category data into a generation AI, and the generation AI can generate an article by applying a generation algorithm appropriate to the category.

[0058] The article generation unit can determine the priority of articles based on the submission timing of the collected knowledge when generating articles. For example, the article generation unit may prioritize generating articles based on the latest knowledge, or postpone generating articles based on older knowledge, or determine the priority of articles according to the submission timing of the knowledge. This allows for the generation of more appropriate articles by determining the priority of articles based on the submission timing of the collected knowledge. Some or all of the above processing in the article generation unit may be performed using a generation AI, or without a generation AI. For example, the article generation unit can input the submission timing data of the collected knowledge into a generation AI, which can analyze the submission timing and determine the priority of articles.

[0059] The article generation unit can adjust the order of articles based on the relevance of the collected knowledge during article generation. For example, the article generation unit may determine the order of articles based on highly relevant knowledge, or postpone articles based on less relevant knowledge, or adjust the order of articles according to the relevance of the knowledge. This allows for the generation of more appropriate articles by adjusting the order of articles based on the relevance of the collected knowledge. Some or all of the above-described processes in the article generation unit may be performed using a generation AI, or without a generation AI. For example, the article generation unit can input the relevance data of the collected knowledge into a generation AI, which can then analyze the relevance and adjust the order of the articles.

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

[0061] The InfoGenius system may further include a history analysis unit that analyzes the user's past behavior history and determines the optimal method of providing information. For example, the history analysis unit analyzes what kind of information the user has requested in the past and provides relevant information preferentially. For example, it provides relevant information based on keywords the user has searched for in the past. For example, it provides information that is frequently requested based on the user's past behavior history. In this way, the optimal method of providing information can be determined by analyzing the user's past behavior history. Some or all of the above processing in the history analysis unit may be performed using AI, for example, or without AI. For example, the history analysis unit can input the user's behavior history data into AI, which can analyze the behavior history and determine the optimal method of providing information.

[0062] The InfoGenius system may further include a location information unit that provides highly relevant information by considering the user's geographical location. For example, the location information unit may prioritize providing region-related information based on the user's current location. For example, it may analyze the user's geographical location and provide the most relevant information. For example, it may provide local events and news based on the user's location. In this way, highly relevant information can be provided by considering the user's geographical location. Some or all of the above processing in the location information unit may be performed using AI, for example, or without AI. For example, the location information unit can input the user's geographical location data into AI, which can then analyze the location information and provide highly relevant information.

[0063] The InfoGenius system may further include a social media analysis unit that analyzes users' social media activity and provides relevant information. The social media analysis unit, for example, analyzes the content of users' social media posts and provides relevant information. For example, it provides information on topics of high interest based on the user's social media activity. For example, it provides relevant information based on the content of posts by the user's social media followers and friends. This allows the system to provide relevant information by analyzing the user's social media activity. Some or all of the above-described processes in the social media analysis unit may be performed using AI, for example, or without AI. For example, the social media analysis unit can input the user's social media data into an AI, which can then analyze the social media activity and provide relevant information.

[0064] The following briefly describes the processing flow for example form 1.

[0065] Step 1: The needs-catching unit captures the user's information needs. For example, it can capture the user's need for information using internet search. If there is a high volume of searches for specific medical information or legal information, it will capture that information. Step 2: The Hearing Unit uses a generation AI to conduct detailed interviews with users who have provided excellent answers on the Q&A site, based on the information gathered by the Needs Catching Unit. For example, regarding medical information, it asks detailed questions to doctors and specialists to collect their knowledge. The Hearing Unit can, for example, send questions to users via messaging apps and collect their answers. Step 3: The knowledge gathering department collects knowledge and opinions from multiple experts. For example, it has the collected medical information verified by other doctors and experts to ensure its accuracy. The knowledge gathering department can also collect knowledge by, for example, conducting interviews with experts. Step 4: The knowledge verification unit verifies the accuracy of the collected knowledge. For example, it ensures the accuracy of the collected medical information by having it checked by other doctors or specialists. The knowledge verification unit can also verify the accuracy of the knowledge by, for example, performing cross-checks. Step 5: The article generation unit uses a generation AI to generate articles based on the verified knowledge. For example, the generation AI automatically creates articles about medical information and provides them to the user. The article generation unit can, for example, use a generation AI to generate articles based on the structure of the text and the algorithm used.

[0066] (Example of form 2) The InfoGenius system according to an embodiment of the present invention is a system for providing users with the information they seek quickly and reliably. This system captures users' information needs, conducts detailed interviews with users who have provided excellent answers in the past on Q&A sites, collects knowledge and opinions from multiple experts, and has other experts verify the accuracy of the content to aggregate highly reliable information, and a generating AI automatically generates articles for MyBest. For example, the InfoGenius system captures information that users are increasingly seeking through internet searches. Next, the generating AI conducts detailed interviews with users who have provided excellent answers in the past on Q&A sites via a messaging app. For example, regarding medical information, it asks detailed questions to doctors and experts to collect their knowledge. Subsequently, it collects knowledge and opinions from multiple experts, and has other experts verify the accuracy of the content. For example, it has other doctors and experts verify the collected medical information to ensure its accuracy. Finally, highly reliable information is aggregated, and based on the results, the generating AI automatically generates articles for MyBest. For example, the generating AI automatically creates an article about medical information and provides it to the user. This allows the InfoGenius system to quickly obtain reliable and high-quality information, supporting efficient decision-making. This process improves the quality and reliability of the information. As a result, the InfoGenius system can efficiently capture users' information needs and provide highly reliable information.

