System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving and storing trial result data; means for analyzing the trial result data and identifying student specialty areas; and means for suggesting an optimal school of choice and faculty based on the specialty areas.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] Currently, many students primarily base their choice of school on deviation scores. However, deviation scores alone do not adequately reflect each student's strengths and areas of expertise, making it difficult to find the school or faculty that best suits them. Furthermore, even if students consult with school teachers or cram school instructors, they do not necessarily have a full understanding of the question trends and characteristics of each school. As a result, there are many cases where students are unable to receive satisfactory recommendations. The present invention aims to solve these problems and enable students to select a school of their choice that utilizes their strengths. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means. First, a means for receiving and saving mock test result data is provided. Next, a means for analyzing the mock test result data and identifying the student's areas of expertise is provided. Furthermore, a means for suggesting the most suitable school and department of choice based on the student's areas of expertise is provided. The accuracy of this suggestion can be improved by reflecting the question trends of the school or department based on past question analysis data. Furthermore, it is possible to suggest schools and departments of choice that take into account the exam schedule. In this way, students can select schools of choice that have a realistic chance of success while making the most of their strengths.

[0006] "Mock test result data" refers to information on the scores and grades in each subject of candidates who took the mock test.

[0007] "Means for saving" refers to the function of storing received data in a storage device such as a database.

[0008] "Means for analysis" refers to the function of identifying students' areas of expertise and strengths based on the received mock test result data.

[0009] "Strong areas" refer to subjects or areas in which a student achieved particularly high scores on mock exams.

[0010] "Preferred school" refers to the school that a student wishes to attend.

[0011] A "department" refers to a unit at a university or vocational school that offers a specific field of study or educational course.

[0012] "Means of suggestion" refers to the function of selecting and presenting the most suitable school and department for each student based on the analysis results.

[0013] "Past question analysis data" refers to data that shows the question trends and characteristics of questions in past exams at each school or faculty.

[0014] "Examination dates" refers to the dates and schedules of entrance examinations conducted by the school or faculty of choice. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This invention relates to a system that analyzes mock exam responses, understands students' areas of expertise and strengths, and then suggests the most suitable schools and departments for them to apply to. This system is primarily composed of a user terminal, a server, and a generative AI model.

[0037] System Overview

[0038] User terminal

[0039] The user terminal provides an interface for students to input their mock exam results and information about their desired faculty and field. The user enters this information into a form and sends it to the server.

[0040] server

[0041] The server receives and stores mock test results and desired information sent from the user's device. It then passes the stored data to a generative AI model, which analyzes the model's areas of expertise. It also has the function of suggesting the most suitable schools and departments based on the analysis results.

[0042] Generative AI Models

[0043] The generative AI model analyzes data provided by the server to identify students' strengths and areas of expertise, and then runs an algorithm to suggest schools and departments with high success rates based on past exam question analysis data.

[0044] Program processing

[0045] 1. User enters mock test results

[0046] The user enters the subject scores for the mock exam, the desired faculty, and the field of study into the input form on the terminal. After completing the input, the user presses a button to send the data to the server.

[0047] 2. The server receives and stores the data

[0048] The server receives the data submitted by the user, validates it to ensure it is in the correct format and has the correct value range, and then stores it in the database.

[0049] 3. Analysis using generative AI models

[0050] The server sends the stored data to the generative AI model, which analyzes the data to identify the student's areas of expertise and strengths, and returns the analysis results to the server.

[0051] 4. The server generates a list of schools of interest

[0052] The server receives the analysis results from the generative AI model and uses them to generate optimal recommendations for schools and departments, taking into account past question analysis data and exam dates. The recommendations are then sent to the user's device.

[0053] 5. The user checks the proposed results

[0054] The user's device receives the proposed results from the server and displays them on the screen. The user can then check the details of the proposed schools and departments and use them as a reference for selecting the school of their choice that best suits them.

[0055] Specific examples

[0056] Example 1: When a user enters a practice test result

[0057] The user enters that their mock test scores are "Mathematics: 85 points, English: 90 points, Japanese: 75 points," that their desired faculty is "Information Engineering," and that their desired field is "AI."

[0058] Example 2: When a server uses a generative AI model to analyze data

[0059] The server sends the received mock test results and desired faculty and field information to the generating AI model, and receives the analysis result that "Mathematics" and "English" are strengths.

[0060] Example 3: When the server suggests a preferred school

[0061] Based on the analysis results and exam information, the server will suggest several universities with "information engineering" departments with high acceptance rates. For example, specific preferred schools such as "Information Engineering Department at University A" or "AI major at University B" will be presented.

[0062] In this way, the present invention is a system that can suggest specific and realistic schools of choice that reflect a student's strengths, allowing students to choose their schools with confidence and increasing their chances of being accepted.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] The user accesses the input form on the device. The user enters the scores for each subject in the mock exam, as well as the desired faculty and field. Once the input is complete, the user clicks the send button to send the data to the server.

[0066] Specific behavior:

[0067] A user enters the following scores into a web form: Math: 85 points, English: 90 points, Japanese: 75 points.

[0068] The user selects "Information Engineering" as the desired faculty and "AI" as the desired field.

[0069] The user clicks the submit button.

[0070] Step 2:

[0071] The server receives the mock test result data sent by the user. The server validates the received data to ensure that the format and value range are correct.

[0072] Specific behavior:

[0073] The server receives the data in JSON format.

[0074] Validate each field of data (e.g., "Math: 85 points").

[0075] If invalid data is included, an error message is generated and returned to the user.

[0076] Step 3:

[0077] The server stores the validated data in a database, which is used later for analysis.

[0078] Specific behavior:

[0079] The server converts the data into the appropriate format and stores it in the database.

[0080] Check that the data has been saved.

[0081] A save completion response is sent to the user's terminal.

[0082] Step 4:

[0083] The server sends the saved data to the generative AI model, which analyzes the mock test results to identify the student's strengths and areas of expertise, and returns the analysis results to the server.

[0084] Specific behavior:

[0085] The server sends the mock test results and desired information to the AI ​​model.

[0086] The generative AI model analyzed the scores for each subject and identified that "Mathematics" and "English" were the student's areas of strength.

[0087] The AI ​​model sends the analysis results back to the server.

[0088] Step 5:

[0089] The server receives the analysis results from the generative AI model and generates optimal recommendations for schools and departments, taking into account past exam question analysis data and exam dates.

[0090] Specific behavior:

[0091] The server searches the database of the desired school based on the analysis results.

[0092] We have compiled a list of schools and faculties with high pass rates based on question trends and examination information.

[0093] The proposals selected were "The Department of Information Engineering at University A" and "The AI ​​major at University B."

[0094] Step 6:

[0095] The server sends the proposal results to the user terminal, which receives the proposal results and displays them on the screen.

[0096] Specific behavior:

[0097] The server generates the proposal results in JSON format.

[0098] The proposal results are sent to the user's device.

[0099] The user's device displays the received information. For example, desired schools such as "Information Engineering Department at University A" or "AI major at University B" are displayed on the screen.

[0100] Step 7:

[0101] Users can check the proposed results and use them as reference material to select the school that best suits them.

[0102] Specific behavior:

[0103] The user can check the details of the proposed results displayed on the screen.

[0104] If necessary, click on each school or faculty for more information.

[0105] Select your preferred school based on the proposed results.

[0106] Example 1

[0107] 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."

[0108] Conventional mock exam systems simply saved test results, but did not have the functionality to identify students' areas of expertise or suggest the most suitable schools or departments based on those areas. This made it difficult for students to understand their strengths and select schools that would utilize those strengths. Furthermore, specific suggestions that took into account past exam trends and exam dates were also insufficient.

[0109] 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.

[0110] In this invention, the server includes a means for inputting and transmitting mock test result data and desired field data from a terminal, a means for receiving and storing the mock test result data and desired field data, a means for identifying a student's areas of expertise using a generative AI model that analyzes the mock test result data and desired field data, and a means for proposing the most suitable school and department of interest based on the student's areas of expertise and taking into account past question analysis data and exam dates. This allows students to select the most suitable school of their choice by utilizing their own strengths.

[0111] A "terminal" is a device through which a user inputs mock test result data and desired domain data and transmits them to a server.

[0112] "Mock exam result data" refers to the subject-specific scores and other evaluation information obtained by students in the mock exam.

[0113] "Desired field data" refers to information about the faculty the student is applying to and the field that will be analyzed.

[0114] "Means for transmission" refers to the interface or protocol for transmitting data from the terminal to the server.

[0115] "Means for receiving and storing" refers to the function by which the server receives data sent from the terminal and stores it in a storage device such as a database.

[0116] A "generative AI model" refers to an artificial intelligence algorithm that analyzes incoming data and identifies students' areas of expertise and strengths.

[0117] The "means of identifying areas of expertise" is a function that uses a generative AI model to analyze students' test result data and extract the subjects and areas in which the student excels.

[0118] "Past question analysis data" refers to data that includes analysis results such as question trends and question difficulty of exams that have been conducted in the past.

[0119] "Exam Schedule" refers to the dates or schedule of exams that a student plans to take.

[0120] "Means to suggest schools and departments of choice" is a function that suggests the most suitable schools and departments to students by taking into consideration the analysis results of the generative AI model, past question analysis data, and exam dates.

[0121] "System" refers to the overall system consisting of the terminal, server, and generative AI model.

[0122] This invention relates to a system that analyzes mock exam responses, understands a student's areas of expertise and strengths, and then suggests the most suitable schools and departments for them to apply to. This system is primarily composed of a user terminal, a server, and a generative AI model.

[0123] The user terminal provides an interface for entering mock test results and information about the desired faculty and field. When the user enters this information into a form and presses the submit button, the data is sent to the server. The terminal uses a standard web browser or dedicated application software.

[0124] The server has the function of receiving and saving the mock test result data and desired domain data sent from the user terminal. The server uses a database to manage and save this data, and also performs validation. Validation is the process of checking whether the format and value range of the received data are correct. Data is saved in the database only if validation is successful.

[0125] The server then sends the stored data to a generative AI model, which analyzes the data and identifies the student's areas of expertise and strengths. The generative AI model uses machine learning algorithms to analyze patterns and characteristics of test results. For example, if a student scores high in math, it determines that the student is good at math. The results of this analysis are then sent back to the server.

[0126] The server generates optimal recommendations for schools and departments based on the analysis results from the generative AI model. The server also takes into account past exam question analysis data and exam dates. For example, a student with high scores in math and English will be suggested departments and universities that emphasize these subjects. These recommendations are then sent to the user's device.

[0127] The user terminal receives the recommendation results from the server and displays them on the screen. The user can check this information and use it as a reference for selecting the school of their choice that is most suitable for them.

[0128] Specific examples

[0129] For example, consider the case where a user enters a practice test score as follows:

[0130] Example input:

[0131] Mathematics: 85 points

[0132] English: 90 points

[0133] Japanese: 75 points

[0134] Preferred Faculty: Information Engineering

[0135] Desired field: AI

[0136] When the user enters this information and presses the send button, the data is sent to the server.

[0137] The server then sends the received data to the generative AI model, which returns the result that "Mathematics" and "English" are the user's strengths. Based on this result, the server suggests several schools with "Information Engineering" departments that have high acceptance rates. Specifically, the user is presented with specific schools of choice, such as "Information Engineering Department at University A" or "AI major at University B."

[0138] In this way, users can select the school of their choice that best reflects their strengths.

[0139] Example prompt sentence:

[0140] "My mock test results are 'Math: 85 points, English: 90 points, Japanese: 75 points'. I would like to study 'Information Engineering' and my preferred field is 'AI'. Based on this information, please suggest my areas of expertise and the best schools for me to apply to."

[0141] This allows students to choose their preferred school with confidence and increases their chances of being accepted.

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

[0143] Step 1:

[0144] The user uses the terminal to input the result data of the mock test and the desired domain data.

[0145] Input: The user enters "Mathematics: 85 points, English: 90 points, Japanese: 75 points", desired faculty "Information Engineering", and desired field "AI".

[0146] Action: The user enters this data into the input form and presses the "Submit" button.

[0147] Output: Data entered from the terminal is sent to the server.

[0148] Step 2:

[0149] The server receives the data sent from the terminal and validates the data.

[0150] Input: Practice test results and desired domain data sent from the terminal.

[0151] Behavior: The server validates the data received, ensuring it is in the correct format and range of values, e.g., checking that the score is between 0 and 100.

[0152] Output: If validation is successful, the data is saved to the database. If validation fails, an error message is generated.

[0153] Step 3:

[0154] The server sends the stored data to the generative AI model and begins analysis.

[0155] Input: Practice test results stored in the database and desired domain data.

[0156] How it works: The server sends the stored data to the generative AI model, which analyzes it and identifies the student's strengths and areas of expertise. Based on a specific algorithm, it may determine that math and English are strong subjects, for example.

[0157] Output: The analysis result is returned to the server, for example, "Strengths: Math and English."

[0158] Step 4:

[0159] Based on the analysis results, the server generates suggestions for the most suitable schools and departments to apply to.

[0160] Input: Analysis results from the generative AI model (areas of expertise), past question analysis data, and exam dates.

[0161] How it works: The server selects the department or university with the highest pass rate, taking into account past exam question analysis data and exam dates. For example, it identifies specific desired schools, such as "University A's Department of Information Engineering" or "University B's AI major."

[0162] Output: The best possible school and department recommendations are generated and sent to the user's device.

[0163] Step 5:

[0164] The user terminal displays the proposal results received from the server so that the user can check them.

[0165] Input: Suggested school and department choices sent from the server.

[0166] Operation: The user's device displays the received recommendations on the screen. The user can then check the details of each school and use them as a reference to select the school that best suits them.

[0167] Output: Display of the proposed results, allowing the user to select specific schools of choice.

[0168] (Application example 1)

[0169] 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."

[0170] Currently, support systems exist for selecting schools and majors based on mock exam results, but they are often limited to physical interfaces and lack flexibility. Users must also expend considerable effort to obtain detailed information about the schools and majors they are considering. Furthermore, they lack visual support for determining how well the proposed information suits them. This can make it difficult for students to obtain sufficient information to make optimal choices, resulting in reduced accuracy in career choices.

[0171] 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.

[0172] In this invention, the server includes means for receiving and storing mock test result data, means for analyzing the mock test result data and identifying the student's areas of expertise, means for suggesting the most suitable educational destination and specialty based on the student's areas of expertise, means for inputting the mock test results into an interface of a smartphone or tablet, and means for a user to check detailed information about the educational destination and specialty using a virtual reality headset. This allows students to easily input their mock test results, receive specific and optimal career suggestions based on analysis by the generative AI model, and check detailed information through virtual reality.

[0173] A "mock test" is a test that students take to measure their academic ability level before taking the exam.

[0174] "Result data" refers to information regarding the scores and grades for each subject obtained after taking the mock test.

[0175] A "strength area" is an area in which a student excels significantly over other areas, based on the results of mock exams.

[0176] "School destination" refers to the educational institution, such as a university or vocational school, that a student aims to attend after graduating from high school.

[0177] A "specialty" is a specific academic field that a student wishes to study at their future university.

[0178] "Proposal methods" are methods or systems that show students the most suitable schools and fields of specialization based on the analysis results.

[0179] An "interface" is a means such as an operation screen or input device that allows a user to interact with a system.

[0180] A "smartphone" is a mobile phone with advanced computing and communication capabilities.

[0181] A "tablet" is a small, portable computer that uses a touchscreen as its primary input means.

[0182] A "virtual reality headset" is a device that allows a user to have an immersive virtual reality experience.

[0183] A "generative AI model" is an artificial intelligence modeling technique designed to perform specific tasks based on training data.

[0184] This invention relates to a system that analyzes mock exam results, understands students' strengths and areas of expertise, and then suggests the most suitable educational destination and field of specialization. This system is primarily composed of a user terminal, a server, and a generative AI model.

[0185] System Program

[0186] The system has the following features:

[0187] 1. Enter your mock test results:

[0188] The user device provides an interface for students to input mock exam results and information about their desired specialization. Students use their smartphones or tablets to input their mock exam scores for each subject, as well as their desired school and specialization.

[0189] 2. Receiving and storing data:

[0190] The server receives and stores the mock test result data and desired information sent from the user terminal.

[0191] 3. Analysis process:

[0192] The server sends the stored data to the generative AI model, which analyzes the received data and identifies the student's areas of expertise and strengths. Specifically, it analyzes the data based on past problem analysis data to identify areas of expertise.

[0193] 4. Proposal of further education and specialization:

[0194] The server receives the analysis results from the generative AI model and uses them to suggest optimal educational destinations and specializations, and can provide detailed information to users through a virtual reality headset.

[0195] Specific usage

[0196] Example 1: User enters practice test results

[0197] A user inputs the results of a mock test using a smartphone. For example, suppose the results are "Mathematics: 85 points, English: 90 points, Japanese: 75 points," and the desired field of specialization is "Information Engineering." This information is sent from the user's device to the server.

[0198] Example 2: Data processing and analysis

[0199] The server sends the received mock test results and desired field of study information to the generative AI model, which analyzes the data and identifies that the student's strengths are "Mathematics" and "English."

[0200] Example 3: Suggesting further education

[0201] Based on the analysis results, the server will suggest the most suitable university and specialty. For example, it will suggest "University A, Department of Information Engineering" and "University B, Department of AI" as universities where users can study "Information Engineering." Using a virtual reality headset, users can visually check detailed information about these universities and majors.

[0202] Example prompt sentence:

[0203] Users input their mock test results, and the generative AI model analyzed them to identify their strengths in mathematics and English. Based on this, it suggested a path to further study in information engineering.

[0204] In this way, the present invention is a system that can suggest specific and realistic educational destinations that reflect a student's strengths, allowing students to choose their educational destinations with confidence and increasing the chances of being accepted.

[0205] As specific hardware and software examples, smartphones and tablets are used as user devices, and servers equipped with generative AI models are used for analysis processing. Virtual reality headsets are useful for providing detailed visual information.

[0206] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0207] Step 1:

[0208] Users input their mock test results using a smartphone or tablet. Specifically, they use a dedicated application to enter their subject scores, such as "Mathematics: 85 points, English: 90 points, Japanese: 75 points," as well as their desired field of specialization, such as "Information Engineering." This input information is sent to the server in JSON format or similar.

[0209] Step 2:

[0210] The server receives the data sent from the user terminal and saves it in the database. Here, the data is first validated. To ensure that the data format is consistent and that the value is within a range, for example, it checks whether "Math: 85 points" is within the range of 0 to 100. If the data is valid, it is saved in the database.

[0211] Step 3:

[0212] The server sends the stored data to a generative AI model. This AI model has been trained in advance on a large amount of past question analysis data and has an analysis algorithm for specific input data. Specifically, using mock test results and desired specialization data, students input their scores for each subject and their desired specialization, and the data is processed and calculated based on that to identify the student's areas of expertise and strengths.

[0213] Step 4:

[0214] The generative AI model returns the analysis results to the server. Specifically, the analysis results show that "math" and "English" are strong subjects based on the input mock test results, and the results are sent back to the server. The server receives this and uses the results to create a list of optimal schools and specializations.

[0215] Step 5:

[0216] The server generates suggestions for schools and specializations, taking into account past exam analysis data, entrance exam dates, and the exam trends of the schools. For example, for a student who excels in math and English and is interested in information engineering, specific schools such as "Information Engineering Department at University A" or "AI Major at University B" will be listed.

[0217] Step 6:

[0218] Users can use a virtual reality headset to view detailed information about proposed schools and majors. This allows them to visually experience the campus atmosphere and curriculum content, providing a deeper understanding. Viewing detailed information about schools using a virtual reality headset can help students decide whether a school is right for them.

[0219] The specific actions taken at each step are as follows:

[0220] Step 1: The user enters the results of the mock test into the application's input form and presses the submit button. The input is sent from the smartphone or tablet to the server.

[0221] Step 2: The server checks the format and range of the data received, and if there are no problems, stores it in the database.

