System

Abstract

To provide a system which efficiently checks the correctness of sentences generated by generative AI or sentences created by a human being.SOLUTION: A system includes: a reception part, an analysis part, a reference part, and a provision part. The reception part inputs a sentence that a user wants to check. The analysis part analyzes a sentence inputted by the reception part and performs fact checking. The reference part refers to databases or information sources that are reliable. The provision part provides the user with a determination result obtained by the analysis part.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] With conventional technology, it was difficult to efficiently check the accuracy of sentences generated by generative AI or sentences written by humans.

[0005] The system of the embodiment aims to efficiently check the accuracy of sentences generated by generative AI or sentences written by humans. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a reference unit, and a provision unit. The reception unit inputs a sentence that a user wants to check. The analysis unit analyzes the sentence input by the reception unit and performs a fact check. The reference unit refers to a reliable database or information source. The provision unit provides the determination result obtained by the analysis unit to the user. Effect of the Invention

[0007] The system according to the embodiment can efficiently check the accuracy of sentences generated by a generative AI or written by humans. [Brief description of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The fact-checking system according to the embodiment of the present invention is a system that performs fact-checking on text generated by a generation AI. In this fact-checking system, a user inputs a text to be checked, the generation AI analyzes the text, and performs fact-checking by referring to a highly reliable database or information source. The judgment result is provided to the user, and corrections or additional information is presented as necessary. For example, when a text of a cooking recipe is input, the generation AI checks whether the steps and ingredients of the recipe are correct. The generation AI refers to a highly reliable cooking database and judges whether the contents of the recipe are accurate. The judgment result is provided to the user, and corrections or additional information is presented as necessary. In addition, text of reports and press releases issued by government agencies and companies are also checked. The generation AI refers to a highly reliable database and information source and judges whether the contents of the report or press release are correct. The judgment result is provided to the user, and corrections or additional information is presented as necessary. This service improves the reliability of text generated by the generation AI, allowing users to use the information with confidence. In addition, since it is possible to check the accuracy of text created by humans, the reliability of information dissemination by government agencies and companies is also improved. As a result, the fact-checking system improves the reliability of text generated by the generation AI, allowing users to use the information with confidence.

[0029] The fact-checking system according to the embodiment includes a reception unit, an analysis unit, a reference unit, and a provision unit. The reception unit inputs a sentence that the user wants to check. The sentence that the user wants to check includes, for example, a news article, a blog post, an academic paper, and the like, but is not limited to such examples. The reception unit inputs, for example, the sentence that the user wants to check in text format. The reception unit can also receive voice input and image input. For example, the voice input is converted into text, and the image input is converted into text using OCR technology. The analysis unit uses a generation AI to analyze the sentence input by the reception unit and perform a fact check. The analysis is performed, for example, using a natural language processing technology or a machine learning algorithm, but is not limited to such examples. For example, the generation AI uses a text generation AI (for example, LLM) to analyze the sentence and perform a fact check. The analysis unit can also analyze the content of the sentence using a multimodal generation AI. For example, the generation AI understands the context of the sentence and compares it with a reliable information source. The reference unit refers to a reliable database or information source. Reliable databases and information sources include, for example, official government databases and academic paper databases, but are not limited to such examples. The reference unit, for example, refers to an official government database to confirm whether the content of the text is correct. The reference unit can also refer to an academic paper database to confirm whether the content of the text is accurate. The provision unit provides the user with the judgment result obtained by the analysis unit. The judgment result includes, for example, a judgment of truth or falsehood and a reliability score, but is not limited to such examples. The provision unit, for example, provides the user with the judgment result in a text format. The provision unit can also provide the judgment result in a visually easy-to-understand format. For example, the judgment result is displayed as a graph or chart. This allows the fact-checking system according to the embodiment to efficiently perform fact-checking of the text that the user wants to check. A part or all of the above-mentioned processing in the provision unit may be performed, for example, using AI, or may be performed without using AI. For example, the provision unit can input the judgment result to the generation AI and cause the generation AI to execute the optimal format for providing it to the user.

[0030] The reception unit inputs a sentence that the user wants to check. Examples of sentences that the user wants to check include, but are not limited to, news articles, blog posts, and academic papers. The reception unit inputs, for example, the sentences that the user wants to check in text format. The reception unit can also accept voice input and image input. For example, the reception unit converts voice input into text and converts image input into text using OCR technology. Specifically, in the case of voice input, the speech of the user is converted into text in real time using voice recognition technology. The voice recognition technology analyzes the characteristics of the voice and generates optimal text using a language model. In the case of image input, OCR (Optical Character Recognition) technology is used to detect characters in the image and convert it into text data. The OCR technology performs noise removal and binarization as preprocessing of the image, extracts the character area, and then performs character recognition. This allows the user to input in various formats, improving convenience. Furthermore, the reception unit automatically determines the format and language of the input sentence and prepares for appropriate analysis processing. For example, if the input sentence is in English, an English natural language processing model is used, and if it is in Japanese, a Japanese model is used. This allows the reception section to handle multiple languages, and can also handle users from around the world.

[0031] The analysis unit uses the generation AI to analyze the text input by the reception unit and perform fact checking. The analysis is performed, for example, using natural language processing technology or machine learning algorithms, but is not limited to such examples. Specifically, the generation AI analyzes the text using a text generation AI (for example, LLM) and performs fact checking. The generation AI understands the context of the text and checks it against a reliable information source. For example, the generation AI breaks down each sentence of the input text and analyzes the meaning and context of each sentence. Next, the analyzed sentence is checked against a reliable database or information source to determine whether it is true or false. The generation AI uses a transformer model for context understanding and grasps the meaning of the entire text. Furthermore, the generation AI can also analyze the content of the text using a multimodal generation AI. The multimodal generation AI has the ability to comprehensively analyze not only text but also data of different formats such as images and audio. For example, it analyzes the contents of images and videos included in a news article and uses them as information to complement the credibility of the text. This allows the analysis unit to perform fact checking from a multifaceted perspective without relying on a single data format. In addition, the analysis unit uses past data and statistical information to evaluate the reliability of a text. For example, it refers to a database of past news articles and academic papers to check whether similar information exists. This enables the analysis unit to achieve more accurate fact-checking and provide users with more reliable information.

[0032] The reference unit refers to a highly reliable database or information source. Reliable databases and information sources include, but are not limited to, official government databases and academic paper databases. Specifically, the reference unit refers to an official government database to check whether the content of the text is correct. For example, based on government statistical data and official announcements, it verifies whether the content of a news article is based on facts. The reference unit can also refer to an academic paper database to check whether the content of the text is accurate. For example, for texts that include scientific assertions or research results, it refers to related academic papers to check whether the content is accurate. The reference unit issues queries to these databases to obtain the required information. The queries are automatically generated using natural language processing technology to efficiently search the databases. Furthermore, the reference unit regularly updates reliable information sources and incorporates new information, so that fact checking can always be performed based on the latest data. For example, when new government statistical data or the latest academic papers are published, the information is quickly incorporated to improve the accuracy of the fact checking. As a result, the reference unit can utilize reliable information sources to accurately verify the content of the text and provide users with reliable fact checking results.

