System

Abstract

An object of a system according to an embodiment is to detect an error in information provided by a user in real time and provide correct information.SOLUTION: A system according to an embodiment includes an incorrect guidance detection unit, a correct information providing unit, and a user interface unit. The incorrect guidance detection unit analyzes the information provided by the user in real time using the generated AI and detects an error. The correct information providing unit provides correct information based on the error detected by the incorrect guidance detection unit. The user interface unit presents the correct information provided by the correct information providing unit to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the problem that if information provided by a user contains an error, it is difficult to detect and correct the error in real time.

[0005] The system according to the embodiment aims to detect errors in information provided by a user in real time and provide correct information. [Means for solving the problem]

[0006] The system according to the embodiment includes a misguidance detection unit, a correct information provision unit, and a user interface unit. The misguidance detection unit uses a generation AI to analyze information provided by a user in real time and detect errors. The correct information provision unit provides correct information based on the errors detected by the misguidance detection unit. The user interface unit presents the correct information provided by the correct information provision unit to the user. [Effects of the Invention]

[0007] The system according to the embodiment can detect errors in information provided by a user in real time and provide correct information. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's 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 read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0028] (Example 1) The misguidance correction tool according to the embodiment of the present invention is a system that analyzes information provided by a user in real time, detects errors, and provides correct information. As a result, the misguidance correction tool can immediately point out errors in the information provided by the user and provide correct information, thereby improving user convenience.

[0029] The misguided navigation correction tool according to the embodiment includes a misguided navigation detection unit, a correct information provision unit, and a user interface unit. The misguided navigation detection unit uses a generation AI to analyze information provided by a user in real time and detect errors. For example, the generation AI analyzes the information provided by the user and detects factual and grammatical errors. The generation AI can also analyze the user's statements and detect logical errors. For example, if a user says, "This bus departs at 10:00," the generation AI analyzes the information and detects an error if the actual departure time is not 10:00. The correct information provision unit provides correct information based on the error detected by the misguided navigation detection unit. For example, the generation AI points out the error and provides correct information. For example, the generation AI provides correct information in the form of, "The actual departure time is 10:30." The generation AI can also provide correct information based on a reliable source of information provided by the user. The user interface unit presents the correct information provided by the correct information provision unit to the user. For example, the generation AI responds in real time to information entered by the user using a chat-style interface. The tool also supports voice input and voice output, allowing users to provide information by voice and the generation AI to respond by voice. For example, the user can provide information by voice, and the generation AI can point out errors by voice and provide correct information. As a result, the misguidance correction tool according to the embodiment can detect errors in information provided by users in real time and provide correct information, thereby improving user convenience.

[0030] The misguidance detection unit can predict and warn of specific error patterns based on the user's past speech history. For example, the generation AI analyzes the user's past speech history to identify frequently occurring error patterns. For example, if a user tends to provide incorrect information during a specific time period, a warning is displayed during that time period. The misguidance detection unit also builds an error prediction model based on the user's speech history and warns of possible errors in real time. For example, if a user frequently makes errors when using a specific phrase, the AI ​​detects that phrase and warns the user. The misguidance detection unit also builds a system in which the AI ​​learns the user's past error data and predicts future errors and warns the user in advance. For example, if a user frequently makes errors when providing specific information, a warning is displayed before the information is provided. This makes it possible to prevent errors from occurring by predicting errors based on the user's past speech history and issuing warnings in advance.

[0031] The misguidance detection unit can understand the context of a user's statements and highlight parts that are likely to be incorrect. For example, the generation AI analyzes the context of a user's statements and automatically highlights parts that are likely to be incorrect. For example, when a user provides information about a time or location, the misguidance detection unit highlights parts that are likely to be incorrect. The misguidance detection unit also builds a system that analyzes the content of a user's statements in real time and highlights parts that are likely to be incorrect. For example, when a user uses a specific keyword, the unit highlights parts that are likely to be incorrect. The misguidance detection unit also provides a function for the generation AI to understand the context of a user's statements and visually highlight parts that are likely to be incorrect. For example, the unit highlights parts that are likely to be incorrect in the information provided by the user. This makes it easier to detect and correct errors by understanding the context of a user's statements and highlighting parts that are likely to be incorrect.

[0032] The misguidance detection unit can support multiple languages ​​so that it can detect misguidance in different languages. For example, the misguidance detection unit adds a multilingual support function to the generation AI so that it can detect misguidance in different languages. For example, it detects errors in multiple languages ​​such as English, Japanese, and Chinese. The misguidance detection unit also develops a multilingual error detection algorithm and builds a system in which the generation AI detects misguidance in different languages ​​in real time. For example, when a user provides information in a different language, it performs error detection corresponding to that language. The misguidance detection unit also equips the generation AI with a multilingual error detection function and automatically detects misguidance in different languages. For example, it detects errors and issues a warning even if the information provided by the user is in a different language. This allows multilingual support so that misguidance in different languages ​​can be detected, thereby expanding the range of misguidance detection.

[0033] The misguidance detection unit can also detect misguidance from the content of images or videos. For example, the misguidance detection unit adds image recognition functionality to the generation AI to build a system that detects misguidance from the content of images and videos. For example, it detects when erroneous information is contained in images or videos provided by users. The misguidance detection unit also uses video analysis technology to develop a function for the generation AI to detect misguidance from the content of videos. For example, it analyzes the text and audio in videos to detect errors. The misguidance detection unit also analyzes the content of images and videos in real time to build a system for the generation AI to detect misguidance. For example, it issues a warning when erroneous information is contained in images or videos provided by users. This allows the detection of misguidance from the content of images and videos, thereby expanding the range of misguidance detection.

[0034] The correct information provision unit can simultaneously provide supporting data to show the reliability of correct information when providing the correct information. For example, the correct information provision unit builds a system that simultaneously provides supporting data to show the reliability of information when the generation AI provides correct information. For example, it presents the source of the information and references. Furthermore, when providing correct information, the correct information provision unit automatically collects data to show the reliability of the information and provides it to the user. For example, it obtains information from a highly reliable website or database. Furthermore, the correct information provision unit develops a system that generates supporting data to show the reliability of information in real time when the generation AI provides correct information. For example, it provides a reliability score using an algorithm that evaluates the reliability of information. This allows for the simultaneous provision of supporting data to show the reliability of information when providing correct information, thereby improving user trust.

[0035] The correct information provision unit can refer to the user's past behavioral history and provide individually optimized correct information. For example, the correct information provision unit constructs a system in which a generation AI analyzes a user's past behavioral history and provides individually optimized correct information. For example, it customizes information based on the user's past search history and browsing history. The correct information provision unit also develops an algorithm that enables the generation AI to provide individually optimized correct information based on the user's behavioral history. For example, it provides information according to the user's interests and concerns. The correct information provision unit also constructs a system in which a generation AI learns the user's past behavioral data and provides individually optimized correct information in real time. For example, it customizes information based on the user's behavioral patterns. This makes it possible to improve user convenience by providing individually optimized correct information based on the user's past behavioral history.