[0067] The InfoGenius system according to this embodiment comprises a needs catching unit, an interviewing unit, a knowledge gathering unit, a knowledge verification unit, and an article generation unit. The needs catching unit catches the user's information needs. For example, the needs catching unit can catch the user's need for information using internet search. For example, if there is a lot of searching for specific medical information or legal information, it will catch that information. The interviewing unit uses a generation AI to conduct detailed interviews with users who have provided excellent answers on Q&A sites, based on the information caught by the needs catching unit. For example, regarding medical information, it will ask detailed questions to doctors and experts and collect their knowledge. The interviewing unit can, for example, send questions to users via a messaging app and collect answers. The knowledge gathering unit collects the knowledge and opinions of multiple experts. For example, it will have the collected medical information checked by other doctors and experts to ensure its accuracy. The knowledge gathering unit can, for example, interview experts to collect knowledge. The knowledge verification unit verifies the accuracy of the collected knowledge. For example, the collected medical information can be verified by other doctors and specialists to ensure its accuracy. The knowledge verification unit can, for example, perform cross-checks to verify the accuracy of the knowledge. The article generation unit uses a generation AI to generate articles based on the verified knowledge. For example, the generation AI can automatically create articles about medical information and provide them to the user. The article generation unit can, for example, use a generation AI to generate articles based on the structure of the text and the algorithm used. As a result, the InfoGenius system according to this embodiment can efficiently capture the user's information needs and provide highly reliable information.

[0068] The Needs Catching Unit captures users' information needs. Specifically, it analyzes trend data from internet search engines and social media to understand what kind of information users are seeking. For example, by collecting search engine query data and analyzing how often specific keywords and phrases are searched, it identifies user interests. It can also analyze social media posts and comments to understand what topics users are discussing. This allows the Needs Catching Unit to quickly capture users' fluctuating information needs in real time and improve the accuracy of information provision throughout the system. Furthermore, the Needs Catching Unit uses natural language processing technology to analyze users' search queries and posts to extract specific information needs. For example, if there is an increase in search queries related to medical information, it can analyze the content of those queries in detail to identify the specific information users are seeking (e.g., treatments or preventive measures for specific diseases). This allows the Needs Catching Unit to more accurately understand users' information needs and smoothly provide information to the next step, the Hearing Unit.

[0069] The Hearing Department uses a generative AI to conduct detailed interviews with users who have provided excellent answers on the Q&A platform, based on information gathered by the Needs Gathering Department. Specifically, the generative AI automatically generates appropriate questions based on the user's information needs and sends them to knowledgeable users. For example, regarding medical information, the generative AI creates detailed questions for doctors and specialists and sends them via messaging apps or email. This allows the Hearing Department to collect detailed answers from specialists and gather foundational data to meet the user's information needs. Furthermore, the generative AI analyzes the collected answers and extracts important information and insights. For example, it can analyze answers from doctors and extract key points regarding treatments and preventive measures for specific diseases. This allows the Hearing Department to efficiently organize the collected information and smoothly provide it to the Knowledge Gathering Department, which is the next step.

[0070] The Knowledge Gathering Department collects knowledge and opinions from multiple experts. Specifically, it ensures the accuracy of collected medical information by having it verified by other doctors and experts. For example, based on information provided by the Interviewing Department, it conducts interviews with other doctors and experts to gather additional knowledge and opinions. This allows the Knowledge Gathering Department to integrate the opinions of multiple experts and improve the accuracy and reliability of the information. Furthermore, the Knowledge Gathering Department stores the collected information in a database, making it accessible to other departments. For example, it stores collected medical information in a database, allowing the Article Generation Department to create articles based on that information. This allows the Knowledge Gathering Department to improve the accuracy and reliability of information provided throughout the entire system.

[0071] The Knowledge Verification Department verifies the accuracy of the collected knowledge. Specifically, it ensures the accuracy of the collected medical information by having other doctors and specialists verify it. For example, it performs cross-checks, ensuring that multiple specialists confirm the same information and guarantee its accuracy. This allows the Knowledge Verification Department to enhance the reliability of the collected information and improve the quality of the information provided to users. Furthermore, the Knowledge Verification Department can regularly update the collected information to provide the latest information. For example, if there are results from new medical research or changes in guidelines, it will quickly reflect this information and keep the information provided to users up-to-date. This allows the Knowledge Verification Department to always provide the latest and most accurate information and gain the trust of users.

[0072] The article generation unit uses a generation AI to generate articles based on verified knowledge. Specifically, the generation AI automatically generates articles in a user-friendly format based on collected information. For example, the generation AI automatically creates articles on medical information and provides them to users. The generation AI can organize information and create easy-to-understand articles based on the structure of the text and the algorithms used. This allows the article generation unit to quickly provide high-quality information to users. Furthermore, the article generation unit can regularly update the generated articles to provide the latest information. For example, if there are results from new medical research or changes in guidelines, the article will be updated to reflect that information quickly. This allows the article generation unit to always provide the latest and most accurate information and gain the trust of users.

[0073] The needs-catching unit can capture users' information needs through internet searches. For example, the needs-catching unit uses internet searches to capture users' needs for information. For instance, if there are many searches for specific medical information or legal information, it will capture that information. This allows for the rapid capture of users' information needs by utilizing internet searches. Some or all of the above-described processing in the needs-catching unit may be performed using AI, for example, or without AI. For example, the needs-catching unit can input internet search queries into AI, which will analyze the search queries and capture the user's information needs.

[0074] The interviewing unit can conduct detailed interviews via a messaging app with users who have provided excellent answers on the Q&A site. For example, the interviewing unit can send questions to users via the messaging app and collect answers. For example, regarding medical information, it can ask detailed questions to doctors and specialists and collect their knowledge. This allows for efficient collection of user knowledge through detailed interviews via the messaging app. Some or all of the above-described processes in the interviewing unit may be performed using, for example, a generative AI, or not. For example, the interviewing unit can input the content of the questions to be sent via the messaging app into a generative AI, which can then generate the questions.

