System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting information of a target educational institution; means for inputting a learning result of a user; means for acquiring past question information of the educational institution; means for collating the learning result with the past question information to identify a weak point area; means for generating a customized learning plan based on the weak point area; and means for providing the learning plan.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional learning support systems have difficulty comprehensively analyzing each individual's learning achievements and the question trends of a specific educational institution, and providing individually optimized learning plans based on that analysis. As a result, users are unable to effectively overcome their weak areas, resulting in inefficient learning. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means.

[0006] a means for inputting information about the target educational institution;

[0007] a means for inputting the user's learning outcomes;

[0008] A means for acquiring information on past exams from the educational institution;

[0009] A means for comparing the learning results with the past exam information and identifying weak areas;

[0010] means for generating a customized learning plan based on said weakness areas;

[0011] means for providing said lesson plan;

[0012] This system makes it possible to provide each individual with an optimized study plan based on past exam information and current learning results.

[0013] This allows users to effectively overcome their weak areas and study efficiently.

[0014] A "target educational institution" refers to a particular school or university that the user is hoping to get into.

[0015] "User's learning results" is information indicating the results, scores, and academic level of tests and mock exams that the user has taken so far.

[0016] "Past exam information" refers to historical data such as past entrance exam questions, question trends, and answers from designated educational institutions.

[0017] "Weakness areas" refer to areas of knowledge or skills in which the user lacks the passing standards of the educational institution he or she is aiming for.

[0018] A "customized study plan" is a study plan that includes exercises, study schedules, and materials specifically designed to address a user's weaknesses. [Brief explanation of the drawings]

[0019] [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. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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, a 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), and an APU (Accelerated Processing Unit).

[0023] 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.

[0024] 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.

[0025] 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), Bluetooth (registered trademark), etc.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] 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.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. 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 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] The learning support system of the present invention provides a study plan that will enable users to efficiently pass the entrance exams for their target educational institutions. The system starts when the user inputs the user's target educational institution and current learning results, identifies the user's weak areas based on past exam information, and provides a study plan that addresses those areas.

[0041] System Overview

[0042] When a user logs in to the system using a device (e.g., a PC or smartphone), the user inputs their target educational institution and current learning outcomes. The system then retrieves past exam information from the target educational institution from a database and compares it with the user's learning outcomes to identify weak areas. It then generates a customized learning plan based on the identified weak areas and displays it on the device.

[0043] Details of each step

[0044] 1. Input method for the target educational institution

[0045] The user inputs the name of the educational institution they are interested in into an input form on their terminal. For example, they input "Tokyo University."

[0046] 2. Means for inputting user learning results

[0047] The user also inputs their current test results (e.g., mock exam scores) into the input form on the terminal. For example, they input 80 points for math, 72 points for English, and 65 points for Japanese.

[0048] 3. How to obtain information on past exam questions

[0049] The server retrieves past exam questions and answers from the database of the target educational institution. For example, it retrieves information on questions from the University of Tokyo for the past 10 years.

[0050] 4. A means of comparing learning outcomes with past exam information

[0051] The server compares the user's learning outcomes with the acquired information on past exam questions and identifies the user's weak areas (e.g., "calculus").

[0052] 5. A way to generate a customized study plan

[0053] The server generates a personalized study plan for the user based on the identified weaknesses, for example, a study plan that includes exercises and explanations for "calculus."

[0054] 6. Means of providing study plans

[0055] The terminal displays the study plan received from the server to the user, who then studies based on it.

[0056] Specific examples

[0057] Suppose a user sets the educational institution they are aiming for as "University of Tokyo" and inputs their current mock exam results as 80 points in mathematics, 72 points in English, and 65 points in Japanese. The server retrieves exam questions from the database for the past 10 years for the University of Tokyo and compares them with the user's mock exam results. As a result, it is determined that the user's weak point in mathematics is "calculus." The server then generates a study plan for "calculus" that includes practice questions and explanations, and displays it on the device. The user then uses this plan to study independently and overcome their weak points.

[0058] As described above, the learning support system of the present invention provides effective and individually optimized learning plans to users, thereby efficiently supporting learning aimed at achieving goals.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] A user logs into the system

[0062] The user enters their ID and password and clicks the login button. The system checks the user's authentication information against the database and allows them to log in.

[0063] Step 2:

[0064] Setting goals

[0065] The user enters the name of the educational institution they are interested in. For example, they enter "Educational Institution A." The device sends this information to the server.

[0066] Step 3:

[0067] Input of learning outcomes

[0068] The user inputs their current learning results (for example, mock test scores). For example, they input 80 points for math, 72 points for English, and 65 points for Japanese. The terminal also sends this data to the server.

[0069] Step 4:

[0070] Obtaining past exam information

[0071] The server accesses the database and retrieves the past exam information of the target educational institution. For example, it retrieves the past 10 years of exam information of educational institution A.

[0072] Step 5:

[0073] Analysis of learning outcomes

[0074] The server analyzes the learning results received from the user. It analyzes the scores for each subject (e.g., Mathematics 80 points, English 72 points, Japanese 65 points) according to the data format.

[0075] Step 6:

[0076] Comparison with the standards of the target educational institution

[0077] The server compares the user's learning results with the passing standards of the target educational institution (e.g., 90 points for math, 85 points for English, and 80 points for Japanese). It calculates the score difference and identifies specific weaknesses. For example, it analyzes that math is -10 points, English is -13 points, and Japanese is -15 points.

[0078] Step 7:

[0079] Identifying weak areas

[0080] The server analyzes detailed problem areas for each subject and identifies areas where students are particularly low-scoring (e.g., calculus).

[0081] Step 8:

[0082] Generate a customized study plan

[0083] Based on the identified weaknesses, the server selects appropriate exercises and explanations and generates a personalized study plan for the user, including calculus exercises and explanations, for example.

[0084] Step 9:

[0085] Submitting and Viewing Learning Plans

[0086] The server sends the generated study plan to the device. The device displays the study plan to the user. The user then proceeds with their study based on the provided practice questions and explanations.

[0087] Step 10:

[0088] Learning implementation and feedback

[0089] The user studies based on the study plan displayed on the device. After completing the study, the user inputs the results into the device and sends them back to the server. The server then analyzes the results again and generates a new study plan.

[0090] These are the main processing steps in the program of the present invention, which allow users to efficiently advance their studies and get closer to their target educational institution.

[0091] Example 1

[0092] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0093] Conventional learning systems have difficulty providing an optimal learning plan tailored to each user's individual learning outcomes and desired educational institution, making it difficult to study efficiently. In particular, they lacked a means to identify specific areas of weakness and automatically generate an appropriate learning plan based on those areas. This resulted in a decrease in users' learning efficiency and a decrease in the chances of passing the entrance exam for the desired educational institution.

[0094] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0095] In this invention, the server includes means for a user to input information about a target educational institution using a communication terminal, means for inputting the user's learning outcomes through the communication terminal, means for retrieving information about past exams of the educational institution from a database, means for comparing the learning outcomes with the past exam information on the server and identifying the user's weak areas, means for generating a customized study plan based on the identified weak areas using the generative AI model, and means for providing the study plan to the communication terminal, thereby making it possible to automatically provide an optimal study plan for each user.

[0096] A "user" is an individual who uses the learning support system and is a subject who studies with the aim of passing the entrance exam to a target educational institution.

[0097] A "communication terminal" is an electronic device that a user uses to access the learning support system, and specifically includes a personal computer or smartphone.

[0098] The term "server" refers to a central control device of the learning support system, and is a computer device that has the function of processing information input by users and generating and providing learning plans.

[0099] A "database" is a system that systematically stores information on past exam questions from educational institutions and users' learning outcomes, and allows data to be searched and retrieved as needed.

[0100] A "generative AI model" is an algorithm or program that uses machine learning and artificial intelligence technology to automatically generate optimal study plans based on a user's learning data and goals.

[0101] "Target educational institution information" is information related to the name of a particular educational institution or exam that the user aims to pass.

[0102] "Learning results" refers to evaluation data obtained as a result of learning, such as the results and scores of tests and mock tests that the user has taken in the past.

[0103] "Past exam information" refers to data on exam questions and answers previously administered by educational institutions.

[0104] "Weak areas" refer to areas or items in which the user has particularly insufficient understanding during their studies, and are areas that need to be supplemented.

[0105] A "Customized Study Plan" is a collection of study content and materials specifically designed to meet a user's individual weaknesses.

[0106] MODE FOR CARRYING OUT THE INVENTION

[0107] The learning support system of the present invention provides a learning plan that will enable a user to efficiently pass the entrance exam for a target educational institution. An embodiment of this system will be specifically described below.

[0108] The system begins when a user accesses the system using a communication device (such as a PC or smartphone) and enters information about the educational institution of interest and their current learning outcomes. Based on this information, the server retrieves the institution's past exam information from a database and compares it with the user's learning outcomes to identify areas of weakness. The system then uses a generative AI model to generate a customized learning plan that addresses the user's weaknesses and provides it to the communication device.

[0109] The server functions using the following main hardware and software:

[0110] 1. Hardware:

[0111] Server body (high-performance CPU, memory, storage)

[0112] Communication infrastructure (Internet connection, network equipment)

[0113] Database Server

[0114] 2. Software:

[0115] Database management system (e.g., MySQL (registered trademark), PostgreSQL)

[0116] Web server software (e.g., Apache (registered trademark), Nginx)

[0117] Programming language (e.g. Python, JavaScript (registered trademark))

[0118] Generative AI models (e.g., GPT-3 (registered trademark), BERT)

[0119] Detailed explanation of each step

[0120] 1. The user logs in and enters the information for the target educational institution

[0121] A user logs into the system using a communication terminal and inputs the target educational institution (e.g., "University of Tokyo") through an input form on a web browser.

[0122] Example: Set "University of Tokyo" as the target educational institution.

[0123] 2. Input of user learning outcomes

[0124] The user uses the communication terminal to input the current learning results (e.g., mock exam scores), for example, 80 points for mathematics, 72 points for English, and 65 points for Japanese.

[0125] Example: Enter 80 points for math, 72 points for English, and 65 points for Japanese.

[0126] 3. Obtaining past exam information

[0127] The server accesses the database and retrieves information on past exam questions from the target educational institution, such as the University of Tokyo's exam questions and answers from the past 10 years.

[0128] Software used: Database management system (MySQL, PostgreSQL)

[0129] 4. Matching learning outcomes with exam information

[0130] The server compares the acquired test information with the user's learning results and identifies the user's weak areas. Specifically, it uses an algorithm to compare mock test results with past test trends.

[0131] Software used: Data analysis tool (Python)

[0132] 5. Generate a customized study plan

[0133] The server uses a generative AI model to generate a study plan based on the identified weaknesses. For example, if calculus is a weakness in mathematics, the server generates prompts to create a study plan that includes practice problems and explanations for this area.

[0134] Software used: Generative AI model (GPT-3)

[0135] 6. Providing study plans

[0136] The generated study plan is provided to the user via a communication terminal, and the user can proceed with their studies based on the provided plan.

[0137] Software used: Web server software (Apache, Nginx)

[0138] Prompt Sentence Examples

[0139] Here is an example of a prompt for a generative AI model:

[0140] "Create a plan that includes detailed explanations and practice questions for calculus."

[0141] As a result, the learning support system of the present invention can provide effective learning plans tailored to the weak points of each individual user, and support the student in passing the entrance exams to their target educational institutions.

[0142] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0143] Step 1:

[0144] User logs in and enters information about the target institution

[0145] Specific behavior:

[0146] Users log in to the system using a communication device such as a PC or smartphone. They enter their user ID and password into the login screen on their web browser and press the login button. If authentication is successful, the dashboard is displayed. Next, they enter the name of their target educational institution from the dashboard (e.g., "University of Tokyo").

[0147] input:

[0148] User ID, password, name of the target educational institution

[0149] output:

[0150] User login status, name of target educational institution

[0151] Step 2:

[0152] Input of user learning outcomes

[0153] Specific behavior:

[0154] The user also uses the communication terminal to input their current learning results (e.g., mock test scores), enter specific score information (e.g., 80 points for mathematics, 72 points for English, 65 points for Japanese) into the input form on the dashboard, and press the send button.

[0155] input:

[0156] Current learning results (e.g., 80 points in mathematics, 72 points in English, 65 points in Japanese)

[0157] output:

[0158] User learning outcome data

[0159] Step 3:

[0160] Obtaining past exam information

[0161] Specific behavior:

[0162] The server accesses the database to obtain information on past exam questions from the target educational institution. Specifically, it issues a database query to obtain, for example, the past 10 years of exam questions and answers from the University of Tokyo. This allows it to collect information such as past exam question trends and frequently asked questions.

[0163] input:

[0164] Name of the target educational institution

[0165] output:

[0166] Past exam information

[0167] Step 4:

[0168] Matching learning outcomes with exam information

[0169] Specific behavior:

[0170] The server compares the acquired past exam information with the user's learning outcomes. Using data analysis tools, it compares the user's grades in each subject with past exam trends and uses statistical methods and algorithms to identify the user's weak areas (e.g., "calculus" in mathematics).

[0171] input:

[0172] Past exam information, user learning outcome data

[0173] output:

[0174] Identified Weak Areas

[0175] Step 5:

[0176] Generate a customized study plan

[0177] Specific behavior:

[0178] The server generates a customized study plan based on the identified weak areas. It uses a generative AI model to automatically generate a study plan that focuses on the weak areas. For example, a study plan including detailed explanations and practice problems for "calculus" can be generated by passing the prompt "Please create a plan including detailed explanations and practice problems for calculus" to the AI ​​model.

[0179] input:

[0180] Identified weak areas, generated AI model prompt sentences

[0181] output:

[0182] Customized Study Plan

[0183] Step 6:

[0184] Providing study plans

[0185] Specific behavior:

[0186] The server sends the generated study plan to the communication device. The communication device then displays the received study plan to the user in a visually easy-to-understand format. For example, the study plan may be displayed in list format on the user's dashboard, with links and explanations provided. The user can use this information to proceed with their studies.

[0187] input:

[0188] Customized Study Plan

[0189] output:

[0190] The learning plan provided to the user

[0191] (Application example 1)

[0192] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0193] Conventional learning support systems simply provide learning plans and do not provide sufficient support for users to efficiently achieve their goals. In particular, there is a lack of learning support tailored to users of online payment services, and a system that can effectively improve payment-related knowledge and skills is needed.

[0194] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0195] In this invention, the server includes a means for inputting information about a target educational institution, a means for inputting a user's learning outcomes, a means for acquiring information about past exams from the educational institution, a means for comparing the learning outcomes with the past exam information and identifying weak areas, a means for generating a customized study plan based on the weak areas, a means for providing the study plan, and a means for sending a notification to a user terminal based on the study plan, thereby enabling support for the user to study efficiently and achieve their goals more quickly.

[0196] "Means for inputting target educational institution information" refers to a device or interface that allows a user to input the name and details of a particular educational institution that the user is targeting.

[0197] "Means for inputting user learning results" refers to a device or interface that allows users to input the results of their learning so far, test scores, etc.

[0198] "Means for obtaining past exam information" refers to the devices and processes for obtaining past exam questions and related information of the designated educational institution from a database.

[0199] "Means for comparing learning outcomes with past exam information and identifying weak areas" refers to devices and processes that compare and analyze the learning outcomes entered by the user with past exam information and identify in which areas or items the user has weaknesses.

[0200] "Means for generating a customized study plan" refers to a device or software for creating an optimized study plan for a user based on identified weaknesses.

[0201] The "means for providing a study plan" refers to a device or interface for providing the generated study plan to the user.

[0202] The "means for sending a notification to a user terminal based on a study plan" refers to a device or process for sending a notification about the created study plan to a terminal used by a user.

[0203] "Means for storing in a database" refers to the devices and processes for storing the acquired past exam information and other related data in a database.

[0204] "Practice problems and their explanations" refers to a set of problems that correspond to the user's weak areas and content that includes explanations for the problems.

[0205] The system of the present invention provides a customized study plan based on past exam information and the user's learning results so that users who are targeting educational institutions can study effectively. The specific configuration of this system is described below.

[0206] System configuration

[0207] The user first uses a terminal to input information about the educational institution of interest and their current learning outcomes, which are then processed by the server.

[0208] 1. Input Method

[0209] An input form is provided on the device as a means of inputting information about the target educational institution (e.g., "a particular university"), as well as the user's current learning achievements (e.g., mock exam results).

[0210] 2. Data Acquisition Method

[0211] The server retrieves the past exam information of the target educational institution from the database. One way to do this is to use an API to import past exam data.

[0212] 3. Verification Method

[0213] The system compares the learning outcomes with the acquired information on past exam questions to identify the user's weak areas. This process uses machine learning algorithms. Specifically, it uses libraries such as TfidfVectorizer and cosine_similarity.

[0214] 4. Learning plan generation tool

[0215] The server generates a customized study plan based on the identified weaknesses, which includes exercises and explanations that address the weaknesses.

[0216] 5. Means of providing study plans

[0217] The generated learning plan is then delivered to the user's device via notifications and a dashboard.

[0218] Specific examples of hardware and software used

[0219] Devices: PC, smartphone, tablet

[0220] Server: Cloud-based server, on-premise server

[0221] software:

[0222] Database management systems: MySQL, PostgreSQL

[0223] API: RESTful API

[0224] Machine learning library: Scikit-learn

[0225] Notification system: Firebase Cloud Messaging (FCM)

[0226] Specific examples of processing

[0227] Suppose a user is aiming for a specific educational institution (e.g., "specific university") and enters their current mock exam scores of 80 points in mathematics, 72 points in English, and 65 points in Japanese. The server retrieves exam questions from the database for the specific university over the past 10 years and compares them with the user's mock exam scores. As a result, it is determined that the user's weak point in mathematics is "calculus." The server then generates a study plan including practice questions and explanations for "calculus" and sends a notification to the user's device.

[0228] Prompt Sentence Examples

[0229] markdown

[0230] You are a tool that helps business people generate customized study plans to improve their skills related to online payments. Based on the user's goals and current level of understanding, we will compare past exam information to identify weak points and provide the optimal study plan. Please provide the following information:

[0231] Goal: Efficient online payment processing

[0232] Current level of understanding: Understands basic payment processing procedures, but weak in advanced troubleshooting

[0233] By using this prompt, the AI ​​can be informed of the user's specific situation and generate the optimal learning plan.

[0234] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0235] Step 1:

[0236] The user uses a terminal to input information about the educational institution of their choice and their current learning outcomes. The input information includes the name of the educational institution of their choice and the user's mock exam results. This allows the user to clarify their learning goals and current status, laying the foundation for the system to perform the necessary data processing.

[0237] Step 2:

[0238] The server retrieves information about the educational institution's past exam questions from a database based on the information about the educational institution entered by the user. Specifically, it queries the database using the name of the educational institution to retrieve past exam questions and their answers. The information retrieved in this process includes question patterns and frequently asked questions from past exams.

[0239] Step 3:

[0240] The server compares the learning outcomes entered by the user with the acquired information on past exam questions. The learning outcomes are mock test scores, and the acquired information on past exam questions. Specifically, the server uses TfidfVectorizer to vectorize the learning outcomes and exam questions, and calculates the similarity between each item using cosine_similarity. This identifies the user's weak areas.

[0241] Step 4:

[0242] The server generates a customized study plan based on the identified weak areas. The generated study plan includes exercises and explanations corresponding to the identified weak areas. For example, if "calculus" in mathematics is identified as a weak area, the server selects exercises and explanations related to "calculus." This allows the user to efficiently overcome their weak areas.

[0243] Step 5:

[0244] The server provides the generated study plan to the user's device. Specifically, the content of the study plan is sent to the user's device in the form of a notification. The notification includes an overview of the study plan and links to practice questions. This allows the user to proceed with their studies based on the provided study plan.

[0245] Step 6:

[0246] The user studies based on the provided study plan and carries out learning activities to overcome their weaknesses. By inputting the new learning results obtained during this process back into the system, the system can provide an even more accurate study plan. This allows for continuous learning support.

