System

Abstract

An object of a system according to an embodiment is to efficiently study a qualification examination.SOLUTION: A system includes a collection part, an analysis part, a generation part, an answer collection part, a weak field analysis part, and a countermeasure part. The collection unit collects past questions. The analysis unit analyzes the past questions collected by the collection unit. The generation part generates a question based on the examination question based on the analysis result obtained by the analysis part. The answer collecting unit collects answer data of the user. The weak field analysis part analyzes the answer data collected by the answer collection part, and specifies the weak point of the user. The countermeasure unit takes a countermeasure based on the weak point identified by the weak field analysis 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] With conventional technology, studying for qualification exams required time-consuming analysis of past exam questions and identification of weak areas, making it difficult to study efficiently.

[0005] The system according to the embodiment aims to enable efficient study for qualification examinations. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a generation unit, an answer collection unit, a weak area analysis unit, and a countermeasure unit. The collection unit collects past exam questions. The analysis unit analyzes the past exam questions collected by the collection unit. The generation unit generates questions based on the exam questions based on the analysis results obtained by the analysis unit. The answer collection unit collects answer data of the user. The weak area analysis unit analyzes the answer data collected by the answer collection unit and identifies the user's weak areas. The countermeasure unit takes countermeasures based on the weak areas identified by the weak area analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment allows students to study for qualification exams efficiently. [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 qualification exam study support system according to an embodiment of the present invention collects and analyzes past exam questions, generates questions tailored to the actual exam, collects user answer data, identifies weak areas, and provides intensive preparation. The qualification exam study support system collects past exam questions, analyzes them using AI, and generates questions tailored to the actual exam. Next, the system collects user answer data, analyzes the user's weak areas, and provides intensive preparation. For example, the qualification exam study support system collects exam questions from the past five years and generates similar questions by analyzing their trends using AI. Next, the qualification exam study support system collects the user's answer history and uses AI to identify weak areas. For example, if the user frequently makes mistakes on math questions, the AI ​​determines that the user is weak in that area and provides intensive preparation. Furthermore, the qualification exam study support system provides an optimal study plan for each user. The AI ​​analyzes the user's study history and progress and proposes an optimal study plan for each individual user. For example, if the user has many weak points in a particular area, the system provides a study plan focusing on that area. This allows the qualification exam study support system to study for qualification exams easily and efficiently. This allows the qualification exam study support system to study efficiently by letting AI analyze the user's past exam questions and address weak areas. In addition, the personalization function provides a study plan tailored to the user, allowing for efficient study. For example, users can study efficiently in a short amount of time, even in their busy daily lives. In this way, studying for qualification exams becomes easier and more efficient.

[0029] A qualification exam study support system according to an embodiment includes a collection unit, an analysis unit, a generation unit, an answer collection unit, a weak area analysis unit, and a countermeasures unit. The collection unit collects past exam questions. Past exam questions include, but are not limited to, past exam questions for a specific exam or a specific year. The collection unit collects exam questions from the past five years, for example. The collection unit can also collect past exam questions from public databases on the Internet. The collection unit can also collect past exam questions provided by exam organizers. For example, the collection unit automatically collects exam questions from the past five years and stores them in a database. When collecting past exam questions from public databases on the Internet, the collection unit searches using specific keywords and collects related past exam questions. When collecting past exam questions provided by exam organizers, the collection unit automatically imports the provided data and stores it in a database. The analysis unit analyzes the past exam questions collected by the collection unit. The analysis is performed, for example, based on an analysis of question trends and extraction of frequently asked questions, but is not limited to, for example. For example, the analysis unit analyzes the question trends of past exam questions and extracts frequently asked questions. The analysis unit can also evaluate the difficulty of past exam questions and classify the questions. The analysis unit can also analyze the question format of past exam questions and identify question patterns. For example, the analysis unit analyzes the question trends of past exam questions and lists frequently asked questions. When evaluating the difficulty of past exam questions, the analysis unit evaluates the difficulty based on the correct answer rate and answer time. When analyzing the question format of past exam questions, the analysis unit analyzes the question format and question pattern and groups similar questions. The generation unit generates questions that are in line with the actual exam based on the analysis results obtained by the analysis unit. Question generation is performed, for example, based on the difficulty and question format of the questions, but is not limited to such examples. For example, the generation unit generates similar questions based on the question trends of past exam questions. The generation unit can also generate new questions based on frequently asked questions in past exam questions. The generation unit can also generate questions by referring to the question format of past exam questions. For example, the generator analyzes the question trends of past exams and generates similar questions. When generating new questions based on frequently asked questions from past exams, the generator extracts patterns of frequently asked questions and creates new questions based on them.When generating questions by referring to the question format of past questions, the generation unit creates new questions by referring to the format and patterns of past questions. The answer collection unit collects the user's answer data. The answer data includes, for example, but is not limited to, the correct answer rate and answer time. The answer collection unit collects, for example, data on questions answered by the user. The answer collection unit can also collect the user's answer history. The answer collection unit can also select the optimal collection means depending on the user's answering method (audio, text, image, etc.). For example, the answer collection unit automatically collects data on questions answered by the user and stores it in a database. When collecting the user's answer history, the answer collection unit collects the user's answer history based on past answer data. When selecting the optimal collection means depending on the user's answering method, the answer collection unit collects answer data using voice recognition technology, text analysis technology, or image recognition technology. The weak area analysis unit analyzes the answer data collected by the answer collection unit and identifies the user's weak areas. The weak areas are identified, for example, based on an analysis of answer data or an evaluation of the correct answer rate, but are not limited to such examples. For example, the weak area analysis unit analyzes the user's answer data to identify the weak areas. The weak area analysis unit can also evaluate the user's correct answer rate to identify the weak areas. The weak area analysis unit can also identify the weak areas based on the user's answer history. For example, the weak area analysis unit analyzes the user's answer data to identify questions that the user frequently gets wrong. When evaluating the user's correct answer rate, the weak area analysis unit identifies areas with a low correct answer rate as the weak areas. When identifying the weak areas based on the user's answer history, the weak area analysis unit analyzes past answer data to identify the weak areas. The countermeasure unit takes intensive countermeasures based on the weak areas identified by the weak area analysis unit. The intensive countermeasures are taken, for example, based on the provision of additional practice questions or explanatory videos, but are not limited to such examples. For example, the countermeasure unit provides additional practice questions based on the identified weak areas. The countermeasure unit can also provide explanatory videos based on the identified weak areas. The remediation department may also provide a personalized study plan based on the identified weaknesses. For example, the remediation department may provide additional practice questions based on the identified weaknesses.When providing an explanatory video, the countermeasures unit provides an explanatory video related to the identified weak areas. When providing an individual study plan, the countermeasures unit creates an individual study plan based on the identified weak areas and provides it to the user. This allows the qualification exam study support system according to the embodiment to easily and efficiently study for the qualification exam. Some or all of the above-described processing in the countermeasures unit may be performed using, for example, AI, or may be performed without using AI. For example, the countermeasures unit may perform intensive countermeasures using an AI model that inputs the weak areas identified by the weak area analysis unit and outputs intensive countermeasures.

[0030] The collection unit can collect past exam questions. Past exam questions include, but are not limited to, past exam questions for a specific exam or a specific year. The collection unit can collect, for example, exam questions from the past five years. The collection unit can also collect past exam questions from public databases on the Internet. Furthermore, the collection unit can collect past exam questions provided by exam organizers. For example, the collection unit automatically collects exam questions from the past five years and stores them in a database. When collecting past exam questions from public databases on the Internet, the collection unit searches using specific keywords and collects related past exam questions. When collecting past exam questions provided by exam organizers, the collection unit automatically imports the provided data and stores it in a database. In this way, by collecting exam questions from the past five years, the latest exam trends can be understood. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using AI or without AI. For example, the collection unit can collect exam questions from the past five years, input the collected data into a generation AI, and have the generation AI organize the collected data.

[0031] The analysis unit can analyze question patterns in past exams. For example, the analysis unit analyzes question trends in past exams and extracts frequently asked questions. For example, the analysis unit analyzes question trends in past exams and lists frequently asked questions. The analysis unit can also evaluate the difficulty of past exams and classify the questions. For example, the analysis unit evaluates the difficulty of past exams and classifies the questions. The analysis unit can also analyze the question format of past exams and identify question patterns. For example, the analysis unit analyzes the question format of past exams and groups similar questions. By analyzing the question trends and frequently asked questions in past exams, questions that are more suited to the actual exam can be generated. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can analyze question patterns using an AI model that analyzes question trends in past exams and extracts frequently asked questions.

[0032] The generation unit can generate questions based on exam questions. The generation unit, for example, generates similar questions based on question trends in past exams. For example, the generation unit analyzes question trends in past exams and generates similar questions. The generation unit can also generate new questions based on frequently asked questions in past exams. For example, the generation unit generates new questions based on frequently asked questions in past exams. The generation unit can also generate questions by referring to the question format of past exams. For example, the generation unit creates new questions by referring to the question format of past exams. This generates questions that are in line with the actual exam, allowing users to study in an environment that is similar to the exam. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can generate questions by analyzing question trends in past exams and using an AI model that generates similar questions.

[0033] The answer collection unit can collect answer data of the user. The answer data includes, for example, the correct answer rate and the answer time, but is not limited to these examples. The answer collection unit, for example, collects data on questions answered by the user. The answer collection unit can also collect the user's answer history. The answer collection unit can also select the optimal collection means depending on the user's answering method (audio, text, image, etc.). For example, the answer collection unit automatically collects data on questions answered by the user and stores it in a database. When collecting the user's answer history, the answer collection unit collects the user's answer history based on past answer data. When selecting the optimal collection means depending on the user's answering method, the answer collection unit collects answer data using voice recognition technology, text analysis technology, or image recognition technology. Collecting the user's answer history thereby makes it easier to identify weak areas. Some or all of the above-described processing in the answer collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer collection unit can collect user answer data, input the collected data into the generation AI, and have the generation AI analyze the answer data.

[0034] The weak area analysis unit can analyze the user's answer data and identify weak points. Identification of weak areas is performed, for example, based on an analysis of answer data and an evaluation of the correct answer rate, but is not limited to such examples. For example, the weak area analysis unit can analyze the user's answer data and identify weak areas. The weak area analysis unit can also evaluate the user's correct answer rate and identify weak areas. The weak area analysis unit can also identify weak areas based on the user's answer history. For example, the weak area analysis unit analyzes the user's answer data and identify questions that the user frequently gets wrong. When evaluating the user's correct answer rate, the weak area analysis unit identifies areas with a low correct answer rate as weak areas. When identifying weak areas based on the user's answer history, the weak area analysis unit analyzes past answer data and identifies weak areas. This makes it easier to identify weak areas by analyzing the user's answer history. Some or all of the above-described processing in the weak area analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the weak area analysis unit can analyze the user's answer data and identify weak areas using an AI model that identifies weak areas.

[0035] The countermeasure unit can take countermeasures based on the identified weak areas. Countermeasures can be taken, for example, by providing additional practice problems or explanatory videos, but are not limited to these examples. For example, the countermeasure unit can provide additional practice problems based on the identified weak areas. The countermeasure unit can also provide explanatory videos based on the identified weak areas. The countermeasure unit can also provide an individualized study plan based on the identified weak areas. For example, the countermeasure unit provides additional practice problems based on the identified weak areas. When providing explanatory videos, the countermeasure unit provides explanatory videos related to the identified weak areas. When providing an individualized study plan, the countermeasure unit creates an individualized study plan based on the identified weak areas and provides it to the user. This allows the user to efficiently overcome their weaknesses by taking intensive measures based on the identified weak areas. Some or all of the above-described processing by the countermeasure unit may be performed using, for example, AI, or may be performed without using AI. For example, the countermeasure unit can take countermeasures using an AI model that inputs the weak areas identified by the weak area analysis unit and outputs intensive measures.

[0036] The countermeasure unit can provide an appropriate study plan for each user. The provision of the study plan is based on, for example, the user's study history and progress, but is not limited to such examples. For example, the countermeasure unit can analyze the user's study history and provide an optimal study plan. The countermeasure unit can also analyze the user's progress and provide an appropriate study plan. The countermeasure unit can also customize the study plan based on the user's weak areas. For example, the countermeasure unit can analyze the user's study history and provide an optimal study plan. When analyzing the user's progress, the countermeasure unit evaluates the user's study progress and provides an appropriate study plan. When customizing the study plan based on the user's weak areas, the countermeasure unit provides a study plan that focuses on the user's weak areas. This provides an optimal study plan for each user, enabling efficient learning tailored to each individual user. Some or all of the above-described processing by the countermeasure unit may be performed using, for example, AI, or may be performed without AI. For example, the countermeasure unit can provide a study plan using an AI model that inputs the user's study history and progress and outputs an optimal study plan.

