System

Abstract

An object of a system according to an embodiment is to efficiently answer a child's homework assignment and provide appropriate advice.SOLUTION: A system includes a text analysis unit, a correct answer determination unit, an advice generation unit, and a provision unit. A text analysis part photographs a print and fetches a text. The correct answer determination unit determines a correct answer or an incorrect answer based on the text captured by the text analysis unit. The advice generation unit generates advice for the incorrect portion determined by the correct answer determination unit. The providing unit provides the advice generated by the advice generation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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 of making it difficult to efficiently check children's homework answers and provide appropriate advice.

[0005] The system according to the embodiment aims to efficiently check children's homework answers and provide appropriate advice. [Means for solving the problem]

[0006] The system according to the embodiment includes a text analysis unit, a correct answer determination unit, an advice generation unit, and a providing unit. The text analysis unit photographs a print and captures the text. The correct answer determination unit determines whether the answer is correct or incorrect based on the text captured by the text analysis unit. The advice generation unit generates advice for the incorrect answers determined by the correct answer determination unit. The providing unit provides the advice generated by the advice generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently check children's homework answers and provide appropriate advice. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention is an application that uses a generative AI to check children's homework answers. The system allows users to take a photo of a printout provided by a school or cram school using a smartphone or tablet, convert it into text using OCR technology, and automatically analyze it. The generative AI distinguishes between correct and incorrect answers, and for incorrect answers, analyzes the answers and provides advice on how to approach the problem. This advice incorporates a coaching element rather than simply providing the answer. Furthermore, by accumulating various correct and incorrect answer data for each target user's age group, the system predicts trends, such as areas where mistakes are likely to be made, and provides optimal advice. This allows the system to develop children's ability to think independently and solve problems. It also makes it easier for parents and teachers to understand their children's learning progress, enabling more effective support.

[0029] A learning assistance system according to an embodiment includes a text analysis unit, a correct answer determination unit, an advice generation unit, and a providing unit. The text analysis unit captures a print photographed by a user as text using OCR technology. For example, the text analysis unit converts an image of a print photographed with a smartphone or tablet into text data using OCR technology. The text analysis unit can also apply an algorithm for recognizing handwritten characters with high accuracy. The correct answer determination unit determines whether an answer is correct or incorrect based on the captured text. For example, the correct answer determination unit analyzes a question and an answer to determine whether the answer is correct or incorrect. The correct answer determination unit can also adjust the strictness of the determination depending on the difficulty of the question. The advice generation unit generates advice for an incorrect answer. For example, the advice generation unit analyzes a calculation process where an error occurred and identifies the part where the error occurred. The advice generation unit can also improve the accuracy of the advice by referring to the user's past answer history. The providing unit provides the generated advice. For example, the providing unit provides the advice to the user as a text message or a voice message. The providing unit can also estimate the user's emotions and adjust the method of providing advice based on the estimated emotions. This allows the learning support system according to the embodiment to analyze the text of a printout photographed by the user, determine whether the answer is correct or incorrect, and provide advice for the incorrect part.

[0030] The text analysis unit can capture text by photographing a print using OCR technology. For example, the text analysis unit converts an image of a print taken with a smartphone or tablet into text data using OCR technology. The text analysis unit can also apply algorithms to recognize handwritten characters with high accuracy. For example, the text analysis unit can improve recognition accuracy by using an AI model that has learned the characteristics of handwritten characters. The text analysis unit also has a function to automatically correct light reflections and shadows. For example, if there is strong light reflection when photographing, it can automatically apply a filter to reduce reflections. This allows the text on the print to be captured accurately using OCR technology.

[0031] The correct answer determination unit can determine whether an answer is correct or incorrect based on the imported text. For example, the correct answer determination unit analyzes the question and answer to determine whether the answer is correct or incorrect. For example, the correct answer determination unit compares the answer with a database of correct answers for the question to determine whether the answer is correct or incorrect. The correct answer determination unit can also adjust the strictness of the determination depending on the difficulty of the question. For example, strict criteria can be applied to easy questions, and lenient criteria can be applied to difficult questions. The correct answer determination unit can also improve the accuracy of the determination by referring to the user's past answer history. For example, the determination criteria can be adjusted based on questions the user got wrong in the past. This makes it possible to accurately determine whether the answer is correct or incorrect based on the imported text.

[0032] The advice generation unit can generate advice for incorrect answers. For example, the advice generation unit analyzes the incorrect calculation process and identifies the part where the mistake occurred. For example, the advice generation unit analyzes the incorrect calculation process step by step and presents the correct calculation method. The advice generation unit can also improve the accuracy of the advice by referring to the user's past answer history. For example, the advice content can be adjusted based on problems the user has gotten wrong in the past. The advice generation unit can also apply different advice algorithms depending on the problem category. For example, an advice algorithm that emphasizes the calculation process can be applied to arithmetic problems, and an advice algorithm that takes context into account can be applied to Japanese language problems. This makes it possible to generate appropriate advice for incorrect answers.

[0033] The providing unit can provide the generated advice. For example, the providing unit provides the advice to the user as a text message or a voice message. For example, the providing unit displays the generated advice on a smartphone or tablet screen. The providing unit can also estimate the user's emotions and adjust the way the advice is provided based on the estimated emotions. For example, if the user is feeling stressed, the providing unit can provide advice in gentle language, and if the user is relaxed, the providing unit can provide advice including detailed explanations. The providing unit can also select the optimal timing for providing the advice by referring to the user's learning history. For example, the providing unit can provide advice immediately after the user solves a problem that they previously got wrong. In this way, the generated advice can be provided to the user.

[0034] The advice generation unit accumulates multiple correct and incorrect answer data for each age group of target users, predicts trends in areas where mistakes are likely to be made, and provides optimal advice. The advice generation unit, for example, collects various correct and incorrect answer data for each age group of target users and analyzes trends in areas where mistakes are likely to be made. For example, in the case of elementary school arithmetic problems, it can be determined that mistakes are likely to be made with specific calculation methods or problem formats. The advice generation unit can provide optimal advice to users based on this data. The advice generation unit can also accumulate data by age group and analyze long-term trends. For example, the advice generation unit can analyze data by age group over time to identify changes in areas where mistakes are likely to be made. This allows the advice generation unit to accumulate data by age group, predict areas where mistakes are likely to be made, and provide optimal advice.

[0035] The text analysis unit can add a function to automatically correct light reflections and shadows when photographing a print. For example, if there is strong light reflection when photographing, the text analysis unit automatically applies a filter to reduce the reflection. For example, the text analysis unit detects light reflections and applies an algorithm to reduce the reflection. The text analysis unit can also automatically apply an algorithm to remove shadows when there is a shadow when photographing. For example, the text analysis unit detects shadow areas and applies a filter to remove the shadow. The text analysis unit can also detect light intensity when photographing and automatically adjust optimal exposure settings. For example, the text analysis unit analyzes light intensity in real time and dynamically adjusts exposure settings. This can improve the quality of the photograph by automatically correcting light reflections and shadows.

[0036] The text analysis unit can apply an algorithm to improve the accuracy of handwritten character recognition during text analysis. The text analysis unit can improve recognition accuracy by, for example, using an AI model that has learned the characteristics of handwritten characters. For example, the text analysis unit can analyze the handwriting of handwritten characters and apply a recognition algorithm optimized for each individual user. The text analysis unit can also apply an algorithm that takes context into account to reduce recognition errors during handwritten character recognition. For example, the text analysis unit can apply an algorithm that improves the accuracy of handwritten character recognition based on context information. The text analysis unit can also continuously train the AI ​​model using training data to improve the accuracy of handwritten character recognition. For example, the text analysis unit collects user handwritten character data and updates the AI ​​model. This improves the accuracy of handwritten character recognition, enabling more accurate text analysis.