[0075] The knowledge gathering unit can collect knowledge and opinions from multiple experts. For example, the knowledge gathering unit can collect knowledge by interviewing experts. For example, it can have the collected medical information verified by other doctors and experts to ensure its accuracy. By collecting knowledge from multiple experts, the reliability of the information can be increased. Some or all of the above processes in the knowledge gathering unit may be performed using AI, for example, or not using AI. For example, the knowledge gathering unit can input the knowledge collected from experts into AI, which can then organize and analyze the knowledge.

[0076] The knowledge verification unit allows other experts to verify the accuracy of the collected knowledge. For example, the knowledge verification unit can perform cross-checks to verify the accuracy of the knowledge. For example, it can have other doctors or experts verify the collected medical information to ensure its accuracy. This ensures the accuracy of the information through verification by other experts. Some or all of the above processes in the knowledge verification unit may be performed using AI, or not using AI. For example, the knowledge verification unit can input the collected knowledge into an AI, which can then verify the accuracy of the knowledge.

[0077] The article generation unit can automatically generate articles for MyBest based on verified knowledge. For example, the article generation unit uses a generation AI to generate articles based on the structure of the text and the algorithm used. For example, the generation AI can automatically create articles on medical information and provide them to users. This allows users to quickly obtain reliable information through automatically generated articles. Some or all of the above-described processes in the article generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the article generation unit can input verified knowledge into a generation AI, and the generation AI can generate an article.

[0078] The needs-catching unit can estimate the user's emotions and prioritize information needs based on those emotions. For example, if the user is feeling anxious, the needs-catching unit will prioritize capturing information of high urgency. For example, if the user is interested, it will prioritize capturing topics of high interest. For example, if the user is relaxed, it will prioritize capturing general information. This allows for the provision of more appropriate information by prioritizing information needs according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the needs-catching unit may be performed using AI or not. For example, the needs-catching unit can input user emotion data into an AI, which can then estimate the emotion and determine the priority of information needs.

[0079] The needs-catching unit can identify the optimal information needs by analyzing the user's past search history during needs detection. For example, the needs-catching unit can identify relevant information needs based on keywords the user has searched for in the past. For example, it can prioritize capturing frequently searched topics from the user's past search history. For example, it can analyze the user's search history to identify information needs related to seasons and events. In this way, the optimal information needs can be identified by analyzing the user's past search history. Some or all of the above processing in the needs-catching unit may be performed using AI, for example, or without AI. For example, the needs-catching unit can input the user's search history data into AI, which can analyze the search history and identify the optimal information needs.

[0080] The needs detection unit can filter information based on the user's current areas of interest when detecting needs. For example, the needs detection unit prioritizes capturing information related to topics the user is currently interested in. For example, it filters and provides relevant information based on the user's areas of interest. For example, it analyzes the user's areas of interest and captures the most relevant information. This allows the system to provide highly relevant information by filtering it based on the user's areas of interest. Some or all of the above processing in the needs detection unit may be performed using AI, or not. For example, the needs detection unit can input user area of ​​interest data into an AI, which can then analyze the areas of interest and filter the information.

[0081] The needs-catching unit can estimate the user's emotions and adjust the timing of information acquisition based on the estimated emotions. For example, if the user is stressed, the needs-catching unit will provide information quickly. For example, if the user is relaxed, it will provide information at an appropriate time. For example, if the user is excited, it will provide information immediately. By adjusting the timing of information acquisition according to the user's emotions, information can be provided at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the needs-catching unit may be performed using AI or not using AI. For example, the needs-catching unit can input user emotion data into an AI, which can estimate the emotion and adjust the timing of information acquisition.

[0082] The needs-catching unit can prioritize capturing highly relevant information by considering the user's geographical location information when capturing needs. For example, the needs-catching unit can prioritize capturing region-related information based on the user's current location. For example, it can analyze the user's geographical location information and provide the most relevant information. For example, it can capture local events and news based on the user's location information. In this way, by considering the user's geographical location information, it can provide highly relevant information. Some or all of the above processing in the needs-catching unit may be performed using AI, for example, or without AI. For example, the needs-catching unit can input the user's geographical location information data into AI, which can analyze the location information and capture highly relevant information.

[0083] The needs-catching unit can analyze a user's social media activity and identify relevant information needs when identifying needs. For example, the needs-catching unit can analyze the content of a user's social media posts to identify relevant information needs. For example, it can identify topics of high interest from the user's social media activity. For example, it can identify relevant information based on the content of posts by the user's followers and friends on social media. In this way, relevant information needs can be identified by analyzing the user's social media activity. Some or all of the above processing in the needs-catching unit may be performed using AI, for example, or without AI. For example, the needs-catching unit can input the user's social media data into AI, which can analyze social media activity and identify relevant information needs.

[0084] The interviewing unit can estimate the user's emotions and adjust the interview questions based on the estimated emotions. For example, if the user is feeling anxious, the interviewing unit will ask questions that provide reassurance. For example, if the user is interested, it will ask detailed questions. For example, if the user is relaxed, it will ask general questions. By adjusting the questions according to the user's emotions, a more appropriate interview becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the interviewing unit may be performed using a generative AI, or not using a generative AI. For example, the interviewing unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the questions.

[0085] The interviewing unit can analyze the history of past excellent respondents during the interview process and select the most appropriate questions. For example, the interviewing unit can analyze the answers of users who have provided excellent answers in the past and select relevant questions. For example, it can select the most effective questions from the history of excellent respondents. For example, it can select the most appropriate questions based on past response history. In this way, the most appropriate questions can be selected by analyzing the history of past respondents. Some or all of the above processing in the interviewing unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the interviewing unit can input past respondent history data into a generative AI, which can then analyze the history and select the most appropriate questions.