[0037] When collecting past exam questions, the collection unit can adjust the range of questions collected based on the content and format of the exam. For example, the collection unit prioritizes collecting difficult exam questions to test the user's ability. For example, the collection unit prioritizes collecting difficult exam questions. The collection unit can also collect questions with different question formats in a balanced manner to enable the user to respond to a variety of questions. For example, the collection unit collects questions with different question formats in a balanced manner. The collection unit can also expand the range of questions collected depending on the difficulty of the exam to expand the user's learning range. For example, the collection unit expands the range of questions collected depending on the difficulty of the exam. In this way, the user's learning range can be expanded by adjusting the range of questions collected based on the difficulty of the exam and the question format. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input the content and format of the exam to a generation AI and cause the generation AI to adjust the range of questions collected.

[0038] When collecting past exam questions, the collection unit can apply different collection algorithms for each exam field. For example, the collection unit may mainly collect calculation questions for mathematics questions, emphasizing the speed of answering. For example, the collection unit may mainly collect calculation questions for mathematics questions. The collection unit may also mainly collect reading comprehension questions for English questions to enhance comprehension. For example, the collection unit may mainly collect reading comprehension questions for English questions. The collection unit may also mainly collect experimental questions for science questions to cultivate practical knowledge. For example, the collection unit may mainly collect experimental questions for science questions. In this way, by applying different collection algorithms for each exam field, questions specialized for each field can be collected. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit may input different collection algorithms for each exam field into the generation AI and cause the generation AI to apply the collection algorithms.

[0039] When collecting past questions, the collection unit can improve the accuracy of the collection by referring to the user's learning history. The collection unit, for example, analyzes trends in questions the user has solved in the past and collects similar questions. For example, the collection unit analyzes trends in questions the user has solved in the past and collects similar questions. The collection unit can also collect questions of an appropriate level of difficulty according to the user's learning progress. For example, the collection unit collects questions of an appropriate level of difficulty according to the user's learning progress. The collection unit can also collect balanced questions by taking into account the user's strengths and weaknesses. For example, the collection unit collects balanced questions by taking into account the user's strengths and weaknesses. By referring to the user's learning history, the accuracy of the collection can be improved and more appropriate questions can be provided. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's learning history into a generation AI and cause the generation AI to improve the accuracy of the collection.

[0040] When collecting past exam questions, the collection unit can adjust the collection range based on the region and year of the exam. For example, the collection unit collects questions that frequently appear in a specific region to address regional trends. For example, the collection unit collects questions that frequently appear in a specific region. The collection unit can also collect questions from the past few years to understand the latest question trends. For example, the collection unit collects questions from the past few years. The collection unit can also collect appropriate questions taking into account differences in exam formats between regions. For example, the collection unit collects appropriate questions taking into account differences in exam formats between regions. In this way, regional trends can be addressed by adjusting the collection range based on the region and year of the exam. Some or all of the above-mentioned processing in the collection unit may be performed using, or without, AI. For example, the collection unit can input the region and year of the exam into the generation AI and have the generation AI adjust the collection range.

[0041] When collecting past exam questions, the collection unit can improve the accuracy of the collection by referring to exam-related literature. The collection unit, for example, refers to academic papers related to the exam to understand question trends. For example, the collection unit refers to academic papers related to the exam. The collection unit can also refer to official exam guidelines to collect questions that capture important points. For example, the collection unit refers to official exam guidelines. The collection unit can also refer to books related to the exam to collect questions that cover a wide range of knowledge. For example, the collection unit refers to books related to the exam. By referring to exam-related literature, the accuracy of the collection can be improved and more appropriate questions can be provided. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using AI, or can be performed without AI. For example, the collection unit can input exam-related literature into a generation AI and have the generation AI improve the accuracy of the collection.

[0042] When collecting past questions, the collection unit can take into account the tendencies of test setters. For example, the collection unit analyzes the tendencies of questions frequently asked by a specific test setter and collects similar questions. For example, the collection unit analyzes the tendencies of questions frequently asked by a specific test setter. The collection unit can also refer to the test setter's past question-setting history to understand the question-setting tendencies. For example, the collection unit refers to the test setter's past question-setting history. The collection unit can also collect related questions based on the test setter's field of expertise. For example, the collection unit collects related questions based on the test setter's field of expertise. In this way, by taking into account the tendencies of the test setter, questions that are in line with the question-setting tendencies can be collected. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the tendencies of the test setter into the generation AI and have the generation AI adjust the collection.

[0043] During analysis, the analysis unit can adjust the level of detail of the analysis based on the frequency of questions in past exams. The analysis unit, for example, performs a detailed analysis of frequently asked questions to understand question trends. For example, the analysis unit performs a detailed analysis of frequently asked questions. The analysis unit can also perform a concise analysis of questions that appear less frequently to promote efficient learning. For example, the analysis unit performs a concise analysis of questions that appear less frequently. The analysis unit can also adjust the level of detail of the analysis according to the frequency of questions to provide balanced learning. For example, the analysis unit adjusts the level of detail of the analysis according to the frequency of questions. As a result, efficient learning is possible by adjusting the level of detail of the analysis based on the frequency of questions in past exams. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the frequency of questions in past exams into a generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0044] During analysis, the analysis unit can apply different analysis algorithms depending on the test category. For example, the analysis unit applies a calculation algorithm to math questions to analyze the accuracy of the answers. For example, the analysis unit applies a calculation algorithm to math questions. The analysis unit can also apply a reading comprehension algorithm to English questions to analyze the level of comprehension. For example, the analysis unit applies a reading comprehension algorithm to English questions. The analysis unit can also apply an experimental algorithm to science questions to analyze practical knowledge. For example, the analysis unit applies an experimental algorithm to science questions. In this way, by applying different analysis algorithms depending on the test category, analysis specialized for each category is possible. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input an analysis algorithm depending on the test category into the generation AI and cause the generation AI to apply the analysis algorithm.

[0045] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis unit improves the analysis accuracy of similar questions based on the user's past analysis results. For example, the analysis unit improves the analysis accuracy of similar questions based on the user's past analysis results. The analysis unit can also select an appropriate analysis method according to the user's learning progress. For example, the analysis unit selects an appropriate analysis method according to the user's learning progress. The analysis unit can also perform a balanced analysis by taking into account the user's strengths and weaknesses. For example, the analysis unit performs a balanced analysis by taking into account the user's strengths and weaknesses. By referring to the user's past analysis results, the accuracy of the analysis is improved, enabling more appropriate learning. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's past analysis results into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0046] During analysis, the analysis unit can determine the analysis priority based on the submission date of past exam questions. For example, the analysis unit prioritizes analysis of the most recent past exam questions to understand the latest exam question trends. For example, the analysis unit prioritizes analysis of the most recent past exam questions. The analysis unit can also analyze questions from the past few years in a balanced manner to cover a wide range of knowledge. For example, the analysis unit analyzes questions from the past few years in a balanced manner. The analysis unit can also adjust the analysis priority based on the submission date to provide efficient learning. For example, the analysis unit adjusts the analysis priority based on the submission date. In this way, by determining the analysis priority based on the submission date of past exam questions, the latest exam question trends can be understood. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the submission date of past exam questions to the generation AI and have the generation AI determine the analysis priority.

[0047] During analysis, the analysis unit can adjust the order of analysis based on the relevance of past questions. The analysis unit, for example, groups similar questions to perform the analysis efficiently. For example, the analysis unit groups similar questions. The analysis unit can also prioritize analyzing highly relevant questions to grasp question trends. For example, the analysis unit prioritizes analyzing highly relevant questions. The analysis unit can also adjust the order of analysis according to the relevance to provide efficient learning. For example, the analysis unit adjusts the order of analysis according to the relevance. As a result, adjusting the order of analysis based on the relevance of past questions enables efficient learning. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the relevance of past questions to a generation AI and have the generation AI adjust the order of analysis.

[0048] During analysis, the analysis unit can adjust the use of technical terminology in the analysis according to the user's level of expertise. For example, the analysis unit uses simple terminology for beginners to provide an analysis that is easy to understand. For example, the analysis unit uses simple terminology for beginners. The analysis unit can also use appropriate technical terminology for intermediate users to deepen understanding. For example, the analysis unit uses appropriate technical terminology for intermediate users. The analysis unit can also use advanced technical terminology for advanced users to provide a detailed analysis. For example, the analysis unit uses advanced technical terminology for advanced users. In this way, by adjusting the use of technical terminology according to the user's level of expertise, it is possible to provide an analysis result that is easy to understand. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's level of expertise into the generation AI and cause the generation AI to adjust the use of technical terminology.

[0049] When generating questions, the generation unit can adjust the level of detail of the generated questions based on the frequency of questions in past exams. For example, the generation unit generates questions that include detailed explanations for frequently-asked questions. For example, the generation unit generates questions that include detailed explanations for frequently-asked questions. The generation unit can also generate questions that include concise explanations for questions that are asked less frequently. For example, the generation unit generates questions that include concise explanations for questions that are asked less frequently. The generation unit can also adjust the level of detail of the generated questions based on the frequency of questions to provide balanced questions. For example, the generation unit adjusts the level of detail of the generated questions based on the frequency of questions asked. This enables efficient learning by adjusting the level of detail of the generated questions based on the frequency of questions asked in past exams. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the frequency of questions in past exams into the generation AI and cause the generation AI to adjust the level of detail of the generated questions.

[0050] When generating questions, the generation unit can apply different generation algorithms depending on the test category. For example, the generation unit applies a calculation algorithm to math questions, emphasizing the accuracy of the answers. For example, the generation unit applies a calculation algorithm to math questions. The generation unit can also apply a reading comprehension algorithm to English questions, emphasizing the level of understanding. For example, the generation unit applies a reading comprehension algorithm to English questions. The generation unit can also apply an experimental algorithm to science questions, emphasizing practical knowledge. For example, the generation unit applies an experimental algorithm to science questions. In this way, by applying different generation algorithms depending on the test category, questions specialized for each category can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input a generation algorithm according to the test category into the generation AI and cause the generation AI to apply the generation algorithm.

[0051] When generating questions, the generation unit can improve the accuracy of the generation by referring to the user's past generation results. For example, the generation unit improves the accuracy of generating similar questions based on the user's past generation results. For example, the generation unit improves the accuracy of generating similar questions based on the user's past generation results. The generation unit can also select an appropriate generation method according to the user's learning progress. For example, the generation unit selects an appropriate generation method according to the user's learning progress. The generation unit can also generate balanced questions by taking into account the user's strengths and weaknesses. For example, the generation unit generates balanced questions by taking into account the user's strengths and weaknesses. By referring to the user's past generation results, the accuracy of generation can be improved and more appropriate questions can be provided. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's past generation results into the generation AI and cause the generation AI to improve the accuracy of generation.

[0052] When generating questions, the generation unit can determine the generation priority based on the submission date of past questions. For example, the generation unit prioritizes generating the most recent past questions to grasp the latest question trends. For example, the generation unit prioritizes generating the most recent past questions. The generation unit can also generate questions from the past few years in a balanced manner to cover a wide range of knowledge. For example, the generation unit generates questions from the past few years in a balanced manner. The generation unit can also adjust the generation priority according to the submission date to provide efficient learning. For example, the generation unit adjusts the generation priority according to the submission date. In this way, by determining the generation priority based on the submission date of past questions, the latest question trends can be grasped. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the submission date of past questions into the generation AI and have the generation AI determine the generation priority.

[0053] When generating questions, the generation unit can adjust the order of generation based on the relevance of past questions. The generation unit, for example, groups similar questions to generate questions efficiently. For example, the generation unit groups similar questions. The generation unit can also prioritize generating highly relevant questions to grasp question trends. For example, the generation unit prioritizes generating highly relevant questions. The generation unit can also adjust the order of generation according to the relevance to provide efficient learning. For example, the generation unit adjusts the order of generation according to the relevance. As a result, adjusting the order of generation based on the relevance of past questions enables efficient learning. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the relevance of past questions into the generation AI and cause the generation AI to adjust the order of generation.

[0054] When generating questions, the generation unit can adjust the use of technical terminology in the generation according to the user's level of expertise. For example, the generation unit uses simple terminology for beginners to generate questions that are easy to understand. For example, the generation unit uses simple terminology for beginners. The generation unit can also use appropriate technical terminology for intermediate learners to deepen understanding. For example, the generation unit uses appropriate technical terminology for intermediate learners. The generation unit can also generate detailed questions using advanced technical terminology for advanced learners. For example, the generation unit uses advanced technical terminology for advanced learners. In this way, by adjusting the use of technical terminology according to the user's level of expertise, it is possible to provide questions that are easy to understand. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's level of expertise into the generation AI and cause the generation AI to adjust the use of technical terminology.

[0055] When collecting answer data, the answer collection unit can select the optimal collection means depending on the user's answering method. For example, when the user answers by voice, the answer collection unit collects answer data using voice recognition technology. For example, when the user answers by voice, the answer collection unit collects answer data using voice recognition technology. Furthermore, when the user answers by text, the answer collection unit can also collect answer data using text analysis technology. For example, when the user answers by text, the answer collection unit collects answer data using text analysis technology. Furthermore, when the user answers by image, the answer collection unit can also collect answer data using image recognition technology. For example, when the user answers by image, the answer collection unit collects answer data using image recognition technology. This enables efficient data collection by selecting the optimal collection means depending on the user's answering method. Some or all of the above-mentioned processing in the answer collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer collection unit can input the user's answer method into the generation AI and have the generation AI select the optimal collection means.

