System

Abstract

To automatically verify and provide the accuracy of responses by generative AI.SOLUTION: A system according to an embodiment comprises a reception unit, a fact-checking unit, and a provision unit. The reception unit receives a question from a user. The fact-checking unit automatically performs fact-checking on a response by generative AI to the question received by the reception unit. The provision unit provides the result fact-checked by the fact-checking unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] Existing technologies do not adequately provide a means to automatically verify the accuracy of the generative AI's answers, leaving room for improvement.

[0005] The system according to the embodiment aims to automatically verify and provide the accuracy of the answers provided by the generating AI. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a fact check unit, and a provision unit. The reception unit receives questions from a user. The fact check unit automatically fact checks the answer of the generation AI to the question received by the reception unit. The provision unit provides the result fact-checked by the fact check unit. Effect of the Invention

[0007] The system according to the embodiment can automatically verify and provide the accuracy of the answers of the generating AI. [Brief description of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The system according to the embodiment of the present invention is a system for verifying the accuracy of answers given by a generation AI. This system integrates a fact-checking plug-in into a browser or a messaging app to automatically fact-check answers. Next, a user community is utilized to evaluate and supplement the answers. Finally, the answers are reviewed by a team of experts to ensure accuracy. By combining these services, the quality and accuracy of answers are improved. For example, a fact-checking plug-in is integrated into a browser or a messaging app. This plug-in automatically fact-checks the answers given by the generation AI and evaluates their accuracy. For example, when a user inputs a question into the generation AI, the plug-in verifies the answer and checks it against a reliable source. This allows the user to check the accuracy of the answer. Next, a user community is utilized. The user can evaluate the answers given by the generation AI and provide supplementary information. For example, the user evaluates the answers as "accurate", "inaccurate", "supplementary information available", etc., and shares them with other users. This allows the quality of answers to be improved throughout the community. Finally, the answers are reviewed by a team of experts. The expert team regularly audits the answers given by the generation AI to check their accuracy. For example, in specialized fields such as medicine and law, experts review answers and make corrections or supplements as necessary. This ensures the accuracy of answers that require specialized knowledge. Combining these services can improve the quality and accuracy of answers from generative AI. Users can obtain highly reliable information and use generative AI with peace of mind. This enables the system to verify the accuracy of answers from generative AI and provide highly reliable information.

[0029] The system according to the embodiment includes a reception unit, a fact check unit, and a provision unit. The reception unit receives a question from a user. For example, the reception unit can receive a question input by the user through a browser or a message app. The fact check unit automatically fact checks the answer of the generation AI to the question received by the reception unit. The fact check unit, for example, evaluates the accuracy of the answer by comparing it with a highly reliable information source. For example, the fact check unit verifies the accuracy of the answer using a highly reliable information source such as data from a government agency or an academic paper. The provision unit provides the result fact-checked by the fact check unit. The provision unit, for example, displays the result of the fact check to the user. This allows the user to confirm the accuracy of the answer. A part or all of the above-mentioned processing in the fact check unit may be performed, for example, using AI, or may be performed without using AI. For example, the fact check unit can perform a fact check using an AI model that receives the answer of the generation AI and a highly reliable information source as input and outputs the result of the fact check. As a result, the system according to the embodiment can automatically verify the accuracy of the answer of the generation AI to the user's question and provide highly reliable information.

[0030] The reception unit receives questions from the user. For example, the reception unit can receive questions input by the user through a browser or a message app. Specifically, when the user inputs a question into a form on a web browser, the reception unit receives the input contents in real time and stores them in a database in the system. When a message app is used, the reception unit receives messages sent by the user and similarly stores them in the database. The reception unit appropriately classifies these questions and performs preprocessing to send them to the fact check unit. For example, the reception unit analyzes the contents of the questions and classifies them into specific categories, enabling the fact check unit to process them efficiently. The reception unit also has a function of detecting input errors and unclear questions made by the user and prompting the user to re-enter the questions as necessary. This allows the reception unit to accurately and quickly receive questions from the user and improve the processing efficiency of the entire system. Furthermore, the reception unit also has a function of automatically suggesting related questions by referring to the user's past question history. This allows the user to efficiently input questions, improving the user experience of the system.

[0031] The fact-checking unit automatically fact-checks the answer of the generation AI to the question received by the reception unit. The fact-checking unit evaluates the accuracy of the answer, for example, by checking it against a reliable source. Specifically, the fact-checking unit refers to reliable sources such as government agency databases, academic papers, specialized books, and news articles, and compares the answer content of the generation AI. The fact-checking unit uses natural language processing technology to analyze the answer and the content of the source to detect the degree of agreement and inconsistency. For example, if the answer is based on specific statistical data, it checks whether the data is up-to-date and accurate. In addition, if the answer is based on historical facts, it verifies whether the facts are supported by a reliable source. Based on these verification results, the fact-checking unit scores the reliability of the answer and provides it to the user. Furthermore, the fact-checking unit can perform fact-checking using an AI model. For example, it uses an AI model that takes the answer of the generation AI and a reliable source as input and outputs the result of the fact-checking. This AI model learns a large amount of data and realizes highly accurate fact-checking. As a result, the fact-checking unit can quickly and accurately evaluate the reliability of the answer and provide the user with reliable information.

[0032] The providing unit provides the results of the fact check by the fact check unit. For example, the providing unit displays the results of the fact check to the user. Specifically, the providing unit provides an interface for visually displaying the results of the fact check in an easy-to-understand manner. For example, the reliability score of the answer is displayed as a graph or an icon, so that the user can judge the reliability at a glance. In addition, the detailed results of the fact check are displayed in text format, and it is clear which information source was referenced and which part was verified. Furthermore, the providing unit also has a function that allows the user to provide feedback on the results of the fact check. This allows the user to submit opinions on the results and additional questions, and the system can make further improvements based on the feedback. The providing unit also puts effort into the design of the user interface, achieving intuitive and easy-to-use operability. For example, a responsive design that can be comfortably used on mobile devices is adopted, so that the user can smoothly access it from any device. As a result, the providing unit quickly and accurately provides the results of the fact check to the user, allowing the user to obtain reliable information.

[0033] The system includes an evaluation unit that utilizes a user community to evaluate the answer of the generation AI. The evaluation unit utilizes the user community to evaluate the answer of the generation AI. For example, the evaluation unit allows the user to evaluate the answer as "accurate", "inaccurate", "supplementary information included", etc., and share the evaluation with other users. The evaluation unit provides, for example, an interface for the user to evaluate the answer. The user can input an evaluation of the answer through the evaluation interface and share it with other users. This can improve the quality of the answers throughout the user community. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can perform evaluation using an AI model that inputs user evaluation data and outputs evaluation results. This allows the system to improve the quality of answers through evaluation by the user community.

[0034] The system includes a review unit that reviews the answer by the expert team. The review unit reviews the answer by the expert team. For example, the review unit allows experts to periodically audit the answer of the generation AI to check its accuracy. The review unit allows experts to review the answer in a specialized field such as medicine or law, and to make corrections or supplements as necessary. The review unit provides, for example, an interface for the expert to review the answer. The expert can input a review of the answer through the review interface and make corrections or supplements as necessary. This makes it possible to ensure the accuracy of the answer that requires specialized knowledge. A part or all of the above-mentioned processing in the review unit may be performed, for example, using AI, or may be performed without using AI. For example, the review unit can perform a review using an AI model that receives the review results of the experts as input and outputs corrections and supplements. This makes it possible for the system to ensure the accuracy of the answer through review by the experts.

