system

Abstract

The system of the embodiment aims to automatically verify the accuracy of the answer generated by the generation AI and provide the correct answer. [Solution] A system according to an embodiment includes a reception unit, a search unit, an analysis unit, a generation unit, and an output unit. The reception unit receives an answer generated by a generation AI. The search unit searches a literature database using keywords related to the answer received by the reception unit. The analysis unit analyzes the content of the literature acquired by the search unit. The generation unit verifies the answer generated by the generation AI based on the content of the literature analyzed by the analysis unit, and generates a correct answer. The output unit provides the correct answer generated by the generation unit to a user.

Description

[Technical Field]

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

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

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

[0004] Conventional technology required humans to search for literature and verify the accuracy of answers generated by the AI, which was inefficient.

[0005] The system of the embodiment aims to automatically verify the accuracy of the answer generated by the generation AI and provide the correct answer. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a search unit, an analysis unit, a generation unit, and an output unit. The reception unit receives an answer generated by the generation AI. The search unit searches a literature database using keywords related to the answer received by the reception unit. The analysis unit analyzes the content of the literature acquired by the search unit. The generation unit verifies the answer generated by the generation AI based on the content of the literature analyzed by the analysis unit and generates a correct answer. The output unit provides the correct answer generated by the generation unit to the user. [Effects of the Invention]

[0007] The system according to the embodiment can automatically verify the accuracy of the answer generated by the generation AI and provide the correct answer. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A fact-checking system according to an embodiment of the present invention is a system that checks whether generated content is factual. This fact-checking system uses a generation AI to generate answers to user questions and crawls a reliable literature database, such as Google Scholar, to verify the accuracy of the generated answers. Specifically, the system searches the literature database using keywords related to the answer generated by the generation AI to obtain related literature. The system analyzes the content of the obtained literature to determine whether the generated answer is based on fact. Finally, the system provides the user with a correct answer. For example, the fact-checking system includes a reception unit that receives the answer generated by the generation AI. Next, the system includes a search unit that searches a literature database using keywords related to the generated answer. The search unit crawls a literature database, such as Google Scholar, to obtain related literature. The system further includes an analysis unit that analyzes the content of the obtained literature. The analysis unit compares the generated answer with the content of the literature to determine whether the generated answer is based on fact. At this time, the analysis unit also takes into account indicators for evaluating the reliability and relevance of the literature. Finally, the system includes a generation unit that generates a correct answer. The generation unit integrates the answer generated by the generation AI with the content of the literature to generate the final answer to be provided to the user. At this time, it identifies which parts of the answer generated by the generation AI match the content of the literature and corrects and supplements the inconsistent parts. Furthermore, the fact-checking system has an output unit that outputs the final answer to be provided to the user. The output unit provides the generated correct answer to the user. These components work together to create a system that checks whether the generated content is factual. This allows the fact-checking system to check whether the generated content is factual and provide the correct answer.

[0029] A fact-checking system according to an embodiment includes a reception unit, a search unit, an analysis unit, a generation unit, and an output unit. The reception unit receives an answer generated by a generation AI. The generation AI generates an answer using natural language generation technology or a machine learning algorithm. For example, the generation AI receives a question from a user as input and generates an answer based on related information. The generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The search unit searches a literature database using keywords related to the answer received by the reception unit. The search unit crawls reliable literature databases such as Google Scholar and PubMed to acquire related literature. For example, the search unit receives keywords as input and searches a literature database to acquire related literature. The search unit automatically searches a literature database using crawling technology to collect related literature. The analysis unit analyzes the content of the literature acquired by the search unit. The analysis unit compares the answer generated by the generation AI with the content of the literature to determine whether the generated answer is based on facts. For example, the analysis unit analyzes the contents of a document using text mining technology and evaluates the degree of match with the generated answer. The analysis unit also considers indicators for evaluating the reliability and relevance of the document. For example, the analysis unit evaluates the number of citations and impact factor of the document to determine the reliability of the document. The generation unit verifies the answer generated by the generation AI based on the content of the document analyzed by the analysis unit and generates a correct answer. The generation unit integrates the answer generated by the generation AI with the content of the document to generate a final answer to be provided to the user. For example, the generation unit identifies which parts of the answer generated by the generation AI match the content of the document and corrects or complements the inconsistent parts. The generation unit generates an accurate answer using information weighting and inconsistency resolution methods. The output unit provides the correct answer generated by the generation unit to the user. The output unit notifies the user of the generated correct answer. For example, the output unit displays the answer through a web application or mobile application. The output unit selects the optimal display method based on the user's device information. For example, the output unit provides a display method optimized for devices such as smartphones and tablets.As a result, the fact checking system according to the embodiment can check whether the generated content is factual and provide a correct answer.

[0030] The search unit may crawl Google Scholar or other reliable literature databases to retrieve relevant literature. Reliable literature databases include, but are not limited to, Google Scholar and PubMed. The search unit may, for example, crawl Google Scholar to retrieve relevant literature. The search unit may automatically search literature databases using crawling technology to collect relevant literature. For example, the search unit may receive keywords as input and search literature databases to retrieve relevant literature. The search unit may analyze the metadata of the retrieved literature to evaluate the credibility of the literature. For example, the search unit may evaluate the number of citations and impact factor of the literature to determine its credibility. This allows the accuracy of answers to be improved by retrieving relevant literature from reliable literature databases. Some or all of the above-described processing in the search unit may be performed using, for example, AI, or may be performed without AI. For example, the search unit may have AI crawl the literature database.

[0031] The analysis unit can compare the answer generated by the generation AI with the content of the literature and determine whether the generated answer is based on facts. The analysis unit, for example, compares the answer generated by the generation AI with the content of the literature using text mining technology. For example, the analysis unit compares keywords in the answer generated by the generation AI with keywords in the literature and evaluates the degree of match. The analysis unit can also compare the sentence structure of the answer generated by the generation AI with the sentence structure of the literature and evaluate the degree of match. For example, the analysis unit analyzes the sentence structure of the answer generated by the generation AI and compares it with the sentence structure of the literature. The analysis unit can also compare the content of the answer generated by the generation AI with the content of the literature using cross-referencing technology and evaluate the degree of match. For example, the analysis unit analyzes the content of the answer generated by the generation AI using cross-referencing technology and compares it with the content of the literature. This makes it possible to accurately determine whether the generated answer is based on facts. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or without AI. For example, the analysis unit can have the AI ​​compare the answers generated by the generation AI with the contents of the literature.

[0032] The analysis unit can evaluate the reliability and relevance of a document based on indicators for assessing the reliability and relevance of the document. For example, the analysis unit evaluates the number of citations and impact factor of the document to evaluate the reliability of the document. For example, the analysis unit analyzes the number of citations of the document to determine the reliability of the document. The analysis unit can also evaluate the impact factor of the document to determine the reliability of the document. For example, the analysis unit analyzes the impact factor of the document to determine the reliability of the document. Furthermore, the analysis unit evaluates the degree of agreement between the content of the document and the content of the answer generated by the generation AI to evaluate the relevance of the document. For example, the analysis unit compares the content of the document with the content of the answer generated by the generation AI and evaluates the degree of agreement. This allows the reliability and relevance of the document to be evaluated, thereby improving the accuracy of the analysis. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can cause AI to evaluate the reliability and relevance of the document.

[0033] The generation unit can integrate the answer generated by the generation AI with the content of the literature to generate a final answer to be provided to the user. The generation unit, for example, weights information to integrate the answer generated by the generation AI with the content of the literature. For example, the generation unit weights each part of the answer generated by the generation AI based on the degree of agreement with the content of the literature. The generation unit also uses a method to resolve inconsistencies between the answer generated by the generation AI and the content of the literature. For example, the generation unit detects inconsistencies between the answer generated by the generation AI and the content of the literature and makes corrections to resolve the inconsistencies. This allows the answer generated by the generation AI to be integrated with the content of the literature to generate an accurate final answer. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can cause AI to integrate the answer generated by the generation AI with the content of the literature.

[0034] The generation unit can identify which parts of the answer generated by the generation AI match the content of the literature and correct or complement the inconsistent parts. For example, the generation unit compares each part of the answer generated by the generation AI with the content of the literature and identifies the matching parts. For example, the generation unit compares keywords in each part of the answer generated by the generation AI with keywords in the literature and identifies the matching parts. The generation unit can also compare the sentence structure of each part of the answer generated by the generation AI with the sentence structure of the literature and identify the matching parts. For example, the generation unit analyzes the sentence structure of each part of the answer generated by the generation AI and compares it with the sentence structure of the literature. The generation unit also uses a method to correct or complement the inconsistent parts of the answer generated by the generation AI. For example, the generation unit regenerates the inconsistent parts of the answer generated by the generation AI. The generation unit can also provide additional information to the inconsistent parts of the answer generated by the generation AI. For example, the generation unit adds literature information related to the inconsistent parts of the answer generated by the generation AI. This can further improve the accuracy of the generated answer. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit may cause AI to correct or complete inconsistent parts of the answers generated by the generation AI.