[0086] The interviewing unit can apply different question algorithms during the interview depending on the respondent's area of ​​expertise. For example, the interviewing unit will ask detailed questions about medicine to medical professionals, specific questions about law to legal professionals, and specialized questions about technology to technology experts. This allows for the collection of more specialized knowledge by asking questions tailored to the respondent's area of ​​expertise. Some or all of the above processing in the interviewing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interviewing unit can input the respondent's area of ​​expertise data into a generative AI, which can then apply a question algorithm to generate the questions.

[0087] The interview unit can estimate the user's emotions and adjust the timing of the interview based on the estimated emotions. For example, if the user is stressed, the interview unit will conduct the interview quickly. For example, if the user is relaxed, the interview will be conducted at an appropriate time. For example, if the user is excited, the interview will be conducted immediately. By adjusting the timing of the interview according to the user's emotions, the interview can be conducted at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the interview unit may be performed using a generative AI, or not using a generative AI. For example, the interview unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the timing of the interview.

[0088] The interviewing unit can prioritize asking highly relevant questions during the interview, taking into account the respondent's geographical location. For example, the interviewing unit can prioritize asking region-related questions based on the respondent's current location. For example, it can analyze the respondent's geographical location and ask the most relevant questions. For example, it can ask questions related to local events or news based on the respondent's location. In this way, highly relevant questions can be asked by considering the respondent's geographical location. Some or all of the above processing in the interviewing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the interviewing unit can input the respondent's geographical location data into a generative AI, which can analyze the location information and generate highly relevant questions.

[0089] The interviewing unit can analyze the respondent's social media activity during the interview and ask relevant questions. For example, the interviewing unit can analyze the content of the respondent's social media posts and ask relevant questions. For example, it can ask questions about topics of high interest based on the respondent's social media activity. For example, it can ask relevant questions based on the content of posts by the respondent's followers and friends on social media. In this way, relevant questions can be asked by analyzing the respondent's social media activity. Some or all of the above processing in the interviewing unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the interviewing unit can input the respondent's social media data into a generative AI, which can analyze the social media activity and generate relevant questions.

[0090] The knowledge gathering unit can estimate the user's emotions and determine the priority of knowledge to collect based on the estimated user emotions. For example, if the user is feeling anxious, the knowledge gathering unit will prioritize collecting urgent knowledge. For example, if the user is interested, it will prioritize collecting knowledge of high interest. For example, if the user is relaxed, it will prioritize collecting general knowledge. In this way, more appropriate knowledge can be collected by determining the priority of knowledge according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the knowledge gathering unit may be performed using AI, or not using AI. For example, the knowledge gathering unit can input user emotion data into an AI, which can estimate the emotions and determine the priority of knowledge.

[0091] The knowledge acquisition unit can analyze the knowledge of past experts and select the most suitable knowledge during the knowledge acquisition process. For example, the knowledge acquisition unit can analyze the knowledge of experts who have provided excellent knowledge in the past and select relevant knowledge. For example, it can select the most effective knowledge from the past knowledge of experts. For example, it can select the most suitable knowledge based on the knowledge of past experts. In this way, the most suitable knowledge can be selected by analyzing the knowledge of past experts. Some or all of the above-described processes in the knowledge acquisition unit may be performed using AI, for example, or without AI. For example, the knowledge acquisition unit can input past expert knowledge data into AI, which can then analyze the knowledge and select the most suitable knowledge.

[0092] The knowledge acquisition unit can apply different acquisition algorithms based on the expert's attribute information when acquiring knowledge. For example, the knowledge acquisition unit prioritizes acquiring medical knowledge for medical professionals, legal knowledge for legal professionals, and technical knowledge for technical professionals. By acquiring knowledge based on the expert's attribute information, more relevant knowledge can be obtained. Some or all of the above processing in the knowledge acquisition unit may be performed using AI, for example, or without AI. For example, the knowledge acquisition unit can input expert attribute information data into AI, which can analyze the attribute information and apply an acquisition algorithm to acquire knowledge.

[0093] The knowledge acquisition unit can estimate the user's emotions and adjust the timing of knowledge acquisition based on the estimated emotions. For example, if the user is stressed, the knowledge acquisition unit will acquire knowledge quickly. For example, if the user is relaxed, it will acquire knowledge at an appropriate time. For example, if the user is excited, it will acquire knowledge immediately. By adjusting the timing of knowledge acquisition according to the user's emotions, knowledge can be acquired at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the knowledge acquisition unit may be performed using AI, or not using AI. For example, the knowledge acquisition unit can input user emotion data into an AI, which can estimate the emotions and adjust the timing of knowledge acquisition.

[0094] The knowledge acquisition unit can prioritize the collection of highly relevant knowledge by considering the geographical location information of experts during the knowledge acquisition process. For example, the knowledge acquisition unit can prioritize the collection of region-related knowledge based on the expert's current location. For example, it can analyze the expert's geographical location information and collect the most relevant knowledge. For example, it can collect knowledge related to local events and news based on the expert's location information. In this way, highly relevant knowledge can be collected by considering the expert's geographical location information. Some or all of the above processing in the knowledge acquisition unit may be performed using AI, for example, or without AI. For example, the knowledge acquisition unit can input the expert's geographical location information data into AI, which can analyze the location information and collect highly relevant knowledge.

[0095] The knowledge gathering unit can analyze experts' social media activities and collect relevant knowledge during the knowledge gathering process. For example, the knowledge gathering unit can analyze the content of experts' social media posts and collect relevant knowledge. For example, it can collect knowledge on topics of high interest from experts' social media activities. For example, it can collect relevant knowledge based on the content of posts by experts' followers and friends on social media. In this way, relevant knowledge can be collected by analyzing experts' social media activities. Some or all of the above processing in the knowledge gathering unit may be performed using AI, for example, or without AI. For example, the knowledge gathering unit can input experts' social media data into AI, which can then analyze social media activities and collect relevant knowledge.