[0035] The fact check unit can evaluate the accuracy of the answer by checking against a highly reliable information source. The fact check unit can, for example, check against a highly reliable information source to evaluate the accuracy of the answer. For example, the fact check unit verifies the accuracy of the answer using highly reliable information sources such as data from government agencies and academic papers. The fact check unit can, for example, build a system that automatically collects highly reliable information sources and checks them against the answer. As a result, the fact check unit can improve the accuracy of the answer by checking against a highly reliable information source. A part or all of the above-mentioned processing in the fact check unit may be performed using, for example, AI, or may be performed without using AI. For example, the fact check unit can perform fact checking using an AI model that uses a highly reliable information source and an answer as input and evaluates the accuracy. As a result, the system can improve the accuracy of the answer by checking against a highly reliable information source.

[0036] The evaluation unit allows the user to evaluate the answer as "accurate", "inaccurate", "supplementary information included", etc., and share the evaluation with other users. The evaluation unit allows the user to evaluate the answer as "accurate", "inaccurate", "supplementary information included", etc., and share the evaluation with other users. The evaluation unit provides, for example, an interface for the user to perform evaluation. The user can input an evaluation of the answer through the evaluation interface and share it with other users. In this way, the quality of the answer can be improved by sharing the user's evaluation. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can perform evaluation using an AI model that inputs the user's evaluation data and outputs the evaluation result. In this way, the system can improve the quality of the answer by sharing the user's evaluation.

[0037] The review unit allows the expert to review the answer and make corrections or supplements as necessary. The review unit allows, for example, the expert to review the answer and make corrections or supplements as necessary. The review unit provides, for example, an interface for the expert to perform the review. The expert can input a review of the answer through the review interface and make corrections or supplements as necessary. This makes it possible to ensure the accuracy of the answer through the corrections and supplements made by the expert. A part or all of the above-mentioned processing in the review unit may be performed, for example, using AI, or may be performed without using AI. For example, the review unit can perform the review using an AI model that receives the review results of the expert as input and outputs corrections and supplements. This makes it possible for the system to ensure the accuracy of the answer through the corrections and supplements made by the expert.

[0038] The reception unit can analyze the user's past question history and select the optimal reception method. The reception unit, for example, analyzes the user's past question history and selects the optimal reception method. For example, the reception unit preferentially receives topics about which the user has frequently asked questions in the past. The reception unit can also preferentially suggest question formats (text, voice, etc.) that the user has used in the past. Furthermore, the reception unit can also suggest a reception method suitable for a specific time period from the user's past question history. In this way, the optimal reception method can be provided to the user by analyzing the past question history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can select the reception method using an AI model that inputs the user's past question history data and outputs the optimal reception method. In this way, the system can provide the optimal reception method by analyzing the user's past question history.

[0039] The reception unit can filter questions based on the user's current field of interest when receiving the questions. For example, the reception unit filters questions based on the user's current field of interest when receiving the questions. For example, the reception unit preferentially receives questions related to topics in which the user is currently interested. The reception unit can also analyze the user's social media activities and filter questions based on the field of interest. Furthermore, the reception unit can preferentially receive related questions with reference to the user's recent search history. As a result, questions can be filtered based on the user's field of interest, thereby allowing more relevant questions to be received. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can filter questions using an AI model that receives the user's field of interest data as input and outputs the filtering result. As a result, the system can filter questions based on the user's current field of interest, thereby allowing more relevant questions to be received.

[0040] The reception unit can preferentially receive questions with high relevance in consideration of the geographical location information of the user when receiving a question. For example, the reception unit preferentially receives questions with high relevance in consideration of the geographical location information of the user when receiving a question. For example, when the user is in a specific area, the reception unit preferentially receives questions related to the area. The reception unit can also preferentially receive questions related to local news and events based on the user's current location. Furthermore, when the user is traveling, the reception unit can also preferentially receive questions related to the travel destination. In this way, by taking into account the geographical location information of the user, more relevant questions can be received. Part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can receive questions using an AI model that inputs the geographical location information data of the user and outputs questions with high relevance. In this way, the system can receive questions with high relevance by taking into account the geographical location information of the user.

[0041] The reception unit can analyze the user's social media activity and receive related questions when receiving a question. For example, the reception unit analyzes the user's social media activity and receives related questions when receiving a question. For example, the reception unit preferentially receives questions related to topics in which the user has recently shown interest on social media. The reception unit can also preferentially receive questions related to topics in which the user's followers and friends are interested. Furthermore, the reception unit can also preferentially receive related questions based on content shared by the user on social media. In this way, by analyzing the user's social media activity, more relevant questions can be received. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can receive questions using an AI model that receives the user's social media activity data as input and outputs related questions. In this way, the system can receive more relevant questions by analyzing the user's social media activity.

[0042] The fact check unit can adjust the level of detail of the check based on the importance of the answer during the fact check. For example, the fact check unit adjusts the level of detail of the check based on the importance of the answer during the fact check. For example, the fact check unit performs detailed fact checks on important questions to provide reliable information. The fact check unit can also perform basic fact checks on general questions to provide information quickly. Furthermore, the fact check unit can perform fact checks on specialized questions with reference to the opinions of experts. As a result, more reliable information can be provided by adjusting the level of detail of the check based on the importance of the answer. Part or all of the above-mentioned processing in the fact check unit may be performed using, for example, AI, or may be performed without using AI. For example, the fact check unit can perform fact checks using an AI model that inputs the importance data of the answer and outputs the level of detail of the check. As a result, the system can provide more reliable information by adjusting the level of detail of the check based on the importance of the answer.

[0043] The fact check unit can apply different check algorithms depending on the category of the answer during fact check. For example, the fact check unit applies different check algorithms depending on the category of the answer during fact check. For example, the fact check unit applies a medical fact check algorithm to a medical-related question. The fact check unit can also apply a legal fact check algorithm to a legal question. The fact check unit can also apply a science and technology fact check algorithm to a science and technology question. This allows more appropriate fact check by applying different check algorithms depending on the category of the answer. Part or all of the above-mentioned processing in the fact check unit may be performed using, for example, AI, or may be performed without using AI. For example, the fact check unit can perform fact check using an AI model that inputs answer category data and outputs a check algorithm. This allows the system to perform more appropriate fact check by applying different check algorithms depending on the category of the answer.

[0044] The fact check unit can determine the priority of the check based on the time of submission of the answer during the fact check. For example, the fact check unit determines the priority of the check based on the time of submission of the answer during the fact check. For example, the fact check unit quickly performs a fact check on the latest question. In addition, the fact check unit can also perform a general fact check on past questions. Furthermore, the fact check unit can preferentially perform a fact check on questions with high urgency. This allows for a faster response by determining the priority of the check based on the time of submission of the answer. Part or all of the above-mentioned processing in the fact check unit may be performed using, for example, AI, or may be performed without using AI. For example, the fact check unit can perform a fact check using an AI model that inputs data on the time of submission of the answer and outputs the priority of the check. This allows the system to determine the priority of the check based on the time of submission of the answer, allowing for a faster response.

[0045] The fact check unit can adjust the order of checks based on the relevance of the answers during fact checks. For example, the fact check unit adjusts the order of checks based on the relevance of the answers during fact checks. For example, the fact check unit prioritizes fact checks on information most relevant to the user's question. The fact check unit can also postpone fact checks on general information for the user's question. Furthermore, the fact check unit can also prioritize fact checks on specialized information for the user's question. This allows more appropriate information to be provided by adjusting the order of checks based on the relevance of the answers. Part or all of the above-mentioned processing in the fact check unit may be performed, for example, using AI, or may be performed without using AI. For example, the fact check unit can perform fact checks using an AI model that inputs answer relevance data and outputs the order of checks. This allows the system to provide more appropriate information by adjusting the order of checks based on the relevance of the answers.