[0033] The providing unit provides the user with the judgment result obtained by the analysis unit. The judgment result includes, for example, a judgment of truth or falsehood and a reliability score, but is not limited to such examples. Specifically, the providing unit provides the user with the judgment result in a text format. For example, the judgment result is displayed in a concise sentence so that the user can easily understand it. The providing unit can also provide the judgment result in a visually easy-to-understand format. For example, the judgment result is displayed as a graph or chart so that the user can intuitively understand it. Furthermore, the providing unit can also provide a detailed explanation of the judgment result and reference information. For example, a link to an information source or database that is the basis of the judgment result is displayed so that the user can check the detailed information. This allows the user to check the reliability of the judgment result for himself or herself. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the judgment result to the generating AI and cause the generating AI to execute the optimal format for providing it to the user. The generating AI selects the optimal display format based on the user's preferences and past usage history, and provides it to the user. This allows the providing unit to provide the judgment result to the user in the optimal format, and effectively convey the results of the fact check. Furthermore, the providing unit can collect feedback from users and continuously improve the display method and content of the judgment results. For example, when users provide comments and ratings on the judgment results, the providing unit can review the display method based on that feedback and build a more user-friendly system. This allows the providing unit to provide users with highly reliable information and effectively communicate the results of fact-checking.

[0034] The reference unit can refer to a reliable database or information source. Reliable databases and information sources include, but are not limited to, official government databases and academic paper databases. The reference unit, for example, refers to an official government database to check whether the content of the text is correct. The reference unit can also refer to an academic paper database to check whether the content of the text is accurate. This improves the accuracy of fact checking by referring to a reliable database or information source. Some or all of the above-mentioned processing in the reference unit may be performed, for example, using AI or may be performed without using AI. For example, the reference unit can input reliable databases and information sources into the generation AI and cause the generation AI to select the database or information source.

[0035] The reception unit can input a sentence that the user wants to check. The sentence that the user wants to check includes, but is not limited to, a news article, a blog post, an academic paper, etc., for example. The reception unit inputs, for example, the sentence that the user wants to check in text format. The reception unit can also accept voice input and image input. For example, the voice input is converted into text, and the image input is converted into text using OCR technology. This allows the user to efficiently input the sentence that he or she wants to check. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the sentence that the user wants to check to a generation AI and have the generation AI execute the format of the input sentence.

[0036] The analysis unit can analyze the text input by the generation AI and perform fact checking. The analysis is performed, for example, using natural language processing technology or machine learning algorithms, but is not limited to such examples. For example, the generation AI analyzes the text using a text generation AI (for example, LLM) and performs fact checking. The analysis unit can also analyze the content of the text using a multimodal generation AI. For example, the generation AI understands the context of the text and compares it with a reliable information source. As a result, the accuracy of text analysis and fact checking is improved by using the generation AI. 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 analyzes the text input to the generation AI and performs fact checking.

[0037] The providing unit can provide the judgment result to the user. The judgment result includes, for example, a judgment of true or false and a reliability score, but is not limited to such examples. The providing unit, for example, provides the judgment result to the user in a text format. The providing unit can also provide the judgment result in a visually easy-to-understand format. For example, the judgment result is displayed as a graph or chart. This allows the user to confirm whether the sentence is correct by providing the judgment result to the user. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the judgment result to a generating AI and cause the generating AI to execute an optimal format for providing to the user.

[0038] The analysis unit can check whether the steps and ingredients of a cooking recipe are accurate. For example, the analysis unit checks whether the steps and ingredients of a cooking recipe are correct. It refers to a highly reliable cooking database and determines whether the contents of the recipe are accurate. For example, the generation AI analyzes the steps and ingredients of a cooking recipe and compares them with a highly reliable cooking database. This makes it possible to confirm the accuracy of the steps and ingredients of the cooking recipe. 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 input the steps and ingredients of a cooking recipe to the generation AI and have the generation AI check the accuracy.

[0039] The analysis unit can check whether the contents of reports and press releases issued by government agencies and companies are accurate. For example, the analysis unit checks whether the contents of reports and press releases issued by government agencies and companies are correct. By referring to a highly reliable database or information source, it is determined whether the contents of the reports and press releases are accurate. For example, the generation AI analyzes the contents of reports and press releases issued by government agencies and companies and compares them with a highly reliable database. This improves the reliability of information dissemination by government agencies and companies. 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 input the contents of reports and press releases issued by government agencies and companies to the generation AI and have the generation AI check the accuracy.

[0040] The reception unit can analyze the user's past input history and select the optimal input method. For example, the reception unit automatically displays the format of the sentence that the user frequently input in the past as a candidate. The reception unit can also preferentially suggest the input method (voice, text, etc.) that the user used in the past. Furthermore, the reception unit predicts and suggests the format of the sentence to be used in a specific time period from the user's past input history. This makes it possible to provide the optimal input method based on the user's past input history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's past input history to the generation AI and cause the generation AI to select the optimal input method.

[0041] The reception unit can perform filtering based on the user's current field of interest when inputting a sentence. For example, the reception unit preferentially inputs sentences related to topics in which the user is currently interested. The reception unit can also suggest related sentences based on the user's recent search history. Furthermore, the reception unit narrows down candidates for sentences to be input based on the user's field of interest. This makes it possible to input optimal sentences based on the user's field of interest. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's field of interest to the generation AI and cause the generation AI to perform filtering.

[0042] The reception unit can preferentially input highly relevant sentences in consideration of the geographical location information of the user when inputting sentences. For example, the reception unit preferentially inputs information related to the user's current location. The reception unit can also suggest related news articles based on the user's geographical location information. Furthermore, the reception unit preferentially inputs sentences related to specific events in the area where the user is located. This allows optimal sentences to be input based on the user's geographical location information. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's geographical location information to the generation AI and cause the generation AI to select highly relevant sentences.

[0043] The reception unit can analyze the user's social media activity and input related sentences when inputting a sentence. For example, the reception unit preferentially inputs sentences related to content recently shared by the user on social media. The reception unit can also suggest sentences related to topics in which the user's social media followers are interested. Furthermore, the reception unit inputs related sentences based on the user's social media activity history. This makes it possible to input optimal sentences based on the user's social media activity. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the user's social media activity to the generation AI and cause the generation AI to select related sentences.

[0044] The analysis unit can adjust the level of detail of the analysis based on the importance of the sentence during analysis. For example, the analysis unit performs a detailed analysis on important sentences. The analysis unit can also perform a concise analysis on general sentences. Furthermore, the analysis unit performs a basic analysis on sentences with low importance. This makes it possible to provide optimal analysis results according to the importance of the sentences. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the importance of the sentence to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0045] The analysis unit can apply different analysis algorithms depending on the category of the text during analysis. For example, the analysis unit applies an analysis algorithm based on a cooking database to a cooking recipe. The analysis unit can also apply an analysis algorithm based on a news database to a news article. Furthermore, the analysis unit applies an analysis algorithm based on an academic database to a scientific paper. This makes it possible to apply an optimal analysis algorithm depending on the category of the text. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the category of the text to the generation AI and cause the generation AI to apply the analysis algorithm.