[0247] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0248] The learning support system of the present invention provides a learning plan that will enable a user to efficiently pass the entrance exam for a target educational institution. This system incorporates an emotion engine that recognizes the user's emotions, and is able to provide a flexible learning plan according to the user's emotional state.

[0249] System Overview

[0250] When a user logs into the system using a terminal, they input their target educational institution and current learning outcomes. The system then retrieves past exam information from the target educational institution from a database and compares it with the user's learning outcomes to identify weak areas. It then generates a customized learning plan based on the identified weak areas and displays it on the terminal. An emotional engine then recognizes the user's emotional state and adjusts the difficulty level and feedback of the learning plan.

[0251] Details of each step

[0252] 1. Input method for the target educational institution

[0253] The user enters the name of the target educational institution into an input form on the terminal, for example, "Educational Institution A." The terminal then sends this information to the server.

[0254] 2. Means of inputting learning outcomes

[0255] The user inputs their current learning results (for example, mock exam scores). For example, they input 80 points for math, 72 points for English, and 65 points for Japanese. The terminal then sends this data to the server.

[0256] 3. How to obtain information on past exam questions

[0257] The server accesses the database and retrieves the past exam information of the target educational institution. For example, it retrieves the past 10 years of exam information of educational institution A.

[0258] 4. Means of analyzing learning outcomes

[0259] The server analyzes the learning results received from the user. It analyzes the scores for each subject (e.g., Mathematics 80 points, English 72 points, Japanese 65 points) according to the data format.

[0260] 5. Compare with the standards of your target educational institution

[0261] The server compares the user's learning results with the passing standards of the target educational institution (e.g., 90 points for math, 85 points for English, and 80 points for Japanese). It calculates the score difference and identifies specific weaknesses. For example, it analyzes that math is -10 points, English is -13 points, and Japanese is -15 points.

[0262] 6. Identifying Weak Areas

[0263] The server analyzes detailed problem areas for each subject and identifies areas where students are particularly low-scoring (e.g., calculus).

[0264] 7. Emotion Engine Recognition

[0265] The device collects data such as the user's facial expressions, voice, and input speed, and the emotion engine analyzes this data to recognize the user's emotional state (e.g., stress, joy, fatigue).

[0266] 8. Generate a customized study plan

[0267] Based on the identified weaknesses, the server selects appropriate exercises and explanations and generates a personalized study plan for the user, including calculus exercises and explanations, for example.

[0268] Based on the recognition results of the emotion engine, the difficulty level of the exercises is adjusted appropriately. For example, if the user is feeling stressed, the difficulty level is lowered and easier exercises are provided.

[0269] 9. Providing study plans

[0270] The server sends the generated learning plan to the terminal, which displays the learning plan to the user, who then proceeds with their learning based on the plan.

[0271] 10. Providing Feedback

[0272] Based on the results of the emotion engine, it provides positive feedback and advice to the user, for example, if the user feels a sense of accomplishment, it suggests next steps.

[0273] Specific examples

[0274] Suppose a user sets their target educational institution as "Educational Institution A" and inputs their current mock exam results as 80 points in mathematics, 72 points in English, and 65 points in Japanese. The server retrieves exam questions from the past 10 years of Institution A from the database and compares them with the user's mock exam results. As a result, it is determined that the user's weak point in mathematics is "calculus." Next, if the emotion engine recognizes the user's emotional state and determines that the user is a little tired, the server generates a study plan including simple "calculus" practice problems and explanations and displays it on the device. The user studies based on this, and when they feel more refreshed, they can tackle more difficult problems.

[0275] As described above, the learning support system of the present invention provides an individually optimized learning plan taking into consideration the emotional state of the user, thereby realizing effective and efficient learning.

[0276] The processing flow will be explained below.

[0277] Step 1:

[0278] A user logs into the system

[0279] The user enters their ID and password and clicks the login button. The system checks the user's authentication information against the database and allows them to log in.

[0280] Step 2:

[0281] Setting goals

[0282] The user enters the name of the educational institution they are interested in. For example, they enter "Educational Institution A." The device sends this information to the server.

[0283] Step 3:

[0284] Input of learning outcomes

[0285] The user inputs their current learning results (for example, mock test scores). For example, they input 80 points for math, 72 points for English, and 65 points for Japanese. The terminal then sends this data to the server.

[0286] Step 4:

[0287] Obtaining past exam information

[0288] The server accesses the database and retrieves the past exam information of the target educational institution. For example, it retrieves the past 10 years of exam information of educational institution A.

[0289] Step 5:

[0290] Analysis of learning outcomes

[0291] The server analyzes the learning results received from the user. It analyzes the scores for each subject (e.g., Mathematics 80 points, English 72 points, Japanese 65 points) according to the data format.

[0292] Step 6:

[0293] Comparison with the standards of the target educational institution

[0294] The server compares the user's learning results with the passing standards of the target educational institution (e.g., 90 points for math, 85 points for English, and 80 points for Japanese). It calculates the score difference and identifies specific weaknesses. For example, it analyzes that math is -10 points, English is -13 points, and Japanese is -15 points.

[0295] Step 7:

[0296] Identifying weak areas

[0297] The server analyzes detailed problem areas for each subject and identifies areas where students are particularly low-scoring (e.g., calculus).

[0298] Step 8:

[0299] Emotion Engine Recognition

[0300] The device collects data such as the user's facial expressions, voice, and input speed, and the emotion engine analyzes this data to recognize the user's emotional state (e.g., stress, joy, fatigue).

[0301] Step 9:

[0302] Generate a customized study plan

[0303] The server selects appropriate exercises and explanations based on the identified weaknesses and generates a personalized learning plan for the user. For example, it may include calculus exercises and explanations. Based on the recognition results of the emotion engine, the difficulty of the exercises is adjusted appropriately. For example, if the user is feeling stressed, the difficulty level is lowered to provide easier exercises.

[0304] Step 10:

[0305] Providing study plans

[0306] The server sends the generated learning plan to the terminal, which displays the learning plan to the user, who then proceeds with their learning based on the plan.

[0307] Step 11:

[0308] Providing feedback

[0309] The device will provide the user with positive feedback and advice based on the results of the emotion engine. For example, if the user feels a sense of accomplishment, it will suggest the next step.

[0310] Step 12:

[0311] Learning implementation and evaluation

[0312] The user studies based on the study plan displayed on the device. After completing the study, the user inputs the results into the device and sends them back to the server. The server then analyzes the results again and generates a new study plan.

[0313] The above are the main processing steps in the learning support system of the present invention. These steps allow the user to efficiently progress through their studies and get closer to their target educational institution.

[0314] Example 2

[0315] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0316] Conventional learning support systems can provide a customized learning plan based on a user's learning achievements and areas of weakness, but lack the functionality to adjust the content of the learning plan and feedback based on the user's emotional state. This creates a problem of reduced learning efficiency when a user continues learning while feeling stressed or fatigued. The present invention aims to solve this problem by providing effective and efficient learning support that takes into account the user's emotional state.

[0317] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for inputting information about a target educational institution, a means for inputting the user's learning outcomes, a means for acquiring information about past questions from the educational institution, a means for comparing the learning outcomes with the past question information and identifying weak areas, a means for generating a customized study plan based on the weak areas, a means for adjusting the content and feedback of the study plan using an emotion engine that recognizes the user's emotions, and a means for providing the study plan. This makes it possible to provide an individually optimized study plan taking the user's emotional state into consideration.

[0318] 1. "Target educational institution" refers to the educational institution that the user aims to be accepted into, including schools, universities, and other educational facilities for further education or qualification acquisition.

[0319] 2. "Learning outcomes" refers to data that indicates the progress and results of a user's learning, such as the grades achieved so far, mock test scores, and assignment evaluations.

[0320] 3. "Past exam information" refers to information such as the contents of exam questions and mock exams previously used by the target educational institution, as well as answers and explanations.

[0321] 4. "Weakness Areas" refers to areas or topics in learning that need improvement, as identified based on user learning outcomes.

[0322] 5. "Customized Study Plan" means a plan that includes study assignments, exercises, and explanations that is individually created based on a User's learning achievements and areas of weakness.

[0323] 6. An "emotion engine" is software or a module that analyzes data such as a user's facial expressions, voice, and input speed to recognize the user's emotional state.

[0324] 7. "Feedback" refers to advice, evaluations, comments on learning progress, etc. provided to users by the system.

[0325] 8. A "database" is a system or storage device for structuring and storing information on past exam questions, learning outcomes, user information, etc.

[0326] MODE FOR CARRYING OUT THE INVENTION

[0327] The learning support system of the present invention provides a learning plan that will enable a user to efficiently pass the entrance exam for a target educational institution. This system incorporates an emotion engine that recognizes the user's emotions, and is able to provide a flexible learning plan that corresponds to the user's emotional state.

[0328] System Overview

[0329] When a user logs into the system using a terminal, they first enter their target educational institution and current learning achievements. Based on this information, the system retrieves past exam information from the target educational institution from a database and compares it with the user's learning achievements to identify weak areas. It then generates a customized learning plan based on the identified weak areas and displays it on the terminal. At this time, an emotional engine recognizes the user's emotional state and adjusts the difficulty level and feedback of the learning plan accordingly.

[0330] Hardware and software used

[0331] Hardware: devices such as computers, smartphones, and tablets

[0332] Software: emotion engine, web browser, database system (e.g., MySQL)

[0333] Data processing and calculation

[0334] Data entry: Users enter information about their target educational institutions and mock test results.

[0335] Data transfer: The device sends the entered data to the server.

[0336] Data acquisition: The server acquires past exam information from the database.

[0337] Data analysis: The server analyzes the user's learning results and compares them with past exam information.

[0338] Weakness Identification: The server analyzes the identified weak areas and generates a customized learning plan.

[0339] Emotion recognition: The device acquires the user's emotional data, which is then analyzed by the emotion engine.

[0340] Learning plan generation: The server adjusts the difficulty of the learning plan based on the results of the emotion engine and provides it to the user.

[0341] Specific examples

[0342] Suppose a user sets their target educational institution as "Educational Institution A" and inputs their current mock exam results as 80 points in mathematics, 72 points in English, and 65 points in Japanese. The server retrieves exam questions from the past 10 years of Institution A from the database and compares them with the user's mock exam results. As a result, it is determined that the user's weak point in mathematics is "calculus." Next, if the emotion engine recognizes the user's emotional state and determines that the user is a little tired, the server generates a study plan including simple "calculus" practice problems and explanations and displays it on the device. The user studies based on this, and when they feel more refreshed, they can tackle more difficult problems.

[0343] Prompt Sentence Examples

[0344] "Please set up your institution as Institution A and enter your current mock test scores of 80 points in math, 72 points in English, and 65 points in Japanese. Then, check the customized study plan provided by the system and incorporate feedback based on your emotional state to help you study."

[0345] As described above, the learning support system of the present invention provides an individually optimized learning plan taking into consideration the emotional state of the user, thereby realizing effective and efficient learning.

[0346] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0347] Step 1:

[0348] A user logs into the system using a terminal. The user inputs the information of the target educational institution (e.g., educational institution A). This input information is sent from the terminal to the server. The server temporarily stores the received information of the target educational institution and prepares it for the next step.

[0349] Step 2:

[0350] The user inputs their current learning results, such as mock exam scores (80 points for math, 72 points for English, and 65 points for Japanese). This data is sent to the server via the terminal. The server stores this data in a database and formats it into a structure for analysis.

[0351] Step 3:

[0352] The server accesses the database and, based on the received information about the target educational institution, retrieves information about past exam questions from that educational institution. Specifically, it retrieves exam questions from the past 10 years from educational institution A, along with their answers and explanations. This information is used in the next analysis step.

[0353] Step 4:

[0354] The server analyzes the user's learning outcomes. Based on the input score data (Mathematics 80 points, English 72 points, Japanese 65 points), it evaluates the grades for each subject and performs an analysis to compare them with past exam information. This analysis calculates the score difference for each subject and identifies the user's strengths and weaknesses.

[0355] Step 5:

[0356] The server compares the user's learning results with the passing standards of the target educational institution (for example, 90 points in mathematics, 85 points in English, and 80 points in Japanese) and calculates the score difference. Specifically, the score difference calculated is -10 points in mathematics, -13 points in English, and -15 points in Japanese. Based on the score difference identified here, weak areas are identified.

[0357] Step 6:

[0358] The server analyzes the detailed problem areas for each subject and identifies areas where the user has particularly low scores (e.g., "calculus"). Specifically, it compares the results with information on past exams and creates a list of topics and areas where the user is weak.

[0359] Step 7:

[0360] The device uses sensors to capture the user's facial expression data, voice data, input speed, etc. This data is sent to the server in real time, and the server inputs it into the emotion engine. The emotion engine analyzes this data and determines the user's emotional state (e.g., stress, joy, fatigue).

[0361] Step 8:

[0362] The server generates a customized study plan based on the identified weaknesses and the results of the emotion engine's recognition. Specifically, it adjusts the difficulty level of calculus problems and explanations to create a study plan suited to the user. If the user is feeling stressed, it lowers the difficulty level and provides easier problems.

[0363] Step 9:

[0364] The server sends the generated learning plan to the terminal. The terminal displays this learning plan to the user and provides guidance on how to proceed to the next learning step. The user independently progresses with their learning based on this learning plan.

[0365] Step 10:

[0366] The server generates feedback based on the results of the emotion engine. Specifically, if the user feels a sense of accomplishment, it provides positive feedback suggesting the next step. This feedback is displayed to the user via their device, and serves to maintain and improve their motivation for learning.

[0367] (Application example 2)

[0368] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0369] Conventional learning support systems identify a user's learning progress and weak areas and provide a customized learning plan, but they rarely take the user's emotional state into consideration. This can lead to stress and make it difficult for users to continue learning. Furthermore, because feedback and plan adjustments based on the user's emotional state are not provided, it is difficult to maintain the user's motivation.

[0370] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting information about the target educational institution; means for inputting the user's learning outcomes; means for acquiring information about past exam questions from the educational institution; means for comparing the learning outcomes with the past exam information and identifying weak areas; means for generating a customized study plan based on the weak areas; means for including exercises corresponding to the weak areas and their explanations in the customized study plan; means for incorporating an emotion engine that recognizes the user's emotional state and adjusting the content of the study plan based on the emotional state; and means for providing the study plan. This makes it possible to adjust the difficulty level of the study plan and provide appropriate feedback while monitoring the user's emotional state in real time.

[0371] "Learning results" is data that indicates the grades and progress that a user has achieved in the course of learning.

[0372] "Information about educational institutions" refers to information about entrance exams for schools, universities, etc. that the user is aiming for, including information about past exam questions and passing criteria.

[0373] "Past exam information" refers to data on exam questions previously used by the target educational institution.

[0374] The "emotion engine" is a system that recognizes and analyzes the user's emotional state from facial expressions, voice, etc., and provides information useful for learning support based on the results.

[0375] A "customized study plan" is a study plan that is individually created for a particular user based on their learning results and areas of weakness.

[0376] A "weak area" is an area of ​​study where the user has particularly low scores or lacks understanding during the learning process.

[0377] "Feedback means" is a function for providing appropriate advice and encouraging messages based on the user's learning and emotional state.

[0378] "Real-time" refers to a state in which processing and reaction are carried out immediately without delay, and refers to the emotion engine instantly recognizing and responding to the user's emotional state.

[0379] The present invention is a learning support system that recognizes the user's emotional state and adjusts the learning plan in real time. The system mainly consists of the following components:

[0380] 1. A way to enter information about your target educational institution

[0381] Users use devices such as smartphones or PCs to enter information about the educational institution they wish to apply to (for example, passing criteria and question trends).

[0382] The entered information is sent to the server and stored in a database.

[0383] 2. Means for inputting user learning outcomes

[0384] The user inputs the results of mock exams and regular tests into the terminal.

[0385] This learning outcome data is also sent to the server and stored together with past grades.

[0386] 3. How to obtain information on past exam questions

[0387] The server retrieves past exam information for the target educational institution from the database.

[0388] For example, it contains mathematics exam questions from a particular year, along with their answers and explanations.

[0389] 4. A means of comparing learning outcomes with past exam information to identify weak areas

[0390] The server compares the user's learning results with the acquired past exam information.

[0391] This identifies areas where the user lacks understanding or scores low. For example, in mathematics, calculus may be identified as a weak point.

[0392] 5. A way to generate a customized study plan

[0393] The server generates a personalized learning plan for the user based on the weakness areas.

[0394] This includes practice questions and explanations, and is tailored to the user's learning progress.

[0395] 6. Emotional engine that adjusts learning plans based on emotional state

[0396] The device uses a camera and microphone to capture the user's facial expressions and voice, which are then analyzed by an emotion engine.

[0397] The emotion engine is built using Keras to recognize the user's emotional state (e.g., joy, stress, tiredness) in real time.

[0398] Based on the recognition results, the server automatically adjusts the difficulty and content of the learning plan. For example, if the user is feeling stressed, it provides easy problems and positive feedback.

[0399] 7. Means of providing study plans

[0400] The server sends the generated and adjusted learning plan to the terminal and displays it to the user.

[0401] The user can proceed with their studies according to this study plan.

[0402] Specific examples

[0403] The user sets "Educational Institution A" as their goal and inputs their mock test results (80 points in mathematics, 72 points in English, and 65 points in Japanese). The server retrieves past exam information from Institution A from the database and compares it with the user's grades to identify their weak points. In this case, calculus in mathematics is identified as their weak point. Furthermore, the emotion engine determines that the user is feeling stressed and generates a study plan including easy calculus problems and their explanations. As the study progresses, the difficulty level is dynamically adjusted according to the user's emotional state, and appropriate feedback is provided.

[0404] Prompt Sentence Examples

[0405] The user entered the educational institution they are studying. It was set to "Educational Institution A."

[0406] Here are some of the latest learnings from users:

[0407] Mathematics: 80 points

[0408] English: 72 points

[0409] Japanese: 65 points

[0410] The emotion engine has determined that the user is currently feeling stressed.

[0411] Generate a customized learning plan for your users based on the following criteria:

[0412] The above describes the embodiments of the present invention.

[0413] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0414] Step 1:

[0415] The user logs into the learning support system and enters information about the educational institution of their choice into the terminal. Specifically, the user enters the name of the school or university of their choice into the input form and presses the submit button. This input data (the name of the educational institution of their choice) is sent to the server, which then stores the input data in a database.

[0416] Step 2:

[0417] The user enters their current learning results into the terminal. The user then enters their mock and regular exam scores into the input form and presses the submit button. This input data (scores for each subject) is sent to the server. The server stores this data in a database and integrates it with past grades.

[0418] Step 3:

[0419] The server retrieves past exam information for the target educational institution from the database. It searches the database for past exam questions and answers corresponding to the input target educational institution and retrieves the results. This exam information is used in the next processing step within the server.

[0420] Step 4:

[0421] The server compares the user's learning outcomes with the acquired information on past exam questions to identify weak areas. Specifically, the scores for each subject are compared with the percentage of correct answers to past exam questions, and areas with low scores (e.g., differential and integral calculus in mathematics) are identified as weak areas. This comparison result (weak areas) is used in the next step.

[0422] Step 5:

[0423] The server generates a customized study plan based on the user's weak areas. It selects exercises and explanations that correspond to the identified weak areas and combines them to create a study plan. The study plan is individually customized based on the user's learning progress.

[0424] Step 6:

[0425] The device uses a camera and microphone to capture the user's facial expressions and voice, which are then analyzed by the emotion engine. The emotion engine (a model built using Keras) recognizes the user's emotional state in real time, and the recognition results (e.g., stress, fatigue, etc.) are sent to the server.

[0426] Step 7:

[0427] The server adjusts the difficulty of the study plan based on the recognition results of the emotion engine. Specifically, if the user is feeling stressed, it selects easier questions and adds positive feedback. The adjusted study plan is then sent to the device.

[0428] Step 8:

[0429] The device receives the learning plan from the server and displays it to the user. The user can continue studying according to the displayed learning plan. As the learning progresses, the device continuously monitors the user's emotional state and adjusts the learning plan in real time.

[0430] 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.

[0431] 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> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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.

[0432] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0433] [Second embodiment]

[0434] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0435] 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.

[0436] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0437] 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.

[0438] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0439] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0440] 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.