[0037] The text analysis unit can add a multilingual recognition function to support multiple languages ​​during text analysis. The text analysis unit applies an algorithm that can simultaneously recognize multiple languages, such as English, Japanese, and Chinese. For example, the text analysis unit automatically selects the optimal recognition model based on the language selected by the user. The text analysis unit can also apply an algorithm that takes context into account to accurately recognize text in multiple languages, even when multiple languages ​​are mixed. For example, the text analysis unit applies an algorithm that accurately analyzes text in multiple languages ​​based on context information. The text analysis unit can also continuously train the AI ​​model using training data to improve the multilingual recognition function. For example, the text analysis unit collects text data in multiple languages ​​and updates the AI ​​model. This allows the system to support multiple languages ​​and analyze text in various languages.

[0038] When analyzing text, the text analysis unit can determine the analysis priority by referring to the user's learning history. For example, the text analysis unit prioritizes analyzing questions that the user answered incorrectly in the past. For example, the text analysis unit determines the analysis priority based on the user's learning history data. The text analysis unit can also prioritize analyzing important questions based on the user's learning progress. For example, the text analysis unit dynamically adjusts the analysis priority based on the user's learning progress data. The text analysis unit can also automatically adjust the analysis priority based on the user's past answer history. For example, the text analysis unit analyzes the user's answer history data and applies an algorithm that determines the priority. In this way, important questions can be prioritized in the analysis by referring to the user's learning history.

[0039] When analyzing text, the text analysis unit can select the optimal analysis method by taking into account the user's device information. For example, if the user is using a smartphone, the text analysis unit provides an analysis method that matches the screen size. For example, the text analysis unit adjusts the analysis method based on the user's device information. Furthermore, if the user is using a tablet, the text analysis unit can also provide an analysis method optimized for a large screen. For example, the text analysis unit analyzes the user's device information in real time and selects the optimal analysis method. Furthermore, if the user is using a desktop, the text analysis unit can also provide a high-resolution analysis method. For example, the text analysis unit adjusts the analysis algorithm based on the device resolution. This allows the analysis accuracy to be improved by providing the optimal analysis method based on the user's device information.

[0040] The text analysis unit can customize the analysis algorithm by reflecting the user's past feedback when analyzing text. The text analysis unit adjusts the analysis algorithm based on, for example, feedback provided by the user in the past. For example, the text analysis unit applies an algorithm that reduces misrecognition based on the user's feedback data. The text analysis unit can also automatically adjust parameters to improve the accuracy of the analysis by reflecting the user's feedback. For example, the text analysis unit analyzes the user's feedback data and dynamically adjusts the parameters of the algorithm. The text analysis unit can also continuously train the analysis algorithm based on the user's feedback. For example, the text analysis unit updates the AI ​​model using the feedback data. In this way, the accuracy of the analysis algorithm can be improved by reflecting the user's feedback.

[0041] The correct answer determination unit can adjust the strictness of the determination depending on the difficulty of the question when determining whether the answer is correct. For example, the correct answer determination unit applies strict determination criteria to easy questions. For example, the correct answer determination unit adjusts the determination criteria based on difficulty data of the question. The correct answer determination unit can also apply lenient determination criteria to difficult questions. For example, the correct answer determination unit dynamically adjusts the determination criteria depending on the difficulty of the question. The correct answer determination unit can also apply different determination algorithms depending on the category of the question. For example, a determination algorithm that emphasizes the accuracy of calculations is applied to arithmetic questions, and a determination algorithm that takes context into account is applied to Japanese questions. In this way, by adjusting the strictness of the determination depending on the difficulty of the question, appropriate determination is possible.

[0042] When determining the correct answer, the correct answer determination unit can improve the accuracy of the determination by referring to the user's past answer history. The correct answer determination unit adjusts the determination criteria, for example, based on questions that the user has answered incorrectly in the past. For example, the correct answer determination unit adjusts the determination criteria based on the user's answer history data. The correct answer determination unit can also analyze the user's past answer history and adjust the determination criteria taking into account tendencies of incorrect answers. For example, the correct answer determination unit analyzes the user's answer history data and identifies tendencies of incorrect answers. The correct answer determination unit can also apply an algorithm that improves the accuracy of the determination based on the user's past answer history. For example, the correct answer determination unit uses the answer history data to update the AI ​​model and improve the accuracy of the determination. In this way, the accuracy of the determination can be improved by referring to the user's past answer history.

[0043] When determining the correct answer, the correct answer determination unit can apply different determination algorithms depending on the category of the question. For example, for arithmetic questions, the correct answer determination unit applies a determination algorithm that emphasizes the accuracy of calculation. For example, the correct answer determination unit selects a determination algorithm based on the category data of the question. The correct answer determination unit can also apply a determination algorithm that takes context into consideration for Japanese language questions. For example, the correct answer determination unit dynamically adjusts the determination algorithm depending on the category of the question. The correct answer determination unit can also apply a determination algorithm that emphasizes the accuracy of experimental results to science questions. For example, the correct answer determination unit selects the optimal determination algorithm based on the category data of the question. This enables accurate determination by applying an appropriate determination algorithm depending on the category of the question.

[0044] When determining whether an answer is correct, the correct answer determination unit can determine the priority of the determination taking into consideration the user's learning progress. For example, the correct answer determination unit prioritizes the determination of questions that the user has answered incorrectly in the past. For example, the correct answer determination unit determines the priority of the determination based on the user's learning progress data. The correct answer determination unit can also prioritize important questions based on the user's learning progress. For example, the correct answer determination unit automatically adjusts the priority of the determination based on the user's past answer history. This makes it possible to prioritize important questions based on the user's learning progress.

[0045] When determining the correct answer, the correct answer determination unit can select the optimal determination method by taking into account the user's device information. For example, if the user is using a smartphone, the correct answer determination unit provides a determination method that matches the screen size. For example, the correct answer determination unit adjusts the determination method based on the user's device information. Furthermore, if the user is using a tablet, the correct answer determination unit can also provide a determination method optimized for a large screen. For example, the correct answer determination unit analyzes the user's device information in real time and selects the optimal determination method. Furthermore, if the user is using a desktop, the correct answer determination unit can also provide a high-resolution determination method. For example, the correct answer determination unit adjusts the determination algorithm based on the device resolution. This allows for improving the accuracy of determination by providing the optimal determination method based on the user's device information.

[0046] The correct answer determination unit can customize the determination algorithm by reflecting the user's past feedback when determining the correct answer. The correct answer determination unit adjusts the determination algorithm, for example, based on feedback provided by the user in the past. For example, the correct answer determination unit applies an algorithm that reduces erroneous determinations based on the user's feedback data. The correct answer determination unit can also automatically adjust parameters to improve the accuracy of the determination by reflecting the user's feedback. For example, the correct answer determination unit analyzes the user's feedback data and dynamically adjusts the parameters of the algorithm. The correct answer determination unit can also continuously train the determination algorithm based on the user's feedback. For example, the correct answer determination unit updates the AI ​​model using the feedback data. In this way, the accuracy of the determination algorithm can be improved by reflecting the user's feedback.

[0047] The advice generation unit can adjust the level of detail of the advice according to the difficulty of the problem when generating advice. For example, for an easy problem, the advice generation unit provides concise advice. For example, the advice generation unit adjusts the level of detail of the advice based on difficulty data of the problem. Furthermore, for a difficult problem, the advice generation unit can also provide advice including a detailed explanation. For example, the advice generation unit dynamically adjusts the level of detail of the advice according to the difficulty of the problem. Furthermore, the advice generation unit can apply different advice algorithms according to the category of the problem. For example, an advice algorithm that emphasizes the calculation process is applied to arithmetic problems, and an advice algorithm that takes context into account is applied to Japanese language problems. In this way, appropriate advice can be provided by adjusting the level of detail of the advice according to the difficulty of the problem.