[0046] The providing unit can adjust the level of detail of the information provided based on the importance of the information at the time of providing. For example, the providing unit adjusts the level of detail of the information provided based on the importance of the information at the time of providing. For example, the providing unit provides a detailed explanation for important information. In addition, the providing unit can also provide a concise explanation for general information. Furthermore, the providing unit can also provide a detailed explanation including technical terms for specialized information. As a result, more appropriate information can be provided by adjusting the level of detail of the information provided based on the importance of the information. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can provide information using an AI model that inputs the importance data of information and outputs the level of detail of the information provided. As a result, the system can provide more appropriate information by adjusting the level of detail of the information provided based on the importance of the information.

[0047] The providing unit can apply different provision algorithms depending on the category of information at the time of provision. For example, the providing unit applies different provision algorithms depending on the category of information at the time of provision. For example, the providing unit applies a medical-specialized provision algorithm to medical-related information. In addition, the providing unit can also apply a legal-specialized provision algorithm to legal-related information. Furthermore, the providing unit can also apply a science and technology-specialized provision algorithm to science and technology-related information. As a result, more appropriate information can be provided by applying different provision algorithms depending on the category of information. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can provide information using an AI model that inputs category data of information and outputs a provision algorithm. As a result, the system can provide more appropriate information by applying different provision algorithms depending on the category of information.

[0048] The providing unit can determine the priority of provision based on the time of submission of information at the time of provision. The providing unit determines the priority of provision based on the time of submission of information, for example, at the time of provision. For example, the providing unit provides the latest information quickly. In addition, the providing unit can provide general information for past information. Furthermore, the providing unit can provide information with priority for high urgency. As a result, a more rapid response is possible by determining the priority of provision based on the time of submission of information. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can provide information using an AI model that inputs data on the time of submission of information and outputs the priority of provision. As a result, the system determines the priority of provision based on the time of submission of information, thereby enabling a more rapid response.

[0049] The providing unit can adjust the order of provision based on the relevance of information at the time of provision. For example, the providing unit adjusts the order of provision based on the relevance of information at the time of provision. For example, the providing unit preferentially provides information most relevant to a user's question. The providing unit can also provide general information to a user's question later. Furthermore, the providing unit can also provide specialized information to a user's question preferentially. As a result, more appropriate information can be provided by adjusting the order of provision based on the relevance of information. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can provide information using an AI model that inputs relevance data of information and outputs the order of provision. As a result, the system can provide more appropriate information by adjusting the order of provision based on the relevance of information.

[0050] The evaluation unit can adjust the level of detail of the evaluation based on the importance of the answer at the time of evaluation. For example, the evaluation unit adjusts the level of detail of the evaluation based on the importance of the answer at the time of evaluation. For example, the evaluation unit performs a detailed evaluation on an important answer to provide highly reliable information. The evaluation unit can also perform a basic evaluation on a general answer to quickly provide information. Furthermore, the evaluation unit can perform an evaluation on a specialized answer by referring to the opinion of an expert. As a result, more reliable information can be provided by adjusting the level of detail of the evaluation based on the importance of the answer. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can perform evaluation using an AI model that inputs the importance data of the answer and outputs the level of detail of the evaluation. As a result, the system can provide more reliable information by adjusting the level of detail of the evaluation based on the importance of the answer.

[0051] The evaluation unit can determine the priority of the evaluation based on the time of submission of the answer at the time of evaluation. The evaluation unit, for example, determines the priority of the evaluation based on the time of submission of the answer at the time of evaluation. For example, the evaluation unit quickly evaluates the latest answer. The evaluation unit can also perform a general evaluation on past answers. Furthermore, the evaluation unit can prioritize evaluation on answers with high urgency. This allows for a faster response by determining the priority of the evaluation based on the time of submission of the answer. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can perform evaluation using an AI model that inputs data on the time of submission of the answer and outputs the priority of the evaluation. This allows the system to determine the priority of the evaluation based on the time of submission of the answer, allowing for a faster response.

[0052] The review unit can adjust the detail level of the review based on the importance of the answer at the time of review. The review unit adjusts the detail level of the review based on the importance of the answer, for example, at the time of review. For example, the review unit performs a detailed review on an important answer to provide reliable information. The review unit can also perform a basic review on a general answer to quickly provide information. Furthermore, the review unit can also perform a review with reference to the opinion of an expert on a specialized answer. As a result, more reliable information can be provided by adjusting the detail level of the review based on the importance of the answer. A part or all of the above-mentioned processing in the review unit may be performed using, for example, AI, or may be performed without using AI. For example, the review unit can perform a review using an AI model that inputs the importance data of the answer and outputs the detail level of the review. As a result, the system can provide more reliable information by adjusting the detail level of the review based on the importance of the answer.

[0053] The review unit can determine the priority of the review based on the time of submission of the answer at the time of review. The review unit, for example, determines the priority of the review based on the time of submission of the answer at the time of review. For example, the review unit quickly reviews the latest answer. The review unit can also perform a general review on past answers. Furthermore, the review unit can preferentially review answers with high urgency. This allows for a faster response by determining the priority of the review based on the time of submission of the answer. A part or all of the above-mentioned processing in the review unit may be performed using, for example, AI, or may be performed without using AI. For example, the review unit can perform the review using an AI model that inputs data on the time of submission of the answer and outputs the priority of the review. This allows the system to determine the priority of the review based on the time of submission of the answer, allowing for a faster response.

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

[0055] The reception unit can analyze the user's past question history and generate personalized feedback to provide optimal answers. For example, the reception unit can provide related new information based on topics that the user has frequently asked about in the past. The reception unit can also find specific patterns from the user's past question history and suggest topics that the user may be interested in. Furthermore, the reception unit can analyze the user's past question history and provide information in a format that the user can easily understand. This makes it possible to provide more personalized information by utilizing the user's past question history.

[0056] The review unit can provide educational content to the user based on the expert's review results. For example, the review unit generates content that explains the errors or shortcomings pointed out by the expert. The review unit can also provide quizzes and tests that allow the user to study based on the expert's review results. Furthermore, the review unit can provide detailed explanations that allow the user to gain a deeper understanding based on the expert's review results. In this way, the expert's review results can be utilized to support the user's learning.

[0057] The evaluation unit can provide evaluation trends to other users based on the user's evaluation data. For example, the evaluation unit analyzes evaluation trends for a specific topic and shares them with other users. The evaluation unit can also provide popular answers and topics in a ranking format based on the evaluation data of the entire user community. Furthermore, the evaluation unit can display evaluation fluctuations in real time based on the user's evaluation data. This makes it possible to provide useful information to other users by utilizing the user's evaluation data.

[0058] The reception unit can provide area-specific information based on the user's geographical location information. For example, when the user is in a particular area, the reception unit can provide news and event information related to that area. The reception unit can also provide local service and store information based on the user's current location. Furthermore, when the user is traveling, the reception unit can provide tourist information and traffic information related to the travel destination. This makes it possible to provide more relevant information by utilizing the user's geographical location information.

[0059] The providing unit can provide new related information based on the user's past question history. For example, the providing unit provides the latest information related to topics that the user has previously asked about. The providing unit can also suggest topics that the user may be interested in based on the user's past question history. Furthermore, the providing unit can analyze the user's past question history and provide information in a format that is easy for the user to understand. This makes it possible to provide more relevant information by utilizing the user's past question history.

[0060] The process flow of the first embodiment will be briefly described below.

[0061] Step 1: The reception unit receives a question from a user. For example, the reception unit can receive a question input by the user through a browser or a message app. Step 2: The fact-checking unit automatically fact-checks the AI's answers to the questions received by the reception unit. For example, the fact-checking unit evaluates the accuracy of the answers by checking them against reliable sources. Reliable sources include government agency data and academic papers. The processing in the fact-checking unit may be performed using AI or without AI. Step 3: The providing unit provides the result fact-checked by the fact-checking unit. For example, the providing unit displays the result of the fact-checking to the user. This allows the user to check the accuracy of the answer.