[0046] During analysis, the analysis unit can determine the priority of analysis based on the submission time of the text. For example, the analysis unit prioritizes analysis of the newest text. The analysis unit can also postpone analysis of older text. Furthermore, the analysis unit prioritizes analysis of text for which the submission time is important. This makes it possible to provide optimal analysis results according to the submission time of the text. 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 input the submission time of the text to the generation AI and have the generation AI determine the priority of analysis.

[0047] The analysis unit can adjust the order of analysis based on the relevance of the sentences during analysis. For example, the analysis unit prioritizes analysis of sentences with high relevance. The analysis unit can also postpone analysis of sentences with low relevance. Furthermore, the analysis unit appropriately analyzes sentences with medium relevance. This makes it possible to provide optimal analysis results according to the relevance of the sentences. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the relevance of the sentences to the generation AI and cause the generation AI to adjust the order of analysis.

[0048] The reference unit can select the optimal database by referring to past reference data at the time of reference. For example, the reference unit preferentially selects a database that the user has frequently referred to in the past. The reference unit can also select a highly relevant database based on the user's past reference history. Furthermore, the reference unit selects the optimal database based on the reliability of the database that the user has referred to in the past. This makes it possible to select the optimal database based on the past reference data. A part or all of the above-mentioned processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input past reference data to the generation AI and cause the generation AI to select the database.

[0049] The reference unit can apply different databases depending on the category of the text when making a reference. For example, the reference unit can refer to a cooking database for a cooking recipe. The reference unit can also refer to a news database for a news article. Furthermore, the reference unit can refer to an academic database for a scientific paper. This makes it possible to refer to the optimal database depending on the category of the text. Some or all of the above-mentioned processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input the category of the text to the generation AI and cause the generation AI to apply the database.

[0050] The reference unit can select the optimal database in consideration of the geographical distribution of the databases at the time of reference. For example, the reference unit preferentially refers to a database related to the region where the user is located. The reference unit can also select a highly relevant database based on the geographical distribution of the databases. Furthermore, the reference unit preferentially refers to a database related to the region in which the user is interested. This makes it possible to select the optimal database based on the geographical distribution of the databases. A part or all of the above-mentioned processing in the reference unit may be performed, for example, using AI, or may be performed without using AI. For example, the reference unit can input the geographical distribution of the databases to the generation AI and cause the generation AI to select the database.

[0051] The reference unit can improve the accuracy of the reference by referring to the related literature in the database at the time of reference. The reference unit improves the accuracy of the reference, for example, based on the related literature in the database. The reference unit can also check the reliability of the database by referring to the related literature. Furthermore, the reference unit selects an optimal database based on the related literature. As a result, the accuracy of the reference is improved by referring to the related literature in the database. Some or all of the above-mentioned processing in the reference unit may be performed, for example, using AI, or may be performed without using AI. For example, the reference unit can input the related literature in the database to the generation AI and cause the generation AI to improve the accuracy of the reference.

[0052] The providing unit can select the optimal providing method by referring to the user's past usage history at the time of providing. For example, the providing unit preferentially suggests a providing method that the user has used in the past. The providing unit can also select a highly relevant providing method based on the user's past usage history. Furthermore, the providing unit analyzes the user's past usage history and suggests the most efficient providing method. This makes it possible to provide the optimal providing method based on the user's past usage history. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the user's past usage history into the generating AI and cause the generating AI to select the providing method.

[0053] The providing unit can customize the means of provision based on the user's current field of interest at the time of provision. For example, the providing unit preferentially provides information related to a topic in which the user is currently interested. The providing unit can also suggest related information based on the user's recent search history. Furthermore, the providing unit narrows down candidates for information to be provided based on the user's field of interest. This makes it possible to provide an optimal means of provision based on the user's field of interest. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the user's field of interest to the generating AI and cause the generating AI to customize the means of provision.

[0054] The providing unit can select the optimal providing method in consideration of the geographical location information of the user at the time of providing. For example, the providing unit preferentially provides information related to the location where the user is currently located. The providing unit can also suggest related news articles based on the geographical location information of the user. Furthermore, the providing unit preferentially provides information related to a specific event in the area where the user is located. This makes it possible to provide the optimal providing method based on the geographical location information of the user. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the geographical location information of the user to the generating AI and cause the generating AI to select the providing method.

[0055] The providing unit can analyze the user's social media activity and suggest a means of provision at the time of provision. For example, the providing unit preferentially provides information related to the content recently shared by the user on social media. The providing unit can also suggest information related to topics in which the user's social media followers are interested. Furthermore, the providing unit provides related information based on the user's social media activity history. This makes it possible to provide an optimal means of provision based on the user's social media activity. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or may be performed without using AI. For example, the providing unit can input the user's social media activity to the generating AI and cause the generating AI to execute the suggestion of a means of provision.

[0056] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0057] When the user inputs a sentence that he or she wants to check, the reception unit can analyze the user's past input history and suggest the optimal input method. For example, input formats that the user has frequently used in the past can be automatically displayed as candidates. The reception unit can also preferentially suggest input methods (such as voice and text) that the user has used in the past. Furthermore, the reception unit predicts and suggests the format of the sentence to be used in a specific time period from the user's past input history. This makes it possible to provide the optimal input method based on the user's past input history.

[0058] When referring to reliable databases or information sources, the reference unit can preferentially refer to highly relevant databases taking into account the user's geographical location information. For example, it preferentially refers to databases related to the area where the user is currently located. It can also suggest related news articles and academic papers based on the user's geographical location information. Furthermore, it preferentially refers to databases related to areas in which the user is interested. This makes it possible to refer to the optimal database based on the user's geographical location information.

[0059] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the text. For example, for cooking recipes, an analysis algorithm based on a cooking database can be applied. For news articles, an analysis algorithm based on a news database can be applied. For scientific papers, an analysis algorithm based on an academic database can be applied. This makes it possible to apply the most suitable analysis algorithm depending on the category of the text.

[0060] During analysis, the analysis unit can determine the priority of analysis based on the submission time of the text. For example, the most recent text can be analyzed first. Also, analysis of older text can be postponed. Furthermore, analysis of text for which the submission time is important can be analyzed first. This makes it possible to provide optimal analysis results according to the submission time of the text.

[0061] The reference unit can select the optimal database by referring to past reference data at the time of reference. For example, it preferentially selects databases that the user has frequently referenced in the past. It can also select highly relevant databases based on the user's past reference history. Furthermore, it selects the optimal database based on the reliability of databases that the user has referenced in the past. This makes it possible to select the optimal database based on past reference data.