[0048] When generating advice, the advice generation unit can improve the accuracy of the advice by referring to the user's past answer history. The advice generation unit adjusts the content of the advice based on, for example, questions that the user got wrong in the past. For example, the advice generation unit adjusts the content of the advice based on the user's answer history data. The advice generation unit can also analyze the user's past answer history and provide advice taking into account tendencies of incorrect answers. For example, the advice generation unit analyzes the user's answer history data and identifies tendencies of incorrect answers. The advice generation unit can also apply an algorithm that improves the accuracy of the advice based on the user's past answer history. For example, the advice generation unit uses the answer history data to update an AI model and improve the accuracy of the advice. In this way, the accuracy of the advice can be improved by referring to the user's past answer history.

[0049] The advice generation unit can apply different advice algorithms depending on the problem category when generating advice. For example, the advice generation unit applies an advice algorithm that emphasizes the calculation process to an arithmetic problem. For example, the advice generation unit selects an advice algorithm based on problem category data. The advice generation unit can also apply an advice algorithm that takes context into consideration to a Japanese language problem. For example, the advice generation unit dynamically adjusts the advice algorithm depending on the problem category. The advice generation unit can also apply an advice algorithm that emphasizes the interpretation of experimental results to a science problem. For example, the advice generation unit selects the optimal advice algorithm based on problem category data. This enables accurate advice to be provided by applying an appropriate advice algorithm depending on the problem category.

[0050] When generating advice, the advice generation unit can determine the priority of advice taking into account the user's learning progress. For example, the advice generation unit prioritizes advice on questions that the user has answered incorrectly in the past. For example, the advice generation unit determines the priority of advice based on the user's learning progress data. The advice generation unit can also prioritize advice on important questions based on the user's learning progress. For example, the advice generation unit automatically adjusts the priority of advice based on the user's past answer history. This makes it possible to prioritize advice on important questions based on the user's learning progress.

[0051] When generating advice, the advice generation unit can select the optimal advice method by taking into consideration device information of the user. For example, if the user is using a smartphone, the advice generation unit provides an advice method that matches the screen size. For example, the advice generation unit adjusts the advice method based on the device information of the user. Furthermore, if the user is using a tablet, the advice generation unit can also provide an advice method that is optimized for a large screen. For example, the advice generation unit analyzes device information of the user in real time and selects the optimal advice method. Furthermore, if the user is using a desktop, the advice generation unit can also provide an advice method for high resolution. For example, the advice generation unit adjusts the advice algorithm based on the resolution of the device. This allows the accuracy of advice to be improved by providing the optimal advice method based on the device information of the user.

[0052] The advice generation unit can customize the advice algorithm by reflecting the user's past feedback when generating advice. The advice generation unit adjusts the advice algorithm based on, for example, feedback provided by the user in the past. For example, the advice generation unit applies an algorithm that reduces erroneous advice based on the user's feedback data. The advice generation unit can also automatically adjust parameters to improve the accuracy of advice by reflecting the user's feedback. For example, the advice generation unit analyzes the user's feedback data and dynamically adjusts the parameters of the algorithm. The advice generation unit can also continuously train the advice algorithm based on the user's feedback. For example, the advice generation unit updates the AI ​​model using the feedback data. In this way, the accuracy of the advice algorithm can be improved by reflecting the user's feedback.

[0053] When providing advice, the providing unit can select the optimal timing for providing advice by referring to the user's learning history. For example, the providing unit provides advice immediately after the user solves a problem that the user previously got wrong. For example, the providing unit determines the timing for providing advice based on the user's learning history data. The providing unit can also provide advice at an appropriate timing based on the user's learning progress. For example, the providing unit dynamically adjusts the timing for providing advice based on the user's learning progress data. The providing unit can also automatically adjust the optimal timing for providing advice based on the user's past answer history. For example, the providing unit analyzes the user's answer history data and applies an algorithm that determines the timing for providing advice. In this way, the optimal timing for providing advice can be selected by referring to the user's learning history.

[0054] When providing advice, the providing unit can select the optimal delivery method by taking into consideration the user's device information. For example, if the user is using a smartphone, the providing unit provides a delivery method that matches the screen size. For example, the providing unit adjusts the delivery method based on the user's device information. Furthermore, if the user is using a tablet, the providing unit can also provide a delivery method optimized for a large screen. For example, the providing unit analyzes the user's device information in real time and selects the optimal delivery method. Furthermore, if the user is using a desktop, the providing unit can also provide a high-resolution delivery method. For example, the providing unit adjusts the delivery algorithm based on the device resolution. This allows the accuracy of advice to be improved by providing the optimal delivery method based on the user's device information.

[0055] The providing unit can customize the advice providing method by reflecting the user's past feedback when providing advice. The providing unit, for example, adjusts the advice providing method based on feedback provided by the user in the past. For example, the providing unit applies a advice providing method that reduces erroneous advice based on the user's feedback data. The providing unit can also automatically adjust parameters to improve the accuracy of advice providing by reflecting the user's feedback. For example, the providing unit analyzes the user's feedback data and dynamically adjusts the parameters of the advice providing method. The providing unit can also continuously train the advice providing algorithm based on the user's feedback. For example, the providing unit updates the AI ​​model using the feedback data. In this way, the accuracy of the advice providing method can be improved by reflecting the user's feedback.

[0056] When providing advice, the providing unit can determine the priority of advice provision taking into account the user's learning progress. For example, the providing unit prioritizes advice on questions that the user has answered incorrectly in the past. For example, the providing unit determines the priority of advice provision based on the user's learning progress data. The providing unit can also prioritize advice on important questions based on the user's learning progress. For example, the providing unit automatically adjusts the priority of advice based on the user's past answer history. This makes it possible to prioritize advice on important questions based on the user's learning progress.

[0057] When providing advice, the providing unit can select the optimal delivery method by taking into consideration the user's device information. For example, if the user is using a smartphone, the providing unit provides a delivery method that matches the screen size. For example, the providing unit adjusts the delivery method based on the user's device information. Furthermore, if the user is using a tablet, the providing unit can also provide a delivery method optimized for a large screen. For example, the providing unit analyzes the user's device information in real time and selects the optimal delivery method. Furthermore, if the user is using a desktop, the providing unit can also provide a high-resolution delivery method. For example, the providing unit adjusts the delivery algorithm based on the device resolution. This allows the accuracy of advice to be improved by providing the optimal delivery method based on the user's device information.

[0058] The providing unit can customize the advice providing method by reflecting the user's past feedback when providing advice. The providing unit, for example, adjusts the advice providing method based on feedback provided by the user in the past. For example, the providing unit applies a advice providing method that reduces erroneous advice based on the user's feedback data. The providing unit can also automatically adjust parameters to improve the accuracy of advice providing by reflecting the user's feedback. For example, the providing unit analyzes the user's feedback data and dynamically adjusts the parameters of the advice providing method. The providing unit can also continuously train the advice providing algorithm based on the user's feedback. For example, the providing unit updates the AI ​​model using the feedback data. In this way, the accuracy of the advice providing method can be improved by reflecting the user's feedback.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The learning assistance system can further include a learning style analysis unit that analyzes the user's learning style. The learning style analysis unit analyzes the user's most effective learning method and provides advice tailored to the user's individual learning style. For example, a user who prefers visual learning can be provided with advice that makes extensive use of diagrams and graphs. A user who prefers auditory learning can be provided with advice using audio messages. Furthermore, a user who prefers practical learning can be presented with specific exercises. This makes it possible to provide optimal advice tailored to the user's learning style.

[0061] The text analysis unit can further include a function for monitoring the user's learning progress in real time. For example, the text analysis unit can record how much time the user spends on each problem and evaluate the efficiency of the learning. If the user is having trouble with a particular problem, the text analysis unit can provide additional hints or explanations for that problem. Furthermore, the text analysis unit can automatically select the next problem to be tackled based on the user's learning progress data. This can improve the user's learning efficiency.