[0062] (Example 2) The system according to the embodiment of the present invention is a system for verifying the accuracy of answers given by a generation AI. This system integrates a fact-checking plug-in into a browser or a messaging app to automatically fact-check answers. Next, a user community is utilized to evaluate and supplement the answers. Finally, the answers are reviewed by a team of experts to ensure accuracy. By combining these services, the quality and accuracy of answers are improved. For example, a fact-checking plug-in is integrated into a browser or a messaging app. This plug-in automatically fact-checks the answers given by the generation AI and evaluates their accuracy. For example, when a user inputs a question into the generation AI, the plug-in verifies the answer and checks it against a reliable source. This allows the user to check the accuracy of the answer. Next, a user community is utilized. The user can evaluate the answers given by the generation AI and provide supplementary information. For example, the user evaluates the answers as "accurate", "inaccurate", "supplementary information available", etc., and shares them with other users. This allows the quality of answers to be improved throughout the community. Finally, the answers are reviewed by a team of experts. The expert team regularly audits the answers given by the generation AI to check their accuracy. For example, in specialized fields such as medicine and law, experts review answers and make corrections or supplements as necessary. This ensures the accuracy of answers that require specialized knowledge. Combining these services can improve the quality and accuracy of answers from generative AI. Users can obtain highly reliable information and use generative AI with peace of mind. This enables the system to verify the accuracy of answers from generative AI and provide highly reliable information.

[0063] The system according to the embodiment includes a reception unit, a fact check unit, and a provision unit. The reception unit receives a question from a user. For example, the reception unit can receive a question input by the user through a browser or a message app. The fact check unit automatically fact checks the answer of the generation AI to the question received by the reception unit. The fact check unit, for example, evaluates the accuracy of the answer by comparing it with a highly reliable information source. For example, the fact check unit verifies the accuracy of the answer using a highly reliable information source such as data from a government agency or an academic paper. The provision unit provides the result fact-checked by the fact check unit. The provision unit, for example, displays the result of the fact check to the user. This allows the user to confirm the accuracy of the answer. A part or all of the above-mentioned processing in the fact check unit may be performed, for example, using AI, or may be performed without using AI. For example, the fact check unit can perform a fact check using an AI model that receives the answer of the generation AI and a highly reliable information source as input and outputs the result of the fact check. As a result, the system according to the embodiment can automatically verify the accuracy of the answer of the generation AI to the user's question and provide highly reliable information.

[0064] The reception unit receives questions from the user. For example, the reception unit can receive questions input by the user through a browser or a message app. Specifically, when the user inputs a question into a form on a web browser, the reception unit receives the input contents in real time and stores them in a database in the system. When a message app is used, the reception unit receives messages sent by the user and similarly stores them in the database. The reception unit appropriately classifies these questions and performs preprocessing to send them to the fact check unit. For example, the reception unit analyzes the contents of the questions and classifies them into specific categories, enabling the fact check unit to process them efficiently. The reception unit also has a function of detecting input errors and unclear questions made by the user and prompting the user to re-enter the questions as necessary. This allows the reception unit to accurately and quickly receive questions from the user and improve the processing efficiency of the entire system. Furthermore, the reception unit also has a function of automatically suggesting related questions by referring to the user's past question history. This allows the user to efficiently input questions, improving the user experience of the system.

[0065] The fact-checking unit automatically fact-checks the answer of the generation AI to the question received by the reception unit. The fact-checking unit evaluates the accuracy of the answer, for example, by checking it against a reliable source. Specifically, the fact-checking unit refers to reliable sources such as government agency databases, academic papers, specialized books, and news articles, and compares the answer content of the generation AI. The fact-checking unit uses natural language processing technology to analyze the answer and the content of the source to detect the degree of agreement and inconsistency. For example, if the answer is based on specific statistical data, it checks whether the data is up-to-date and accurate. In addition, if the answer is based on historical facts, it verifies whether the facts are supported by a reliable source. Based on these verification results, the fact-checking unit scores the reliability of the answer and provides it to the user. Furthermore, the fact-checking unit can perform fact-checking using an AI model. For example, it uses an AI model that takes the answer of the generation AI and a reliable source as input and outputs the result of the fact-checking. This AI model learns a large amount of data and realizes highly accurate fact-checking. As a result, the fact-checking unit can quickly and accurately evaluate the reliability of the answer and provide the user with reliable information.

[0066] The providing unit provides the results of the fact check by the fact check unit. For example, the providing unit displays the results of the fact check to the user. Specifically, the providing unit provides an interface for visually displaying the results of the fact check in an easy-to-understand manner. For example, the reliability score of the answer is displayed as a graph or an icon, so that the user can judge the reliability at a glance. In addition, the detailed results of the fact check are displayed in text format, and it is clear which information source was referenced and which part was verified. Furthermore, the providing unit also has a function that allows the user to provide feedback on the results of the fact check. This allows the user to submit opinions on the results and additional questions, and the system can make further improvements based on the feedback. The providing unit also puts effort into the design of the user interface, achieving intuitive and easy-to-use operability. For example, a responsive design that can be comfortably used on mobile devices is adopted, so that the user can smoothly access it from any device. As a result, the providing unit quickly and accurately provides the results of the fact check to the user, allowing the user to obtain reliable information.

[0067] The system includes an evaluation unit that utilizes a user community to evaluate the answer of the generation AI. The evaluation unit utilizes the user community to evaluate the answer of the generation AI. For example, the evaluation unit allows the user to evaluate the answer as "accurate", "inaccurate", "supplementary information included", etc., and share the evaluation with other users. The evaluation unit provides, for example, an interface for the user to evaluate the answer. The user can input an evaluation of the answer through the evaluation interface and share it with other users. This can improve the quality of the answers throughout the user community. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can perform evaluation using an AI model that inputs user evaluation data and outputs evaluation results. This allows the system to improve the quality of answers through evaluation by the user community.

[0068] The system includes a review unit that reviews the answer by the expert team. The review unit reviews the answer by the expert team. For example, the review unit allows experts to periodically audit the answer of the generation AI to check its accuracy. The review unit allows experts to review the answer in a specialized field such as medicine or law, and to make corrections or supplements as necessary. The review unit provides, for example, an interface for the expert to review the answer. The expert can input a review of the answer through the review interface and make corrections or supplements as necessary. This makes it possible to ensure the accuracy of the answer that requires specialized knowledge. A part or all of the above-mentioned processing in the review unit may be performed, for example, using AI, or may be performed without using AI. For example, the review unit can perform a review using an AI model that receives the review results of the experts as input and outputs corrections and supplements. This makes it possible for the system to ensure the accuracy of the answer through review by the experts.

[0069] The fact check unit can evaluate the accuracy of the answer by checking against a highly reliable information source. The fact check unit can, for example, check against a highly reliable information source to evaluate the accuracy of the answer. For example, the fact check unit verifies the accuracy of the answer using highly reliable information sources such as data from government agencies and academic papers. The fact check unit can, for example, build a system that automatically collects highly reliable information sources and checks them against the answer. As a result, the fact check unit can improve the accuracy of the answer by checking against a highly reliable information source. A part or all of the above-mentioned processing in the fact check unit may be performed using, for example, AI, or may be performed without using AI. For example, the fact check unit can perform fact checking using an AI model that uses a highly reliable information source and an answer as input and evaluates the accuracy. As a result, the system can improve the accuracy of the answer by checking against a highly reliable information source.