[0035] The output unit can provide the generated correct answer to the user. For example, the output unit displays the answer through a web application or a mobile application to notify the user of the generated correct answer. For example, the output unit selects an optimal display method taking into account the user's device information. The output unit provides a display method optimized for devices such as smartphones and tablets. For example, the output unit provides a display method tailored to the smartphone screen size. The output unit can also customize the display method based on the user's preferences. For example, the output unit preferentially provides a display method that the user has previously preferred. This makes it possible to provide the user with the correct answer. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can cause AI to execute the display method for the generated correct answer.

[0036] The reception unit can analyze the user's past question history and select the optimal reception method. The reception unit, for example, stores the user's past question history in a database and analyzes it. For example, the reception unit prioritizes receiving topics that the user has frequently asked about in the past. The reception unit can also prioritize suggesting question formats (text, voice, etc.) that the user has used in the past. For example, the reception unit suggests the optimal reception method for a specific time period based on the user's past question history. This makes it possible to provide the optimal reception method based on the user's past question history. Some 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 have AI analyze the user's past question history and select the optimal reception method.

[0037] When receiving answers, the reception unit can filter them based on the user's current areas of interest. For example, the reception unit can analyze the user's search history and social media activity to identify the user's current areas of interest. For example, the reception unit can prioritize receiving questions related to topics that the user is currently interested in. The reception unit can also filter related questions based on the user's recent search history. For example, the reception unit can filter questions based on topics of experts and influencers that the user follows. This makes it possible to receive appropriate questions based on the user's areas of interest. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can have AI perform the identification of the user's areas of interest and the filtering of questions.

[0038] When accepting answers, the acceptance unit can prioritize accepting highly relevant answers by taking into account the user's geographical location information. The acceptance unit, for example, uses GPS data or an IP address to acquire the user's geographical location information. For example, the acceptance unit prioritizes accepting questions related to the user's current location. The acceptance unit can also prioritize accepting questions about region-specific issues based on the user's geographical location information. For example, if the user is traveling, the acceptance unit prioritizes accepting questions related to the user's travel destination. This makes it possible to accept appropriate questions based on the user's geographical location information. Some or all of the above-described processing in the acceptance unit may be performed using, for example, AI, or may be performed without using AI. For example, the acceptance unit may cause AI to acquire the user's geographical location information and accept highly relevant questions.

[0039] The reception unit can analyze the user's social media activity when receiving an answer and receive a related answer. For example, the reception unit analyzes the user's social media postings and the number of followers to analyze the user's social media activity. For example, the reception unit prioritizes receiving questions related to topics in which the user is interested on social media. The reception unit can also receive questions related to topics in which the user's social media followers and friends are interested. For example, the reception unit receives related questions based on the user's recent social media postings. This makes it possible to receive appropriate questions based on the user's social media activity. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can cause AI to analyze the user's social media activity and receive related questions.

[0040] During a search, the search unit can adjust the level of detail of search results based on the importance of the document. For example, the search unit evaluates the number of citations and impact factor of a document to evaluate the importance of the document. For example, the search unit analyzes the number of citations of a document to determine the importance of the document. The search unit can also evaluate the impact factor of a document to determine the importance of the document. For example, the search unit analyzes the impact factor of a document to determine the importance of the document. The search unit adjusts the level of detail of the search results based on the importance of the document. For example, the search unit prioritizes displaying documents with high importance and providing detailed information. The search unit can also briefly display documents with low importance and provide detailed information as needed. Furthermore, the search unit adjusts the display order of the search results based on the importance of the document. This allows appropriate search results to be provided based on the importance of the document. Some or all of the above-described processing in the search unit may be performed using, for example, AI, or may be performed without using AI. For example, the search unit may have AI perform the evaluation of the importance of the document and the adjustment of the level of detail of the search results.

[0041] The search unit can apply different search algorithms depending on the category of the document during the search. For example, the search unit analyzes the metadata of the document to identify the document category. For example, the search unit analyzes the title and abstract of the document to identify the document category. The search unit applies different search algorithms depending on the document category. For example, the search unit applies a specialized search algorithm to medical documents to provide highly accurate search results. The search unit can also adjust the search algorithm based on technical keywords for technical documents. Furthermore, the search unit applies an algorithm that prioritizes searching for highly relevant keywords to social science documents. This makes it possible to provide an appropriate search algorithm depending on the document category. Some or all of the above-mentioned processing in the search unit may be performed using, for example, AI, or may be performed without using AI. For example, the search unit can have AI perform the identification of the document category and the application of the search algorithm.

[0042] During a search, the search unit can determine the priority of search results based on the publication date of the document. For example, the search unit analyzes the metadata of the document to identify the publication date of the document. For example, the search unit analyzes the publication year of the document to identify the publication date of the document. The search unit determines the priority of search results based on the publication date of the document. For example, the search unit prioritizes displaying the most recent document to provide the latest information. The search unit can also display older documents as needed and provide them as reference information. Furthermore, the search unit adjusts the display order of search results based on the publication date of the document. This makes it possible to provide appropriate search results based on the publication date of the document. Some or all of the above-described processing in the search unit may be performed using, for example, AI, or may be performed without using AI. For example, the search unit may have AI perform the identification of the publication date of the document and the determination of the priority of search results.

[0043] During a search, the search unit can adjust the order of search results based on the relevance of the documents. The search unit, for example, uses keyword matching technology to evaluate the relevance of the documents. For example, the search unit compares keywords in the documents with keywords in the user's search query to evaluate the relevance. The search unit can also evaluate the relevance of the documents using a co-author network. For example, the search unit analyzes the co-author network of the documents to evaluate the relevance. The search unit adjusts the order of search results based on the relevance of the documents. For example, the search unit prioritizes displaying the most relevant documents to provide useful information to the user. The search unit can also briefly display less relevant documents and provide more detailed information as needed. Furthermore, the search unit adjusts the display order of the search results based on the relevance of the documents. This allows appropriate search results to be provided based on the relevance of the documents. Some or all of the above-described processing in the search unit may be performed using, for example, AI, or may be performed without using AI. For example, the search unit can have AI perform the evaluation of the relevance of the documents and the adjustment of the order of search results.

[0044] The analysis unit can improve the accuracy of the analysis by taking into account the interrelationships between documents during the analysis. The analysis unit, for example, analyzes citation relationships to evaluate the interrelationships between documents. For example, the analysis unit analyzes the citation relationships between documents and identifies related documents. The analysis unit can also evaluate the interrelationships between documents using a co-author network. For example, the analysis unit analyzes the co-author network of documents and identifies related documents. The analysis unit improves the accuracy of the analysis by taking into account the interrelationships between documents. For example, the analysis unit cross-references related documents to improve the accuracy of the analysis. The analysis unit can also complement the analysis results by taking into account the citation relationships between documents. Furthermore, the analysis unit improves the reliability of the analysis based on the interrelationships between documents. In this way, the accuracy of the analysis can be improved by taking into account the interrelationships between documents. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can cause AI to evaluate the interrelationships between documents and improve the accuracy of the analysis.

[0045] The analysis unit can perform the analysis while taking into account the attribute information of the author of the document. The analysis unit, for example, analyzes the metadata of the document to obtain the attribute information of the author of the document. For example, the analysis unit analyzes the affiliated institution and research field of the author of the document to identify the attribute information of the author. The analysis unit performs the analysis while taking into account the attribute information of the author of the document. For example, the analysis unit improves the accuracy of the analysis by taking into account the author's field of expertise. The analysis unit can also complement the analysis results by referring to the author's past research results. Furthermore, the analysis unit improves the reliability of the analysis based on the attribute information of the author. In this way, the reliability of the analysis can be improved by taking into account the attribute information of the author of the document. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can cause AI to obtain and analyze the attribute information of the author of the document.

[0046] The analysis unit can perform the analysis taking into account the geographical distribution of the document. For example, the analysis unit analyzes metadata of the document to identify the geographical distribution of the document. For example, the analysis unit analyzes the country or region of publication of the document to identify the geographical distribution. The analysis unit performs the analysis taking into account the geographical distribution of the document. For example, the analysis unit analyzes region-specific information based on the geographical distribution of the document. The analysis unit can also cross-reference geographically related documents to improve the accuracy of the analysis. Furthermore, the analysis unit improves the reliability of the analysis results by taking into account the geographical distribution. In this way, the reliability of the analysis can be improved by taking into account the geographical distribution of the document. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can have AI perform the identification and analysis of the geographical distribution of the document.