[0062] The correct answer determination unit can further create an individual study plan based on the user's study history. For example, the correct answer determination unit can identify questions the user answered incorrectly in the past or areas in which the user is weak, and adjust the study plan based on that. The correct answer determination unit can also monitor the progress of the study plan according to the user's study goals and revise the plan as necessary. Furthermore, the correct answer determination unit can adjust the difficulty level of the study plan to match the user's learning pace. This makes it possible to provide the user with an optimal study plan that meets their individual learning needs.

[0063] The advice generation unit can further include a customization function according to the user's learning style. For example, if the user prefers visual learning, the advice generation unit can provide advice that makes extensive use of diagrams and graphs. If the user prefers auditory learning, the advice generation unit can provide advice using audio messages. Furthermore, if the user prefers practical learning, the advice generation unit can also present specific exercises. This makes it possible to provide optimal advice according to the user's learning style.

[0064] The text analysis unit can also create an individualized study plan based on the user's study history. For example, the text analysis unit can identify questions the user has answered incorrectly in the past or areas of weakness, and adjust the study plan based on that information. The text analysis unit can also monitor the progress of the study plan according to the user's study goals and revise the plan as necessary. Furthermore, the text analysis unit can adjust the difficulty level of the study plan to match the user's learning pace. This makes it possible to provide the user with an optimal study plan that meets their individual learning needs.

[0065] The advice generation unit can further include a function for monitoring the user's learning progress in real time. For example, the advice generation unit can record how much time the user spends on each problem and evaluate the efficiency of the learning. If the user is having trouble with a particular problem, the advice generation unit can provide additional hints or explanations for that problem. Furthermore, the advice generation unit can automatically select the next problem to tackle based on the user's learning progress data. This can improve the user's learning efficiency.

[0066] The providing unit can further include a customization function according to the user's learning style. For example, if the user prefers visual learning, the providing unit can provide advice that makes extensive use of diagrams and graphs. If the user prefers auditory learning, the providing unit can provide advice using voice messages. Furthermore, if the user prefers practical learning, the providing unit can also present specific exercises. This makes it possible to provide optimal advice according to the user's learning style.

[0067] The processing flow of the first embodiment will be briefly explained below.

[0068] Step 1: The text analysis unit uses OCR technology to capture the print image taken by the user as text. For example, an image of a print taken with a smartphone or tablet can be converted into text data using OCR technology. It can also apply algorithms to recognize handwritten characters with high accuracy. Step 2: The correct answer determination unit determines whether the answer is correct or incorrect based on the imported text. For example, it analyzes the question and answer and determines whether the answer is correct or incorrect. It can also adjust the strictness of the determination depending on the difficulty of the question. Step 3: The advice generator generates advice for the incorrect answers. For example, it analyzes the incorrect calculation process and identifies the part where the mistake occurred. It can also improve the accuracy of advice by referring to the user's past answer history. Step 4: The providing unit provides the generated advice to the user. For example, the advice is provided to the user as a text message or a voice message. The providing unit can also estimate the user's emotions and adjust the way the advice is provided based on the estimated emotions.

[0069] (Example 2) A system according to an embodiment of the present invention is an application that uses a generative AI to check children's homework answers. The system allows users to take a photo of a printout provided by a school or cram school using a smartphone or tablet, convert it into text using OCR technology, and automatically analyze it. The generative AI distinguishes between correct and incorrect answers, and for incorrect answers, analyzes the answers and provides advice on how to approach the problem. This advice incorporates a coaching element rather than simply providing the answer. Furthermore, by accumulating various correct and incorrect answer data for each target user's age group, the system predicts trends, such as areas where mistakes are likely to be made, and provides optimal advice. This allows the system to develop children's ability to think independently and solve problems. It also makes it easier for parents and teachers to understand their children's learning progress, enabling more effective support.

[0070] A learning assistance system according to an embodiment includes a text analysis unit, a correct answer determination unit, an advice generation unit, and a providing unit. The text analysis unit captures a print photographed by a user as text using OCR technology. For example, the text analysis unit converts an image of a print photographed with a smartphone or tablet into text data using OCR technology. The text analysis unit can also apply an algorithm for recognizing handwritten characters with high accuracy. The correct answer determination unit determines whether an answer is correct or incorrect based on the captured text. For example, the correct answer determination unit analyzes a question and an answer to determine whether the answer is correct or incorrect. The correct answer determination unit can also adjust the strictness of the determination depending on the difficulty of the question. The advice generation unit generates advice for an incorrect answer. For example, the advice generation unit analyzes a calculation process where an error occurred and identifies the part where the error occurred. The advice generation unit can also improve the accuracy of the advice by referring to the user's past answer history. The providing unit provides the generated advice. For example, the providing unit provides the advice to the user as a text message or a voice message. The providing unit can also estimate the user's emotions and adjust the method of providing advice based on the estimated emotions. This allows the learning support system according to the embodiment to analyze the text of a printout photographed by the user, determine whether the answer is correct or incorrect, and provide advice for the incorrect part.

[0071] The text analysis unit can capture text by photographing a print using OCR technology. For example, the text analysis unit converts an image of a print taken with a smartphone or tablet into text data using OCR technology. The text analysis unit can also apply algorithms to recognize handwritten characters with high accuracy. For example, the text analysis unit can improve recognition accuracy by using an AI model that has learned the characteristics of handwritten characters. The text analysis unit also has a function to automatically correct light reflections and shadows. For example, if there is strong light reflection when photographing, it can automatically apply a filter to reduce reflections. This allows the text on the print to be captured accurately using OCR technology.

[0072] The correct answer determination unit can determine whether an answer is correct or incorrect based on the imported text. For example, the correct answer determination unit analyzes the question and answer to determine whether the answer is correct or incorrect. For example, the correct answer determination unit compares the answer with a database of correct answers for the question to determine whether the answer is correct or incorrect. The correct answer determination unit can also adjust the strictness of the determination depending on the difficulty of the question. For example, strict criteria can be applied to easy questions, and lenient criteria can be applied to difficult questions. The correct answer determination unit can also improve the accuracy of the determination by referring to the user's past answer history. For example, the determination criteria can be adjusted based on questions the user got wrong in the past. This makes it possible to accurately determine whether the answer is correct or incorrect based on the imported text.

[0073] The advice generation unit can generate advice for incorrect answers. For example, the advice generation unit analyzes the incorrect calculation process and identifies the part where the mistake occurred. For example, the advice generation unit analyzes the incorrect calculation process step by step and presents the correct calculation method. The advice generation unit can also improve the accuracy of the advice by referring to the user's past answer history. For example, the advice content can be adjusted based on problems the user has gotten wrong in the past. The advice generation unit can also apply different advice algorithms depending on the problem category. For example, an advice algorithm that emphasizes the calculation process can be applied to arithmetic problems, and an advice algorithm that takes context into account can be applied to Japanese language problems. This makes it possible to generate appropriate advice for incorrect answers.

[0074] The providing unit can provide the generated advice. For example, the providing unit provides the advice to the user as a text message or a voice message. For example, the providing unit displays the generated advice on a smartphone or tablet screen. The providing unit can also estimate the user's emotions and adjust the way the advice is provided based on the estimated emotions. For example, if the user is feeling stressed, the providing unit can provide advice in gentle language, and if the user is relaxed, the providing unit can provide advice including detailed explanations. The providing unit can also select the optimal timing for providing the advice by referring to the user's learning history. For example, the providing unit can provide advice immediately after the user solves a problem that they previously got wrong. In this way, the generated advice can be provided to the user.