[0056] When collecting answer data, the answer collection unit can improve the accuracy of the collection by referring to the user's past answer history. The answer collection unit, for example, collects similar answer data based on the user's past answer history. For example, the answer collection unit collects similar answer data based on the user's past answer history. The answer collection unit can also collect appropriate answer data according to the user's learning progress. For example, the answer collection unit collects appropriate answer data according to the user's learning progress. The answer collection unit can also collect balanced answer data by taking into account the user's strengths and weaknesses. For example, the answer collection unit collects balanced answer data by taking into account the user's strengths and weaknesses. By referring to the user's past answer history, the accuracy of the collection can be improved and more appropriate data can be provided. Some or all of the above-mentioned processing in the answer collection unit may be performed, for example, using AI or without AI. For example, the answer collection unit can input the user's past answer history into the generation AI and cause the generation AI to improve the accuracy of collection.

[0057] When collecting answer data, the answer collection unit can adjust the collection range based on the user's current learning situation. The answer collection unit, for example, collects an appropriate range of answer data according to the user's learning progress. For example, the answer collection unit collects an appropriate range of answer data according to the user's learning progress. The answer collection unit can also collect balanced answer data taking into account the user's strengths and weaknesses. For example, the answer collection unit collects balanced answer data taking into account the user's strengths and weaknesses. The answer collection unit can also adjust the collection range based on the user's current learning situation to provide efficient learning. For example, the answer collection unit adjusts the collection range based on the user's current learning situation. This enables efficient learning by adjusting the collection range based on the user's current learning situation. Some or all of the above-mentioned processing in the answer collection unit may be performed using AI, for example, or may be performed without using AI. For example, the answer collection unit can input the user's current learning situation to the generation AI and cause the generation AI to adjust the collection range.

[0058] When collecting answer data, the answer collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. For example, when the user is in a specific area, the answer collection unit prioritizes collecting answer data related to that area. For example, when the user is in a specific area, the answer collection unit prioritizes collecting answer data related to that area. The answer collection unit can also collect highly relevant answer data based on the user's geographical location information. For example, the answer collection unit collects highly relevant answer data based on the user's geographical location information. The answer collection unit can also collect appropriate answer data by taking into account the user's geographical location information. For example, the answer collection unit collects appropriate answer data by taking into account the user's geographical location information. In this way, highly relevant data can be preferentially collected by taking into account the user's geographical location information. Some or all of the above-described processing in the answer collection unit may be performed using AI, for example, or may be performed without using AI. For example, the answer collection unit can input the user's geographical location information to the generation AI and cause the generation AI to collect highly relevant data.

[0059] The answer collection unit can analyze the user's social media activities and collect related data when collecting answer data. The answer collection unit, for example, analyzes the user's social media posts and collects related answer data. For example, the answer collection unit analyzes the user's social media posts and collects related answer data. The answer collection unit can also collect related answer data by referring to the activities of the user's friends on social media. For example, the answer collection unit collects related answer data by referring to the activities of the user's friends on social media. The answer collection unit can also collect related answer data based on the user's check-in information on social media. For example, the answer collection unit collects related answer data based on the user's check-in information on social media. In this way, related data can be collected by analyzing the user's social media activities. Some or all of the above-mentioned processing in the answer collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer collection unit can input the user's social media activities into the generation AI and cause the generation AI to collect related data.

[0060] When collecting answer data, the answer collection unit can customize the collection method by reflecting the user's past feedback. The answer collection unit customizes the collection method based on, for example, the user's past feedback to collect efficient answer data. For example, the answer collection unit customizes the collection method based on the user's past feedback. The answer collection unit can also select an appropriate collection method by reflecting the user's feedback. For example, the answer collection unit selects an appropriate collection method by reflecting the user's feedback. The answer collection unit can also adjust the collection method by taking the user's past feedback into account to provide efficient learning. For example, the answer collection unit adjusts the collection method by taking the user's past feedback into account. This enables the collection method to be customized by reflecting the user's past feedback, enabling efficient data collection. Some or all of the above-described processing in the answer collection unit may be performed using, or without, AI. For example, the answer collection unit can input the user's past feedback into the generation AI and cause the generation AI to customize the collection method.

[0061] When analyzing weak areas, the weak area analysis unit can adjust the level of detail of the analysis based on the user's answer frequency. The weak area analysis unit, for example, performs a detailed analysis of questions that are frequently answered incorrectly to identify weak areas. For example, the weak area analysis unit performs a detailed analysis of questions that are frequently answered incorrectly. The weak area analysis unit can also perform a concise analysis of questions that are infrequently answered to promote efficient learning. For example, the weak area analysis unit performs a concise analysis of questions that are infrequently answered. The weak area analysis unit can also adjust the level of detail of the analysis according to the answer frequency to provide balanced learning. For example, the weak area analysis unit adjusts the level of detail of the analysis according to the answer frequency. This enables efficient learning by adjusting the level of detail of the analysis based on the user's answer frequency. Some or all of the above-mentioned processing in the weak area analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the weak area analysis unit can input the user's answer frequency to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0062] When analyzing weak areas, the weak area analysis unit can apply different analysis algorithms depending on the category of the test. For example, the weak area analysis unit applies a calculation algorithm to math questions to analyze the accuracy of the answers. For example, the weak area analysis unit applies a calculation algorithm to math questions. The weak area analysis unit can also apply a reading comprehension algorithm to English questions to analyze the level of comprehension. For example, the weak area analysis unit applies a reading comprehension algorithm to English questions. The weak area analysis unit can also apply an experimental algorithm to science questions to analyze practical knowledge. For example, the weak area analysis unit applies an experimental algorithm to science questions. In this way, by applying different analysis algorithms depending on the category of the test, analysis specialized for each category is possible. Some or all of the above-mentioned processing in the weak area analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the weak area analysis unit can input an analysis algorithm depending on the category of the test to the generation AI and cause the generation AI to apply the analysis algorithm.

[0063] When analyzing weak areas, the weak area analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The weak area analysis unit, for example, improves the analysis accuracy of similar questions based on the user's past analysis results. For example, the weak area analysis unit improves the analysis accuracy of similar questions based on the user's past analysis results. The weak area analysis unit can also select an appropriate analysis method depending on the user's learning progress. For example, the weak area analysis unit selects an appropriate analysis method depending on the user's learning progress. The weak area analysis unit can also perform a balanced analysis by taking into account the user's strong and weak areas. For example, the weak area analysis unit performs a balanced analysis by taking into account the user's strong and weak areas. By referring to the user's past analysis results, the accuracy of the analysis can be improved, enabling more appropriate learning. Some or all of the above-mentioned processing in the weak area analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the weak area analysis unit can input the user's past analysis results into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0064] When analyzing weak areas, the weak area analysis unit can determine the analysis priority based on the time of the user's answer. The weak area analysis unit, for example, prioritizes analysis of the most recent answer data to identify the most recent weak area. For example, the weak area analysis unit prioritizes analysis of the most recent answer data. The weak area analysis unit can also analyze answer data from the past few years in a balanced manner to cover a wide range of knowledge. For example, the weak area analysis unit analyzes answer data from the past few years in a balanced manner. The weak area analysis unit can also adjust the analysis priority according to the time of the answer to provide efficient learning. For example, the weak area analysis unit adjusts the analysis priority according to the time of the answer. In this way, the most recent weak area can be identified by determining the analysis priority based on the time of the user's answer. Some or all of the above-mentioned processing in the weak area analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the weak area analysis unit can input the time of the user's answer into the generation AI and have the generation AI determine the analysis priority.

[0065] The weak area analysis unit can improve the accuracy of the analysis by referring to the user's knowledge of related fields when analyzing the weak areas. The weak area analysis unit, for example, improves the analysis accuracy of the weak areas based on the user's knowledge of related fields. For example, the weak area analysis unit improves the analysis accuracy of the weak areas based on the user's knowledge of related fields. The weak area analysis unit can also select an appropriate analysis method depending on the user's learning progress. For example, the weak area analysis unit selects an appropriate analysis method depending on the user's learning progress. The weak area analysis unit can also perform a balanced analysis by taking into account the user's strong and weak areas. For example, the weak area analysis unit performs a balanced analysis by taking into account the user's strong and weak areas. By referring to the user's knowledge of related fields, the accuracy of the analysis is improved, enabling more appropriate learning. Some or all of the above-mentioned processing in the weak area analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the weak area analysis unit can input the user's knowledge of related fields into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0066] When analyzing weak areas, the weak area analysis unit can adjust the analysis method according to the user's learning style. For example, if the user prefers visual learning, the weak area analysis unit provides an analysis using graphs and diagrams. For example, if the user prefers visual learning, the weak area analysis unit provides an analysis using graphs and diagrams. Furthermore, if the user prefers auditory learning, the weak area analysis unit can provide an analysis including audio commentary. For example, if the user prefers auditory learning, the weak area analysis unit provides an analysis including audio commentary. Furthermore, if the user prefers hands-on learning, the weak area analysis unit can provide an analysis using real-life examples. For example, if the user prefers hands-on learning, the weak area analysis unit provides an analysis using real-life examples. This enables efficient learning by adjusting the analysis method according to the user's learning style. Some or all of the above-described processing in the weak area analysis unit may be performed using AI, for example, or may be performed without AI. For example, the weak area analysis unit can input the user's learning style into the generation AI and cause the generation AI to adjust the analysis method.

[0067] When taking countermeasures, the countermeasure unit can analyze the user's past learning history and select the optimal countermeasure. The countermeasure unit, for example, selects an effective countermeasure based on the user's past learning history. For example, the countermeasure unit selects an effective countermeasure based on the user's past learning history. The countermeasure unit can also select an appropriate countermeasure according to the user's learning progress. For example, the countermeasure unit selects an appropriate countermeasure according to the user's learning progress. The countermeasure unit can also select a balanced countermeasure taking into account the user's strengths and weaknesses. For example, the countermeasure unit selects a balanced countermeasure taking into account the user's strengths and weaknesses. This allows the user's past learning history to be analyzed to select the optimal countermeasure, enabling efficient learning. Some or all of the above-described processing in the countermeasure unit may be performed using, or without, AI. For example, the countermeasure unit can input the user's past learning history into a generation AI and have the generation AI select the optimal countermeasure.

[0068] When taking countermeasures, the countermeasure unit can customize the countermeasure measures based on the user's current learning situation. The countermeasure unit, for example, customizes appropriate countermeasure measures according to the user's learning progress. For example, the countermeasure unit customizes appropriate countermeasure measures according to the user's learning progress. The countermeasure unit can also customize balanced countermeasure measures taking into account the user's strengths and weaknesses. For example, the countermeasure unit customizes balanced countermeasures taking into account the user's strengths and weaknesses. The countermeasure unit can also adjust the countermeasure measures based on the user's current learning situation to provide efficient learning. For example, the countermeasure unit adjusts the countermeasure measures based on the user's current learning situation. This enables efficient learning by customizing the countermeasure measures based on the user's current learning situation. Some or all of the above-mentioned processing in the countermeasure unit may be performed using, or without, AI. For example, the countermeasure unit can input the user's current learning situation into the generation AI and cause the generation AI to customize the countermeasure measures.

[0069] The countermeasure unit can improve the countermeasure method by reflecting user feedback when taking countermeasures. For example, the countermeasure unit improves the countermeasure method based on user feedback and provides efficient learning. For example, the countermeasure unit improves the countermeasure method based on user feedback. The countermeasure unit can also select an appropriate countermeasure method by reflecting user feedback. For example, the countermeasure unit selects an appropriate countermeasure method by reflecting user feedback. The countermeasure unit can also adjust the countermeasure method by taking into account the user's past feedback and provide efficient learning. For example, the countermeasure unit adjusts the countermeasure method by taking into account the user's past feedback. In this way, the countermeasure method is improved by reflecting user feedback, enabling efficient learning. Some or all of the above-mentioned processing in the countermeasure unit may be performed using AI, for example, or may be performed without using AI. For example, the countermeasure unit can input user feedback into a generation AI and cause the generation AI to improve the countermeasure method.

[0070] When taking countermeasures, the countermeasure unit can select the optimal countermeasure method by taking into account the user's geographical location information. For example, if the user is in a specific area, the countermeasure unit provides a countermeasure method related to that area. For example, if the user is in a specific area, the countermeasure unit provides a countermeasure method related to that area. The countermeasure unit can also provide a highly relevant countermeasure method based on the user's geographical location information. For example, the countermeasure unit provides a highly relevant countermeasure method based on the user's geographical location information. The countermeasure unit can also provide an appropriate countermeasure method by taking into account the user's geographical location information. For example, the countermeasure unit provides an appropriate countermeasure method by taking into account the user's geographical location information. This enables the optimal countermeasure method to be selected and efficient learning to be achieved by taking into account the user's geographical location information. Some or all of the above-described processing in the countermeasure unit may be performed using, or without, AI. For example, the countermeasure unit can input the user's geographical location information into the generation AI and cause the generation AI to select the optimal countermeasure method.