[0441] 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.

[0442] 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 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.

[0443] 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.

[0444] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0445] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0446] The learning support system of the present invention provides a study plan that will enable users to efficiently pass the entrance exams for their target educational institutions. The system starts when the user inputs the user's target educational institution and current learning results, identifies the user's weak areas based on past exam information, and provides a study plan that addresses those areas.

[0447] System Overview

[0448] When a user logs in to the system using a device (e.g., a PC or smartphone), the user inputs their target educational institution and current learning outcomes. The system then retrieves past exam information from the target educational institution from a database and compares it with the user's learning outcomes to identify weak areas. It then generates a customized learning plan based on the identified weak areas and displays it on the device.

[0449] Details of each step

[0450] 1. Input method for the target educational institution

[0451] The user inputs the name of the educational institution they are interested in into an input form on their terminal. For example, they input "Tokyo University."

[0452] 2. Means for inputting user learning results

[0453] The user also inputs their current test results (e.g., mock exam scores) into the input form on the terminal. For example, they input 80 points for math, 72 points for English, and 65 points for Japanese.

[0454] 3. How to obtain information on past exam questions

[0455] The server retrieves past exam questions and answers from the database of the target educational institution. For example, it retrieves information on questions from the University of Tokyo for the past 10 years.

[0456] 4. A means of comparing learning outcomes with past exam information

[0457] The server compares the user's learning outcomes with the acquired information on past exam questions and identifies the user's weak areas (e.g., "calculus").

[0458] 5. A way to generate a customized study plan

[0459] The server generates a personalized study plan for the user based on the identified weaknesses, for example, a study plan that includes exercises and explanations for "calculus."

[0460] 6. Means of providing study plans

[0461] The terminal displays the study plan received from the server to the user, who then studies based on it.

[0462] Specific examples

[0463] Suppose a user sets the educational institution they are aiming for as "University of Tokyo" and inputs their current mock exam results as 80 points in mathematics, 72 points in English, and 65 points in Japanese. The server retrieves exam questions from the database for the past 10 years for the University of Tokyo and compares them with the user's mock exam results. As a result, it is determined that the user's weak point in mathematics is "calculus." The server then generates a study plan for "calculus" that includes practice questions and explanations, and displays it on the device. The user then uses this plan to study independently and overcome their weak points.

[0464] As described above, the learning support system of the present invention provides effective and individually optimized learning plans to users, thereby efficiently supporting learning aimed at achieving goals.

[0465] The processing flow will be explained below.

[0466] Step 1:

[0467] A user logs into the system

[0468] The user enters their ID and password and clicks the login button. The system checks the user's authentication information against the database and allows them to log in.

[0469] Step 2:

[0470] Setting goals

[0471] The user enters the name of the educational institution they are interested in. For example, they enter "Educational Institution A." The device sends this information to the server.

[0472] Step 3:

[0473] Input of learning outcomes

[0474] The user inputs their current learning results (for example, mock test scores). For example, they input 80 points for math, 72 points for English, and 65 points for Japanese. The terminal also sends this data to the server.

[0475] Step 4:

[0476] Obtaining past exam information

[0477] The server accesses the database and retrieves the past exam information of the target educational institution. For example, it retrieves the past 10 years of exam information of educational institution A.

[0478] Step 5:

[0479] Analysis of learning outcomes

[0480] The server analyzes the learning results received from the user. It analyzes the scores for each subject (e.g., Mathematics 80 points, English 72 points, Japanese 65 points) according to the data format.

[0481] Step 6:

[0482] Comparison with the standards of the target educational institution

[0483] The server compares the user's learning results with the passing standards of the target educational institution (e.g., 90 points for math, 85 points for English, and 80 points for Japanese). It calculates the score difference and identifies specific weaknesses. For example, it analyzes that math is -10 points, English is -13 points, and Japanese is -15 points.

[0484] Step 7:

[0485] Identifying weak areas

[0486] The server analyzes detailed problem areas for each subject and identifies areas where students are particularly low-scoring (e.g., calculus).

[0487] Step 8:

[0488] Generate a customized study plan

[0489] Based on the identified weaknesses, the server selects appropriate exercises and explanations and generates a personalized study plan for the user, including calculus exercises and explanations, for example.

[0490] Step 9:

[0491] Submitting and Viewing Learning Plans

[0492] The server sends the generated study plan to the device. The device displays the study plan to the user. The user then proceeds with their study based on the provided practice questions and explanations.

[0493] Step 10:

[0494] Learning implementation and feedback

[0495] The user studies based on the study plan displayed on the device. After completing the study, the user inputs the results into the device and sends them back to the server. The server then analyzes the results again and generates a new study plan.

[0496] These are the main processing steps in the program of the present invention, which allow users to efficiently advance their studies and get closer to their target educational institution.

[0497] Example 1

[0498] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0499] Conventional learning systems have difficulty providing an optimal learning plan tailored to each user's individual learning outcomes and desired educational institution, making it difficult to study efficiently. In particular, they lacked a means to identify specific areas of weakness and automatically generate an appropriate learning plan based on those areas. This resulted in a decrease in users' learning efficiency and a decrease in the chances of passing the entrance exam for the desired educational institution.

[0500] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0501] In this invention, the server includes means for a user to input information about a target educational institution using a communication terminal, means for inputting the user's learning outcomes through the communication terminal, means for retrieving information about past exams of the educational institution from a database, means for comparing the learning outcomes with the past exam information on the server and identifying the user's weak areas, means for generating a customized study plan based on the identified weak areas using the generative AI model, and means for providing the study plan to the communication terminal, thereby making it possible to automatically provide an optimal study plan for each user.

[0502] A "user" is an individual who uses the learning support system and is a subject who studies with the aim of passing the entrance exam to a target educational institution.

[0503] A "communication terminal" is an electronic device that a user uses to access the learning support system, and specifically includes a personal computer or smartphone.

[0504] The term "server" refers to a central control device of the learning support system, and is a computer device that has the function of processing information input by users and generating and providing learning plans.

[0505] A "database" is a system that systematically stores information on past exam questions from educational institutions and users' learning outcomes, and allows data to be searched and retrieved as needed.

[0506] A "generative AI model" is an algorithm or program that uses machine learning and artificial intelligence technology to automatically generate optimal study plans based on a user's learning data and goals.

[0507] "Target educational institution information" is information related to the name of a particular educational institution or exam that the user aims to pass.

[0508] "Learning results" refers to evaluation data obtained as a result of learning, such as the results and scores of tests and mock tests that the user has taken in the past.

[0509] "Past exam information" refers to data on exam questions and answers previously administered by educational institutions.

[0510] "Weak areas" refer to areas or items in which the user has particularly insufficient understanding during their studies, and are areas that need to be supplemented.

[0511] A "Customized Study Plan" is a collection of study content and materials specifically designed to meet a user's individual weaknesses.

[0512] MODE FOR CARRYING OUT THE INVENTION

[0513] The learning support system of the present invention provides a learning plan that will enable a user to efficiently pass the entrance exam for a target educational institution. An embodiment of this system will be specifically described below.

[0514] The system begins when a user accesses the system using a communication device (such as a PC or smartphone) and enters information about the educational institution of interest and their current learning outcomes. Based on this information, the server retrieves the institution's past exam information from a database and compares it with the user's learning outcomes to identify areas of weakness. The system then uses a generative AI model to generate a customized learning plan that addresses the user's weaknesses and provides it to the communication device.

[0515] The server functions using the following main hardware and software:

[0516] 1. Hardware:

[0517] Server body (high-performance CPU, memory, storage)

[0518] Communication infrastructure (Internet connection, network equipment)

[0519] Database Server

[0520] 2. Software:

[0521] Database management systems (e.g., MySQL, PostgreSQL)

[0522] Web server software (e.g., Apache, Nginx)

[0523] Programming language (e.g. Python, JavaScript)

[0524] Generative AI models (e.g., GPT-3, BERT)

[0525] Detailed explanation of each step

[0526] 1. The user logs in and enters the information for the target educational institution

[0527] A user logs into the system using a communication terminal and inputs the target educational institution (e.g., "University of Tokyo") through an input form on a web browser.

[0528] Example: Set "University of Tokyo" as the target educational institution.

[0529] 2. Input of user learning outcomes

[0530] The user uses the communication terminal to input the current learning results (e.g., mock exam scores), for example, 80 points for mathematics, 72 points for English, and 65 points for Japanese.

[0531] Example: Enter 80 points for math, 72 points for English, and 65 points for Japanese.

[0532] 3. Obtaining past exam information

[0533] The server accesses the database and retrieves information on past exam questions from the target educational institution, such as the University of Tokyo's exam questions and answers from the past 10 years.

[0534] Software used: Database management system (MySQL, PostgreSQL)

[0535] 4. Matching learning outcomes with exam information

[0536] The server compares the acquired test information with the user's learning results and identifies the user's weak areas. Specifically, it uses an algorithm to compare mock test results with past test trends.

[0537] Software used: Data analysis tool (Python)

[0538] 5. Generate a customized study plan

[0539] The server uses a generative AI model to generate a study plan based on the identified weaknesses. For example, if calculus is a weakness in mathematics, the server generates prompts to create a study plan that includes practice problems and explanations for this area.

[0540] Software used: Generative AI model (GPT-3)

[0541] 6. Providing study plans

[0542] The generated study plan is provided to the user via a communication terminal, and the user can proceed with their studies based on the provided plan.

[0543] Software used: Web server software (Apache, Nginx)

[0544] Prompt Sentence Examples

[0545] Here is an example of a prompt for a generative AI model:

[0546] "Create a plan that includes detailed explanations and practice questions for calculus."

[0547] As a result, the learning support system of the present invention can provide effective learning plans tailored to the weak points of each individual user, and support the student in passing the entrance exams to their target educational institutions.

[0548] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0549] Step 1:

[0550] User logs in and enters information about the target institution

[0551] Specific behavior:

[0552] Users log in to the system using a communication device such as a PC or smartphone. They enter their user ID and password into the login screen on their web browser and press the login button. If authentication is successful, the dashboard is displayed. Next, they enter the name of their target educational institution from the dashboard (e.g., "University of Tokyo").

[0553] input:

[0554] User ID, password, name of the target educational institution

[0555] output:

[0556] User login status, name of target educational institution

[0557] Step 2:

[0558] Input of user learning outcomes

[0559] Specific behavior:

[0560] The user also uses the communication terminal to input their current learning results (e.g., mock test scores), enter specific score information (e.g., 80 points for mathematics, 72 points for English, 65 points for Japanese) into the input form on the dashboard, and press the send button.

[0561] input:

[0562] Current learning results (e.g., 80 points in mathematics, 72 points in English, 65 points in Japanese)

[0563] output:

[0564] User learning outcome data

[0565] Step 3:

[0566] Obtaining past exam information

[0567] Specific behavior:

[0568] The server accesses the database to obtain information on past exam questions from the target educational institution. Specifically, it issues a database query to obtain, for example, the past 10 years of exam questions and answers from the University of Tokyo. This allows it to collect information such as past exam question trends and frequently asked questions.

[0569] input:

[0570] Name of the target educational institution

[0571] output:

[0572] Past exam information

[0573] Step 4:

[0574] Matching learning outcomes with exam information

[0575] Specific behavior:

[0576] The server compares the acquired past exam information with the user's learning outcomes. Using data analysis tools, it compares the user's grades in each subject with past exam trends and uses statistical methods and algorithms to identify the user's weak areas (e.g., "calculus" in mathematics).

[0577] input:

[0578] Past exam information, user learning outcome data

[0579] output:

[0580] Identified Weak Areas

[0581] Step 5:

[0582] Generate a customized study plan

[0583] Specific behavior:

[0584] The server generates a customized study plan based on the identified weak areas. It uses a generative AI model to automatically generate a study plan that focuses on the weak areas. For example, a study plan including detailed explanations and practice problems for "calculus" can be generated by passing the prompt "Please create a plan including detailed explanations and practice problems for calculus" to the AI ​​model.

[0585] input:

[0586] Identified weak areas, generated AI model prompt sentences

[0587] output:

[0588] Customized Study Plan

[0589] Step 6:

[0590] Providing study plans

[0591] Specific behavior:

[0592] The server sends the generated study plan to the communication device. The communication device then displays the received study plan to the user in a visually easy-to-understand format. For example, the study plan may be displayed in list format on the user's dashboard, with links and explanations provided. The user can use this information to proceed with their studies.

[0593] input:

[0594] Customized Study Plan

[0595] output:

[0596] The learning plan provided to the user

[0597] (Application example 1)

[0598] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0599] Conventional learning support systems simply provide learning plans and do not provide sufficient support for users to efficiently achieve their goals. In particular, there is a lack of learning support tailored to users of online payment services, and a system that can effectively improve payment-related knowledge and skills is needed.

[0600] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0601] In this invention, the server includes a means for inputting information about a target educational institution, a means for inputting a user's learning outcomes, a means for acquiring information about past exams from the educational institution, a means for comparing the learning outcomes with the past exam information and identifying weak areas, a means for generating a customized study plan based on the weak areas, a means for providing the study plan, and a means for sending a notification to a user terminal based on the study plan, thereby enabling support for the user to study efficiently and achieve their goals more quickly.

[0602] "Means for inputting target educational institution information" refers to a device or interface that allows a user to input the name and details of a particular educational institution that the user is targeting.

[0603] "Means for inputting user learning results" refers to a device or interface that allows users to input the results of their learning so far, test scores, etc.

[0604] "Means for obtaining past exam information" refers to the devices and processes for obtaining past exam questions and related information of the designated educational institution from a database.

[0605] "Means for comparing learning outcomes with past exam information and identifying weak areas" refers to devices and processes that compare and analyze the learning outcomes entered by the user with past exam information and identify in which areas or items the user has weaknesses.

[0606] "Means for generating a customized study plan" refers to a device or software for creating an optimized study plan for a user based on identified weaknesses.

[0607] The "means for providing a study plan" refers to a device or interface for providing the generated study plan to the user.

[0608] The "means for sending a notification to a user terminal based on a study plan" refers to a device or process for sending a notification about the created study plan to a terminal used by a user.

[0609] "Means for storing in a database" refers to the devices and processes for storing the acquired past exam information and other related data in a database.

[0610] "Practice problems and their explanations" refers to a set of problems that correspond to the user's weak areas and content that includes explanations for the problems.

[0611] The system of the present invention provides a customized study plan based on past exam information and the user's learning results so that users who are targeting educational institutions can study effectively. The specific configuration of this system is described below.

[0612] System configuration

[0613] The user first uses a terminal to input information about the educational institution of interest and their current learning outcomes, which are then processed by the server.

[0614] 1. Input Method

[0615] An input form is provided on the device as a means of inputting information about the target educational institution (e.g., "a particular university"), as well as the user's current learning achievements (e.g., mock exam results).

[0616] 2. Data Acquisition Method

[0617] The server retrieves the past exam information of the target educational institution from the database. One way to do this is to use an API to import past exam data.

[0618] 3. Verification Method

[0619] The system compares the learning outcomes with the acquired information on past exam questions to identify the user's weak areas. This process uses machine learning algorithms. Specifically, it uses libraries such as TfidfVectorizer and cosine_similarity.

[0620] 4. Learning plan generation tool

[0621] The server generates a customized study plan based on the identified weaknesses, which includes exercises and explanations that address the weaknesses.

[0622] 5. Means of providing study plans

[0623] The generated learning plan is then delivered to the user's device via notifications and a dashboard.

[0624] Specific examples of hardware and software used

[0625] Devices: PC, smartphone, tablet

[0626] Server: Cloud-based server, on-premise server

[0627] software:

[0628] Database management systems: MySQL, PostgreSQL

[0629] API: RESTful API

[0630] Machine learning library: Scikit-learn

[0631] Notification system: Firebase Cloud Messaging (FCM)

[0632] Specific examples of processing

[0633] Suppose a user is aiming for a specific educational institution (e.g., "specific university") and enters their current mock exam scores of 80 points in mathematics, 72 points in English, and 65 points in Japanese. The server retrieves exam questions from the database for the specific university over the past 10 years and compares them with the user's mock exam scores. As a result, it is determined that the user's weak point in mathematics is "calculus." The server then generates a study plan including practice questions and explanations for "calculus" and sends a notification to the user's device.

[0634] Prompt Sentence Examples

[0635] markdown

[0636] You are a tool that helps business people generate customized study plans to improve their skills related to online payments. Based on the user's goals and current level of understanding, we will compare past exam information to identify weak points and provide the optimal study plan. Please provide the following information:

[0637] Goal: Efficient online payment processing

[0638] Current level of understanding: Understands basic payment processing procedures, but weak in advanced troubleshooting

[0639] By using this prompt, the AI ​​can be informed of the user's specific situation and generate the optimal learning plan.

[0640] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0641] Step 1:

[0642] The user uses a terminal to input information about the educational institution of their choice and their current learning outcomes. The input information includes the name of the educational institution of their choice and the user's mock exam results. This allows the user to clarify their learning goals and current status, laying the foundation for the system to perform the necessary data processing.

[0643] Step 2:

[0644] The server retrieves information about the educational institution's past exam questions from a database based on the information about the educational institution entered by the user. Specifically, it queries the database using the name of the educational institution to retrieve past exam questions and their answers. The information retrieved in this process includes question patterns and frequently asked questions from past exams.

[0645] Step 3:

[0646] The server compares the learning outcomes entered by the user with the acquired information on past exam questions. The learning outcomes are mock test scores, and the acquired information on past exam questions. Specifically, the server uses TfidfVectorizer to vectorize the learning outcomes and exam questions, and calculates the similarity between each item using cosine_similarity. This identifies the user's weak areas.

[0647] Step 4:

[0648] The server generates a customized study plan based on the identified weak areas. The generated study plan includes exercises and explanations corresponding to the identified weak areas. For example, if "calculus" in mathematics is identified as a weak area, the server selects exercises and explanations related to "calculus." This allows the user to efficiently overcome their weak areas.

[0649] Step 5:

[0650] The server provides the generated study plan to the user's device. Specifically, the content of the study plan is sent to the user's device in the form of a notification. The notification includes an overview of the study plan and links to practice questions. This allows the user to proceed with their studies based on the provided study plan.

[0651] Step 6:

[0652] The user studies based on the provided study plan and carries out learning activities to overcome their weaknesses. By inputting the new learning results obtained during this process back into the system, the system can provide an even more accurate study plan. This allows for continuous learning support.

[0653] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0654] The learning support system of the present invention provides a learning plan that will enable a user to efficiently pass the entrance exam for a target educational institution. This system incorporates an emotion engine that recognizes the user's emotions, and is able to provide a flexible learning plan according to the user's emotional state.

[0655] System Overview

[0656] When a user logs into the system using a terminal, they input their target educational institution and current learning outcomes. The system then retrieves past exam information from the target educational institution from a database and compares it with the user's learning outcomes to identify weak areas. It then generates a customized learning plan based on the identified weak areas and displays it on the terminal. An emotional engine then recognizes the user's emotional state and adjusts the difficulty level and feedback of the learning plan.

[0657] Details of each step

[0658] 1. Input method for the target educational institution

[0659] The user enters the name of the target educational institution into an input form on the terminal, for example, "Educational Institution A." The terminal then sends this information to the server.

[0660] 2. Means of inputting learning outcomes

[0661] The user inputs their current learning results (for example, mock exam scores). For example, they input 80 points for math, 72 points for English, and 65 points for Japanese. The terminal then sends this data to the server.

[0662] 3. How to obtain information on past exam questions

[0663] The server accesses the database and retrieves the past exam information of the target educational institution. For example, it retrieves the past 10 years of exam information of educational institution A.

[0664] 4. Means of analyzing learning outcomes

[0665] The server analyzes the learning results received from the user. It analyzes the scores for each subject (e.g., Mathematics 80 points, English 72 points, Japanese 65 points) according to the data format.

[0666] 5. Compare with the standards of your target educational institution

[0667] The server compares the user's learning results with the passing standards of the target educational institution (e.g., 90 points for math, 85 points for English, and 80 points for Japanese). It calculates the score difference and identifies specific weaknesses. For example, it analyzes that math is -10 points, English is -13 points, and Japanese is -15 points.