[0222] Step 3: The server sends the stored data to the generative AI model, which then analyzes the data.

[0223] Step 4: The generative AI model sends the analysis results back to the server, which receives the results and generates recommendations for further education and specialization.

[0224] Step 5: The server creates a list of optimal educational destinations and fields of specialization based on the analysis results and sends it to the user.

[0225] Step 6: The user uses a virtual reality headset to visually review the details of the proposed education and specialization.

[0226] 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.

[0227] This invention combines a system that analyzes mock test results, understands a student's areas of expertise and strengths, and then suggests the most suitable schools and departments to apply to with an emotion engine that recognizes the user's emotions. This system is primarily composed of a user terminal, a server, a generative AI model, and an emotion engine.

[0228] System Overview

[0229] User terminal

[0230] The user terminal provides an interface for students to input their mock exam results and information about their desired faculty and field. The user enters this information into a form and sends it to the server. Data is also collected from the user's facial expressions and voice when entering information, allowing the emotion engine to analyze it.

[0231] server

[0232] The server receives and stores mock test results, desired information, and emotional data sent from the user's device. It then passes the stored data to a generative AI model, which analyzes the user's areas of expertise and emotions. It also has the function of suggesting the most suitable schools and departments based on the analysis results.

[0233] Generative AI Models

[0234] The generative AI model analyzes data provided by the server to identify students' strengths and areas of expertise, and then runs an algorithm to suggest schools and departments with high success rates based on past exam question analysis data.

[0235] Emotion Engine

[0236] The emotion engine analyzes the user's facial expressions and voice when inputting information to identify the user's emotional state. The acquired emotional data is reflected in the content of suggestions, providing advice and suggestions that correspond to the student's emotional state.

[0237] Program processing

[0238] 1. User enters mock test results

[0239] The user enters their mock exam subject scores and desired faculty and field into the input form on the device. Once the user has completed the input, they press a button to send the data to the server. At the same time, the emotion engine analyzes the user's facial expressions and voice to collect emotional data.

[0240] 2. The server receives and stores the data

[0241] The server receives the mock test result data, preference information, and emotion data sent by the user. The server validates the received data to ensure that the format and value range are correct. Then, it stores the data in the database.

[0242] 3. Analysis using generative AI models

[0243] The server sends the stored data to the generative AI model, which analyzes the data, identifies the student's areas of expertise and strengths, and returns the analysis results to the server, taking into account the emotional data obtained.

[0244] 4. Analysis by Emotion Engine

[0245] The server sends the emotion data to the emotion engine, which analyzes the user's emotional state and determines whether the state is negative or positive.

[0246] 5. The server generates a list of schools of interest

[0247] The server receives the analysis results of the generative AI model and the emotion data from the emotion engine, and generates optimal recommendations for schools and departments. The recommendations also take into account past exam question analysis data and exam dates. If the emotional state is negative, the server includes advice on how to reduce stress, and if the emotional state is positive, the server includes recommendations for challenging schools.

[0248] 6. The user checks the proposed results

[0249] The server sends the proposed results to the user's device. The user's device receives the proposed results and displays them on the screen. The user can check the detailed information of the proposed schools and departments and use it as a reference for selecting the school of their choice that is most suitable for them.

[0250] Specific examples

[0251] Example 1: When a user enters a practice test result

[0252] The user inputs their mock test scores of "Mathematics: 85 points, English: 90 points, Japanese: 75 points," their desired faculty of study as "Information Engineering," and their desired field as "AI." The emotion engine analyzes the user's facial expressions and voice and determines that the user is relaxed.

[0253] Example 2: Server passes data to generative AI model and emotion engine

[0254] The server sends the received mock test results, desired information, and emotional data to the generative AI model and emotion engine, and receives the analysis results from each. If the generative AI model identifies "math" and "English" as areas of expertise and the emotion engine detects negative emotions, it will include advice on stress reduction in the proposal.

[0255] Example 3: When the server suggests a preferred school

[0256] The server searches a database of schools of choice based on the analysis results and emotional data, and lists schools and departments with high acceptance rates, taking into account question trends and exam information. If negative emotions are detected, the server suggests more realistic schools, and if positive emotions are detected, it suggests more challenging schools.

[0257] In this way, the present invention is a system that can suggest specific and realistic schools of choice that reflect a student's strengths and take into consideration their emotional state, allowing students to choose their schools with confidence and increasing their chances of being accepted.

[0258] The processing flow will be explained below.

[0259] Step 1:

[0260] The user accesses the input form on the device. The user enters information such as the scores for each subject in the mock exam, the desired faculty, and the field of study. At the same time, the device collects the user's facial expressions and voice to pass to the emotion engine. Once the input is complete, the user clicks the send button to send the data to the server.

[0261] Specific behavior:

[0262] A user enters the following scores into a web form: Math: 85 points, English: 90 points, Japanese: 75 points.

[0263] The user selects "Information Engineering" as the desired faculty and "AI" as the desired field.

[0264] The user's facial expressions and voice are recorded using a camera and microphone, and the emotion engine is prepared to analyze them.

[0265] The user clicks the submit button.

[0266] Step 2:

[0267] The server receives the mock test result data, desired information, and emotion data sent by the user. The server validates the received data to ensure that the format and value range are correct.

[0268] Specific behavior:

[0269] The server receives the data in JSON format.

[0270] Validate each field of data (e.g., "Math: 85 points").

[0271] If invalid data is included, an error message is generated and returned to the user.

[0272] Step 3:

[0273] The server stores the validated data in a database, which is used later for analysis.

[0274] Specific behavior:

[0275] The server converts the data into the appropriate format and stores it in the database.

[0276] Check that the data has been saved.

[0277] A save completion response is sent to the user's terminal.

[0278] Step 4:

[0279] The server sends the saved data to the generative AI model, which analyzes the mock test results to identify the student's strengths and areas of expertise, and returns the analysis results to the server.

[0280] Specific behavior:

[0281] The server retrieves the data from the database and sends it to the generative AI model.

[0282] The generative AI model analyzes the scores for each subject and identifies "Mathematics" and "English" as areas of strength.

[0283] The AI ​​model sends the analysis results back to the server.

[0284] Step 5:

[0285] The server sends the emotion data to the emotion engine, which analyzes the user's facial expressions and voice to identify the user's emotional state and returns the analysis results to the server.

[0286] Specific behavior:

[0287] The server sends the emotion data to the emotion engine.

[0288] The emotion engine analyzes facial and voice data to identify the user's emotional state (e.g., negative, positive).

[0289] The emotion engine sends the analysis results back to the server.

[0290] Step 6:

[0291] The server receives the analysis results of the generative AI model and the emotion data from the emotion engine, and generates optimal recommendations for schools and departments to apply to. These recommendations also take into account past exam question analysis data and exam dates.

[0292] Specific behavior:

[0293] The server integrates and analyzes data from the generative AI model and the emotion engine.

[0294] If the emotional state is negative, include advice on reducing stress.

[0295] If they are positive, we will make suggestions for challenging schools to apply to.

[0296] Generate a list of suggestions including "Information Engineering Department at University A" and "AI major at University B."

[0297] Step 7:

[0298] The server sends the proposal results to the user terminal, which receives the proposal results and displays them on the screen.

[0299] Specific behavior:

[0300] The server generates the proposal results in JSON format.

[0301] The proposal results are transmitted to the user terminal.

[0302] The content received by the user's device is displayed. For example, detailed information about "University A's Department of Information Engineering" and "University B's AI major" is displayed on the screen.

[0303] Step 8:

[0304] Users can check the proposed results and use them as reference material to select the school that best suits them.

[0305] Specific behavior:

[0306] The user checks the proposed results displayed on the screen in detail.

[0307] If necessary, click on each school or faculty to view detailed information.

[0308] Select your preferred school based on the suggested results.

[0309] Example 2

[0310] 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."

[0311] Traditional career suggestion systems based on mock exam results focus on analyzing students' areas of expertise, but do not take into account the student's emotional state. As a result, they are unable to provide appropriate advice when students feel stressed or anxious, which can lead to ineffective career choices. Furthermore, these systems tend to offer uniform suggestions, and flexible support tailored to each student's emotional state and aspirations is needed.

[0312] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0313] In this invention, the server includes means for receiving and storing mock test result data, means for analyzing the mock test result data and identifying the student's areas of expertise, means for suggesting the most suitable school and department of choice based on the student's areas of expertise, and means for analyzing the user's emotions and generating suggestions according to the user's emotional state. This makes it possible to suggest a career path that takes into account not only the student's areas of expertise but also their emotional state.

[0314] "Mock test result data" refers to data that includes information related to the scores for individual subjects and total scores of mock tests taken by students, or grades.

[0315] "Means for receiving and storing" refers to a device or function that receives data transmitted from a user terminal and stores it in a database or other storage device.

[0316] "Means for analyzing and identifying" refers to devices or algorithms that process and analyze given data to derive specific information or results.

[0317] "Means for suggesting preferred schools and departments" refers to devices or functions that suggest the most suitable school to attend (preferred school) and field of study (department) to students based on the analysis results obtained.

[0318] "Means for analyzing emotions" refers to devices or algorithms that analyze a user's facial expressions and voice data to determine the user's emotional state.

[0319] The term "means for generating suggestions according to emotional state" refers to a device or function that takes into account the emotional state of the user and generates advice or suggestions appropriate to that state.

[0320] "Past question analysis data" refers to data that includes information based on the content and trends of exam questions that have been asked in the past, as well as the results of question analysis.

[0321] "Means for considering exam dates" refers to devices or functions that suggest career paths based on students' desired exam schedules and actual exam dates.

[0322] This invention is a system that analyzes mock test results, understands students' areas of expertise and strengths, and then suggests the most suitable schools and departments for them to apply to. This system consists of a user terminal, a server, a generative AI model, and an emotion engine.

[0323] System configuration

[0324] User terminal

[0325] The user terminal provides an interface for students to input information about their mock exam results, desired faculty, and field. When the user enters this information into a form and sends it to the server, their facial expressions and voice are simultaneously recorded.

[0326] server

[0327] The server receives mock test results, desired information, and emotional data sent from the user's device and stores this data. The server also provides the stored data to a generative AI model, which analyzes areas of expertise and emotions. Based on the analysis results, the server suggests the most suitable schools and departments to apply to.

[0328] Generative AI Models

[0329] The generative AI model is built using Python's TensorFlow library. It analyzes data provided by the server to identify students' areas of expertise and strengths. It then runs an algorithm based on past exam question analysis data to suggest schools and departments with high acceptance rates.

[0330] Emotion Engine

[0331] The emotion engine uses OpenCV and the Google Cloud Speech-to-Text API to analyze the user's facial expressions and voice during input. From this data, the emotion engine identifies the user's emotional state, determining whether it is positive or negative.

[0332] System Operation

[0333] The system operates as follows: the user enters the results of a mock test into an input form on their device and sends it to the server. The emotion engine captures the user's facial expressions and voice and generates emotion data. The server stores the received data, validates it, and then sends it to the generative AI model and emotion engine. The generative AI model identifies the user's areas of expertise, and the emotion engine determines the user's emotional state. The server then generates optimal recommendations for schools and departments based on the results of these analyses.

[0334] Specific examples

[0335] Example 1: When a user enters a practice test result

[0336] The user inputs their mock test scores of "Mathematics: 85 points, English: 90 points, Japanese: 75 points," their desired faculty of study as "Information Engineering," and their desired field as "AI." The emotion engine analyzes the user's facial expressions and voice and determines that the user is relaxed.

[0337] Example 2: Server passes data to generative AI model and emotion engine

[0338] The server sends the received mock test results, preference information, and emotional data to the generative AI model and emotion engine, and receives the analysis results from each. If the generative AI model identifies "math" and "English" as strong subjects and the emotion engine detects positive emotions, it will include suggestions for challenging schools of choice.

[0339] Example 3: When the server suggests a preferred school

[0340] The server searches a database of schools of choice based on the analysis results and emotional data, and takes into account question trends and exam information to create a list of schools and departments with high acceptance rates. If positive emotions are detected, it may suggest challenging schools to choose from.

[0341] Example prompt sentence:

[0342] Mock exam results: Math 85 points, English 90 points, Japanese 75 points

[0343] Preferred Faculty: Information Engineering

[0344] Desired field: AI

[0345] Thus, the mode for carrying out the invention proposes the most suitable school and department of choice for a student, taking into consideration the student's areas of expertise and emotional state, through a series of steps from data entry to analysis and final proposal, allowing the student to choose their preferred school with confidence and increasing their chances of being accepted.

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

[0347] Step 1: User enters practice test results

[0348] The user opens the web application on their device. They enter their mock exam subject scores (Mathematics: 85 points, English: 90 points, Japanese: 75 points), their desired faculty (Information Engineering), and their desired field (AI). After completing the input, they click the send button. The input data is sent from the device to the server. At the same time, the emotion engine captures the user's facial expressions and voice through the camera and microphone and generates emotion data.

[0349] Input: mock test results and desired information entered by the user in the input form, facial expressions and voice data

[0350] Output: Mock test result data, preference information, and emotion data sent to the server

[0351] Step 2: The server receives and stores the data

[0352] The server receives the mock test result data, desired information, and emotion data sent from the user's device. Firewalls and data validation functions are used to check the security and accuracy of the received data. Once validated, the data is stored in a database.

[0353] Input: Received mock test result data, desired information, emotional data

[0354] Output: Mock test results data, preference information, and emotion data stored in the database

[0355] Step 3: Analyze the data with a generative AI model

[0356] The server sends the stored data to the generative AI model, which uses Python's TensorFlow library to analyze the data and identify the student's areas of expertise and strengths. "Mathematics" and "English" are identified as areas of expertise. The analysis results are then sent back to the server.

[0357] Input: Mock test result data, desired information, and emotional data stored in the database

[0358] Output: Information on areas of expertise and strengths after analysis by the generative AI model

[0359] Step 4: Emotional state analysis by the emotion engine

[0360] The server sends the emotion data to the emotion engine, which uses OpenCV and the Google Cloud Speech-to-Text API to analyze the user's facial expressions and voice. A positive emotional state is identified as a result of the analysis and sent back to the server.

[0361] Input: Received emotion data

[0362] Output: Emotional state information after analysis

[0363] Step 5: The server generates school recommendations

[0364] The server receives the analysis results of the AI ​​model and the emotional state of the emotion engine, and generates optimal recommendations for schools and departments. The recommendations also take into account past exam question analysis data and exam schedule information. Challenging schools suited to a positive emotional state can also be included in the recommendations.

[0365] Input: Analyzed areas of expertise and strengths, emotional state information

[0366] Output: Suggested best schools and departments

[0367] Step 6: User confirms the proposed results

[0368] The server sends the proposed results to the user's device. The user's device receives the proposed results and displays them on the screen. The user can check the detailed information of the proposed schools and departments and use it as a reference for selecting the school of their choice that best suits them.

[0369] Input: Suggested best school and department information

[0370] Output: Suggestion results displayed on the user's device

[0371] The above is the specific flow of the system's program processing, and the detailed operations at each step are clarified.

[0372] (Application example 2)

[0373] 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."

[0374] Conventional systems for suggesting preferred schools and departments make suggestions based solely on students' mock exam results. However, this system cannot take into account the student's individual psychological state, such as their emotional state or stress level at the time, which can affect the accuracy of the suggestions and the student's motivation. Therefore, it is necessary for students to study in a relaxed state and receive appropriate advice.

[0375] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0376] In this invention, the server includes means for receiving and saving mock test result data, means for analyzing the mock test result data and identifying the student's areas of expertise, means for proposing the most suitable school and department of choice based on the student's areas of expertise, means for recognizing and saving the user's emotional data, and means for analyzing the emotional data and adjusting the content of the proposal based on the user's emotional state. This makes it possible to propose appropriate and personalized schools and departments of choice that take into account the student's emotional state as well as their academic ability data.

[0377] "Mock exam result data" refers to data relating to the scores and grades obtained by students in each subject in the mock exam.

[0378] A "strength area" is an area of ​​study or subject in which a student shows particular ability or interest.

[0379] "Preferred school" refers to the educational institution that a student wishes to attend.

[0380] A "faculty" is a unit of education and research established for each academic field at a university or higher education institution.

[0381] "Emotion data" is information about emotions acquired from the user's facial expressions, voice, etc.

[0382] "Emotional state" refers to the positive or negative mental state or emotion that a user is currently experiencing.

[0383] A "generative AI model" is an artificial intelligence algorithm that analyzes input data and generates optimal suggestions based on the user's areas of expertise.

[0384] A "prompt sentence" is a specific input sentence that a generative AI model uses to generate suggestions.

[0385] This invention combines a system that analyzes mock test results data, understands a student's areas of expertise and strengths, and then suggests the most suitable school or department to apply to with an emotion engine that recognizes the user's emotions.The system of this invention is mainly composed of a user terminal, a server, a generative AI model, and an emotion engine.

[0386] First, the user device provides an interface for students to input their mock exam results and information about their desired faculty and field. The user enters this information into a form on the device and sends it to the server. Data is also collected from the user's facial expressions and voice when entering information, which the emotion engine analyzes. Furthermore, hardware such as a webcam and microphone is required to acquire emotion data.

[0387] The server then receives and stores the mock test results, desired information, and emotional data sent from the user's device. The server validates the received data to ensure that the format and value range are correct. The server then analyzes this data using a generative AI model. The generative AI model is implemented using a programming language such as Python and includes past question analysis data and algorithms for identifying schools and departments with high pass rates.

[0388] The emotion engine analyzes the user's facial expressions and voice when inputting information to identify the user's emotional state. It uses the EmotionEngine library to determine whether the user is relaxed or stressed. The server combines the emotion data obtained from the emotion engine with the analysis results of the generative AI model to generate optimal recommendations for schools and departments.

[0389] For example, if a user inputs their mock exam scores and indicates that they want to study computer engineering and AI, the emotion engine analyzes their facial expressions and voice and determines that they are relaxed. The server then uses a generative AI model to analyze this data and identify their strengths in math and English. If the user's emotional state is positive, the engine returns results that include suggestions for challenging schools.

[0390] Examples of specific prompts include:

[0391] "User entered mock test results: Math 85, English 90, Japanese 75. Desired department: Computer Engineering. Desired field: AI. Emotional state: Relaxed."

[0392] In this way, the system of the present invention can integrate and analyze a student's academic ability data and emotional data, and can suggest the most suitable schools and departments for each student, allowing students to select their preferred schools with greater confidence.

[0393] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0394] Step 1:

[0395] The user enters the results of the mock exam and the desired faculty and field.

[0396] Input: Mock exam scores by subject, desired faculty information, desired field information

[0397] Output: The entered data is collected from the terminal

[0398] Specific operation: The user enters grade information such as "Math: 85 points, English: 90 points, Japanese: 75 points" and a desired field such as "Information Engineering" or "AI" into the form on the device, and presses the submit button. At this time, the user's facial expressions and voice are collected using the device's webcam and microphone.

[0399] Step 2:

[0400] The emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[0401] Input: User's facial expression data, voice data

[0402] Output: Emotion data (e.g., relaxed, nervous, etc.)

[0403] How it works: Facial and voice data collected on the device is analyzed by the EmotionEngine library to identify the user's emotional state, for example, determining whether the user is relaxed or tense.

[0404] Step 3:

[0405] The server receives and stores the mock test result data, desired information, and emotion data.

[0406] Input: mock test results, desired faculty information, desired field information, emotional data

[0407] Output: User data stored in the database

[0408] Specific operation: Data sent from the user terminal is sent to the server, which validates the data to ensure it is in the correct format and stores it in the database.

[0409] Step 4:

[0410] The server sends the data to the generated AI model, which analyzes the student's areas of expertise and the best schools and departments to apply to.

[0411] Input: Saved user data (mock test results, preferences, emotional data)

[0412] Output: Analysis results from the generative AI model (areas of expertise, preferred schools and departments)

[0413] How it works: The server inputs the saved data into a generative AI model implemented in Python to identify areas of strength in each subject. It also uses past question analysis data to calculate schools and departments with high pass rates.