[0070] The evaluation unit allows the user to evaluate the answer as "accurate", "inaccurate", "supplementary information included", etc., and share the evaluation with other users. The evaluation unit allows the user to evaluate the answer as "accurate", "inaccurate", "supplementary information included", etc., and share the evaluation with other users. The evaluation unit provides, for example, an interface for the user to perform evaluation. The user can input an evaluation of the answer through the evaluation interface and share it with other users. In this way, the quality of the answer can be improved by sharing the user's evaluation. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can perform evaluation using an AI model that inputs the user's evaluation data and outputs the evaluation result. In this way, the system can improve the quality of the answer by sharing the user's evaluation.

[0071] The review unit allows the expert to review the answer and make corrections or supplements as necessary. The review unit allows, for example, the expert to review the answer and make corrections or supplements as necessary. The review unit provides, for example, an interface for the expert to perform the review. The expert can input a review of the answer through the review interface and make corrections or supplements as necessary. This makes it possible to ensure the accuracy of the answer through the corrections and supplements made by the expert. A part or all of the above-mentioned processing in the review unit may be performed, for example, using AI, or may be performed without using AI. For example, the review unit can perform the review using an AI model that receives the review results of the expert as input and outputs corrections and supplements. This makes it possible for the system to ensure the accuracy of the answer through the corrections and supplements made by the expert.

[0072] The reception unit can estimate the user's emotion and adjust the timing of receiving the question based on the estimated user's emotion. The reception unit, for example, estimates the user's emotion and adjusts the timing of receiving the question based on the estimated user's emotion. For example, when the user is stressed, the reception unit quickly receives the question and provides an answer immediately. Also, when the user is relaxed, the reception unit can receive detailed questions and provide deeper information. Furthermore, when the user is in a hurry, the reception unit can preferentially receive brief questions and provide an answer quickly. This allows for more appropriate response by adjusting the timing of receiving the question according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation. This allows the system to adjust the timing of question acceptance according to the user's emotions, enabling a more appropriate response.

[0073] The reception unit can analyze the user's past question history and select the optimal reception method. The reception unit, for example, analyzes the user's past question history and selects the optimal reception method. For example, the reception unit preferentially receives topics about which the user has frequently asked questions in the past. The reception unit can also preferentially suggest question formats (text, voice, etc.) that the user has used in the past. Furthermore, the reception unit can also suggest a reception method suitable for a specific time period from the user's past question history. In this way, the optimal reception method can be provided to the user by analyzing the past question history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can select the reception method using an AI model that inputs the user's past question history data and outputs the optimal reception method. In this way, the system can provide the optimal reception method by analyzing the user's past question history.

[0074] The reception unit can filter questions based on the user's current field of interest when receiving the questions. For example, the reception unit filters questions based on the user's current field of interest when receiving the questions. For example, the reception unit preferentially receives questions related to topics in which the user is currently interested. The reception unit can also analyze the user's social media activities and filter questions based on the field of interest. Furthermore, the reception unit can preferentially receive related questions with reference to the user's recent search history. As a result, questions can be filtered based on the user's field of interest, thereby allowing more relevant questions to be received. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can filter questions using an AI model that receives the user's field of interest data as input and outputs the filtering result. As a result, the system can filter questions based on the user's current field of interest, thereby allowing more relevant questions to be received.

[0075] The reception unit can estimate the user's emotion and determine the priority of questions to be received based on the estimated user's emotion. The reception unit, for example, estimates the user's emotion and determines the priority of questions to be received based on the estimated user's emotion. For example, when the user feels anxious, the reception unit preferentially receives questions with high urgency. In addition, when the user is relaxed, the reception unit can also preferentially receive detailed questions. Furthermore, when the user is excited, the reception unit can also preferentially receive questions related to interesting topics. This enables a more appropriate response by determining the priority of questions according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation. This allows the system to prioritize questions based on the user's emotions, enabling a more appropriate response.

[0076] The reception unit can preferentially receive questions with high relevance in consideration of the geographical location information of the user when receiving a question. For example, the reception unit preferentially receives questions with high relevance in consideration of the geographical location information of the user when receiving a question. For example, when the user is in a specific area, the reception unit preferentially receives questions related to the area. The reception unit can also preferentially receive questions related to local news and events based on the user's current location. Furthermore, when the user is traveling, the reception unit can also preferentially receive questions related to the travel destination. In this way, by taking into account the geographical location information of the user, more relevant questions can be received. Part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can receive questions using an AI model that inputs the geographical location information data of the user and outputs questions with high relevance. In this way, the system can receive questions with high relevance by taking into account the geographical location information of the user.

[0077] The reception unit can analyze the user's social media activity and receive related questions when receiving a question. For example, the reception unit analyzes the user's social media activity and receives related questions when receiving a question. For example, the reception unit preferentially receives questions related to topics in which the user has recently shown interest on social media. The reception unit can also preferentially receive questions related to topics in which the user's followers and friends are interested. Furthermore, the reception unit can also preferentially receive related questions based on content shared by the user on social media. In this way, by analyzing the user's social media activity, more relevant questions can be received. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can receive questions using an AI model that receives the user's social media activity data as input and outputs related questions. In this way, the system can receive more relevant questions by analyzing the user's social media activity.

[0078] The fact check unit can estimate the user's emotions and adjust the fact check criteria based on the estimated user's emotions. The fact check unit, for example, estimates the user's emotions and adjusts the fact check criteria based on the estimated user's emotions. For example, when the user feels anxious, the fact check unit performs strict fact check to provide highly reliable information. In addition, when the user is relaxed, the fact check unit can also perform general fact check to provide information quickly. Furthermore, when the user is excited, the fact check unit can also perform detailed fact check to provide interesting information. In this way, by adjusting the fact check criteria according to the user's emotions, more appropriate information can be provided. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the fact check unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the fact check unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation. This allows the system to provide more relevant information by adjusting its fact-checking criteria according to the user's sentiment.

[0079] The fact check unit can adjust the level of detail of the check based on the importance of the answer during the fact check. For example, the fact check unit adjusts the level of detail of the check based on the importance of the answer during the fact check. For example, the fact check unit performs detailed fact checks on important questions to provide reliable information. The fact check unit can also perform basic fact checks on general questions to provide information quickly. Furthermore, the fact check unit can perform fact checks on specialized questions with reference to the opinions of experts. As a result, more reliable information can be provided by adjusting the level of detail of the check based on the importance of the answer. Part or all of the above-mentioned processing in the fact check unit may be performed using, for example, AI, or may be performed without using AI. For example, the fact check unit can perform fact checks using an AI model that inputs the importance data of the answer and outputs the level of detail of the check. As a result, the system can provide more reliable information by adjusting the level of detail of the check based on the importance of the answer.

[0080] The fact check unit can apply different check algorithms depending on the category of the answer during fact check. For example, the fact check unit applies different check algorithms depending on the category of the answer during fact check. For example, the fact check unit applies a medical fact check algorithm to a medical-related question. The fact check unit can also apply a legal fact check algorithm to a legal question. The fact check unit can also apply a science and technology fact check algorithm to a science and technology question. This allows more appropriate fact check by applying different check algorithms depending on the category of the answer. Part or all of the above-mentioned processing in the fact check unit may be performed using, for example, AI, or may be performed without using AI. For example, the fact check unit can perform fact check using an AI model that inputs answer category data and outputs a check algorithm. This allows the system to perform more appropriate fact check by applying different check algorithms depending on the category of the answer.

[0081] The fact check unit can estimate the user's emotions and determine the priority of the fact check based on the estimated user's emotions. The fact check unit, for example, estimates the user's emotions and determines the priority of the fact check based on the estimated user's emotions. For example, when the user feels anxious, the fact check unit prioritizes fact check on questions with high urgency. In addition, when the user is relaxed, the fact check unit can also prioritize fact check on general questions. Furthermore, when the user is excited, the fact check unit can also prioritize fact check on interesting questions. In this way, by determining the priority of the fact check according to the user's emotions, more appropriate information can be provided. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the fact check unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the fact check unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation. This allows the system to provide more relevant information by prioritizing fact-checks based on the user's sentiment.