[0075] The advice generation unit accumulates multiple correct and incorrect answer data for each age group of target users, predicts trends in areas where mistakes are likely to be made, and provides optimal advice. The advice generation unit, for example, collects various correct and incorrect answer data for each age group of target users and analyzes trends in areas where mistakes are likely to be made. For example, in the case of elementary school arithmetic problems, it can be determined that mistakes are likely to be made with specific calculation methods or problem formats. The advice generation unit can provide optimal advice to users based on this data. The advice generation unit can also accumulate data by age group and analyze long-term trends. For example, the advice generation unit can analyze data by age group over time to identify changes in areas where mistakes are likely to be made. This allows the advice generation unit to accumulate data by age group, predict areas where mistakes are likely to be made, and provide optimal advice.

[0076] The text analysis unit can estimate the user's emotions and adjust the accuracy of the text analysis based on the estimated user emotions. For example, if the user is feeling stressed, the text analysis unit increases the accuracy of the analysis to reduce misrecognition. For example, the text analysis unit adjusts the parameters of the analysis algorithm based on the user's emotional data. Furthermore, if the user is relaxed, the text analysis unit can perform processing with normal analysis accuracy. For example, the text analysis unit dynamically adjusts the analysis accuracy according to the user's emotional state. Furthermore, if the user is in a hurry, the text analysis unit can prioritize analysis speed and tolerate some misrecognition. For example, the text analysis unit analyzes the user's emotional data in real time and instantly adjusts the analysis accuracy. This allows for more accurate analysis by adjusting the accuracy of the text analysis according to the user's emotions.

[0077] The text analysis unit can add a function to automatically correct light reflections and shadows when photographing a print. For example, if there is strong light reflection when photographing, the text analysis unit automatically applies a filter to reduce the reflection. For example, the text analysis unit detects light reflections and applies an algorithm to reduce the reflection. The text analysis unit can also automatically apply an algorithm to remove shadows when there is a shadow when photographing. For example, the text analysis unit detects shadow areas and applies a filter to remove the shadow. The text analysis unit can also detect light intensity when photographing and automatically adjust optimal exposure settings. For example, the text analysis unit analyzes light intensity in real time and dynamically adjusts exposure settings. This can improve the quality of the photograph by automatically correcting light reflections and shadows.

[0078] The text analysis unit can apply an algorithm to improve the accuracy of handwritten character recognition during text analysis. The text analysis unit can improve recognition accuracy by, for example, using an AI model that has learned the characteristics of handwritten characters. For example, the text analysis unit can analyze the handwriting of handwritten characters and apply a recognition algorithm optimized for each individual user. The text analysis unit can also apply an algorithm that takes context into account to reduce recognition errors during handwritten character recognition. For example, the text analysis unit can apply an algorithm that improves the accuracy of handwritten character recognition based on context information. The text analysis unit can also continuously train the AI ​​model using training data to improve the accuracy of handwritten character recognition. For example, the text analysis unit collects user handwritten character data and updates the AI ​​model. This improves the accuracy of handwritten character recognition, enabling more accurate text analysis.

[0079] The text analysis unit can add a multilingual recognition function to support multiple languages ​​during text analysis. The text analysis unit applies an algorithm that can simultaneously recognize multiple languages, such as English, Japanese, and Chinese. For example, the text analysis unit automatically selects the optimal recognition model based on the language selected by the user. The text analysis unit can also apply an algorithm that takes context into account to accurately recognize text in multiple languages, even when multiple languages ​​are mixed. For example, the text analysis unit applies an algorithm that accurately analyzes text in multiple languages ​​based on context information. The text analysis unit can also continuously train the AI ​​model using training data to improve the multilingual recognition function. For example, the text analysis unit collects text data in multiple languages ​​and updates the AI ​​model. This allows the system to support multiple languages ​​and analyze text in various languages.

[0080] The text analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the text analysis unit provides a simple, highly visible display method. For example, the text analysis unit adjusts the display method based on the user's emotional data. Furthermore, if the user is relaxed, the text analysis unit can also provide a display method that includes detailed information. For example, the text analysis unit dynamically adjusts the display method according to the user's emotional state. Furthermore, if the user is in a hurry, the text analysis unit can also provide a display method that focuses on the main points. For example, the text analysis unit analyzes the user's emotional data in real time and instantly adjusts the display method. In this way, by adjusting the display method of the analysis results according to the user's emotions, it is possible to provide a display that is easy for the user to view.

[0081] When analyzing text, the text analysis unit can determine the analysis priority by referring to the user's learning history. For example, the text analysis unit prioritizes analyzing questions that the user answered incorrectly in the past. For example, the text analysis unit determines the analysis priority based on the user's learning history data. The text analysis unit can also prioritize analyzing important questions based on the user's learning progress. For example, the text analysis unit dynamically adjusts the analysis priority based on the user's learning progress data. The text analysis unit can also automatically adjust the analysis priority based on the user's past answer history. For example, the text analysis unit analyzes the user's answer history data and applies an algorithm that determines the priority. In this way, important questions can be prioritized in the analysis by referring to the user's learning history.

[0082] When analyzing text, the text analysis unit can select the optimal analysis method by taking into account the user's device information. For example, if the user is using a smartphone, the text analysis unit provides an analysis method that matches the screen size. For example, the text analysis unit adjusts the analysis method based on the user's device information. Furthermore, if the user is using a tablet, the text analysis unit can also provide an analysis method optimized for a large screen. For example, the text analysis unit analyzes the user's device information in real time and selects the optimal analysis method. Furthermore, if the user is using a desktop, the text analysis unit can also provide a high-resolution analysis method. For example, the text analysis unit adjusts the analysis algorithm based on the device resolution. This allows the analysis accuracy to be improved by providing the optimal analysis method based on the user's device information.

[0083] The text analysis unit can customize the analysis algorithm by reflecting the user's past feedback when analyzing text. The text analysis unit adjusts the analysis algorithm based on, for example, feedback provided by the user in the past. For example, the text analysis unit applies an algorithm that reduces misrecognition based on the user's feedback data. The text analysis unit can also automatically adjust parameters to improve the accuracy of the analysis by reflecting the user's feedback. For example, the text analysis unit analyzes the user's feedback data and dynamically adjusts the parameters of the algorithm. The text analysis unit can also continuously train the analysis algorithm based on the user's feedback. For example, the text analysis unit updates the AI ​​model using the feedback data. In this way, the accuracy of the analysis algorithm can be improved by reflecting the user's feedback.

[0084] The correct answer determination unit can estimate the user's emotions and adjust the criteria for determining correct answers based on the estimated user emotions. For example, if the user is feeling stressed, the correct answer determination unit relaxes the criteria to reduce incorrect answers. For example, the correct answer determination unit adjusts the criteria based on the user's emotional data. Furthermore, if the user is relaxed, the correct answer determination unit can also perform processing using normal criteria. For example, the correct answer determination unit dynamically adjusts the criteria according to the user's emotional state. Furthermore, if the user is in a hurry, the correct answer determination unit can prioritize determination speed and tolerate some erroneous determination. For example, the correct answer determination unit analyzes the user's emotional data in real time and instantly adjusts the criteria. This allows for more appropriate determination by adjusting the criteria for determining correct answers according to the user's emotions.

[0085] The correct answer determination unit can adjust the strictness of the determination depending on the difficulty of the question when determining whether the answer is correct. For example, the correct answer determination unit applies strict determination criteria to easy questions. For example, the correct answer determination unit adjusts the determination criteria based on difficulty data of the question. The correct answer determination unit can also apply lenient determination criteria to difficult questions. For example, the correct answer determination unit dynamically adjusts the determination criteria depending on the difficulty of the question. The correct answer determination unit can also apply different determination algorithms depending on the category of the question. For example, a determination algorithm that emphasizes the accuracy of calculations is applied to arithmetic questions, and a determination algorithm that takes context into account is applied to Japanese questions. In this way, by adjusting the strictness of the determination depending on the difficulty of the question, appropriate determination is possible.