[0414] Step 5:

[0415] The server adjusts the suggestions based on the emotional data.

[0416] Input: Analysis results of generative AI model, emotion data

[0417] Output: Recommendations for the best schools and departments to apply to based on the emotional state

[0418] How it works: The server reviews the analysis results returned by the generative AI model and adjusts the suggestions based on the data from the emotion engine. For example, if the emotion data is positive, it will suggest more challenging schools, and if it is negative, it will make more realistic suggestions.

[0419] Step 6:

[0420] The server sends the final proposal of preferred schools and departments to the user's device.

[0421] Input: Suggestion data according to emotional state

[0422] Output: User device showing the proposed results

[0423] Specific operation: The server generates a list of the most suitable schools and departments according to the user's emotional state and sends it to the user's device. The user's device then displays this information on the screen so that the user can confirm it.

[0424] This makes it possible to integrate mock test results data with emotional data to suggest the most suitable schools and departments for students to apply to.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] [Second embodiment]

[0429] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0430] 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.

[0431] 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).

[0432] 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.

[0433] 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.

[0434] 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).

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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.

[0440] 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."

[0441] This invention relates to a system that analyzes mock exam responses, understands students' areas of expertise and strengths, and then suggests the most suitable schools and departments for them to apply to. This system is primarily composed of a user terminal, a server, and a generative AI model.

[0442] System Overview

[0443] User terminal

[0444] The user terminal provides an interface for students to input their mock exam results and information about their desired faculty and field. The user enters this information into a form and sends it to the server.

[0445] server

[0446] The server receives and stores mock test results and desired information sent from the user's device. It then passes the stored data to a generative AI model, which analyzes the model's areas of expertise. It also has the function of suggesting the most suitable schools and departments based on the analysis results.

[0447] Generative AI Models

[0448] The generative AI model analyzes data provided by the server to identify students' strengths and areas of expertise, and then runs an algorithm to suggest schools and departments with high success rates based on past exam question analysis data.

[0449] Program processing

[0450] 1. User enters mock test results

[0451] The user enters the subject scores for the mock exam, the desired faculty, and the field of study into the input form on the terminal. After completing the input, the user presses a button to send the data to the server.

[0452] 2. The server receives and stores the data

[0453] The server receives the data submitted by the user, validates it to ensure it is in the correct format and has the correct value range, and then stores it in the database.

[0454] 3. Analysis using generative AI models

[0455] The server sends the stored data to the generative AI model, which analyzes the data to identify the student's areas of expertise and strengths, and returns the analysis results to the server.

[0456] 4. The server generates a list of schools of interest

[0457] The server receives the analysis results from the generative AI model and uses them to generate optimal recommendations for schools and departments, taking into account past question analysis data and exam dates. The recommendations are then sent to the user's device.

[0458] 5. The user checks the proposed results

[0459] The user's device receives the proposed results from the server and displays them on the screen. The user can then check the details of the proposed schools and departments and use them as a reference for selecting the school of their choice that best suits them.

[0460] Specific examples

[0461] Example 1: When a user enters a practice test result

[0462] The user enters that their mock test scores are "Mathematics: 85 points, English: 90 points, Japanese: 75 points," that their desired faculty is "Information Engineering," and that their desired field is "AI."

[0463] Example 2: When a server uses a generative AI model to analyze data

[0464] The server sends the received mock test results and desired faculty and field information to the generating AI model, and receives the analysis result that "Mathematics" and "English" are strengths.

[0465] Example 3: When the server suggests a preferred school

[0466] Based on the analysis results and exam information, the server will suggest several universities with "information engineering" departments with high acceptance rates. For example, specific preferred schools such as "Information Engineering Department at University A" or "AI major at University B" will be presented.

[0467] In this way, the present invention is a system that can suggest specific and realistic schools of choice that reflect a student's strengths, allowing students to choose their schools with confidence and increasing their chances of being accepted.

[0468] The processing flow will be explained below.

[0469] Step 1:

[0470] The user accesses the input form on the device. The user enters the scores for each subject in the mock exam, as well as the desired faculty and field. Once the input is complete, the user clicks the send button to send the data to the server.

[0471] Specific behavior:

[0472] A user enters the following scores into a web form: Math: 85 points, English: 90 points, Japanese: 75 points.

[0473] The user selects "Information Engineering" as the desired faculty and "AI" as the desired field.

[0474] The user clicks the submit button.

[0475] Step 2:

[0476] The server receives the mock test result data sent by the user. The server validates the received data to ensure that the format and value range are correct.

[0477] Specific behavior:

[0478] The server receives the data in JSON format.

[0479] Validate each field of data (e.g., "Math: 85 points").

[0480] If invalid data is included, an error message is generated and returned to the user.

[0481] Step 3:

[0482] The server stores the validated data in a database, which is used later for analysis.

[0483] Specific behavior:

[0484] The server converts the data into the appropriate format and stores it in the database.

[0485] Check that the data has been saved.

[0486] A save completion response is sent to the user's terminal.

[0487] Step 4:

[0488] The server sends the saved data to the generative AI model, which analyzes the mock test results to identify the student's strengths and areas of expertise, and returns the analysis results to the server.

[0489] Specific behavior:

[0490] The server sends the mock test results and desired information to the AI ​​model.

[0491] The generative AI model analyzed the scores for each subject and identified that "Mathematics" and "English" were the student's areas of strength.

[0492] The AI ​​model sends the analysis results back to the server.

[0493] Step 5:

[0494] The server receives the analysis results from the generative AI model and generates optimal recommendations for schools and departments, taking into account past exam question analysis data and exam dates.

[0495] Specific behavior:

[0496] The server searches the database of the desired school based on the analysis results.

[0497] We have compiled a list of schools and faculties with high pass rates based on question trends and examination information.

[0498] The proposals selected were "The Department of Information Engineering at University A" and "The AI ​​major at University B."

[0499] Step 6:

[0500] The server sends the proposal results to the user terminal, which receives the proposal results and displays them on the screen.

[0501] Specific behavior:

[0502] The server generates the proposal results in JSON format.

[0503] The proposal results are sent to the user's device.

[0504] The user's device displays the received information. For example, desired schools such as "Information Engineering Department at University A" or "AI major at University B" are displayed on the screen.

[0505] Step 7:

[0506] Users can check the proposed results and use them as reference material to select the school that best suits them.

[0507] Specific behavior:

[0508] The user can check the details of the proposed results displayed on the screen.

[0509] If necessary, click on each school or faculty for more information.

[0510] Select your preferred school based on the proposed results.

[0511] Example 1

[0512] 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."

[0513] Conventional mock exam systems simply saved test results, but did not have the functionality to identify students' areas of expertise or suggest the most suitable schools or departments based on those areas. This made it difficult for students to understand their strengths and select schools that would utilize those strengths. Furthermore, specific suggestions that took into account past exam trends and exam dates were also insufficient.

[0514] 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.

[0515] In this invention, the server includes a means for inputting and transmitting mock test result data and desired field data from a terminal, a means for receiving and storing the mock test result data and desired field data, a means for identifying a student's areas of expertise using a generative AI model that analyzes the mock test result data and desired field data, and a means for proposing the most suitable school and department of interest based on the student's areas of expertise and taking into account past question analysis data and exam dates. This allows students to select the most suitable school of their choice by utilizing their own strengths.

[0516] A "terminal" is a device through which a user inputs mock test result data and desired domain data and transmits them to a server.

[0517] "Mock exam result data" refers to the subject-specific scores and other evaluation information obtained by students in the mock exam.

[0518] "Desired field data" refers to information about the faculty the student is applying to and the field that will be analyzed.

[0519] "Means for transmission" refers to the interface or protocol for transmitting data from the terminal to the server.

[0520] "Means for receiving and storing" refers to the function by which the server receives data sent from the terminal and stores it in a storage device such as a database.

[0521] A "generative AI model" refers to an artificial intelligence algorithm that analyzes incoming data and identifies students' areas of expertise and strengths.

[0522] The "means of identifying areas of expertise" is a function that uses a generative AI model to analyze students' test result data and extract the subjects and areas in which the student excels.

[0523] "Past question analysis data" refers to data that includes analysis results such as question trends and question difficulty of exams that have been conducted in the past.

[0524] "Exam Schedule" refers to the dates or schedule of exams that a student plans to take.

[0525] "Means to suggest schools and departments of choice" is a function that suggests the most suitable schools and departments to students by taking into consideration the analysis results of the generative AI model, past question analysis data, and exam dates.

[0526] "System" refers to the overall system consisting of the terminal, server, and generative AI model.

[0527] This invention relates to a system that analyzes mock exam responses, understands a student's areas of expertise and strengths, and then suggests the most suitable schools and departments for them to apply to. This system is primarily composed of a user terminal, a server, and a generative AI model.

[0528] The user terminal provides an interface for entering mock test results and information about the desired faculty and field. When the user enters this information into a form and presses the submit button, the data is sent to the server. The terminal uses a standard web browser or dedicated application software.

[0529] The server has the function of receiving and saving the mock test result data and desired domain data sent from the user terminal. The server uses a database to manage and save this data, and also performs validation. Validation is the process of checking whether the format and value range of the received data are correct. Data is saved in the database only if validation is successful.

[0530] The server then sends the stored data to a generative AI model, which analyzes the data and identifies the student's areas of expertise and strengths. The generative AI model uses machine learning algorithms to analyze patterns and characteristics of test results. For example, if a student scores high in math, it determines that the student is good at math. The results of this analysis are then sent back to the server.

[0531] The server generates optimal recommendations for schools and departments based on the analysis results from the generative AI model. The server also takes into account past exam question analysis data and exam dates. For example, a student with high scores in math and English will be suggested departments and universities that emphasize these subjects. These recommendations are then sent to the user's device.

[0532] The user terminal receives the recommendation results from the server and displays them on the screen. The user can check this information and use it as a reference for selecting the school of their choice that is most suitable for them.

[0533] Specific examples

[0534] For example, consider the case where a user enters a practice test score as follows:

[0535] Example input:

[0536] Mathematics: 85 points

[0537] English: 90 points

[0538] Japanese: 75 points

[0539] Preferred Faculty: Information Engineering

[0540] Desired field: AI

[0541] When the user enters this information and presses the send button, the data is sent to the server.

[0542] The server then sends the received data to the generative AI model, which returns the result that "Mathematics" and "English" are the user's strengths. Based on this result, the server suggests several schools with "Information Engineering" departments that have high acceptance rates. Specifically, the user is presented with specific schools of choice, such as "Information Engineering Department at University A" or "AI major at University B."

[0543] In this way, users can select the school of their choice that best reflects their strengths.

[0544] Example prompt sentence:

[0545] "My mock test results are 'Math: 85 points, English: 90 points, Japanese: 75 points'. I would like to study 'Information Engineering' and my preferred field is 'AI'. Based on this information, please suggest my areas of expertise and the best schools for me to apply to."

[0546] This allows students to choose their preferred school with confidence and increases their chances of being accepted.

[0547] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0548] Step 1:

[0549] The user uses the terminal to input the result data of the mock test and the desired domain data.

[0550] Input: The user enters "Mathematics: 85 points, English: 90 points, Japanese: 75 points", desired faculty "Information Engineering", and desired field "AI".

[0551] Action: The user enters this data into the input form and presses the "Submit" button.

[0552] Output: Data entered from the terminal is sent to the server.

[0553] Step 2:

[0554] The server receives the data sent from the terminal and validates the data.

[0555] Input: Practice test results and desired domain data sent from the terminal.

[0556] Behavior: The server validates the data received, ensuring it is in the correct format and range of values, e.g., checking that the score is between 0 and 100.

[0557] Output: If validation is successful, the data is saved to the database. If validation fails, an error message is generated.

[0558] Step 3:

[0559] The server sends the stored data to the generative AI model and begins analysis.

[0560] Input: Practice test results stored in the database and desired domain data.

[0561] How it works: The server sends the stored data to the generative AI model, which analyzes it and identifies the student's strengths and areas of expertise. Based on a specific algorithm, it may determine that math and English are strong subjects, for example.

[0562] Output: The analysis result is returned to the server, for example, "Strengths: Math and English."

[0563] Step 4:

[0564] Based on the analysis results, the server generates suggestions for the most suitable schools and departments to apply to.

[0565] Input: Analysis results from the generative AI model (areas of expertise), past question analysis data, and exam dates.

[0566] How it works: The server selects the department or university with the highest pass rate, taking into account past exam question analysis data and exam dates. For example, it identifies specific desired schools, such as "University A's Department of Information Engineering" or "University B's AI major."

[0567] Output: The best possible school and department recommendations are generated and sent to the user's device.

[0568] Step 5:

[0569] The user terminal displays the proposal results received from the server so that the user can check them.

[0570] Input: Suggested school and department choices sent from the server.

[0571] Operation: The user's device displays the received recommendations on the screen. The user can then check the details of each school and use them as a reference to select the school that best suits them.

[0572] Output: Display of the proposed results, allowing the user to select specific schools of choice.

[0573] (Application example 1)

[0574] 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."

[0575] Currently, support systems exist for selecting schools and majors based on mock exam results, but they are often limited to physical interfaces and lack flexibility. Users must also expend considerable effort to obtain detailed information about the schools and majors they are considering. Furthermore, they lack visual support for determining how well the proposed information suits them. This can make it difficult for students to obtain sufficient information to make optimal choices, resulting in reduced accuracy in career choices.

[0576] 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.

[0577] In this invention, the server includes means for receiving and storing mock test result data, means for analyzing the mock test result data and identifying the student's areas of expertise, means for suggesting the most suitable educational destination and specialty based on the student's areas of expertise, means for inputting the mock test results into an interface of a smartphone or tablet, and means for a user to check detailed information about the educational destination and specialty using a virtual reality headset. This allows students to easily input their mock test results, receive specific and optimal career suggestions based on analysis by the generative AI model, and check detailed information through virtual reality.

[0578] A "mock test" is a test that students take to measure their academic ability level before taking the exam.

[0579] "Result data" refers to information regarding the scores and grades for each subject obtained after taking the mock test.

[0580] A "strength area" is an area in which a student excels significantly over other areas, based on the results of mock exams.

[0581] "School destination" refers to the educational institution, such as a university or vocational school, that a student aims to attend after graduating from high school.

[0582] A "specialty" is a specific academic field that a student wishes to study at their future university.

[0583] "Proposal methods" are methods or systems that show students the most suitable schools and fields of specialization based on the analysis results.

[0584] An "interface" is a means such as an operation screen or input device that allows a user to interact with a system.

[0585] A "smartphone" is a mobile phone with advanced computing and communication capabilities.

[0586] A "tablet" is a small, portable computer that uses a touchscreen as its primary input means.

[0587] A "virtual reality headset" is a device that allows a user to have an immersive virtual reality experience.

[0588] A "generative AI model" is an artificial intelligence modeling technique designed to perform specific tasks based on training data.

[0589] This invention relates to a system that analyzes mock exam results, understands students' strengths and areas of expertise, and then suggests the most suitable educational destination and field of specialization. This system is primarily composed of a user terminal, a server, and a generative AI model.

[0590] System Program

[0591] The system has the following features:

[0592] 1. Enter your mock test results:

[0593] The user device provides an interface for students to input mock exam results and information about their desired specialization. Students use their smartphones or tablets to input their mock exam scores for each subject, as well as their desired school and specialization.

[0594] 2. Receiving and storing data:

[0595] The server receives and stores the mock test result data and desired information sent from the user terminal.

[0596] 3. Analysis process:

[0597] The server sends the stored data to the generative AI model, which analyzes the received data and identifies the student's areas of expertise and strengths. Specifically, it analyzes the data based on past problem analysis data to identify areas of expertise.

[0598] 4. Proposal of further education and specialization:

[0599] The server receives the analysis results from the generative AI model and uses them to suggest optimal educational destinations and specializations, and can provide detailed information to users through a virtual reality headset.

[0600] Specific usage

[0601] Example 1: User enters practice test results

[0602] A user inputs the results of a mock test using a smartphone. For example, suppose the results are "Mathematics: 85 points, English: 90 points, Japanese: 75 points," and the desired field of specialization is "Information Engineering." This information is sent from the user's device to the server.

[0603] Example 2: Data processing and analysis

[0604] The server sends the received mock test results and desired field of study information to the generative AI model, which analyzes the data and identifies that the student's strengths are "Mathematics" and "English."

[0605] Example 3: Suggesting further education

[0606] Based on the analysis results, the server will suggest the most suitable university and specialty. For example, it will suggest "University A, Department of Information Engineering" and "University B, Department of AI" as universities where users can study "Information Engineering." Using a virtual reality headset, users can visually check detailed information about these universities and majors.

[0607] Example prompt sentence:

[0608] Users input their mock test results, and the generative AI model analyzed them to identify their strengths in mathematics and English. Based on this, it suggested a path to further study in information engineering.

[0609] In this way, the present invention is a system that can suggest specific and realistic educational destinations that reflect a student's strengths, allowing students to choose their educational destinations with confidence and increasing the chances of being accepted.

[0610] As specific hardware and software examples, smartphones and tablets are used as user devices, and servers equipped with generative AI models are used for analysis processing. Virtual reality headsets are useful for providing detailed visual information.

[0611] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0612] Step 1:

[0613] Users input their mock test results using a smartphone or tablet. Specifically, they use a dedicated application to enter their subject scores, such as "Mathematics: 85 points, English: 90 points, Japanese: 75 points," as well as their desired field of specialization, such as "Information Engineering." This input information is sent to the server in JSON format or similar.

[0614] Step 2:

[0615] The server receives the data sent from the user terminal and saves it in the database. Here, the data is first validated. To ensure that the data format is consistent and that the value is within a range, for example, it checks whether "Math: 85 points" is within the range of 0 to 100. If the data is valid, it is saved in the database.

[0616] Step 3:

[0617] The server sends the stored data to a generative AI model. This AI model has been trained in advance on a large amount of past question analysis data and has an analysis algorithm for specific input data. Specifically, using mock test results and desired specialization data, students input their scores for each subject and their desired specialization, and the data is processed and calculated based on that to identify the student's areas of expertise and strengths.

[0618] Step 4:

[0619] The generative AI model returns the analysis results to the server. Specifically, the analysis results show that "math" and "English" are strong subjects based on the input mock test results, and the results are sent back to the server. The server receives this and uses the results to create a list of optimal schools and specializations.

[0620] Step 5:

[0621] The server generates suggestions for schools and specializations, taking into account past exam analysis data, entrance exam dates, and the exam trends of the schools. For example, for a student who excels in math and English and is interested in information engineering, specific schools such as "Information Engineering Department at University A" or "AI Major at University B" will be listed.

[0622] Step 6:

[0623] Users can use a virtual reality headset to view detailed information about proposed schools and majors. This allows them to visually experience the campus atmosphere and curriculum content, providing a deeper understanding. Viewing detailed information about schools using a virtual reality headset can help students decide whether a school is right for them.

[0624] The specific actions taken at each step are as follows:

[0625] Step 1: The user enters the results of the mock test into the application's input form and presses the submit button. The input is sent from the smartphone or tablet to the server.

[0626] Step 2: The server checks the format and range of the data received, and if there are no problems, stores it in the database.

[0627] Step 3: The server sends the stored data to the generative AI model, which then analyzes the data.

[0628] Step 4: The generative AI model sends the analysis results back to the server, which receives the results and generates recommendations for further education and specialization.

[0629] Step 5: The server creates a list of optimal educational destinations and fields of specialization based on the analysis results and sends it to the user.

[0630] Step 6: The user uses a virtual reality headset to visually review the details of the proposed education and specialization.

[0631] 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.

[0632] This invention combines a system that analyzes mock test results, understands a student's areas of expertise and strengths, and then suggests the most suitable schools and departments to apply to with an emotion engine that recognizes the user's emotions. This system is primarily composed of a user terminal, a server, a generative AI model, and an emotion engine.