[0036] The correct information provision unit can simultaneously provide related additional information and reference materials when providing correct information. For example, the correct information provision unit builds a system that simultaneously provides related additional information and reference materials when the generation AI provides correct information. For example, it presents links to related articles and databases. Furthermore, when providing correct information, the correct information provision unit automatically collects related additional information and reference materials and provides them to the user. For example, it presents related research papers and statistical data. Furthermore, the correct information provision unit develops a system that generates related additional information and reference materials in real time when the generation AI provides correct information. For example, it provides a reliability score using an algorithm that evaluates the reliability of information. This allows the user's understanding to be deepened by simultaneously providing related additional information and reference materials when providing correct information.

[0037] The correct information providing unit can provide the correct information in a format that suits the user's preferences when providing the correct information. For example, the correct information providing unit builds a system in which, when the generation AI provides the correct information, the information is provided in a format that suits the user's preferences. For example, it allows the user to select between text, audio, and video. The correct information providing unit also develops an algorithm that automatically selects the format in which the generation AI provides the correct information according to the user's preferences. For example, it provides the optimal format based on the user's past selection history. The correct information providing unit also builds a system in which, when the generation AI provides the correct information, the information is generated in real time in a format that suits the user's preferences. For example, if the user wants to receive information by audio, the information is provided by audio. This makes it possible to improve user convenience by providing the correct information in a format that suits the user's preferences.

[0038] The user interface unit can analyze the user's input content in real time and instantly correct any parts that may be incorrect. For example, the user interface unit builds a system in which a generation AI analyzes the user's input content in real time and instantly corrects any parts that may be incorrect. For example, it analyzes the text entered by the user and detects and corrects errors. The user interface unit also develops an algorithm in which the generation AI analyzes the user's input content in real time and automatically corrects any parts that may be incorrect. For example, it verifies the date, time, and location information entered by the user and corrects any errors. The user interface unit also provides a function in which the generation AI analyzes the user's input content in real time and instantly corrects any parts that may be incorrect. For example, the generation AI provides feedback in real time on the information entered by the user and corrects any errors. In this way, by analyzing the user's input content in real time and instantly correcting any parts that may be incorrect, it is possible to prevent errors from occurring.

[0039] The user interface unit can visually highlight the user's input content, making it easier to detect and correct errors. For example, the user interface unit builds a system in which the generation AI visually highlights the user's input content, making it easier to detect and correct errors. For example, it highlights parts that may be erroneous with color or underline. The user interface unit also develops an algorithm in which the generation AI visually highlights the user's input content and supports the detection and correction of errors. For example, it automatically highlights parts of the information entered by the user that are likely to be erroneous. The user interface unit also provides a function in which the generation AI visually highlights the user's input content, making it easier to detect and correct errors. For example, it highlights parts that may be erroneous in the text entered by the user. This visually highlights the user's input content, making it easier to detect and correct errors, thereby improving user convenience.

[0040] The user interface unit can read out the user's input aloud and, if an error is detected, suggest corrections aloud. The user interface unit, for example, builds a system in which the generation AI reads out the user's input aloud and, if an error is detected, suggests corrections aloud. For example, the information entered by the user is confirmed aloud and, if an error is found, a correction is suggested aloud. The user interface unit also develops an algorithm in which the generation AI reads out the user's input aloud and, if an error is found, suggests corrections aloud. For example, the information entered by the user, such as date, time, and location, is confirmed aloud and, if an error is found, a correction is suggested aloud. The user interface unit also provides a function in which the generation AI reads out the user's input aloud and, if an error is found, suggests corrections aloud. For example, the information entered by the user is confirmed aloud and, if an error is found, a correction is suggested aloud. This makes it possible to improve user convenience by reading out the user's input aloud and, if an error is found, suggesting corrections aloud.

[0041] The user interface unit can convert user input content into visual notes or mind maps to assist in error detection and correction. The user interface unit, for example, builds a system in which a generation AI converts user input content into visual notes or mind maps to assist in error detection and correction. For example, the information entered by the user may be displayed in visual note or mind map format to make errors easier to detect. The user interface unit also develops an algorithm in which a generation AI converts user input content into visual notes or mind maps to assist in error detection and correction. For example, the information entered by the user may be visually organized to make errors easier to detect. The user interface unit also provides a function in which a generation AI converts user input content into visual notes or mind maps to assist in error detection and correction. For example, the information entered by the user may be displayed in visual note or mind map format to make errors easier to detect. This improves user convenience by converting user input content into visual notes or mind maps to assist in error detection and correction.

[0042] The learning function unit can learn a user's error patterns and predict future errors and provide advance warnings. For example, the learning function unit constructs a system in which a generation AI learns a user's error patterns and predicts future errors and provides advance warnings. For example, if a user frequently makes errors when using a specific phrase, the system detects that phrase and provides an advance warning. The learning function unit also constructs an error prediction model based on the user's past error data and provides real-time warnings of possible errors. For example, if a user frequently makes errors when providing specific information, the system warns the user before providing that information. The learning function unit also develops an algorithm in which the generation AI learns a user's error patterns and predicts future errors and provides advance warnings. For example, if a user tends to provide incorrect information during a certain time period, the system displays an advance warning during that time period. This allows the system to learn a user's error patterns, predict future errors, and provide advance warnings, thereby preventing errors from occurring.

[0043] The learning function unit can analyze the cause of a user's error and provide advice to resolve the cause. The learning function unit, for example, builds a system in which a generation AI analyzes the cause of a user's error and provides advice to resolve the cause. For example, the learning function unit identifies the cause of a user incorrectly providing specific information and provides advice to resolve the cause. The learning function unit also builds a system in which a generation AI analyzes the cause of an error based on user error data and provides specific advice to resolve the cause. For example, the learning function unit identifies the cause of a user incorrectly using a specific phrase and provides advice on the correct way to use that phrase. The learning function unit also builds a system in which a generation AI analyzes the cause of a user's error and provides advice to resolve the cause in real time. For example, when a user provides incorrect information, the learning function unit identifies the cause and provides advice to provide correct information. This makes it possible to analyze the cause of a user's error and provide advice to resolve the cause, thereby preventing the error from recurring.

[0044] The learning function unit can compare the error patterns of different users and identify and correct common errors. For example, the learning function unit constructs a system in which the generation AI compares the error patterns of different users and identifies and corrects common errors. For example, if multiple users make the same error, the error is identified and corrected. The learning function unit also analyzes the error data of different users and develops an algorithm to identify common error patterns. For example, if many users make errors on a particular phrase or piece of information, the pattern is identified and corrected. The learning function unit also provides a function in which the generation AI compares the error patterns of different users and identifies and corrects common errors. For example, if a user repeatedly makes the same error, the system provides advice on identifying and correcting the error. This makes it possible to reduce the occurrence of errors by comparing the error patterns of different users and identifying and correcting common errors.