[0086] When determining the correct answer, the correct answer determination unit can improve the accuracy of the determination by referring to the user's past answer history. The correct answer determination unit adjusts the determination criteria, for example, based on questions that the user has answered incorrectly in the past. For example, the correct answer determination unit adjusts the determination criteria based on the user's answer history data. The correct answer determination unit can also analyze the user's past answer history and adjust the determination criteria taking into account tendencies of incorrect answers. For example, the correct answer determination unit analyzes the user's answer history data and identifies tendencies of incorrect answers. The correct answer determination unit can also apply an algorithm that improves the accuracy of the determination based on the user's past answer history. For example, the correct answer determination unit uses the answer history data to update the AI ​​model and improve the accuracy of the determination. In this way, the accuracy of the determination can be improved by referring to the user's past answer history.

[0087] When determining the correct answer, the correct answer determination unit can apply different determination algorithms depending on the category of the question. For example, for arithmetic questions, the correct answer determination unit applies a determination algorithm that emphasizes the accuracy of calculation. For example, the correct answer determination unit selects a determination algorithm based on the category data of the question. The correct answer determination unit can also apply a determination algorithm that takes context into consideration for Japanese language questions. For example, the correct answer determination unit dynamically adjusts the determination algorithm depending on the category of the question. The correct answer determination unit can also apply a determination algorithm that emphasizes the accuracy of experimental results to science questions. For example, the correct answer determination unit selects the optimal determination algorithm based on the category data of the question. This enables accurate determination by applying an appropriate determination algorithm depending on the category of the question.

[0088] The correct answer determination unit can estimate the user's emotions and adjust the display method of the determination result based on the estimated user's emotions. For example, if the user is nervous, the correct answer determination unit provides a simple, highly visible display method. For example, the correct answer determination unit adjusts the display method based on the user's emotional data. Furthermore, if the user is relaxed, the correct answer determination unit can also provide a display method that includes detailed information. For example, the correct answer determination unit dynamically adjusts the display method according to the user's emotional state. Furthermore, if the user is in a hurry, the correct answer determination unit can also provide a display method that focuses on the main points. For example, the correct answer determination unit analyzes the user's emotional data in real time and instantly adjusts the display method. In this way, by adjusting the display method of the determination result according to the user's emotions, it is possible to provide a display that is easy for the user to see.

[0089] When determining whether an answer is correct, the correct answer determination unit can determine the priority of the determination taking into consideration the user's learning progress. For example, the correct answer determination unit prioritizes the determination of questions that the user has answered incorrectly in the past. For example, the correct answer determination unit determines the priority of the determination based on the user's learning progress data. The correct answer determination unit can also prioritize important questions based on the user's learning progress. For example, the correct answer determination unit automatically adjusts the priority of the determination based on the user's past answer history. This makes it possible to prioritize important questions based on the user's learning progress.

[0090] When determining the correct answer, the correct answer determination unit can select the optimal determination method by taking into account the user's device information. For example, if the user is using a smartphone, the correct answer determination unit provides a determination method that matches the screen size. For example, the correct answer determination unit adjusts the determination method based on the user's device information. Furthermore, if the user is using a tablet, the correct answer determination unit can also provide a determination method optimized for a large screen. For example, the correct answer determination unit analyzes the user's device information in real time and selects the optimal determination method. Furthermore, if the user is using a desktop, the correct answer determination unit can also provide a high-resolution determination method. For example, the correct answer determination unit adjusts the determination algorithm based on the device resolution. This allows for improving the accuracy of determination by providing the optimal determination method based on the user's device information.

[0091] The correct answer determination unit can customize the determination algorithm by reflecting the user's past feedback when determining the correct answer. The correct answer determination unit adjusts the determination algorithm, for example, based on feedback provided by the user in the past. For example, the correct answer determination unit applies an algorithm that reduces erroneous determinations based on the user's feedback data. The correct answer determination unit can also automatically adjust parameters to improve the accuracy of the determination by reflecting the user's feedback. For example, the correct answer determination unit analyzes the user's feedback data and dynamically adjusts the parameters of the algorithm. The correct answer determination unit can also continuously train the determination algorithm based on the user's feedback. For example, the correct answer determination unit updates the AI ​​model using the feedback data. In this way, the accuracy of the determination algorithm can be improved by reflecting the user's feedback.

[0092] The advice generation unit can estimate the user's emotions and adjust the way the advice is expressed based on the estimated user's emotions. For example, if the user is feeling stressed, the advice generation unit provides advice in gentle language. For example, the advice generation unit adjusts the way the advice is expressed based on the user's emotion data. Furthermore, if the user is relaxed, the advice generation unit can also provide advice including detailed explanations. For example, the advice generation unit dynamically adjusts the way the advice is expressed according to the user's emotional state. Furthermore, if the user is in a hurry, the advice generation unit can provide concise and to-the-point advice. For example, the advice generation unit analyzes the user's emotion data in real time and instantly adjusts the way the advice is expressed. In this way, more appropriate advice can be provided by adjusting the way the advice is expressed according to the user's emotions.

[0093] The advice generation unit can adjust the level of detail of the advice according to the difficulty of the problem when generating advice. For example, for an easy problem, the advice generation unit provides concise advice. For example, the advice generation unit adjusts the level of detail of the advice based on difficulty data of the problem. Furthermore, for a difficult problem, the advice generation unit can also provide advice including a detailed explanation. For example, the advice generation unit dynamically adjusts the level of detail of the advice according to the difficulty of the problem. Furthermore, the advice generation unit can apply different advice algorithms according to the category of the problem. For example, an advice algorithm that emphasizes the calculation process is applied to arithmetic problems, and an advice algorithm that takes context into account is applied to Japanese language problems. In this way, appropriate advice can be provided by adjusting the level of detail of the advice according to the difficulty of the problem.

[0094] When generating advice, the advice generation unit can improve the accuracy of the advice by referring to the user's past answer history. The advice generation unit adjusts the content of the advice based on, for example, questions that the user got wrong in the past. For example, the advice generation unit adjusts the content of the advice based on the user's answer history data. The advice generation unit can also analyze the user's past answer history and provide advice taking into account tendencies of incorrect answers. For example, the advice generation unit analyzes the user's answer history data and identifies tendencies of incorrect answers. The advice generation unit can also apply an algorithm that improves the accuracy of the advice based on the user's past answer history. For example, the advice generation unit uses the answer history data to update an AI model and improve the accuracy of the advice. In this way, the accuracy of the advice can be improved by referring to the user's past answer history.

[0095] The advice generation unit can apply different advice algorithms depending on the problem category when generating advice. For example, the advice generation unit applies an advice algorithm that emphasizes the calculation process to an arithmetic problem. For example, the advice generation unit selects an advice algorithm based on problem category data. The advice generation unit can also apply an advice algorithm that takes context into consideration to a Japanese language problem. For example, the advice generation unit dynamically adjusts the advice algorithm depending on the problem category. The advice generation unit can also apply an advice algorithm that emphasizes the interpretation of experimental results to a science problem. For example, the advice generation unit selects the optimal advice algorithm based on problem category data. This enables accurate advice to be provided by applying an appropriate advice algorithm depending on the problem category.

[0096] The advice generation unit can estimate the user's emotion and adjust the length of the advice based on the estimated user's emotion. For example, if the user is feeling stressed, the advice generation unit provides short, to-the-point advice. For example, the advice generation unit adjusts the length of the advice based on the user's emotion data. Furthermore, if the user is relaxed, the advice generation unit can provide longer advice including detailed explanations. For example, the advice generation unit dynamically adjusts the length of the advice according to the user's emotional state. Furthermore, if the user is in a hurry, the advice generation unit can provide concise, quick advice. For example, the advice generation unit analyzes the user's emotion data in real time and instantly adjusts the length of the advice. In this way, more appropriate advice can be provided by adjusting the length of the advice according to the user's emotion.