[0047] The analysis unit can improve the accuracy of the analysis by referring to related documents of a document during analysis. The analysis unit, for example, analyzes citation relationships to identify related documents of a document. For example, the analysis unit analyzes citation relationships of documents and identifies related documents. The analysis unit can also identify related documents of a document using a co-author network. For example, the analysis unit analyzes the co-author network of a document and identifies related documents. The analysis unit improves the accuracy of the analysis by referring to related documents of a document. For example, the analysis unit mutually references related documents to improve the accuracy of the analysis. The analysis unit can also complement the analysis results by taking into account the citation relationships of related documents. Furthermore, the analysis unit improves the reliability of the analysis based on the related documents. As a result, the accuracy of the analysis can be improved by referring to related documents. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can cause AI to identify and analyze related documents of a document.

[0048] The generation unit can improve the accuracy of generation by taking into account the interrelationships between documents during generation. The generation unit, for example, analyzes citation relationships to evaluate the interrelationships between documents. For example, the generation unit analyzes the citation relationships between documents and identifies related documents. The generation unit can also evaluate the interrelationships between documents using a co-author network. For example, the generation unit analyzes the co-author network of documents and identifies related documents. The generation unit improves the accuracy of generation by taking into account the interrelationships between documents. For example, the generation unit cross-references related documents to improve the accuracy of generation. The generation unit can also complement the generation results by taking into account the citation relationships between documents. Furthermore, the generation unit improves the reliability of generation based on the interrelationships between documents. In this way, the accuracy of generation can be improved by taking into account the interrelationships between documents. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can cause AI to evaluate the interrelationships between documents and improve the accuracy of generation.

[0049] The generation unit can generate the document taking into account the attribute information of the author of the document. The generation unit, for example, analyzes the metadata of the document to obtain the attribute information of the author of the document. For example, the generation unit analyzes the affiliated institution and research field of the author of the document to identify the author's attribute information. The generation unit generates the document taking into account the attribute information of the author of the document. For example, the generation unit improves the accuracy of the generation by taking into account the author's field of expertise. The generation unit can also complement the generation results by referring to the author's past research results. Furthermore, the generation unit improves the reliability of the generation based on the author's attribute information. In this way, the reliability of the generation can be improved by taking into account the attribute information of the author of the document. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can cause AI to obtain and generate the attribute information of the author of the document.

[0050] The generation unit can generate the information taking into account the geographical distribution of the documents. For example, the generation unit analyzes metadata of the documents to identify the geographical distribution of the documents. For example, the generation unit analyzes the country or region of publication of the documents to identify the geographical distribution. The generation unit generates information specific to the region based on the geographical distribution of the documents. The generation unit can also cross-reference geographically related documents to improve the accuracy of the generation. Furthermore, the generation unit improves the reliability of the generated results by taking the geographical distribution into account. In this way, the reliability of the generation can be improved by taking the geographical distribution of the documents into account. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can cause AI to identify and generate the geographical distribution of the documents.

[0051] The generation unit can improve the accuracy of generation by referring to related documents of a document during generation. The generation unit, for example, analyzes citation relationships to identify related documents of a document. For example, the generation unit analyzes citation relationships of documents and identifies related documents. The generation unit can also identify related documents of a document using a co-author network. For example, the generation unit analyzes the co-author network of a document and identifies related documents. The generation unit improves the accuracy of generation by referring to related documents of a document. For example, the generation unit mutually references related documents to improve the accuracy of generation. The generation unit can also complement the generation results by taking into account citation relationships of related documents. Furthermore, the generation unit improves the reliability of generation based on related documents. As a result, the accuracy of generation can be improved by referring to related documents. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can cause AI to identify and generate related documents of a document.

[0052] The output unit can select the optimal display method by referring to the user's past operation history at the time of output. The output unit, for example, stores the user's past operation history in a database and analyzes it. For example, the output unit preferentially provides a display method that the user has previously preferred. The output unit can also suggest the optimal display method based on the user's past operation history. For example, the output unit selects the optimal display method for a specific time period from the user's past operation history. This makes it possible to provide the optimal display method based on the user's past operation history. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can cause AI to analyze the user's past operation history and select the optimal display method.

[0053] The output unit can select the optimal display method by taking into account the user's device information when outputting. The output unit, for example, analyzes device metadata to acquire the user's device information. For example, the output unit analyzes the screen size and OS type of the user's device to identify the device information. The output unit selects the optimal display method by taking into account the user's device information. For example, if the user is using a smartphone, the output unit provides a display method tailored to the screen size. Furthermore, if the user is using a tablet, the output unit can provide a display method optimized for a large screen. Furthermore, if the user is using a smartwatch, the output unit provides a display method that is simple and highly visible. This makes it possible to provide the optimal display method based on the user's device information. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can cause AI to acquire the user's device information and select the optimal display method.

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

[0055] The fact-checking system may further include a reliability evaluation unit that evaluates the reliability of a user. The reliability evaluation unit analyzes the user's past question history and the accuracy of the answers to evaluate the user's reliability. For example, the reliability evaluation unit calculates the reliability based on the number of questions the user has submitted in the past and the percentage of accurate answers to those questions. The reliability evaluation unit may also evaluate the consistency and relevance of the user's questions and adjust the reliability. Furthermore, the reliability evaluation unit may adjust the priority of answers based on the user's reliability. For example, the reliability evaluation unit may provide quick answers to users with high reliability and perform additional verification procedures for users with low reliability. This may improve the reliability and efficiency of the entire system.

[0056] The fact-checking system may further include an additional information providing unit that provides related additional information based on the content of the user's question. The additional information providing unit analyzes the content of the user's question and searches for related topics and literature. For example, the additional information providing unit may provide the latest research results or news articles related to the topic the user has asked about. The additional information providing unit may also provide FAQs or guidelines related to the content of the user's question. Furthermore, the additional information providing unit may suggest related topics that the user may be interested in. This allows the user to obtain not only an answer to their question but also related additional information, thereby broadening their knowledge.

[0057] The fact-checking system may further include a history analysis unit that analyzes the user's past question history and selects the optimal answering method. The history analysis unit stores the user's past question history in a database and analyzes it. For example, the history analysis unit may prioritize answers to topics that the user has frequently asked about in the past. The history analysis unit may also prioritize suggesting question formats (text, voice, etc.) that the user has used in the past. Furthermore, the history analysis unit may suggest the optimal answering method for a specific time period based on the user's past question history. This allows the optimal answering method to be provided based on the user's past question history.

[0058] The fact-checking system may further include a geographic information unit that prioritizes providing relevant answers based on the user's geographic location. The geographic information unit uses GPS data or an IP address to obtain the user's geographic location. For example, the geographic information unit may prioritize answers to questions related to the user's current location. The geographic information unit may also prioritize answers to questions about region-specific issues based on the user's geographic location. Furthermore, if the user is traveling, the geographic information unit may prioritize answers to questions related to the user's travel destination. This allows the system to provide appropriate answers to questions based on the user's geographic location.

[0059] The fact-checking system may further include a social media analysis unit that analyzes the user's social media activity and provides relevant answers. The social media analysis unit analyzes the user's social media posts and the number of followers to analyze the user's social media activity. For example, the social media analysis unit prioritizes answers to questions related to topics that the user is interested in on social media. The social media analysis unit may also answer questions related to topics that the user's social media followers and friends are interested in. Furthermore, the social media analysis unit answers relevant questions based on the user's recent social media posts. This allows the system to answer appropriate questions based on the user's social media activity.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The reception unit accepts the answer generated by the generation AI. The generation AI generates an answer using natural language generation technology and machine learning algorithms. For example, the generation AI receives a question from a user as input and generates an answer based on related information. Step 2: The search unit searches a literature database using keywords related to the answer received by the reception unit. The search unit crawls reliable literature databases such as Google Scholar and PubMed to obtain relevant literature. For example, the search unit receives keywords as input and searches a literature database to obtain relevant literature. Step 3: The analysis unit analyzes the content of the literature retrieved by the search unit. The analysis unit compares the answer generated by the generation AI with the content of the literature and determines whether the generated answer is based on facts. For example, the analysis unit may use text mining technology to analyze the content of the literature and evaluate the degree of agreement with the generated answer. The analysis unit also considers indicators for evaluating the reliability and relevance of the literature. Step 4: The generation unit verifies the answer generated by the generation AI based on the content of the literature analyzed by the analysis unit and generates a correct answer. The generation unit integrates the answer generated by the generation AI with the content of the literature to generate the final answer to be provided to the user. For example, the generation unit identifies which parts of the answer generated by the generation AI match the content of the literature and corrects and completes the inconsistent parts. Step 5: The output unit provides the user with the correct answer generated by the generation unit. The output unit notifies the user of the generated correct answer. For example, the output unit displays the answer through a web application or a mobile application. The output unit selects the optimal display method taking into account the user's device information.