[0062] The providing unit can analyze the user's social media activity and suggest a means of provision at the time of provision. For example, the providing unit can provide information related to the content recently shared by the user on social media with priority. The providing unit can also suggest information related to topics that are of interest to the user's social media followers. Furthermore, the providing unit can provide related information based on the user's social media activity history. This makes it possible to provide the optimal means of provision based on the user's social media activity.

[0063] The process flow of the first embodiment will be briefly described below.

[0064] Step 1: The reception unit inputs the text that the user wants to check. The text that the user wants to check can be a news article, a blog post, an academic paper, etc. In addition to input in text form, the reception unit also accepts voice input and image input. Voice input is converted to text, and image input is converted to text using OCR technology. Step 2: The analysis unit uses the generation AI to analyze the text entered by the reception unit and perform fact checking. The analysis is performed using natural language processing technology and machine learning algorithms. The generation AI uses text generation AI (e.g., LLM) and multimodal generation AI to understand the context of the text and compare it with reliable sources. Step 3: The reference section refers to reliable databases and sources. Reliable databases and sources include official government databases and academic paper databases. The reference section refers to these databases to verify whether the content of the text is correct. Step 4: The providing unit provides the judgment result obtained by the analysis unit to the user. The judgment result includes a judgment of truth or falsity and a reliability score. The providing unit can provide the judgment result in a text format, or in a visually easy-to-understand format such as a graph or chart.

[0065] (Example 2) The fact-checking system according to the embodiment of the present invention is a system that performs fact-checking on text generated by a generation AI. In this fact-checking system, a user inputs a text to be checked, the generation AI analyzes the text, and performs fact-checking by referring to a highly reliable database or information source. The judgment result is provided to the user, and corrections or additional information is presented as necessary. For example, when a text of a cooking recipe is input, the generation AI checks whether the steps and ingredients of the recipe are correct. The generation AI refers to a highly reliable cooking database and judges whether the contents of the recipe are accurate. The judgment result is provided to the user, and corrections or additional information is presented as necessary. In addition, text of reports and press releases issued by government agencies and companies are also checked. The generation AI refers to a highly reliable database and information source and judges whether the contents of the report or press release are correct. The judgment result is provided to the user, and corrections or additional information is presented as necessary. This service improves the reliability of text generated by the generation AI, allowing users to use the information with confidence. In addition, since it is possible to check the accuracy of text created by humans, the reliability of information dissemination by government agencies and companies is also improved. As a result, the fact-checking system improves the reliability of text generated by the generation AI, allowing users to use the information with confidence.

[0066] The fact-checking system according to the embodiment includes a reception unit, an analysis unit, a reference unit, and a provision unit. The reception unit inputs a sentence that the user wants to check. The sentence that the user wants to check includes, for example, a news article, a blog post, an academic paper, and the like, but is not limited to such examples. The reception unit inputs, for example, the sentence that the user wants to check in text format. The reception unit can also receive voice input and image input. For example, the voice input is converted into text, and the image input is converted into text using OCR technology. The analysis unit uses a generation AI to analyze the sentence input by the reception unit and perform a fact check. The analysis is performed, for example, using a natural language processing technology or a machine learning algorithm, but is not limited to such examples. For example, the generation AI uses a text generation AI (for example, LLM) to analyze the sentence and perform a fact check. The analysis unit can also analyze the content of the sentence using a multimodal generation AI. For example, the generation AI understands the context of the sentence and compares it with a reliable information source. The reference unit refers to a reliable database or information source. Reliable databases and information sources include, for example, official government databases and academic paper databases, but are not limited to such examples. The reference unit, for example, refers to an official government database to confirm whether the content of the text is correct. The reference unit can also refer to an academic paper database to confirm whether the content of the text is accurate. The provision unit provides the user with the judgment result obtained by the analysis unit. The judgment result includes, for example, a judgment of truth or falsehood and a reliability score, but is not limited to such examples. The provision unit, for example, provides the user with the judgment result in a text format. The provision unit can also provide the judgment result in a visually easy-to-understand format. For example, the judgment result is displayed as a graph or chart. This allows the fact-checking system according to the embodiment to efficiently perform fact-checking of the text that the user wants to check. A part or all of the above-mentioned processing in the provision unit may be performed, for example, using AI, or may be performed without using AI. For example, the provision unit can input the judgment result to the generation AI and cause the generation AI to execute the optimal format for providing it to the user.

[0067] The reception unit inputs a sentence that the user wants to check. Examples of sentences that the user wants to check include, but are not limited to, news articles, blog posts, and academic papers. The reception unit inputs, for example, the sentences that the user wants to check in text format. The reception unit can also accept voice input and image input. For example, the reception unit converts voice input into text and converts image input into text using OCR technology. Specifically, in the case of voice input, the speech of the user is converted into text in real time using voice recognition technology. The voice recognition technology analyzes the characteristics of the voice and generates optimal text using a language model. In the case of image input, OCR (Optical Character Recognition) technology is used to detect characters in the image and convert it into text data. The OCR technology performs noise removal and binarization as preprocessing of the image, extracts the character area, and then performs character recognition. This allows the user to input in various formats, improving convenience. Furthermore, the reception unit automatically determines the format and language of the input sentence and prepares for appropriate analysis processing. For example, if the input sentence is in English, an English natural language processing model is used, and if it is in Japanese, a Japanese model is used. This allows the reception section to handle multiple languages, and can also handle users from around the world.

[0068] The analysis unit uses the generation AI to analyze the text input by the reception unit and perform fact checking. The analysis is performed, for example, using natural language processing technology or machine learning algorithms, but is not limited to such examples. Specifically, the generation AI analyzes the text using a text generation AI (for example, LLM) and performs fact checking. The generation AI understands the context of the text and checks it against a reliable information source. For example, the generation AI breaks down each sentence of the input text and analyzes the meaning and context of each sentence. Next, the analyzed sentence is checked against a reliable database or information source to determine whether it is true or false. The generation AI uses a transformer model for context understanding and grasps the meaning of the entire text. Furthermore, the generation AI can also analyze the content of the text using a multimodal generation AI. The multimodal generation AI has the ability to comprehensively analyze not only text but also data of different formats such as images and audio. For example, it analyzes the contents of images and videos included in a news article and uses them as information to complement the credibility of the text. This allows the analysis unit to perform fact checking from a multifaceted perspective without relying on a single data format. In addition, the analysis unit uses past data and statistical information to evaluate the reliability of a text. For example, it refers to a database of past news articles and academic papers to check whether similar information exists. This enables the analysis unit to achieve more accurate fact-checking and provide users with more reliable information.