[0097] When generating advice, the advice generation unit can determine the priority of advice taking into account the user's learning progress. For example, the advice generation unit prioritizes advice on questions that the user has answered incorrectly in the past. For example, the advice generation unit determines the priority of advice based on the user's learning progress data. The advice generation unit can also prioritize advice on important questions based on the user's learning progress. For example, the advice generation unit automatically adjusts the priority of advice based on the user's past answer history. This makes it possible to prioritize advice on important questions based on the user's learning progress.

[0098] When generating advice, the advice generation unit can select the optimal advice method by taking into consideration device information of the user. For example, if the user is using a smartphone, the advice generation unit provides an advice method that matches the screen size. For example, the advice generation unit adjusts the advice method based on the device information of the user. Furthermore, if the user is using a tablet, the advice generation unit can also provide an advice method that is optimized for a large screen. For example, the advice generation unit analyzes device information of the user in real time and selects the optimal advice method. Furthermore, if the user is using a desktop, the advice generation unit can also provide an advice method for high resolution. For example, the advice generation unit adjusts the advice algorithm based on the resolution of the device. This allows the accuracy of advice to be improved by providing the optimal advice method based on the device information of the user.

[0099] The advice generation unit can customize the advice algorithm by reflecting the user's past feedback when generating advice. The advice generation unit adjusts the advice algorithm based on, for example, feedback provided by the user in the past. For example, the advice generation unit applies an algorithm that reduces erroneous advice based on the user's feedback data. The advice generation unit can also automatically adjust parameters to improve the accuracy of advice by reflecting the user's feedback. For example, the advice generation unit analyzes the user's feedback data and dynamically adjusts the parameters of the algorithm. The advice generation unit can also continuously train the advice algorithm based on the user's feedback. For example, the advice generation unit updates the AI ​​model using the feedback data. In this way, the accuracy of the advice algorithm can be improved by reflecting the user's feedback.

[0100] The providing unit can estimate the user's emotions and adjust the method of providing advice based on the estimated user's emotions. For example, if the user is feeling stressed, the providing unit provides advice using gentle language. For example, the providing unit adjusts the method of providing advice based on the user's emotion data. Furthermore, if the user is relaxed, the providing unit can also provide advice including detailed explanations. For example, the providing unit dynamically adjusts the method of providing advice according to the user's emotional state. Furthermore, if the user is in a hurry, the providing unit can provide concise and to-the-point advice. For example, the providing unit analyzes the user's emotion data in real time and instantly adjusts the method of providing advice. In this way, more appropriate advice can be provided by adjusting the method of providing advice according to the user's emotions.

[0101] When providing advice, the providing unit can select the optimal timing for providing advice by referring to the user's learning history. For example, the providing unit provides advice immediately after the user solves a problem that the user previously got wrong. For example, the providing unit determines the timing for providing advice based on the user's learning history data. The providing unit can also provide advice at an appropriate timing based on the user's learning progress. For example, the providing unit dynamically adjusts the timing for providing advice based on the user's learning progress data. The providing unit can also automatically adjust the optimal timing for providing advice based on the user's past answer history. For example, the providing unit analyzes the user's answer history data and applies an algorithm that determines the timing for providing advice. In this way, the optimal timing for providing advice can be selected by referring to the user's learning history.

[0102] When providing advice, the providing unit can select the optimal delivery method by taking into consideration the user's device information. For example, if the user is using a smartphone, the providing unit provides a delivery method that matches the screen size. For example, the providing unit adjusts the delivery method based on the user's device information. Furthermore, if the user is using a tablet, the providing unit can also provide a delivery method optimized for a large screen. For example, the providing unit analyzes the user's device information in real time and selects the optimal delivery method. Furthermore, if the user is using a desktop, the providing unit can also provide a high-resolution delivery method. For example, the providing unit adjusts the delivery algorithm based on the device resolution. This allows the accuracy of advice to be improved by providing the optimal delivery method based on the user's device information.

[0103] The providing unit can customize the advice providing method by reflecting the user's past feedback when providing advice. The providing unit, for example, adjusts the advice providing method based on feedback provided by the user in the past. For example, the providing unit applies a advice providing method that reduces erroneous advice based on the user's feedback data. The providing unit can also automatically adjust parameters to improve the accuracy of advice providing by reflecting the user's feedback. For example, the providing unit analyzes the user's feedback data and dynamically adjusts the parameters of the advice providing method. The providing unit can also continuously train the advice providing algorithm based on the user's feedback. For example, the providing unit updates the AI ​​model using the feedback data. In this way, the accuracy of the advice providing method can be improved by reflecting the user's feedback.

[0104] The providing unit can estimate the user's emotions and adjust the frequency of providing advice based on the estimated user's emotions. For example, the providing unit reduces the frequency of providing advice when the user is feeling stressed. For example, the providing unit adjusts the frequency of providing advice based on the user's emotion data. The providing unit can also provide advice at a normal frequency when the user is relaxed. For example, the providing unit dynamically adjusts the frequency of providing advice according to the user's emotional state. The providing unit can also increase the frequency of providing advice when the user is in a hurry. For example, the providing unit analyzes the user's emotion data in real time and instantly adjusts the frequency of providing advice. In this way, by adjusting the frequency of providing advice according to the user's emotions, it is possible to provide advice at a more appropriate frequency.

[0105] When providing advice, the providing unit can determine the priority of advice provision taking into account the user's learning progress. For example, the providing unit prioritizes advice on questions that the user has answered incorrectly in the past. For example, the providing unit determines the priority of advice provision based on the user's learning progress data. The providing unit can also prioritize advice on important questions based on the user's learning progress. For example, the providing unit automatically adjusts the priority of advice based on the user's past answer history. This makes it possible to prioritize advice on important questions based on the user's learning progress.

[0106] When providing advice, the providing unit can select the optimal delivery method by taking into consideration the user's device information. For example, if the user is using a smartphone, the providing unit provides a delivery method that matches the screen size. For example, the providing unit adjusts the delivery method based on the user's device information. Furthermore, if the user is using a tablet, the providing unit can also provide a delivery method optimized for a large screen. For example, the providing unit analyzes the user's device information in real time and selects the optimal delivery method. Furthermore, if the user is using a desktop, the providing unit can also provide a high-resolution delivery method. For example, the providing unit adjusts the delivery algorithm based on the device resolution. This allows the accuracy of advice to be improved by providing the optimal delivery method based on the user's device information.

[0107] The providing unit can customize the advice providing method by reflecting the user's past feedback when providing advice. The providing unit, for example, adjusts the advice providing method based on feedback provided by the user in the past. For example, the providing unit applies a advice providing method that reduces erroneous advice based on the user's feedback data. The providing unit can also automatically adjust parameters to improve the accuracy of advice providing by reflecting the user's feedback. For example, the providing unit analyzes the user's feedback data and dynamically adjusts the parameters of the advice providing method. The providing unit can also continuously train the advice providing algorithm based on the user's feedback. For example, the providing unit updates the AI ​​model using the feedback data. In this way, the accuracy of the advice providing method can be improved by reflecting the user's feedback. === Hard Collateral 1-1 === Each of the multiple elements including the text analysis unit, correct answer determination unit, advice generation unit, and provision unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the text analysis unit photographs a print using the camera 42 of the smart device 14 and converts it into text data using OCR technology. The correct answer determination unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and determines whether the answer is correct or incorrect based on the imported text. The advice generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates advice for incorrect answers. The provision unit is realized, for example, by the control unit 46A of the smart device 14 and provides the generated advice to the user as a text message or a voice message. === Hard Collateral 1-2 === Each of the multiple elements including the text analysis unit, correct answer determination unit, advice generation unit, and provision unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the text analysis unit photographs a print using the camera 42 of the smart glasses 214 and converts it into text data using OCR technology. The correct answer determination unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and determines whether the answer is correct or incorrect based on the imported text. The advice generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates advice for incorrect answers. The provision unit is realized, for example, by the control unit 46A of the smart glasses 214 and provides the generated advice to the user as a text message or a voice message. === Hard Collateral 1-3 === Each of the multiple elements including the text analysis unit, correct answer determination unit, advice generation unit, and provision unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the text analysis unit photographs a print using the camera 42 of the headset type terminal 314 and converts it into text data using OCR technology. The correct answer determination unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and determines whether the answer is correct or incorrect based on the imported text. The advice generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates advice for incorrect answers. The provision unit is realized, for example, by the control unit 46A of the headset type terminal 314, and provides the generated advice to the user as a text message or a voice message. === Hard Collateral 1-4 === Each of the multiple elements including the text analysis unit, correct answer determination unit, advice generation unit, and provision unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the text analysis unit photographs a print using the camera 42 of the robot 414 and converts it into text data using OCR technology. The correct answer determination unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and determines whether the answer is correct or incorrect based on the imported text. The advice generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates advice for incorrect answers. The provision unit is realized, for example, by the control unit 46A of the robot 414, and provides the generated advice to the user as a text message or a voice message.