[0045] The learning function unit synchronizes data between different devices when learning user errors, allowing it to provide consistent error correction across devices. For example, the learning function unit builds a system that synchronizes data between different devices when the generation AI learns user errors. For example, if a user uses multiple devices, such as a smartphone and a PC, error data is synchronized to provide consistent correction. The learning function unit also synchronizes data between different devices and develops an algorithm that allows the generation AI to learn user errors. For example, if a user makes the same error on different devices, the data is synchronized and corrected. The learning function unit also provides a function that synchronizes data between different devices when the generation AI learns user errors, allowing it to provide consistent error correction. For example, the information entered by the user on their smartphone and the information entered on their PC are synchronized and corrected. This allows data synchronization between different devices and consistent error correction, improving user convenience.

[0046] The customization function unit can learn specialized knowledge so that the generation AI can provide error detection and correction functions specialized for a specific industry or field. For example, the customization function unit builds a system that learns specialized knowledge so that the generation AI can provide error detection and correction functions specialized for a specific industry or field. For example, error detection specialized for a specific industry, such as the medical field or the legal field. The customization function unit also learns specialized knowledge and develops an algorithm that allows the generation AI to provide error detection and correction functions specialized for a specific industry or field. For example, error detection specialized for medical terminology or legal terminology. The customization function unit also provides a function for learning specialized knowledge so that the generation AI can provide error detection and correction functions specialized for a specific industry or field. For example, when a user provides information about a specific industry, error detection specialized for that industry is performed. This allows the generation AI to learn specialized knowledge and improve the accuracy of error detection and correction so that it can provide error detection and correction functions specialized for a specific industry or field.

[0047] The customization function unit enables the generation AI to customize the error detection and correction algorithms according to the individual needs of the user. For example, the customization function unit builds a system in which the generation AI customizes the error detection and correction algorithms according to the individual needs of the user. For example, if a user frequently provides specific information, error detection specialized for that information is performed. The customization function unit also provides a function in which the generation AI customizes the error detection and correction algorithms according to the user's needs. For example, when a user provides information about a specific industry or field, error detection specialized for that industry or field is performed. The customization function unit also develops a system in which the generation AI customizes the error detection and correction algorithms according to the individual needs of the user. For example, if a user frequently uses a specific phrase or information, error detection specialized for that phrase or information is performed. This allows the generation AI to customize the error detection and correction algorithms according to the individual needs of the user, thereby improving user convenience.

[0048] The customization function unit allows the generation AI to combine error detection and correction functions from different industries and fields to support new applications. For example, the customization function unit combines error detection and correction functions from different industries and fields in the generation AI to build a system that supports new applications. For example, it combines error detection functions from the medical and educational fields to support new applications. The customization function unit also develops algorithms that support new applications by combining error detection and correction functions from different industries and fields. For example, it combines error detection functions from the legal and technical fields to support new applications. The customization function unit also provides functions that support new applications by combining error detection and correction functions from different industries and fields in the generation AI. For example, if information provided by a user is related to multiple industries or fields, error detection specialized for that information can be performed. This allows the generation AI to combine error detection and correction functions from different industries and fields to support new applications, thereby expanding the scope of error detection and correction.

[0049] The customization function unit enables the generation AI to continuously improve its error detection and correction functions based on user feedback. For example, the customization function unit builds a system in which the generation AI continuously improves its error detection and correction functions based on user feedback. For example, it analyzes feedback provided by the user and improves the error detection algorithm. The customization function unit also develops an algorithm that enables the generation AI to continuously improve its error detection and correction functions based on user feedback. For example, it learns from the feedback provided by the user and improves the accuracy of error detection. The customization function unit also provides a function in which the generation AI continuously improves its error detection and correction functions based on user feedback. For example, it analyzes feedback provided by the user in real time and dynamically adjusts the error detection algorithm. This allows the generation AI to continuously improve its error detection and correction functions based on user feedback, thereby improving the accuracy of error detection and correction.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The misinformation correction tool can also be equipped with a prediction unit that predicts specific error patterns based on the user's behavioral history and issues a warning in advance. For example, if a user tends to provide incorrect information during a certain time period, a warning can be displayed during that time period. Also, if a user frequently makes errors when using a specific phrase, the tool can detect that phrase and issue a warning. Furthermore, it is possible to build a system that learns the user's past error data, predicts future errors, and issues a warning in advance. This makes it possible to prevent errors from occurring by predicting errors based on the user's past behavioral history and issuing a warning in advance.

[0052] The misguidance correction tool may further include a highlighting section that understands the context of a user's utterance and highlights parts that are likely to be incorrect. For example, when a user provides information about a time or location, the tool may highlight the information if it is likely to be incorrect. Also, when a specific keyword is used, the tool may highlight the keyword if it is likely to be incorrect. Furthermore, it is possible to provide a function that understands the context of a user's utterance and visually highlights parts that are likely to be incorrect. This makes it easier to detect and correct errors by understanding the context of a user's utterance and highlighting parts that are likely to be incorrect.

[0053] Misguided guidance correction tools can also be made multilingual so that they can detect misguided guidance in different languages. For example, by adding a multilingual function to the generation AI, it is possible to detect errors in multiple languages, such as English, Japanese, and Chinese. It is also possible to develop a multilingual error detection algorithm and build a system in which the generation AI detects misguided guidance in different languages ​​in real time. Furthermore, the generation AI can be equipped with a multilingual error detection function and automatically detect misguided guidance in different languages. By making the tool multilingual so that it can detect misguided guidance in different languages, it is possible to expand the range of misguided guidance detection.

[0054] Misguided guidance correction tools can also detect misguided guidance from the content of images or videos. For example, by adding an image recognition function to the generation AI, a system can be built to detect misguided guidance from the content of images and videos. For example, this can detect when incorrect information is contained in images or videos provided by users. It is also possible to develop a function that uses video analysis technology to enable the generation AI to detect misguided guidance from the content of videos. Furthermore, it is possible to build a system that analyzes the content of images and videos in real time and enables the generation AI to detect misguided guidance. This can expand the scope of misguided guidance detection by detecting misguided guidance from the content of images and videos.

[0055] Furthermore, when providing correct information, the misinformation correction tool can simultaneously provide supporting data to demonstrate the reliability of that information. For example, a system can be constructed in which, when the generation AI provides correct information, supporting data to demonstrate the reliability of that information is simultaneously provided. For example, the source of the information and references can be presented. In addition, when providing correct information, data to demonstrate the reliability of that information can be automatically collected and provided to the user. Furthermore, it is also possible to develop a system in which, when the generation AI provides correct information, supporting data to demonstrate the reliability of that information is generated in real time. This can improve user trust by simultaneously providing supporting data to demonstrate the reliability of that information when correct information is provided.

[0056] The misguided guidance correction tool can also refer to the user's past behavioral history to provide individually optimized, correct information. For example, a system can be built in which the generation AI analyzes the user's past behavioral history and provides individually optimized, correct information. For example, information can be customized based on the user's past search history and browsing history. It is also possible to develop an algorithm in which the generation AI provides individually optimized, correct information based on the user's behavioral history. Furthermore, it is possible to build a system in which the generation AI learns the user's past behavioral data and provides individually optimized, correct information in real time. This can improve user convenience by providing individually optimized, correct information based on the user's past behavioral history.