[0668] 6. Identifying Weak Areas

[0669] The server analyzes detailed problem areas for each subject and identifies areas where students are particularly low-scoring (e.g., calculus).

[0670] 7. Emotion Engine Recognition

[0671] The device collects data such as the user's facial expressions, voice, and input speed, and the emotion engine analyzes this data to recognize the user's emotional state (e.g., stress, joy, fatigue).

[0672] 8. Generate a customized study plan

[0673] Based on the identified weaknesses, the server selects appropriate exercises and explanations and generates a personalized study plan for the user, including calculus exercises and explanations, for example.

[0674] Based on the recognition results of the emotion engine, the difficulty level of the exercises is adjusted appropriately. For example, if the user is feeling stressed, the difficulty level is lowered and easier exercises are provided.

[0675] 9. Providing study plans

[0676] The server sends the generated learning plan to the terminal, which displays the learning plan to the user, who then proceeds with their learning based on the plan.

[0677] 10. Providing Feedback

[0678] Based on the results of the emotion engine, it provides positive feedback and advice to the user, for example, if the user feels a sense of accomplishment, it suggests next steps.

[0679] Specific examples

[0680] Suppose a user sets their target educational institution as "Educational Institution A" and inputs their current mock exam results as 80 points in mathematics, 72 points in English, and 65 points in Japanese. The server retrieves exam questions from the past 10 years of Institution A from the database and compares them with the user's mock exam results. As a result, it is determined that the user's weak point in mathematics is "calculus." Next, if the emotion engine recognizes the user's emotional state and determines that the user is a little tired, the server generates a study plan including simple "calculus" practice problems and explanations and displays it on the device. The user studies based on this, and when they feel more refreshed, they can tackle more difficult problems.

[0681] As described above, the learning support system of the present invention provides an individually optimized learning plan taking into consideration the emotional state of the user, thereby realizing effective and efficient learning.

[0682] The processing flow will be explained below.

[0683] Step 1:

[0684] A user logs into the system

[0685] The user enters their ID and password and clicks the login button. The system checks the user's authentication information against the database and allows them to log in.

[0686] Step 2:

[0687] Setting goals

[0688] The user enters the name of the educational institution they are interested in. For example, they enter "Educational Institution A." The device sends this information to the server.

[0689] Step 3:

[0690] Input of learning outcomes

[0691] The user inputs their current learning results (for example, mock test scores). For example, they input 80 points for math, 72 points for English, and 65 points for Japanese. The terminal then sends this data to the server.

[0692] Step 4:

[0693] Obtaining past exam information

[0694] The server accesses the database and retrieves the past exam information of the target educational institution. For example, it retrieves the past 10 years of exam information of educational institution A.

[0695] Step 5:

[0696] Analysis of learning outcomes

[0697] The server analyzes the learning results received from the user. It analyzes the scores for each subject (e.g., Mathematics 80 points, English 72 points, Japanese 65 points) according to the data format.

[0698] Step 6:

[0699] Comparison with the standards of the target educational institution

[0700] The server compares the user's learning results with the passing standards of the target educational institution (e.g., 90 points for math, 85 points for English, and 80 points for Japanese). It calculates the score difference and identifies specific weaknesses. For example, it analyzes that math is -10 points, English is -13 points, and Japanese is -15 points.

[0701] Step 7:

[0702] Identifying weak areas

[0703] The server analyzes detailed problem areas for each subject and identifies areas where students are particularly low-scoring (e.g., calculus).

[0704] Step 8:

[0705] Emotion Engine Recognition

[0706] The device collects data such as the user's facial expressions, voice, and input speed, and the emotion engine analyzes this data to recognize the user's emotional state (e.g., stress, joy, fatigue).

[0707] Step 9:

[0708] Generate a customized study plan

[0709] The server selects appropriate exercises and explanations based on the identified weaknesses and generates a personalized learning plan for the user. For example, it may include calculus exercises and explanations. Based on the recognition results of the emotion engine, the difficulty of the exercises is adjusted appropriately. For example, if the user is feeling stressed, the difficulty level is lowered to provide easier exercises.

[0710] Step 10:

[0711] Providing study plans

[0712] The server sends the generated learning plan to the terminal, which displays the learning plan to the user, who then proceeds with their learning based on the plan.

[0713] Step 11:

[0714] Providing feedback

[0715] The device will provide the user with positive feedback and advice based on the results of the emotion engine. For example, if the user feels a sense of accomplishment, it will suggest the next step.

[0716] Step 12:

[0717] Learning implementation and evaluation

[0718] The user studies based on the study plan displayed on the device. After completing the study, the user inputs the results into the device and sends them back to the server. The server then analyzes the results again and generates a new study plan.

[0719] The above are the main processing steps in the learning support system of the present invention. These steps allow the user to efficiently progress through their studies and get closer to their target educational institution.

[0720] Example 2

[0721] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0722] Conventional learning support systems can provide a customized learning plan based on a user's learning achievements and areas of weakness, but lack the functionality to adjust the content of the learning plan and feedback based on the user's emotional state. This creates a problem of reduced learning efficiency when a user continues learning while feeling stressed or fatigued. The present invention aims to solve this problem by providing effective and efficient learning support that takes into account the user's emotional state.

[0723] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for inputting information about a target educational institution, a means for inputting the user's learning outcomes, a means for acquiring information about past questions from the educational institution, a means for comparing the learning outcomes with the past question information and identifying weak areas, a means for generating a customized study plan based on the weak areas, a means for adjusting the content and feedback of the study plan using an emotion engine that recognizes the user's emotions, and a means for providing the study plan. This makes it possible to provide an individually optimized study plan taking the user's emotional state into consideration.

[0724] 1. "Target educational institution" refers to the educational institution that the user aims to be accepted into, including schools, universities, and other educational facilities for further education or qualification acquisition.

[0725] 2. "Learning outcomes" refers to data that indicates the progress and results of a user's learning, such as the grades achieved so far, mock test scores, and assignment evaluations.

[0726] 3. "Past exam information" refers to information such as the contents of exam questions and mock exams previously used by the target educational institution, as well as answers and explanations.

[0727] 4. "Weakness Areas" refers to areas or topics in learning that need improvement, as identified based on user learning outcomes.

[0728] 5. "Customized Study Plan" means a plan that includes study assignments, exercises, and explanations that is individually created based on a User's learning achievements and areas of weakness.

[0729] 6. An "emotion engine" is software or a module that analyzes data such as a user's facial expressions, voice, and input speed to recognize the user's emotional state.

[0730] 7. "Feedback" refers to advice, evaluations, comments on learning progress, etc. provided to users by the system.

[0731] 8. A "database" is a system or storage device for structuring and storing information on past exam questions, learning outcomes, user information, etc.

[0732] MODE FOR CARRYING OUT THE INVENTION

[0733] The learning support system of the present invention provides a learning plan that will enable a user to efficiently pass the entrance exam for a target educational institution. This system incorporates an emotion engine that recognizes the user's emotions, and is able to provide a flexible learning plan that corresponds to the user's emotional state.

[0734] System Overview

[0735] When a user logs into the system using a terminal, they first enter their target educational institution and current learning achievements. Based on this information, the system retrieves past exam information from the target educational institution from a database and compares it with the user's learning achievements to identify weak areas. It then generates a customized learning plan based on the identified weak areas and displays it on the terminal. At this time, an emotional engine recognizes the user's emotional state and adjusts the difficulty level and feedback of the learning plan accordingly.

[0736] Hardware and software used

[0737] Hardware: devices such as computers, smartphones, and tablets

[0738] Software: emotion engine, web browser, database system (e.g., MySQL)

[0739] Data processing and calculation

[0740] Data entry: Users enter information about their target educational institutions and mock test results.

[0741] Data transfer: The device sends the entered data to the server.

[0742] Data acquisition: The server acquires past exam information from the database.

[0743] Data analysis: The server analyzes the user's learning results and compares them with past exam information.

[0744] Weakness Identification: The server analyzes the identified weak areas and generates a customized learning plan.

[0745] Emotion recognition: The device acquires the user's emotional data, which is then analyzed by the emotion engine.

[0746] Learning plan generation: The server adjusts the difficulty of the learning plan based on the results of the emotion engine and provides it to the user.

[0747] Specific examples

[0748] Suppose a user sets their target educational institution as "Educational Institution A" and inputs their current mock exam results as 80 points in mathematics, 72 points in English, and 65 points in Japanese. The server retrieves exam questions from the past 10 years of Institution A from the database and compares them with the user's mock exam results. As a result, it is determined that the user's weak point in mathematics is "calculus." Next, if the emotion engine recognizes the user's emotional state and determines that the user is a little tired, the server generates a study plan including simple "calculus" practice problems and explanations and displays it on the device. The user studies based on this, and when they feel more refreshed, they can tackle more difficult problems.

[0749] Prompt Sentence Examples

[0750] "Please set up your institution as Institution A and enter your current mock test scores of 80 points in math, 72 points in English, and 65 points in Japanese. Then, check the customized study plan provided by the system and incorporate feedback based on your emotional state to help you study."

[0751] As described above, the learning support system of the present invention provides an individually optimized learning plan taking into consideration the emotional state of the user, thereby realizing effective and efficient learning.

[0752] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0753] Step 1:

[0754] A user logs into the system using a terminal. The user inputs the information of the target educational institution (e.g., educational institution A). This input information is sent from the terminal to the server. The server temporarily stores the received information of the target educational institution and prepares it for the next step.

[0755] Step 2:

[0756] The user inputs their current learning results, such as mock exam scores (80 points for math, 72 points for English, and 65 points for Japanese). This data is sent to the server via the terminal. The server stores this data in a database and formats it into a structure for analysis.

[0757] Step 3:

[0758] The server accesses the database and, based on the received information about the target educational institution, retrieves information about past exam questions from that educational institution. Specifically, it retrieves exam questions from the past 10 years from educational institution A, along with their answers and explanations. This information is used in the next analysis step.

[0759] Step 4:

[0760] The server analyzes the user's learning outcomes. Based on the input score data (Mathematics 80 points, English 72 points, Japanese 65 points), it evaluates the grades for each subject and performs an analysis to compare them with past exam information. This analysis calculates the score difference for each subject and identifies the user's strengths and weaknesses.

[0761] Step 5:

[0762] The server compares the user's learning results with the passing standards of the target educational institution (for example, 90 points in mathematics, 85 points in English, and 80 points in Japanese) and calculates the score difference. Specifically, the score difference calculated is -10 points in mathematics, -13 points in English, and -15 points in Japanese. Based on the score difference identified here, weak areas are identified.

[0763] Step 6:

[0764] The server analyzes the detailed problem areas for each subject and identifies areas where the user has particularly low scores (e.g., "calculus"). Specifically, it compares the results with information on past exams and creates a list of topics and areas where the user is weak.

[0765] Step 7:

[0766] The device uses sensors to capture the user's facial expression data, voice data, input speed, etc. This data is sent to the server in real time, and the server inputs it into the emotion engine. The emotion engine analyzes this data and determines the user's emotional state (e.g., stress, joy, fatigue).

[0767] Step 8:

[0768] The server generates a customized study plan based on the identified weaknesses and the results of the emotion engine's recognition. Specifically, it adjusts the difficulty level of calculus problems and explanations to create a study plan suited to the user. If the user is feeling stressed, it lowers the difficulty level and provides easier problems.

[0769] Step 9:

[0770] The server sends the generated learning plan to the terminal. The terminal displays this learning plan to the user and provides guidance on how to proceed to the next learning step. The user independently progresses with their learning based on this learning plan.

[0771] Step 10:

[0772] The server generates feedback based on the results of the emotion engine. Specifically, if the user feels a sense of accomplishment, it provides positive feedback suggesting the next step. This feedback is displayed to the user via their device, and serves to maintain and improve their motivation for learning.

[0773] (Application example 2)

[0774] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0775] Conventional learning support systems identify a user's learning progress and weak areas and provide a customized learning plan, but they rarely take the user's emotional state into consideration. This can lead to stress and make it difficult for users to continue learning. Furthermore, because feedback and plan adjustments based on the user's emotional state are not provided, it is difficult to maintain the user's motivation.

[0776] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting information about the target educational institution; means for inputting the user's learning outcomes; means for acquiring information about past exam questions from the educational institution; means for comparing the learning outcomes with the past exam information and identifying weak areas; means for generating a customized study plan based on the weak areas; means for including exercises corresponding to the weak areas and their explanations in the customized study plan; means for incorporating an emotion engine that recognizes the user's emotional state and adjusting the content of the study plan based on the emotional state; and means for providing the study plan. This makes it possible to adjust the difficulty level of the study plan and provide appropriate feedback while monitoring the user's emotional state in real time.

[0777] "Learning results" is data that indicates the grades and progress that a user has achieved in the course of learning.

[0778] "Information about educational institutions" refers to information about entrance exams for schools, universities, etc. that the user is aiming for, including information about past exam questions and passing criteria.

[0779] "Past exam information" refers to data on exam questions previously used by the target educational institution.

[0780] The "emotion engine" is a system that recognizes and analyzes the user's emotional state from facial expressions, voice, etc., and provides information useful for learning support based on the results.

[0781] A "customized study plan" is a study plan that is individually created for a particular user based on their learning results and areas of weakness.

[0782] A "weak area" is an area of ​​study where the user has particularly low scores or lacks understanding during the learning process.

[0783] "Feedback means" is a function for providing appropriate advice and encouraging messages based on the user's learning and emotional state.

[0784] "Real-time" refers to a state in which processing and reaction are carried out immediately without delay, and refers to the emotion engine instantly recognizing and responding to the user's emotional state.

[0785] The present invention is a learning support system that recognizes the user's emotional state and adjusts the learning plan in real time. The system mainly consists of the following components:

[0786] 1. A way to enter information about your target educational institution

[0787] Users use devices such as smartphones or PCs to enter information about the educational institution they wish to apply to (for example, passing criteria and question trends).

[0788] The entered information is sent to the server and stored in a database.

[0789] 2. Means for inputting user learning outcomes

[0790] The user inputs the results of mock exams and regular tests into the terminal.

[0791] This learning outcome data is also sent to the server and stored together with past grades.

[0792] 3. How to obtain information on past exam questions

[0793] The server retrieves past exam information for the target educational institution from the database.

[0794] For example, it contains mathematics exam questions from a particular year, along with their answers and explanations.

[0795] 4. A means of comparing learning outcomes with past exam information to identify weak areas

[0796] The server compares the user's learning results with the acquired past exam information.

[0797] This identifies areas where the user lacks understanding or scores low. For example, in mathematics, calculus may be identified as a weak point.

[0798] 5. A way to generate a customized study plan

[0799] The server generates a personalized learning plan for the user based on the weakness areas.

[0800] This includes practice questions and explanations, and is tailored to the user's learning progress.

[0801] 6. Emotional engine that adjusts learning plans based on emotional state

[0802] The device uses a camera and microphone to capture the user's facial expressions and voice, which are then analyzed by an emotion engine.

[0803] The emotion engine is built using Keras to recognize the user's emotional state (e.g., joy, stress, tiredness) in real time.

[0804] Based on the recognition results, the server automatically adjusts the difficulty and content of the learning plan. For example, if the user is feeling stressed, it provides easy problems and positive feedback.

[0805] 7. Means of providing study plans

[0806] The server sends the generated and adjusted learning plan to the terminal and displays it to the user.

[0807] The user can proceed with their studies according to this study plan.

[0808] Specific examples

[0809] The user sets "Educational Institution A" as their goal and inputs their mock test results (80 points in mathematics, 72 points in English, and 65 points in Japanese). The server retrieves past exam information from Institution A from the database and compares it with the user's grades to identify their weak points. In this case, calculus in mathematics is identified as their weak point. Furthermore, the emotion engine determines that the user is feeling stressed and generates a study plan including easy calculus problems and their explanations. As the study progresses, the difficulty level is dynamically adjusted according to the user's emotional state, and appropriate feedback is provided.

[0810] Prompt Sentence Examples

[0811] The user entered the educational institution they are studying. It was set to "Educational Institution A."

[0812] Here are some of the latest learnings from users:

[0813] Mathematics: 80 points

[0814] English: 72 points

[0815] Japanese: 65 points

[0816] The emotion engine has determined that the user is currently feeling stressed.

[0817] Generate a customized learning plan for your users based on the following criteria:

[0818] The above describes the embodiments of the present invention.

[0819] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0820] Step 1:

[0821] The user logs into the learning support system and enters information about the educational institution of their choice into the terminal. Specifically, the user enters the name of the school or university of their choice into the input form and presses the submit button. This input data (the name of the educational institution of their choice) is sent to the server, which then stores the input data in a database.

[0822] Step 2:

[0823] The user enters their current learning results into the terminal. The user then enters their mock and regular exam scores into the input form and presses the submit button. This input data (scores for each subject) is sent to the server. The server stores this data in a database and integrates it with past grades.

[0824] Step 3:

[0825] The server retrieves past exam information for the target educational institution from the database. It searches the database for past exam questions and answers corresponding to the input target educational institution and retrieves the results. This exam information is used in the next processing step within the server.

[0826] Step 4:

[0827] The server compares the user's learning outcomes with the acquired information on past exam questions to identify weak areas. Specifically, the scores for each subject are compared with the percentage of correct answers to past exam questions, and areas with low scores (e.g., differential and integral calculus in mathematics) are identified as weak areas. This comparison result (weak areas) is used in the next step.

[0828] Step 5:

[0829] The server generates a customized study plan based on the user's weak areas. It selects exercises and explanations that correspond to the identified weak areas and combines them to create a study plan. The study plan is individually customized based on the user's learning progress.

[0830] Step 6:

[0831] The device uses a camera and microphone to capture the user's facial expressions and voice, which are then analyzed by the emotion engine. The emotion engine (a model built using Keras) recognizes the user's emotional state in real time, and the recognition results (e.g., stress, fatigue, etc.) are sent to the server.

[0832] Step 7:

[0833] The server adjusts the difficulty of the study plan based on the recognition results of the emotion engine. Specifically, if the user is feeling stressed, it selects easier questions and adds positive feedback. The adjusted study plan is then sent to the device.

[0834] Step 8:

[0835] The device receives the learning plan from the server and displays it to the user. The user can continue studying according to the displayed learning plan. As the learning progresses, the device continuously monitors the user's emotional state and adjusts the learning plan in real time.

[0836] 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.

[0837] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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.

[0838] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0839] [Third embodiment]

[0840] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0841] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0842] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0843] 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.

[0844] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0845] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0846] 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.

[0847] 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.

[0848] 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 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.

[0849] 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.

[0850] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0851] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0852] The learning support system of the present invention provides a study plan that will enable users to efficiently pass the entrance exams for their target educational institutions. The system starts when the user inputs the user's target educational institution and current learning results, identifies the user's weak areas based on past exam information, and provides a study plan that addresses those areas.

[0853] System Overview

[0854] When a user logs in to the system using a device (e.g., a PC or smartphone), the user inputs their target educational institution and current learning outcomes. The system then retrieves past exam information from the target educational institution from a database and compares it with the user's learning outcomes to identify weak areas. It then generates a customized learning plan based on the identified weak areas and displays it on the device.

[0855] Details of each step

[0856] 1. Input method for the target educational institution

[0857] The user inputs the name of the educational institution they are interested in into an input form on their terminal. For example, they input "Tokyo University."

[0858] 2. Means for inputting user learning results

[0859] The user also inputs their current test results (e.g., mock exam scores) into the input form on the terminal. For example, they input 80 points for math, 72 points for English, and 65 points for Japanese.

[0860] 3. How to obtain information on past exam questions

[0861] The server retrieves past exam questions and answers from the database of the target educational institution. For example, it retrieves information on questions from the University of Tokyo for the past 10 years.

[0862] 4. A means of comparing learning outcomes with past exam information

[0863] The server compares the user's learning outcomes with the acquired information on past exam questions and identifies the user's weak areas (e.g., "calculus").

[0864] 5. A way to generate a customized study plan

[0865] The server generates a personalized study plan for the user based on the identified weaknesses, for example, a study plan that includes exercises and explanations for "calculus."