[0633] System Overview

[0634] User terminal

[0635] The user terminal provides an interface for students to input their mock exam results and information about their desired faculty and field. The user enters this information into a form and sends it to the server. Data is also collected from the user's facial expressions and voice when entering information, allowing the emotion engine to analyze it.

[0636] server

[0637] The server receives and stores mock test results, desired information, and emotional data sent from the user's device. It then passes the stored data to a generative AI model, which analyzes the user's areas of expertise and emotions. It also has the function of suggesting the most suitable schools and departments based on the analysis results.

[0638] Generative AI Models

[0639] The generative AI model analyzes data provided by the server to identify students' strengths and areas of expertise, and then runs an algorithm to suggest schools and departments with high success rates based on past exam question analysis data.

[0640] Emotion Engine

[0641] The emotion engine analyzes the user's facial expressions and voice when inputting information to identify the user's emotional state. The acquired emotional data is reflected in the content of suggestions, providing advice and suggestions that correspond to the student's emotional state.

[0642] Program processing

[0643] 1. User enters mock test results

[0644] The user enters their mock exam subject scores and desired faculty and field into the input form on the device. Once the user has completed the input, they press a button to send the data to the server. At the same time, the emotion engine analyzes the user's facial expressions and voice to collect emotional data.

[0645] 2. The server receives and stores the data

[0646] The server receives the mock test result data, preference information, and emotion data sent by the user. The server validates the received data to ensure that the format and value range are correct. Then, it stores the data in the database.

[0647] 3. Analysis using generative AI models

[0648] The server sends the stored data to the generative AI model, which analyzes the data, identifies the student's areas of expertise and strengths, and returns the analysis results to the server, taking into account the emotional data obtained.

[0649] 4. Analysis by Emotion Engine

[0650] The server sends the emotion data to the emotion engine, which analyzes the user's emotional state and determines whether the state is negative or positive.

[0651] 5. The server generates a list of schools of interest

[0652] The server receives the analysis results of the generative AI model and the emotion data from the emotion engine, and generates optimal recommendations for schools and departments. The recommendations also take into account past exam question analysis data and exam dates. If the emotional state is negative, the server includes advice on how to reduce stress, and if the emotional state is positive, the server includes recommendations for challenging schools.

[0653] 6. The user checks the proposed results

[0654] The server sends the proposed results to the user's device. The user's device receives the proposed results and displays them on the screen. The user can check the detailed information of the proposed schools and departments and use it as a reference for selecting the school of their choice that is most suitable for them.

[0655] Specific examples

[0656] Example 1: When a user enters a practice test result

[0657] The user inputs their mock test scores of "Mathematics: 85 points, English: 90 points, Japanese: 75 points," their desired faculty of study as "Information Engineering," and their desired field as "AI." The emotion engine analyzes the user's facial expressions and voice and determines that the user is relaxed.

[0658] Example 2: Server passes data to generative AI model and emotion engine

[0659] The server sends the received mock test results, desired information, and emotional data to the generative AI model and emotion engine, and receives the analysis results from each. If the generative AI model identifies "math" and "English" as areas of expertise and the emotion engine detects negative emotions, it will include advice on stress reduction in the proposal.

[0660] Example 3: When the server suggests a preferred school

[0661] The server searches a database of schools of choice based on the analysis results and emotional data, and lists schools and departments with high acceptance rates, taking into account question trends and exam information. If negative emotions are detected, the server suggests more realistic schools, and if positive emotions are detected, it suggests more challenging schools.

[0662] In this way, the present invention is a system that can suggest specific and realistic schools of choice that reflect a student's strengths and take into consideration their emotional state, allowing students to choose their schools with confidence and increasing their chances of being accepted.

[0663] The processing flow will be explained below.

[0664] Step 1:

[0665] The user accesses the input form on the device. The user enters information such as the scores for each subject in the mock exam, the desired faculty, and the field of study. At the same time, the device collects the user's facial expressions and voice to pass to the emotion engine. Once the input is complete, the user clicks the send button to send the data to the server.

[0666] Specific behavior:

[0667] A user enters the following scores into a web form: Math: 85 points, English: 90 points, Japanese: 75 points.

[0668] The user selects "Information Engineering" as the desired faculty and "AI" as the desired field.

[0669] The user's facial expressions and voice are recorded using a camera and microphone, and the emotion engine is prepared to analyze them.

[0670] The user clicks the submit button.

[0671] Step 2:

[0672] The server receives the mock test result data, desired information, and emotion data sent by the user. The server validates the received data to ensure that the format and value range are correct.

[0673] Specific behavior:

[0674] The server receives the data in JSON format.

[0675] Validate each field of data (e.g., "Math: 85 points").

[0676] If invalid data is included, an error message is generated and returned to the user.

[0677] Step 3:

[0678] The server stores the validated data in a database, which is used later for analysis.

[0679] Specific behavior:

[0680] The server converts the data into the appropriate format and stores it in the database.

[0681] Check that the data has been saved.

[0682] A save completion response is sent to the user's terminal.

[0683] Step 4:

[0684] The server sends the saved data to the generative AI model, which analyzes the mock test results to identify the student's strengths and areas of expertise, and returns the analysis results to the server.

[0685] Specific behavior:

[0686] The server retrieves the data from the database and sends it to the generative AI model.

[0687] The generative AI model analyzes the scores for each subject and identifies "Mathematics" and "English" as areas of strength.

[0688] The AI ​​model sends the analysis results back to the server.

[0689] Step 5:

[0690] The server sends the emotion data to the emotion engine, which analyzes the user's facial expressions and voice to identify the user's emotional state and returns the analysis results to the server.

[0691] Specific behavior:

[0692] The server sends the emotion data to the emotion engine.

[0693] The emotion engine analyzes facial and voice data to identify the user's emotional state (e.g., negative, positive).

[0694] The emotion engine sends the analysis results back to the server.

[0695] Step 6:

[0696] The server receives the analysis results of the generative AI model and the emotion data from the emotion engine, and generates optimal recommendations for schools and departments to apply to. These recommendations also take into account past exam question analysis data and exam dates.

[0697] Specific behavior:

[0698] The server integrates and analyzes data from the generative AI model and the emotion engine.

[0699] If the emotional state is negative, include advice on reducing stress.

[0700] If they are positive, we will make suggestions for challenging schools to apply to.

[0701] Generate a list of suggestions including "Information Engineering Department at University A" and "AI major at University B."

[0702] Step 7:

[0703] The server sends the proposal results to the user terminal, which receives the proposal results and displays them on the screen.

[0704] Specific behavior:

[0705] The server generates the proposal results in JSON format.

[0706] The proposal results are transmitted to the user terminal.

[0707] The content received by the user's device is displayed. For example, detailed information about "University A's Department of Information Engineering" and "University B's AI major" is displayed on the screen.

[0708] Step 8:

[0709] Users can check the proposed results and use them as reference material to select the school that best suits them.

[0710] Specific behavior:

[0711] The user checks the proposed results displayed on the screen in detail.

[0712] If necessary, click on each school or faculty to view detailed information.

[0713] Select your preferred school based on the suggested results.

[0714] Example 2

[0715] 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."

[0716] Traditional career suggestion systems based on mock exam results focus on analyzing students' areas of expertise, but do not take into account the student's emotional state. As a result, they are unable to provide appropriate advice when students feel stressed or anxious, which can lead to ineffective career choices. Furthermore, these systems tend to offer uniform suggestions, and flexible support tailored to each student's emotional state and aspirations is needed.

[0717] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0718] In this invention, the server includes means for receiving and storing mock test result data, means for analyzing the mock test result data and identifying the student's areas of expertise, means for suggesting the most suitable school and department of choice based on the student's areas of expertise, and means for analyzing the user's emotions and generating suggestions according to the user's emotional state. This makes it possible to suggest a career path that takes into account not only the student's areas of expertise but also their emotional state.

[0719] "Mock test result data" refers to data that includes information related to the scores for individual subjects and total scores of mock tests taken by students, or grades.

[0720] "Means for receiving and storing" refers to a device or function that receives data transmitted from a user terminal and stores it in a database or other storage device.

[0721] "Means for analyzing and identifying" refers to devices or algorithms that process and analyze given data to derive specific information or results.

[0722] "Means for suggesting preferred schools and departments" refers to devices or functions that suggest the most suitable school to attend (preferred school) and field of study (department) to students based on the analysis results obtained.

[0723] "Means for analyzing emotions" refers to devices or algorithms that analyze a user's facial expressions and voice data to determine the user's emotional state.

[0724] The term "means for generating suggestions according to emotional state" refers to a device or function that takes into account the emotional state of the user and generates advice or suggestions appropriate to that state.

[0725] "Past question analysis data" refers to data that includes information based on the content and trends of exam questions that have been asked in the past, as well as the results of question analysis.

[0726] "Means for considering exam dates" refers to devices or functions that suggest career paths based on students' desired exam schedules and actual exam dates.

[0727] This invention is a system that analyzes mock test results, understands students' areas of expertise and strengths, and then suggests the most suitable schools and departments for them to apply to. This system consists of a user terminal, a server, a generative AI model, and an emotion engine.

[0728] System configuration

[0729] User terminal

[0730] The user terminal provides an interface for students to input information about their mock exam results, desired faculty, and field. When the user enters this information into a form and sends it to the server, their facial expressions and voice are simultaneously recorded.

[0731] server

[0732] The server receives mock test results, desired information, and emotional data sent from the user's device and stores this data. The server also provides the stored data to a generative AI model, which analyzes areas of expertise and emotions. Based on the analysis results, the server suggests the most suitable schools and departments to apply to.

[0733] Generative AI Models

[0734] The generative AI model is built using Python's TensorFlow library. It analyzes data provided by the server to identify students' areas of expertise and strengths. It then runs an algorithm based on past exam question analysis data to suggest schools and departments with high acceptance rates.

[0735] Emotion Engine

[0736] The emotion engine uses OpenCV and the Google Cloud Speech-to-Text API to analyze the user's facial expressions and voice during input. From this data, the emotion engine identifies the user's emotional state, determining whether it is positive or negative.

[0737] System Operation

[0738] The system operates as follows: the user enters the results of a mock test into an input form on their device and sends it to the server. The emotion engine captures the user's facial expressions and voice and generates emotion data. The server stores the received data, validates it, and then sends it to the generative AI model and emotion engine. The generative AI model identifies the user's areas of expertise, and the emotion engine determines the user's emotional state. The server then generates optimal recommendations for schools and departments based on the results of these analyses.

[0739] Specific examples

[0740] Example 1: When a user enters a practice test result

[0741] The user inputs their mock test scores of "Mathematics: 85 points, English: 90 points, Japanese: 75 points," their desired faculty of study as "Information Engineering," and their desired field as "AI." The emotion engine analyzes the user's facial expressions and voice and determines that the user is relaxed.

[0742] Example 2: Server passes data to generative AI model and emotion engine

[0743] The server sends the received mock test results, preference information, and emotional data to the generative AI model and emotion engine, and receives the analysis results from each. If the generative AI model identifies "math" and "English" as strong subjects and the emotion engine detects positive emotions, it will include suggestions for challenging schools of choice.

[0744] Example 3: When the server suggests a preferred school

[0745] The server searches a database of schools of choice based on the analysis results and emotional data, and takes into account question trends and exam information to create a list of schools and departments with high acceptance rates. If positive emotions are detected, it may suggest challenging schools to choose from.

[0746] Example prompt sentence:

[0747] Mock exam results: Math 85 points, English 90 points, Japanese 75 points

[0748] Preferred Faculty: Information Engineering

[0749] Desired field: AI

[0750] Thus, the mode for carrying out the invention proposes the most suitable school and department of choice for a student, taking into consideration the student's areas of expertise and emotional state, through a series of steps from data entry to analysis and final proposal, allowing the student to choose their preferred school with confidence and increasing their chances of being accepted.

[0751] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0752] Step 1: User enters practice test results

[0753] The user opens the web application on their device. They enter their mock exam subject scores (Mathematics: 85 points, English: 90 points, Japanese: 75 points), their desired faculty (Information Engineering), and their desired field (AI). After completing the input, they click the send button. The input data is sent from the device to the server. At the same time, the emotion engine captures the user's facial expressions and voice through the camera and microphone and generates emotion data.

[0754] Input: mock test results and desired information entered by the user in the input form, facial expressions and voice data

[0755] Output: Mock test result data, preference information, and emotion data sent to the server

[0756] Step 2: The server receives and stores the data

[0757] The server receives the mock test result data, desired information, and emotion data sent from the user's device. Firewalls and data validation functions are used to check the security and accuracy of the received data. Once validated, the data is stored in a database.

[0758] Input: Received mock test result data, desired information, emotional data

[0759] Output: Mock test results data, preference information, and emotion data stored in the database

[0760] Step 3: Analyze the data with a generative AI model

[0761] The server sends the stored data to the generative AI model, which uses Python's TensorFlow library to analyze the data and identify the student's areas of expertise and strengths. "Mathematics" and "English" are identified as areas of expertise. The analysis results are then sent back to the server.

[0762] Input: Mock test result data, desired information, and emotional data stored in the database

[0763] Output: Information on areas of expertise and strengths after analysis by the generative AI model

[0764] Step 4: Emotional state analysis by the emotion engine

[0765] The server sends the emotion data to the emotion engine, which uses OpenCV and the Google Cloud Speech-to-Text API to analyze the user's facial expressions and voice. A positive emotional state is identified as a result of the analysis and sent back to the server.

[0766] Input: Received emotion data

[0767] Output: Emotional state information after analysis

[0768] Step 5: The server generates school recommendations

[0769] The server receives the analysis results of the AI ​​model and the emotional state of the emotion engine, and generates optimal recommendations for schools and departments. The recommendations also take into account past exam question analysis data and exam schedule information. Challenging schools suited to a positive emotional state can also be included in the recommendations.

[0770] Input: Analyzed areas of expertise and strengths, emotional state information

[0771] Output: Suggested best schools and departments

[0772] Step 6: User confirms the proposed results

[0773] The server sends the proposed results to the user's device. The user's device receives the proposed results and displays them on the screen. The user can check the detailed information of the proposed schools and departments and use it as a reference for selecting the school of their choice that best suits them.

[0774] Input: Suggested best school and department information

[0775] Output: Suggestion results displayed on the user's device

[0776] The above is the specific flow of the system's program processing, and the detailed operations at each step are clarified.

[0777] (Application example 2)

[0778] 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."

[0779] Conventional systems for suggesting preferred schools and departments make suggestions based solely on students' mock exam results. However, this system cannot take into account the student's individual psychological state, such as their emotional state or stress level at the time, which can affect the accuracy of the suggestions and the student's motivation. Therefore, it is necessary for students to study in a relaxed state and receive appropriate advice.

[0780] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0781] In this invention, the server includes means for receiving and saving mock test result data, means for analyzing the mock test result data and identifying the student's areas of expertise, means for proposing the most suitable school and department of choice based on the student's areas of expertise, means for recognizing and saving the user's emotional data, and means for analyzing the emotional data and adjusting the content of the proposal based on the user's emotional state. This makes it possible to propose appropriate and personalized schools and departments of choice that take into account the student's emotional state as well as their academic ability data.

[0782] "Mock exam result data" refers to data relating to the scores and grades obtained by students in each subject in the mock exam.

[0783] A "strength area" is an area of ​​study or subject in which a student shows particular ability or interest.

[0784] "Preferred school" refers to the educational institution that a student wishes to attend.

[0785] A "faculty" is a unit of education and research established for each academic field at a university or higher education institution.

[0786] "Emotion data" is information about emotions acquired from the user's facial expressions, voice, etc.

[0787] "Emotional state" refers to the positive or negative mental state or emotion that a user is currently experiencing.

[0788] A "generative AI model" is an artificial intelligence algorithm that analyzes input data and generates optimal suggestions based on the user's areas of expertise.

[0789] A "prompt sentence" is a specific input sentence that a generative AI model uses to generate suggestions.

[0790] This invention combines a system that analyzes mock test results data, understands a student's areas of expertise and strengths, and then suggests the most suitable school or department to apply to with an emotion engine that recognizes the user's emotions.The system of this invention is mainly composed of a user terminal, a server, a generative AI model, and an emotion engine.

[0791] First, the user device provides an interface for students to input their mock exam results and information about their desired faculty and field. The user enters this information into a form on the device and sends it to the server. Data is also collected from the user's facial expressions and voice when entering information, which the emotion engine analyzes. Furthermore, hardware such as a webcam and microphone is required to acquire emotion data.

[0792] The server then receives and stores the mock test results, desired information, and emotional data sent from the user's device. The server validates the received data to ensure that the format and value range are correct. The server then analyzes this data using a generative AI model. The generative AI model is implemented using a programming language such as Python and includes past question analysis data and algorithms for identifying schools and departments with high pass rates.

[0793] The emotion engine analyzes the user's facial expressions and voice when inputting information to identify the user's emotional state. It uses the EmotionEngine library to determine whether the user is relaxed or stressed. The server combines the emotion data obtained from the emotion engine with the analysis results of the generative AI model to generate optimal recommendations for schools and departments.

[0794] For example, if a user inputs their mock exam scores and indicates that they want to study computer engineering and AI, the emotion engine analyzes their facial expressions and voice and determines that they are relaxed. The server then uses a generative AI model to analyze this data and identify their strengths in math and English. If the user's emotional state is positive, the engine returns results that include suggestions for challenging schools.

[0795] Examples of specific prompts include:

[0796] "User entered mock test results: Math 85, English 90, Japanese 75. Desired department: Computer Engineering. Desired field: AI. Emotional state: Relaxed."

[0797] In this way, the system of the present invention can integrate and analyze a student's academic ability data and emotional data, and can suggest the most suitable schools and departments for each student, allowing students to select their preferred schools with greater confidence.

[0798] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0799] Step 1:

[0800] The user enters the results of the mock exam and the desired faculty and field.

[0801] Input: Mock exam scores by subject, desired faculty information, desired field information

[0802] Output: The entered data is collected from the terminal

[0803] Specific operation: The user enters grade information such as "Math: 85 points, English: 90 points, Japanese: 75 points" and a desired field such as "Information Engineering" or "AI" into the form on the device, and presses the submit button. At this time, the user's facial expressions and voice are collected using the device's webcam and microphone.

[0804] Step 2:

[0805] The emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[0806] Input: User's facial expression data, voice data

[0807] Output: Emotion data (e.g., relaxed, nervous, etc.)

[0808] How it works: Facial and voice data collected on the device is analyzed by the EmotionEngine library to identify the user's emotional state, for example, determining whether the user is relaxed or tense.

[0809] Step 3:

[0810] The server receives and stores the mock test result data, desired information, and emotion data.

[0811] Input: mock test results, desired faculty information, desired field information, emotional data

[0812] Output: User data stored in the database

[0813] Specific operation: Data sent from the user terminal is sent to the server, which validates the data to ensure it is in the correct format and stores it in the database.

[0814] Step 4:

[0815] The server sends the data to the generated AI model, which analyzes the student's areas of expertise and the best schools and departments to apply to.

[0816] Input: Saved user data (mock test results, preferences, emotional data)

[0817] Output: Analysis results from the generative AI model (areas of expertise, preferred schools and departments)

[0818] How it works: The server inputs the saved data into a generative AI model implemented in Python to identify areas of strength in each subject. It also uses past question analysis data to calculate schools and departments with high pass rates.

[0819] Step 5:

[0820] The server adjusts the suggestions based on the emotional data.

[0821] Input: Analysis results of generative AI model, emotion data

[0822] Output: Recommendations for the best schools and departments to apply to based on the emotional state

[0823] How it works: The server reviews the analysis results returned by the generative AI model and adjusts the suggestions based on the data from the emotion engine. For example, if the emotion data is positive, it will suggest more challenging schools, and if it is negative, it will make more realistic suggestions.

[0824] Step 6:

[0825] The server sends the final proposal of preferred schools and departments to the user's device.