[0071] When taking countermeasures, the countermeasure unit can analyze the user's social media activity and suggest countermeasures. The countermeasure unit, for example, analyzes the content of the user's social media posts and suggests relevant countermeasures. For example, the countermeasure unit analyzes the content of the user's social media posts and suggests relevant countermeasures. The countermeasure unit can also suggest relevant countermeasures by referring to the activities of the user's friends on social media. For example, the countermeasure unit can suggest relevant countermeasures by referring to the activities of the user's friends on social media. The countermeasure unit can also suggest relevant countermeasures based on the user's check-in information on social media. For example, the countermeasure unit suggests relevant countermeasures based on the user's check-in information on social media. In this way, relevant countermeasures can be suggested by analyzing the user's social media activity. Some or all of the above-mentioned processing in the countermeasure unit may be performed using, for example, AI, or may be performed without using AI. For example, the countermeasure unit can input the user's social media activity into a generation AI and have the generation AI execute the suggestion of countermeasures.

[0072] When taking countermeasures, the countermeasure unit can customize the countermeasure method by reflecting the user's past feedback. The countermeasure unit, for example, customizes the countermeasure method based on the user's past feedback to provide efficient learning. For example, the countermeasure unit customizes the countermeasure method based on the user's past feedback. The countermeasure unit can also select an appropriate countermeasure method by reflecting the user's feedback. For example, the countermeasure unit selects an appropriate countermeasure method by reflecting the user's feedback. The countermeasure unit can also adjust the countermeasure method by taking the user's past feedback into account to provide efficient learning. For example, the countermeasure unit adjusts the countermeasure method by taking the user's past feedback into account. In this way, the countermeasure method can be customized by reflecting the user's past feedback, enabling efficient learning. Some or all of the above-described processing in the countermeasure unit may be performed using, or without, AI. For example, the countermeasure unit can input the user's past feedback into a generation AI and cause the generation AI to customize the countermeasure method.

[0073] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0074] The qualification exam study support system may further include an environment monitoring unit that monitors the user's study environment. The environment monitoring unit monitors the user's study environment (e.g., lighting, noise level, temperature, etc.) in real time and provides advice to provide an optimal study environment. For example, if the lighting is dim, the environment monitoring unit may suggest to the user to turn up the lights. Also, if the noise level is high, the environment monitoring unit may suggest to the user to move to a quieter place. Furthermore, if the temperature is inappropriate, the environment monitoring unit may suggest to the user to adjust the temperature appropriately. This allows the user to study efficiently in an optimal study environment.

[0075] The collection unit can collect the latest research papers and articles related to a specific field based on the user's learning history. For example, if the user is interested in a specific field, the collection unit can collect the latest research papers related to that field and provide them to the user. The collection unit can also collect research papers of appropriate difficulty level according to the user's learning progress. Furthermore, the collection unit can collect balanced research papers taking into account the user's strong and weak areas. This allows the user to understand the latest research trends and gain deeper knowledge.

[0076] The generator can customize the question format according to the user's learning style. For example, for a user who prefers visual learning, questions that make extensive use of diagrams and graphs can be generated. For a user who prefers auditory learning, questions that include audio commentary can be generated. Furthermore, for a user who prefers practical learning, questions that use real-life examples can be generated. This allows for efficient learning by providing questions that suit the user's learning style.

[0077] The weak area analysis unit can provide additional learning resources related to a specific area based on the user's learning history. For example, if the user has many weak points in a specific area, the weak area analysis unit can provide additional practice questions or explanatory videos related to that area. It can also provide learning resources of an appropriate level of difficulty according to the user's learning progress. Furthermore, it can provide balanced learning resources taking into account the user's strong and weak areas. This allows the user to efficiently overcome their weak areas.

[0078] The countermeasures unit can customize a study plan for a specific subject based on the user's study history. For example, if the user has many weak points in a specific subject, the countermeasures unit can provide a study plan that focuses on that subject. The countermeasures unit can also provide a study plan with an appropriate level of difficulty according to the user's study progress. Furthermore, the countermeasures unit can provide a balanced study plan that takes into account the user's strong and weak subjects. This allows the user to study efficiently.

[0079] The generator can customize the method of generating questions related to a specific field based on the user's learning history. For example, if the user has many questions in a specific field that they are weak at, the generator can generate questions that focus on that field. It can also generate questions of an appropriate level of difficulty according to the user's learning progress. Furthermore, it can generate balanced questions taking into account the user's strong and weak fields. This allows the user to study efficiently.

[0080] The processing flow of the first embodiment will be briefly explained below.

[0081] Step 1: The collection department collects past exam questions. Past exam questions include those for a specific exam or a specific year. The collection department collects exam questions from the past five years and can collect past exam questions from public databases on the Internet or provided by the exam organizer. The collected past exam questions are stored in a database. Step 2: The analysis unit analyzes the past exam questions collected by the collection unit. The analysis is based on the analysis of question trends, extraction of frequently asked questions, evaluation of difficulty, classification of questions, and analysis of question format. This identifies the question trends, frequently asked questions, difficulty level, and question format of past exam questions. Step 3: The generator generates questions based on the analysis results obtained by the analyzer, and is designed to fit the actual exam. Question generation is based on the difficulty and format of the questions, and new questions are created with reference to past exam trends, frequently asked questions, and question formats. Step 4: The answer collection unit collects the user's answer data. The answer data includes the correct answer rate, answer time, etc., and data on the questions answered by the user and the answer history are collected. The answer collection unit can collect the answer data using voice recognition technology, text analysis technology, and image recognition technology. Step 5: The weak area analysis unit analyzes the answer data collected by the answer collection unit and identifies the user's weak areas. The weak areas are identified based on the analysis of the answer data, evaluation of the correct answer rate, and analysis of the answer history. This identifies questions that the user frequently gets wrong and areas where the correct answer rate is low. Step 6: The countermeasures unit implements intensive countermeasures based on the weak areas identified by the weak area analysis unit. The intensive countermeasures are implemented by providing additional practice problems and explanatory videos, and providing an individual study plan. The countermeasures unit provides explanatory videos and practice problems related to the identified weak areas, and creates an individual study plan and provides it to the user.

[0082] (Example 2) A qualification exam study support system according to an embodiment of the present invention collects and analyzes past exam questions, generates questions tailored to the actual exam, collects user answer data, identifies weak areas, and provides intensive preparation. The qualification exam study support system collects past exam questions, analyzes them using AI, and generates questions tailored to the actual exam. Next, the system collects user answer data, analyzes the user's weak areas, and provides intensive preparation. For example, the qualification exam study support system collects exam questions from the past five years and generates similar questions by analyzing their trends using AI. Next, the qualification exam study support system collects the user's answer history and uses AI to identify weak areas. For example, if the user frequently makes mistakes on math questions, the AI ​​determines that the user is weak in that area and provides intensive preparation. Furthermore, the qualification exam study support system provides an optimal study plan for each user. The AI ​​analyzes the user's study history and progress and proposes an optimal study plan for each individual user. For example, if the user has many weak points in a particular area, the system provides a study plan focusing on that area. This allows the qualification exam study support system to study for qualification exams easily and efficiently. This allows the qualification exam study support system to study efficiently by letting AI analyze the user's past exam questions and address weak areas. In addition, the personalization function provides a study plan tailored to the user, allowing for efficient study. For example, users can study efficiently in a short amount of time, even in their busy daily lives. In this way, studying for qualification exams becomes easier and more efficient.

[0083] A qualification exam study support system according to an embodiment includes a collection unit, an analysis unit, a generation unit, an answer collection unit, a weak area analysis unit, and a countermeasures unit. The collection unit collects past exam questions. Past exam questions include, but are not limited to, past exam questions for a specific exam or a specific year. The collection unit collects exam questions from the past five years, for example. The collection unit can also collect past exam questions from public databases on the Internet. The collection unit can also collect past exam questions provided by exam organizers. For example, the collection unit automatically collects exam questions from the past five years and stores them in a database. When collecting past exam questions from public databases on the Internet, the collection unit searches using specific keywords and collects related past exam questions. When collecting past exam questions provided by exam organizers, the collection unit automatically imports the provided data and stores it in a database. The analysis unit analyzes the past exam questions collected by the collection unit. The analysis is performed, for example, based on an analysis of question trends and extraction of frequently asked questions, but is not limited to, for example. For example, the analysis unit analyzes the question trends of past exam questions and extracts frequently asked questions. The analysis unit can also evaluate the difficulty of past exam questions and classify the questions. The analysis unit can also analyze the question format of past exam questions and identify question patterns. For example, the analysis unit analyzes the question trends of past exam questions and lists frequently asked questions. When evaluating the difficulty of past exam questions, the analysis unit evaluates the difficulty based on the correct answer rate and answer time. When analyzing the question format of past exam questions, the analysis unit analyzes the question format and question pattern and groups similar questions. The generation unit generates questions that are in line with the actual exam based on the analysis results obtained by the analysis unit. Question generation is performed, for example, based on the difficulty and question format of the questions, but is not limited to such examples. For example, the generation unit generates similar questions based on the question trends of past exam questions. The generation unit can also generate new questions based on frequently asked questions in past exam questions. The generation unit can also generate questions by referring to the question format of past exam questions. For example, the generator analyzes the question trends of past exams and generates similar questions. When generating new questions based on frequently asked questions from past exams, the generator extracts patterns of frequently asked questions and creates new questions based on them.When generating questions by referring to the question format of past questions, the generation unit creates new questions by referring to the format and patterns of past questions. The answer collection unit collects the user's answer data. The answer data includes, for example, but is not limited to, the correct answer rate and answer time. The answer collection unit collects, for example, data on questions answered by the user. The answer collection unit can also collect the user's answer history. The answer collection unit can also select the optimal collection means depending on the user's answering method (audio, text, image, etc.). For example, the answer collection unit automatically collects data on questions answered by the user and stores it in a database. When collecting the user's answer history, the answer collection unit collects the user's answer history based on past answer data. When selecting the optimal collection means depending on the user's answering method, the answer collection unit collects answer data using voice recognition technology, text analysis technology, or image recognition technology. The weak area analysis unit analyzes the answer data collected by the answer collection unit and identifies the user's weak areas. The weak areas are identified, for example, based on an analysis of answer data or an evaluation of the correct answer rate, but are not limited to such examples. For example, the weak area analysis unit analyzes the user's answer data to identify the weak areas. The weak area analysis unit can also evaluate the user's correct answer rate to identify the weak areas. The weak area analysis unit can also identify the weak areas based on the user's answer history. For example, the weak area analysis unit analyzes the user's answer data to identify questions that the user frequently gets wrong. When evaluating the user's correct answer rate, the weak area analysis unit identifies areas with a low correct answer rate as the weak areas. When identifying the weak areas based on the user's answer history, the weak area analysis unit analyzes past answer data to identify the weak areas. The countermeasure unit takes intensive countermeasures based on the weak areas identified by the weak area analysis unit. The intensive countermeasures are taken, for example, based on the provision of additional practice questions or explanatory videos, but are not limited to such examples. For example, the countermeasure unit provides additional practice questions based on the identified weak areas. The countermeasure unit can also provide explanatory videos based on the identified weak areas. The remediation department may also provide a personalized study plan based on the identified weaknesses. For example, the remediation department may provide additional practice questions based on the identified weaknesses.When providing an explanatory video, the countermeasures unit provides an explanatory video related to the identified weak areas. When providing an individual study plan, the countermeasures unit creates an individual study plan based on the identified weak areas and provides it to the user. This allows the qualification exam study support system according to the embodiment to easily and efficiently study for the qualification exam. Some or all of the above-described processing in the countermeasures unit may be performed using, for example, AI, or may be performed without using AI. For example, the countermeasures unit may perform intensive countermeasures using an AI model that inputs the weak areas identified by the weak area analysis unit and outputs intensive countermeasures.

[0084] The collection unit can collect past exam questions. Past exam questions include, but are not limited to, past exam questions for a specific exam or a specific year. The collection unit can collect, for example, exam questions from the past five years. The collection unit can also collect past exam questions from public databases on the Internet. Furthermore, the collection unit can collect past exam questions provided by exam organizers. For example, the collection unit automatically collects exam questions from the past five years and stores them in a database. When collecting past exam questions from public databases on the Internet, the collection unit searches using specific keywords and collects related past exam questions. When collecting past exam questions provided by exam organizers, the collection unit automatically imports the provided data and stores it in a database. In this way, by collecting exam questions from the past five years, the latest exam trends can be understood. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using AI or without AI. For example, the collection unit can collect exam questions from the past five years, input the collected data into a generation AI, and have the generation AI organize the collected data.