[0866] 6. Means of providing study plans

[0867] The terminal displays the study plan received from the server to the user, who then studies based on it.

[0868] Specific examples

[0869] Suppose a user sets the educational institution they are aiming for as "University of Tokyo" and inputs their current mock exam results as 80 points in mathematics, 72 points in English, and 65 points in Japanese. The server retrieves exam questions from the database for the past 10 years for the University of Tokyo and compares them with the user's mock exam results. As a result, it is determined that the user's weak point in mathematics is "calculus." The server then generates a study plan for "calculus" that includes practice questions and explanations, and displays it on the device. The user then uses this plan to study independently and overcome their weak points.

[0870] As described above, the learning support system of the present invention provides effective and individually optimized learning plans to users, thereby efficiently supporting learning aimed at achieving goals.

[0871] The processing flow will be explained below.

[0872] Step 1:

[0873] A user logs into the system

[0874] The user enters their ID and password and clicks the login button. The system checks the user's authentication information against the database and allows them to log in.

[0875] Step 2:

[0876] Setting goals

[0877] The user enters the name of the educational institution they are interested in. For example, they enter "Educational Institution A." The device sends this information to the server.

[0878] Step 3:

[0879] Input of learning outcomes

[0880] The user inputs their current learning results (for example, mock test scores). For example, they input 80 points for math, 72 points for English, and 65 points for Japanese. The terminal also sends this data to the server.

[0881] Step 4:

[0882] Obtaining past exam information

[0883] The server accesses the database and retrieves the past exam information of the target educational institution. For example, it retrieves the past 10 years of exam information of educational institution A.

[0884] Step 5:

[0885] Analysis of learning outcomes

[0886] The server analyzes the learning results received from the user. It analyzes the scores for each subject (e.g., Mathematics 80 points, English 72 points, Japanese 65 points) according to the data format.

[0887] Step 6:

[0888] Comparison with the standards of the target educational institution

[0889] The server compares the user's learning results with the passing standards of the target educational institution (e.g., 90 points for math, 85 points for English, and 80 points for Japanese). It calculates the score difference and identifies specific weaknesses. For example, it analyzes that math is -10 points, English is -13 points, and Japanese is -15 points.

[0890] Step 7:

[0891] Identifying weak areas

[0892] The server analyzes detailed problem areas for each subject and identifies areas where students are particularly low-scoring (e.g., calculus).

[0893] Step 8:

[0894] Generate a customized study plan

[0895] Based on the identified weaknesses, the server selects appropriate exercises and explanations and generates a personalized study plan for the user, including calculus exercises and explanations, for example.

[0896] Step 9:

[0897] Submitting and Viewing Learning Plans

[0898] The server sends the generated study plan to the device. The device displays the study plan to the user. The user then proceeds with their study based on the provided practice questions and explanations.

[0899] Step 10:

[0900] Learning implementation and feedback

[0901] The user studies based on the study plan displayed on the device. After completing the study, the user inputs the results into the device and sends them back to the server. The server then analyzes the results again and generates a new study plan.

[0902] These are the main processing steps in the program of the present invention, which allow users to efficiently advance their studies and get closer to their target educational institution.

[0903] Example 1

[0904] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0905] Conventional learning systems have difficulty providing an optimal learning plan tailored to each user's individual learning outcomes and desired educational institution, making it difficult to study efficiently. In particular, they lacked a means to identify specific areas of weakness and automatically generate an appropriate learning plan based on those areas. This resulted in a decrease in users' learning efficiency and a decrease in the chances of passing the entrance exam for the desired educational institution.

[0906] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0907] In this invention, the server includes means for a user to input information about a target educational institution using a communication terminal, means for inputting the user's learning outcomes through the communication terminal, means for retrieving information about past exams of the educational institution from a database, means for comparing the learning outcomes with the past exam information on the server and identifying the user's weak areas, means for generating a customized study plan based on the identified weak areas using the generative AI model, and means for providing the study plan to the communication terminal, thereby making it possible to automatically provide an optimal study plan for each user.

[0908] A "user" is an individual who uses the learning support system and is a subject who studies with the aim of passing the entrance exam to a target educational institution.

[0909] A "communication terminal" is an electronic device that a user uses to access the learning support system, and specifically includes a personal computer or smartphone.

[0910] The term "server" refers to a central control device of the learning support system, and is a computer device that has the function of processing information input by users and generating and providing learning plans.

[0911] A "database" is a system that systematically stores information on past exam questions from educational institutions and users' learning outcomes, and allows data to be searched and retrieved as needed.

[0912] A "generative AI model" is an algorithm or program that uses machine learning and artificial intelligence technology to automatically generate optimal study plans based on a user's learning data and goals.

[0913] "Target educational institution information" is information related to the name of a particular educational institution or exam that the user aims to pass.

[0914] "Learning results" refers to evaluation data obtained as a result of learning, such as the results and scores of tests and mock tests that the user has taken in the past.

[0915] "Past exam information" refers to data on exam questions and answers previously administered by educational institutions.

[0916] "Weak areas" refer to areas or items in which the user has particularly insufficient understanding during their studies, and are areas that need to be supplemented.

[0917] A "Customized Study Plan" is a collection of study content and materials specifically designed to meet a user's individual weaknesses.

[0918] MODE FOR CARRYING OUT THE INVENTION

[0919] The learning support system of the present invention provides a learning plan that will enable a user to efficiently pass the entrance exam for a target educational institution. An embodiment of this system will be specifically described below.

[0920] The system begins when a user accesses the system using a communication device (such as a PC or smartphone) and enters information about the educational institution of interest and their current learning outcomes. Based on this information, the server retrieves the institution's past exam information from a database and compares it with the user's learning outcomes to identify areas of weakness. The system then uses a generative AI model to generate a customized learning plan that addresses the user's weaknesses and provides it to the communication device.

[0921] The server functions using the following main hardware and software:

[0922] 1. Hardware:

[0923] Server body (high-performance CPU, memory, storage)

[0924] Communication infrastructure (Internet connection, network equipment)

[0925] Database Server

[0926] 2. Software:

[0927] Database management systems (e.g., MySQL, PostgreSQL)

[0928] Web server software (e.g., Apache, Nginx)

[0929] Programming language (e.g. Python, JavaScript)

[0930] Generative AI models (e.g., GPT-3, BERT)

[0931] Detailed explanation of each step

[0932] 1. The user logs in and enters the information for the target educational institution

[0933] A user logs into the system using a communication terminal and inputs the target educational institution (e.g., "University of Tokyo") through an input form on a web browser.

[0934] Example: Set "University of Tokyo" as the target educational institution.

[0935] 2. Input of user learning outcomes

[0936] The user uses the communication terminal to input the current learning results (e.g., mock exam scores), for example, 80 points for mathematics, 72 points for English, and 65 points for Japanese.

[0937] Example: Enter 80 points for math, 72 points for English, and 65 points for Japanese.

[0938] 3. Obtaining past exam information

[0939] The server accesses the database and retrieves information on past exam questions from the target educational institution, such as the University of Tokyo's exam questions and answers from the past 10 years.

[0940] Software used: Database management system (MySQL, PostgreSQL)

[0941] 4. Matching learning outcomes with exam information

[0942] The server compares the acquired test information with the user's learning results and identifies the user's weak areas. Specifically, it uses an algorithm to compare mock test results with past test trends.

[0943] Software used: Data analysis tool (Python)

[0944] 5. Generate a customized study plan

[0945] The server uses a generative AI model to generate a study plan based on the identified weaknesses. For example, if calculus is a weakness in mathematics, the server generates prompts to create a study plan that includes practice problems and explanations for this area.

[0946] Software used: Generative AI model (GPT-3)

[0947] 6. Providing study plans

[0948] The generated study plan is provided to the user via a communication terminal, and the user can proceed with their studies based on the provided plan.

[0949] Software used: Web server software (Apache, Nginx)

[0950] Prompt Sentence Examples

[0951] Here is an example of a prompt for a generative AI model:

[0952] "Create a plan that includes detailed explanations and practice questions for calculus."

[0953] As a result, the learning support system of the present invention can provide effective learning plans tailored to the weak points of each individual user, and support the student in passing the entrance exams to their target educational institutions.

[0954] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0955] Step 1:

[0956] User logs in and enters information about the target institution

[0957] Specific behavior:

[0958] Users log in to the system using a communication device such as a PC or smartphone. They enter their user ID and password into the login screen on their web browser and press the login button. If authentication is successful, the dashboard is displayed. Next, they enter the name of their target educational institution from the dashboard (e.g., "University of Tokyo").

[0959] input:

[0960] User ID, password, name of the target educational institution

[0961] output:

[0962] User login status, name of target educational institution

[0963] Step 2:

[0964] Input of user learning outcomes

[0965] Specific behavior:

[0966] The user also uses the communication terminal to input their current learning results (e.g., mock test scores), enter specific score information (e.g., 80 points for mathematics, 72 points for English, 65 points for Japanese) into the input form on the dashboard, and press the send button.

[0967] input:

[0968] Current learning results (e.g., 80 points in mathematics, 72 points in English, 65 points in Japanese)

[0969] output:

[0970] User learning outcome data

[0971] Step 3:

[0972] Obtaining past exam information

[0973] Specific behavior:

[0974] The server accesses the database to obtain information on past exam questions from the target educational institution. Specifically, it issues a database query to obtain, for example, the past 10 years of exam questions and answers from the University of Tokyo. This allows it to collect information such as past exam question trends and frequently asked questions.

[0975] input:

[0976] Name of the target educational institution

[0977] output:

[0978] Past exam information

[0979] Step 4:

[0980] Matching learning outcomes with exam information

[0981] Specific behavior:

[0982] The server compares the acquired past exam information with the user's learning outcomes. Using data analysis tools, it compares the user's grades in each subject with past exam trends and uses statistical methods and algorithms to identify the user's weak areas (e.g., "calculus" in mathematics).

[0983] input:

[0984] Past exam information, user learning outcome data

[0985] output:

[0986] Identified Weak Areas

[0987] Step 5:

[0988] Generate a customized study plan

[0989] Specific behavior:

[0990] The server generates a customized study plan based on the identified weak areas. It uses a generative AI model to automatically generate a study plan that focuses on the weak areas. For example, a study plan including detailed explanations and practice problems for "calculus" can be generated by passing the prompt "Please create a plan including detailed explanations and practice problems for calculus" to the AI ​​model.

[0991] input:

[0992] Identified weak areas, generated AI model prompt sentences

[0993] output:

[0994] Customized Study Plan

[0995] Step 6:

[0996] Providing study plans

[0997] Specific behavior:

[0998] The server sends the generated study plan to the communication device. The communication device then displays the received study plan to the user in a visually easy-to-understand format. For example, the study plan may be displayed in list format on the user's dashboard, with links and explanations provided. The user can use this information to proceed with their studies.

[0999] input:

[1000] Customized Study Plan

[1001] output:

[1002] The learning plan provided to the user

[1003] (Application example 1)

[1004] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1005] Conventional learning support systems simply provide learning plans and do not provide sufficient support for users to efficiently achieve their goals. In particular, there is a lack of learning support tailored to users of online payment services, and a system that can effectively improve payment-related knowledge and skills is needed.

[1006] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1007] In this invention, the server includes a means for inputting information about a target educational institution, a means for inputting a user's learning outcomes, a means for acquiring information about past exams from the educational institution, a means for comparing the learning outcomes with the past exam information and identifying weak areas, a means for generating a customized study plan based on the weak areas, a means for providing the study plan, and a means for sending a notification to a user terminal based on the study plan, thereby enabling support for the user to study efficiently and achieve their goals more quickly.

[1008] "Means for inputting target educational institution information" refers to a device or interface that allows a user to input the name and details of a particular educational institution that the user is targeting.

[1009] "Means for inputting user learning results" refers to a device or interface that allows users to input the results of their learning so far, test scores, etc.

[1010] "Means for obtaining past exam information" refers to the devices and processes for obtaining past exam questions and related information of the designated educational institution from a database.

[1011] "Means for comparing learning outcomes with past exam information and identifying weak areas" refers to devices and processes that compare and analyze the learning outcomes entered by the user with past exam information and identify in which areas or items the user has weaknesses.

[1012] "Means for generating a customized study plan" refers to a device or software for creating an optimized study plan for a user based on identified weaknesses.

[1013] The "means for providing a study plan" refers to a device or interface for providing the generated study plan to the user.

[1014] The "means for sending a notification to a user terminal based on a study plan" refers to a device or process for sending a notification about the created study plan to a terminal used by a user.

[1015] "Means for storing in a database" refers to the devices and processes for storing the acquired past exam information and other related data in a database.

[1016] "Practice problems and their explanations" refers to a set of problems that correspond to the user's weak areas and content that includes explanations for the problems.

[1017] The system of the present invention provides a customized study plan based on past exam information and the user's learning results so that users who are targeting educational institutions can study effectively. The specific configuration of this system is described below.

[1018] System configuration

[1019] The user first uses a terminal to input information about the educational institution of interest and their current learning outcomes, which are then processed by the server.

[1020] 1. Input Method

[1021] An input form is provided on the device as a means of inputting information about the target educational institution (e.g., "a particular university"), as well as the user's current learning achievements (e.g., mock exam results).

[1022] 2. Data Acquisition Method

[1023] The server retrieves the past exam information of the target educational institution from the database. One way to do this is to use an API to import past exam data.

[1024] 3. Verification Method

[1025] The system compares the learning outcomes with the acquired information on past exam questions to identify the user's weak areas. This process uses machine learning algorithms. Specifically, it uses libraries such as TfidfVectorizer and cosine_similarity.

[1026] 4. Learning plan generation tool

[1027] The server generates a customized study plan based on the identified weaknesses, which includes exercises and explanations that address the weaknesses.

[1028] 5. Means of providing study plans

[1029] The generated learning plan is then delivered to the user's device via notifications and a dashboard.

[1030] Specific examples of hardware and software used

[1031] Devices: PC, smartphone, tablet

[1032] Server: Cloud-based server, on-premise server

[1033] software:

[1034] Database management systems: MySQL, PostgreSQL

[1035] API: RESTful API

[1036] Machine learning library: Scikit-learn

[1037] Notification system: Firebase Cloud Messaging (FCM)

[1038] Specific examples of processing

[1039] Suppose a user is aiming for a specific educational institution (e.g., "specific university") and enters their current mock exam scores of 80 points in mathematics, 72 points in English, and 65 points in Japanese. The server retrieves exam questions from the database for the specific university over the past 10 years and compares them with the user's mock exam scores. As a result, it is determined that the user's weak point in mathematics is "calculus." The server then generates a study plan including practice questions and explanations for "calculus" and sends a notification to the user's device.

[1040] Prompt Sentence Examples

[1041] markdown

[1042] You are a tool that helps business people generate customized study plans to improve their skills related to online payments. Based on the user's goals and current level of understanding, we will compare past exam information to identify weak points and provide the optimal study plan. Please provide the following information:

[1043] Goal: Efficient online payment processing

[1044] Current level of understanding: Understands basic payment processing procedures, but weak in advanced troubleshooting

[1045] By using this prompt, the AI ​​can be informed of the user's specific situation and generate the optimal learning plan.

[1046] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1047] Step 1:

[1048] The user uses a terminal to input information about the educational institution of their choice and their current learning outcomes. The input information includes the name of the educational institution of their choice and the user's mock exam results. This allows the user to clarify their learning goals and current status, laying the foundation for the system to perform the necessary data processing.

[1049] Step 2:

[1050] The server retrieves information about the educational institution's past exam questions from a database based on the information about the educational institution entered by the user. Specifically, it queries the database using the name of the educational institution to retrieve past exam questions and their answers. The information retrieved in this process includes question patterns and frequently asked questions from past exams.

[1051] Step 3:

[1052] The server compares the learning outcomes entered by the user with the acquired information on past exam questions. The learning outcomes are mock test scores, and the acquired information on past exam questions. Specifically, the server uses TfidfVectorizer to vectorize the learning outcomes and exam questions, and calculates the similarity between each item using cosine_similarity. This identifies the user's weak areas.

[1053] Step 4:

[1054] The server generates a customized study plan based on the identified weak areas. The generated study plan includes exercises and explanations corresponding to the identified weak areas. For example, if "calculus" in mathematics is identified as a weak area, the server selects exercises and explanations related to "calculus." This allows the user to efficiently overcome their weak areas.

[1055] Step 5:

[1056] The server provides the generated study plan to the user's device. Specifically, the content of the study plan is sent to the user's device in the form of a notification. The notification includes an overview of the study plan and links to practice questions. This allows the user to proceed with their studies based on the provided study plan.

[1057] Step 6:

[1058] The user studies based on the provided study plan and carries out learning activities to overcome their weaknesses. By inputting the new learning results obtained during this process back into the system, the system can provide an even more accurate study plan. This allows for continuous learning support.

[1059] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1060] The learning support system of the present invention provides a learning plan that will enable a user to efficiently pass the entrance exam for a target educational institution. This system incorporates an emotion engine that recognizes the user's emotions, and is able to provide a flexible learning plan according to the user's emotional state.

[1061] System Overview

[1062] When a user logs into the system using a terminal, they input their target educational institution and current learning outcomes. The system then retrieves past exam information from the target educational institution from a database and compares it with the user's learning outcomes to identify weak areas. It then generates a customized learning plan based on the identified weak areas and displays it on the terminal. An emotional engine then recognizes the user's emotional state and adjusts the difficulty level and feedback of the learning plan.

[1063] Details of each step

[1064] 1. Input method for the target educational institution

[1065] The user enters the name of the target educational institution into an input form on the terminal, for example, "Educational Institution A." The terminal then sends this information to the server.

[1066] 2. Means of inputting learning outcomes

[1067] The user inputs their current learning results (for example, mock exam scores). For example, they input 80 points for math, 72 points for English, and 65 points for Japanese. The terminal then sends this data to the server.

[1068] 3. How to obtain information on past exam questions

[1069] The server accesses the database and retrieves the past exam information of the target educational institution. For example, it retrieves the past 10 years of exam information of educational institution A.

[1070] 4. Means of analyzing learning outcomes

[1071] The server analyzes the learning results received from the user. It analyzes the scores for each subject (e.g., Mathematics 80 points, English 72 points, Japanese 65 points) according to the data format.

[1072] 5. Compare with the standards of your target educational institution

[1073] The server compares the user's learning results with the passing standards of the target educational institution (e.g., 90 points for math, 85 points for English, and 80 points for Japanese). It calculates the score difference and identifies specific weaknesses. For example, it analyzes that math is -10 points, English is -13 points, and Japanese is -15 points.

[1074] 6. Identifying Weak Areas

[1075] The server analyzes detailed problem areas for each subject and identifies areas where students are particularly low-scoring (e.g., calculus).

[1076] 7. Emotion Engine Recognition

[1077] The device collects data such as the user's facial expressions, voice, and input speed, and the emotion engine analyzes this data to recognize the user's emotional state (e.g., stress, joy, fatigue).

[1078] 8. Generate a customized study plan

[1079] Based on the identified weaknesses, the server selects appropriate exercises and explanations and generates a personalized study plan for the user, including calculus exercises and explanations, for example.

[1080] Based on the recognition results of the emotion engine, the difficulty level of the exercises is adjusted appropriately. For example, if the user is feeling stressed, the difficulty level is lowered and easier exercises are provided.

[1081] 9. Providing study plans

[1082] The server sends the generated learning plan to the terminal, which displays the learning plan to the user, who then proceeds with their learning based on the plan.

[1083] 10. Providing Feedback

[1084] Based on the results of the emotion engine, it provides positive feedback and advice to the user, for example, if the user feels a sense of accomplishment, it suggests next steps.

[1085] Specific examples

[1086] Suppose a user sets their target educational institution as "Educational Institution A" and inputs their current mock exam results as 80 points in mathematics, 72 points in English, and 65 points in Japanese. The server retrieves exam questions from the past 10 years of Institution A from the database and compares them with the user's mock exam results. As a result, it is determined that the user's weak point in mathematics is "calculus." Next, if the emotion engine recognizes the user's emotional state and determines that the user is a little tired, the server generates a study plan including simple "calculus" practice problems and explanations and displays it on the device. The user studies based on this, and when they feel more refreshed, they can tackle more difficult problems.