[0826] Input: Suggestion data according to emotional state

[0827] Output: User device showing the proposed results

[0828] Specific operation: The server generates a list of the most suitable schools and departments according to the user's emotional state and sends it to the user's device. The user's device then displays this information on the screen so that the user can confirm it.

[0829] This makes it possible to integrate mock test results data with emotional data to suggest the most suitable schools and departments for students to apply to.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] [Third embodiment]

[0834] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0835] 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.

[0836] 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).

[0837] 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.

[0838] 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.

[0839] 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).

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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."

[0846] This invention relates to a system that analyzes mock exam responses, understands students' areas of expertise and strengths, and then suggests the most suitable schools and departments for them to apply to. This system is primarily composed of a user terminal, a server, and a generative AI model.

[0847] System Overview

[0848] User terminal

[0849] The user terminal provides an interface for students to input their mock exam results and information about their desired faculty and field. The user enters this information into a form and sends it to the server.

[0850] server

[0851] The server receives and stores mock test results and desired information sent from the user's device. It then passes the stored data to a generative AI model, which analyzes the model's areas of expertise. It also has the function of suggesting the most suitable schools and departments based on the analysis results.

[0852] Generative AI Models

[0853] The generative AI model analyzes data provided by the server to identify students' strengths and areas of expertise, and then runs an algorithm to suggest schools and departments with high success rates based on past exam question analysis data.

[0854] Program processing

[0855] 1. User enters mock test results

[0856] The user enters the subject scores for the mock exam, the desired faculty, and the field of study into the input form on the terminal. After completing the input, the user presses a button to send the data to the server.

[0857] 2. The server receives and stores the data

[0858] The server receives the data submitted by the user, validates it to ensure it is in the correct format and has the correct value range, and then stores it in the database.

[0859] 3. Analysis using generative AI models

[0860] The server sends the stored data to the generative AI model, which analyzes the data to identify the student's areas of expertise and strengths, and returns the analysis results to the server.

[0861] 4. The server generates a list of schools of interest

[0862] The server receives the analysis results from the generative AI model and uses them to generate optimal recommendations for schools and departments, taking into account past question analysis data and exam dates. The recommendations are then sent to the user's device.

[0863] 5. The user checks the proposed results

[0864] The user's device receives the proposed results from the server and displays them on the screen. The user can then check the details of the proposed schools and departments and use them as a reference for selecting the school of their choice that best suits them.

[0865] Specific examples

[0866] Example 1: When a user enters a practice test result

[0867] The user enters that their mock test scores are "Mathematics: 85 points, English: 90 points, Japanese: 75 points," that their desired faculty is "Information Engineering," and that their desired field is "AI."

[0868] Example 2: When a server uses a generative AI model to analyze data

[0869] The server sends the received mock test results and desired faculty and field information to the generating AI model, and receives the analysis result that "Mathematics" and "English" are strengths.

[0870] Example 3: When the server suggests a preferred school

[0871] Based on the analysis results and exam information, the server will suggest several universities with "information engineering" departments with high acceptance rates. For example, specific preferred schools such as "Information Engineering Department at University A" or "AI major at University B" will be presented.

[0872] In this way, the present invention is a system that can suggest specific and realistic schools of choice that reflect a student's strengths, allowing students to choose their schools with confidence and increasing their chances of being accepted.

[0873] The processing flow will be explained below.

[0874] Step 1:

[0875] The user accesses the input form on the device. The user enters the scores for each subject in the mock exam, as well as the desired faculty and field. Once the input is complete, the user clicks the send button to send the data to the server.

[0876] Specific behavior:

[0877] A user enters the following scores into a web form: Math: 85 points, English: 90 points, Japanese: 75 points.

[0878] The user selects "Information Engineering" as the desired faculty and "AI" as the desired field.

[0879] The user clicks the submit button.

[0880] Step 2:

[0881] The server receives the mock test result data sent by the user. The server validates the received data to ensure that the format and value range are correct.

[0882] Specific behavior:

[0883] The server receives the data in JSON format.

[0884] Validate each field of data (e.g., "Math: 85 points").

[0885] If invalid data is included, an error message is generated and returned to the user.

[0886] Step 3:

[0887] The server stores the validated data in a database, which is used later for analysis.

[0888] Specific behavior:

[0889] The server converts the data into the appropriate format and stores it in the database.

[0890] Check that the data has been saved.

[0891] A save completion response is sent to the user's terminal.

[0892] Step 4:

[0893] The server sends the saved data to the generative AI model, which analyzes the mock test results to identify the student's strengths and areas of expertise, and returns the analysis results to the server.

[0894] Specific behavior:

[0895] The server sends the mock test results and desired information to the AI ​​model.

[0896] The generative AI model analyzed the scores for each subject and identified that "Mathematics" and "English" were the student's areas of strength.

[0897] The AI ​​model sends the analysis results back to the server.

[0898] Step 5:

[0899] The server receives the analysis results from the generative AI model and generates optimal recommendations for schools and departments, taking into account past exam question analysis data and exam dates.

[0900] Specific behavior:

[0901] The server searches the database of the desired school based on the analysis results.

[0902] We have compiled a list of schools and faculties with high pass rates based on question trends and examination information.

[0903] The proposals selected were "The Department of Information Engineering at University A" and "The AI ​​major at University B."

[0904] Step 6:

[0905] The server sends the proposal results to the user terminal, which receives the proposal results and displays them on the screen.

[0906] Specific behavior:

[0907] The server generates the proposal results in JSON format.

[0908] The proposal results are sent to the user's device.

[0909] The user's device displays the received information. For example, desired schools such as "Information Engineering Department at University A" or "AI major at University B" are displayed on the screen.

[0910] Step 7:

[0911] Users can check the proposed results and use them as reference material to select the school that best suits them.

[0912] Specific behavior:

[0913] The user can check the details of the proposed results displayed on the screen.

[0914] If necessary, click on each school or faculty for more information.

[0915] Select your preferred school based on the proposed results.

[0916] Example 1

[0917] 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."

[0918] Conventional mock exam systems simply saved test results, but did not have the functionality to identify students' areas of expertise or suggest the most suitable schools or departments based on those areas. This made it difficult for students to understand their strengths and select schools that would utilize those strengths. Furthermore, specific suggestions that took into account past exam trends and exam dates were also insufficient.

[0919] 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.

[0920] In this invention, the server includes a means for inputting and transmitting mock test result data and desired field data from a terminal, a means for receiving and storing the mock test result data and desired field data, a means for identifying a student's areas of expertise using a generative AI model that analyzes the mock test result data and desired field data, and a means for proposing the most suitable school and department of interest based on the student's areas of expertise and taking into account past question analysis data and exam dates. This allows students to select the most suitable school of their choice by utilizing their own strengths.

[0921] A "terminal" is a device through which a user inputs mock test result data and desired domain data and transmits them to a server.

[0922] "Mock exam result data" refers to the subject-specific scores and other evaluation information obtained by students in the mock exam.

[0923] "Desired field data" refers to information about the faculty the student is applying to and the field that will be analyzed.

[0924] "Means for transmission" refers to the interface or protocol for transmitting data from the terminal to the server.

[0925] "Means for receiving and storing" refers to the function by which the server receives data sent from the terminal and stores it in a storage device such as a database.

[0926] A "generative AI model" refers to an artificial intelligence algorithm that analyzes incoming data and identifies students' areas of expertise and strengths.

[0927] The "means of identifying areas of expertise" is a function that uses a generative AI model to analyze students' test result data and extract the subjects and areas in which the student excels.

[0928] "Past question analysis data" refers to data that includes analysis results such as question trends and question difficulty of exams that have been conducted in the past.

[0929] "Exam Schedule" refers to the dates or schedule of exams that a student plans to take.

[0930] "Means to suggest schools and departments of choice" is a function that suggests the most suitable schools and departments to students by taking into consideration the analysis results of the generative AI model, past question analysis data, and exam dates.

[0931] "System" refers to the overall system consisting of the terminal, server, and generative AI model.

[0932] This invention relates to a system that analyzes mock exam responses, understands a student's areas of expertise and strengths, and then suggests the most suitable schools and departments for them to apply to. This system is primarily composed of a user terminal, a server, and a generative AI model.

[0933] The user terminal provides an interface for entering mock test results and information about the desired faculty and field. When the user enters this information into a form and presses the submit button, the data is sent to the server. The terminal uses a standard web browser or dedicated application software.

[0934] The server has the function of receiving and saving the mock test result data and desired domain data sent from the user terminal. The server uses a database to manage and save this data, and also performs validation. Validation is the process of checking whether the format and value range of the received data are correct. Data is saved in the database only if validation is successful.

[0935] The server then sends the stored data to a generative AI model, which analyzes the data and identifies the student's areas of expertise and strengths. The generative AI model uses machine learning algorithms to analyze patterns and characteristics of test results. For example, if a student scores high in math, it determines that the student is good at math. The results of this analysis are then sent back to the server.

[0936] The server generates optimal recommendations for schools and departments based on the analysis results from the generative AI model. The server also takes into account past exam question analysis data and exam dates. For example, a student with high scores in math and English will be suggested departments and universities that emphasize these subjects. These recommendations are then sent to the user's device.

[0937] The user terminal receives the recommendation results from the server and displays them on the screen. The user can check this information and use it as a reference for selecting the school of their choice that is most suitable for them.

[0938] Specific examples

[0939] For example, consider the case where a user enters a practice test score as follows:

[0940] Example input:

[0941] Mathematics: 85 points

[0942] English: 90 points

[0943] Japanese: 75 points

[0944] Preferred Faculty: Information Engineering

[0945] Desired field: AI

[0946] When the user enters this information and presses the send button, the data is sent to the server.

[0947] The server then sends the received data to the generative AI model, which returns the result that "Mathematics" and "English" are the user's strengths. Based on this result, the server suggests several schools with "Information Engineering" departments that have high acceptance rates. Specifically, the user is presented with specific schools of choice, such as "Information Engineering Department at University A" or "AI major at University B."

[0948] In this way, users can select the school of their choice that best reflects their strengths.

[0949] Example prompt sentence:

[0950] "My mock test results are 'Math: 85 points, English: 90 points, Japanese: 75 points'. I would like to study 'Information Engineering' and my preferred field is 'AI'. Based on this information, please suggest my areas of expertise and the best schools for me to apply to."

[0951] This allows students to choose their preferred school with confidence and increases their chances of being accepted.

[0952] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0953] Step 1:

[0954] The user uses the terminal to input the result data of the mock test and the desired domain data.

[0955] Input: The user enters "Mathematics: 85 points, English: 90 points, Japanese: 75 points", desired faculty "Information Engineering", and desired field "AI".

[0956] Action: The user enters this data into the input form and presses the "Submit" button.

[0957] Output: Data entered from the terminal is sent to the server.

[0958] Step 2:

[0959] The server receives the data sent from the terminal and validates the data.

[0960] Input: Practice test results and desired domain data sent from the terminal.

[0961] Behavior: The server validates the data received, ensuring it is in the correct format and range of values, e.g., checking that the score is between 0 and 100.

[0962] Output: If validation is successful, the data is saved to the database. If validation fails, an error message is generated.

[0963] Step 3:

[0964] The server sends the stored data to the generative AI model and begins analysis.

[0965] Input: Practice test results stored in the database and desired domain data.

[0966] How it works: The server sends the stored data to the generative AI model, which analyzes it and identifies the student's strengths and areas of expertise. Based on a specific algorithm, it may determine that math and English are strong subjects, for example.

[0967] Output: The analysis result is returned to the server, for example, "Strengths: Math and English."

[0968] Step 4:

[0969] Based on the analysis results, the server generates suggestions for the most suitable schools and departments to apply to.

[0970] Input: Analysis results from the generative AI model (areas of expertise), past question analysis data, and exam dates.

[0971] How it works: The server selects the department or university with the highest pass rate, taking into account past exam question analysis data and exam dates. For example, it identifies specific desired schools, such as "University A's Department of Information Engineering" or "University B's AI major."

[0972] Output: The best possible school and department recommendations are generated and sent to the user's device.

[0973] Step 5:

[0974] The user terminal displays the proposal results received from the server so that the user can check them.

[0975] Input: Suggested school and department choices sent from the server.

[0976] Operation: The user's device displays the received recommendations on the screen. The user can then check the details of each school and use them as a reference to select the school that best suits them.

[0977] Output: Display of the proposed results, allowing the user to select specific schools of choice.

[0978] (Application example 1)

[0979] 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."

[0980] Currently, support systems exist for selecting schools and majors based on mock exam results, but they are often limited to physical interfaces and lack flexibility. Users must also expend considerable effort to obtain detailed information about the schools and majors they are considering. Furthermore, they lack visual support for determining how well the proposed information suits them. This can make it difficult for students to obtain sufficient information to make optimal choices, resulting in reduced accuracy in career choices.

[0981] 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.

[0982] In this invention, the server includes means for receiving and storing mock test result data, means for analyzing the mock test result data and identifying the student's areas of expertise, means for suggesting the most suitable educational destination and specialty based on the student's areas of expertise, means for inputting the mock test results into an interface of a smartphone or tablet, and means for a user to check detailed information about the educational destination and specialty using a virtual reality headset. This allows students to easily input their mock test results, receive specific and optimal career suggestions based on analysis by the generative AI model, and check detailed information through virtual reality.

[0983] A "mock test" is a test that students take to measure their academic ability level before taking the exam.

[0984] "Result data" refers to information regarding the scores and grades for each subject obtained after taking the mock test.

[0985] A "strength area" is an area in which a student excels significantly over other areas, based on the results of mock exams.

[0986] "School destination" refers to the educational institution, such as a university or vocational school, that a student aims to attend after graduating from high school.

[0987] A "specialty" is a specific academic field that a student wishes to study at their future university.

[0988] "Proposal methods" are methods or systems that show students the most suitable schools and fields of specialization based on the analysis results.

[0989] An "interface" is a means such as an operation screen or input device that allows a user to interact with a system.

[0990] A "smartphone" is a mobile phone with advanced computing and communication capabilities.

[0991] A "tablet" is a small, portable computer that uses a touchscreen as its primary input means.

[0992] A "virtual reality headset" is a device that allows a user to have an immersive virtual reality experience.

[0993] A "generative AI model" is an artificial intelligence modeling technique designed to perform specific tasks based on training data.

[0994] This invention relates to a system that analyzes mock exam results, understands students' strengths and areas of expertise, and then suggests the most suitable educational destination and field of specialization. This system is primarily composed of a user terminal, a server, and a generative AI model.

[0995] System Program

[0996] The system has the following features:

[0997] 1. Enter your mock test results:

[0998] The user device provides an interface for students to input mock exam results and information about their desired specialization. Students use their smartphones or tablets to input their mock exam scores for each subject, as well as their desired school and specialization.

[0999] 2. Receiving and storing data:

[1000] The server receives and stores the mock test result data and desired information sent from the user terminal.

[1001] 3. Analysis process:

[1002] The server sends the stored data to the generative AI model, which analyzes the received data and identifies the student's areas of expertise and strengths. Specifically, it analyzes the data based on past problem analysis data to identify areas of expertise.

[1003] 4. Proposal of further education and specialization:

[1004] The server receives the analysis results from the generative AI model and uses them to suggest optimal educational destinations and specializations, and can provide detailed information to users through a virtual reality headset.

[1005] Specific usage

[1006] Example 1: User enters practice test results

[1007] A user inputs the results of a mock test using a smartphone. For example, suppose the results are "Mathematics: 85 points, English: 90 points, Japanese: 75 points," and the desired field of specialization is "Information Engineering." This information is sent from the user's device to the server.

[1008] Example 2: Data processing and analysis

[1009] The server sends the received mock test results and desired field of study information to the generative AI model, which analyzes the data and identifies that the student's strengths are "Mathematics" and "English."

[1010] Example 3: Suggesting further education

[1011] Based on the analysis results, the server will suggest the most suitable university and specialty. For example, it will suggest "University A, Department of Information Engineering" and "University B, Department of AI" as universities where users can study "Information Engineering." Using a virtual reality headset, users can visually check detailed information about these universities and majors.

[1012] Example prompt sentence:

[1013] Users input their mock test results, and the generative AI model analyzed them to identify their strengths in mathematics and English. Based on this, it suggested a path to further study in information engineering.

[1014] In this way, the present invention is a system that can suggest specific and realistic educational destinations that reflect a student's strengths, allowing students to choose their educational destinations with confidence and increasing the chances of being accepted.

[1015] As specific hardware and software examples, smartphones and tablets are used as user devices, and servers equipped with generative AI models are used for analysis processing. Virtual reality headsets are useful for providing detailed visual information.

[1016] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1017] Step 1:

[1018] Users input their mock test results using a smartphone or tablet. Specifically, they use a dedicated application to enter their subject scores, such as "Mathematics: 85 points, English: 90 points, Japanese: 75 points," as well as their desired field of specialization, such as "Information Engineering." This input information is sent to the server in JSON format or similar.

[1019] Step 2:

[1020] The server receives the data sent from the user terminal and saves it in the database. Here, the data is first validated. To ensure that the data format is consistent and that the value is within a range, for example, it checks whether "Math: 85 points" is within the range of 0 to 100. If the data is valid, it is saved in the database.

[1021] Step 3:

[1022] The server sends the stored data to a generative AI model. This AI model has been trained in advance on a large amount of past question analysis data and has an analysis algorithm for specific input data. Specifically, using mock test results and desired specialization data, students input their scores for each subject and their desired specialization, and the data is processed and calculated based on that to identify the student's areas of expertise and strengths.

[1023] Step 4:

[1024] The generative AI model returns the analysis results to the server. Specifically, the analysis results show that "math" and "English" are strong subjects based on the input mock test results, and the results are sent back to the server. The server receives this and uses the results to create a list of optimal schools and specializations.

[1025] Step 5:

[1026] The server generates suggestions for schools and specializations, taking into account past exam analysis data, entrance exam dates, and the exam trends of the schools. For example, for a student who excels in math and English and is interested in information engineering, specific schools such as "Information Engineering Department at University A" or "AI Major at University B" will be listed.

[1027] Step 6:

[1028] Users can use a virtual reality headset to view detailed information about proposed schools and majors. This allows them to visually experience the campus atmosphere and curriculum content, providing a deeper understanding. Viewing detailed information about schools using a virtual reality headset can help students decide whether a school is right for them.

[1029] The specific actions taken at each step are as follows:

[1030] Step 1: The user enters the results of the mock test into the application's input form and presses the submit button. The input is sent from the smartphone or tablet to the server.

[1031] Step 2: The server checks the format and range of the data received, and if there are no problems, stores it in the database.

[1032] Step 3: The server sends the stored data to the generative AI model, which then analyzes the data.

[1033] Step 4: The generative AI model sends the analysis results back to the server, which receives the results and generates recommendations for further education and specialization.

[1034] Step 5: The server creates a list of optimal educational destinations and fields of specialization based on the analysis results and sends it to the user.

[1035] Step 6: The user uses a virtual reality headset to visually review the details of the proposed education and specialization.

[1036] 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.

[1037] This invention combines a system that analyzes mock test results, understands a student's areas of expertise and strengths, and then suggests the most suitable schools and departments to apply to with an emotion engine that recognizes the user's emotions. This system is primarily composed of a user terminal, a server, a generative AI model, and an emotion engine.

[1038] System Overview

[1039] User terminal

[1040] The user terminal provides an interface for students to input their mock exam results and information about their desired faculty and field. The user enters this information into a form and sends it to the server. Data is also collected from the user's facial expressions and voice when entering information, allowing the emotion engine to analyze it.

[1041] server

[1042] The server receives and stores mock test results, desired information, and emotional data sent from the user's device. It then passes the stored data to a generative AI model, which analyzes the user's areas of expertise and emotions. It also has the function of suggesting the most suitable schools and departments based on the analysis results.

[1043] Generative AI Models

[1044] The generative AI model analyzes data provided by the server to identify students' strengths and areas of expertise, and then runs an algorithm to suggest schools and departments with high success rates based on past exam question analysis data.