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

[0109] The learning assistance system can further include a learning style analysis unit that analyzes the user's learning style. The learning style analysis unit analyzes the user's most effective learning method and provides advice tailored to the user's individual learning style. For example, a user who prefers visual learning can be provided with advice that makes extensive use of diagrams and graphs. A user who prefers auditory learning can be provided with advice using audio messages. Furthermore, a user who prefers practical learning can be presented with specific exercises. This makes it possible to provide optimal advice tailored to the user's learning style.

[0110] The text analysis unit can further include a function for monitoring the user's learning progress in real time. For example, the text analysis unit can record how much time the user spends on each problem and evaluate the efficiency of the learning. If the user is having trouble with a particular problem, the text analysis unit can provide additional hints or explanations for that problem. Furthermore, the text analysis unit can automatically select the next problem to be tackled based on the user's learning progress data. This can improve the user's learning efficiency.

[0111] The correct answer determination unit can further create an individual study plan based on the user's study history. For example, the correct answer determination unit can identify questions the user answered incorrectly in the past or areas in which the user is weak, and adjust the study plan based on that. The correct answer determination unit can also monitor the progress of the study plan according to the user's study goals and revise the plan as necessary. Furthermore, the correct answer determination unit can adjust the difficulty level of the study plan to match the user's learning pace. This makes it possible to provide the user with an optimal study plan that meets their individual learning needs.

[0112] The advice generation unit can further include a function for improving the user's motivation to learn. For example, the advice generation unit can provide praise or encouraging messages when the user achieves a goal. The advice generation unit can also provide positive feedback so that the user will have positive feelings about learning. Furthermore, the advice generation unit can also introduce related topics and interesting cases so that the user will become interested in learning. This can improve the user's motivation to learn.

[0113] The providing unit may further include a function for optimizing the user's learning environment. For example, the providing unit may suggest settings for the learning environment so that the user can concentrate on their studies. The providing unit may also select a time period suitable for the user to study and provide advice on that time period. Furthermore, the providing unit may also provide music or environmental sounds that have a relaxing effect so that the user can relax while studying. This may optimize the user's learning environment and improve learning effectiveness.

[0114] The advice generation unit can further include a customization function according to the user's learning style. For example, if the user prefers visual learning, the advice generation unit can provide advice that makes extensive use of diagrams and graphs. If the user prefers auditory learning, the advice generation unit can provide advice using audio messages. Furthermore, if the user prefers practical learning, the advice generation unit can also present specific exercises. This makes it possible to provide optimal advice according to the user's learning style.

[0115] The text analysis unit can also create an individualized study plan based on the user's study history. For example, the text analysis unit can identify questions the user has answered incorrectly in the past or areas of weakness, and adjust the study plan based on that information. The text analysis unit can also monitor the progress of the study plan according to the user's study goals and revise the plan as necessary. Furthermore, the text analysis unit can adjust the difficulty level of the study plan to match the user's learning pace. This makes it possible to provide the user with an optimal study plan that meets their individual learning needs.

[0116] The correct answer determination unit can further include a function for improving the user's motivation to learn. For example, the correct answer determination unit can provide praise or encouraging messages when the user achieves a goal. The correct answer determination unit can also provide positive feedback so that the user has a positive feeling about learning. Furthermore, the correct answer determination unit can also introduce related topics and interesting cases so that the user will become interested in learning. This can improve the user's motivation to learn.

[0117] The advice generation unit can further include a function for monitoring the user's learning progress in real time. For example, the advice generation unit can record how much time the user spends on each problem and evaluate the efficiency of the learning. If the user is having trouble with a particular problem, the advice generation unit can provide additional hints or explanations for that problem. Furthermore, the advice generation unit can automatically select the next problem to tackle based on the user's learning progress data. This can improve the user's learning efficiency.

[0118] The providing unit can further include a customization function according to the user's learning style. For example, if the user prefers visual learning, the providing unit can provide advice that makes extensive use of diagrams and graphs. If the user prefers auditory learning, the providing unit can provide advice using voice messages. Furthermore, if the user prefers practical learning, the providing unit can also present specific exercises. This makes it possible to provide optimal advice according to the user's learning style.

[0119] The processing flow of the second embodiment will be briefly explained below.

[0120] Step 1: The text analysis unit uses OCR technology to capture the print image taken by the user as text. For example, an image of a print taken with a smartphone or tablet can be converted into text data using OCR technology. It can also apply algorithms to recognize handwritten characters with high accuracy. Step 2: The correct answer determination unit determines whether the answer is correct or incorrect based on the imported text. For example, it analyzes the question and answer and determines whether the answer is correct or incorrect. It can also adjust the strictness of the determination depending on the difficulty of the question. Step 3: The advice generator generates advice for the incorrect answers. For example, it analyzes the incorrect calculation process and identifies the part where the mistake occurred. It can also improve the accuracy of advice by referring to the user's past answer history. Step 4: The providing unit provides the generated advice to the user. For example, the advice is provided to the user as a text message or a voice message. The providing unit can also estimate the user's emotions and adjust the way the advice is provided based on the estimated emotions.

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

[0122] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of 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.

[0123] 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.

[0124] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

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

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

[0127] The data processing device 12 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] 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.

[0133] 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.

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

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

[0136] 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.

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

[0138] 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 AI 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.

[0139] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is 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.

[0140] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

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

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

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0149] 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.

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

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

[0152] 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.

[0153] 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.

[0154] 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 AI 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.

[0155] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is 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.

[0156] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

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

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

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

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

[0168] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0169] 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.

[0170] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the 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.

[0171] 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 AI 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.

[0172] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is 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.

[0173] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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).

[0178] 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.

[0179] 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."

[0180] 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.

[0181] 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.

[0182] 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.

[0183] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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, in order to avoid confusion and to 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.

[0191] 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.

[0192] [Explanation of symbols]

[0193] 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 text analysis unit that takes a photograph of the print and captures the text; a correct answer determination unit that determines whether an answer is correct or incorrect based on the text captured by the text analysis unit; an advice generating unit that generates advice for the incorrect answer determined by the correct answer determining unit; a providing unit that provides the advice generated by the advice generating unit. A system characterized by:

2. The text analysis unit Use OCR technology to capture text from a print 2. The system of claim 1.

3. The correct answer determination unit Determine whether the answer is correct or incorrect based on the imported text 2. The system of claim 1.

4. The advice generation unit Generate advice for incorrect answers 2. The system of claim 1.

5. The providing unit Providing generated advice 2. The system of claim 1.

6. The advice generation unit Accumulates multiple correct and incorrect data for each target user age group, predicts trends in points where users are likely to make mistakes, and provides optimal advice 2. The system of claim 1.

7. The text analysis unit Estimate user sentiment and adjust the accuracy of text analysis based on the estimated user sentiment 2. The system of claim 1.

8. The text analysis unit Add a function to automatically correct light reflections and shadows when photographing prints.

2. The system of claim 1.

Images