[0062] (Example 2) A fact-checking system according to an embodiment of the present invention is a system that checks whether generated content is factual. This fact-checking system uses a generation AI to generate answers to user questions and crawls a reliable literature database, such as Google Scholar, to verify the accuracy of the generated answers. Specifically, the system searches the literature database using keywords related to the answer generated by the generation AI to obtain related literature. The system analyzes the content of the obtained literature to determine whether the generated answer is based on fact. Finally, the system provides the user with a correct answer. For example, the fact-checking system includes a reception unit that receives the answer generated by the generation AI. Next, the system includes a search unit that searches a literature database using keywords related to the generated answer. The search unit crawls a literature database, such as Google Scholar, to obtain related literature. The system further includes an analysis unit that analyzes the content of the obtained literature. The analysis unit compares the generated answer with the content of the literature to determine whether the generated answer is based on fact. This analysis unit also takes into account indicators for evaluating the reliability and relevance of the literature. Finally, the system includes a generation unit that generates a correct answer. The generation unit integrates the answer generated by the generation AI with the content of the literature to generate the final answer to be provided to the user. At this time, it identifies which parts of the answer generated by the generation AI match the content of the literature and corrects and supplements the inconsistent parts. Furthermore, the fact-checking system has an output unit that outputs the final answer to be provided to the user. The output unit provides the generated correct answer to the user. These components work together to create a system that checks whether the generated content is factual. This allows the fact-checking system to check whether the generated content is factual and provide the correct answer.

[0063] A fact-checking system according to an embodiment includes a reception unit, a search unit, an analysis unit, a generation unit, and an output unit. The reception unit receives an answer generated by a generation AI. The generation AI generates an answer using natural language generation technology or a machine learning algorithm. For example, the generation AI receives a question from a user as input and generates an answer based on related information. The generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The search unit searches a literature database using keywords related to the answer received by the reception unit. The search unit crawls reliable literature databases such as Google Scholar and PubMed to acquire related literature. For example, the search unit receives keywords as input and searches a literature database to acquire related literature. The search unit automatically searches a literature database using crawling technology to collect related literature. The analysis unit analyzes the content of the literature acquired by the search unit. The analysis unit compares the answer generated by the generation AI with the content of the literature to determine whether the generated answer is based on facts. For example, the analysis unit analyzes the contents of a document using text mining technology and evaluates the degree of match with the generated answer. The analysis unit also considers indicators for evaluating the reliability and relevance of the document. For example, the analysis unit evaluates the number of citations and impact factor of the document to determine the reliability of the document. The generation unit verifies the answer generated by the generation AI based on the content of the document analyzed by the analysis unit and generates a correct answer. The generation unit integrates the answer generated by the generation AI with the content of the document to generate a final answer to be provided to the user. For example, the generation unit identifies which parts of the answer generated by the generation AI match the content of the document and corrects or complements the inconsistent parts. The generation unit generates an accurate answer using information weighting and inconsistency resolution methods. The output unit provides the correct answer generated by the generation unit to the user. The output unit notifies the user of the generated correct answer. For example, the output unit displays the answer through a web application or mobile application. The output unit selects the optimal display method based on the user's device information. For example, the output unit provides a display method optimized for devices such as smartphones and tablets.As a result, the fact checking system according to the embodiment can check whether the generated content is factual and provide a correct answer.

[0064] The search unit may crawl Google Scholar or other reliable literature databases to retrieve relevant literature. Reliable literature databases include, but are not limited to, Google Scholar and PubMed. The search unit may, for example, crawl Google Scholar to retrieve relevant literature. The search unit may automatically search literature databases using crawling technology to collect relevant literature. For example, the search unit may receive keywords as input and search literature databases to retrieve relevant literature. The search unit may analyze the metadata of the retrieved literature to evaluate the credibility of the literature. For example, the search unit may evaluate the number of citations and impact factor of the literature to determine its credibility. This allows the accuracy of answers to be improved by retrieving relevant literature from reliable literature databases. Some or all of the above-described processing in the search unit may be performed using, for example, AI, or may be performed without AI. For example, the search unit may have AI crawl the literature database.

[0065] The analysis unit can compare the answer generated by the generation AI with the content of the literature and determine whether the generated answer is based on facts. The analysis unit, for example, compares the answer generated by the generation AI with the content of the literature using text mining technology. For example, the analysis unit compares keywords in the answer generated by the generation AI with keywords in the literature and evaluates the degree of match. The analysis unit can also compare the sentence structure of the answer generated by the generation AI with the sentence structure of the literature and evaluate the degree of match. For example, the analysis unit analyzes the sentence structure of the answer generated by the generation AI and compares it with the sentence structure of the literature. The analysis unit can also compare the content of the answer generated by the generation AI with the content of the literature using cross-referencing technology and evaluate the degree of match. For example, the analysis unit analyzes the content of the answer generated by the generation AI using cross-referencing technology and compares it with the content of the literature. This makes it possible to accurately determine whether the generated answer is based on facts. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or without AI. For example, the analysis unit can have the AI ​​compare the answers generated by the generation AI with the contents of the literature.

[0066] The analysis unit can evaluate the reliability and relevance of a document based on indicators for assessing the reliability and relevance of the document. For example, the analysis unit evaluates the number of citations and impact factor of the document to evaluate the reliability of the document. For example, the analysis unit analyzes the number of citations of the document to determine the reliability of the document. The analysis unit can also evaluate the impact factor of the document to determine the reliability of the document. For example, the analysis unit analyzes the impact factor of the document to determine the reliability of the document. Furthermore, the analysis unit evaluates the degree of agreement between the content of the document and the content of the answer generated by the generation AI to evaluate the relevance of the document. For example, the analysis unit compares the content of the document with the content of the answer generated by the generation AI and evaluates the degree of agreement. This allows the reliability and relevance of the document to be evaluated, thereby improving the accuracy of the analysis. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can cause AI to evaluate the reliability and relevance of the document.

[0067] The generation unit can integrate the answer generated by the generation AI with the content of the literature to generate a final answer to be provided to the user. The generation unit, for example, weights information to integrate the answer generated by the generation AI with the content of the literature. For example, the generation unit weights each part of the answer generated by the generation AI based on the degree of agreement with the content of the literature. The generation unit also uses a method to resolve inconsistencies between the answer generated by the generation AI and the content of the literature. For example, the generation unit detects inconsistencies between the answer generated by the generation AI and the content of the literature and makes corrections to resolve the inconsistencies. This allows the answer generated by the generation AI to be integrated with the content of the literature to generate an accurate final answer. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can cause AI to integrate the answer generated by the generation AI with the content of the literature.

[0068] The generation unit can identify which parts of the answer generated by the generation AI match the content of the literature and correct or complement the inconsistent parts. For example, the generation unit compares each part of the answer generated by the generation AI with the content of the literature and identifies the matching parts. For example, the generation unit compares keywords in each part of the answer generated by the generation AI with keywords in the literature and identifies the matching parts. The generation unit can also compare the sentence structure of each part of the answer generated by the generation AI with the sentence structure of the literature and identify the matching parts. For example, the generation unit analyzes the sentence structure of each part of the answer generated by the generation AI and compares it with the sentence structure of the literature. The generation unit also uses a method to correct or complement the inconsistent parts of the answer generated by the generation AI. For example, the generation unit regenerates the inconsistent parts of the answer generated by the generation AI. The generation unit can also provide additional information to the inconsistent parts of the answer generated by the generation AI. For example, the generation unit adds literature information related to the inconsistent parts of the answer generated by the generation AI. This can further improve the accuracy of the generated answer. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit may cause AI to correct or complete inconsistent parts of the answers generated by the generation AI.

[0069] The output unit can provide the generated correct answer to the user. For example, the output unit displays the answer through a web application or a mobile application to notify the user of the generated correct answer. For example, the output unit selects an optimal display method taking into account the user's device information. The output unit provides a display method optimized for devices such as smartphones and tablets. For example, the output unit provides a display method tailored to the smartphone screen size. The output unit can also customize the display method based on the user's preferences. For example, the output unit preferentially provides a display method that the user has previously preferred. This makes it possible to provide the user with the correct answer. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can cause AI to execute the display method for the generated correct answer.