[0069] The reference unit refers to a highly reliable database or information source. Reliable databases and information sources include, but are not limited to, official government databases and academic paper databases. Specifically, the reference unit refers to an official government database to check whether the content of the text is correct. For example, based on government statistical data and official announcements, it verifies whether the content of a news article is based on facts. The reference unit can also refer to an academic paper database to check whether the content of the text is accurate. For example, for texts that include scientific assertions or research results, it refers to related academic papers to check whether the content is accurate. The reference unit issues queries to these databases to obtain the required information. The queries are automatically generated using natural language processing technology to efficiently search the databases. Furthermore, the reference unit regularly updates reliable information sources and incorporates new information, so that fact checking can always be performed based on the latest data. For example, when new government statistical data or the latest academic papers are published, the information is quickly incorporated to improve the accuracy of the fact checking. As a result, the reference unit can utilize reliable information sources to accurately verify the content of the text and provide users with reliable fact checking results.

[0070] The providing unit provides the user with the judgment result obtained by the analysis unit. The judgment result includes, for example, a judgment of truth or falsehood and a reliability score, but is not limited to such examples. Specifically, the providing unit provides the user with the judgment result in a text format. For example, the judgment result is displayed in a concise sentence so that the user can easily understand it. The providing unit can also provide the judgment result in a visually easy-to-understand format. For example, the judgment result is displayed as a graph or chart so that the user can intuitively understand it. Furthermore, the providing unit can also provide a detailed explanation of the judgment result and reference information. For example, a link to an information source or database that is the basis of the judgment result is displayed so that the user can check the detailed information. This allows the user to check the reliability of the judgment result for himself or herself. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the judgment result to the generating AI and cause the generating AI to execute the optimal format for providing it to the user. The generating AI selects the optimal display format based on the user's preferences and past usage history, and provides it to the user. This allows the providing unit to provide the judgment result to the user in the optimal format, and effectively convey the results of the fact check. Furthermore, the providing unit can collect feedback from users and continuously improve the display method and content of the judgment results. For example, when users provide comments and ratings on the judgment results, the providing unit can review the display method based on that feedback and build a more user-friendly system. This allows the providing unit to provide users with highly reliable information and effectively communicate the results of fact-checking.

[0071] The reference unit can refer to a reliable database or information source. Reliable databases and information sources include, but are not limited to, official government databases and academic paper databases. The reference unit, for example, refers to an official government database to check whether the content of the text is correct. The reference unit can also refer to an academic paper database to check whether the content of the text is accurate. This improves the accuracy of fact checking by referring to a reliable database or information source. Some or all of the above-mentioned processing in the reference unit may be performed, for example, using AI or may be performed without using AI. For example, the reference unit can input reliable databases and information sources into the generation AI and cause the generation AI to select the database or information source.

[0072] The reception unit can input a sentence that the user wants to check. The sentence that the user wants to check includes, but is not limited to, a news article, a blog post, an academic paper, etc., for example. The reception unit inputs, for example, the sentence that the user wants to check in text format. The reception unit can also accept voice input and image input. For example, the voice input is converted into text, and the image input is converted into text using OCR technology. This allows the user to efficiently input the sentence that he or she wants to check. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the sentence that the user wants to check to a generation AI and have the generation AI execute the format of the input sentence.

[0073] The analysis unit can analyze the text input by the generation AI and perform fact checking. The analysis is performed, for example, using natural language processing technology or machine learning algorithms, but is not limited to such examples. For example, the generation AI analyzes the text using a text generation AI (for example, LLM) and performs fact checking. The analysis unit can also analyze the content of the text using a multimodal generation AI. For example, the generation AI understands the context of the text and compares it with a reliable information source. As a result, the accuracy of text analysis and fact checking is improved by using the generation AI. 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 analyzes the text input to the generation AI and performs fact checking.

[0074] The providing unit can provide the judgment result to the user. The judgment result includes, for example, a judgment of true or false and a reliability score, but is not limited to such examples. The providing unit, for example, provides the judgment result to the user in a text format. The providing unit can also provide the judgment result in a visually easy-to-understand format. For example, the judgment result is displayed as a graph or chart. This allows the user to confirm whether the sentence is correct by providing the judgment result to the user. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the judgment result to a generating AI and cause the generating AI to execute an optimal format for providing to the user.

[0075] The analysis unit can check whether the steps and ingredients of a cooking recipe are accurate. For example, the analysis unit checks whether the steps and ingredients of a cooking recipe are correct. It refers to a highly reliable cooking database and determines whether the contents of the recipe are accurate. For example, the generation AI analyzes the steps and ingredients of a cooking recipe and compares them with a highly reliable cooking database. This makes it possible to confirm the accuracy of the steps and ingredients of the cooking recipe. 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 input the steps and ingredients of a cooking recipe to the generation AI and have the generation AI check the accuracy.

[0076] The analysis unit can check whether the contents of reports and press releases issued by government agencies and companies are accurate. For example, the analysis unit checks whether the contents of reports and press releases issued by government agencies and companies are correct. By referring to a highly reliable database or information source, it is determined whether the contents of the reports and press releases are accurate. For example, the generation AI analyzes the contents of reports and press releases issued by government agencies and companies and compares them with a highly reliable database. This improves the reliability of information dissemination by government agencies and companies. 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 input the contents of reports and press releases issued by government agencies and companies to the generation AI and have the generation AI check the accuracy.

[0077] The reception unit can estimate the user's emotion and adjust the input timing of the sentence based on the estimated user's emotion. For example, when the user is stressed, the reception unit simplifies the input interface and minimizes the input procedure. In addition, when the user is relaxed, the reception unit can provide detailed input options and suggest a customizable input method. Furthermore, when the user is in a hurry, the reception unit prioritizes voice input and enables the user to input the sentence quickly. This makes it possible to provide the optimal input timing according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the input timing.

[0078] The reception unit can analyze the user's past input history and select the optimal input method. For example, the reception unit automatically displays the format of the sentence that the user frequently input in the past as a candidate. The reception unit can also preferentially suggest the input method (voice, text, etc.) that the user used in the past. Furthermore, the reception unit predicts and suggests the format of the sentence to be used in a specific time period from the user's past input history. This makes it possible to provide the optimal input method based on the user's past input history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's past input history to the generation AI and cause the generation AI to select the optimal input method.

[0079] The reception unit can perform filtering based on the user's current field of interest when inputting a sentence. For example, the reception unit preferentially inputs sentences related to topics in which the user is currently interested. The reception unit can also suggest related sentences based on the user's recent search history. Furthermore, the reception unit narrows down candidates for sentences to be input based on the user's field of interest. This makes it possible to input optimal sentences based on the user's field of interest. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's field of interest to the generation AI and cause the generation AI to perform filtering.

[0080] The reception unit can estimate the user's emotion and determine the priority of sentences to be input based on the estimated user's emotion. For example, when the user is feeling stressed, the reception unit preferentially inputs important sentences. In addition, when the user is relaxed, the reception unit can also preferentially input detailed sentences. Furthermore, when the user is in a hurry, the reception unit preferentially inputs concise sentences. This makes it possible to provide optimal sentence priorities according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority of sentences.