[0057] Misinformation correction tools can also provide related additional information and reference materials at the same time as providing correct information. For example, a system can be built in which related additional information and reference materials are provided simultaneously when the generation AI provides correct information. For example, links to related articles or databases can be presented. Furthermore, when providing correct information, the generation AI can automatically collect related additional information and reference materials and provide them to the user. Furthermore, it is possible to develop a system in which related additional information and reference materials are generated in real time when the generation AI provides correct information. This allows the user to deepen their understanding by providing related additional information and reference materials simultaneously when providing correct information.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The misguidance detection unit uses the generation AI to analyze the information provided by the user in real time and detect errors. For example, the generation AI analyzes the information provided by the user and detects factual and grammatical errors. The generation AI can also analyze the content of the user's statements and detect logical errors. For example, if the user says, "This bus departs at 10 o'clock," the generation AI analyzes the information and detects an error if the actual departure time is not 10 o'clock. Step 2: The correct information provision unit provides correct information based on the errors detected by the misguided guidance detection unit. For example, the generation AI points out the errors and provides correct information. For example, the generation AI provides correct information such as "The actual departure time is 10:30." The generation AI can also provide correct information based on reliable information sources in response to the information provided by the user. Step 3: The user interface unit presents the correct information provided by the correct information providing unit to the user. For example, using a chat-style interface, the generation AI responds in real time to the information entered by the user. It also supports voice input and voice output, so the user can provide information by voice and the generation AI can respond by voice. For example, the user can provide information by voice, and the generation AI can point out the error by voice and provide the correct information.

[0060] (Example 2) The misguidance correction tool according to the embodiment of the present invention is a system that analyzes information provided by a user in real time, detects errors, and provides correct information. As a result, the misguidance correction tool can immediately point out errors in the information provided by the user and provide correct information, thereby improving user convenience.

[0061] The misguided navigation correction tool according to the embodiment includes a misguided navigation detection unit, a correct information provision unit, and a user interface unit. The misguided navigation detection unit uses a generation AI to analyze information provided by a user in real time and detect errors. For example, the generation AI analyzes the information provided by the user and detects factual and grammatical errors. The generation AI can also analyze the user's statements and detect logical errors. For example, if a user says, "This bus departs at 10:00," the generation AI analyzes the information and detects an error if the actual departure time is not 10:00. The correct information provision unit provides correct information based on the error detected by the misguided navigation detection unit. For example, the generation AI points out the error and provides correct information. For example, the generation AI provides correct information in the form of, "The actual departure time is 10:30." The generation AI can also provide correct information based on a reliable source of information provided by the user. The user interface unit presents the correct information provided by the correct information provision unit to the user. For example, the generation AI responds in real time to information entered by the user using a chat-style interface. The tool also supports voice input and voice output, allowing users to provide information by voice and the generation AI to respond by voice. For example, the user can provide information by voice, and the generation AI can point out errors by voice and provide correct information. As a result, the misguidance correction tool according to the embodiment can detect errors in information provided by users in real time and provide correct information, thereby improving user convenience.

[0062] The misguidance detection unit can predict and warn of specific error patterns based on the user's past speech history. For example, the generation AI analyzes the user's past speech history to identify frequently occurring error patterns. For example, if a user tends to provide incorrect information during a specific time period, a warning is displayed during that time period. The misguidance detection unit also builds an error prediction model based on the user's speech history and warns of possible errors in real time. For example, if a user frequently makes errors when using a specific phrase, the AI ​​detects that phrase and warns the user. The misguidance detection unit also builds a system in which the AI ​​learns the user's past error data and predicts future errors and warns the user in advance. For example, if a user frequently makes errors when providing specific information, a warning is displayed before the information is provided. This makes it possible to prevent errors from occurring by predicting errors based on the user's past speech history and issuing warnings in advance.

[0063] The misguidance detection unit can understand the context of a user's statements and highlight parts that are likely to be incorrect. For example, the generation AI analyzes the context of a user's statements and automatically highlights parts that are likely to be incorrect. For example, when a user provides information about a time or location, the misguidance detection unit highlights parts that are likely to be incorrect. The misguidance detection unit also builds a system that analyzes the content of a user's statements in real time and highlights parts that are likely to be incorrect. For example, when a user uses a specific keyword, the unit highlights parts that are likely to be incorrect. The misguidance detection unit also provides a function for the generation AI to understand the context of a user's statements and visually highlight parts that are likely to be incorrect. For example, the unit highlights parts that are likely to be incorrect in the information provided by the user. This makes it easier to detect and correct errors by understanding the context of a user's statements and highlighting parts that are likely to be incorrect.

[0064] The misguidance detection unit can use the emotion estimation function to improve error detection accuracy when the user is feeling anxious or confused. The misguidance detection unit, for example, uses the emotion estimation function to build a system that improves error detection accuracy when the user is feeling anxious or confused. For example, it analyzes the user's facial expression and voice tone and adjusts the error detection accuracy according to the user's emotional state. The misguidance detection unit also analyzes the user's emotional state in real time to improve error detection accuracy when the user is feeling anxious or confused. For example, it more precisely detects parts that are likely to be errors when the user is feeling stressed. The misguidance detection unit also develops an algorithm based on the emotion estimation data that improves error detection accuracy when the user is feeling anxious or confused. For example, it adjusts the error detection threshold according to the user's emotional state. This improves error detection accuracy when the user is feeling anxious or confused, thereby improving error detection accuracy.

[0065] The misguidance detection unit can support multiple languages ​​so that it can detect misguidance in different languages. For example, the misguidance detection unit adds a multilingual support function to the generation AI so that it can detect misguidance in different languages. For example, it detects errors in multiple languages ​​such as English, Japanese, and Chinese. The misguidance detection unit also develops a multilingual error detection algorithm and builds a system in which the generation AI detects misguidance in different languages ​​in real time. For example, when a user provides information in a different language, it performs error detection corresponding to that language. The misguidance detection unit also equips the generation AI with a multilingual error detection function and automatically detects misguidance in different languages. For example, it detects errors and issues a warning even if the information provided by the user is in a different language. This allows multilingual support so that misguidance in different languages ​​can be detected, thereby expanding the range of misguidance detection.

[0066] The misguidance detection unit can also detect misguidance from the content of images or videos. For example, the misguidance detection unit adds image recognition functionality to the generation AI to build a system that detects misguidance from the content of images and videos. For example, it detects when erroneous information is contained in images or videos provided by users. The misguidance detection unit also uses video analysis technology to develop a function for the generation AI to detect misguidance from the content of videos. For example, it analyzes the text and audio in videos to detect errors. The misguidance detection unit also analyzes the content of images and videos in real time to build a system for the generation AI to detect misguidance. For example, it issues a warning when erroneous information is contained in images or videos provided by users. This allows the detection of misguidance from the content of images and videos, thereby expanding the range of misguidance detection.