[0082] The fact check unit can determine the priority of the check based on the time of submission of the answer during the fact check. For example, the fact check unit determines the priority of the check based on the time of submission of the answer during the fact check. For example, the fact check unit quickly performs a fact check on the latest question. In addition, the fact check unit can also perform a general fact check on past questions. Furthermore, the fact check unit can preferentially perform a fact check on questions with high urgency. This allows for a faster response by determining the priority of the check based on the time of submission of the answer. Part or all of the above-mentioned processing in the fact check unit may be performed using, for example, AI, or may be performed without using AI. For example, the fact check unit can perform a fact check using an AI model that inputs data on the time of submission of the answer and outputs the priority of the check. This allows the system to determine the priority of the check based on the time of submission of the answer, allowing for a faster response.

[0083] The fact check unit can adjust the order of checks based on the relevance of the answers during fact checks. For example, the fact check unit adjusts the order of checks based on the relevance of the answers during fact checks. For example, the fact check unit prioritizes fact checks on information most relevant to the user's question. The fact check unit can also postpone fact checks on general information for the user's question. Furthermore, the fact check unit can also prioritize fact checks on specialized information for the user's question. This allows more appropriate information to be provided by adjusting the order of checks based on the relevance of the answers. Part or all of the above-mentioned processing in the fact check unit may be performed, for example, using AI, or may be performed without using AI. For example, the fact check unit can perform fact checks using an AI model that inputs answer relevance data and outputs the order of checks. This allows the system to provide more appropriate information by adjusting the order of checks based on the relevance of the answers.

[0084] The providing unit can estimate the user's emotion and adjust the expression method of the information to be provided based on the estimated user's emotion. The providing unit, for example, estimates the user's emotion and adjusts the expression method of the information to be provided based on the estimated user's emotion. For example, when the user feels anxious, the providing unit provides simple and highly visible information. Furthermore, when the user is relaxed, the providing unit can also provide detailed information. Furthermore, when the user is excited, the providing unit can also provide visually stimulating information. As a result, by adjusting the expression method of the information according to the user's emotion, more appropriate information can be provided. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the user's emotion data to the generation AI and cause the generation AI to execute the emotion estimation. As a result, the system can provide more appropriate information by adjusting the expression method of the information according to the user's emotion.

[0085] The providing unit can adjust the level of detail of the information provided based on the importance of the information at the time of providing. For example, the providing unit adjusts the level of detail of the information provided based on the importance of the information at the time of providing. For example, the providing unit provides a detailed explanation for important information. In addition, the providing unit can also provide a concise explanation for general information. Furthermore, the providing unit can also provide a detailed explanation including technical terms for specialized information. As a result, more appropriate information can be provided by adjusting the level of detail of the information provided based on the importance of the information. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can provide information using an AI model that inputs the importance data of information and outputs the level of detail of the information provided. As a result, the system can provide more appropriate information by adjusting the level of detail of the information provided based on the importance of the information.

[0086] The providing unit can apply different provision algorithms depending on the category of information at the time of provision. For example, the providing unit applies different provision algorithms depending on the category of information at the time of provision. For example, the providing unit applies a medical-specialized provision algorithm to medical-related information. In addition, the providing unit can also apply a legal-specialized provision algorithm to legal-related information. Furthermore, the providing unit can also apply a science and technology-specialized provision algorithm to science and technology-related information. As a result, more appropriate information can be provided by applying different provision algorithms depending on the category of information. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can provide information using an AI model that inputs category data of information and outputs a provision algorithm. As a result, the system can provide more appropriate information by applying different provision algorithms depending on the category of information.

[0087] The providing unit can estimate the user's emotion and determine the priority of information to be provided based on the estimated user's emotion. The providing unit, for example, estimates the user's emotion and determines the priority of information to be provided based on the estimated user's emotion. For example, when the user feels anxious, the providing unit provides information with high urgency with priority. In addition, when the user is relaxed, the providing unit can also provide general information with priority. Furthermore, when the user is excited, the providing unit can also provide interesting information with priority. In this way, by determining the priority of information according to the user's emotion, more appropriate information can be provided. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the providing unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation. In this way, the system can provide more appropriate information by determining the priority of information according to the user's emotion.

[0088] The providing unit can determine the priority of provision based on the time of submission of information at the time of provision. The providing unit determines the priority of provision based on the time of submission of information, for example, at the time of provision. For example, the providing unit provides the latest information quickly. In addition, the providing unit can provide general information for past information. Furthermore, the providing unit can provide information with priority for high urgency. As a result, a more rapid response is possible by determining the priority of provision based on the time of submission of information. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can provide information using an AI model that inputs data on the time of submission of information and outputs the priority of provision. As a result, the system determines the priority of provision based on the time of submission of information, thereby enabling a more rapid response.

[0089] The providing unit can adjust the order of provision based on the relevance of information at the time of provision. For example, the providing unit adjusts the order of provision based on the relevance of information at the time of provision. For example, the providing unit preferentially provides information most relevant to a user's question. The providing unit can also provide general information to a user's question later. Furthermore, the providing unit can also provide specialized information to a user's question preferentially. As a result, more appropriate information can be provided by adjusting the order of provision based on the relevance of information. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can provide information using an AI model that inputs relevance data of information and outputs the order of provision. As a result, the system can provide more appropriate information by adjusting the order of provision based on the relevance of information.

[0090] The evaluation unit can estimate the user's emotion and adjust the evaluation criteria based on the estimated user's emotion. The evaluation unit, for example, estimates the user's emotion and adjusts the evaluation criteria based on the estimated user's emotion. For example, the evaluation unit applies strict evaluation criteria when the user feels anxious. The evaluation unit can also apply general evaluation criteria when the user is relaxed. Furthermore, the evaluation unit can apply detailed evaluation criteria when the user is excited. This allows for more appropriate evaluation by adjusting the evaluation criteria according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the evaluation unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation. This allows the system to adjust the evaluation criteria according to the user's emotion and perform more appropriate evaluation.

[0091] The evaluation unit can adjust the level of detail of the evaluation based on the importance of the answer at the time of evaluation. For example, the evaluation unit adjusts the level of detail of the evaluation based on the importance of the answer at the time of evaluation. For example, the evaluation unit performs a detailed evaluation on an important answer to provide highly reliable information. The evaluation unit can also perform a basic evaluation on a general answer to quickly provide information. Furthermore, the evaluation unit can perform an evaluation on a specialized answer by referring to the opinion of an expert. As a result, more reliable information can be provided by adjusting the level of detail of the evaluation based on the importance of the answer. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can perform evaluation using an AI model that inputs the importance data of the answer and outputs the level of detail of the evaluation. As a result, the system can provide more reliable information by adjusting the level of detail of the evaluation based on the importance of the answer.

[0092] The evaluation unit can estimate the user's emotion and determine the priority of the evaluation based on the estimated user's emotion. The evaluation unit, for example, estimates the user's emotion and determines the priority of the evaluation based on the estimated user's emotion. For example, when the user feels anxious, the evaluation unit prioritizes answers with high urgency. In addition, when the user is relaxed, the evaluation unit can also prioritize general answers. Furthermore, when the user is excited, the evaluation unit can also prioritize interesting answers. This enables more appropriate evaluation by determining the priority of the evaluation according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the evaluation unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation. This allows the system to prioritize evaluations based on the user's emotions, enabling more appropriate evaluations.