[0081] The reception unit can preferentially input highly relevant sentences in consideration of the geographical location information of the user when inputting sentences. For example, the reception unit preferentially inputs information related to the user's current location. The reception unit can also suggest related news articles based on the user's geographical location information. Furthermore, the reception unit preferentially inputs sentences related to specific events in the area where the user is located. This allows optimal sentences to be input based on the user's geographical location information. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's geographical location information to the generation AI and cause the generation AI to select highly relevant sentences.

[0082] The reception unit can analyze the user's social media activity and input related sentences when inputting a sentence. For example, the reception unit preferentially inputs sentences related to content recently shared by the user on social media. The reception unit can also suggest sentences related to topics in which the user's social media followers are interested. Furthermore, the reception unit inputs related sentences based on the user's social media activity history. This makes it possible to input optimal sentences based on the user's social media activity. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the user's social media activity to the generation AI and cause the generation AI to select related sentences.

[0083] The analysis unit can estimate the user's emotion and adjust the expression method of the analysis based on the estimated user's emotion. For example, the analysis unit provides a detailed analysis result when the user is relaxed. In addition, the analysis unit can also provide a concise analysis result when the user is in a hurry. Furthermore, the analysis unit provides a visually easy-to-understand analysis result when the user is stressed. This makes it possible to provide an optimal analysis result according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the expression method of the analysis.

[0084] The analysis unit can adjust the level of detail of the analysis based on the importance of the sentence during analysis. For example, the analysis unit performs a detailed analysis on important sentences. The analysis unit can also perform a concise analysis on general sentences. Furthermore, the analysis unit performs a basic analysis on sentences with low importance. This makes it possible to provide optimal analysis results according to the importance of the sentences. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the importance of the sentence to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0085] The analysis unit can apply different analysis algorithms depending on the category of the text during analysis. For example, the analysis unit applies an analysis algorithm based on a cooking database to a cooking recipe. The analysis unit can also apply an analysis algorithm based on a news database to a news article. Furthermore, the analysis unit applies an analysis algorithm based on an academic database to a scientific paper. This makes it possible to apply an optimal analysis algorithm depending on the category of the text. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the category of the text to the generation AI and cause the generation AI to apply the analysis algorithm.

[0086] The analysis unit can estimate the user's emotion and adjust the length of the analysis based on the estimated user's emotion. For example, when the user is in a hurry, the analysis unit provides a short and to the point analysis result. In addition, when the user is relaxed, the analysis unit can also provide a detailed analysis result. Furthermore, when the user is stressed, the analysis unit provides a visually easy-to-understand analysis result. This makes it possible to provide an optimal length of the analysis result according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the length of the analysis.

[0087] During analysis, the analysis unit can determine the priority of analysis based on the submission time of the text. For example, the analysis unit prioritizes analysis of the newest text. The analysis unit can also postpone analysis of older text. Furthermore, the analysis unit prioritizes analysis of text for which the submission time is important. This makes it possible to provide optimal analysis results according to the submission time of the text. 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 input the submission time of the text to the generation AI and have the generation AI determine the priority of analysis.

[0088] The analysis unit can adjust the order of analysis based on the relevance of the sentences during analysis. For example, the analysis unit prioritizes analysis of sentences with high relevance. The analysis unit can also postpone analysis of sentences with low relevance. Furthermore, the analysis unit appropriately analyzes sentences with medium relevance. This makes it possible to provide optimal analysis results according to the relevance of the sentences. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the relevance of the sentences to the generation AI and cause the generation AI to adjust the order of analysis.

[0089] The reference unit can estimate the user's emotion and select a database to be referenced based on the estimated user's emotion. For example, when the user is relaxed, the reference unit refers to a detailed database. Also, when the user is in a hurry, the reference unit can refer to a concise database. Furthermore, when the user is stressed, the reference unit refers to a visually easy-to-understand database. This allows the optimal database to be referenced according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reference unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reference unit can input the user's emotion data to the generation AI and cause the generation AI to select a database.

[0090] The reference unit can select the optimal database by referring to past reference data at the time of reference. For example, the reference unit preferentially selects a database that the user has frequently referred to in the past. The reference unit can also select a highly relevant database based on the user's past reference history. Furthermore, the reference unit selects the optimal database based on the reliability of the database that the user has referred to in the past. This makes it possible to select the optimal database based on the past reference data. A part or all of the above-mentioned processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input past reference data to the generation AI and cause the generation AI to select the database.

[0091] The reference unit can apply different databases depending on the category of the text when making a reference. For example, the reference unit can refer to a cooking database for a cooking recipe. The reference unit can also refer to a news database for a news article. Furthermore, the reference unit can refer to an academic database for a scientific paper. This makes it possible to refer to the optimal database depending on the category of the text. Some or all of the above-mentioned processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input the category of the text to the generation AI and cause the generation AI to apply the database.

[0092] The reference unit can estimate the user's emotion and determine the priority of the database to be referenced based on the estimated user's emotion. For example, when the user is relaxed, the reference unit preferentially refers to a detailed database. Also, when the user is in a hurry, the reference unit can preferentially refer to a concise database. Furthermore, when the user is stressed, the reference unit preferentially refers to a visually easy-to-understand database. This allows the optimal database to be preferentially referenced according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reference unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reference unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority of the database.

[0093] The reference unit can select the optimal database in consideration of the geographical distribution of the databases at the time of reference. For example, the reference unit preferentially refers to a database related to the region where the user is located. The reference unit can also select a highly relevant database based on the geographical distribution of the databases. Furthermore, the reference unit preferentially refers to a database related to the region in which the user is interested. This makes it possible to select the optimal database based on the geographical distribution of the databases. A part or all of the above-mentioned processing in the reference unit may be performed, for example, using AI, or may be performed without using AI. For example, the reference unit can input the geographical distribution of the databases to the generation AI and cause the generation AI to select the database.

[0094] The reference unit can improve the accuracy of the reference by referring to the related literature in the database at the time of reference. The reference unit improves the accuracy of the reference, for example, based on the related literature in the database. The reference unit can also check the reliability of the database by referring to the related literature. Furthermore, the reference unit selects an optimal database based on the related literature. As a result, the accuracy of the reference is improved by referring to the related literature in the database. Some or all of the above-mentioned processing in the reference unit may be performed, for example, using AI, or may be performed without using AI. For example, the reference unit can input the related literature in the database to the generation AI and cause the generation AI to improve the accuracy of the reference.

[0095] The providing unit can estimate the user's emotion and adjust the method of providing based on the estimated user's emotion. For example, when the user is relaxed, the providing unit proposes a detailed method of providing. Also, when the user is in a hurry, the providing unit can propose a simple method of providing. Furthermore, when the user is stressed, the providing unit proposes a visually easy-to-understand method of providing. This makes it possible to provide an optimal method of providing according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the method of providing.