[0067] The misguidance detection unit can use the emotion estimation function to analyze the emotional reaction of a user when they receive misguided guidance and propose measures to minimize the impact of the misguided guidance. The misguided guidance detection unit, for example, uses the emotion estimation function to build a system that analyzes the emotional reaction of a user when they receive misguided guidance in real time. For example, it analyzes the user's facial expression and voice tone to understand their emotional state. The misguided guidance detection unit also proposes measures to minimize the impact of the misguided guidance based on the user's emotional reaction data. For example, if the user is feeling stressed, it provides advice on how to relax. The misguided guidance detection unit also develops a system that analyzes the emotional reaction of a user when they receive misguided guidance based on the emotion estimation data and proposes specific measures to minimize the impact of the misguided guidance. For example, if the user is confused, it provides an easy-to-understand explanation. In this way, the user's emotional reaction when they receive misguided guidance can be analyzed and measures to minimize the impact of the misguided guidance can be proposed, thereby reducing the user's stress.

[0068] The correct information provision unit can simultaneously provide supporting data to show the reliability of correct information when providing the correct information. For example, the correct information provision unit builds a system that simultaneously provides supporting data to show the reliability of information when the generation AI provides correct information. For example, it presents the source of the information and references. Furthermore, when providing correct information, the correct information provision unit automatically collects data to show the reliability of the information and provides it to the user. For example, it obtains information from a highly reliable website or database. Furthermore, the correct information provision unit develops a system that generates supporting data to show the reliability of information in real time when the generation AI provides correct information. For example, it provides a reliability score using an algorithm that evaluates the reliability of information. This allows for the simultaneous provision of supporting data to show the reliability of information when providing correct information, thereby improving user trust.

[0069] The correct information provision unit can refer to the user's past behavioral history and provide individually optimized correct information. For example, the correct information provision unit constructs a system in which a generation AI analyzes a user's past behavioral history and provides individually optimized correct information. For example, it customizes information based on the user's past search history and browsing history. The correct information provision unit also develops an algorithm that enables the generation AI to provide individually optimized correct information based on the user's behavioral history. For example, it provides information according to the user's interests and concerns. The correct information provision unit also constructs a system in which a generation AI learns the user's past behavioral data and provides individually optimized correct information in real time. For example, it customizes information based on the user's behavioral patterns. This makes it possible to improve user convenience by providing individually optimized correct information based on the user's past behavioral history.

[0070] The correct information providing unit can use the emotion estimation function to provide correct information in a format most easily accepted by the user. The correct information providing unit, for example, uses the emotion estimation function to build a system that provides correct information in a format most easily accepted by the user. For example, it adjusts the way information is presented depending on the user's emotional state. The correct information providing unit also analyzes the user's emotional response in real time and provides correct information in a format most easily accepted by the user. For example, it provides detailed information when the user is relaxed and provides concise information when the user is feeling stressed. The correct information providing unit also develops an algorithm that provides correct information in a format most easily accepted by the user based on the emotion estimation data. For example, it adjusts the format and presentation method of the information depending on the user's emotional state. This makes it possible to promote user understanding by providing correct information in a format most easily accepted by the user.

[0071] The correct information provision unit can simultaneously provide related additional information and reference materials when providing correct information. For example, the correct information provision unit builds a system that simultaneously provides related additional information and reference materials when the generation AI provides correct information. For example, it presents links to related articles and databases. Furthermore, when providing correct information, the correct information provision unit automatically collects related additional information and reference materials and provides them to the user. For example, it presents related research papers and statistical data. Furthermore, the correct information provision unit develops a system that generates related additional information and reference materials in real time when the generation AI provides correct information. For example, it provides a reliability score using an algorithm that evaluates the reliability of information. This allows the user's understanding to be deepened by simultaneously providing related additional information and reference materials when providing correct information.

[0072] The correct information providing unit can provide the correct information in a format that suits the user's preferences when providing the correct information. For example, the correct information providing unit builds a system in which, when the generation AI provides the correct information, the information is provided in a format that suits the user's preferences. For example, it allows the user to select between text, audio, and video. The correct information providing unit also develops an algorithm that automatically selects the format in which the generation AI provides the correct information according to the user's preferences. For example, it provides the optimal format based on the user's past selection history. The correct information providing unit also builds a system in which, when the generation AI provides the correct information, the information is generated in real time in a format that suits the user's preferences. For example, if the user wants to receive information by audio, the information is provided by audio. This makes it possible to improve user convenience by providing the correct information in a format that suits the user's preferences.

[0073] The correct information provision unit can use the emotion estimation function to analyze the emotional response of the user when they receive correct information and optimize the method of providing information. The correct information provision unit, for example, uses the emotion estimation function to build a system that analyzes the emotional response of the user when they receive correct information in real time. For example, it analyzes the user's facial expression and tone of voice to understand their emotional state. The correct information provision unit also develops an algorithm that optimizes the method of providing information based on the user's emotional response data. For example, it preferentially adopts an information provision method that shows the user's positive emotions. The correct information provision unit also builds a system that analyzes the emotional response of the user when they receive correct information based on the emotion estimation data and dynamically adjusts the method of providing information. For example, it changes the method of presenting information depending on the user's emotional state. In this way, it is possible to promote user understanding by analyzing the emotional response of the user when they receive correct information and optimizing the method of providing information.

[0074] The user interface unit can analyze the user's input content in real time and instantly correct any parts that may be incorrect. For example, the user interface unit builds a system in which a generation AI analyzes the user's input content in real time and instantly corrects any parts that may be incorrect. For example, it analyzes the text entered by the user and detects and corrects errors. The user interface unit also develops an algorithm in which the generation AI analyzes the user's input content in real time and automatically corrects any parts that may be incorrect. For example, it verifies the date, time, and location information entered by the user and corrects any errors. The user interface unit also provides a function in which the generation AI analyzes the user's input content in real time and instantly corrects any parts that may be incorrect. For example, the generation AI provides feedback in real time on the information entered by the user and corrects any errors. In this way, by analyzing the user's input content in real time and instantly correcting any parts that may be incorrect, it is possible to prevent errors from occurring.

[0075] The user interface unit can visually highlight the user's input content, making it easier to detect and correct errors. For example, the user interface unit builds a system in which the generation AI visually highlights the user's input content, making it easier to detect and correct errors. For example, it highlights parts that may be erroneous with color or underline. The user interface unit also develops an algorithm in which the generation AI visually highlights the user's input content and supports the detection and correction of errors. For example, it automatically highlights parts of the information entered by the user that are likely to be erroneous. The user interface unit also provides a function in which the generation AI visually highlights the user's input content, making it easier to detect and correct errors. For example, it highlights parts that may be erroneous in the text entered by the user. This visually highlights the user's input content, making it easier to detect and correct errors, thereby improving user convenience.

[0076] The user interface unit can use the emotion estimation function to adjust the interface design and response when the user is feeling stressed. The user interface unit, for example, uses the emotion estimation function to build a system that adjusts the interface design and response when the user is feeling stressed. For example, the user interface unit analyzes the user's facial expression and voice tone and changes the interface color and layout when the user is feeling stressed. The user interface unit also analyzes the user's emotional state in real time and adjusts the interface response when the user is feeling stressed. For example, when the user is feeling stressed, the generation AI responds in a gentle tone. The user interface unit also develops a system that dynamically adjusts the interface design and response when the user is feeling stressed based on the emotion estimation data. For example, the interface design and response are customized according to the user's emotional state. As a result, the interface design and response can be adjusted when the user is feeling stressed, thereby reducing the user's stress.