[1045] Emotion Engine

[1046] The emotion engine analyzes the user's facial expressions and voice when inputting information to identify the user's emotional state. The acquired emotional data is reflected in the content of suggestions, providing advice and suggestions that correspond to the student's emotional state.

[1047] Program processing

[1048] 1. User enters mock test results

[1049] The user enters their mock exam subject scores and desired faculty and field into the input form on the device. Once the user has completed the input, they press a button to send the data to the server. At the same time, the emotion engine analyzes the user's facial expressions and voice to collect emotional data.

[1050] 2. The server receives and stores the data

[1051] The server receives the mock test result data, preference information, and emotion data sent by the user. The server validates the received data to ensure that the format and value range are correct. Then, it stores the data in the database.

[1052] 3. Analysis using generative AI models

[1053] The server sends the stored data to the generative AI model, which analyzes the data, identifies the student's areas of expertise and strengths, and returns the analysis results to the server, taking into account the emotional data obtained.

[1054] 4. Analysis by Emotion Engine

[1055] The server sends the emotion data to the emotion engine, which analyzes the user's emotional state and determines whether the state is negative or positive.

[1056] 5. The server generates a list of schools of interest

[1057] The server receives the analysis results of the generative AI model and the emotion data from the emotion engine, and generates optimal recommendations for schools and departments. The recommendations also take into account past exam question analysis data and exam dates. If the emotional state is negative, the server includes advice on how to reduce stress, and if the emotional state is positive, the server includes recommendations for challenging schools.

[1058] 6. The user checks the proposed results

[1059] The server sends the proposed results to the user's device. The user's device receives the proposed results and displays them on the screen. The user can check the detailed information of the proposed schools and departments and use it as a reference for selecting the school of their choice that is most suitable for them.

[1060] Specific examples

[1061] Example 1: When a user enters a practice test result

[1062] The user inputs their mock test scores of "Mathematics: 85 points, English: 90 points, Japanese: 75 points," their desired faculty of study as "Information Engineering," and their desired field as "AI." The emotion engine analyzes the user's facial expressions and voice and determines that the user is relaxed.

[1063] Example 2: Server passes data to generative AI model and emotion engine

[1064] The server sends the received mock test results, desired information, and emotional data to the generative AI model and emotion engine, and receives the analysis results from each. If the generative AI model identifies "math" and "English" as areas of expertise and the emotion engine detects negative emotions, it will include advice on stress reduction in the proposal.

[1065] Example 3: When the server suggests a preferred school

[1066] The server searches a database of schools of choice based on the analysis results and emotional data, and lists schools and departments with high acceptance rates, taking into account question trends and exam information. If negative emotions are detected, the server suggests more realistic schools, and if positive emotions are detected, it suggests more challenging schools.

[1067] In this way, the present invention is a system that can suggest specific and realistic schools of choice that reflect a student's strengths and take into consideration their emotional state, allowing students to choose their schools with confidence and increasing their chances of being accepted.

[1068] The processing flow will be explained below.

[1069] Step 1:

[1070] The user accesses the input form on the device. The user enters information such as the scores for each subject in the mock exam, the desired faculty, and the field of study. At the same time, the device collects the user's facial expressions and voice to pass to the emotion engine. Once the input is complete, the user clicks the send button to send the data to the server.

[1071] Specific behavior:

[1072] A user enters the following scores into a web form: Math: 85 points, English: 90 points, Japanese: 75 points.

[1073] The user selects "Information Engineering" as the desired faculty and "AI" as the desired field.

[1074] The user's facial expressions and voice are recorded using a camera and microphone, and the emotion engine is prepared to analyze them.

[1075] The user clicks the submit button.

[1076] Step 2:

[1077] The server receives the mock test result data, desired information, and emotion data sent by the user. The server validates the received data to ensure that the format and value range are correct.

[1078] Specific behavior:

[1079] The server receives the data in JSON format.

[1080] Validate each field of data (e.g., "Math: 85 points").

[1081] If invalid data is included, an error message is generated and returned to the user.

[1082] Step 3:

[1083] The server stores the validated data in a database, which is used later for analysis.

[1084] Specific behavior:

[1085] The server converts the data into the appropriate format and stores it in the database.

[1086] Check that the data has been saved.

[1087] A save completion response is sent to the user's terminal.

[1088] Step 4:

[1089] The server sends the saved data to the generative AI model, which analyzes the mock test results to identify the student's strengths and areas of expertise, and returns the analysis results to the server.

[1090] Specific behavior:

[1091] The server retrieves the data from the database and sends it to the generative AI model.

[1092] The generative AI model analyzes the scores for each subject and identifies "Mathematics" and "English" as areas of strength.

[1093] The AI ​​model sends the analysis results back to the server.

[1094] Step 5:

[1095] The server sends the emotion data to the emotion engine, which analyzes the user's facial expressions and voice to identify the user's emotional state and returns the analysis results to the server.

[1096] Specific behavior:

[1097] The server sends the emotion data to the emotion engine.

[1098] The emotion engine analyzes facial and voice data to identify the user's emotional state (e.g., negative, positive).

[1099] The emotion engine sends the analysis results back to the server.

[1100] Step 6:

[1101] The server receives the analysis results of the generative AI model and the emotion data from the emotion engine, and generates optimal recommendations for schools and departments to apply to. These recommendations also take into account past exam question analysis data and exam dates.

[1102] Specific behavior:

[1103] The server integrates and analyzes data from the generative AI model and the emotion engine.

[1104] If the emotional state is negative, include advice on reducing stress.

[1105] If they are positive, we will make suggestions for challenging schools to apply to.

[1106] Generate a list of suggestions including "Information Engineering Department at University A" and "AI major at University B."

[1107] Step 7:

[1108] The server sends the proposal results to the user terminal, which receives the proposal results and displays them on the screen.

[1109] Specific behavior:

[1110] The server generates the proposal results in JSON format.

[1111] The proposal results are transmitted to the user terminal.

[1112] The content received by the user's device is displayed. For example, detailed information about "University A's Department of Information Engineering" and "University B's AI major" is displayed on the screen.

[1113] Step 8:

[1114] Users can check the proposed results and use them as reference material to select the school that best suits them.

[1115] Specific behavior:

[1116] The user checks the proposed results displayed on the screen in detail.

[1117] If necessary, click on each school or faculty to view detailed information.

[1118] Select your preferred school based on the suggested results.

[1119] Example 2

[1120] 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."

[1121] Traditional career suggestion systems based on mock exam results focus on analyzing students' areas of expertise, but do not take into account the student's emotional state. As a result, they are unable to provide appropriate advice when students feel stressed or anxious, which can lead to ineffective career choices. Furthermore, these systems tend to offer uniform suggestions, and flexible support tailored to each student's emotional state and aspirations is needed.

[1122] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1123] In this invention, the server includes means for receiving and storing mock test result data, means for analyzing the mock test result data and identifying the student's areas of expertise, means for suggesting the most suitable school and department of choice based on the student's areas of expertise, and means for analyzing the user's emotions and generating suggestions according to the user's emotional state. This makes it possible to suggest a career path that takes into account not only the student's areas of expertise but also their emotional state.

[1124] "Mock test result data" refers to data that includes information related to the scores for individual subjects and total scores of mock tests taken by students, or grades.

[1125] "Means for receiving and storing" refers to a device or function that receives data transmitted from a user terminal and stores it in a database or other storage device.

[1126] "Means for analyzing and identifying" refers to devices or algorithms that process and analyze given data to derive specific information or results.

[1127] "Means for suggesting preferred schools and departments" refers to devices or functions that suggest the most suitable school to attend (preferred school) and field of study (department) to students based on the analysis results obtained.

[1128] "Means for analyzing emotions" refers to devices or algorithms that analyze a user's facial expressions and voice data to determine the user's emotional state.

[1129] The term "means for generating suggestions according to emotional state" refers to a device or function that takes into account the emotional state of the user and generates advice or suggestions appropriate to that state.

[1130] "Past question analysis data" refers to data that includes information based on the content and trends of exam questions that have been asked in the past, as well as the results of question analysis.

[1131] "Means for considering exam dates" refers to devices or functions that suggest career paths based on students' desired exam schedules and actual exam dates.

[1132] This invention is a system that analyzes mock test results, understands students' areas of expertise and strengths, and then suggests the most suitable schools and departments for them to apply to. This system consists of a user terminal, a server, a generative AI model, and an emotion engine.

[1133] System configuration

[1134] User terminal

[1135] The user terminal provides an interface for students to input information about their mock exam results, desired faculty, and field. When the user enters this information into a form and sends it to the server, their facial expressions and voice are simultaneously recorded.

[1136] server

[1137] The server receives mock test results, desired information, and emotional data sent from the user's device and stores this data. The server also provides the stored data to a generative AI model, which analyzes areas of expertise and emotions. Based on the analysis results, the server suggests the most suitable schools and departments to apply to.

[1138] Generative AI Models

[1139] The generative AI model is built using Python's TensorFlow library. It analyzes data provided by the server to identify students' areas of expertise and strengths. It then runs an algorithm based on past exam question analysis data to suggest schools and departments with high acceptance rates.

[1140] Emotion Engine

[1141] The emotion engine uses OpenCV and the Google Cloud Speech-to-Text API to analyze the user's facial expressions and voice during input. From this data, the emotion engine identifies the user's emotional state, determining whether it is positive or negative.

[1142] System Operation

[1143] The system operates as follows: the user enters the results of a mock test into an input form on their device and sends it to the server. The emotion engine captures the user's facial expressions and voice and generates emotion data. The server stores the received data, validates it, and then sends it to the generative AI model and emotion engine. The generative AI model identifies the user's areas of expertise, and the emotion engine determines the user's emotional state. The server then generates optimal recommendations for schools and departments based on the results of these analyses.

[1144] Specific examples

[1145] Example 1: When a user enters a practice test result

[1146] The user inputs their mock test scores of "Mathematics: 85 points, English: 90 points, Japanese: 75 points," their desired faculty of study as "Information Engineering," and their desired field as "AI." The emotion engine analyzes the user's facial expressions and voice and determines that the user is relaxed.

[1147] Example 2: Server passes data to generative AI model and emotion engine

[1148] The server sends the received mock test results, preference information, and emotional data to the generative AI model and emotion engine, and receives the analysis results from each. If the generative AI model identifies "math" and "English" as strong subjects and the emotion engine detects positive emotions, it will include suggestions for challenging schools of choice.

[1149] Example 3: When the server suggests a preferred school

[1150] The server searches a database of schools of choice based on the analysis results and emotional data, and takes into account question trends and exam information to create a list of schools and departments with high acceptance rates. If positive emotions are detected, it may suggest challenging schools to choose from.

[1151] Example prompt sentence:

[1152] Mock exam results: Math 85 points, English 90 points, Japanese 75 points

[1153] Preferred Faculty: Information Engineering

[1154] Desired field: AI

[1155] Thus, the mode for carrying out the invention proposes the most suitable school and department of choice for a student, taking into consideration the student's areas of expertise and emotional state, through a series of steps from data entry to analysis and final proposal, allowing the student to choose their preferred school with confidence and increasing their chances of being accepted.

[1156] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1157] Step 1: User enters practice test results

[1158] The user opens the web application on their device. They enter their mock exam subject scores (Mathematics: 85 points, English: 90 points, Japanese: 75 points), their desired faculty (Information Engineering), and their desired field (AI). After completing the input, they click the send button. The input data is sent from the device to the server. At the same time, the emotion engine captures the user's facial expressions and voice through the camera and microphone and generates emotion data.

[1159] Input: mock test results and desired information entered by the user in the input form, facial expressions and voice data

[1160] Output: Mock test result data, preference information, and emotion data sent to the server

[1161] Step 2: The server receives and stores the data

[1162] The server receives the mock test result data, desired information, and emotion data sent from the user's device. Firewalls and data validation functions are used to check the security and accuracy of the received data. Once validated, the data is stored in a database.

[1163] Input: Received mock test result data, desired information, emotional data

[1164] Output: Mock test results data, preference information, and emotion data stored in the database

[1165] Step 3: Analyze the data with a generative AI model

[1166] The server sends the stored data to the generative AI model, which uses Python's TensorFlow library to analyze the data and identify the student's areas of expertise and strengths. "Mathematics" and "English" are identified as areas of expertise. The analysis results are then sent back to the server.

[1167] Input: Mock test result data, desired information, and emotional data stored in the database

[1168] Output: Information on areas of expertise and strengths after analysis by the generative AI model

[1169] Step 4: Emotional state analysis by the emotion engine

[1170] The server sends the emotion data to the emotion engine, which uses OpenCV and the Google Cloud Speech-to-Text API to analyze the user's facial expressions and voice. A positive emotional state is identified as a result of the analysis and sent back to the server.

[1171] Input: Received emotion data

[1172] Output: Emotional state information after analysis

[1173] Step 5: The server generates school recommendations

[1174] The server receives the analysis results of the AI ​​model and the emotional state of the emotion engine, and generates optimal recommendations for schools and departments. The recommendations also take into account past exam question analysis data and exam schedule information. Challenging schools suited to a positive emotional state can also be included in the recommendations.

[1175] Input: Analyzed areas of expertise and strengths, emotional state information

[1176] Output: Suggested best schools and departments

[1177] Step 6: User confirms the proposed results

[1178] The server sends the proposed results to the user's device. The user's device receives the proposed results and displays them on the screen. The user can check the detailed information of the proposed schools and departments and use it as a reference for selecting the school of their choice that best suits them.

[1179] Input: Suggested best school and department information

[1180] Output: Suggestion results displayed on the user's device

[1181] The above is the specific flow of the system's program processing, and the detailed operations at each step are clarified.

[1182] (Application example 2)

[1183] 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."

[1184] Conventional systems for suggesting preferred schools and departments make suggestions based solely on students' mock exam results. However, this system cannot take into account the student's individual psychological state, such as their emotional state or stress level at the time, which can affect the accuracy of the suggestions and the student's motivation. Therefore, it is necessary for students to study in a relaxed state and receive appropriate advice.

[1185] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1186] In this invention, the server includes means for receiving and saving mock test result data, means for analyzing the mock test result data and identifying the student's areas of expertise, means for proposing the most suitable school and department of choice based on the student's areas of expertise, means for recognizing and saving the user's emotional data, and means for analyzing the emotional data and adjusting the content of the proposal based on the user's emotional state. This makes it possible to propose appropriate and personalized schools and departments of choice that take into account the student's emotional state as well as their academic ability data.

[1187] "Mock exam result data" refers to data relating to the scores and grades obtained by students in each subject in the mock exam.

[1188] A "strength area" is an area of ​​study or subject in which a student shows particular ability or interest.

[1189] "Preferred school" refers to the educational institution that a student wishes to attend.

[1190] A "faculty" is a unit of education and research established for each academic field at a university or higher education institution.

[1191] "Emotion data" is information about emotions acquired from the user's facial expressions, voice, etc.

[1192] "Emotional state" refers to the positive or negative mental state or emotion that a user is currently experiencing.

[1193] A "generative AI model" is an artificial intelligence algorithm that analyzes input data and generates optimal suggestions based on the user's areas of expertise.

[1194] A "prompt sentence" is a specific input sentence that a generative AI model uses to generate suggestions.

[1195] This invention combines a system that analyzes mock test results data, understands a student's areas of expertise and strengths, and then suggests the most suitable school or department to apply to with an emotion engine that recognizes the user's emotions.The system of this invention is mainly composed of a user terminal, a server, a generative AI model, and an emotion engine.

[1196] First, the user device provides an interface for students to input their mock exam results and information about their desired faculty and field. The user enters this information into a form on the device and sends it to the server. Data is also collected from the user's facial expressions and voice when entering information, which the emotion engine analyzes. Furthermore, hardware such as a webcam and microphone is required to acquire emotion data.

[1197] The server then receives and stores the mock test results, desired information, and emotional data sent from the user's device. The server validates the received data to ensure that the format and value range are correct. The server then analyzes this data using a generative AI model. The generative AI model is implemented using a programming language such as Python and includes past question analysis data and algorithms for identifying schools and departments with high pass rates.

[1198] The emotion engine analyzes the user's facial expressions and voice when inputting information to identify the user's emotional state. It uses the EmotionEngine library to determine whether the user is relaxed or stressed. The server combines the emotion data obtained from the emotion engine with the analysis results of the generative AI model to generate optimal recommendations for schools and departments.

[1199] For example, if a user inputs their mock exam scores and indicates that they want to study computer engineering and AI, the emotion engine analyzes their facial expressions and voice and determines that they are relaxed. The server then uses a generative AI model to analyze this data and identify their strengths in math and English. If the user's emotional state is positive, the engine returns results that include suggestions for challenging schools.

[1200] Examples of specific prompts include:

[1201] "User entered mock test results: Math 85, English 90, Japanese 75. Desired department: Computer Engineering. Desired field: AI. Emotional state: Relaxed."

[1202] In this way, the system of the present invention can integrate and analyze a student's academic ability data and emotional data, and can suggest the most suitable schools and departments for each student, allowing students to select their preferred schools with greater confidence.

[1203] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1204] Step 1:

[1205] The user enters the results of the mock exam and the desired faculty and field.

[1206] Input: Mock exam scores by subject, desired faculty information, desired field information

[1207] Output: The entered data is collected from the terminal

[1208] Specific operation: The user enters grade information such as "Math: 85 points, English: 90 points, Japanese: 75 points" and a desired field such as "Information Engineering" or "AI" into the form on the device, and presses the submit button. At this time, the user's facial expressions and voice are collected using the device's webcam and microphone.

[1209] Step 2:

[1210] The emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[1211] Input: User's facial expression data, voice data

[1212] Output: Emotion data (e.g., relaxed, nervous, etc.)

[1213] How it works: Facial and voice data collected on the device is analyzed by the EmotionEngine library to identify the user's emotional state, for example, determining whether the user is relaxed or tense.

[1214] Step 3:

[1215] The server receives and stores the mock test result data, desired information, and emotion data.

[1216] Input: mock test results, desired faculty information, desired field information, emotional data

[1217] Output: User data stored in the database

[1218] Specific operation: Data sent from the user terminal is sent to the server, which validates the data to ensure it is in the correct format and stores it in the database.

[1219] Step 4:

[1220] The server sends the data to the generated AI model, which analyzes the student's areas of expertise and the best schools and departments to apply to.

[1221] Input: Saved user data (mock test results, preferences, emotional data)

[1222] Output: Analysis results from the generative AI model (areas of expertise, preferred schools and departments)

[1223] How it works: The server inputs the saved data into a generative AI model implemented in Python to identify areas of strength in each subject. It also uses past question analysis data to calculate schools and departments with high pass rates.

[1224] Step 5:

[1225] The server adjusts the suggestions based on the emotional data.

[1226] Input: Analysis results of generative AI model, emotion data

[1227] Output: Recommendations for the best schools and departments to apply to based on the emotional state

[1228] How it works: The server reviews the analysis results returned by the generative AI model and adjusts the suggestions based on the data from the emotion engine. For example, if the emotion data is positive, it will suggest more challenging schools, and if it is negative, it will make more realistic suggestions.

[1229] Step 6:

[1230] The server sends the final proposal of preferred schools and departments to the user's device.

[1231] Input: Suggestion data according to emotional state

[1232] Output: User device showing the proposed results

[1233] Specific operation: The server generates a list of the most suitable schools and departments according to the user's emotional state and sends it to the user's device. The user's device then displays this information on the screen so that the user can confirm it.

[1234] This makes it possible to integrate mock test results data with emotional data to suggest the most suitable schools and departments for students to apply to.

[1235] 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.

[1236] 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.

[1237] 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.

[1238] [Fourth embodiment]

[1239] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1240] 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.

[1241] 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).

[1242] 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.

[1243] 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.

[1244] 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).

[1245] 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.

[1246] 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.

[1247] 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.

[1248] 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.

[1249] 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.

[1250] 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.