[0093] The evaluation unit can determine the priority of the evaluation based on the time of submission of the answer at the time of evaluation. The evaluation unit, for example, determines the priority of the evaluation based on the time of submission of the answer at the time of evaluation. For example, the evaluation unit quickly evaluates the latest answer. The evaluation unit can also perform a general evaluation on past answers. Furthermore, the evaluation unit can prioritize evaluation on answers with high urgency. This allows for a faster response by determining the priority of the evaluation based on the time of submission of the answer. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can perform evaluation using an AI model that inputs data on the time of submission of the answer and outputs the priority of the evaluation. This allows the system to determine the priority of the evaluation based on the time of submission of the answer, allowing for a faster response.

[0094] The review unit can estimate the user's emotion and adjust the review criteria based on the estimated user's emotion. The review unit, for example, estimates the user's emotion and adjusts the review criteria based on the estimated user's emotion. For example, the review unit applies strict review criteria when the user is anxious. The review unit can also apply general review criteria when the user is relaxed. Furthermore, the review unit can apply detailed review criteria when the user is excited. This allows for a more appropriate review by adjusting the review criteria according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the review unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the review unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation. This allows the system to adjust the review criteria according to the user's emotion and provide a more appropriate review.

[0095] The review unit can adjust the detail level of the review based on the importance of the answer at the time of review. The review unit adjusts the detail level of the review based on the importance of the answer, for example, at the time of review. For example, the review unit performs a detailed review on an important answer to provide reliable information. The review unit can also perform a basic review on a general answer to quickly provide information. Furthermore, the review unit can also perform a review with reference to the opinion of an expert on a specialized answer. As a result, more reliable information can be provided by adjusting the detail level of the review based on the importance of the answer. A part or all of the above-mentioned processing in the review unit may be performed using, for example, AI, or may be performed without using AI. For example, the review unit can perform a review using an AI model that inputs the importance data of the answer and outputs the detail level of the review. As a result, the system can provide more reliable information by adjusting the detail level of the review based on the importance of the answer.

[0096] The review unit can estimate the user's emotion and determine the priority of the reviews based on the estimated user's emotion. The review unit, for example, estimates the user's emotion and determines the priority of the reviews based on the estimated user's emotion. For example, when the user feels anxious, the review unit preferentially reviews answers with high urgency. In addition, when the user is relaxed, the review unit can also preferentially review general answers. Furthermore, when the user is excited, the review unit can also preferentially review interesting answers. This enables more appropriate reviews by determining the priority of reviews according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the review unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the review unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation. This allows the system to prioritize reviews based on the user's emotions, enabling more appropriate reviews.

[0097] The review unit can determine the priority of the review based on the time of submission of the answer at the time of review. The review unit, for example, determines the priority of the review based on the time of submission of the answer at the time of review. For example, the review unit quickly reviews the latest answer. The review unit can also perform a general review on past answers. Furthermore, the review unit can preferentially review answers with high urgency. This allows for a faster response by determining the priority of the review based on the time of submission of the answer. A part or all of the above-mentioned processing in the review unit may be performed using, for example, AI, or may be performed without using AI. For example, the review unit can perform the review using an AI model that inputs data on the time of submission of the answer and outputs the priority of the review. This allows the system to determine the priority of the review based on the time of submission of the answer, allowing for a faster response.

[0098] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0099] The reception unit can analyze the user's past question history and generate personalized feedback to provide optimal answers. For example, the reception unit can provide related new information based on topics that the user has frequently asked about in the past. The reception unit can also find specific patterns from the user's past question history and suggest topics that the user may be interested in. Furthermore, the reception unit can analyze the user's past question history and provide information in a format that the user can easily understand. This makes it possible to provide more personalized information by utilizing the user's past question history.

[0100] The evaluation unit can estimate the user's emotion and adjust the evaluation feedback based on the estimated user's emotion. For example, the evaluation unit can provide positive feedback preferentially when the user feels anxious. The evaluation unit can also provide detailed feedback when the user feels relaxed. Furthermore, the evaluation unit can provide interactive feedback when the user feels excited. This allows for more appropriate evaluation by adjusting the evaluation feedback according to the user's emotion.

[0101] The review unit can provide educational content to the user based on the expert's review results. For example, the review unit generates content that explains the errors or shortcomings pointed out by the expert. The review unit can also provide quizzes and tests that allow the user to study based on the expert's review results. Furthermore, the review unit can provide detailed explanations that allow the user to gain a deeper understanding based on the expert's review results. In this way, the expert's review results can be utilized to support the user's learning.

[0102] The fact check unit can estimate the user's emotions and adjust the way in which the fact check results are provided based on the estimated user's emotions. For example, the fact check unit can provide concise and clear results when the user is anxious. The fact check unit can also provide detailed explanations when the user is relaxed. Furthermore, the fact check unit can provide visually appealing results when the user is excited. This allows for more appropriate information provision by adjusting the way in which the fact check results are provided according to the user's emotions.

[0103] The evaluation unit can provide evaluation trends to other users based on the user's evaluation data. For example, the evaluation unit analyzes evaluation trends for a specific topic and shares them with other users. The evaluation unit can also provide popular answers and topics in a ranking format based on the evaluation data of the entire user community. Furthermore, the evaluation unit can display evaluation fluctuations in real time based on the user's evaluation data. This makes it possible to provide useful information to other users by utilizing the user's evaluation data.

[0104] The review unit can estimate the user's emotions and adjust the review feedback based on the estimated user's emotions. For example, the review unit can provide positive feedback preferentially when the user feels anxious. The review unit can also provide detailed feedback when the user feels relaxed. Furthermore, the review unit can provide interactive feedback when the user feels excited. This allows for more appropriate reviews by adjusting the review feedback according to the user's emotions.

[0105] The reception unit can provide area-specific information based on the user's geographical location information. For example, when the user is in a particular area, the reception unit can provide news and event information related to that area. The reception unit can also provide local service and store information based on the user's current location. Furthermore, when the user is traveling, the reception unit can provide tourist information and traffic information related to the travel destination. This makes it possible to provide more relevant information by utilizing the user's geographical location information.

[0106] The fact check unit can estimate the user's emotions and adjust the order in which the fact check results are provided based on the estimated user's emotions. For example, when the user feels anxious, the fact check unit can provide the most reliable information preferentially. In addition, when the user feels relaxed, the fact check unit can also provide general information preferentially. Furthermore, when the user is excited, the fact check unit can also provide interesting information preferentially. This makes it possible to provide more appropriate information by adjusting the order in which the fact check results are provided according to the user's emotions.

[0107] The providing unit can provide new related information based on the user's past question history. For example, the providing unit provides the latest information related to topics that the user has previously asked about. The providing unit can also suggest topics that the user may be interested in based on the user's past question history. Furthermore, the providing unit can analyze the user's past question history and provide information in a format that is easy for the user to understand. This makes it possible to provide more relevant information by utilizing the user's past question history.

[0108] The providing unit can estimate the user's emotion and adjust the format of the information to be provided based on the estimated user's emotion. For example, when the user feels anxious, the providing unit provides simple information with high visibility. In addition, when the user feels relaxed, the providing unit can also provide detailed information. Furthermore, when the user is excited, the providing unit can also provide visually attractive information. In this way, by adjusting the format of information according to the user's emotion, more appropriate information can be provided.

[0109] The process flow of the second embodiment will be briefly described below.

[0110] Step 1: The reception unit receives a question from a user. For example, the reception unit can receive a question input by the user through a browser or a message app. Step 2: The fact-checking unit automatically fact-checks the AI's answers to the questions received by the reception unit. For example, the fact-checking unit evaluates the accuracy of the answers by checking them against reliable sources. Reliable sources include government agency data and academic papers. The processing in the fact-checking unit may be performed using AI or without AI. Step 3: The providing unit provides the result fact-checked by the fact-checking unit. For example, the providing unit displays the result of the fact-checking to the user. This allows the user to check the accuracy of the answer.