[0077] The user interface unit can read out the user's input aloud and, if an error is detected, suggest corrections aloud. The user interface unit, for example, builds a system in which the generation AI reads out the user's input aloud and, if an error is detected, suggests corrections aloud. For example, the information entered by the user is confirmed aloud and, if an error is found, a correction is suggested aloud. The user interface unit also develops an algorithm in which the generation AI reads out the user's input aloud and, if an error is found, suggests corrections aloud. For example, the information entered by the user, such as date, time, and location, is confirmed aloud and, if an error is found, a correction is suggested aloud. The user interface unit also provides a function in which the generation AI reads out the user's input aloud and, if an error is found, suggests corrections aloud. For example, the information entered by the user is confirmed aloud and, if an error is found, a correction is suggested aloud. This makes it possible to improve user convenience by reading out the user's input aloud and, if an error is found, suggesting corrections aloud.

[0078] The user interface unit can convert user input content into visual notes or mind maps to assist in error detection and correction. The user interface unit, for example, builds a system in which a generation AI converts user input content into visual notes or mind maps to assist in error detection and correction. For example, the information entered by the user may be displayed in visual note or mind map format to make errors easier to detect. The user interface unit also develops an algorithm in which a generation AI converts user input content into visual notes or mind maps to assist in error detection and correction. For example, the information entered by the user may be visually organized to make errors easier to detect. The user interface unit also provides a function in which a generation AI converts user input content into visual notes or mind maps to assist in error detection and correction. For example, the information entered by the user may be displayed in visual note or mind map format to make errors easier to detect. This improves user convenience by converting user input content into visual notes or mind maps to assist in error detection and correction.

[0079] The user interface unit can use the emotion estimation function to analyze the emotional response of a user when an error is pointed out and adjust the interface response. The user interface unit, for example, uses the emotion estimation function to build a system that analyzes the emotional response of a user when an error is pointed out in real time. For example, it analyzes the user's facial expressions and voice tone to understand the user's emotional state. The user interface unit also develops an algorithm that adjusts the interface response based on the user's emotional response data. For example, if the user is feeling stressed, the generation AI responds in a gentle tone. The user interface unit also builds a system that analyzes the emotional response of a user when an error is pointed out and dynamically adjusts the interface response based on the emotion estimation data. For example, it customizes the interface response according to the user's emotional state. In this way, the user's emotional response when an error is pointed out can be analyzed and the interface response adjusted, thereby reducing user stress.

[0080] The learning function unit can learn a user's error patterns and predict future errors and provide advance warnings. For example, the learning function unit constructs a system in which a generation AI learns a user's error patterns and predicts future errors and provides advance warnings. For example, if a user frequently makes errors when using a specific phrase, the system detects that phrase and provides an advance warning. The learning function unit also constructs an error prediction model based on the user's past error data and provides real-time warnings of possible errors. For example, if a user frequently makes errors when providing specific information, the system warns the user before providing that information. The learning function unit also develops an algorithm in which the generation AI learns a user's error patterns and predicts future errors and provides advance warnings. For example, if a user tends to provide incorrect information during a certain time period, the system displays an advance warning during that time period. This allows the system to learn a user's error patterns, predict future errors, and provide advance warnings, thereby preventing errors from occurring.

[0081] The learning function unit can analyze the cause of a user's error and provide advice to resolve the cause. The learning function unit, for example, builds a system in which a generation AI analyzes the cause of a user's error and provides advice to resolve the cause. For example, the learning function unit identifies the cause of a user incorrectly providing specific information and provides advice to resolve the cause. The learning function unit also builds a system in which a generation AI analyzes the cause of an error based on user error data and provides specific advice to resolve the cause. For example, the learning function unit identifies the cause of a user incorrectly using a specific phrase and provides advice on the correct way to use that phrase. The learning function unit also builds a system in which a generation AI analyzes the cause of a user's error and provides advice to resolve the cause in real time. For example, when a user provides incorrect information, the learning function unit identifies the cause and provides advice to provide correct information. This makes it possible to analyze the cause of a user's error and provide advice to resolve the cause, thereby preventing the error from recurring.

[0082] The learning function unit uses the emotion estimation function to learn the emotional state of a user when making an error and can prevent errors before they occur. The learning function unit, for example, uses the emotion estimation function to learn the emotional state of a user when making an error and builds a system that prevents errors before they occur. For example, it analyzes the user's facial expressions and tone of voice to grasp the emotional state before making an error. The learning function unit also analyzes the user's emotional state in real time and learns the emotional patterns when making an error. For example, if a user tends to make an error when feeling stressed, it detects that emotional state and issues a warning. The learning function unit also learns the emotional state of a user when making an error based on the emotion estimation data and develops an algorithm that prevents errors before they occur. For example, it displays a warning before the user makes an error depending on the user's emotional state. In this way, the occurrence of errors can be reduced by learning the emotional state of a user when making an error and preventing errors before they occur.

[0083] The learning function unit can compare the error patterns of different users and identify and correct common errors. For example, the learning function unit constructs a system in which the generation AI compares the error patterns of different users and identifies and corrects common errors. For example, if multiple users make the same error, the error is identified and corrected. The learning function unit also analyzes the error data of different users and develops an algorithm to identify common error patterns. For example, if many users make errors on a particular phrase or piece of information, the pattern is identified and corrected. The learning function unit also provides a function in which the generation AI compares the error patterns of different users and identifies and corrects common errors. For example, if a user repeatedly makes the same error, the system provides advice on identifying and correcting the error. This makes it possible to reduce the occurrence of errors by comparing the error patterns of different users and identifying and correcting common errors.

[0084] The learning function unit synchronizes data between different devices when learning user errors, allowing it to provide consistent error correction across devices. For example, the learning function unit builds a system that synchronizes data between different devices when the generation AI learns user errors. For example, if a user uses multiple devices, such as a smartphone and a PC, error data is synchronized to provide consistent correction. The learning function unit also synchronizes data between different devices and develops an algorithm that allows the generation AI to learn user errors. For example, if a user makes the same error on different devices, the data is synchronized and corrected. The learning function unit also provides a function that synchronizes data between different devices when the generation AI learns user errors, allowing it to provide consistent error correction. For example, the information entered by the user on their smartphone and the information entered on their PC are synchronized and corrected. This allows data synchronization between different devices and consistent error correction, improving user convenience.