[0070] The reception unit can estimate the user's emotions and adjust the timing of accepting answers based on the estimated user's emotions. The reception unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the reception unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The reception unit can also estimate the user's emotions using voice analysis technology. For example, the reception unit analyzes the tone and speed of the user's voice to estimate the emotions. Furthermore, the reception unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor to estimate the emotions. For example, the reception unit estimates the emotions based on heart rate fluctuations. The reception unit adjusts the timing of accepting answers based on the estimated user's emotions. For example, if the user is feeling stressed, the reception unit quickly accepts answers to reduce the user's burden. Furthermore, if the user is relaxed, the reception unit can accept answers at a normal timing to match the user's pace. Furthermore, if the user is in a hurry, the reception unit immediately accepts answers to provide a prompt response. This allows the reception of answers at appropriate timing according to the user's emotions. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may have AI execute the estimation of the user's emotions and the adjustment of the reception timing.

[0071] The reception unit can analyze the user's past question history and select the optimal reception method. The reception unit, for example, stores the user's past question history in a database and analyzes it. For example, the reception unit prioritizes receiving topics that the user has frequently asked about in the past. The reception unit can also prioritize suggesting question formats (text, voice, etc.) that the user has used in the past. For example, the reception unit suggests the optimal reception method for a specific time period based on the user's past question history. This makes it possible to provide the optimal reception method based on the user's past question history. Some 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 have AI analyze the user's past question history and select the optimal reception method.

[0072] When receiving answers, the reception unit can filter them based on the user's current areas of interest. For example, the reception unit can analyze the user's search history and social media activity to identify the user's current areas of interest. For example, the reception unit can prioritize receiving questions related to topics that the user is currently interested in. The reception unit can also filter related questions based on the user's recent search history. For example, the reception unit can filter questions based on topics of experts and influencers that the user follows. This makes it possible to receive appropriate questions based on the user's areas of interest. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can have AI perform the identification of the user's areas of interest and the filtering of questions.

[0073] The reception unit can estimate the user's emotions and determine the priority of answers to be received based on the estimated user's emotions. The reception unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the reception unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The reception unit can also estimate the user's emotions using voice analysis technology. For example, the reception unit analyzes the tone and speed of the user's voice to estimate the emotions. Furthermore, the reception unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor to estimate the emotions. For example, the reception unit estimates the emotions based on heart rate fluctuations. The reception unit determines the priority of answers to be received based on the estimated user's emotions. For example, if the user is feeling stressed, the reception unit can prioritize important questions. Furthermore, if the user is relaxed, the reception unit can prioritize questions with normal priority. Furthermore, if the user is in a hurry, the reception unit can prioritize urgent questions. This makes it possible to receive answers with appropriate priority according to the user's emotions. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may have AI execute the estimation of the user's emotions and the determination of the priority of answers.

[0074] When accepting answers, the acceptance unit can prioritize accepting highly relevant answers by taking into account the user's geographical location information. The acceptance unit, for example, uses GPS data or an IP address to acquire the user's geographical location information. For example, the acceptance unit prioritizes accepting questions related to the user's current location. The acceptance unit can also prioritize accepting questions about region-specific issues based on the user's geographical location information. For example, if the user is traveling, the acceptance unit prioritizes accepting questions related to the user's travel destination. This makes it possible to accept appropriate questions based on the user's geographical location information. Some or all of the above-described processing in the acceptance unit may be performed using, for example, AI, or may be performed without using AI. For example, the acceptance unit may cause AI to acquire the user's geographical location information and accept highly relevant questions.

[0075] The reception unit can analyze the user's social media activity when receiving an answer and receive a related answer. For example, the reception unit analyzes the user's social media postings and the number of followers to analyze the user's social media activity. For example, the reception unit prioritizes receiving questions related to topics in which the user is interested on social media. The reception unit can also receive questions related to topics in which the user's social media followers and friends are interested. For example, the reception unit receives related questions based on the user's recent social media postings. This makes it possible to receive appropriate questions based on the user's social media activity. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can cause AI to analyze the user's social media activity and receive related questions.

[0076] The search unit can estimate a user's emotions and adjust the search expression method based on the estimated user's emotions. The search unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the search unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The search unit can also estimate the user's emotions using voice analysis technology. For example, the search unit analyzes the tone and speed of the user's voice to estimate the emotions. Furthermore, the search unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor to estimate the emotions. For example, the search unit estimates the emotions based on heart rate fluctuations. The search unit adjusts the search expression method based on the estimated user's emotions. For example, if the user is feeling stressed, the search unit provides a simple and intuitive search interface. Furthermore, if the user is relaxed, the search unit can provide detailed search options and suggest a customizable search method. Furthermore, if the user is in a hurry, the search unit prioritizes voice search and quickly displays search results. This makes it possible to provide an appropriate search expression method according to the user's emotions. Some or all of the above-described processing in the search unit may be performed using, for example, AI, or may be performed without using AI. For example, the search unit may use AI to estimate the user's emotions and adjust the search expression method.

[0077] During a search, the search unit can adjust the level of detail of search results based on the importance of the document. For example, the search unit evaluates the number of citations and impact factor of a document to evaluate the importance of the document. For example, the search unit analyzes the number of citations of a document to determine the importance of the document. The search unit can also evaluate the impact factor of a document to determine the importance of the document. For example, the search unit analyzes the impact factor of a document to determine the importance of the document. The search unit adjusts the level of detail of the search results based on the importance of the document. For example, the search unit prioritizes displaying documents with high importance and providing detailed information. The search unit can also briefly display documents with low importance and provide detailed information as needed. Furthermore, the search unit adjusts the display order of the search results based on the importance of the document. This allows appropriate search results to be provided based on the importance of the document. Some or all of the above-described processing in the search unit may be performed using, for example, AI, or may be performed without using AI. For example, the search unit may have AI perform the evaluation of the importance of the document and the adjustment of the level of detail of the search results.

[0078] The search unit can apply different search algorithms depending on the category of the document during the search. For example, the search unit analyzes the metadata of the document to identify the document category. For example, the search unit analyzes the title and abstract of the document to identify the document category. The search unit applies different search algorithms depending on the document category. For example, the search unit applies a specialized search algorithm to medical documents to provide highly accurate search results. The search unit can also adjust the search algorithm based on technical keywords for technical documents. Furthermore, the search unit applies an algorithm that prioritizes searching for highly relevant keywords to social science documents. This makes it possible to provide an appropriate search algorithm depending on the document category. Some or all of the above-mentioned processing in the search unit may be performed using, for example, AI, or may be performed without using AI. For example, the search unit can have AI perform the identification of the document category and the application of the search algorithm.

[0079] The search unit can estimate a user's emotion and adjust the display order of search results based on the estimated user's emotion. The search unit, for example, uses facial expression recognition technology to estimate the user's emotion. For example, the search unit captures the user's facial expression with a camera and estimates the emotion using a facial expression recognition algorithm. The search unit can also estimate the user's emotion using voice analysis technology. For example, the search unit analyzes the tone and speed of the user's voice to estimate the emotion. Furthermore, the search unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor to estimate the emotion. For example, the search unit estimates the emotion based on heart rate fluctuations. The search unit adjusts the display order of search results based on the estimated user's emotion. For example, if the user is feeling stressed, the search unit prioritizes displaying the most relevant search results. Furthermore, if the user is relaxed, the search unit can display detailed search results to allow the user to select. Furthermore, if the user is in a hurry, the search unit quickly displays search results and highlights important information. This makes it possible to provide an appropriate display order of search results according to the user's emotion. Some or all of the above-described processing in the search unit may be performed using, for example, AI, or may be performed without using AI. For example, the search unit may use AI to estimate the user's emotions and adjust the display order of search results.

[0080] During a search, the search unit can determine the priority of search results based on the publication date of the document. For example, the search unit analyzes the metadata of the document to identify the publication date of the document. For example, the search unit analyzes the publication year of the document to identify the publication date of the document. The search unit determines the priority of search results based on the publication date of the document. For example, the search unit prioritizes displaying the most recent document to provide the latest information. The search unit can also display older documents as needed and provide them as reference information. Furthermore, the search unit adjusts the display order of search results based on the publication date of the document. This makes it possible to provide appropriate search results based on the publication date of the document. Some or all of the above-described processing in the search unit may be performed using, for example, AI, or may be performed without using AI. For example, the search unit may have AI perform the identification of the publication date of the document and the determination of the priority of search results.