[0096] The knowledge verification unit can estimate the user's emotions and adjust the knowledge verification method based on the estimated user emotions. For example, if the user is feeling anxious, the knowledge verification unit can provide a detailed verification method. For example, if the user is interested, it can provide a verification method related to a topic of high interest. For example, if the user is relaxed, it can provide a general verification method. This allows for more appropriate verification by adjusting the knowledge verification method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the knowledge verification unit may be performed using AI or not using AI. For example, the knowledge verification unit can input user emotion data into an AI, which can estimate the emotions and adjust the verification method.

[0097] The knowledge verification unit can analyze past verification history and select the optimal verification method during knowledge verification. For example, the knowledge verification unit can select the optimal verification method based on verification methods that have been effective in the past. For example, it can analyze the verification history and select the most reliable verification method. For example, it can select the optimal verification method based on past verification history. In this way, the optimal verification method can be selected by analyzing past verification history. Some or all of the above processing in the knowledge verification unit may be performed using AI, for example, or without using AI. For example, the knowledge verification unit can input past verification history data into AI, which can analyze the verification history and select the optimal verification method.

[0098] The knowledge verification unit can apply different verification algorithms depending on the verifier's area of ​​expertise during knowledge verification. For example, the knowledge verification unit can apply a method for verifying medical knowledge to a medical professional, a method for verifying legal knowledge to a legal professional, and a method for verifying technical knowledge to a technical professional. This allows for more accurate knowledge verification by performing verification according to the verifier's area of ​​expertise. Some or all of the above-described processes in the knowledge verification unit may be performed using AI, for example, or without AI. For example, the knowledge verification unit can input the verifier's area of ​​expertise data into an AI, which can then analyze the area of ​​expertise and apply a verification algorithm to verify the knowledge.

[0099] The knowledge verification unit can estimate the user's emotions and adjust the timing of knowledge verification based on the estimated emotions. For example, if the user is stressed, the knowledge verification unit will quickly verify the knowledge. For example, if the user is relaxed, the knowledge will be verified at an appropriate time. For example, if the user is excited, the knowledge will be verified immediately. By adjusting the timing of knowledge verification according to the user's emotions, knowledge can be verified at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the knowledge verification unit may be performed using AI or not using AI. For example, the knowledge verification unit can input user emotion data into an AI, which can estimate the emotion and adjust the timing of knowledge verification.

[0100] The knowledge verification unit can prioritize verifying highly relevant knowledge by considering the geographical location information of the verifier during knowledge verification. For example, the knowledge verification unit can prioritize verifying knowledge related to a region based on the verifier's current location. For example, it can analyze the verifier's geographical location information and verify the most relevant knowledge. For example, it can verify knowledge related to local events and news based on the verifier's location information. In this way, highly relevant knowledge can be verified by considering the verifier's geographical location information. Some or all of the above processing in the knowledge verification unit may be performed using AI, for example, or without using AI. For example, the knowledge verification unit can input the verifier's geographical location information data into AI, which can analyze the location information and verify highly relevant knowledge.

[0101] The knowledge verification unit can analyze the verifier's social media activity and verify relevant knowledge during knowledge verification. For example, the knowledge verification unit can analyze the content of the verifier's social media posts and verify relevant knowledge. For example, it can verify knowledge about topics of high interest from the verifier's social media activity. For example, it can verify relevant knowledge based on the content of posts by the verifier's followers and friends on social media. In this way, relevant knowledge can be verified by analyzing the verifier's social media activity. Some or all of the above processing in the knowledge verification unit may be performed using AI, for example, or without AI. For example, the knowledge verification unit can input the verifier's social media data into AI, which can analyze social media activity and verify relevant knowledge.

[0102] The article generation unit can estimate the user's emotions and adjust the way the article is written based on those estimated emotions. For example, if the user is feeling anxious, the article generation unit will use a reassuring style of writing. For example, if the user is interested, it will use a style of writing that includes detailed information. For example, if the user is relaxed, it will use a general style of writing. By adjusting the way the article is written according to the user's emotions, a more appropriate article can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processes in the article generation unit may be performed using a generative AI, or not using a generative AI. For example, the article generation unit can input user emotion data into a generative AI, which can then estimate the emotion and adjust the way the article is written.

[0103] The article generation unit can adjust the level of detail in an article based on the importance of the collected knowledge during article generation. For example, the article generation unit can generate a detailed article based on highly important knowledge, or a concise article based on less important knowledge. For example, it can adjust the level of detail in an article according to the importance of the knowledge. This allows for the generation of more appropriate articles by adjusting the level of detail based on the importance of the collected knowledge. Some or all of the above-described processes in the article generation unit may be performed using a generation AI, or without a generation AI. For example, the article generation unit can input the importance data of the collected knowledge into a generation AI, which can then analyze the importance of the knowledge and adjust the level of detail in the article.

[0104] The article generation unit can apply different generation algorithms depending on the article category when generating an article. For example, for articles in the medical category, the article generation unit applies a generation algorithm related to medicine. For example, for articles in the legal category, it applies a generation algorithm related to law. For example, for articles in the technology category, it applies a generation algorithm related to technology. By applying a generation algorithm appropriate to the article category, more appropriate articles can be generated. Some or all of the above processing in the article generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the article generation unit can input article category data into a generation AI, and the generation AI can generate an article by applying a generation algorithm appropriate to the category.

[0105] The article generation unit can estimate the user's emotions and adjust the length of the article based on the estimated emotions. For example, if the user is in a hurry, the article generation unit will generate a short, concise article. For example, if the user is relaxed, it will generate a longer article with detailed explanations. For example, if the user is excited, it will generate an article with visually stimulating effects. By adjusting the length of the article according to the user's emotions, it is possible to generate more appropriate articles. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the article generation unit may be performed using a generation AI, or not using a generation AI. For example, the article generation unit can input user emotion data into a generation AI, which can estimate the emotions and adjust the length of the article.