[1251] 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."

[1252] This invention relates to a system that analyzes mock exam responses, understands students' areas of expertise and strengths, and then suggests the most suitable schools and departments for them to apply to. This system is primarily composed of a user terminal, a server, and a generative AI model.

[1253] System Overview

[1254] User terminal

[1255] The user terminal provides an interface for students to input their mock exam results and information about their desired faculty and field. The user enters this information into a form and sends it to the server.

[1256] server

[1257] The server receives and stores mock test results and desired information sent from the user's device. It then passes the stored data to a generative AI model, which analyzes the model's areas of expertise. It also has the function of suggesting the most suitable schools and departments based on the analysis results.

[1258] Generative AI Models

[1259] The generative AI model analyzes data provided by the server to identify students' strengths and areas of expertise, and then runs an algorithm to suggest schools and departments with high success rates based on past exam question analysis data.

[1260] Program processing

[1261] 1. User enters mock test results

[1262] The user enters the subject scores for the mock exam, the desired faculty, and the field of study into the input form on the terminal. After completing the input, the user presses a button to send the data to the server.

[1263] 2. The server receives and stores the data

[1264] The server receives the data submitted by the user, validates it to ensure it is in the correct format and has the correct value range, and then stores it in the database.

[1265] 3. Analysis using generative AI models

[1266] The server sends the stored data to the generative AI model, which analyzes the data to identify the student's areas of expertise and strengths, and returns the analysis results to the server.

[1267] 4. The server generates a list of schools of interest

[1268] The server receives the analysis results from the generative AI model and uses them to generate optimal recommendations for schools and departments, taking into account past question analysis data and exam dates. The recommendations are then sent to the user's device.

[1269] 5. The user checks the proposed results

[1270] The user's device receives the proposed results from the server and displays them on the screen. The user can then check the details of the proposed schools and departments and use them as a reference for selecting the school of their choice that best suits them.

[1271] Specific examples

[1272] Example 1: When a user enters a practice test result

[1273] The user enters that their mock test scores are "Mathematics: 85 points, English: 90 points, Japanese: 75 points," that their desired faculty is "Information Engineering," and that their desired field is "AI."

[1274] Example 2: When a server uses a generative AI model to analyze data

[1275] The server sends the received mock test results and desired faculty and field information to the generating AI model, and receives the analysis result that "Mathematics" and "English" are strengths.

[1276] Example 3: When the server suggests a preferred school

[1277] Based on the analysis results and exam information, the server will suggest several universities with "information engineering" departments with high acceptance rates. For example, specific preferred schools such as "Information Engineering Department at University A" or "AI major at University B" will be presented.

[1278] In this way, the present invention is a system that can suggest specific and realistic schools of choice that reflect a student's strengths, allowing students to choose their schools with confidence and increasing their chances of being accepted.

[1279] The processing flow will be explained below.

[1280] Step 1:

[1281] The user accesses the input form on the device. The user enters the scores for each subject in the mock exam, as well as the desired faculty and field. Once the input is complete, the user clicks the send button to send the data to the server.

[1282] Specific behavior:

[1283] A user enters the following scores into a web form: Math: 85 points, English: 90 points, Japanese: 75 points.

[1284] The user selects "Information Engineering" as the desired faculty and "AI" as the desired field.

[1285] The user clicks the submit button.

[1286] Step 2:

[1287] The server receives the mock test result data sent by the user. The server validates the received data to ensure that the format and value range are correct.

[1288] Specific behavior:

[1289] The server receives the data in JSON format.

[1290] Validate each field of data (e.g., "Math: 85 points").

[1291] If invalid data is included, an error message is generated and returned to the user.

[1292] Step 3:

[1293] The server stores the validated data in a database, which is used later for analysis.

[1294] Specific behavior:

[1295] The server converts the data into the appropriate format and stores it in the database.

[1296] Check that the data has been saved.

[1297] A save completion response is sent to the user's terminal.

[1298] Step 4:

[1299] The server sends the saved data to the generative AI model, which analyzes the mock test results to identify the student's strengths and areas of expertise, and returns the analysis results to the server.

[1300] Specific behavior:

[1301] The server sends the mock test results and desired information to the AI ​​model.

[1302] The generative AI model analyzed the scores for each subject and identified that "Mathematics" and "English" were the student's areas of strength.

[1303] The AI ​​model sends the analysis results back to the server.

[1304] Step 5:

[1305] The server receives the analysis results from the generative AI model and generates optimal recommendations for schools and departments, taking into account past exam question analysis data and exam dates.

[1306] Specific behavior:

[1307] The server searches the database of the desired school based on the analysis results.

[1308] We have compiled a list of schools and faculties with high pass rates based on question trends and examination information.

[1309] The proposals selected were "The Department of Information Engineering at University A" and "The AI ​​major at University B."

[1310] Step 6:

[1311] The server sends the proposal results to the user terminal, which receives the proposal results and displays them on the screen.

[1312] Specific behavior:

[1313] The server generates the proposal results in JSON format.

[1314] The proposal results are sent to the user's device.

[1315] The user's device displays the received information. For example, desired schools such as "Information Engineering Department at University A" or "AI major at University B" are displayed on the screen.

[1316] Step 7:

[1317] Users can check the proposed results and use them as reference material to select the school that best suits them.

[1318] Specific behavior:

[1319] The user can check the details of the proposed results displayed on the screen.

[1320] If necessary, click on each school or faculty for more information.

[1321] Select your preferred school based on the proposed results.

[1322] Example 1

[1323] 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."

[1324] Conventional mock exam systems simply saved test results, but did not have the functionality to identify students' areas of expertise or suggest the most suitable schools or departments based on those areas. This made it difficult for students to understand their strengths and select schools that would utilize those strengths. Furthermore, specific suggestions that took into account past exam trends and exam dates were also insufficient.

[1325] 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.

[1326] In this invention, the server includes a means for inputting and transmitting mock test result data and desired field data from a terminal, a means for receiving and storing the mock test result data and desired field data, a means for identifying a student's areas of expertise using a generative AI model that analyzes the mock test result data and desired field data, and a means for proposing the most suitable school and department of interest based on the student's areas of expertise and taking into account past question analysis data and exam dates. This allows students to select the most suitable school of their choice by utilizing their own strengths.

[1327] A "terminal" is a device through which a user inputs mock test result data and desired domain data and transmits them to a server.

[1328] "Mock exam result data" refers to the subject-specific scores and other evaluation information obtained by students in the mock exam.

[1329] "Desired field data" refers to information about the faculty the student is applying to and the field that will be analyzed.

[1330] "Means for transmission" refers to the interface or protocol for transmitting data from the terminal to the server.

[1331] "Means for receiving and storing" refers to the function by which the server receives data sent from the terminal and stores it in a storage device such as a database.

[1332] A "generative AI model" refers to an artificial intelligence algorithm that analyzes incoming data and identifies students' areas of expertise and strengths.

[1333] The "means of identifying areas of expertise" is a function that uses a generative AI model to analyze students' test result data and extract the subjects and areas in which the student excels.

[1334] "Past question analysis data" refers to data that includes analysis results such as question trends and question difficulty of exams that have been conducted in the past.

[1335] "Exam Schedule" refers to the dates or schedule of exams that a student plans to take.

[1336] "Means to suggest schools and departments of choice" is a function that suggests the most suitable schools and departments to students by taking into consideration the analysis results of the generative AI model, past question analysis data, and exam dates.

[1337] "System" refers to the overall system consisting of the terminal, server, and generative AI model.

[1338] This invention relates to a system that analyzes mock exam responses, understands a student's areas of expertise and strengths, and then suggests the most suitable schools and departments for them to apply to. This system is primarily composed of a user terminal, a server, and a generative AI model.

[1339] The user terminal provides an interface for entering mock test results and information about the desired faculty and field. When the user enters this information into a form and presses the submit button, the data is sent to the server. The terminal uses a standard web browser or dedicated application software.

[1340] The server has the function of receiving and saving the mock test result data and desired domain data sent from the user terminal. The server uses a database to manage and save this data, and also performs validation. Validation is the process of checking whether the format and value range of the received data are correct. Data is saved in the database only if validation is successful.

[1341] The server then sends the stored data to a generative AI model, which analyzes the data and identifies the student's areas of expertise and strengths. The generative AI model uses machine learning algorithms to analyze patterns and characteristics of test results. For example, if a student scores high in math, it determines that the student is good at math. The results of this analysis are then sent back to the server.

[1342] The server generates optimal recommendations for schools and departments based on the analysis results from the generative AI model. The server also takes into account past exam question analysis data and exam dates. For example, a student with high scores in math and English will be suggested departments and universities that emphasize these subjects. These recommendations are then sent to the user's device.

[1343] The user terminal receives the recommendation results from the server and displays them on the screen. The user can check this information and use it as a reference for selecting the school of their choice that is most suitable for them.

[1344] Specific examples

[1345] For example, consider the case where a user enters a practice test score as follows:

[1346] Example input:

[1347] Mathematics: 85 points

[1348] English: 90 points

[1349] Japanese: 75 points

[1350] Preferred Faculty: Information Engineering

[1351] Desired field: AI

[1352] When the user enters this information and presses the send button, the data is sent to the server.

[1353] The server then sends the received data to the generative AI model, which returns the result that "Mathematics" and "English" are the user's strengths. Based on this result, the server suggests several schools with "Information Engineering" departments that have high acceptance rates. Specifically, the user is presented with specific schools of choice, such as "Information Engineering Department at University A" or "AI major at University B."

[1354] In this way, users can select the school of their choice that best reflects their strengths.

[1355] Example prompt sentence:

[1356] "My mock test results are 'Math: 85 points, English: 90 points, Japanese: 75 points'. I would like to study 'Information Engineering' and my preferred field is 'AI'. Based on this information, please suggest my areas of expertise and the best schools for me to apply to."

[1357] This allows students to choose their preferred school with confidence and increases their chances of being accepted.

[1358] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1359] Step 1:

[1360] The user uses the terminal to input the result data of the mock test and the desired domain data.

[1361] Input: The user enters "Mathematics: 85 points, English: 90 points, Japanese: 75 points", desired faculty "Information Engineering", and desired field "AI".

[1362] Action: The user enters this data into the input form and presses the "Submit" button.

[1363] Output: Data entered from the terminal is sent to the server.

[1364] Step 2:

[1365] The server receives the data sent from the terminal and validates the data.

[1366] Input: Practice test results and desired domain data sent from the terminal.

[1367] Behavior: The server validates the data received, ensuring it is in the correct format and range of values, e.g., checking that the score is between 0 and 100.

[1368] Output: If validation is successful, the data is saved to the database. If validation fails, an error message is generated.

[1369] Step 3:

[1370] The server sends the stored data to the generative AI model and begins analysis.

[1371] Input: Practice test results stored in the database and desired domain data.

[1372] How it works: The server sends the stored data to the generative AI model, which analyzes it and identifies the student's strengths and areas of expertise. Based on a specific algorithm, it may determine that math and English are strong subjects, for example.

[1373] Output: The analysis result is returned to the server, for example, "Strengths: Math and English."

[1374] Step 4:

[1375] Based on the analysis results, the server generates suggestions for the most suitable schools and departments to apply to.

[1376] Input: Analysis results from the generative AI model (areas of expertise), past question analysis data, and exam dates.

[1377] How it works: The server selects the department or university with the highest pass rate, taking into account past exam question analysis data and exam dates. For example, it identifies specific desired schools, such as "University A's Department of Information Engineering" or "University B's AI major."

[1378] Output: The best possible school and department recommendations are generated and sent to the user's device.

[1379] Step 5:

[1380] The user terminal displays the proposal results received from the server so that the user can check them.

[1381] Input: Suggested school and department choices sent from the server.

[1382] Operation: The user's device displays the received recommendations on the screen. The user can then check the details of each school and use them as a reference to select the school that best suits them.

[1383] Output: Display of the proposed results, allowing the user to select specific schools of choice.

[1384] (Application example 1)

[1385] 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."

[1386] Currently, support systems exist for selecting schools and majors based on mock exam results, but they are often limited to physical interfaces and lack flexibility. Users must also expend considerable effort to obtain detailed information about the schools and majors they are considering. Furthermore, they lack visual support for determining how well the proposed information suits them. This can make it difficult for students to obtain sufficient information to make optimal choices, resulting in reduced accuracy in career choices.

[1387] 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.

[1388] In this invention, the server includes means for receiving and storing mock test result data, means for analyzing the mock test result data and identifying the student's areas of expertise, means for suggesting the most suitable educational destination and specialty based on the student's areas of expertise, means for inputting the mock test results into an interface of a smartphone or tablet, and means for a user to check detailed information about the educational destination and specialty using a virtual reality headset. This allows students to easily input their mock test results, receive specific and optimal career suggestions based on analysis by the generative AI model, and check detailed information through virtual reality.

[1389] A "mock test" is a test that students take to measure their academic ability level before taking the exam.

[1390] "Result data" refers to information regarding the scores and grades for each subject obtained after taking the mock test.

[1391] A "strength area" is an area in which a student excels significantly over other areas, based on the results of mock exams.

[1392] "School destination" refers to the educational institution, such as a university or vocational school, that a student aims to attend after graduating from high school.

[1393] A "specialty" is a specific academic field that a student wishes to study at their future university.

[1394] "Proposal methods" are methods or systems that show students the most suitable schools and fields of specialization based on the analysis results.

[1395] An "interface" is a means such as an operation screen or input device that allows a user to interact with a system.

[1396] A "smartphone" is a mobile phone with advanced computing and communication capabilities.

[1397] A "tablet" is a small, portable computer that uses a touchscreen as its primary input means.

[1398] A "virtual reality headset" is a device that allows a user to have an immersive virtual reality experience.

[1399] A "generative AI model" is an artificial intelligence modeling technique designed to perform specific tasks based on training data.

[1400] This invention relates to a system that analyzes mock exam results, understands students' strengths and areas of expertise, and then suggests the most suitable educational destination and field of specialization. This system is primarily composed of a user terminal, a server, and a generative AI model.

[1401] System Program

[1402] The system has the following features:

[1403] 1. Enter your mock test results:

[1404] The user device provides an interface for students to input mock exam results and information about their desired specialization. Students use their smartphones or tablets to input their mock exam scores for each subject, as well as their desired school and specialization.

[1405] 2. Receiving and storing data:

[1406] The server receives and stores the mock test result data and desired information sent from the user terminal.

[1407] 3. Analysis process:

[1408] The server sends the stored data to the generative AI model, which analyzes the received data and identifies the student's areas of expertise and strengths. Specifically, it analyzes the data based on past problem analysis data to identify areas of expertise.

[1409] 4. Proposal of further education and specialization:

[1410] The server receives the analysis results from the generative AI model and uses them to suggest optimal educational destinations and specializations, and can provide detailed information to users through a virtual reality headset.

[1411] Specific usage

[1412] Example 1: User enters practice test results

[1413] A user inputs the results of a mock test using a smartphone. For example, suppose the results are "Mathematics: 85 points, English: 90 points, Japanese: 75 points," and the desired field of specialization is "Information Engineering." This information is sent from the user's device to the server.

[1414] Example 2: Data processing and analysis

[1415] The server sends the received mock test results and desired field of study information to the generative AI model, which analyzes the data and identifies that the student's strengths are "Mathematics" and "English."

[1416] Example 3: Suggesting further education

[1417] Based on the analysis results, the server will suggest the most suitable university and specialty. For example, it will suggest "University A, Department of Information Engineering" and "University B, Department of AI" as universities where users can study "Information Engineering." Using a virtual reality headset, users can visually check detailed information about these universities and majors.

[1418] Example prompt sentence:

[1419] Users input their mock test results, and the generative AI model analyzed them to identify their strengths in mathematics and English. Based on this, it suggested a path to further study in information engineering.

[1420] In this way, the present invention is a system that can suggest specific and realistic educational destinations that reflect a student's strengths, allowing students to choose their educational destinations with confidence and increasing the chances of being accepted.

[1421] As specific hardware and software examples, smartphones and tablets are used as user devices, and servers equipped with generative AI models are used for analysis processing. Virtual reality headsets are useful for providing detailed visual information.

[1422] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1423] Step 1:

[1424] Users input their mock test results using a smartphone or tablet. Specifically, they use a dedicated application to enter their subject scores, such as "Mathematics: 85 points, English: 90 points, Japanese: 75 points," as well as their desired field of specialization, such as "Information Engineering." This input information is sent to the server in JSON format or similar.

[1425] Step 2:

[1426] The server receives the data sent from the user terminal and saves it in the database. Here, the data is first validated. To ensure that the data format is consistent and that the value is within a range, for example, it checks whether "Math: 85 points" is within the range of 0 to 100. If the data is valid, it is saved in the database.

[1427] Step 3:

[1428] The server sends the stored data to a generative AI model. This AI model has been trained in advance on a large amount of past question analysis data and has an analysis algorithm for specific input data. Specifically, using mock test results and desired specialization data, students input their scores for each subject and their desired specialization, and the data is processed and calculated based on that to identify the student's areas of expertise and strengths.

[1429] Step 4:

[1430] The generative AI model returns the analysis results to the server. Specifically, the analysis results show that "math" and "English" are strong subjects based on the input mock test results, and the results are sent back to the server. The server receives this and uses the results to create a list of optimal schools and specializations.

[1431] Step 5:

[1432] The server generates suggestions for schools and specializations, taking into account past exam analysis data, entrance exam dates, and the exam trends of the schools. For example, for a student who excels in math and English and is interested in information engineering, specific schools such as "Information Engineering Department at University A" or "AI Major at University B" will be listed.

[1433] Step 6:

[1434] Users can use a virtual reality headset to view detailed information about proposed schools and majors. This allows them to visually experience the campus atmosphere and curriculum content, providing a deeper understanding. Viewing detailed information about schools using a virtual reality headset can help students decide whether a school is right for them.

[1435] The specific actions taken at each step are as follows:

[1436] Step 1: The user enters the results of the mock test into the application's input form and presses the submit button. The input is sent from the smartphone or tablet to the server.

[1437] Step 2: The server checks the format and range of the data received, and if there are no problems, stores it in the database.

[1438] Step 3: The server sends the stored data to the generative AI model, which then analyzes the data.

[1439] Step 4: The generative AI model sends the analysis results back to the server, which receives the results and generates recommendations for further education and specialization.

[1440] Step 5: The server creates a list of optimal educational destinations and fields of specialization based on the analysis results and sends it to the user.

[1441] Step 6: The user uses a virtual reality headset to visually review the details of the proposed education and specialization.

[1442] 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.

[1443] This invention combines a system that analyzes mock test results, understands a student's areas of expertise and strengths, and then suggests the most suitable schools and departments to apply to with an emotion engine that recognizes the user's emotions. This system is primarily composed of a user terminal, a server, a generative AI model, and an emotion engine.

[1444] System Overview

[1445] User terminal

[1446] The user terminal provides an interface for students to input their mock exam results and information about their desired faculty and field. The user enters this information into a form and sends it to the server. Data is also collected from the user's facial expressions and voice when entering information, allowing the emotion engine to analyze it.

[1447] server

[1448] The server receives and stores mock test results, desired information, and emotional data sent from the user's device. It then passes the stored data to a generative AI model, which analyzes the user's areas of expertise and emotions. It also has the function of suggesting the most suitable schools and departments based on the analysis results.

[1449] Generative AI Models

[1450] The generative AI model analyzes data provided by the server to identify students' strengths and areas of expertise, and then runs an algorithm to suggest schools and departments with high success rates based on past exam question analysis data.

[1451] Emotion Engine

[1452] The emotion engine analyzes the user's facial expressions and voice when inputting information to identify the user's emotional state. The acquired emotional data is reflected in the content of suggestions, providing advice and suggestions that correspond to the student's emotional state.

[1453] Program processing

[1454] 1. User enters mock test results

[1455] The user enters their mock exam subject scores and desired faculty and field into the input form on the device. Once the user has completed the input, they press a button to send the data to the server. At the same time, the emotion engine analyzes the user's facial expressions and voice to collect emotional data.