[1087] As described above, the learning support system of the present invention provides an individually optimized learning plan taking into consideration the emotional state of the user, thereby realizing effective and efficient learning.

[1088] The processing flow will be explained below.

[1089] Step 1:

[1090] A user logs into the system

[1091] The user enters their ID and password and clicks the login button. The system checks the user's authentication information against the database and allows them to log in.

[1092] Step 2:

[1093] Setting goals

[1094] The user enters the name of the educational institution they are interested in. For example, they enter "Educational Institution A." The device sends this information to the server.

[1095] Step 3:

[1096] Input of learning outcomes

[1097] The user inputs their current learning results (for example, mock test scores). For example, they input 80 points for math, 72 points for English, and 65 points for Japanese. The terminal then sends this data to the server.

[1098] Step 4:

[1099] Obtaining past exam information

[1100] The server accesses the database and retrieves the past exam information of the target educational institution. For example, it retrieves the past 10 years of exam information of educational institution A.

[1101] Step 5:

[1102] Analysis of learning outcomes

[1103] The server analyzes the learning results received from the user. It analyzes the scores for each subject (e.g., Mathematics 80 points, English 72 points, Japanese 65 points) according to the data format.

[1104] Step 6:

[1105] Comparison with the standards of the target educational institution

[1106] The server compares the user's learning results with the passing standards of the target educational institution (e.g., 90 points for math, 85 points for English, and 80 points for Japanese). It calculates the score difference and identifies specific weaknesses. For example, it analyzes that math is -10 points, English is -13 points, and Japanese is -15 points.

[1107] Step 7:

[1108] Identifying weak areas

[1109] The server analyzes detailed problem areas for each subject and identifies areas where students are particularly low-scoring (e.g., calculus).

[1110] Step 8:

[1111] Emotion Engine Recognition

[1112] The device collects data such as the user's facial expressions, voice, and input speed, and the emotion engine analyzes this data to recognize the user's emotional state (e.g., stress, joy, fatigue).

[1113] Step 9:

[1114] Generate a customized study plan

[1115] The server selects appropriate exercises and explanations based on the identified weaknesses and generates a personalized learning plan for the user. For example, it may include calculus exercises and explanations. Based on the recognition results of the emotion engine, the difficulty of the exercises is adjusted appropriately. For example, if the user is feeling stressed, the difficulty level is lowered to provide easier exercises.

[1116] Step 10:

[1117] Providing study plans

[1118] The server sends the generated learning plan to the terminal, which displays the learning plan to the user, who then proceeds with their learning based on the plan.

[1119] Step 11:

[1120] Providing feedback

[1121] The device will provide the user with positive feedback and advice based on the results of the emotion engine. For example, if the user feels a sense of accomplishment, it will suggest the next step.

[1122] Step 12:

[1123] Learning implementation and evaluation

[1124] The user studies based on the study plan displayed on the device. After completing the study, the user inputs the results into the device and sends them back to the server. The server then analyzes the results again and generates a new study plan.

[1125] The above are the main processing steps in the learning support system of the present invention. These steps allow the user to efficiently progress through their studies and get closer to their target educational institution.

[1126] Example 2

[1127] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1128] Conventional learning support systems can provide a customized learning plan based on a user's learning achievements and areas of weakness, but lack the functionality to adjust the content of the learning plan and feedback based on the user's emotional state. This creates a problem of reduced learning efficiency when a user continues learning while feeling stressed or fatigued. The present invention aims to solve this problem by providing effective and efficient learning support that takes into account the user's emotional state.

[1129] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for inputting information about a target educational institution, a means for inputting the user's learning outcomes, a means for acquiring information about past questions from the educational institution, a means for comparing the learning outcomes with the past question information and identifying weak areas, a means for generating a customized study plan based on the weak areas, a means for adjusting the content and feedback of the study plan using an emotion engine that recognizes the user's emotions, and a means for providing the study plan. This makes it possible to provide an individually optimized study plan taking the user's emotional state into consideration.

[1130] 1. "Target educational institution" refers to the educational institution that the user aims to be accepted into, including schools, universities, and other educational facilities for further education or qualification acquisition.

[1131] 2. "Learning outcomes" refers to data that indicates the progress and results of a user's learning, such as the grades achieved so far, mock test scores, and assignment evaluations.

[1132] 3. "Past exam information" refers to information such as the contents of exam questions and mock exams previously used by the target educational institution, as well as answers and explanations.

[1133] 4. "Weakness Areas" refers to areas or topics in learning that need improvement, as identified based on user learning outcomes.

[1134] 5. "Customized Study Plan" means a plan that includes study assignments, exercises, and explanations that is individually created based on a User's learning achievements and areas of weakness.

[1135] 6. An "emotion engine" is software or a module that analyzes data such as a user's facial expressions, voice, and input speed to recognize the user's emotional state.

[1136] 7. "Feedback" refers to advice, evaluations, comments on learning progress, etc. provided to users by the system.

[1137] 8. A "database" is a system or storage device for structuring and storing information on past exam questions, learning outcomes, user information, etc.

[1138] MODE FOR CARRYING OUT THE INVENTION

[1139] The learning support system of the present invention provides a learning plan that will enable a user to efficiently pass the entrance exam for a target educational institution. This system incorporates an emotion engine that recognizes the user's emotions, and is able to provide a flexible learning plan that corresponds to the user's emotional state.

[1140] System Overview

[1141] When a user logs into the system using a terminal, they first enter their target educational institution and current learning achievements. Based on this information, the system retrieves past exam information from the target educational institution from a database and compares it with the user's learning achievements to identify weak areas. It then generates a customized learning plan based on the identified weak areas and displays it on the terminal. At this time, an emotional engine recognizes the user's emotional state and adjusts the difficulty level and feedback of the learning plan accordingly.

[1142] Hardware and software used

[1143] Hardware: devices such as computers, smartphones, and tablets

[1144] Software: emotion engine, web browser, database system (e.g., MySQL)

[1145] Data processing and calculation

[1146] Data entry: Users enter information about their target educational institutions and mock test results.

[1147] Data transfer: The device sends the entered data to the server.

[1148] Data acquisition: The server acquires past exam information from the database.

[1149] Data analysis: The server analyzes the user's learning results and compares them with past exam information.

[1150] Weakness Identification: The server analyzes the identified weak areas and generates a customized learning plan.

[1151] Emotion recognition: The device acquires the user's emotional data, which is then analyzed by the emotion engine.

[1152] Learning plan generation: The server adjusts the difficulty of the learning plan based on the results of the emotion engine and provides it to the user.

[1153] Specific examples

[1154] Suppose a user sets their target educational institution as "Educational Institution A" and inputs their current mock exam results as 80 points in mathematics, 72 points in English, and 65 points in Japanese. The server retrieves exam questions from the past 10 years of Institution A from the database and compares them with the user's mock exam results. As a result, it is determined that the user's weak point in mathematics is "calculus." Next, if the emotion engine recognizes the user's emotional state and determines that the user is a little tired, the server generates a study plan including simple "calculus" practice problems and explanations and displays it on the device. The user studies based on this, and when they feel more refreshed, they can tackle more difficult problems.

[1155] Prompt Sentence Examples

[1156] "Please set up your institution as Institution A and enter your current mock test scores of 80 points in math, 72 points in English, and 65 points in Japanese. Then, check the customized study plan provided by the system and incorporate feedback based on your emotional state to help you study."

[1157] As described above, the learning support system of the present invention provides an individually optimized learning plan taking into consideration the emotional state of the user, thereby realizing effective and efficient learning.

[1158] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1159] Step 1:

[1160] A user logs into the system using a terminal. The user inputs the information of the target educational institution (e.g., educational institution A). This input information is sent from the terminal to the server. The server temporarily stores the received information of the target educational institution and prepares it for the next step.

[1161] Step 2:

[1162] The user inputs their current learning results, such as mock exam scores (80 points for math, 72 points for English, and 65 points for Japanese). This data is sent to the server via the terminal. The server stores this data in a database and formats it into a structure for analysis.

[1163] Step 3:

[1164] The server accesses the database and, based on the received information about the target educational institution, retrieves information about past exam questions from that educational institution. Specifically, it retrieves exam questions from the past 10 years from educational institution A, along with their answers and explanations. This information is used in the next analysis step.

[1165] Step 4:

[1166] The server analyzes the user's learning outcomes. Based on the input score data (Mathematics 80 points, English 72 points, Japanese 65 points), it evaluates the grades for each subject and performs an analysis to compare them with past exam information. This analysis calculates the score difference for each subject and identifies the user's strengths and weaknesses.

[1167] Step 5:

[1168] The server compares the user's learning results with the passing standards of the target educational institution (for example, 90 points in mathematics, 85 points in English, and 80 points in Japanese) and calculates the score difference. Specifically, the score difference calculated is -10 points in mathematics, -13 points in English, and -15 points in Japanese. Based on the score difference identified here, weak areas are identified.

[1169] Step 6:

[1170] The server analyzes the detailed problem areas for each subject and identifies areas where the user has particularly low scores (e.g., "calculus"). Specifically, it compares the results with information on past exams and creates a list of topics and areas where the user is weak.

[1171] Step 7:

[1172] The device uses sensors to capture the user's facial expression data, voice data, input speed, etc. This data is sent to the server in real time, and the server inputs it into the emotion engine. The emotion engine analyzes this data and determines the user's emotional state (e.g., stress, joy, fatigue).

[1173] Step 8:

[1174] The server generates a customized study plan based on the identified weaknesses and the results of the emotion engine's recognition. Specifically, it adjusts the difficulty level of calculus problems and explanations to create a study plan suited to the user. If the user is feeling stressed, it lowers the difficulty level and provides easier problems.

[1175] Step 9:

[1176] The server sends the generated learning plan to the terminal. The terminal displays this learning plan to the user and provides guidance on how to proceed to the next learning step. The user independently progresses with their learning based on this learning plan.

[1177] Step 10:

[1178] The server generates feedback based on the results of the emotion engine. Specifically, if the user feels a sense of accomplishment, it provides positive feedback suggesting the next step. This feedback is displayed to the user via their device, and serves to maintain and improve their motivation for learning.

[1179] (Application example 2)

[1180] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1181] Conventional learning support systems identify a user's learning progress and weak areas and provide a customized learning plan, but they rarely take the user's emotional state into consideration. This can lead to stress and make it difficult for users to continue learning. Furthermore, because feedback and plan adjustments based on the user's emotional state are not provided, it is difficult to maintain the user's motivation.

[1182] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting information about the target educational institution; means for inputting the user's learning outcomes; means for acquiring information about past exam questions from the educational institution; means for comparing the learning outcomes with the past exam information and identifying weak areas; means for generating a customized study plan based on the weak areas; means for including exercises corresponding to the weak areas and their explanations in the customized study plan; means for incorporating an emotion engine that recognizes the user's emotional state and adjusting the content of the study plan based on the emotional state; and means for providing the study plan. This makes it possible to adjust the difficulty level of the study plan and provide appropriate feedback while monitoring the user's emotional state in real time.

[1183] "Learning results" is data that indicates the grades and progress that a user has achieved in the course of learning.

[1184] "Information about educational institutions" refers to information about entrance exams for schools, universities, etc. that the user is aiming for, including information about past exam questions and passing criteria.

[1185] "Past exam information" refers to data on exam questions previously used by the target educational institution.

[1186] The "emotion engine" is a system that recognizes and analyzes the user's emotional state from facial expressions, voice, etc., and provides information useful for learning support based on the results.

[1187] A "customized study plan" is a study plan that is individually created for a particular user based on their learning results and areas of weakness.

[1188] A "weak area" is an area of ​​study where the user has particularly low scores or lacks understanding during the learning process.

[1189] "Feedback means" is a function for providing appropriate advice and encouraging messages based on the user's learning and emotional state.

[1190] "Real-time" refers to a state in which processing and reaction are carried out immediately without delay, and refers to the emotion engine instantly recognizing and responding to the user's emotional state.

[1191] The present invention is a learning support system that recognizes the user's emotional state and adjusts the learning plan in real time. The system mainly consists of the following components:

[1192] 1. A way to enter information about your target educational institution

[1193] Users use devices such as smartphones or PCs to enter information about the educational institution they wish to apply to (for example, passing criteria and question trends).

[1194] The entered information is sent to the server and stored in a database.

[1195] 2. Means for inputting user learning outcomes

[1196] The user inputs the results of mock exams and regular tests into the terminal.

[1197] This learning outcome data is also sent to the server and stored together with past grades.

[1198] 3. How to obtain information on past exam questions

[1199] The server retrieves past exam information for the target educational institution from the database.

[1200] For example, it contains mathematics exam questions from a particular year, along with their answers and explanations.

[1201] 4. A means of comparing learning outcomes with past exam information to identify weak areas

[1202] The server compares the user's learning results with the acquired past exam information.

[1203] This identifies areas where the user lacks understanding or scores low. For example, in mathematics, calculus may be identified as a weak point.

[1204] 5. A way to generate a customized study plan

[1205] The server generates a personalized learning plan for the user based on the weakness areas.

[1206] This includes practice questions and explanations, and is tailored to the user's learning progress.

[1207] 6. Emotional engine that adjusts learning plans based on emotional state

[1208] The device uses a camera and microphone to capture the user's facial expressions and voice, which are then analyzed by an emotion engine.

[1209] The emotion engine is built using Keras to recognize the user's emotional state (e.g., joy, stress, tiredness) in real time.

[1210] Based on the recognition results, the server automatically adjusts the difficulty and content of the learning plan. For example, if the user is feeling stressed, it provides easy problems and positive feedback.

[1211] 7. Means of providing study plans

[1212] The server sends the generated and adjusted learning plan to the terminal and displays it to the user.

[1213] The user can proceed with their studies according to this study plan.

[1214] Specific examples

[1215] The user sets "Educational Institution A" as their goal and inputs their mock test results (80 points in mathematics, 72 points in English, and 65 points in Japanese). The server retrieves past exam information from Institution A from the database and compares it with the user's grades to identify their weak points. In this case, calculus in mathematics is identified as their weak point. Furthermore, the emotion engine determines that the user is feeling stressed and generates a study plan including easy calculus problems and their explanations. As the study progresses, the difficulty level is dynamically adjusted according to the user's emotional state, and appropriate feedback is provided.

[1216] Prompt Sentence Examples

[1217] The user entered the educational institution they are studying. It was set to "Educational Institution A."

[1218] Here are some of the latest learnings from users:

[1219] Mathematics: 80 points

[1220] English: 72 points

[1221] Japanese: 65 points

[1222] The emotion engine has determined that the user is currently feeling stressed.

[1223] Generate a customized learning plan for your users based on the following criteria:

[1224] The above describes the embodiments of the present invention.

[1225] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1226] Step 1:

[1227] The user logs into the learning support system and enters information about the educational institution of their choice into the terminal. Specifically, the user enters the name of the school or university of their choice into the input form and presses the submit button. This input data (the name of the educational institution of their choice) is sent to the server, which then stores the input data in a database.

[1228] Step 2:

[1229] The user enters their current learning results into the terminal. The user then enters their mock and regular exam scores into the input form and presses the submit button. This input data (scores for each subject) is sent to the server. The server stores this data in a database and integrates it with past grades.

[1230] Step 3:

[1231] The server retrieves past exam information for the target educational institution from the database. It searches the database for past exam questions and answers corresponding to the input target educational institution and retrieves the results. This exam information is used in the next processing step within the server.

[1232] Step 4:

[1233] The server compares the user's learning outcomes with the acquired information on past exam questions to identify weak areas. Specifically, the scores for each subject are compared with the percentage of correct answers to past exam questions, and areas with low scores (e.g., differential and integral calculus in mathematics) are identified as weak areas. This comparison result (weak areas) is used in the next step.

[1234] Step 5:

[1235] The server generates a customized study plan based on the user's weak areas. It selects exercises and explanations that correspond to the identified weak areas and combines them to create a study plan. The study plan is individually customized based on the user's learning progress.

[1236] Step 6:

[1237] The device uses a camera and microphone to capture the user's facial expressions and voice, which are then analyzed by the emotion engine. The emotion engine (a model built using Keras) recognizes the user's emotional state in real time, and the recognition results (e.g., stress, fatigue, etc.) are sent to the server.

[1238] Step 7:

[1239] The server adjusts the difficulty of the study plan based on the recognition results of the emotion engine. Specifically, if the user is feeling stressed, it selects easier questions and adds positive feedback. The adjusted study plan is then sent to the device.

[1240] Step 8:

[1241] The device receives the learning plan from the server and displays it to the user. The user can continue studying according to the displayed learning plan. As the learning progresses, the device continuously monitors the user's emotional state and adjusts the learning plan in real time.

[1242] 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.

[1243] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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.

[1244] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1245] [Fourth embodiment]

[1246] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1247] 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.

[1248] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1249] 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.

[1250] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1251] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1252] 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.

[1253] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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.

[1254] 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.

[1255] 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 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.

[1256] 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.

[1257] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1258] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1259] The learning support system of the present invention provides a study plan that will enable users to efficiently pass the entrance exams for their target educational institutions. The system starts when the user inputs the user's target educational institution and current learning results, identifies the user's weak areas based on past exam information, and provides a study plan that addresses those areas.

[1260] System Overview

[1261] When a user logs in to the system using a device (e.g., a PC or smartphone), the user inputs their target educational institution and current learning outcomes. The system then retrieves past exam information from the target educational institution from a database and compares it with the user's learning outcomes to identify weak areas. It then generates a customized learning plan based on the identified weak areas and displays it on the device.

[1262] Details of each step

[1263] 1. Input method for the target educational institution

[1264] The user inputs the name of the educational institution they are interested in into an input form on their terminal. For example, they input "Tokyo University."

[1265] 2. Means for inputting user learning results

[1266] The user also inputs their current test results (e.g., mock exam scores) into the input form on the terminal. For example, they input 80 points for math, 72 points for English, and 65 points for Japanese.

[1267] 3. How to obtain information on past exam questions

[1268] The server retrieves past exam questions and answers from the database of the target educational institution. For example, it retrieves information on questions from the University of Tokyo for the past 10 years.

[1269] 4. A means of comparing learning outcomes with past exam information

[1270] The server compares the user's learning outcomes with the acquired information on past exam questions and identifies the user's weak areas (e.g., "calculus").

[1271] 5. A way to generate a customized study plan

[1272] The server generates a personalized study plan for the user based on the identified weaknesses, for example, a study plan that includes exercises and explanations for "calculus."

[1273] 6. Means of providing study plans

[1274] The terminal displays the study plan received from the server to the user, who then studies based on it.

[1275] Specific examples

[1276] Suppose a user sets the educational institution they are aiming for as "University of Tokyo" and inputs their current mock exam results as 80 points in mathematics, 72 points in English, and 65 points in Japanese. The server retrieves exam questions from the database for the past 10 years for the University of Tokyo and compares them with the user's mock exam results. As a result, it is determined that the user's weak point in mathematics is "calculus." The server then generates a study plan for "calculus" that includes practice questions and explanations, and displays it on the device. The user then uses this plan to study independently and overcome their weak points.

[1277] As described above, the learning support system of the present invention provides effective and individually optimized learning plans to users, thereby efficiently supporting learning aimed at achieving goals.

[1278] The processing flow will be explained below.

[1279] Step 1:

[1280] A user logs into the system

[1281] The user enters their ID and password and clicks the login button. The system checks the user's authentication information against the database and allows them to log in.

[1282] Step 2:

[1283] Setting goals

[1284] The user enters the name of the educational institution they are interested in. For example, they enter "Educational Institution A." The device sends this information to the server.

[1285] Step 3:

[1286] Input of learning outcomes

[1287] The user inputs their current learning results (for example, mock test scores). For example, they input 80 points for math, 72 points for English, and 65 points for Japanese. The terminal also sends this data to the server.

[1288] Step 4:

[1289] Obtaining past exam information

[1290] The server accesses the database and retrieves the past exam information of the target educational institution. For example, it retrieves the past 10 years of exam information of educational institution A.

[1291] Step 5:

[1292] Analysis of learning outcomes

[1293] The server analyzes the learning results received from the user. It analyzes the scores for each subject (e.g., Mathematics 80 points, English 72 points, Japanese 65 points) according to the data format.