[0106] The article generation unit can determine the priority of articles based on the submission timing of the collected knowledge when generating articles. For example, the article generation unit may prioritize generating articles based on the latest knowledge, or postpone generating articles based on older knowledge, or determine the priority of articles according to the submission timing of the knowledge. This allows for the generation of more appropriate articles by determining the priority of articles based on the submission timing of the collected knowledge. Some or all of the above processing in the article generation unit may be performed using a generation AI, or without a generation AI. For example, the article generation unit can input the submission timing data of the collected knowledge into a generation AI, which can analyze the submission timing and determine the priority of articles.

[0107] The article generation unit can adjust the order of articles based on the relevance of the collected knowledge during article generation. For example, the article generation unit may determine the order of articles based on highly relevant knowledge, or postpone articles based on less relevant knowledge, or adjust the order of articles according to the relevance of the knowledge. This allows for the generation of more appropriate articles by adjusting the order of articles based on the relevance of the collected knowledge. Some or all of the above-described processes in the article generation unit may be performed using a generation AI, or without a generation AI. For example, the article generation unit can input the relevance data of the collected knowledge into a generation AI, which can then analyze the relevance and adjust the order of the articles.

[0108] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0109] The InfoGenius system may further include a delivery unit that estimates the user's emotions and adjusts the way information is delivered based on the estimated emotions. For example, if the user is feeling anxious, the delivery unit will provide information using reassuring language. For example, if the user is interested, it will provide detailed information. For example, if the user is relaxed, it will provide general information. This allows for more appropriate information delivery by adjusting the way information is delivered according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Some or all of the above processing in the delivery unit may be performed using AI, or not using AI. For example, the delivery unit can input user emotion data into an AI, which will estimate the emotions and adjust the way information is delivered.

[0110] The InfoGenius system may further include a history analysis unit that analyzes the user's past behavior history and determines the optimal method of providing information. For example, the history analysis unit analyzes what kind of information the user has requested in the past and provides relevant information preferentially. For example, it provides relevant information based on keywords the user has searched for in the past. For example, it provides information that is frequently requested based on the user's past behavior history. In this way, the optimal method of providing information can be determined by analyzing the user's past behavior history. Some or all of the above processing in the history analysis unit may be performed using AI, for example, or without AI. For example, the history analysis unit can input the user's behavior history data into AI, which can analyze the behavior history and determine the optimal method of providing information.

[0111] The InfoGenius system may further include a location information unit that provides highly relevant information by considering the user's geographical location. For example, the location information unit may prioritize providing region-related information based on the user's current location. For example, it may analyze the user's geographical location and provide the most relevant information. For example, it may provide local events and news based on the user's location. In this way, highly relevant information can be provided by considering the user's geographical location. Some or all of the above processing in the location information unit may be performed using AI, for example, or without AI. For example, the location information unit can input the user's geographical location data into AI, which can then analyze the location information and provide highly relevant information.

[0112] The InfoGenius system may further include a social media analysis unit that analyzes users' social media activity and provides relevant information. The social media analysis unit, for example, analyzes the content of users' social media posts and provides relevant information. For example, it provides information on topics of high interest based on the user's social media activity. For example, it provides relevant information based on the content of posts by the user's social media followers and friends. This allows the system to provide relevant information by analyzing the user's social media activity. Some or all of the above-described processes in the social media analysis unit may be performed using AI, for example, or without AI. For example, the social media analysis unit can input the user's social media data into an AI, which can then analyze the social media activity and provide relevant information.

[0113] The InfoGenius system may further include an acquisition timing adjustment unit that estimates the user's emotions and adjusts the timing of information acquisition based on the estimated emotions. For example, the acquisition timing adjustment unit provides information quickly if the user is stressed. For example, it provides information at an appropriate time if the user is relaxed. For example, it provides information immediately if the user is excited. In this way, by adjusting the timing of information acquisition according to the user's emotions, information can be provided at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Some or all of the above processing in the acquisition timing adjustment unit may be performed using AI, for example, or without using AI. For example, the acquisition timing adjustment unit can input user emotion data into AI, which can estimate emotions and adjust the timing of information acquisition.

[0114] The InfoGenius system may further include a priority determination unit that estimates the user's emotions and determines the priority of information based on the estimated emotions. For example, if the user is feeling anxious, the priority determination unit will prioritize providing information of high urgency. For example, if the user is interested, it will prioritize providing information of high interest. For example, if the user is relaxed, it will prioritize providing general information. This makes it possible to provide more appropriate information by determining the priority of information according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Some or all of the above processing in the priority determination unit may be performed using AI, or not using AI. For example, the priority determination unit can input user emotion data into an AI, which will estimate the emotions and determine the priority of information.

[0115] The InfoGenius system may further include a question content adjustment unit that estimates the user's emotions and adjusts the interview questions based on the estimated emotions. For example, if the user is feeling anxious, the question content adjustment unit will ask questions that provide reassurance. For example, if the user is interested, it will ask detailed questions. For example, if the user is relaxed, it will ask general questions. This allows for more appropriate interviews by adjusting the questions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Some or all of the above processing in the question content adjustment unit may be performed using, for example, generative AI, or without generative AI. For example, the question content adjustment unit can input user emotion data into a generative AI, which will estimate the emotions and adjust the questions.

[0116] The InfoGenius system may further include an expression adjustment unit that estimates the user's emotions and adjusts the way the article is presented based on the estimated emotions. For example, if the user is feeling anxious, the expression adjustment unit may use a reassuring expression. For example, if the user is interested, it may use an expression that includes detailed information. For example, if the user is relaxed, it may use a general expression. This allows for the generation of more appropriate articles by adjusting the expression of the article according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. Some or all of the above-described processing in the expression adjustment unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the expression adjustment unit may input user emotion data into a generative AI, which may estimate the emotions and adjust the way the article is presented.