[0085] The analysis unit can analyze question patterns in past exams. For example, the analysis unit analyzes question trends in past exams and extracts frequently asked questions. For example, the analysis unit analyzes question trends in past exams and lists frequently asked questions. The analysis unit can also evaluate the difficulty of past exams and classify the questions. For example, the analysis unit evaluates the difficulty of past exams and classifies the questions. The analysis unit can also analyze the question format of past exams and identify question patterns. For example, the analysis unit analyzes the question format of past exams and groups similar questions. By analyzing the question trends and frequently asked questions in past exams, questions that are more suited to the actual exam can be generated. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can analyze question patterns using an AI model that analyzes question trends in past exams and extracts frequently asked questions.

[0086] The generation unit can generate questions based on exam questions. The generation unit, for example, generates similar questions based on question trends in past exams. For example, the generation unit analyzes question trends in past exams and generates similar questions. The generation unit can also generate new questions based on frequently asked questions in past exams. For example, the generation unit generates new questions based on frequently asked questions in past exams. The generation unit can also generate questions by referring to the question format of past exams. For example, the generation unit creates new questions by referring to the question format of past exams. This generates questions that are in line with the actual exam, allowing users to study in an environment that is similar to the exam. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can generate questions by analyzing question trends in past exams and using an AI model that generates similar questions.

[0087] The answer collection unit can collect answer data of the user. The answer data includes, for example, the correct answer rate and the answer time, but is not limited to these examples. The answer collection unit, for example, collects data on questions answered by the user. The answer collection unit can also collect the user's answer history. The answer collection unit can also select the optimal collection means depending on the user's answering method (audio, text, image, etc.). For example, the answer collection unit automatically collects data on questions answered by the user and stores it in a database. When collecting the user's answer history, the answer collection unit collects the user's answer history based on past answer data. When selecting the optimal collection means depending on the user's answering method, the answer collection unit collects answer data using voice recognition technology, text analysis technology, or image recognition technology. Collecting the user's answer history thereby makes it easier to identify weak areas. Some or all of the above-described processing in the answer collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer collection unit can collect user answer data, input the collected data into the generation AI, and have the generation AI analyze the answer data.

[0088] The weak area analysis unit can analyze the user's answer data and identify weak points. Identification of weak areas is performed, for example, based on an analysis of answer data and an evaluation of the correct answer rate, but is not limited to such examples. For example, the weak area analysis unit can analyze the user's answer data and identify weak areas. The weak area analysis unit can also evaluate the user's correct answer rate and identify weak areas. The weak area analysis unit can also identify weak areas based on the user's answer history. For example, the weak area analysis unit analyzes the user's answer data and identify questions that the user frequently gets wrong. When evaluating the user's correct answer rate, the weak area analysis unit identifies areas with a low correct answer rate as weak areas. When identifying weak areas based on the user's answer history, the weak area analysis unit analyzes past answer data and identifies weak areas. This makes it easier to identify weak areas by analyzing the user's answer history. Some or all of the above-described processing in the weak area analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the weak area analysis unit can analyze the user's answer data and identify weak areas using an AI model that identifies weak areas.

[0089] The countermeasure unit can take countermeasures based on the identified weak areas. Countermeasures can be taken, for example, by providing additional practice problems or explanatory videos, but are not limited to these examples. For example, the countermeasure unit can provide additional practice problems based on the identified weak areas. The countermeasure unit can also provide explanatory videos based on the identified weak areas. The countermeasure unit can also provide an individualized study plan based on the identified weak areas. For example, the countermeasure unit provides additional practice problems based on the identified weak areas. When providing explanatory videos, the countermeasure unit provides explanatory videos related to the identified weak areas. When providing an individualized study plan, the countermeasure unit creates an individualized study plan based on the identified weak areas and provides it to the user. This allows the user to efficiently overcome their weaknesses by taking intensive measures based on the identified weak areas. Some or all of the above-described processing by the countermeasure unit may be performed using, for example, AI, or may be performed without using AI. For example, the countermeasure unit can take countermeasures using an AI model that inputs the weak areas identified by the weak area analysis unit and outputs intensive measures.

[0090] The countermeasure unit can provide an appropriate study plan for each user. The provision of the study plan is based on, for example, the user's study history and progress, but is not limited to such examples. For example, the countermeasure unit can analyze the user's study history and provide an optimal study plan. The countermeasure unit can also analyze the user's progress and provide an appropriate study plan. The countermeasure unit can also customize the study plan based on the user's weak areas. For example, the countermeasure unit can analyze the user's study history and provide an optimal study plan. When analyzing the user's progress, the countermeasure unit evaluates the user's study progress and provides an appropriate study plan. When customizing the study plan based on the user's weak areas, the countermeasure unit provides a study plan that focuses on the user's weak areas. This provides an optimal study plan for each user, enabling efficient learning tailored to each individual user. Some or all of the above-described processing by the countermeasure unit may be performed using, for example, AI, or may be performed without AI. For example, the countermeasure unit can provide a study plan using an AI model that inputs the user's study history and progress and outputs an optimal study plan.

[0091] The collection unit can analyze the user's emotions and adjust the timing of collecting past exam questions based on the analyzed emotions. For example, if the user is feeling stressed, the collection unit delays the collection timing to reduce the user's burden. For example, if the user is feeling stressed, the collection unit delays the collection timing. Furthermore, if the user is relaxed, the collection unit can also advance the collection timing to promote efficient learning. For example, if the user is relaxed, the collection unit advances the collection timing. Furthermore, if the user is concentrating, the collection unit can optimize the collection timing to maintain the flow of learning. For example, if the user is concentrating, the collection unit optimizes the collection timing. This allows for maximizing learning efficiency by adjusting the collection timing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotional data into the generation AI and have the generation AI perform emotional analysis.

[0092] When collecting past exam questions, the collection unit can adjust the range of questions collected based on the content and format of the exam. For example, the collection unit prioritizes collecting difficult exam questions to test the user's ability. For example, the collection unit prioritizes collecting difficult exam questions. The collection unit can also collect questions with different question formats in a balanced manner to enable the user to respond to a variety of questions. For example, the collection unit collects questions with different question formats in a balanced manner. The collection unit can also expand the range of questions collected depending on the difficulty of the exam to expand the user's learning range. For example, the collection unit expands the range of questions collected depending on the difficulty of the exam. In this way, the user's learning range can be expanded by adjusting the range of questions collected based on the difficulty of the exam and the question format. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input the content and format of the exam to a generation AI and cause the generation AI to adjust the range of questions collected.

[0093] When collecting past exam questions, the collection unit can apply different collection algorithms for each exam field. For example, the collection unit may mainly collect calculation questions for mathematics questions, emphasizing the speed of answering. For example, the collection unit may mainly collect calculation questions for mathematics questions. The collection unit may also mainly collect reading comprehension questions for English questions to enhance comprehension. For example, the collection unit may mainly collect reading comprehension questions for English questions. The collection unit may also mainly collect experimental questions for science questions to cultivate practical knowledge. For example, the collection unit may mainly collect experimental questions for science questions. In this way, by applying different collection algorithms for each exam field, questions specialized for each field can be collected. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit may input different collection algorithms for each exam field into the generation AI and cause the generation AI to apply the collection algorithms.

[0094] When collecting past questions, the collection unit can improve the accuracy of the collection by referring to the user's learning history. The collection unit, for example, analyzes trends in questions the user has solved in the past and collects similar questions. For example, the collection unit analyzes trends in questions the user has solved in the past and collects similar questions. The collection unit can also collect questions of an appropriate level of difficulty according to the user's learning progress. For example, the collection unit collects questions of an appropriate level of difficulty according to the user's learning progress. The collection unit can also collect balanced questions by taking into account the user's strengths and weaknesses. For example, the collection unit collects balanced questions by taking into account the user's strengths and weaknesses. By referring to the user's learning history, the accuracy of the collection can be improved and more appropriate questions can be provided. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's learning history into a generation AI and cause the generation AI to improve the accuracy of the collection.

[0095] The collection unit can estimate the user's emotions and determine the priority of past exam questions to be collected based on the estimated user emotions. For example, when the user is feeling stressed, the collection unit prioritizes collecting easy questions to reduce the burden of studying. For example, when the user is feeling stressed, the collection unit prioritizes collecting easy questions. Furthermore, when the user is relaxed, the collection unit can prioritize collecting difficult questions to increase the user's motivation to take on new challenges. For example, when the user is relaxed, the collection unit prioritizes collecting difficult questions. Furthermore, when the user is concentrating, the collection unit can collect balanced questions to maximize study efficiency. For example, when the user is concentrating, the collection unit collects balanced questions. This maximizes study efficiency by prioritizing past exam questions according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input user emotion data to the generation AI and cause the generation AI to estimate the emotion.

[0096] When collecting past exam questions, the collection unit can adjust the collection range based on the region and year of the exam. For example, the collection unit collects questions that frequently appear in a specific region to address regional trends. For example, the collection unit collects questions that frequently appear in a specific region. The collection unit can also collect questions from the past few years to understand the latest question trends. For example, the collection unit collects questions from the past few years. The collection unit can also collect appropriate questions taking into account differences in exam formats between regions. For example, the collection unit collects appropriate questions taking into account differences in exam formats between regions. In this way, regional trends can be addressed by adjusting the collection range based on the region and year of the exam. Some or all of the above-mentioned processing in the collection unit may be performed using, or without, AI. For example, the collection unit can input the region and year of the exam into the generation AI and have the generation AI adjust the collection range.

[0097] When collecting past exam questions, the collection unit can improve the accuracy of the collection by referring to exam-related literature. The collection unit, for example, refers to academic papers related to the exam to understand question trends. For example, the collection unit refers to academic papers related to the exam. The collection unit can also refer to official exam guidelines to collect questions that capture important points. For example, the collection unit refers to official exam guidelines. The collection unit can also refer to books related to the exam to collect questions that cover a wide range of knowledge. For example, the collection unit refers to books related to the exam. By referring to exam-related literature, the accuracy of the collection can be improved and more appropriate questions can be provided. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using AI, or can be performed without AI. For example, the collection unit can input exam-related literature into a generation AI and have the generation AI improve the accuracy of the collection.

[0098] When collecting past questions, the collection unit can take into account the tendencies of test setters. For example, the collection unit analyzes the tendencies of questions frequently asked by a specific test setter and collects similar questions. For example, the collection unit analyzes the tendencies of questions frequently asked by a specific test setter. The collection unit can also refer to the test setter's past question-setting history to understand the question-setting tendencies. For example, the collection unit refers to the test setter's past question-setting history. The collection unit can also collect related questions based on the test setter's field of expertise. For example, the collection unit collects related questions based on the test setter's field of expertise. In this way, by taking into account the tendencies of the test setter, questions that are in line with the question-setting tendencies can be collected. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the tendencies of the test setter into the generation AI and have the generation AI adjust the collection.

[0099] The analysis unit can estimate the user's emotions and adjust the way the analysis is presented based on the estimated user's emotions. For example, when the user is nervous, the analysis unit provides simple, highly visible analysis results. For example, when the user is nervous, the analysis unit provides simple, highly visible analysis results. Furthermore, when the user is relaxed, the analysis unit can provide detailed analysis results to deepen understanding. For example, when the user is relaxed, the analysis unit provides detailed analysis results. Furthermore, when the user is concentrating, the analysis unit can provide analysis results that focus on the key points to promote efficient learning. For example, when the user is concentrating, the analysis unit provides analysis results that focus on the key points. This allows for maximizing learning efficiency by adjusting the way the analysis is presented based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0100] During analysis, the analysis unit can adjust the level of detail of the analysis based on the frequency of questions in past exams. The analysis unit, for example, performs a detailed analysis of frequently asked questions to understand question trends. For example, the analysis unit performs a detailed analysis of frequently asked questions. The analysis unit can also perform a concise analysis of questions that appear less frequently to promote efficient learning. For example, the analysis unit performs a concise analysis of questions that appear less frequently. The analysis unit can also adjust the level of detail of the analysis according to the frequency of questions to provide balanced learning. For example, the analysis unit adjusts the level of detail of the analysis according to the frequency of questions. As a result, efficient learning is possible by adjusting the level of detail of the analysis based on the frequency of questions in past exams. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the frequency of questions in past exams into a generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0101] During analysis, the analysis unit can apply different analysis algorithms depending on the test category. For example, the analysis unit applies a calculation algorithm to math questions to analyze the accuracy of the answers. For example, the analysis unit applies a calculation algorithm to math questions. The analysis unit can also apply a reading comprehension algorithm to English questions to analyze the level of comprehension. For example, the analysis unit applies a reading comprehension algorithm to English questions. The analysis unit can also apply an experimental algorithm to science questions to analyze practical knowledge. For example, the analysis unit applies an experimental algorithm to science questions. In this way, by applying different analysis algorithms depending on the test category, analysis specialized for each category is possible. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input an analysis algorithm depending on the test category into the generation AI and cause the generation AI to apply the analysis algorithm.