[0096] The providing unit can select the optimal providing method by referring to the user's past usage history at the time of providing. For example, the providing unit preferentially suggests a providing method that the user has used in the past. The providing unit can also select a highly relevant providing method based on the user's past usage history. Furthermore, the providing unit analyzes the user's past usage history and suggests the most efficient providing method. This makes it possible to provide the optimal providing method based on the user's past usage history. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the user's past usage history into the generating AI and cause the generating AI to select the providing method.

[0097] The providing unit can customize the means of provision based on the user's current field of interest at the time of provision. For example, the providing unit preferentially provides information related to a topic in which the user is currently interested. The providing unit can also suggest related information based on the user's recent search history. Furthermore, the providing unit narrows down candidates for information to be provided based on the user's field of interest. This makes it possible to provide an optimal means of provision based on the user's field of interest. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the user's field of interest to the generating AI and cause the generating AI to customize the means of provision.

[0098] The providing unit can estimate the user's emotion and determine the priority of provision based on the estimated user's emotion. For example, when the user is relaxed, the providing unit can provide detailed information preferentially. Furthermore, when the user is in a hurry, the providing unit can also provide concise information preferentially. Furthermore, when the user is stressed, the providing unit can provide information that is visually easy to understand preferentially. This makes it possible to provide an optimal provision priority according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority of provision.

[0099] The providing unit can select the optimal providing method in consideration of the geographical location information of the user at the time of providing. For example, the providing unit preferentially provides information related to the location where the user is currently located. The providing unit can also suggest related news articles based on the geographical location information of the user. Furthermore, the providing unit preferentially provides information related to a specific event in the area where the user is located. This makes it possible to provide the optimal providing method based on the geographical location information of the user. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the geographical location information of the user to the generating AI and cause the generating AI to select the providing method.

[0100] The providing unit can analyze the user's social media activity and suggest a means of provision at the time of provision. For example, the providing unit preferentially provides information related to the content recently shared by the user on social media. The providing unit can also suggest information related to topics in which the user's social media followers are interested. Furthermore, the providing unit provides related information based on the user's social media activity history. This makes it possible to provide an optimal means of provision based on the user's social media activity. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or may be performed without using AI. For example, the providing unit can input the user's social media activity to the generating AI and cause the generating AI to execute the suggestion of a means of provision.

[0101] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0102] When the user inputs a sentence that he or she wants to check, the reception unit can analyze the user's past input history and suggest the optimal input method. For example, input formats that the user has frequently used in the past can be automatically displayed as candidates. The reception unit can also preferentially suggest input methods (such as voice and text) that the user has used in the past. Furthermore, the reception unit predicts and suggests the format of the sentence to be used in a specific time period from the user's past input history. This makes it possible to provide the optimal input method based on the user's past input history.

[0103] When referring to reliable databases or information sources, the reference unit can preferentially refer to highly relevant databases taking into account the user's geographical location information. For example, it preferentially refers to databases related to the area where the user is currently located. It can also suggest related news articles and academic papers based on the user's geographical location information. Furthermore, it preferentially refers to databases related to areas in which the user is interested. This makes it possible to refer to the optimal database based on the user's geographical location information.

[0104] The reception unit can estimate the user's emotion and determine the priority of sentences to be input based on the estimated user's emotion. For example, if the user is stressed, important sentences can be input with priority. Also, if the user is relaxed, detailed sentences can be input with priority. Furthermore, if the user is in a hurry, concise sentences can be input with priority. In this way, it is possible to provide optimal sentence priorities according to the user's emotion.

[0105] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the text. For example, for cooking recipes, an analysis algorithm based on a cooking database can be applied. For news articles, an analysis algorithm based on a news database can be applied. For scientific papers, an analysis algorithm based on an academic database can be applied. This makes it possible to apply the most suitable analysis algorithm depending on the category of the text.

[0106] The providing unit can estimate the user's emotion and adjust the method of providing based on the estimated user's emotion. For example, if the user is relaxed, a detailed method of providing can be proposed. Also, if the user is in a hurry, a simple method of providing can be proposed. Furthermore, if the user is stressed, a visually easy-to-understand method of providing can be proposed. In this way, the optimal method of providing can be provided according to the user's emotion.

[0107] During analysis, the analysis unit can determine the priority of analysis based on the submission time of the text. For example, the most recent text can be analyzed first. Also, analysis of older text can be postponed. Furthermore, analysis of text for which the submission time is important can be analyzed first. This makes it possible to provide optimal analysis results according to the submission time of the text.

[0108] The analysis unit can estimate the user's emotions and adjust the way the analysis is presented based on the estimated user's emotions. For example, if the user is relaxed, detailed analysis results can be provided. If the user is in a hurry, concise analysis results can be provided. Furthermore, if the user is stressed, analysis results that are visually easy to understand can be provided. This makes it possible to provide optimal analysis results according to the user's emotions.

[0109] The reference unit can select the optimal database by referring to past reference data at the time of reference. For example, it preferentially selects databases that the user has frequently referenced in the past. It can also select highly relevant databases based on the user's past reference history. Furthermore, it selects the optimal database based on the reliability of databases that the user has referenced in the past. This makes it possible to select the optimal database based on past reference data.

[0110] The providing unit can analyze the user's social media activity and suggest a means of provision at the time of provision. For example, the providing unit can provide information related to the content recently shared by the user on social media with priority. The providing unit can also suggest information related to topics that are of interest to the user's social media followers. Furthermore, the providing unit can provide related information based on the user's social media activity history. This makes it possible to provide the optimal means of provision based on the user's social media activity.

[0111] The providing unit can estimate the user's emotion and determine the priority of information provision based on the estimated user's emotion. For example, when the user is relaxed, detailed information can be provided preferentially. Also, when the user is in a hurry, concise information can be provided preferentially. Furthermore, when the user is stressed, information that is visually easy to understand can be provided preferentially. In this way, it is possible to provide optimal information provision priorities according to the user's emotion.

[0112] The process flow of the second embodiment will be briefly described below.

[0113] Step 1: The reception unit inputs the text that the user wants to check. The text that the user wants to check can be a news article, a blog post, an academic paper, etc. In addition to input in text form, the reception unit also accepts voice input and image input. Voice input is converted to text, and image input is converted to text using OCR technology. Step 2: The analysis unit uses the generation AI to analyze the text entered by the reception unit and perform fact checking. The analysis is performed using natural language processing technology and machine learning algorithms. The generation AI uses text generation AI (e.g., LLM) and multimodal generation AI to understand the context of the text and compare it with reliable sources. Step 3: The reference section refers to reliable databases and sources. Reliable databases and sources include official government databases and academic paper databases. The reference section refers to these databases to verify whether the content of the text is correct. Step 4: The providing unit provides the judgment result obtained by the analysis unit to the user. The judgment result includes a judgment of truth or falsity and a reliability score. The providing unit can provide the judgment result in a text format, or in a visually easy-to-understand format such as a graph or chart.