[0117] The InfoGenius system may further include a length adjustment unit that estimates the user's emotions and adjusts the article length based on the estimated emotions. For example, if the user is in a hurry, the length adjustment unit generates a short, concise article. For example, if the user is relaxed, it generates a longer article with detailed explanations. For example, if the user is excited, it generates an article with visually stimulating effects. This allows for the generation of more appropriate articles by adjusting the article length according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. Some or all of the above-described processing in the length adjustment unit may be performed using a generative AI, or not using a generative AI. For example, the length adjustment unit can input user emotion data into a generative AI, which can then estimate the emotions and adjust the article length.

[0118] The InfoGenius system may further include a priority determination unit that estimates the user's emotions and determines the priority of articles based on the estimated emotions. For example, if the user is feeling anxious, the priority determination unit will prioritize generating articles of high urgency. For example, if the user is interested, it will prioritize generating articles of high interest. For example, if the user is relaxed, it will prioritize generating general articles. In this way, by determining the priority of articles according to the user's emotions, more appropriate articles can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. Some or all of the above processing in the priority determination unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the priority determination unit can input user emotion data into a generative AI, which will estimate the emotions and determine the priority of articles.

[0119] The following briefly describes the processing flow for example form 2.

[0120] Step 1: The needs-catching unit captures the user's information needs. For example, it can capture the user's need for information using internet search. If there is a high volume of searches for specific medical information or legal information, it will capture that information. Step 2: The Hearing Unit uses a generation AI to conduct detailed interviews with users who have provided excellent answers on the Q&A site, based on the information gathered by the Needs Catching Unit. For example, regarding medical information, it asks detailed questions to doctors and specialists to collect their knowledge. The Hearing Unit can, for example, send questions to users via messaging apps and collect their answers. Step 3: The knowledge gathering department collects knowledge and opinions from multiple experts. For example, it has the collected medical information verified by other doctors and experts to ensure its accuracy. The knowledge gathering department can also collect knowledge by, for example, conducting interviews with experts. Step 4: The knowledge verification unit verifies the accuracy of the collected knowledge. For example, it ensures the accuracy of the collected medical information by having it checked by other doctors or specialists. The knowledge verification unit can also verify the accuracy of the knowledge by, for example, performing cross-checks. Step 5: The article generation unit uses a generation AI to generate articles based on the verified knowledge. For example, the generation AI automatically creates articles about medical information and provides them to the user. The article generation unit can, for example, use a generation AI to generate articles based on the structure of the text and the algorithm used.

[0121] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0122] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0123] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0124] Each of the multiple elements described above, including the needs-catching unit, interview unit, knowledge-gathering unit, knowledge-verification unit, and article-generating unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the needs-catching unit is implemented by the control unit 46A of the smart device 14 and captures the user's information needs using internet search. The interview unit is implemented by the specific processing unit 290 of the data processing device 12 and conducts detailed interviews with users who have provided excellent answers on the Q&A site using a generating AI. The knowledge-gathering unit is implemented by the control unit 46A of the smart device 14 and collects the knowledge and opinions of multiple experts. The knowledge-verification unit is implemented by the specific processing unit 290 of the data processing device 12 and verifies the accuracy of the collected knowledge. The article-generating unit is implemented by the specific processing unit 290 of the data processing device 12 and generates an article using a generating AI based on the verified knowledge. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0125] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0126] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0127] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0128] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0129] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0130] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0131] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0132] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0133] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0134] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0135] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0136] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0137] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

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

[0139] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0140] Each of the multiple elements described above, including the needs-catching unit, interview unit, knowledge-gathering unit, knowledge-verification unit, and article-generating unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the needs-catching unit is implemented by the control unit 46A of the smart glasses 214 and captures the user's information needs using internet search. The interview unit is implemented by the specific processing unit 290 of the data processing device 12 and conducts detailed interviews with users who have provided excellent answers on the Q&A site using a generating AI. The knowledge-gathering unit is implemented by the control unit 46A of the smart glasses 214 and collects the knowledge and opinions of multiple experts. The knowledge-verification unit is implemented by the specific processing unit 290 of the data processing device 12 and verifies the accuracy of the collected knowledge. The article-generating unit is implemented by the specific processing unit 290 of the data processing device 12 and generates an article using a generating AI based on the verified knowledge. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0141] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0142] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

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

[0144] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

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

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

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

[0148] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0149] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0150] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0151] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

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

[0153] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

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

[0155] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0156] Each of the multiple elements described above, including the needs-catching unit, interview unit, knowledge-gathering unit, knowledge-verification unit, and article-generating unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the needs-catching unit is implemented by the control unit 46A of the headset terminal 314 and captures the user's information needs using internet search. The interview unit is implemented by the specific processing unit 290 of the data processing unit 12 and conducts detailed interviews with users who have provided excellent answers on the Q&A site using a generating AI. The knowledge-gathering unit is implemented by the control unit 46A of the headset terminal 314 and collects the knowledge and opinions of multiple experts. The knowledge-verification unit is implemented by the specific processing unit 290 of the data processing unit 12 and verifies the accuracy of the collected knowledge. The article-generating unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates an article using a generating AI based on the verified knowledge. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0157] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0158] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

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

[0160] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

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

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

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

[0164] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0165] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0166] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0167] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0168] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0169] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0170] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0171] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0172] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0173] Each of the multiple elements described above, including the needs-catching unit, interview unit, knowledge-gathering unit, knowledge-verification unit, and article-generating unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the needs-catching unit is implemented by the control unit 46A of the robot 414 and uses internet search to capture the user's information needs. The interview unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and uses a generating AI to conduct detailed interviews with users who have provided excellent answers on the Q&A site. The knowledge-gathering unit is implemented by, for example, the control unit 46A of the robot 414 and collects the knowledge and opinions of multiple experts. The knowledge-verification unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and verifies the accuracy of the collected knowledge. The article-generating unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and uses a generating AI to generate an article based on the verified knowledge. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0174] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0175] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0176] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0177] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0178] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0179] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0180] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0181] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0182] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0183] 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.