[0085] The learning function unit uses the emotion estimation function to analyze the emotional state of a user when making an error and can correct the error based on the emotion. The learning function unit, for example, uses the emotion estimation function to analyze the emotional state of a user when making an error and builds a system that corrects errors based on the emotion. For example, the learning function unit analyzes the user's facial expression and tone of voice and corrects errors based on the emotional state. The learning function unit also analyzes the user's emotional state in real time and learns emotional patterns when making errors. For example, if a user tends to make errors when feeling stressed, the learning function unit detects and corrects the emotional state. The learning function unit also analyzes the emotional state of a user when making an error based on the emotion estimation data and develops an algorithm that corrects errors based on the emotion. For example, the learning function unit adjusts the error correction method according to the user's emotional state. In this way, the occurrence of errors can be reduced by analyzing the emotional state of a user when making an error and correcting errors based on the emotion.

[0086] The customization function unit can learn specialized knowledge so that the generation AI can provide error detection and correction functions specialized for a specific industry or field. For example, the customization function unit builds a system that learns specialized knowledge so that the generation AI can provide error detection and correction functions specialized for a specific industry or field. For example, error detection specialized for a specific industry, such as the medical field or the legal field. The customization function unit also learns specialized knowledge and develops an algorithm that allows the generation AI to provide error detection and correction functions specialized for a specific industry or field. For example, error detection specialized for medical terminology or legal terminology. The customization function unit also provides a function for learning specialized knowledge so that the generation AI can provide error detection and correction functions specialized for a specific industry or field. For example, when a user provides information about a specific industry, error detection specialized for that industry is performed. This allows the generation AI to learn specialized knowledge and improve the accuracy of error detection and correction so that it can provide error detection and correction functions specialized for a specific industry or field.

[0087] The customization function unit enables the generation AI to customize the error detection and correction algorithms according to the individual needs of the user. For example, the customization function unit builds a system in which the generation AI customizes the error detection and correction algorithms according to the individual needs of the user. For example, if a user frequently provides specific information, error detection specialized for that information is performed. The customization function unit also provides a function in which the generation AI customizes the error detection and correction algorithms according to the user's needs. For example, when a user provides information about a specific industry or field, error detection specialized for that industry or field is performed. The customization function unit also develops a system in which the generation AI customizes the error detection and correction algorithms according to the individual needs of the user. For example, if a user frequently uses a specific phrase or information, error detection specialized for that phrase or information is performed. This allows the generation AI to customize the error detection and correction algorithms according to the individual needs of the user, thereby improving user convenience.

[0088] The customization function unit can use the emotion estimation function to perform customization according to the user's emotional state and provide optimal error correction. The customization function unit, for example, uses the emotion estimation function to perform customization according to the user's emotional state and build a system that provides optimal error correction. For example, the customization function unit analyzes the user's facial expression and voice tone and performs error correction according to the emotional state. The customization function unit also analyzes the user's emotional state in real time and develops an algorithm that performs emotion-based error correction. For example, if the user is feeling stressed, the customization function unit provides advice on how to relax. The customization function unit also provides a function that performs customization according to the user's emotional state based on the emotion estimation data and provides optimal error correction. For example, the error correction method is adjusted according to the user's emotional state. As a result, the emotion estimation function can be used to perform customization according to the user's emotional state and provide optimal error correction, thereby improving user convenience.

[0089] The customization function unit allows the generation AI to combine error detection and correction functions from different industries and fields to support new applications. For example, the customization function unit combines error detection and correction functions from different industries and fields in the generation AI to build a system that supports new applications. For example, it combines error detection functions from the medical and educational fields to support new applications. The customization function unit also develops algorithms that support new applications by combining error detection and correction functions from different industries and fields. For example, it combines error detection functions from the legal and technical fields to support new applications. The customization function unit also provides functions that support new applications by combining error detection and correction functions from different industries and fields in the generation AI. For example, if information provided by a user is related to multiple industries or fields, error detection specialized for that information can be performed. This allows the generation AI to combine error detection and correction functions from different industries and fields to support new applications, thereby expanding the scope of error detection and correction.

[0090] The customization function unit enables the generation AI to continuously improve its error detection and correction functions based on user feedback. For example, the customization function unit builds a system in which the generation AI continuously improves its error detection and correction functions based on user feedback. For example, it analyzes feedback provided by the user and improves the error detection algorithm. The customization function unit also develops an algorithm that enables the generation AI to continuously improve its error detection and correction functions based on user feedback. For example, it learns from the feedback provided by the user and improves the accuracy of error detection. The customization function unit also provides a function in which the generation AI continuously improves its error detection and correction functions based on user feedback. For example, it analyzes feedback provided by the user in real time and dynamically adjusts the error detection algorithm. This allows the generation AI to continuously improve its error detection and correction functions based on user feedback, thereby improving the accuracy of error detection and correction.

[0091] The customization function unit can use the emotion estimation function to perform customization based on the user's emotional state and improve the user experience. The customization function unit, for example, uses the emotion estimation function to perform customization based on the user's emotional state and build a system that improves the user experience. For example, the customization function unit analyzes the user's facial expression and voice tone and adjusts the interface according to the emotional state. The customization function unit also analyzes the user's emotional state in real time and develops an algorithm that performs emotion-based customization. For example, if the user is feeling stressed, the customization function unit provides advice on how to relax. The customization function unit also provides a function that performs customization based on the user's emotional state based on the emotion estimation data and improves the user experience. For example, the design and response of the interface are adjusted according to the user's emotional state. As a result, the emotion estimation function can be used to perform customization based on the user's emotional state and improve the user experience, thereby improving user convenience.

[0092] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0093] The misinformation correction tool can also be equipped with a prediction unit that predicts specific error patterns based on the user's behavioral history and issues a warning in advance. For example, if a user tends to provide incorrect information during a certain time period, a warning can be displayed during that time period. Also, if a user frequently makes errors when using a specific phrase, the tool can detect that phrase and issue a warning. Furthermore, it is possible to build a system that learns the user's past error data, predicts future errors, and issues a warning in advance. This makes it possible to prevent errors from occurring by predicting errors based on the user's past behavioral history and issuing a warning in advance.

[0094] The misguidance correction tool may further include a highlighting section that understands the context of a user's utterance and highlights parts that are likely to be incorrect. For example, when a user provides information about a time or location, the tool may highlight the information if it is likely to be incorrect. Also, when a specific keyword is used, the tool may highlight the keyword if it is likely to be incorrect. Furthermore, it is possible to provide a function that understands the context of a user's utterance and visually highlights parts that are likely to be incorrect. This makes it easier to detect and correct errors by understanding the context of a user's utterance and highlighting parts that are likely to be incorrect.

[0095] The misguidance correction tool can further use an emotion estimation function to improve error detection accuracy when the user is feeling anxious or confused. For example, the tool can analyze the user's facial expression and tone of voice to adjust the error detection accuracy according to the user's emotional state. It can also analyze the user's emotional state in real time to improve error detection accuracy when the user is feeling anxious or confused. Furthermore, it is possible to develop an algorithm based on the emotion estimation data to improve error detection accuracy when the user is feeling anxious or confused. This can improve error detection accuracy by improving error detection accuracy when the user is feeling anxious or confused.