[0102] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis unit improves the analysis accuracy of similar questions based on the user's past analysis results. For example, the analysis unit improves the analysis accuracy of similar questions based on the user's past analysis results. The analysis unit can also select an appropriate analysis method according to the user's learning progress. For example, the analysis unit selects an appropriate analysis method according to the user's learning progress. The analysis unit can also perform a balanced analysis by taking into account the user's strengths and weaknesses. For example, the analysis unit performs a balanced analysis by taking into account the user's strengths and weaknesses. By referring to the user's past analysis results, the accuracy of the analysis is improved, enabling more appropriate learning. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's past analysis results into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0103] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. For example, if the user is nervous, the analysis unit provides a short and concise analysis. For example, if the user is nervous, the analysis unit provides a short and concise analysis. The analysis unit can also provide a detailed analysis to deepen understanding if the user is relaxed. For example, if the user is relaxed, the analysis unit provides a detailed analysis. The analysis unit can also provide a balanced analysis to promote efficient learning if the user is focused. For example, if the user is focused, the analysis unit provides a balanced analysis. This allows for maximizing learning efficiency by adjusting the length of the analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0104] During analysis, the analysis unit can determine the analysis priority based on the submission date of past exam questions. For example, the analysis unit prioritizes analysis of the most recent past exam questions to understand the latest exam question trends. For example, the analysis unit prioritizes analysis of the most recent past exam questions. The analysis unit can also analyze questions from the past few years in a balanced manner to cover a wide range of knowledge. For example, the analysis unit analyzes questions from the past few years in a balanced manner. The analysis unit can also adjust the analysis priority based on the submission date to provide efficient learning. For example, the analysis unit adjusts the analysis priority based on the submission date. In this way, by determining the analysis priority based on the submission date of past exam questions, the latest exam question trends can be understood. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the submission date of past exam questions to the generation AI and have the generation AI determine the analysis priority.

[0105] During analysis, the analysis unit can adjust the order of analysis based on the relevance of past questions. The analysis unit, for example, groups similar questions to perform the analysis efficiently. For example, the analysis unit groups similar questions. The analysis unit can also prioritize analyzing highly relevant questions to grasp question trends. For example, the analysis unit prioritizes analyzing highly relevant questions. The analysis unit can also adjust the order of analysis according to the relevance to provide efficient learning. For example, the analysis unit adjusts the order of analysis according to the relevance. As a result, adjusting the order of analysis based on the relevance of past questions enables efficient learning. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the relevance of past questions to a generation AI and have the generation AI adjust the order of analysis.

[0106] During analysis, the analysis unit can adjust the use of technical terminology in the analysis according to the user's level of expertise. For example, the analysis unit uses simple terminology for beginners to provide an analysis that is easy to understand. For example, the analysis unit uses simple terminology for beginners. The analysis unit can also use appropriate technical terminology for intermediate users to deepen understanding. For example, the analysis unit uses appropriate technical terminology for intermediate users. The analysis unit can also use advanced technical terminology for advanced users to provide a detailed analysis. For example, the analysis unit uses advanced technical terminology for advanced users. In this way, by adjusting the use of technical terminology according to the user's level of expertise, it is possible to provide an analysis result that is easy to understand. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's level of expertise into the generation AI and cause the generation AI to adjust the use of technical terminology.

[0107] The generation unit can estimate the user's emotions and adjust the way questions are expressed based on the estimated user's emotions. For example, when the user is nervous, the generation unit generates simple, highly visible questions. For example, when the user is nervous, the generation unit generates simple, highly visible questions. The generation unit can also generate questions that include detailed explanations when the user is relaxed. For example, when the user is relaxed, the generation unit generates questions that include detailed explanations. The generation unit can also generate questions that focus on the main points when the user is concentrating. For example, when the user is concentrating, the generation unit generates questions that focus on the main points. This maximizes learning efficiency by adjusting the way questions are expressed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the generation unit can be performed using, for example, an AI, or without an AI. For example, the generation unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0108] When generating questions, the generation unit can adjust the level of detail of the generated questions based on the frequency of questions in past exams. For example, the generation unit generates questions that include detailed explanations for frequently-asked questions. For example, the generation unit generates questions that include detailed explanations for frequently-asked questions. The generation unit can also generate questions that include concise explanations for questions that are asked less frequently. For example, the generation unit generates questions that include concise explanations for questions that are asked less frequently. The generation unit can also adjust the level of detail of the generated questions based on the frequency of questions to provide balanced questions. For example, the generation unit adjusts the level of detail of the generated questions based on the frequency of questions asked. This enables efficient learning by adjusting the level of detail of the generated questions based on the frequency of questions asked in past exams. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the frequency of questions in past exams into the generation AI and cause the generation AI to adjust the level of detail of the generated questions.

[0109] When generating questions, the generation unit can apply different generation algorithms depending on the test category. For example, the generation unit applies a calculation algorithm to math questions, emphasizing the accuracy of the answers. For example, the generation unit applies a calculation algorithm to math questions. The generation unit can also apply a reading comprehension algorithm to English questions, emphasizing the level of understanding. For example, the generation unit applies a reading comprehension algorithm to English questions. The generation unit can also apply an experimental algorithm to science questions, emphasizing practical knowledge. For example, the generation unit applies an experimental algorithm to science questions. In this way, by applying different generation algorithms depending on the test category, questions specialized for each category can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input a generation algorithm according to the test category into the generation AI and cause the generation AI to apply the generation algorithm.

[0110] When generating questions, the generation unit can improve the accuracy of the generation by referring to the user's past generation results. For example, the generation unit improves the accuracy of generating similar questions based on the user's past generation results. For example, the generation unit improves the accuracy of generating similar questions based on the user's past generation results. The generation unit can also select an appropriate generation method according to the user's learning progress. For example, the generation unit selects an appropriate generation method according to the user's learning progress. The generation unit can also generate balanced questions by taking into account the user's strengths and weaknesses. For example, the generation unit generates balanced questions by taking into account the user's strengths and weaknesses. By referring to the user's past generation results, the accuracy of generation can be improved and more appropriate questions can be provided. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's past generation results into the generation AI and cause the generation AI to improve the accuracy of generation.

[0111] The generation unit can estimate the user's emotions and adjust the length of the questions to be generated based on the estimated user emotions. For example, when the user is nervous, the generation unit generates short, to-the-point questions. For example, when the user is nervous, the generation unit generates short, to-the-point questions. The generation unit can also generate longer questions with detailed explanations when the user is relaxed. For example, when the user is relaxed, the generation unit generates longer questions with detailed explanations. The generation unit can also generate balanced questions when the user is focused. For example, when the user is focused, the generation unit generates balanced questions. This allows the learning efficiency to be maximized by adjusting the length of the questions according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the generation unit can be performed, for example, using AI or without AI. For example, the generation unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0112] When generating questions, the generation unit can determine the generation priority based on the submission date of past questions. For example, the generation unit prioritizes generating the most recent past questions to grasp the latest question trends. For example, the generation unit prioritizes generating the most recent past questions. The generation unit can also generate questions from the past few years in a balanced manner to cover a wide range of knowledge. For example, the generation unit generates questions from the past few years in a balanced manner. The generation unit can also adjust the generation priority according to the submission date to provide efficient learning. For example, the generation unit adjusts the generation priority according to the submission date. In this way, by determining the generation priority based on the submission date of past questions, the latest question trends can be grasped. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the submission date of past questions into the generation AI and have the generation AI determine the generation priority.

[0113] When generating questions, the generation unit can adjust the order of generation based on the relevance of past questions. The generation unit, for example, groups similar questions to generate questions efficiently. For example, the generation unit groups similar questions. The generation unit can also prioritize generating highly relevant questions to grasp question trends. For example, the generation unit prioritizes generating highly relevant questions. The generation unit can also adjust the order of generation according to the relevance to provide efficient learning. For example, the generation unit adjusts the order of generation according to the relevance. As a result, adjusting the order of generation based on the relevance of past questions enables efficient learning. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the relevance of past questions into the generation AI and cause the generation AI to adjust the order of generation.

[0114] When generating questions, the generation unit can adjust the use of technical terminology in the generation according to the user's level of expertise. For example, the generation unit uses simple terminology for beginners to generate questions that are easy to understand. For example, the generation unit uses simple terminology for beginners. The generation unit can also use appropriate technical terminology for intermediate learners to deepen understanding. For example, the generation unit uses appropriate technical terminology for intermediate learners. The generation unit can also generate detailed questions using advanced technical terminology for advanced learners. For example, the generation unit uses advanced technical terminology for advanced learners. In this way, by adjusting the use of technical terminology according to the user's level of expertise, it is possible to provide questions that are easy to understand. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's level of expertise into the generation AI and cause the generation AI to adjust the use of technical terminology.

[0115] The answer collection unit can estimate the user's emotions and adjust the timing of answer data collection based on the estimated user emotions. For example, if the user is feeling stressed, the answer collection unit delays the timing of collection to reduce the user's burden. For example, if the user is feeling stressed, the answer collection unit delays the timing of collection. Furthermore, if the user is relaxed, the answer collection unit can also advance the timing of collection to promote efficient learning. For example, if the user is relaxed, the answer collection unit advances the timing of collection. Furthermore, if the user is concentrating, the answer collection unit can optimize the timing of collection to maintain the flow of learning. For example, if the user is concentrating, the answer collection unit optimizes the timing of collection. This allows for maximizing learning efficiency by adjusting the timing of answer data collection according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the answer collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer collection unit may input user emotion data to the generation AI and have the generation AI estimate the emotion.

[0116] When collecting answer data, the answer collection unit can select the optimal collection means depending on the user's answering method. For example, when the user answers by voice, the answer collection unit collects answer data using voice recognition technology. For example, when the user answers by voice, the answer collection unit collects answer data using voice recognition technology. Furthermore, when the user answers by text, the answer collection unit can also collect answer data using text analysis technology. For example, when the user answers by text, the answer collection unit collects answer data using text analysis technology. Furthermore, when the user answers by image, the answer collection unit can also collect answer data using image recognition technology. For example, when the user answers by image, the answer collection unit collects answer data using image recognition technology. This enables efficient data collection by selecting the optimal collection means depending on the user's answering method. Some or all of the above-mentioned processing in the answer collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer collection unit can input the user's answer method into the generation AI and have the generation AI select the optimal collection means.

[0117] When collecting answer data, the answer collection unit can improve the accuracy of the collection by referring to the user's past answer history. The answer collection unit, for example, collects similar answer data based on the user's past answer history. For example, the answer collection unit collects similar answer data based on the user's past answer history. The answer collection unit can also collect appropriate answer data according to the user's learning progress. For example, the answer collection unit collects appropriate answer data according to the user's learning progress. The answer collection unit can also collect balanced answer data by taking into account the user's strengths and weaknesses. For example, the answer collection unit collects balanced answer data by taking into account the user's strengths and weaknesses. By referring to the user's past answer history, the accuracy of the collection can be improved and more appropriate data can be provided. Some or all of the above-mentioned processing in the answer collection unit may be performed, for example, using AI or without AI. For example, the answer collection unit can input the user's past answer history into the generation AI and cause the generation AI to improve the accuracy of collection.

[0118] When collecting answer data, the answer collection unit can adjust the collection range based on the user's current learning situation. The answer collection unit, for example, collects an appropriate range of answer data according to the user's learning progress. For example, the answer collection unit collects an appropriate range of answer data according to the user's learning progress. The answer collection unit can also collect balanced answer data taking into account the user's strengths and weaknesses. For example, the answer collection unit collects balanced answer data taking into account the user's strengths and weaknesses. The answer collection unit can also adjust the collection range based on the user's current learning situation to provide efficient learning. For example, the answer collection unit adjusts the collection range based on the user's current learning situation. This enables efficient learning by adjusting the collection range based on the user's current learning situation. Some or all of the above-mentioned processing in the answer collection unit may be performed using AI, for example, or may be performed without using AI. For example, the answer collection unit can input the user's current learning situation to the generation AI and cause the generation AI to adjust the collection range.

[0119] The answer collection unit can estimate the user's emotions and determine the priority of the answer data to be collected based on the estimated user emotions. For example, when the user is feeling stressed, the answer collection unit prioritizes collecting easy answer data, thereby reducing the burden of learning. For example, when the user is feeling stressed, the answer collection unit prioritizes collecting easy answer data. Furthermore, when the user is relaxed, the answer collection unit can prioritize collecting more difficult answer data, thereby increasing the user's motivation to take on challenges. For example, when the user is relaxed, the answer collection unit prioritizes collecting more difficult answer data. Furthermore, when the user is concentrating, the answer collection unit can collect balanced answer data, thereby maximizing learning efficiency. For example, when the user is concentrating, the answer collection unit collects balanced answer data. In this way, by determining the priority of answer data according to the user's emotions, learning efficiency can be maximized. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the answer collection unit may be performed using, or without, an AI. For example, the answer collection unit may input user emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0120] When collecting answer data, the answer collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. For example, when the user is in a specific area, the answer collection unit prioritizes collecting answer data related to that area. For example, when the user is in a specific area, the answer collection unit prioritizes collecting answer data related to that area. The answer collection unit can also collect highly relevant answer data based on the user's geographical location information. For example, the answer collection unit collects highly relevant answer data based on the user's geographical location information. The answer collection unit can also collect appropriate answer data by taking into account the user's geographical location information. For example, the answer collection unit collects appropriate answer data by taking into account the user's geographical location information. In this way, highly relevant data can be preferentially collected by taking into account the user's geographical location information. Some or all of the above-described processing in the answer collection unit may be performed using AI, for example, or may be performed without using AI. For example, the answer collection unit can input the user's geographical location information to the generation AI and cause the generation AI to collect highly relevant data.