[0184] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0185] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0186] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0187] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0188] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0189] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0190] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0191] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0192] (Note 1) A needs-catching unit that captures the user's information needs, Based on the information gathered by the aforementioned needs gathering unit, the interviewing unit conducts detailed interviews with excellent respondents on the Q&A site. The knowledge gathering unit collects knowledge from multiple experts, based on the knowledge gathered by the aforementioned hearing unit. A knowledge verification unit that verifies the accuracy of the knowledge collected by the aforementioned knowledge acquisition unit, The system comprises an article generation unit that generates an article based on the knowledge confirmed by the aforementioned knowledge verification unit. A system characterized by the following features. (Note 2) The aforementioned needs detection unit is Capture users' information needs through internet searches. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned hearing section is, We will conduct detailed interviews via messaging apps with users who have provided excellent answers on Yahoo! Answers. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned knowledge acquisition unit, Gather the knowledge and opinions of multiple experts. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned knowledge verification unit, The accuracy of the collected knowledge is verified by another expert. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned article generation unit, Based on verified knowledge, automatically generate articles for MyBest. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned needs detection unit is It estimates user emotions and prioritizes information needs based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned needs detection unit is When identifying needs, we analyze the user's past search history to pinpoint their optimal information needs. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned needs detection unit is When identifying needs, filtering is performed based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned needs detection unit is It estimates the user's emotions and adjusts the timing of information acquisition based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned needs detection unit is When identifying user needs, the system prioritizes capturing highly relevant information by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned needs detection unit is When identifying needs, analyze users' social media activity to identify relevant information needs. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned hearing section is, The system estimates the user's emotions and adjusts the interview questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned hearing section is, During the interview, we analyze the history of past high-performing respondents to select the most appropriate questions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned hearing section is, During the interview, different question algorithms are applied depending on the respondent's area of ​​expertise. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned hearing section is, The system estimates the user's emotions and adjusts the timing of interviews based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned hearing section is, During the interview, we prioritize asking questions that are highly relevant to the respondent's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned hearing section is, During the interview, we will analyze the respondents' social media activity and ask relevant questions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned knowledge acquisition unit, It estimates the user's emotions and determines the priority of knowledge to collect based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned knowledge acquisition unit, When gathering knowledge, analyze the knowledge of past experts and select the most relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned knowledge acquisition unit, When gathering knowledge, different collection algorithms are applied based on the attribute information of the experts. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned knowledge acquisition unit, It estimates the user's emotions and adjusts the timing of knowledge acquisition based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned knowledge acquisition unit, When gathering knowledge, prioritize collecting highly relevant information by considering the geographical location of experts. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned knowledge acquisition unit, When gathering knowledge, analyze the social media activities of experts and collect relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned knowledge verification unit, We estimate the user's emotions and adjust the knowledge verification method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned knowledge verification unit, When verifying knowledge, we analyze past verification history and select the most suitable verification method. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned knowledge verification unit, When verifying knowledge, different verification algorithms are applied depending on the verifier's area of ​​expertise. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned knowledge verification unit, The system estimates the user's emotions and adjusts the timing of knowledge checks based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned knowledge verification unit, When verifying knowledge, the system prioritizes checking highly relevant knowledge by considering the geographical location of the person verifying the knowledge. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned knowledge verification unit, During knowledge verification, the verifier's social media activity is analyzed to confirm relevant knowledge. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned article generation unit, We estimate the user's emotions and adjust the way the article is written based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned article generation unit, When generating an article, adjust the level of detail based on the importance of the collected knowledge. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned article generation unit, When generating articles, different generation algorithms are applied depending on the article category. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned article generation unit, It estimates the user's sentiment and adjusts the article length based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned article generation unit, When generating articles, the priority of articles is determined based on when the collected knowledge was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned article generation unit, When generating articles, the order of articles is adjusted based on the relevance of the collected knowledge. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0193] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A needs-catching unit that captures the user's information needs, Based on the information gathered by the aforementioned needs gathering unit, the interviewing unit conducts detailed interviews with excellent respondents on the Q&A site. The knowledge gathering unit collects knowledge from multiple experts, based on the knowledge gathered by the aforementioned hearing unit. A knowledge verification unit that verifies the accuracy of the knowledge collected by the aforementioned knowledge acquisition unit, The system comprises an article generation unit that generates an article based on the knowledge confirmed by the aforementioned knowledge verification unit. A system characterized by the following features.

2. The aforementioned needs detection unit is Capture users' information needs through internet searches. The system according to feature 1.

3. The aforementioned hearing section is, We will conduct detailed interviews via messaging apps with users who have provided excellent answers on Yahoo! Answers. The system according to feature 1.

4. The aforementioned knowledge acquisition unit, Gather the knowledge and opinions of multiple experts. The system according to feature 1.

5. The aforementioned knowledge verification unit, The accuracy of the collected knowledge is verified by another expert. The system according to feature 1.

6. The aforementioned article generation unit, Based on verified knowledge, automatically generate articles for MyBest. The system according to feature 1.

7. The aforementioned needs detection unit is It estimates user emotions and prioritizes information needs based on those estimated emotions. The system according to feature 1.

8. The aforementioned needs detection unit is When identifying needs, we analyze the user's past search history to pinpoint their optimal information needs. The system according to feature 1.

9. The aforementioned needs detection unit is When identifying needs, filtering is performed based on the user's current areas of interest. The system according to feature 1.

10. The aforementioned needs detection unit is It estimates the user's emotions and adjusts the timing of information acquisition based on the estimated user emotions. The system according to feature 1.

Images