[0114] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0115] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0116] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0117] Each of the multiple elements including the above-mentioned reception unit, analysis unit, reference unit, and provision 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 reception device 38 of the smart device 14, and the user inputs a sentence to be checked. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the sentence using a generation AI to perform fact checking. The reference unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and refers to a highly reliable database or information source. The provision unit is realized, for example, by the output device 40 of the smart device 14, and provides the judgment result to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0118] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0119] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0120] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0121] 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.

[0122] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0124] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0125] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0126] 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.

[0127] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0128] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0129] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0130] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0131] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0132] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0133] Each of the multiple elements including the above-mentioned reception unit, analysis unit, reference unit, and provision 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 microphone 238 of the smart glasses 214, and the user inputs a sentence to be checked. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the sentence using a generation AI to perform fact checking. The reference unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and refers to a highly reliable database or information source. The provision unit is realized, for example, by the speaker 240 of the smart glasses 214, and provides the judgment result to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0134] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0135] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0136] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0137] 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.

[0138] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0139] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0140] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0141] 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.

[0142] 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.

[0143] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0144] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0145] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0146] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0147] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0148] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0149] Each of the multiple elements including the above-mentioned reception unit, analysis unit, reference unit, and provision 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 microphone 238 of the headset type terminal 314, and the user inputs a sentence that he or she wants to check. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the sentence using a generation AI to perform fact checking. The reference unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and refers to a highly reliable database or information source. The provision unit is realized, for example, by the display 343 of the headset type terminal 314, and provides the judgment result to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0150] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0151] 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.

[0152] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0153] 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.

[0154] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0155] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0156] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0157] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0158] 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.

[0159] 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.

[0160] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0161] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0162] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0163] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0164] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0165] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0166] Each of the multiple elements including the above-mentioned reception unit, analysis unit, reference unit, and provision 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 microphone 238 of the robot 414, and the user inputs a sentence that he or she wants to check. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the sentence using a generation AI to perform fact checking. The reference unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and refers to a highly reliable database or information source. The provision unit is realized, for example, by the speaker 240 of the robot 414, and provides the judgment result to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0167] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0168] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0169] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0170] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0171] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0172] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0173] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0174] 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.

[0175] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0176] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0177] 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.

[0178] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0179] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0180] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0181] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0182] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0183] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0184] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0185] (Appendix 1) A reception section for inputting a sentence that a user wants to check; an analysis unit that analyzes the text input by the reception unit and performs fact checking; A reference section that refers to a reliable database or source; a providing unit that provides a user with the determination result obtained by the analysis unit. system. (Appendix 2) The reference portion is Refer to a reliable database or source 2. The system of claim 1, (Appendix 3) The reception unit is The user inputs the text to be checked. 2. The system of claim 1, (Appendix 4) The analysis unit is Generative AI analyzes input text and performs fact-checking 2. The system of claim 1, (Appendix 5) The providing unit is Providing the judgment result to the user 2. The system of claim 1, (Appendix 6) The analysis unit is Check recipes for accuracy of steps and ingredients 2. The system of claim 1, (Appendix 7) The analysis unit is Check whether the contents of reports and press releases issued by government agencies and companies are accurate 2. The system of claim 1, (Appendix 8) The reception unit is Estimate the user's emotions and adjust the timing of sentence input based on the estimated user emotions. 2. The system of claim 1, (Appendix 9) The reception unit is Analyze the user's past input history and select the optimal input method 2. The system of claim 1, (Appendix 10) The reception unit is Filter text as you type based on your current interests 2. The system of claim 1, (Appendix 11) The reception unit is Estimate the user's emotions and prioritize the sentences to be input based on the estimated user emotions. 2. The system of claim 1, (Appendix 12) The reception unit is When inputting text, the system takes into account the user's geographic location information and prioritizes input of highly relevant text. 2. The system of claim 1, (Appendix 13) The reception unit is Analyzes the user's social media activity and inputs relevant text as the user types 2. The system of claim 1, (Appendix 14) The analysis unit is Infer user emotions and adjust the presentation of analytics based on the inferred user emotions 2. The system of claim 1, (Appendix 15) The analysis unit is During analysis, adjust the level of analysis detail based on the importance of the sentence 2. The system of claim 1, (Appendix 16) The analysis unit is During analysis, different analysis algorithms are applied depending on the category of the text. 2. The system of claim 1, (Appendix 17) The analysis unit is Infer user sentiment and adjust the length of the analysis based on the inferred user sentiment 2. The system of claim 1, (Appendix 18) The analysis unit is During analysis, prioritize analysis based on when the documents were submitted 2. The system of claim 1, (Appendix 19) The analysis unit is During parsing, adjust the order of parsing based on the relevance of the sentences 2. The system of claim 1, (Appendix 20) The reference portion is The user's emotions are estimated, and a database to be referenced is selected based on the estimated user's emotions. 2. The system of claim 1, (Appendix 21) The reference portion is When searching, select the most suitable database by referring to past reference data. 2. The system of claim 1, (Appendix 22) The reference portion is When referencing, different databases are applied depending on the category of the text. 2. The system of claim 1, (Appendix 23) The reference portion is The user's emotions are estimated, and the priority of the databases to be referenced is determined based on the estimated user's emotions. 2. The system of claim 1, (Appendix 24) The reference portion is When referencing, select the most appropriate database, taking into account the geographical distribution of the databases. 2. The system of claim 1, (Appendix 25) The reference portion is When referencing, we refer to related articles in the database to improve the accuracy of the reference. 2. The system of claim 1, (Appendix 26) The providing unit is Inferring user emotion and adjusting the method of serving based on the estimated user emotion 2. The system of claim 1, (Appendix 27) The providing unit is When providing the service, the optimal method of providing the service is selected by referring to the user's past usage history. 2. The system of claim 1, (Appendix 28) The providing unit is At the time of delivery, customize the delivery experience based on the user's current interests 2. The system of claim 1, (Appendix 29) The providing unit is Estimate user sentiment and determine priority of offerings based on the estimated user sentiment 2. The system of claim 1, (Appendix 30) The providing unit is When providing information, the optimal method of providing the information is selected taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 31) The providing unit is At the time of delivery, we analyze your social media activity to suggest delivery methods. 2. The system of claim 1, [Explanation of symbols]

[0186] 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 section for inputting a sentence that a user wants to check; an analysis unit that analyzes the text input by the reception unit and performs fact checking; A reference section that refers to a reliable database or source; a providing unit that provides a user with the determination result obtained by the analysis unit. system.

2. The reference portion is Refer to a reliable database or source 2. The system of claim 1 .

3. The reception unit is The user inputs the text to be checked.

2. The system of claim 1 .

4. The analysis unit is Analyze the input text using generative AI and perform fact-checking 2. The system of claim 1 .

5. The analysis unit is Check recipes for accuracy of steps and ingredients 2. The system of claim 1 .

6. The analysis unit is Check whether the contents of reports and press releases issued by government agencies and companies are accurate 2. The system of claim 1 .

7. The reception unit is Estimate the user's emotions and adjust the timing of sentence input based on the estimated user emotions.

2. The system of claim 1 .

Images