[0121] The answer collection unit can analyze the user's social media activities and collect related data when collecting answer data. The answer collection unit, for example, analyzes the user's social media posts and collects related answer data. For example, the answer collection unit analyzes the user's social media posts and collects related answer data. The answer collection unit can also collect related answer data by referring to the activities of the user's friends on social media. For example, the answer collection unit collects related answer data by referring to the activities of the user's friends on social media. The answer collection unit can also collect related answer data based on the user's check-in information on social media. For example, the answer collection unit collects related answer data based on the user's check-in information on social media. In this way, related data can be collected by analyzing the user's social media activities. Some or all of the above-mentioned processing in the answer collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer collection unit can input the user's social media activities into the generation AI and cause the generation AI to collect related data.

[0122] When collecting answer data, the answer collection unit can customize the collection method by reflecting the user's past feedback. The answer collection unit customizes the collection method based on, for example, the user's past feedback to collect efficient answer data. For example, the answer collection unit customizes the collection method based on the user's past feedback. The answer collection unit can also select an appropriate collection method by reflecting the user's feedback. For example, the answer collection unit selects an appropriate collection method by reflecting the user's feedback. The answer collection unit can also adjust the collection method by taking the user's past feedback into account to provide efficient learning. For example, the answer collection unit adjusts the collection method by taking the user's past feedback into account. This enables the collection method to be customized by reflecting the user's past feedback, enabling efficient data collection. Some or all of the above-described processing in the answer collection unit may be performed using, or without, AI. For example, the answer collection unit can input the user's past feedback into the generation AI and cause the generation AI to customize the collection method.

[0123] The weak area analysis unit can estimate the user's emotions and adjust the analysis method for the weak areas based on the estimated user emotions. For example, when the user is nervous, the weak area analysis unit provides simple, highly visible analysis results. For example, when the user is nervous, the weak area analysis unit provides simple, highly visible analysis results. Furthermore, when the user is relaxed, the weak area analysis unit can provide detailed analysis results to deepen understanding. For example, when the user is relaxed, the weak area analysis unit provides detailed analysis results. Furthermore, when the user is concentrating, the weak area analysis unit can provide analysis results that highlight the key points to promote efficient learning. For example, when the user is concentrating, the weak area analysis unit provides analysis results that highlight the key points. This allows the analysis method to be adjusted according to the user's emotions, thereby maximizing learning efficiency. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the weak area analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the weak area analysis unit may input the user's emotion data into the generation AI and have the generation AI estimate the emotion.

[0124] When analyzing weak areas, the weak area analysis unit can adjust the level of detail of the analysis based on the user's answer frequency. The weak area analysis unit, for example, performs a detailed analysis of questions that are frequently answered incorrectly to identify weak areas. For example, the weak area analysis unit performs a detailed analysis of questions that are frequently answered incorrectly. The weak area analysis unit can also perform a concise analysis of questions that are infrequently answered to promote efficient learning. For example, the weak area analysis unit performs a concise analysis of questions that are infrequently answered. The weak area analysis unit can also adjust the level of detail of the analysis according to the answer frequency to provide balanced learning. For example, the weak area analysis unit adjusts the level of detail of the analysis according to the answer frequency. This enables efficient learning by adjusting the level of detail of the analysis based on the user's answer frequency. Some or all of the above-mentioned processing in the weak area analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the weak area analysis unit can input the user's answer frequency to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0125] When analyzing weak areas, the weak area analysis unit can apply different analysis algorithms depending on the category of the test. For example, the weak area analysis unit applies a calculation algorithm to math questions to analyze the accuracy of the answers. For example, the weak area analysis unit applies a calculation algorithm to math questions. The weak area analysis unit can also apply a reading comprehension algorithm to English questions to analyze the level of comprehension. For example, the weak area analysis unit applies a reading comprehension algorithm to English questions. The weak area analysis unit can also apply an experimental algorithm to science questions to analyze practical knowledge. For example, the weak area analysis unit applies an experimental algorithm to science questions. In this way, by applying different analysis algorithms depending on the category of the test, analysis specialized for each category is possible. Some or all of the above-mentioned processing in the weak area analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the weak area analysis unit can input an analysis algorithm depending on the category of the test to the generation AI and cause the generation AI to apply the analysis algorithm.

[0126] When analyzing weak areas, the weak area analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The weak area analysis unit, for example, improves the analysis accuracy of similar questions based on the user's past analysis results. For example, the weak area analysis unit improves the analysis accuracy of similar questions based on the user's past analysis results. The weak area analysis unit can also select an appropriate analysis method depending on the user's learning progress. For example, the weak area analysis unit selects an appropriate analysis method depending on the user's learning progress. The weak area analysis unit can also perform a balanced analysis by taking into account the user's strong and weak areas. For example, the weak area analysis unit performs a balanced analysis by taking into account the user's strong and weak areas. By referring to the user's past analysis results, the accuracy of the analysis can be improved, enabling more appropriate learning. Some or all of the above-mentioned processing in the weak area analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the weak area analysis unit can input the user's past analysis results into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0127] The weak area analysis unit can estimate the user's emotions and determine the priority of weak areas based on the estimated user emotions. For example, when the user is feeling stressed, the weak area analysis unit prioritizes analyzing easy questions to reduce the burden of learning. For example, when the user is feeling stressed, the weak area analysis unit prioritizes analyzing easy questions. Furthermore, when the user is relaxed, the weak area analysis unit can prioritize analyzing difficult questions to increase the user's motivation to take on new challenges. For example, when the user is relaxed, the weak area analysis unit prioritizes analyzing difficult questions. Furthermore, when the user is concentrating, the weak area analysis unit can analyze balanced questions to maximize learning efficiency. For example, when the user is concentrating, the weak area analysis unit analyzes balanced questions. This maximizes learning efficiency by prioritizing weak areas according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the weak area analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the weak area analysis unit may input the user's emotion data into the generation AI and have the generation AI estimate the emotion.

[0128] When analyzing weak areas, the weak area analysis unit can determine the analysis priority based on the time of the user's answer. The weak area analysis unit, for example, prioritizes analysis of the most recent answer data to identify the most recent weak area. For example, the weak area analysis unit prioritizes analysis of the most recent answer data. The weak area analysis unit can also analyze answer data from the past few years in a balanced manner to cover a wide range of knowledge. For example, the weak area analysis unit analyzes answer data from the past few years in a balanced manner. The weak area analysis unit can also adjust the analysis priority according to the time of the answer to provide efficient learning. For example, the weak area analysis unit adjusts the analysis priority according to the time of the answer. In this way, the most recent weak area can be identified by determining the analysis priority based on the time of the user's answer. Some or all of the above-mentioned processing in the weak area analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the weak area analysis unit can input the time of the user's answer into the generation AI and have the generation AI determine the analysis priority.

[0129] The weak area analysis unit can improve the accuracy of the analysis by referring to the user's knowledge of related fields when analyzing the weak areas. The weak area analysis unit, for example, improves the analysis accuracy of the weak areas based on the user's knowledge of related fields. For example, the weak area analysis unit improves the analysis accuracy of the weak areas based on the user's knowledge of related fields. The weak area analysis unit can also select an appropriate analysis method depending on the user's learning progress. For example, the weak area analysis unit selects an appropriate analysis method depending on the user's learning progress. The weak area analysis unit can also perform a balanced analysis by taking into account the user's strong and weak areas. For example, the weak area analysis unit performs a balanced analysis by taking into account the user's strong and weak areas. By referring to the user's knowledge of related fields, the accuracy of the analysis is improved, enabling more appropriate learning. Some or all of the above-mentioned processing in the weak area analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the weak area analysis unit can input the user's knowledge of related fields into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0130] When analyzing weak areas, the weak area analysis unit can adjust the analysis method according to the user's learning style. For example, if the user prefers visual learning, the weak area analysis unit provides an analysis using graphs and diagrams. For example, if the user prefers visual learning, the weak area analysis unit provides an analysis using graphs and diagrams. Furthermore, if the user prefers auditory learning, the weak area analysis unit can provide an analysis including audio commentary. For example, if the user prefers auditory learning, the weak area analysis unit provides an analysis including audio commentary. Furthermore, if the user prefers hands-on learning, the weak area analysis unit can provide an analysis using real-life examples. For example, if the user prefers hands-on learning, the weak area analysis unit provides an analysis using real-life examples. This enables efficient learning by adjusting the analysis method according to the user's learning style. Some or all of the above-described processing in the weak area analysis unit may be performed using AI, for example, or may be performed without AI. For example, the weak area analysis unit can input the user's learning style into the generation AI and cause the generation AI to adjust the analysis method.

[0131] The countermeasure unit can estimate the user's emotions and adjust the countermeasure method based on the estimated user's emotions. For example, if the user is nervous, the countermeasure unit provides a countermeasure that allows the user to relax. For example, if the user is nervous, the countermeasure unit provides a countermeasure that allows the user to relax. The countermeasure unit can also provide a countermeasure that improves concentration when the user is relaxed. For example, if the user is relaxed, the countermeasure unit provides a countermeasure that improves concentration. The countermeasure unit can also provide an efficient countermeasure when the user is concentrating. For example, if the user is concentrating, the countermeasure unit provides an efficient countermeasure when the user is concentrating. This allows the countermeasure method to be adjusted according to the user's emotions, thereby maximizing learning efficiency. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the countermeasure unit can be performed using an AI, for example, or without an AI. For example, the countermeasure unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0132] When taking countermeasures, the countermeasure unit can analyze the user's past learning history and select the optimal countermeasure. The countermeasure unit, for example, selects an effective countermeasure based on the user's past learning history. For example, the countermeasure unit selects an effective countermeasure based on the user's past learning history. The countermeasure unit can also select an appropriate countermeasure according to the user's learning progress. For example, the countermeasure unit selects an appropriate countermeasure according to the user's learning progress. The countermeasure unit can also select a balanced countermeasure taking into account the user's strengths and weaknesses. For example, the countermeasure unit selects a balanced countermeasure taking into account the user's strengths and weaknesses. This allows the user's past learning history to be analyzed to select the optimal countermeasure, enabling efficient learning. Some or all of the above-described processing in the countermeasure unit may be performed using, or without, AI. For example, the countermeasure unit can input the user's past learning history into a generation AI and have the generation AI select the optimal countermeasure.

[0133] When taking countermeasures, the countermeasure unit can customize the countermeasure measures based on the user's current learning situation. The countermeasure unit, for example, customizes appropriate countermeasure measures according to the user's learning progress. For example, the countermeasure unit customizes appropriate countermeasure measures according to the user's learning progress. The countermeasure unit can also customize balanced countermeasure measures taking into account the user's strengths and weaknesses. For example, the countermeasure unit customizes balanced countermeasures taking into account the user's strengths and weaknesses. The countermeasure unit can also adjust the countermeasure measures based on the user's current learning situation to provide efficient learning. For example, the countermeasure unit adjusts the countermeasure measures based on the user's current learning situation. This enables efficient learning by customizing the countermeasure measures based on the user's current learning situation. Some or all of the above-mentioned processing in the countermeasure unit may be performed using, or without, AI. For example, the countermeasure unit can input the user's current learning situation into the generation AI and cause the generation AI to customize the countermeasure measures.

[0134] The countermeasure unit can improve the countermeasure method by reflecting user feedback when taking countermeasures. For example, the countermeasure unit improves the countermeasure method based on user feedback and provides efficient learning. For example, the countermeasure unit improves the countermeasure method based on user feedback. The countermeasure unit can also select an appropriate countermeasure method by reflecting user feedback. For example, the countermeasure unit selects an appropriate countermeasure method by reflecting user feedback. The countermeasure unit can also adjust the countermeasure method by taking into account the user's past feedback and provide efficient learning. For example, the countermeasure unit adjusts the countermeasure method by taking into account the user's past feedback. In this way, the countermeasure method is improved by reflecting user feedback, enabling efficient learning. Some or all of the above-mentioned processing in the countermeasure unit may be performed using AI, for example, or may be performed without using AI. For example, the countermeasure unit can input user feedback into a generation AI and cause the generation AI to improve the countermeasure method.

[0135] The countermeasure unit can estimate the user's emotions and prioritize countermeasures based on the estimated user emotions. For example, when the user is feeling stressed, the countermeasure unit prioritizes providing easy countermeasures to reduce the burden of learning. For example, when the user is feeling stressed, the countermeasure unit prioritizes providing easy countermeasures. Furthermore, when the user is relaxed, the countermeasure unit can prioritize providing more difficult countermeasures to increase the user's motivation to take on new challenges. For example, when the user is relaxed, the countermeasure unit prioritizes providing more difficult countermeasures. Furthermore, when the user is concentrating, the countermeasure unit can provide balanced countermeasures to maximize learning efficiency. For example, when the user is concentrating, the countermeasure unit provides balanced countermeasures. This maximizes learning efficiency by prioritizing countermeasures according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing by the countermeasure unit may be performed using, for example, AI, or may be performed without using AI. For example, the countermeasure unit may input user emotion data to the generation AI and have the generation AI estimate the emotion.