[0081] During a search, the search unit can adjust the order of search results based on the relevance of the documents. The search unit, for example, uses keyword matching technology to evaluate the relevance of the documents. For example, the search unit compares keywords in the documents with keywords in the user's search query to evaluate the relevance. The search unit can also evaluate the relevance of the documents using a co-author network. For example, the search unit analyzes the co-author network of the documents to evaluate the relevance. The search unit adjusts the order of search results based on the relevance of the documents. For example, the search unit prioritizes displaying the most relevant documents to provide useful information to the user. The search unit can also briefly display less relevant documents and provide more detailed information as needed. Furthermore, the search unit adjusts the display order of the search results based on the relevance of the documents. This allows appropriate search results to be provided based on the relevance of the documents. Some or all of the above-described processing in the search unit may be performed using, for example, AI, or may be performed without using AI. For example, the search unit can have AI perform the evaluation of the relevance of the documents and the adjustment of the order of search results.

[0082] The analysis unit can estimate the user's emotions and adjust the analysis criteria based on the estimated user's emotions. The analysis unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the analysis unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The analysis unit can also estimate the user's emotions using voice analysis technology. For example, the analysis unit analyzes the tone and speed of the user's voice to estimate the emotions. Furthermore, the analysis unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor to estimate the emotions. For example, the analysis unit estimates the emotions based on heart rate fluctuations. The analysis unit adjusts the analysis criteria based on the estimated user's emotions. For example, if the user is feeling stressed, the analysis unit relaxes the analysis criteria and provides results quickly. Furthermore, if the user is relaxed, the analysis unit can perform a detailed analysis and provide highly accurate results. Furthermore, if the user is in a hurry, the analysis unit performs an analysis that focuses on important points and provides results quickly. This makes it possible to provide appropriate analysis criteria according to the user's emotions. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may have AI perform the estimation of the user's emotions and the adjustment of the analysis criteria.

[0083] The analysis unit can improve the accuracy of the analysis by taking into account the interrelationships between documents during the analysis. The analysis unit, for example, analyzes citation relationships to evaluate the interrelationships between documents. For example, the analysis unit analyzes the citation relationships between documents and identifies related documents. The analysis unit can also evaluate the interrelationships between documents using a co-author network. For example, the analysis unit analyzes the co-author network of documents and identifies related documents. The analysis unit improves the accuracy of the analysis by taking into account the interrelationships between documents. For example, the analysis unit cross-references related documents to improve the accuracy of the analysis. The analysis unit can also complement the analysis results by taking into account the citation relationships between documents. Furthermore, the analysis unit improves the reliability of the analysis based on the interrelationships between documents. In this way, the accuracy of the analysis can be improved by taking into account the interrelationships between documents. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can cause AI to evaluate the interrelationships between documents and improve the accuracy of the analysis.

[0084] The analysis unit can perform the analysis while taking into account the attribute information of the author of the document. The analysis unit, for example, analyzes the metadata of the document to obtain the attribute information of the author of the document. For example, the analysis unit analyzes the affiliated institution and research field of the author of the document to identify the attribute information of the author. The analysis unit performs the analysis while taking into account the attribute information of the author of the document. For example, the analysis unit improves the accuracy of the analysis by taking into account the author's field of expertise. The analysis unit can also complement the analysis results by referring to the author's past research results. Furthermore, the analysis unit improves the reliability of the analysis based on the attribute information of the author. In this way, the reliability of the analysis can be improved by taking into account the attribute information of the author of the document. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can cause AI to obtain and analyze the attribute information of the author of the document.

[0085] The analysis unit can estimate the user's emotions and adjust the display order of the analysis results based on the estimated user's emotions. The analysis unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the analysis unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The analysis unit can also estimate the user's emotions using voice analysis technology. For example, the analysis unit analyzes the tone and speed of the user's voice to estimate the emotions. Furthermore, the analysis unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor to estimate the emotions. For example, the analysis unit estimates the emotions based on heart rate fluctuations. The analysis unit adjusts the display order of the analysis results based on the estimated user's emotions. For example, if the user is feeling stressed, the analysis unit prioritizes displaying the most important analysis results. Furthermore, if the user is relaxed, the analysis unit can display detailed analysis results and allow the user to select them. Furthermore, if the user is in a hurry, the analysis unit quickly displays the analysis results and emphasizes important information. This makes it possible to provide an appropriate display order of the analysis results according to the user's emotions. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may have AI execute the estimation of the user's emotions and the adjustment of the display order of the analysis results.

[0086] The analysis unit can perform the analysis taking into account the geographical distribution of the document. For example, the analysis unit analyzes metadata of the document to identify the geographical distribution of the document. For example, the analysis unit analyzes the country or region of publication of the document to identify the geographical distribution. The analysis unit performs the analysis taking into account the geographical distribution of the document. For example, the analysis unit analyzes region-specific information based on the geographical distribution of the document. The analysis unit can also cross-reference geographically related documents to improve the accuracy of the analysis. Furthermore, the analysis unit improves the reliability of the analysis results by taking into account the geographical distribution. In this way, the reliability of the analysis can be improved by taking into account the geographical distribution of the document. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can have AI perform the identification and analysis of the geographical distribution of the document.

[0087] The analysis unit can improve the accuracy of the analysis by referring to related documents of a document during analysis. The analysis unit, for example, analyzes citation relationships to identify related documents of a document. For example, the analysis unit analyzes citation relationships of documents and identifies related documents. The analysis unit can also identify related documents of a document using a co-author network. For example, the analysis unit analyzes the co-author network of a document and identifies related documents. The analysis unit improves the accuracy of the analysis by referring to related documents of a document. For example, the analysis unit mutually references related documents to improve the accuracy of the analysis. The analysis unit can also complement the analysis results by taking into account the citation relationships of related documents. Furthermore, the analysis unit improves the reliability of the analysis based on the related documents. As a result, the accuracy of the analysis can be improved by referring to related documents. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can cause AI to identify and analyze related documents of a document.

[0088] The generation unit can estimate the user's emotions and determine the priority of answers to be generated based on the estimated user's emotions. The generation unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the generation unit captures the user's facial expressions with a camera and estimates the emotions using a facial expression recognition algorithm. The generation unit can also estimate the user's emotions using voice analysis technology. For example, the generation unit analyzes the tone and speed of the user's voice to estimate the emotions. Furthermore, the generation unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor to estimate the emotions. For example, the generation unit estimates the emotions based on heart rate fluctuations. The generation unit determines the priority of answers to be generated based on the estimated user's emotions. For example, if the user is feeling stressed, the generation unit can prioritize generating important answers. Furthermore, if the user is relaxed, the generation unit can generate answers with normal priority. Furthermore, if the user is in a hurry, the generation unit can prioritize generating answers with high urgency. This makes it possible to generate answers with appropriate priority according to the user's emotions. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit may have AI perform the estimation of the user's emotions and the determination of the priority of answers.

[0089] The generation unit can improve the accuracy of generation by taking into account the interrelationships between documents during generation. The generation unit, for example, analyzes citation relationships to evaluate the interrelationships between documents. For example, the generation unit analyzes the citation relationships between documents and identifies related documents. The generation unit can also evaluate the interrelationships between documents using a co-author network. For example, the generation unit analyzes the co-author network of documents and identifies related documents. The generation unit improves the accuracy of generation by taking into account the interrelationships between documents. For example, the generation unit cross-references related documents to improve the accuracy of generation. The generation unit can also complement the generation results by taking into account the citation relationships between documents. Furthermore, the generation unit improves the reliability of generation based on the interrelationships between documents. In this way, the accuracy of generation can be improved by taking into account the interrelationships between documents. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can cause AI to evaluate the interrelationships between documents and improve the accuracy of generation.

[0090] The generation unit can generate the document taking into account the attribute information of the author of the document. The generation unit, for example, analyzes the metadata of the document to obtain the attribute information of the author of the document. For example, the generation unit analyzes the affiliated institution and research field of the author of the document to identify the author's attribute information. The generation unit generates the document taking into account the attribute information of the author of the document. For example, the generation unit improves the accuracy of the generation by taking into account the author's field of expertise. The generation unit can also complement the generation results by referring to the author's past research results. Furthermore, the generation unit improves the reliability of the generation based on the author's attribute information. In this way, the reliability of the generation can be improved by taking into account the attribute information of the author of the document. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can cause AI to obtain and generate the attribute information of the author of the document.