[0096] Misguided guidance correction tools can also be made multilingual so that they can detect misguided guidance in different languages. For example, by adding a multilingual function to the generation AI, it is possible to detect errors in multiple languages, such as English, Japanese, and Chinese. It is also possible to develop a multilingual error detection algorithm and build a system in which the generation AI detects misguided guidance in different languages ​​in real time. Furthermore, the generation AI can be equipped with a multilingual error detection function and automatically detect misguided guidance in different languages. By making the tool multilingual so that it can detect misguided guidance in different languages, it is possible to expand the range of misguided guidance detection.

[0097] Misguided guidance correction tools can also detect misguided guidance from the content of images or videos. For example, by adding an image recognition function to the generation AI, a system can be built to detect misguided guidance from the content of images and videos. For example, this can detect when incorrect information is contained in images or videos provided by users. It is also possible to develop a function that uses video analysis technology to enable the generation AI to detect misguided guidance from the content of videos. Furthermore, it is possible to build a system that analyzes the content of images and videos in real time and enables the generation AI to detect misguided guidance. This can expand the scope of misguided guidance detection by detecting misguided guidance from the content of images and videos.

[0098] The misguided navigation correction tool can further use its emotion estimation function to analyze the user's emotional reaction when receiving misguided navigation and propose measures to minimize the impact of the misguided navigation. For example, it can analyze the user's facial expression and tone of voice to understand their emotional state. It can also propose measures to minimize the impact of misguided navigation based on the user's emotional reaction data. Furthermore, it is possible to develop a system that analyzes the user's emotional reaction when receiving misguided navigation and proposes specific measures to minimize the impact of misguided navigation based on the emotion estimation data. This makes it possible to reduce the user's stress by analyzing the user's emotional reaction when receiving misguided navigation and proposing measures to minimize the impact of misguided navigation.

[0099] Furthermore, when providing correct information, the misinformation correction tool can simultaneously provide supporting data to demonstrate the reliability of that information. For example, a system can be constructed in which, when the generation AI provides correct information, supporting data to demonstrate the reliability of that information is simultaneously provided. For example, the source of the information and references can be presented. In addition, when providing correct information, data to demonstrate the reliability of that information can be automatically collected and provided to the user. Furthermore, it is also possible to develop a system in which, when the generation AI provides correct information, supporting data to demonstrate the reliability of that information is generated in real time. This can improve user trust by simultaneously providing supporting data to demonstrate the reliability of that information when correct information is provided.

[0100] The misguided guidance correction tool can also refer to the user's past behavioral history to provide individually optimized, correct information. For example, a system can be built in which the generation AI analyzes the user's past behavioral history and provides individually optimized, correct information. For example, information can be customized based on the user's past search history and browsing history. It is also possible to develop an algorithm in which the generation AI provides individually optimized, correct information based on the user's behavioral history. Furthermore, it is possible to build a system in which the generation AI learns the user's past behavioral data and provides individually optimized, correct information in real time. This can improve user convenience by providing individually optimized, correct information based on the user's past behavioral history.

[0101] The misinformation correction tool can also use emotion estimation to provide correct information in the most acceptable format for the user. For example, it can adjust the way information is presented depending on the user's emotional state. It can also analyze the user's emotional response in real time and provide correct information in the most acceptable format. Furthermore, it is possible to develop an algorithm based on emotion estimation data to provide correct information in the most acceptable format for the user. This can promote user understanding by providing correct information in the most acceptable format for the user.

[0102] Misinformation correction tools can also provide related additional information and reference materials at the same time as providing correct information. For example, a system can be built in which related additional information and reference materials are provided simultaneously when the generation AI provides correct information. For example, links to related articles or databases can be presented. Furthermore, when providing correct information, the generation AI can automatically collect related additional information and reference materials and provide them to the user. Furthermore, it is possible to develop a system in which related additional information and reference materials are generated in real time when the generation AI provides correct information. This allows the user to deepen their understanding by providing related additional information and reference materials simultaneously when providing correct information.

[0103] The misinformation correction tool can also use its emotion estimation function to analyze the user's emotional response when they receive correct information and optimize the method of providing information. For example, it can analyze the user's facial expression and tone of voice to understand their emotional state. It can also develop an algorithm that optimizes the method of providing information based on the user's emotional response data. Furthermore, it can also build a system that analyzes the user's emotional response when they receive correct information and dynamically adjusts the method of providing information based on the emotion estimation data. This can promote user understanding by analyzing the user's emotional response when they receive correct information and optimizing the method of providing information.

[0104] The processing flow of the second embodiment will be briefly explained below.

[0105] Step 1: The misguidance detection unit uses the generation AI to analyze the information provided by the user in real time and detect errors. For example, the generation AI analyzes the information provided by the user and detects factual and grammatical errors. The generation AI can also analyze the content of the user's statements and detect logical errors. For example, if the user says, "This bus departs at 10 o'clock," the generation AI analyzes the information and detects an error if the actual departure time is not 10 o'clock. Step 2: The correct information provision unit provides correct information based on the errors detected by the misguided guidance detection unit. For example, the generation AI points out the errors and provides correct information. For example, the generation AI provides correct information such as "The actual departure time is 10:30." The generation AI can also provide correct information based on reliable information sources in response to the information provided by the user. Step 3: The user interface unit presents the correct information provided by the correct information providing unit to the user. For example, using a chat-style interface, the generation AI responds in real time to the information entered by the user. It also supports voice input and voice output, so the user can provide information by voice and the generation AI can respond by voice. For example, the user can provide information by voice, and the generation AI can point out the error by voice and provide the correct information.

[0106] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0107] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0108] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0109] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0110] 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.

[0111] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0112] 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.

[0113] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0114] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0115] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0116] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0117] 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.

[0118] 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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0119] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0120] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0121] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0122] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0123] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0124] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0125] 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.

[0126] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0127] 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.

[0128] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0129] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0130] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0131] 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.

[0132] 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.

[0133] 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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0134] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0135] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0136] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0137] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0138] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0139] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0140] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0141] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0142] 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.

[0143] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0145] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0146] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0147] 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.

[0148] 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.

[0149] 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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0150] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0151] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0152] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0153] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0154] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0155] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0156] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0157] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0158] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0159] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0160] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0161] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0162] 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.

[0163] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0164] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0165] 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.

[0166] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0167] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0168] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0169] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0170] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0171] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0172] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0173] 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 misguidance detection unit that uses generation AI to analyze information provided by users in real time and detect errors; a correct information providing unit that provides correct information based on the error detected by the incorrect guidance detecting unit; a user interface unit that presents the correct information provided by the correct information providing unit to the user. A system characterized by:

2. The misguidance detection unit Support multiple languages ​​so that misinformation in different languages ​​can be detected.

2. The system of claim 1.

3. The correct information providing unit When providing the correct information, provide evidence data to demonstrate the reliability of the information at the same time.

2. The system of claim 1.

4. The user interface unit Analyzing the user's input in real time and immediately correcting any possible errors.

2. The system of claim 1.

5. The learning function section is Learning the emotional state of the user when making the error and preventing the error from occurring 2. The system of claim 1.

6. The customization function section is Customize the error correction according to the emotional state of the user and provide the most appropriate correction.

2. The system of claim 1.

Images