[1294] Step 6:

[1295] Comparison with the standards of the target educational institution

[1296] The server compares the user's learning results with the passing standards of the target educational institution (e.g., 90 points for math, 85 points for English, and 80 points for Japanese). It calculates the score difference and identifies specific weaknesses. For example, it analyzes that math is -10 points, English is -13 points, and Japanese is -15 points.

[1297] Step 7:

[1298] Identifying weak areas

[1299] The server analyzes detailed problem areas for each subject and identifies areas where students are particularly low-scoring (e.g., calculus).

[1300] Step 8:

[1301] Generate a customized study plan

[1302] Based on the identified weaknesses, the server selects appropriate exercises and explanations and generates a personalized study plan for the user, including calculus exercises and explanations, for example.

[1303] Step 9:

[1304] Submitting and Viewing Learning Plans

[1305] The server sends the generated study plan to the device. The device displays the study plan to the user. The user then proceeds with their study based on the provided practice questions and explanations.

[1306] Step 10:

[1307] Learning implementation and feedback

[1308] The user studies based on the study plan displayed on the device. After completing the study, the user inputs the results into the device and sends them back to the server. The server then analyzes the results again and generates a new study plan.

[1309] These are the main processing steps in the program of the present invention, which allow users to efficiently advance their studies and get closer to their target educational institution.

[1310] Example 1

[1311] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1312] Conventional learning systems have difficulty providing an optimal learning plan tailored to each user's individual learning outcomes and desired educational institution, making it difficult to study efficiently. In particular, they lacked a means to identify specific areas of weakness and automatically generate an appropriate learning plan based on those areas. This resulted in a decrease in users' learning efficiency and a decrease in the chances of passing the entrance exam for the desired educational institution.

[1313] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1314] In this invention, the server includes means for a user to input information about a target educational institution using a communication terminal, means for inputting the user's learning outcomes through the communication terminal, means for retrieving information about past exams of the educational institution from a database, means for comparing the learning outcomes with the past exam information on the server and identifying the user's weak areas, means for generating a customized study plan based on the identified weak areas using the generative AI model, and means for providing the study plan to the communication terminal, thereby making it possible to automatically provide an optimal study plan for each user.

[1315] A "user" is an individual who uses the learning support system and is a subject who studies with the aim of passing the entrance exam to a target educational institution.

[1316] A "communication terminal" is an electronic device that a user uses to access the learning support system, and specifically includes a personal computer or smartphone.

[1317] The term "server" refers to a central control device of the learning support system, and is a computer device that has the function of processing information input by users and generating and providing learning plans.

[1318] A "database" is a system that systematically stores information on past exam questions from educational institutions and users' learning outcomes, and allows data to be searched and retrieved as needed.

[1319] A "generative AI model" is an algorithm or program that uses machine learning and artificial intelligence technology to automatically generate optimal study plans based on a user's learning data and goals.

[1320] "Target educational institution information" is information related to the name of a particular educational institution or exam that the user aims to pass.

[1321] "Learning results" refers to evaluation data obtained as a result of learning, such as the results and scores of tests and mock tests that the user has taken in the past.

[1322] "Past exam information" refers to data on exam questions and answers previously administered by educational institutions.

[1323] "Weak areas" refer to areas or items in which the user has particularly insufficient understanding during their studies, and are areas that need to be supplemented.

[1324] A "Customized Study Plan" is a collection of study content and materials specifically designed to meet a user's individual weaknesses.

[1325] MODE FOR CARRYING OUT THE INVENTION

[1326] The learning support system of the present invention provides a learning plan that will enable a user to efficiently pass the entrance exam for a target educational institution. An embodiment of this system will be specifically described below.

[1327] The system begins when a user accesses the system using a communication device (such as a PC or smartphone) and enters information about the educational institution of interest and their current learning outcomes. Based on this information, the server retrieves the institution's past exam information from a database and compares it with the user's learning outcomes to identify areas of weakness. The system then uses a generative AI model to generate a customized learning plan that addresses the user's weaknesses and provides it to the communication device.

[1328] The server functions using the following main hardware and software:

[1329] 1. Hardware:

[1330] Server body (high-performance CPU, memory, storage)

[1331] Communication infrastructure (Internet connection, network equipment)

[1332] Database Server

[1333] 2. Software:

[1334] Database management systems (e.g., MySQL, PostgreSQL)

[1335] Web server software (e.g., Apache, Nginx)

[1336] Programming language (e.g. Python, JavaScript)

[1337] Generative AI models (e.g., GPT-3, BERT)

[1338] Detailed explanation of each step

[1339] 1. The user logs in and enters the information for the target educational institution

[1340] A user logs into the system using a communication terminal and inputs the target educational institution (e.g., "University of Tokyo") through an input form on a web browser.

[1341] Example: Set "University of Tokyo" as the target educational institution.

[1342] 2. Input of user learning outcomes

[1343] The user uses the communication terminal to input the current learning results (e.g., mock exam scores), for example, 80 points for mathematics, 72 points for English, and 65 points for Japanese.

[1344] Example: Enter 80 points for math, 72 points for English, and 65 points for Japanese.

[1345] 3. Obtaining past exam information

[1346] The server accesses the database and retrieves information on past exam questions from the target educational institution, such as the University of Tokyo's exam questions and answers from the past 10 years.

[1347] Software used: Database management system (MySQL, PostgreSQL)

[1348] 4. Matching learning outcomes with exam information

[1349] The server compares the acquired test information with the user's learning results and identifies the user's weak areas. Specifically, it uses an algorithm to compare mock test results with past test trends.

[1350] Software used: Data analysis tool (Python)

[1351] 5. Generate a customized study plan

[1352] The server uses a generative AI model to generate a study plan based on the identified weaknesses. For example, if calculus is a weakness in mathematics, the server generates prompts to create a study plan that includes practice problems and explanations for this area.

[1353] Software used: Generative AI model (GPT-3)

[1354] 6. Providing study plans

[1355] The generated study plan is provided to the user via a communication terminal, and the user can proceed with their studies based on the provided plan.

[1356] Software used: Web server software (Apache, Nginx)

[1357] Prompt Sentence Examples

[1358] Here is an example of a prompt for a generative AI model:

[1359] "Create a plan that includes detailed explanations and practice questions for calculus."

[1360] As a result, the learning support system of the present invention can provide effective learning plans tailored to the weak points of each individual user, and support the student in passing the entrance exams to their target educational institutions.

[1361] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1362] Step 1:

[1363] User logs in and enters information about the target institution

[1364] Specific behavior:

[1365] Users log in to the system using a communication device such as a PC or smartphone. They enter their user ID and password into the login screen on their web browser and press the login button. If authentication is successful, the dashboard is displayed. Next, they enter the name of their target educational institution from the dashboard (e.g., "University of Tokyo").

[1366] input:

[1367] User ID, password, name of the target educational institution

[1368] output:

[1369] User login status, name of target educational institution

[1370] Step 2:

[1371] Input of user learning outcomes

[1372] Specific behavior:

[1373] The user also uses the communication terminal to input their current learning results (e.g., mock test scores), enter specific score information (e.g., 80 points for mathematics, 72 points for English, 65 points for Japanese) into the input form on the dashboard, and press the send button.

[1374] input:

[1375] Current learning results (e.g., 80 points in mathematics, 72 points in English, 65 points in Japanese)

[1376] output:

[1377] User learning outcome data

[1378] Step 3:

[1379] Obtaining past exam information

[1380] Specific behavior:

[1381] The server accesses the database to obtain information on past exam questions from the target educational institution. Specifically, it issues a database query to obtain, for example, the past 10 years of exam questions and answers from the University of Tokyo. This allows it to collect information such as past exam question trends and frequently asked questions.

[1382] input:

[1383] Name of the target educational institution

[1384] output:

[1385] Past exam information

[1386] Step 4:

[1387] Matching learning outcomes with exam information

[1388] Specific behavior:

[1389] The server compares the acquired past exam information with the user's learning outcomes. Using data analysis tools, it compares the user's grades in each subject with past exam trends and uses statistical methods and algorithms to identify the user's weak areas (e.g., "calculus" in mathematics).

[1390] input:

[1391] Past exam information, user learning outcome data

[1392] output:

[1393] Identified Weak Areas

[1394] Step 5:

[1395] Generate a customized study plan

[1396] Specific behavior:

[1397] The server generates a customized study plan based on the identified weak areas. It uses a generative AI model to automatically generate a study plan that focuses on the weak areas. For example, a study plan including detailed explanations and practice problems for "calculus" can be generated by passing the prompt "Please create a plan including detailed explanations and practice problems for calculus" to the AI ​​model.

[1398] input:

[1399] Identified weak areas, generated AI model prompt sentences

[1400] output:

[1401] Customized Study Plan

[1402] Step 6:

[1403] Providing study plans

[1404] Specific behavior:

[1405] The server sends the generated study plan to the communication device. The communication device then displays the received study plan to the user in a visually easy-to-understand format. For example, the study plan may be displayed in list format on the user's dashboard, with links and explanations provided. The user can use this information to proceed with their studies.

[1406] input:

[1407] Customized Study Plan

[1408] output:

[1409] The learning plan provided to the user

[1410] (Application example 1)

[1411] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1412] Conventional learning support systems simply provide learning plans and do not provide sufficient support for users to efficiently achieve their goals. In particular, there is a lack of learning support tailored to users of online payment services, and a system that can effectively improve payment-related knowledge and skills is needed.

[1413] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1414] In this invention, the server includes a means for inputting information about a target educational institution, a means for inputting a user's learning outcomes, a means for acquiring information about past exams from the educational institution, a means for comparing the learning outcomes with the past exam information and identifying weak areas, a means for generating a customized study plan based on the weak areas, a means for providing the study plan, and a means for sending a notification to a user terminal based on the study plan, thereby enabling support for the user to study efficiently and achieve their goals more quickly.

[1415] "Means for inputting target educational institution information" refers to a device or interface that allows a user to input the name and details of a particular educational institution that the user is targeting.

[1416] "Means for inputting user learning results" refers to a device or interface that allows users to input the results of their learning so far, test scores, etc.

[1417] "Means for obtaining past exam information" refers to the devices and processes for obtaining past exam questions and related information of the designated educational institution from a database.

[1418] "Means for comparing learning outcomes with past exam information and identifying weak areas" refers to devices and processes that compare and analyze the learning outcomes entered by the user with past exam information and identify in which areas or items the user has weaknesses.

[1419] "Means for generating a customized study plan" refers to a device or software for creating an optimized study plan for a user based on identified weaknesses.

[1420] The "means for providing a study plan" refers to a device or interface for providing the generated study plan to the user.

[1421] The "means for sending a notification to a user terminal based on a study plan" refers to a device or process for sending a notification about the created study plan to a terminal used by a user.

[1422] "Means for storing in a database" refers to the devices and processes for storing the acquired past exam information and other related data in a database.

[1423] "Practice problems and their explanations" refers to a set of problems that correspond to the user's weak areas and content that includes explanations for the problems.

[1424] The system of the present invention provides a customized study plan based on past exam information and the user's learning results so that users who are targeting educational institutions can study effectively. The specific configuration of this system is described below.

[1425] System configuration

[1426] The user first uses a terminal to input information about the educational institution of interest and their current learning outcomes, which are then processed by the server.

[1427] 1. Input Method

[1428] An input form is provided on the device as a means of inputting information about the target educational institution (e.g., "a particular university"), as well as the user's current learning achievements (e.g., mock exam results).

[1429] 2. Data Acquisition Method

[1430] The server retrieves the past exam information of the target educational institution from the database. One way to do this is to use an API to import past exam data.

[1431] 3. Verification Method

[1432] The system compares the learning outcomes with the acquired information on past exam questions to identify the user's weak areas. This process uses machine learning algorithms. Specifically, it uses libraries such as TfidfVectorizer and cosine_similarity.

[1433] 4. Learning plan generation tool

[1434] The server generates a customized study plan based on the identified weaknesses, which includes exercises and explanations that address the weaknesses.

[1435] 5. Means of providing study plans

[1436] The generated learning plan is then delivered to the user's device via notifications and a dashboard.

[1437] Specific examples of hardware and software used

[1438] Devices: PC, smartphone, tablet

[1439] Server: Cloud-based server, on-premise server

[1440] software:

[1441] Database management systems: MySQL, PostgreSQL

[1442] API: RESTful API

[1443] Machine learning library: Scikit-learn

[1444] Notification system: Firebase Cloud Messaging (FCM)

[1445] Specific examples of processing

[1446] Suppose a user is aiming for a specific educational institution (e.g., "specific university") and enters their current mock exam scores of 80 points in mathematics, 72 points in English, and 65 points in Japanese. The server retrieves exam questions from the database for the specific university over the past 10 years and compares them with the user's mock exam scores. As a result, it is determined that the user's weak point in mathematics is "calculus." The server then generates a study plan including practice questions and explanations for "calculus" and sends a notification to the user's device.

[1447] Prompt Sentence Examples

[1448] markdown

[1449] You are a tool that helps business people generate customized study plans to improve their skills related to online payments. Based on the user's goals and current level of understanding, we will compare past exam information to identify weak points and provide the optimal study plan. Please provide the following information:

[1450] Goal: Efficient online payment processing

[1451] Current level of understanding: Understands basic payment processing procedures, but weak in advanced troubleshooting

[1452] By using this prompt, the AI ​​can be informed of the user's specific situation and generate the optimal learning plan.

[1453] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1454] Step 1:

[1455] The user uses a terminal to input information about the educational institution of their choice and their current learning outcomes. The input information includes the name of the educational institution of their choice and the user's mock exam results. This allows the user to clarify their learning goals and current status, laying the foundation for the system to perform the necessary data processing.

[1456] Step 2:

[1457] The server retrieves information about the educational institution's past exam questions from a database based on the information about the educational institution entered by the user. Specifically, it queries the database using the name of the educational institution to retrieve past exam questions and their answers. The information retrieved in this process includes question patterns and frequently asked questions from past exams.

[1458] Step 3:

[1459] The server compares the learning outcomes entered by the user with the acquired information on past exam questions. The learning outcomes are mock test scores, and the acquired information on past exam questions. Specifically, the server uses TfidfVectorizer to vectorize the learning outcomes and exam questions, and calculates the similarity between each item using cosine_similarity. This identifies the user's weak areas.

[1460] Step 4:

[1461] The server generates a customized study plan based on the identified weak areas. The generated study plan includes exercises and explanations corresponding to the identified weak areas. For example, if "calculus" in mathematics is identified as a weak area, the server selects exercises and explanations related to "calculus." This allows the user to efficiently overcome their weak areas.

[1462] Step 5:

[1463] The server provides the generated study plan to the user's device. Specifically, the content of the study plan is sent to the user's device in the form of a notification. The notification includes an overview of the study plan and links to practice questions. This allows the user to proceed with their studies based on the provided study plan.

[1464] Step 6:

[1465] The user studies based on the provided study plan and carries out learning activities to overcome their weaknesses. By inputting the new learning results obtained during this process back into the system, the system can provide an even more accurate study plan. This allows for continuous learning support.

[1466] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1467] The learning support system of the present invention provides a learning plan that will enable a user to efficiently pass the entrance exam for a target educational institution. This system incorporates an emotion engine that recognizes the user's emotions, and is able to provide a flexible learning plan according to the user's emotional state.

[1468] System Overview

[1469] When a user logs into the system using a terminal, they input their target educational institution and current learning outcomes. The system then retrieves past exam information from the target educational institution from a database and compares it with the user's learning outcomes to identify weak areas. It then generates a customized learning plan based on the identified weak areas and displays it on the terminal. An emotional engine then recognizes the user's emotional state and adjusts the difficulty level and feedback of the learning plan.

[1470] Details of each step

[1471] 1. Input method for the target educational institution

[1472] The user enters the name of the target educational institution into an input form on the terminal, for example, "Educational Institution A." The terminal then sends this information to the server.

[1473] 2. Means of inputting learning outcomes

[1474] The user inputs their current learning results (for example, mock exam scores). For example, they input 80 points for math, 72 points for English, and 65 points for Japanese. The terminal then sends this data to the server.

[1475] 3. How to obtain information on past exam questions

[1476] The server accesses the database and retrieves the past exam information of the target educational institution. For example, it retrieves the past 10 years of exam information of educational institution A.

[1477] 4. Means of analyzing learning outcomes

[1478] The server analyzes the learning results received from the user. It analyzes the scores for each subject (e.g., Mathematics 80 points, English 72 points, Japanese 65 points) according to the data format.

[1479] 5. Compare with the standards of your target educational institution

[1480] The server compares the user's learning results with the passing standards of the target educational institution (e.g., 90 points for math, 85 points for English, and 80 points for Japanese). It calculates the score difference and identifies specific weaknesses. For example, it analyzes that math is -10 points, English is -13 points, and Japanese is -15 points.

[1481] 6. Identifying Weak Areas

[1482] The server analyzes detailed problem areas for each subject and identifies areas where students are particularly low-scoring (e.g., calculus).

[1483] 7. Emotion Engine Recognition

[1484] The device collects data such as the user's facial expressions, voice, and input speed, and the emotion engine analyzes this data to recognize the user's emotional state (e.g., stress, joy, fatigue).

[1485] 8. Generate a customized study plan

[1486] Based on the identified weaknesses, the server selects appropriate exercises and explanations and generates a personalized study plan for the user, including calculus exercises and explanations, for example.

[1487] Based on the recognition results of the emotion engine, the difficulty level of the exercises is adjusted appropriately. For example, if the user is feeling stressed, the difficulty level is lowered and easier exercises are provided.

[1488] 9. Providing study plans

[1489] The server sends the generated learning plan to the terminal, which displays the learning plan to the user, who then proceeds with their learning based on the plan.

[1490] 10. Providing Feedback

[1491] Based on the results of the emotion engine, it provides positive feedback and advice to the user, for example, if the user feels a sense of accomplishment, it suggests next steps.

[1492] Specific examples

[1493] Suppose a user sets their target educational institution as "Educational Institution A" and inputs their current mock exam results as 80 points in mathematics, 72 points in English, and 65 points in Japanese. The server retrieves exam questions from the past 10 years of Institution A from the database and compares them with the user's mock exam results. As a result, it is determined that the user's weak point in mathematics is "calculus." Next, if the emotion engine recognizes the user's emotional state and determines that the user is a little tired, the server generates a study plan including simple "calculus" practice problems and explanations and displays it on the device. The user studies based on this, and when they feel more refreshed, they can tackle more difficult problems.

[1494] As described above, the learning support system of the present invention provides an individually optimized learning plan taking into consideration the emotional state of the user, thereby realizing effective and efficient learning.

[1495] The processing flow will be explained below.

[1496] Step 1:

[1497] A user logs into the system

[1498] The user enters their ID and password and clicks the login button. The system checks the user's authentication information against the database and allows them to log in.

[1499] Step 2:

[1500] Setting goals

[1501] The user enters the name of the educational institution they are interested in. For example, they enter "Educational Institution A." The device sends this information to the server.

[1502] Step 3:

[1503] Input of learning outcomes

[1504] The user inputs their current learning results (for example, mock test scores). For example, they input 80 points for math, 72 points for English, and 65 points for Japanese. The terminal then sends this data to the server.

[1505] Step 4:

[1506] Obtaining past exam information

[1507] The server accesses the database and retrieves the past exam information of the target educational institution. For example, it retrieves the past 10 years of exam information of educational institution A.

[1508] Step 5:

[1509] Analysis of learning outcomes

[1510] The server analyzes the learning results received from the user. It analyzes the scores for each subject (e.g., Mathematics 80 points, English 72 points, Japanese 65 points) according to the data format.

[1511] Step 6:

[1512] Comparison with the standards of the target educational institution

[1513] The server compares the user's learning results with the passing standards of the target educational institution (e.g., 90 points for math, 85 points for English, and 80 points for Japanese). It calculates the score difference and identifies specific weaknesses. For example, it analyzes that math is -10 points, English is -13 points, and Japanese is -15 points.