[0091] The generation unit can estimate the user's emotion and adjust the display method of the generated answer based on the estimated user's emotion. The generation unit, for example, uses facial expression recognition technology to estimate the user's emotion. For example, the generation unit captures the user's facial expression with a camera and estimates the emotion using a facial expression recognition algorithm. The generation unit can also estimate the user's emotion using voice analysis technology. For example, the generation unit analyzes the tone and speed of the user's voice to estimate the emotion. Furthermore, the generation unit can collect the user's biometric data (heart rate and electrodermal activity) with a sensor to estimate the emotion. For example, the generation unit estimates the emotion based on heart rate fluctuations. The generation unit adjusts the display method of the generated answer based on the estimated user's emotion. For example, if the user is feeling stressed, the generation unit provides a simple, highly visible display method. Furthermore, if the user is relaxed, the generation unit can provide a display method including detailed information. Furthermore, if the user is in a hurry, the generation unit provides a display method that focuses on the main points. This makes it possible to provide an answer in an appropriate display method depending on the user's emotion. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit may have AI execute the estimation of the user's emotion and the adjustment of the display method.

[0092] The generation unit can generate the information taking into account the geographical distribution of the documents. For example, the generation unit analyzes metadata of the documents to identify the geographical distribution of the documents. For example, the generation unit analyzes the country or region of publication of the documents to identify the geographical distribution. The generation unit generates information specific to the region based on the geographical distribution of the documents. The generation unit can also cross-reference geographically related documents to improve the accuracy of the generation. Furthermore, the generation unit improves the reliability of the generated results by taking the geographical distribution into account. In this way, the reliability of the generation can be improved by taking the geographical distribution of the documents into account. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can cause AI to identify and generate the geographical distribution of the documents.

[0093] The generation unit can improve the accuracy of generation by referring to related documents of a document during generation. The generation unit, for example, analyzes citation relationships to identify related documents of a document. For example, the generation unit analyzes citation relationships of documents and identifies related documents. The generation unit can also identify related documents of a document using a co-author network. For example, the generation unit analyzes the co-author network of a document and identifies related documents. The generation unit improves the accuracy of generation by referring to related documents of a document. For example, the generation unit mutually references related documents to improve the accuracy of generation. The generation unit can also complement the generation results by taking into account citation relationships of related documents. Furthermore, the generation unit improves the reliability of generation based on related documents. As a result, the accuracy of generation can be improved by referring to related documents. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can cause AI to identify and generate related documents of a document.

[0094] The output unit can estimate the user's emotion and adjust the output display method based on the estimated user's emotion. The output unit, for example, uses facial expression recognition technology to estimate the user's emotion. For example, the output unit captures the user's facial expression with a camera and estimates the emotion using a facial expression recognition algorithm. The output unit can also estimate the user's emotion using voice analysis technology. For example, the output unit analyzes the tone and speed of the user's voice to estimate the emotion. Furthermore, the output unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor to estimate the emotion. For example, the output unit estimates the emotion based on heart rate fluctuations. The output unit adjusts the output display method based on the estimated user's emotion. For example, if the user is feeling stressed, the output unit provides a simple, highly visible display method. Furthermore, if the user is relaxed, the output unit can provide a display method including detailed information. Furthermore, if the user is in a hurry, the output unit provides a display method that focuses on the main points. This makes it possible to provide output in an appropriate display method according to the user's emotion. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit may have AI execute the estimation of the user's emotion and the adjustment of the display method.

[0095] The output unit can select the optimal display method by referring to the user's past operation history at the time of output. The output unit, for example, stores the user's past operation history in a database and analyzes it. For example, the output unit preferentially provides a display method that the user has previously preferred. The output unit can also suggest the optimal display method based on the user's past operation history. For example, the output unit selects the optimal display method for a specific time period from the user's past operation history. This makes it possible to provide the optimal display method based on the user's past operation history. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can cause AI to analyze the user's past operation history and select the optimal display method.

[0096] The output unit can estimate the user's emotion and adjust the output operation procedure based on the estimated user's emotion. The output unit, for example, uses facial expression recognition technology to estimate the user's emotion. For example, the output unit captures the user's facial expression with a camera and estimates the emotion using a facial expression recognition algorithm. The output unit can also estimate the user's emotion using voice analysis technology. For example, the output unit analyzes the tone and speed of the user's voice to estimate the emotion. Furthermore, the output unit can collect the user's biometric data (heart rate and electrodermal activity) with a sensor to estimate the emotion. For example, the output unit estimates the emotion based on heart rate fluctuations. The output unit adjusts the output operation procedure based on the estimated user's emotion. For example, if the user is feeling stressed, the output unit simplifies the operation procedure and quickly provides results. Furthermore, if the user is relaxed, the output unit can provide detailed operation procedures to allow the user to select. Furthermore, if the user is in a hurry, the output unit quickly provides operation procedures and emphasizes important information. This makes it possible to provide output with appropriate operation procedures according to the user's emotion. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit may have AI execute the estimation of the user's emotions and the adjustment of the operation procedure.

[0097] The output unit can select the optimal display method by taking into account the user's device information when outputting. The output unit, for example, analyzes device metadata to acquire the user's device information. For example, the output unit analyzes the screen size and OS type of the user's device to identify the device information. The output unit selects the optimal display method by taking into account the user's device information. For example, if the user is using a smartphone, the output unit provides a display method tailored to the screen size. Furthermore, if the user is using a tablet, the output unit can provide a display method optimized for a large screen. Furthermore, if the user is using a smartwatch, the output unit provides a display method that is simple and highly visible. This makes it possible to provide the optimal display method based on the user's device information. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can cause AI to acquire the user's device information and select the optimal display method. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned reception unit, search unit, analysis unit, generation unit, and output 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 a question from a user. The search unit is realized by the specific processing unit 290 of the data processing device 12 and crawls a literature database to acquire relevant literature. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the content of the acquired literature. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and integrates the answer generated by the generation AI with the content of the literature to generate a correct answer. The output unit is realized by the control unit 46A of the smart device 14 and provides the generated correct answer to the user. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, search unit, analysis unit, generation unit, and output 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 a question from a user. The search unit is realized by the identification processing unit 290 of the data processing device 12 and crawls a literature database to acquire relevant literature. The analysis unit is realized by the identification processing unit 290 of the data processing device 12 and analyzes the content of the acquired literature. The generation unit is realized by the identification processing unit 290 of the data processing device 12 and integrates the answer generated by the generation AI with the content of the literature to generate a correct answer. The output unit is realized by the control unit 46A of the smart glasses 214 and provides the generated correct answer to the user. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, search unit, analysis unit, generation unit, and output 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 a question from a user. The search unit is realized by the identification processing unit 290 of the data processing device 12 and crawls a literature database to acquire relevant literature. The analysis unit is realized by the identification processing unit 290 of the data processing device 12 and analyzes the content of the acquired literature. The generation unit is realized by the identification processing unit 290 of the data processing device 12 and integrates the answer generated by the generation AI with the content of the literature to generate a correct answer. The output unit is realized by the control unit 46A of the headset-type terminal 314 and provides the generated correct answer to the user. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, search unit, analysis unit, generation unit, and output 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 search unit is realized by the specific processing unit 290 of the data processing device 12 and crawls a literature database to acquire relevant literature. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the content of the acquired literature. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and integrates the answer generated by the generation AI with the content of the literature to generate a correct answer. The output unit is realized by the control unit 46A of the robot 414 and provides the generated correct answer to the user.

[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 fact-checking system may further include a reliability evaluation unit that evaluates the reliability of a user. The reliability evaluation unit analyzes the user's past question history and the accuracy of the answers to evaluate the user's reliability. For example, the reliability evaluation unit calculates the reliability based on the number of questions the user has submitted in the past and the percentage of accurate answers to those questions. The reliability evaluation unit may also evaluate the consistency and relevance of the user's questions and adjust the reliability. Furthermore, the reliability evaluation unit may adjust the priority of answers based on the user's reliability. For example, the reliability evaluation unit may provide quick answers to users with high reliability and perform additional verification procedures for users with low reliability. This may improve the reliability and efficiency of the entire system.

[0100] The fact checking system may further include an emotion response unit that estimates the user's emotion and adjusts the way in which the answer is expressed based on the estimated emotion. The emotion response unit uses facial expression recognition technology and voice analysis technology to estimate the user's emotion. For example, the emotion response unit may capture the user's facial expression with a camera and estimate the emotion using a facial expression recognition algorithm. The emotion response unit may also estimate the emotion by analyzing the tone and speed of the user's voice using voice analysis technology. The emotion response unit adjusts the way in which the answer is expressed based on the estimated emotion. For example, if the user is feeling stressed, the emotion response unit may provide a simple and intuitive answer to reduce the user's burden. Furthermore, if the user is relaxed, the emotion response unit may provide an answer that includes detailed information. This makes it possible to provide an appropriate answer according to the user's emotion.