[0111] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0112] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0113] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0114] Each of the multiple elements including the above-mentioned reception unit, fact check unit, provision unit, evaluation unit, and review unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and receives questions from a user. The fact check unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically fact-checks the answer of the generation AI. The provision unit is realized, for example, by the control unit 46A of the smart device 14 and displays the result of the fact check to the user. The evaluation unit is realized, for example, by the control unit 46A of the smart device 14 and utilizes a user community to evaluate the answer. The review unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and reviews the answer by a team of experts. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0115] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0116] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0117] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0118] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0119] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0121] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0122] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0123] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0124] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0125] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0126] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0128] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0129] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements including the above-mentioned reception unit, fact check unit, provision unit, evaluation unit, and review unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and receives questions from a user. The fact check unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically fact-checks the answer of the generation AI. The provision unit is realized, for example, by the control unit 46A of the smart glasses 214 and displays the result of the fact check to the user. The evaluation unit is realized, for example, by the control unit 46A of the smart glasses 214 and utilizes a user community to evaluate the answer. The review unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and reviews the answer by a team of experts. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0131] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0132] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0133] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0135] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0137] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0138] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0139] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0140] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0141] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0142] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0144] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements including the above-mentioned reception unit, fact check unit, provision unit, evaluation unit, and review unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314 and receives questions from a user. The fact check unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically fact-checks the answer of the generation AI. The provision unit is realized, for example, by the control unit 46A of the headset type terminal 314 and displays the result of the fact check to the user. The evaluation unit is realized, for example, by the control unit 46A of the headset type terminal 314 and utilizes a user community to evaluate the answer. The review unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and reviews the answer by a team of experts. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0147] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0148] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0149] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0150] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0151] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0153] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0154] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0155] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0156] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0157] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0158] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0159] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0160] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0161] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0162] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0163] Each of the multiple elements including the above-mentioned reception unit, fact check unit, provision unit, evaluation unit, and review unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and receives questions from a user. The fact check unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically fact-checks the answer of the generation AI. The provision unit is realized, for example, by the control unit 46A of the robot 414 and displays the result of the fact check to the user. The evaluation unit is realized, for example, by the control unit 46A of the robot 414 and utilizes a user community to evaluate the answer. The review unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and reviews the answer by a team of experts. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0164] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0165] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0166] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0167] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0168] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0169] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0171] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0172] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0173] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0174] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0175] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0176] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0177] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration in which a processor is used that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0178] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0179] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0180] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0181] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0182] (Appendix 1) A reception unit that receives questions from users; A fact checking unit that automatically fact-checks the answer of the generation AI to the question received by the reception unit; A providing unit that provides the results of the fact check by the fact check unit. A system characterized by: (Appendix 2) Equipping the user community with an evaluation section that evaluates the answers of the generative AI 2. The system of claim 1, (Appendix 3) Have a review department where responses are reviewed by a team of experts 2. The system of claim 1, (Appendix 4) The fact-checking department: Evaluate the accuracy of your answers against reliable sources 2. The system of claim 1, (Appendix 5) The evaluation unit is The user rates the answer as "correct", "incorrect", or "additional information required" and shares it with other users. 3. The system of claim 2, (Appendix 6) The review unit includes: Experts will review your answers and make corrections or additions as necessary 4. The system of claim 3. (Appendix 7) The reception unit is The system estimates the user's emotions and adjusts the timing of accepting questions based on the estimated user emotions. 2. The system of claim 1, (Appendix 8) The reception unit is Analyze the user's past question history and select the appropriate reception method 2. The system of claim 1, (Appendix 9) The reception unit is When questions are asked, they are filtered based on the user's current interests 2. The system of claim 1, (Appendix 10) The reception unit is Estimate the user's emotions and prioritize questions to be accepted based on the estimated user emotions. 2. The system of claim 1, (Appendix 11) The reception unit is When accepting questions, the system takes into account the user's geographic location information to prioritize questions that are more relevant to the user. 2. The system of claim 1, (Appendix 12) The reception unit is When a question is submitted, we analyze the user's social media activity and submit related questions. 2. The system of claim 1, (Appendix 13) The fact-checking department: Infer user sentiment and adjust fact-checking criteria based on the inferred user sentiment 2. The system of claim 1, (Appendix 14) The fact-checking department: When fact-checking, adjust the level of detail of your check based on the importance of the answer 2. The system of claim 1, (Appendix 15) The fact-checking department: When fact-checking, different checking algorithms are applied depending on the answer category 2. The system of claim 1, (Appendix 16) The fact-checking department: Infer user sentiment and prioritize fact-checks based on the inferred user sentiment 2. The system of claim 1, (Appendix 17) The fact-checking department: When fact-checking, prioritize checks based on when responses were submitted 2. The system of claim 1, (Appendix 18) The fact-checking department: When fact-checking, adjust the order of checks based on the relevance of the answer 2. The system of claim 1, (Appendix 19) The providing unit is Estimate the user's emotions and adjust the way information is presented based on the estimated user's emotions 2. The system of claim 1, (Appendix 20) The providing unit is When providing information, adjust the level of detail provided based on the importance of the information 2. The system of claim 1, (Appendix 21) The providing unit is When serving, different serving algorithms are applied depending on the category of information 2. The system of claim 1, (Appendix 22) The providing unit is Estimate the user's emotions and prioritize the information to be provided based on the estimated user's emotions. 2. The system of claim 1, (Appendix 23) The providing unit is At the time of submission, the information will be prioritized based on when it was submitted. 2. The system of claim 1, (Appendix 24) The providing unit is When serving, adjust the order of serving based on the relevance of the information 2. The system of claim 1, (Appendix 25) The evaluation unit is Inferring user emotions and adjusting evaluation criteria based on the estimated user emotions 3. The system of claim 2, (Appendix 26) The evaluation unit is When assessing, adjust the detail of the assessment based on the importance of the answer 3. The system of claim 2, (Appendix 27) The evaluation unit is Estimate user sentiment and prioritize ratings based on the estimated user sentiment 3. The system of claim 2, (Appendix 28) The evaluation unit is During evaluation, prioritize evaluations based on when responses were submitted 3. The system of claim 2, (Appendix 29) The review unit includes: Infer user sentiment and adjust review criteria based on the inferred user sentiment 4. The system of claim 3. (Appendix 30) The review unit includes: During review, adjust the review detail based on the importance of the response 4. The system of claim 3. (Appendix 31) The review unit includes: Infer user sentiment and prioritize reviews based on the inferred user sentiment 4. The system of claim 3. (Appendix 32) The review unit includes: During review, we prioritize reviews based on when responses are submitted 4. The system of claim 3. [Explanation of symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception unit that receives questions from users; A fact checking unit that automatically fact-checks the answer of the generation AI to the question accepted by the acceptance unit; A providing unit that provides the results of the fact check by the fact check unit. A system characterized by:

2. Equipping an evaluation section that utilizes the user community to evaluate the answers of the generated AI 2. The system of claim 1 .

3. Have a review department where responses are reviewed by a team of experts 2. The system of claim 1 .

4. The fact-checking department: Evaluate the accuracy of your answers against reliable sources 2. The system of claim 1 .

5. The evaluation unit is Users can share their ratings for answers with other users 3. The system of claim 2.

6. The review unit includes: Experts will review your answers and make corrections or additions as necessary 4. The system of claim 3.

7. The reception unit is The system estimates the user's emotions and adjusts the timing of accepting questions based on the estimated user emotions.

2. The system of claim 1 .

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

9. The reception unit is When questions are asked, they are filtered based on the user's current interests 2. The system of claim 1 .

10. The reception unit is Estimate the user's emotions and prioritize questions to be accepted based on the estimated user emotions.

2. The system of claim 1 .

Images