[1514] Step 7:

[1515] Identifying weak areas

[1516] The server analyzes detailed problem areas for each subject and identifies areas where students are particularly low-scoring (e.g., calculus).

[1517] Step 8:

[1518] Emotion Engine Recognition

[1519] The device collects data such as the user's facial expressions, voice, and input speed, and the emotion engine analyzes this data to recognize the user's emotional state (e.g., stress, joy, fatigue).

[1520] Step 9:

[1521] Generate a customized study plan

[1522] The server selects appropriate exercises and explanations based on the identified weaknesses and generates a personalized learning plan for the user. For example, it may include calculus exercises and explanations. Based on the recognition results of the emotion engine, the difficulty of the exercises is adjusted appropriately. For example, if the user is feeling stressed, the difficulty level is lowered to provide easier exercises.

[1523] Step 10:

[1524] Providing study plans

[1525] The server sends the generated learning plan to the terminal, which displays the learning plan to the user, who then proceeds with their learning based on the plan.

[1526] Step 11:

[1527] Providing feedback

[1528] The device will provide the user with positive feedback and advice based on the results of the emotion engine. For example, if the user feels a sense of accomplishment, it will suggest the next step.

[1529] Step 12:

[1530] Learning implementation and evaluation

[1531] The user studies based on the study plan displayed on the device. After completing the study, the user inputs the results into the device and sends them back to the server. The server then analyzes the results again and generates a new study plan.

[1532] The above are the main processing steps in the learning support system of the present invention. These steps allow the user to efficiently progress through their studies and get closer to their target educational institution.

[1533] Example 2

[1534] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1535] Conventional learning support systems can provide a customized learning plan based on a user's learning achievements and areas of weakness, but lack the functionality to adjust the content of the learning plan and feedback based on the user's emotional state. This creates a problem of reduced learning efficiency when a user continues learning while feeling stressed or fatigued. The present invention aims to solve this problem by providing effective and efficient learning support that takes into account the user's emotional state.

[1536] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for inputting information about a target educational institution, a means for inputting the user's learning outcomes, a means for acquiring information about past questions from the educational institution, a means for comparing the learning outcomes with the past question information and identifying weak areas, a means for generating a customized study plan based on the weak areas, a means for adjusting the content and feedback of the study plan using an emotion engine that recognizes the user's emotions, and a means for providing the study plan. This makes it possible to provide an individually optimized study plan taking the user's emotional state into consideration.

[1537] 1. "Target educational institution" refers to the educational institution that the user aims to be accepted into, including schools, universities, and other educational facilities for further education or qualification acquisition.

[1538] 2. "Learning outcomes" refers to data that indicates the progress and results of a user's learning, such as the grades achieved so far, mock test scores, and assignment evaluations.

[1539] 3. "Past exam information" refers to information such as the contents of exam questions and mock exams previously used by the target educational institution, as well as answers and explanations.

[1540] 4. "Weakness Areas" refers to areas or topics in learning that need improvement, as identified based on user learning outcomes.

[1541] 5. "Customized Study Plan" means a plan that includes study assignments, exercises, and explanations that is individually created based on a User's learning achievements and areas of weakness.

[1542] 6. An "emotion engine" is software or a module that analyzes data such as a user's facial expressions, voice, and input speed to recognize the user's emotional state.

[1543] 7. "Feedback" refers to advice, evaluations, comments on learning progress, etc. provided to users by the system.

[1544] 8. A "database" is a system or storage device for structuring and storing information on past exam questions, learning outcomes, user information, etc.

[1545] MODE FOR CARRYING OUT THE INVENTION

[1546] The learning support system of the present invention provides a learning plan that will enable a user to efficiently pass the entrance exam for a target educational institution. This system incorporates an emotion engine that recognizes the user's emotions, and is able to provide a flexible learning plan that corresponds to the user's emotional state.

[1547] System Overview

[1548] When a user logs into the system using a terminal, they first enter their target educational institution and current learning achievements. Based on this information, the system retrieves past exam information from the target educational institution from a database and compares it with the user's learning achievements to identify weak areas. It then generates a customized learning plan based on the identified weak areas and displays it on the terminal. At this time, an emotional engine recognizes the user's emotional state and adjusts the difficulty level and feedback of the learning plan accordingly.

[1549] Hardware and software used

[1550] Hardware: devices such as computers, smartphones, and tablets

[1551] Software: emotion engine, web browser, database system (e.g., MySQL)

[1552] Data processing and calculation

[1553] Data entry: Users enter information about their target educational institutions and mock test results.

[1554] Data transfer: The device sends the entered data to the server.

[1555] Data acquisition: The server acquires past exam information from the database.

[1556] Data analysis: The server analyzes the user's learning results and compares them with past exam information.

[1557] Weakness Identification: The server analyzes the identified weak areas and generates a customized learning plan.

[1558] Emotion recognition: The device acquires the user's emotional data, which is then analyzed by the emotion engine.

[1559] Learning plan generation: The server adjusts the difficulty of the learning plan based on the results of the emotion engine and provides it to the user.

[1560] Specific examples

[1561] Suppose a user sets their target educational institution as "Educational Institution A" and inputs their current mock exam results as 80 points in mathematics, 72 points in English, and 65 points in Japanese. The server retrieves exam questions from the past 10 years of Institution A from the database and compares them with the user's mock exam results. As a result, it is determined that the user's weak point in mathematics is "calculus." Next, if the emotion engine recognizes the user's emotional state and determines that the user is a little tired, the server generates a study plan including simple "calculus" practice problems and explanations and displays it on the device. The user studies based on this, and when they feel more refreshed, they can tackle more difficult problems.

[1562] Prompt Sentence Examples

[1563] "Please set up your institution as Institution A and enter your current mock test scores of 80 points in math, 72 points in English, and 65 points in Japanese. Then, check the customized study plan provided by the system and incorporate feedback based on your emotional state to help you study."

[1564] As described above, the learning support system of the present invention provides an individually optimized learning plan taking into consideration the emotional state of the user, thereby realizing effective and efficient learning.

[1565] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1566] Step 1:

[1567] A user logs into the system using a terminal. The user inputs the information of the target educational institution (e.g., educational institution A). This input information is sent from the terminal to the server. The server temporarily stores the received information of the target educational institution and prepares it for the next step.

[1568] Step 2:

[1569] The user inputs their current learning results, such as mock exam scores (80 points for math, 72 points for English, and 65 points for Japanese). This data is sent to the server via the terminal. The server stores this data in a database and formats it into a structure for analysis.

[1570] Step 3:

[1571] The server accesses the database and, based on the received information about the target educational institution, retrieves information about past exam questions from that educational institution. Specifically, it retrieves exam questions from the past 10 years from educational institution A, along with their answers and explanations. This information is used in the next analysis step.

[1572] Step 4:

[1573] The server analyzes the user's learning outcomes. Based on the input score data (Mathematics 80 points, English 72 points, Japanese 65 points), it evaluates the grades for each subject and performs an analysis to compare them with past exam information. This analysis calculates the score difference for each subject and identifies the user's strengths and weaknesses.

[1574] Step 5:

[1575] The server compares the user's learning results with the passing standards of the target educational institution (for example, 90 points in mathematics, 85 points in English, and 80 points in Japanese) and calculates the score difference. Specifically, the score difference calculated is -10 points in mathematics, -13 points in English, and -15 points in Japanese. Based on the score difference identified here, weak areas are identified.

[1576] Step 6:

[1577] The server analyzes the detailed problem areas for each subject and identifies areas where the user has particularly low scores (e.g., "calculus"). Specifically, it compares the results with information on past exams and creates a list of topics and areas where the user is weak.

[1578] Step 7:

[1579] The device uses sensors to capture the user's facial expression data, voice data, input speed, etc. This data is sent to the server in real time, and the server inputs it into the emotion engine. The emotion engine analyzes this data and determines the user's emotional state (e.g., stress, joy, fatigue).

[1580] Step 8:

[1581] The server generates a customized study plan based on the identified weaknesses and the results of the emotion engine's recognition. Specifically, it adjusts the difficulty level of calculus problems and explanations to create a study plan suited to the user. If the user is feeling stressed, it lowers the difficulty level and provides easier problems.

[1582] Step 9:

[1583] The server sends the generated learning plan to the terminal. The terminal displays this learning plan to the user and provides guidance on how to proceed to the next learning step. The user independently progresses with their learning based on this learning plan.

[1584] Step 10:

[1585] The server generates feedback based on the results of the emotion engine. Specifically, if the user feels a sense of accomplishment, it provides positive feedback suggesting the next step. This feedback is displayed to the user via their device, and serves to maintain and improve their motivation for learning.

[1586] (Application example 2)

[1587] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1588] Conventional learning support systems identify a user's learning progress and weak areas and provide a customized learning plan, but they rarely take the user's emotional state into consideration. This can lead to stress and make it difficult for users to continue learning. Furthermore, because feedback and plan adjustments based on the user's emotional state are not provided, it is difficult to maintain the user's motivation.

[1589] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting information about the target educational institution; means for inputting the user's learning outcomes; means for acquiring information about past exam questions from the educational institution; means for comparing the learning outcomes with the past exam information and identifying weak areas; means for generating a customized study plan based on the weak areas; means for including exercises corresponding to the weak areas and their explanations in the customized study plan; means for incorporating an emotion engine that recognizes the user's emotional state and adjusting the content of the study plan based on the emotional state; and means for providing the study plan. This makes it possible to adjust the difficulty level of the study plan and provide appropriate feedback while monitoring the user's emotional state in real time.

[1590] "Learning results" is data that indicates the grades and progress that a user has achieved in the course of learning.

[1591] "Information about educational institutions" refers to information about entrance exams for schools, universities, etc. that the user is aiming for, including information about past exam questions and passing criteria.

[1592] "Past exam information" refers to data on exam questions previously used by the target educational institution.

[1593] The "emotion engine" is a system that recognizes and analyzes the user's emotional state from facial expressions, voice, etc., and provides information useful for learning support based on the results.

[1594] A "customized study plan" is a study plan that is individually created for a particular user based on their learning results and areas of weakness.

[1595] A "weak area" is an area of ​​study where the user has particularly low scores or lacks understanding during the learning process.

[1596] "Feedback means" is a function for providing appropriate advice and encouraging messages based on the user's learning and emotional state.

[1597] "Real-time" refers to a state in which processing and reaction are carried out immediately without delay, and refers to the emotion engine instantly recognizing and responding to the user's emotional state.

[1598] The present invention is a learning support system that recognizes the user's emotional state and adjusts the learning plan in real time. The system mainly consists of the following components:

[1599] 1. A way to enter information about your target educational institution

[1600] Users use devices such as smartphones or PCs to enter information about the educational institution they wish to apply to (for example, passing criteria and question trends).

[1601] The entered information is sent to the server and stored in a database.

[1602] 2. Means for inputting user learning outcomes

[1603] The user inputs the results of mock exams and regular tests into the terminal.

[1604] This learning outcome data is also sent to the server and stored together with past grades.

[1605] 3. How to obtain information on past exam questions

[1606] The server retrieves past exam information for the target educational institution from the database.

[1607] For example, it contains mathematics exam questions from a particular year, along with their answers and explanations.

[1608] 4. A means of comparing learning outcomes with past exam information to identify weak areas

[1609] The server compares the user's learning results with the acquired past exam information.

[1610] This identifies areas where the user lacks understanding or scores low. For example, in mathematics, calculus may be identified as a weak point.

[1611] 5. A way to generate a customized study plan

[1612] The server generates a personalized learning plan for the user based on the weakness areas.

[1613] This includes practice questions and explanations, and is tailored to the user's learning progress.

[1614] 6. Emotional engine that adjusts learning plans based on emotional state

[1615] The device uses a camera and microphone to capture the user's facial expressions and voice, which are then analyzed by an emotion engine.

[1616] The emotion engine is built using Keras to recognize the user's emotional state (e.g., joy, stress, tiredness) in real time.

[1617] Based on the recognition results, the server automatically adjusts the difficulty and content of the learning plan. For example, if the user is feeling stressed, it provides easy problems and positive feedback.

[1618] 7. Means of providing study plans

[1619] The server sends the generated and adjusted learning plan to the terminal and displays it to the user.

[1620] The user can proceed with their studies according to this study plan.

[1621] Specific examples

[1622] The user sets "Educational Institution A" as their goal and inputs their mock test results (80 points in mathematics, 72 points in English, and 65 points in Japanese). The server retrieves past exam information from Institution A from the database and compares it with the user's grades to identify their weak points. In this case, calculus in mathematics is identified as their weak point. Furthermore, the emotion engine determines that the user is feeling stressed and generates a study plan including easy calculus problems and their explanations. As the study progresses, the difficulty level is dynamically adjusted according to the user's emotional state, and appropriate feedback is provided.

[1623] Prompt Sentence Examples

[1624] The user entered the educational institution they are studying. It was set to "Educational Institution A."

[1625] Here are some of the latest learnings from users:

[1626] Mathematics: 80 points

[1627] English: 72 points

[1628] Japanese: 65 points

[1629] The emotion engine has determined that the user is currently feeling stressed.

[1630] Generate a customized learning plan for your users based on the following criteria:

[1631] The above describes the embodiments of the present invention.

[1632] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1633] Step 1:

[1634] The user logs into the learning support system and enters information about the educational institution of their choice into the terminal. Specifically, the user enters the name of the school or university of their choice into the input form and presses the submit button. This input data (the name of the educational institution of their choice) is sent to the server, which then stores the input data in a database.

[1635] Step 2:

[1636] The user enters their current learning results into the terminal. The user then enters their mock and regular exam scores into the input form and presses the submit button. This input data (scores for each subject) is sent to the server. The server stores this data in a database and integrates it with past grades.

[1637] Step 3:

[1638] The server retrieves past exam information for the target educational institution from the database. It searches the database for past exam questions and answers corresponding to the input target educational institution and retrieves the results. This exam information is used in the next processing step within the server.

[1639] Step 4:

[1640] The server compares the user's learning outcomes with the acquired information on past exam questions to identify weak areas. Specifically, the scores for each subject are compared with the percentage of correct answers to past exam questions, and areas with low scores (e.g., differential and integral calculus in mathematics) are identified as weak areas. This comparison result (weak areas) is used in the next step.

[1641] Step 5:

[1642] The server generates a customized study plan based on the user's weak areas. It selects exercises and explanations that correspond to the identified weak areas and combines them to create a study plan. The study plan is individually customized based on the user's learning progress.

[1643] Step 6:

[1644] The device uses a camera and microphone to capture the user's facial expressions and voice, which are then analyzed by the emotion engine. The emotion engine (a model built using Keras) recognizes the user's emotional state in real time, and the recognition results (e.g., stress, fatigue, etc.) are sent to the server.

[1645] Step 7:

[1646] The server adjusts the difficulty of the study plan based on the recognition results of the emotion engine. Specifically, if the user is feeling stressed, it selects easier questions and adds positive feedback. The adjusted study plan is then sent to the device.

[1647] Step 8:

[1648] The device receives the learning plan from the server and displays it to the user. The user can continue studying according to the displayed learning plan. As the learning progresses, the device continuously monitors the user's emotional state and adjusts the learning plan in real time.

[1649] 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.

[1650] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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.

[1651] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1652] 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.

[1653] FIG. 9 is a diagram illustrating 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 actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect 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.

[1654] 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.

[1655] 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).

[1656] 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 indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, 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 indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, 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.

[1657] 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."

[1658] 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.

[1659] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1660] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1661] 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.

[1662] 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.

[1663] 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.

[1664] The hardware resource for executing a specific process can be any of the following processors: An example of a processor 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. Another example of a processor is 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.

[1665] The hardware resource that executes the specific processing 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 processing may be a single processor.

[1666] 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.

[1667] 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.

[1668] 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.

[1669] 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.

[1670] The following is further disclosed regarding the above embodiment.

[1671] (Claim 1)

[1672] a means for inputting information about the target educational institution;

[1673] a means for inputting the user's learning outcomes;

[1674] A means for acquiring information on past exams from the educational institution;

[1675] A means for comparing the learning results with the past exam information and identifying weak areas;

[1676] means for generating a customized learning plan based on said weakness areas;

[1677] means for providing said lesson plan;

[1678] A system including:

[1679] (Claim 2)

[1680] 2. The system according to claim 1, further comprising means for storing the information on past questions in a database.

[1681] (Claim 3)

[1682] 2. The system of claim 1, wherein the customized study plan includes exercises and explanations that address the weakness areas.

[1683] "Example 1"

[1684] (Claim 1)

[1685] A means for a user to input information about a target educational institution using a communication terminal;

[1686] A means for inputting the user's learning results through a communication terminal;

[1687] means for acquiring information on past exam questions from the educational institution from a database;

[1688] a means for comparing the learning results with the past question information on a server and identifying weak areas of the user;

[1689] means for generating a customized learning plan based on the identified weakness areas using the generative AI model;

[1690] means for providing the learning plan to a communication terminal;

[1691] A learning support system including:

[1692] (Claim 2)

[1693] 2. The learning support system according to claim 1, further comprising means for storing the information on past questions in a database.

[1694] (Claim 3)

[1695] 2. The learning support system according to claim 1, wherein the customized learning plan includes exercises corresponding to the weak areas and explanations thereof.

[1696] "Application Example 1"

[1697] (Claim 1)

[1698] a means for inputting information about the target educational institution;

[1699] a means for inputting the user's learning outcomes;

[1700] A means for acquiring information on past exams from the educational institution;

[1701] A means for comparing the learning results with the past exam information and identifying weak areas;

[1702] means for generating a customized learning plan based on said weakness areas;

[1703] means for providing said lesson plan;

[1704] means for sending notifications to a user terminal based on the learning plan;

[1705] A system including:

[1706] (Claim 2)

[1707] 2. The system according to claim 1, further comprising means for storing the information on past questions in a database.

[1708] (Claim 3)

[1709] 2. The system of claim 1, wherein the customized study plan includes exercises and explanations that address the weakness areas.

[1710] "Example 2: Combining Emotion Engines"

[1711] (Claim 1)

[1712] a means for inputting information about the target educational institution;

[1713] a means for inputting the user's learning outcomes;

[1714] A means for acquiring information on past exams from the educational institution;

[1715] A means for comparing the learning results with the past exam information and identifying weak areas;

[1716] means for generating a customized learning plan based on said weakness areas;

[1717] A means to tailor the content and feedback of the learning plan using an emotion engine that recognizes the user's emotions;

[1718] means for providing said lesson plan;

[1719] A system including:

[1720] (Claim 2)

[1721] 2. The system according to claim 1, further comprising means for storing the information on past questions in a database.

[1722] (Claim 3)

[1723] 2. The system of claim 1, wherein the customized study plan includes practice questions and explanations that address the weak areas, and further includes adjusting the difficulty of the questions according to the emotional state of the emotional engine.

[1724] "Application example 2 when combining emotion engines"

[1725] (Claim 1)

[1726] a means for inputting information about the target educational institution;

[1727] a means for inputting the user's learning outcomes;

[1728] A means for acquiring information on past exams from the educational institution;

[1729] A means for comparing the learning results with the past exam information and identifying weak areas;

[1730] means for generating a customized learning plan based on said weakness areas;

[1731] means for including in said customized study plan exercises and explanations corresponding to said weak areas;

[1732] a means for adjusting the content of a learning plan based on an emotional engine that recognizes the emotional state of a user;

[1733] means for providing said lesson plan;

[1734] A system including:

[1735] (Claim 2)

[1736] 2. The system according to claim 1, further comprising means for storing the information on past questions in a database.

[1737] (Claim 3)

[1738] 10. The system of claim 1, further comprising a feedback means for monitoring a user's emotional state in real time and dynamically adjusting the difficulty level of said learning plan. [Explanation of symbols]

[1739] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for inputting information about the target educational institution; a means for inputting the user's learning outcomes; A means for acquiring information on past exams from the educational institution; A means for comparing the learning results with the past exam information and identifying weak areas; means for generating a customized learning plan based on said weakness areas; means for providing said lesson plan; A system including:

2. 2. The system according to claim 1, further comprising means for storing the information on past questions in a database.

3. 2. The system of claim 1, wherein the customized study plan includes exercises and explanations that address the weakness areas.

Images