[0101] The fact-checking system may further include an additional information providing unit that provides related additional information based on the content of the user's question. The additional information providing unit analyzes the content of the user's question and searches for related topics and literature. For example, the additional information providing unit may provide the latest research results or news articles related to the topic the user has asked about. The additional information providing unit may also provide FAQs or guidelines related to the content of the user's question. Furthermore, the additional information providing unit may suggest related topics that the user may be interested in. This allows the user to obtain not only an answer to their question but also related additional information, thereby broadening their knowledge.

[0102] The fact checking system may further include an emotion prioritization unit that estimates the user's emotion and prioritizes answers based on the estimated emotion. The emotion prioritization unit uses facial expression recognition technology and voice analysis technology to estimate the user's emotion. For example, the emotion prioritization unit may capture the user's facial expression with a camera and estimate the emotion using an emotion recognition algorithm. Voice analysis technology may also be used to analyze the tone and speed of the user's voice to estimate the emotion. The emotion prioritization unit prioritizes answers based on the estimated emotion. For example, if the user is feeling stressed, the emotion prioritization unit may prioritize answers to important questions. On the other hand, if the user is relaxed, questions may be answered with a normal priority. This allows answers to be provided with an appropriate priority according to the user's emotion.

[0103] The fact-checking system may further include a history analysis unit that analyzes the user's past question history and selects the optimal answering method. The history analysis unit stores the user's past question history in a database and analyzes it. For example, the history analysis unit may prioritize answers to topics that the user has frequently asked about in the past. The history analysis unit may also prioritize suggesting question formats (text, voice, etc.) that the user has used in the past. Furthermore, the history analysis unit may suggest the optimal answering method for a specific time period based on the user's past question history. This allows the optimal answering method to be provided based on the user's past question history.

[0104] The fact-checking system may further include an emotion expression unit that estimates the user's emotion and adjusts the way an answer is expressed based on the estimated emotion. The emotion expression unit uses facial expression recognition technology and voice analysis technology to estimate the user's emotion. For example, the emotion expression unit may capture the user's facial expression with a camera and estimate the emotion using a facial expression recognition algorithm. The emotion expression unit may also estimate the emotion by analyzing the tone and speed of the user's voice using voice analysis technology. The emotion expression unit adjusts the way an answer is expressed based on the estimated emotion. For example, if the user is feeling stressed, the emotion expression unit may provide a simple and intuitive answer to reduce the user's burden. Alternatively, if the user is relaxed, the emotion expression unit may provide an answer that includes detailed information. This makes it possible to provide an appropriate answer according to the user's emotion.

[0105] The fact-checking system may further include a geographic information unit that prioritizes providing relevant answers based on the user's geographic location. The geographic information unit uses GPS data or an IP address to obtain the user's geographic location. For example, the geographic information unit may prioritize answers to questions related to the user's current location. The geographic information unit may also prioritize answers to questions about region-specific issues based on the user's geographic location. Furthermore, if the user is traveling, the geographic information unit may prioritize answers to questions related to the user's travel destination. This allows the system to provide appropriate answers to questions based on the user's geographic location.

[0106] The fact-checking system may further include an emotion display unit that estimates the user's emotion and adjusts the display method of the answer based on the estimated emotion. The emotion display unit uses facial expression recognition technology and voice analysis technology to estimate the user's emotion. For example, the emotion display unit may capture the user's facial expression with a camera and estimate the emotion using a facial expression recognition algorithm. Alternatively, the emotion display unit may use voice analysis technology to analyze the tone and speed of the user's voice to estimate the emotion. The emotion display unit adjusts the display method of the answer based on the estimated emotion. For example, if the user is feeling stressed, the emotion display unit may provide a simple, highly visible display method. Alternatively, if the user is relaxed, the emotion display unit may provide a display method including detailed information. This allows the answer to be provided in an appropriate display method according to the user's emotion.

[0107] The fact-checking system may further include a social media analysis unit that analyzes the user's social media activity and provides relevant answers. The social media analysis unit analyzes the user's social media posts and the number of followers to analyze the user's social media activity. For example, the social media analysis unit prioritizes answers to questions related to topics that the user is interested in on social media. The social media analysis unit may also answer questions related to topics that the user's social media followers and friends are interested in. Furthermore, the social media analysis unit answers relevant questions based on the user's recent social media posts. This allows the system to answer appropriate questions based on the user's social media activity.

[0108] The fact-checking system may further include an emotion analysis unit that estimates the user's emotion and adjusts the analysis criteria based on the estimated emotion. The emotion analysis unit uses facial expression recognition technology and voice analysis technology to estimate the user's emotion. For example, the emotion analysis unit may capture the user's facial expression with a camera and estimate the emotion using a facial expression recognition algorithm. Voice analysis technology may also be used to analyze the tone and speed of the user's voice to estimate the emotion. The emotion analysis unit adjusts the analysis criteria based on the estimated emotion. For example, if the user is feeling stressed, the emotion analysis unit may relax the analysis criteria and provide quick results. On the other hand, if the user is relaxed, the emotion analysis unit may perform a detailed analysis and provide highly accurate results. This makes it possible to provide appropriate analysis criteria according to the user's emotion.

[0109] The processing flow of the second embodiment will be briefly explained below.

[0110] Step 1: The reception unit accepts the answer generated by the generation AI. The generation AI generates an answer using natural language generation technology and machine learning algorithms. For example, the generation AI receives a question from a user as input and generates an answer based on related information. Step 2: The search unit searches a literature database using keywords related to the answer received by the reception unit. The search unit crawls reliable literature databases such as Google Scholar and PubMed to obtain relevant literature. For example, the search unit receives keywords as input and searches a literature database to obtain relevant literature. Step 3: The analysis unit analyzes the content of the literature retrieved by the search unit. The analysis unit compares the answer generated by the generation AI with the content of the literature and determines whether the generated answer is based on facts. For example, the analysis unit may use text mining technology to analyze the content of the literature and evaluate the degree of agreement with the generated answer. The analysis unit also considers indicators for evaluating the reliability and relevance of the literature. Step 4: The generation unit verifies the answer generated by the generation AI based on the content of the literature analyzed by the analysis unit and generates a correct answer. The generation unit integrates the answer generated by the generation AI with the content of the literature to generate the final answer to be provided to the user. For example, the generation unit identifies which parts of the answer generated by the generation AI match the content of the literature and corrects and completes the inconsistent parts. Step 5: The output unit provides the user with the correct answer generated by the generation unit. The output unit notifies the user of the generated correct answer. For example, the output unit displays the answer through a web application or a mobile application. The output unit selects the optimal display method taking into account the user's device information.

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

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

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

[0114] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications 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 a 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[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 audio according to instructions from the processor 46.

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

[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 carried out in a secure state.

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

[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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

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

[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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[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 audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[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. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an 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 also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0130] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications 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 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[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 audio according to instructions from the processor 46.

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

[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 carried out 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

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

[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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[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 audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[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. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an 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 also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0146] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[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 audio according to instructions from the processor 46.

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

[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 carried out in a secure state.

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

[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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

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

[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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[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 voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[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. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an 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 also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0163] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

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

[0165] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

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

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

[0168] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

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

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

[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 USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

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

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

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

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

[0178] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

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

[0180] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

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

[0182] [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 the answer generated by the generation AI; a search unit that searches a literature database using keywords related to the answer received by the reception unit; an analysis unit that analyzes the contents of the documents acquired by the search unit; A generation unit that verifies the answer generated by the generation AI based on the content of the document analyzed by the analysis unit and generates a correct answer; an output unit that provides the user with the correct answer generated by the generation unit; A system characterized by:

2. The search unit Crawl literature databases and retrieve relevant literature The system of claim 1 .

3. The analysis unit The answer generated by the AI ​​is compared with the contents of the literature to determine whether the answer is based on facts. The system of claim 1 .

4. The analysis unit Evaluate based on indicators for assessing the reliability and relevance of literature The system of claim 1 .

5. The generation unit The answer generated by the AI ​​is integrated with the contents of the literature to generate the final answer to be provided to the user. The system of claim 1 .

6. The generation unit Identify which parts of the answers generated by the AI ​​match the content of the literature, and correct or complete the inconsistent parts. The system of claim 1 .

7. The output unit Providing the generated correct answer to the user The system of claim 1 .

8. The reception unit Estimates the user's emotions and adjusts the timing of accepting answers based on the estimated user emotions. The system of claim 1 .

Images