[0136] When taking countermeasures, the countermeasure unit can select the optimal countermeasure method by taking into account the user's geographical location information. For example, if the user is in a specific area, the countermeasure unit provides a countermeasure method related to that area. For example, if the user is in a specific area, the countermeasure unit provides a countermeasure method related to that area. The countermeasure unit can also provide a highly relevant countermeasure method based on the user's geographical location information. For example, the countermeasure unit provides a highly relevant countermeasure method based on the user's geographical location information. The countermeasure unit can also provide an appropriate countermeasure method by taking into account the user's geographical location information. For example, the countermeasure unit provides an appropriate countermeasure method by taking into account the user's geographical location information. This enables the optimal countermeasure method to be selected and efficient learning to be achieved by taking into account the user's geographical location information. Some or all of the above-described processing in the countermeasure unit may be performed using, or without, AI. For example, the countermeasure unit can input the user's geographical location information into the generation AI and cause the generation AI to select the optimal countermeasure method.

[0137] When taking countermeasures, the countermeasure unit can analyze the user's social media activity and suggest countermeasures. The countermeasure unit, for example, analyzes the content of the user's social media posts and suggests relevant countermeasures. For example, the countermeasure unit analyzes the content of the user's social media posts and suggests relevant countermeasures. The countermeasure unit can also suggest relevant countermeasures by referring to the activities of the user's friends on social media. For example, the countermeasure unit can suggest relevant countermeasures by referring to the activities of the user's friends on social media. The countermeasure unit can also suggest relevant countermeasures based on the user's check-in information on social media. For example, the countermeasure unit suggests relevant countermeasures based on the user's check-in information on social media. In this way, relevant countermeasures can be suggested by analyzing the user's social media activity. Some or all of the above-mentioned processing in the countermeasure unit may be performed using, for example, AI, or may be performed without using AI. For example, the countermeasure unit can input the user's social media activity into a generation AI and have the generation AI execute the suggestion of countermeasures.

[0138] When taking countermeasures, the countermeasure unit can customize the countermeasure method by reflecting the user's past feedback. The countermeasure unit, for example, customizes the countermeasure method based on the user's past feedback to provide efficient learning. For example, the countermeasure unit customizes the countermeasure method based on the user's past feedback. The countermeasure unit can also select an appropriate countermeasure method by reflecting the user's feedback. For example, the countermeasure unit selects an appropriate countermeasure method by reflecting the user's feedback. The countermeasure unit can also adjust the countermeasure method by taking the user's past feedback into account to provide efficient learning. For example, the countermeasure unit adjusts the countermeasure method by taking the user's past feedback into account. In this way, the countermeasure method can be customized by reflecting the user's past feedback, enabling efficient learning. Some or all of the above-described processing in the countermeasure unit may be performed using, or without, AI. For example, the countermeasure unit can input the user's past feedback into a generation AI and cause the generation AI to customize the countermeasure method. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, answer collection unit, weak area analysis unit, and preparation unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects past exam questions using the control unit 46A of the smart device 14 and analyzes the collected data using the specific processing unit 290 of the data processing device 12. The generation unit generates questions tailored to the actual exam using the specific processing unit 290 of the data processing device 12. The answer collection unit collects the user's answer data using the control unit 46A of the smart device 14, and the weak area analysis unit identifies the user's weak areas using the specific processing unit 290 of the data processing device 12. The preparation unit performs intensive preparation using the specific processing unit 290 of the data processing device 12. The collection unit can analyze the user's emotions and adjust the timing of collecting past exam questions based on the analyzed emotions. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, answer collection unit, weak area analysis unit, and countermeasures 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 collection unit collects past exam questions using the control unit 46A of the smart glasses 214 and analyzes the collected data using the specific processing unit 290 of the data processing device 12. The generation unit generates questions that are in line with the actual exam using the specific processing unit 290 of the data processing device 12. The answer collection unit collects the user's answer data using the control unit 46A of the smart glasses 214, and the weak area analysis unit identifies the user's weak areas using the specific processing unit 290 of the data processing device 12. The countermeasures unit performs intensive countermeasures using the specific processing unit 290 of the data processing device 12. The collection unit can analyze the user's emotions and adjust the timing of collecting past exam questions based on the analyzed emotions. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, answer collection unit, weak area analysis unit, and countermeasures unit, is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects past exam questions using the control unit 46A of the headset type terminal 314, and analyzes the collected data using the specific processing unit 290 of the data processing device 12. The generation unit generates questions that are in line with the actual exam using the specific processing unit 290 of the data processing device 12. The answer collection unit collects the user's answer data using the control unit 46A of the headset type terminal 314, and the weak area analysis unit identifies the user's weak areas using the specific processing unit 290 of the data processing device 12. The countermeasures unit performs intensive countermeasures using the specific processing unit 290 of the data processing device 12. The collection unit can analyze the user's emotions and adjust the timing of collecting past exam questions based on the analyzed emotions. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, answer collection unit, weak area analysis unit, and countermeasures unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects past exam questions using the control unit 46A of the robot 414 and analyzes the collected data using the specific processing unit 290 of the data processing device 12. The generation unit generates questions that are appropriate for the actual exam using the specific processing unit 290 of the data processing device 12. The answer collection unit collects the user's answer data using the control unit 46A of the robot 414, and the weak area analysis unit identifies the user's weak areas using the specific processing unit 290 of the data processing device 12. The countermeasures unit performs intensive countermeasures using the specific processing unit 290 of the data processing device 12. The collection unit can analyze the user's emotions and adjust the timing of collecting past exam questions based on the analyzed emotions.

[0139] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0140] The qualification exam study support system may further include an environment monitoring unit that monitors the user's study environment. The environment monitoring unit monitors the user's study environment (e.g., lighting, noise level, temperature, etc.) in real time and provides advice to provide an optimal study environment. For example, if the lighting is dim, the environment monitoring unit may suggest to the user to turn up the lights. Also, if the noise level is high, the environment monitoring unit may suggest to the user to move to a quieter place. Furthermore, if the temperature is inappropriate, the environment monitoring unit may suggest to the user to adjust the temperature appropriately. This allows the user to study efficiently in an optimal study environment.

[0141] The collection unit can collect the latest research papers and articles related to a specific field based on the user's learning history. For example, if the user is interested in a specific field, the collection unit can collect the latest research papers related to that field and provide them to the user. The collection unit can also collect research papers of appropriate difficulty level according to the user's learning progress. Furthermore, the collection unit can collect balanced research papers taking into account the user's strong and weak areas. This allows the user to understand the latest research trends and gain deeper knowledge.

[0142] The analysis unit can estimate the user's emotions and adjust the method of providing feedback on the analysis results based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit can provide simple, positive feedback. If the user is relaxed, the analysis unit can provide detailed analysis results to deepen understanding. Furthermore, if the user is concentrating, the analysis unit can provide feedback that focuses on the key points to promote efficient learning. This makes it possible to maximize learning efficiency by providing feedback that corresponds to the user's emotions.

[0143] The generator can customize the question format according to the user's learning style. For example, for a user who prefers visual learning, questions that make extensive use of diagrams and graphs can be generated. For a user who prefers auditory learning, questions that include audio commentary can be generated. Furthermore, for a user who prefers practical learning, questions that use real-life examples can be generated. This allows for efficient learning by providing questions that suit the user's learning style.

[0144] The answer collection unit can estimate the user's emotions and adjust the answer data collection method based on the estimated user emotions. For example, if the user is feeling stressed, the answer collection unit can simplify the collection method to reduce the user's burden. Also, if the user is relaxed, detailed answer data can be collected and a deeper analysis can be performed. Furthermore, if the user is concentrating, balanced answer data can be collected to promote efficient learning. Thus, by providing a collection method that corresponds to the user's emotions, learning efficiency can be maximized.

[0145] The weak area analysis unit can provide additional learning resources related to a specific area based on the user's learning history. For example, if the user has many weak points in a specific area, the weak area analysis unit can provide additional practice questions or explanatory videos related to that area. It can also provide learning resources of an appropriate level of difficulty according to the user's learning progress. Furthermore, it can provide balanced learning resources taking into account the user's strong and weak areas. This allows the user to efficiently overcome their weak areas.

[0146] The countermeasure unit can estimate the user's emotions and adjust the content of the countermeasures based on the estimated user's emotions. For example, if the user is feeling stressed, the countermeasure unit can provide countermeasures that will help the user relax. Also, if the user is relaxed, the countermeasure unit can provide countermeasures that will increase concentration. Furthermore, if the user is concentrating, the countermeasure unit can provide efficient countermeasures. In this way, by providing countermeasures that correspond to the user's emotions, it is possible to maximize the efficiency of learning.

[0147] The countermeasures unit can customize a study plan for a specific subject based on the user's study history. For example, if the user has many weak points in a specific subject, the countermeasures unit can provide a study plan that focuses on that subject. The countermeasures unit can also provide a study plan with an appropriate level of difficulty according to the user's study progress. Furthermore, the countermeasures unit can provide a balanced study plan that takes into account the user's strong and weak subjects. This allows the user to study efficiently.

[0148] The collection unit can estimate the user's emotions and adjust the difficulty of the past questions to be collected based on the estimated user's emotions. For example, if the user is feeling stressed, the collection unit can prioritize collecting easier past questions, thereby reducing the user's burden. Also, if the user is relaxed, the collection unit can prioritize collecting more difficult past questions, thereby increasing the user's motivation to take on new challenges. Furthermore, if the user is concentrating, a balanced set of past questions can be collected, promoting efficient learning. This makes it possible to maximize learning efficiency by providing past questions that correspond to the user's emotions.

[0149] The generator can customize the method of generating questions related to a specific field based on the user's learning history. For example, if the user has many questions in a specific field that they are weak at, the generator can generate questions that focus on that field. It can also generate questions of an appropriate level of difficulty according to the user's learning progress. Furthermore, it can generate balanced questions taking into account the user's strong and weak fields. This allows the user to study efficiently.

[0150] The processing flow of the second embodiment will be briefly explained below.

[0151] Step 1: The collection department collects past exam questions. Past exam questions include those for a specific exam or a specific year. The collection department collects exam questions from the past five years and can collect past exam questions from public databases on the Internet or provided by the exam organizer. The collected past exam questions are stored in a database. Step 2: The analysis unit analyzes the past exam questions collected by the collection unit. The analysis is based on the analysis of question trends, extraction of frequently asked questions, evaluation of difficulty, classification of questions, and analysis of question format. This identifies the question trends, frequently asked questions, difficulty level, and question format of past exam questions. Step 3: The generator generates questions based on the analysis results obtained by the analyzer, and is designed to fit the actual exam. Question generation is based on the difficulty and format of the questions, and new questions are created with reference to past exam trends, frequently asked questions, and question formats. Step 4: The answer collection unit collects the user's answer data. The answer data includes the correct answer rate, answer time, etc., and data on the questions answered by the user and the answer history are collected. The answer collection unit can collect the answer data using voice recognition technology, text analysis technology, and image recognition technology. Step 5: The weak area analysis unit analyzes the answer data collected by the answer collection unit and identifies the user's weak areas. The weak areas are identified based on the analysis of the answer data, evaluation of the correct answer rate, and analysis of the answer history. This identifies questions that the user frequently gets wrong and areas where the correct answer rate is low. Step 6: The countermeasures unit implements intensive countermeasures based on the weak areas identified by the weak area analysis unit. The intensive countermeasures are implemented by providing additional practice problems and explanatory videos, and providing an individual study plan. The countermeasures unit provides explanatory videos and practice problems related to the identified weak areas, and creates an individual study plan and provides it to the user.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0157] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0172] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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).

[0178] 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.

[0179] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0188] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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).

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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).

[0209] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0210] 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."

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0222] 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.

[0223] [Explanation of symbols]

[0224] 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 collection department that collects past exam questions, an analysis unit that analyzes past questions collected by the collection unit; a generation unit that generates test questions based on the analysis results obtained by the analysis unit; an answer collection unit that collects answer data of users; a weak area analysis unit that analyzes the answer data collected by the answer collection unit and identifies the weak points of the user; a countermeasure unit that takes measures based on the weaknesses identified by the weak area analysis unit. A system characterized by:

2. The collecting unit Collect past exam questions 2. The system of claim 1.

3. The analysis unit Analyzing the question patterns of past exam questions 2. The system of claim 1.

4. The generation unit Generate questions based on exam questions 2. The system of claim 1.

5. The answer collection unit Collect user response data 2. The system of claim 1.

6. The weak area analysis unit Analyze user answer data and identify weaknesses 2. The system of claim 1.

7. The countermeasure unit Take action based on identified weaknesses 2. The system of claim 1.

8. The countermeasure unit Providing appropriate learning plans for each user 2. The system of claim 1.

Images