[1456] 2. The server receives and stores the data

[1457] The server receives the mock test result data, preference information, and emotion data sent by the user. The server validates the received data to ensure that the format and value range are correct. Then, it stores the data in the database.

[1458] 3. Analysis using generative AI models

[1459] The server sends the stored data to the generative AI model, which analyzes the data, identifies the student's areas of expertise and strengths, and returns the analysis results to the server, taking into account the emotional data obtained.

[1460] 4. Analysis by Emotion Engine

[1461] The server sends the emotion data to the emotion engine, which analyzes the user's emotional state and determines whether the state is negative or positive.

[1462] 5. The server generates a list of schools of interest

[1463] The server receives the analysis results of the generative AI model and the emotion data from the emotion engine, and generates optimal recommendations for schools and departments. The recommendations also take into account past exam question analysis data and exam dates. If the emotional state is negative, the server includes advice on how to reduce stress, and if the emotional state is positive, the server includes recommendations for challenging schools.

[1464] 6. The user checks the proposed results

[1465] The server sends the proposed results to the user's device. The user's device receives the proposed results and displays them on the screen. The user can check the detailed information of the proposed schools and departments and use it as a reference for selecting the school of their choice that is most suitable for them.

[1466] Specific examples

[1467] Example 1: When a user enters a practice test result

[1468] The user inputs their mock test scores of "Mathematics: 85 points, English: 90 points, Japanese: 75 points," their desired faculty of study as "Information Engineering," and their desired field as "AI." The emotion engine analyzes the user's facial expressions and voice and determines that the user is relaxed.

[1469] Example 2: Server passes data to generative AI model and emotion engine

[1470] The server sends the received mock test results, desired information, and emotional data to the generative AI model and emotion engine, and receives the analysis results from each. If the generative AI model identifies "math" and "English" as areas of expertise and the emotion engine detects negative emotions, it will include advice on stress reduction in the proposal.

[1471] Example 3: When the server suggests a preferred school

[1472] The server searches a database of schools of choice based on the analysis results and emotional data, and lists schools and departments with high acceptance rates, taking into account question trends and exam information. If negative emotions are detected, the server suggests more realistic schools, and if positive emotions are detected, it suggests more challenging schools.

[1473] In this way, the present invention is a system that can suggest specific and realistic schools of choice that reflect a student's strengths and take into consideration their emotional state, allowing students to choose their schools with confidence and increasing their chances of being accepted.

[1474] The processing flow will be explained below.

[1475] Step 1:

[1476] The user accesses the input form on the device. The user enters information such as the scores for each subject in the mock exam, the desired faculty, and the field of study. At the same time, the device collects the user's facial expressions and voice to pass to the emotion engine. Once the input is complete, the user clicks the send button to send the data to the server.

[1477] Specific behavior:

[1478] A user enters the following scores into a web form: Math: 85 points, English: 90 points, Japanese: 75 points.

[1479] The user selects "Information Engineering" as the desired faculty and "AI" as the desired field.

[1480] The user's facial expressions and voice are recorded using a camera and microphone, and the emotion engine is prepared to analyze them.

[1481] The user clicks the submit button.

[1482] Step 2:

[1483] The server receives the mock test result data, desired information, and emotion data sent by the user. The server validates the received data to ensure that the format and value range are correct.

[1484] Specific behavior:

[1485] The server receives the data in JSON format.

[1486] Validate each field of data (e.g., "Math: 85 points").

[1487] If invalid data is included, an error message is generated and returned to the user.

[1488] Step 3:

[1489] The server stores the validated data in a database, which is used later for analysis.

[1490] Specific behavior:

[1491] The server converts the data into the appropriate format and stores it in the database.

[1492] Check that the data has been saved.

[1493] A save completion response is sent to the user's terminal.

[1494] Step 4:

[1495] The server sends the saved data to the generative AI model, which analyzes the mock test results to identify the student's strengths and areas of expertise, and returns the analysis results to the server.

[1496] Specific behavior:

[1497] The server retrieves the data from the database and sends it to the generative AI model.

[1498] The generative AI model analyzes the scores for each subject and identifies "Mathematics" and "English" as areas of strength.

[1499] The AI ​​model sends the analysis results back to the server.

[1500] Step 5:

[1501] The server sends the emotion data to the emotion engine, which analyzes the user's facial expressions and voice to identify the user's emotional state and returns the analysis results to the server.

[1502] Specific behavior:

[1503] The server sends the emotion data to the emotion engine.

[1504] The emotion engine analyzes facial and voice data to identify the user's emotional state (e.g., negative, positive).

[1505] The emotion engine sends the analysis results back to the server.

[1506] Step 6:

[1507] The server receives the analysis results of the generative AI model and the emotion data from the emotion engine, and generates optimal recommendations for schools and departments to apply to. These recommendations also take into account past exam question analysis data and exam dates.

[1508] Specific behavior:

[1509] The server integrates and analyzes data from the generative AI model and the emotion engine.

[1510] If the emotional state is negative, include advice on reducing stress.

[1511] If they are positive, we will make suggestions for challenging schools to apply to.

[1512] Generate a list of suggestions including "Information Engineering Department at University A" and "AI major at University B."

[1513] Step 7:

[1514] The server sends the proposal results to the user terminal, which receives the proposal results and displays them on the screen.

[1515] Specific behavior:

[1516] The server generates the proposal results in JSON format.

[1517] The proposal results are transmitted to the user terminal.

[1518] The content received by the user's device is displayed. For example, detailed information about "University A's Department of Information Engineering" and "University B's AI major" is displayed on the screen.

[1519] Step 8:

[1520] Users can check the proposed results and use them as reference material to select the school that best suits them.

[1521] Specific behavior:

[1522] The user checks the proposed results displayed on the screen in detail.

[1523] If necessary, click on each school or faculty to view detailed information.

[1524] Select your preferred school based on the suggested results.

[1525] Example 2

[1526] 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."

[1527] Traditional career suggestion systems based on mock exam results focus on analyzing students' areas of expertise, but do not take into account the student's emotional state. As a result, they are unable to provide appropriate advice when students feel stressed or anxious, which can lead to ineffective career choices. Furthermore, these systems tend to offer uniform suggestions, and flexible support tailored to each student's emotional state and aspirations is needed.

[1528] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1529] In this invention, the server includes means for receiving and storing mock test result data, means for analyzing the mock test result data and identifying the student's areas of expertise, means for suggesting the most suitable school and department of choice based on the student's areas of expertise, and means for analyzing the user's emotions and generating suggestions according to the user's emotional state. This makes it possible to suggest a career path that takes into account not only the student's areas of expertise but also their emotional state.

[1530] "Mock test result data" refers to data that includes information related to the scores for individual subjects and total scores of mock tests taken by students, or grades.

[1531] "Means for receiving and storing" refers to a device or function that receives data transmitted from a user terminal and stores it in a database or other storage device.

[1532] "Means for analyzing and identifying" refers to devices or algorithms that process and analyze given data to derive specific information or results.

[1533] "Means for suggesting preferred schools and departments" refers to devices or functions that suggest the most suitable school to attend (preferred school) and field of study (department) to students based on the analysis results obtained.

[1534] "Means for analyzing emotions" refers to devices or algorithms that analyze a user's facial expressions and voice data to determine the user's emotional state.

[1535] The term "means for generating suggestions according to emotional state" refers to a device or function that takes into account the emotional state of the user and generates advice or suggestions appropriate to that state.

[1536] "Past question analysis data" refers to data that includes information based on the content and trends of exam questions that have been asked in the past, as well as the results of question analysis.

[1537] "Means for considering exam dates" refers to devices or functions that suggest career paths based on students' desired exam schedules and actual exam dates.

[1538] This invention is a system that analyzes mock test results, understands students' areas of expertise and strengths, and then suggests the most suitable schools and departments for them to apply to. This system consists of a user terminal, a server, a generative AI model, and an emotion engine.

[1539] System configuration

[1540] User terminal

[1541] The user terminal provides an interface for students to input information about their mock exam results, desired faculty, and field. When the user enters this information into a form and sends it to the server, their facial expressions and voice are simultaneously recorded.

[1542] server

[1543] The server receives mock test results, desired information, and emotional data sent from the user's device and stores this data. The server also provides the stored data to a generative AI model, which analyzes areas of expertise and emotions. Based on the analysis results, the server suggests the most suitable schools and departments to apply to.

[1544] Generative AI Models

[1545] The generative AI model is built using Python's TensorFlow library. It analyzes data provided by the server to identify students' areas of expertise and strengths. It then runs an algorithm based on past exam question analysis data to suggest schools and departments with high acceptance rates.

[1546] Emotion Engine

[1547] The emotion engine uses OpenCV and the Google Cloud Speech-to-Text API to analyze the user's facial expressions and voice during input. From this data, the emotion engine identifies the user's emotional state, determining whether it is positive or negative.

[1548] System Operation

[1549] The system operates as follows: the user enters the results of a mock test into an input form on their device and sends it to the server. The emotion engine captures the user's facial expressions and voice and generates emotion data. The server stores the received data, validates it, and then sends it to the generative AI model and emotion engine. The generative AI model identifies the user's areas of expertise, and the emotion engine determines the user's emotional state. The server then generates optimal recommendations for schools and departments based on the results of these analyses.

[1550] Specific examples

[1551] Example 1: When a user enters a practice test result

[1552] The user inputs their mock test scores of "Mathematics: 85 points, English: 90 points, Japanese: 75 points," their desired faculty of study as "Information Engineering," and their desired field as "AI." The emotion engine analyzes the user's facial expressions and voice and determines that the user is relaxed.

[1553] Example 2: Server passes data to generative AI model and emotion engine

[1554] The server sends the received mock test results, preference information, and emotional data to the generative AI model and emotion engine, and receives the analysis results from each. If the generative AI model identifies "math" and "English" as strong subjects and the emotion engine detects positive emotions, it will include suggestions for challenging schools of choice.

[1555] Example 3: When the server suggests a preferred school

[1556] The server searches a database of schools of choice based on the analysis results and emotional data, and takes into account question trends and exam information to create a list of schools and departments with high acceptance rates. If positive emotions are detected, it may suggest challenging schools to choose from.

[1557] Example prompt sentence:

[1558] Mock exam results: Math 85 points, English 90 points, Japanese 75 points

[1559] Preferred Faculty: Information Engineering

[1560] Desired field: AI

[1561] Thus, the mode for carrying out the invention proposes the most suitable school and department of choice for a student, taking into consideration the student's areas of expertise and emotional state, through a series of steps from data entry to analysis and final proposal, allowing the student to choose their preferred school with confidence and increasing their chances of being accepted.

[1562] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1563] Step 1: User enters practice test results

[1564] The user opens the web application on their device. They enter their mock exam subject scores (Mathematics: 85 points, English: 90 points, Japanese: 75 points), their desired faculty (Information Engineering), and their desired field (AI). After completing the input, they click the send button. The input data is sent from the device to the server. At the same time, the emotion engine captures the user's facial expressions and voice through the camera and microphone and generates emotion data.

[1565] Input: mock test results and desired information entered by the user in the input form, facial expressions and voice data

[1566] Output: Mock test result data, preference information, and emotion data sent to the server

[1567] Step 2: The server receives and stores the data

[1568] The server receives the mock test result data, desired information, and emotion data sent from the user's device. Firewalls and data validation functions are used to check the security and accuracy of the received data. Once validated, the data is stored in a database.

[1569] Input: Received mock test result data, desired information, emotional data

[1570] Output: Mock test results data, preference information, and emotion data stored in the database

[1571] Step 3: Analyze the data with a generative AI model

[1572] The server sends the stored data to the generative AI model, which uses Python's TensorFlow library to analyze the data and identify the student's areas of expertise and strengths. "Mathematics" and "English" are identified as areas of expertise. The analysis results are then sent back to the server.

[1573] Input: Mock test result data, desired information, and emotional data stored in the database

[1574] Output: Information on areas of expertise and strengths after analysis by the generative AI model

[1575] Step 4: Emotional state analysis by the emotion engine

[1576] The server sends the emotion data to the emotion engine, which uses OpenCV and the Google Cloud Speech-to-Text API to analyze the user's facial expressions and voice. A positive emotional state is identified as a result of the analysis and sent back to the server.

[1577] Input: Received emotion data

[1578] Output: Emotional state information after analysis

[1579] Step 5: The server generates school recommendations

[1580] The server receives the analysis results of the AI ​​model and the emotional state of the emotion engine, and generates optimal recommendations for schools and departments. The recommendations also take into account past exam question analysis data and exam schedule information. Challenging schools suited to a positive emotional state can also be included in the recommendations.

[1581] Input: Analyzed areas of expertise and strengths, emotional state information

[1582] Output: Suggested best schools and departments

[1583] Step 6: User confirms the proposed results

[1584] The server sends the proposed results to the user's device. The user's device receives the proposed results and displays them on the screen. The user can check the detailed information of the proposed schools and departments and use it as a reference for selecting the school of their choice that best suits them.

[1585] Input: Suggested best school and department information

[1586] Output: Suggestion results displayed on the user's device

[1587] The above is the specific flow of the system's program processing, and the detailed operations at each step are clarified.

[1588] (Application example 2)

[1589] 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."

[1590] Conventional systems for suggesting preferred schools and departments make suggestions based solely on students' mock exam results. However, this system cannot take into account the student's individual psychological state, such as their emotional state or stress level at the time, which can affect the accuracy of the suggestions and the student's motivation. Therefore, it is necessary for students to study in a relaxed state and receive appropriate advice.

[1591] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1592] In this invention, the server includes means for receiving and saving mock test result data, means for analyzing the mock test result data and identifying the student's areas of expertise, means for proposing the most suitable school and department of choice based on the student's areas of expertise, means for recognizing and saving the user's emotional data, and means for analyzing the emotional data and adjusting the content of the proposal based on the user's emotional state. This makes it possible to propose appropriate and personalized schools and departments of choice that take into account the student's emotional state as well as their academic ability data.

[1593] "Mock exam result data" refers to data relating to the scores and grades obtained by students in each subject in the mock exam.

[1594] A "strength area" is an area of ​​study or subject in which a student shows particular ability or interest.

[1595] "Preferred school" refers to the educational institution that a student wishes to attend.

[1596] A "faculty" is a unit of education and research established for each academic field at a university or higher education institution.

[1597] "Emotion data" is information about emotions acquired from the user's facial expressions, voice, etc.

[1598] "Emotional state" refers to the positive or negative mental state or emotion that a user is currently experiencing.

[1599] A "generative AI model" is an artificial intelligence algorithm that analyzes input data and generates optimal suggestions based on the user's areas of expertise.

[1600] A "prompt sentence" is a specific input sentence that a generative AI model uses to generate suggestions.

[1601] This invention combines a system that analyzes mock test results data, understands a student's areas of expertise and strengths, and then suggests the most suitable school or department to apply to with an emotion engine that recognizes the user's emotions.The system of this invention is mainly composed of a user terminal, a server, a generative AI model, and an emotion engine.

[1602] First, the user device provides an interface for students to input their mock exam results and information about their desired faculty and field. The user enters this information into a form on the device and sends it to the server. Data is also collected from the user's facial expressions and voice when entering information, which the emotion engine analyzes. Furthermore, hardware such as a webcam and microphone is required to acquire emotion data.

[1603] The server then receives and stores the mock test results, desired information, and emotional data sent from the user's device. The server validates the received data to ensure that the format and value range are correct. The server then analyzes this data using a generative AI model. The generative AI model is implemented using a programming language such as Python and includes past question analysis data and algorithms for identifying schools and departments with high pass rates.

[1604] The emotion engine analyzes the user's facial expressions and voice when inputting information to identify the user's emotional state. It uses the EmotionEngine library to determine whether the user is relaxed or stressed. The server combines the emotion data obtained from the emotion engine with the analysis results of the generative AI model to generate optimal recommendations for schools and departments.

[1605] For example, if a user inputs their mock exam scores and indicates that they want to study computer engineering and AI, the emotion engine analyzes their facial expressions and voice and determines that they are relaxed. The server then uses a generative AI model to analyze this data and identify their strengths in math and English. If the user's emotional state is positive, the engine returns results that include suggestions for challenging schools.

[1606] Examples of specific prompts include:

[1607] "User entered mock test results: Math 85, English 90, Japanese 75. Desired department: Computer Engineering. Desired field: AI. Emotional state: Relaxed."

[1608] In this way, the system of the present invention can integrate and analyze a student's academic ability data and emotional data, and can suggest the most suitable schools and departments for each student, allowing students to select their preferred schools with greater confidence.

[1609] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1610] Step 1:

[1611] The user enters the results of the mock exam and the desired faculty and field.

[1612] Input: Mock exam scores by subject, desired faculty information, desired field information

[1613] Output: The entered data is collected from the terminal

[1614] Specific operation: The user enters grade information such as "Math: 85 points, English: 90 points, Japanese: 75 points" and a desired field such as "Information Engineering" or "AI" into the form on the device, and presses the submit button. At this time, the user's facial expressions and voice are collected using the device's webcam and microphone.

[1615] Step 2:

[1616] The emotion engine analyzes the user's facial expressions and voice to generate emotion data.

[1617] Input: User's facial expression data, voice data

[1618] Output: Emotion data (e.g., relaxed, nervous, etc.)

[1619] How it works: Facial and voice data collected on the device is analyzed by the EmotionEngine library to identify the user's emotional state, for example, determining whether the user is relaxed or tense.

[1620] Step 3:

[1621] The server receives and stores the mock test result data, desired information, and emotion data.

[1622] Input: mock test results, desired faculty information, desired field information, emotional data

[1623] Output: User data stored in the database

[1624] Specific operation: Data sent from the user terminal is sent to the server, which validates the data to ensure it is in the correct format and stores it in the database.

[1625] Step 4:

[1626] The server sends the data to the generated AI model, which analyzes the student's areas of expertise and the best schools and departments to apply to.

[1627] Input: Saved user data (mock test results, preferences, emotional data)

[1628] Output: Analysis results from the generative AI model (areas of expertise, preferred schools and departments)

[1629] How it works: The server inputs the saved data into a generative AI model implemented in Python to identify areas of strength in each subject. It also uses past question analysis data to calculate schools and departments with high pass rates.

[1630] Step 5:

[1631] The server adjusts the suggestions based on the emotional data.

[1632] Input: Analysis results of generative AI model, emotion data

[1633] Output: Recommendations for the best schools and departments to apply to based on the emotional state

[1634] How it works: The server reviews the analysis results returned by the generative AI model and adjusts the suggestions based on the data from the emotion engine. For example, if the emotion data is positive, it will suggest more challenging schools, and if it is negative, it will make more realistic suggestions.

[1635] Step 6:

[1636] The server sends the final proposal of preferred schools and departments to the user's device.

[1637] Input: Suggestion data according to emotional state

[1638] Output: User device showing the proposed results

[1639] Specific operation: The server generates a list of the most suitable schools and departments according to the user's emotional state and sends it to the user's device. The user's device then displays this information on the screen so that the user can confirm it.

[1640] This makes it possible to integrate mock test results data with emotional data to suggest the most suitable schools and departments for students to apply to.

[1641] 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.

[1642] 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.

[1643] 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.

[1644] 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.

[1645] 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.

[1646] 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.

[1647] 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).

[1648] 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.

[1649] 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."

[1650] 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.

[1651] 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).

[1652] 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.

[1653] 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.

[1654] 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.

[1655] 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.

[1656] 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.

[1657] 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.

[1658] 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.

[1659] 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.

[1660] 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.

[1661] 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.

[1662] The following is further disclosed regarding the above embodiment.

[1663] (Claim 1)

[1664] means for receiving and storing mock test result data;

[1665] A means for analyzing the result data of the mock test and identifying the areas of expertise of the student;

[1666] A means to suggest the most suitable school and faculty based on your field of expertise,

[1667] A system including:

[1668] (Claim 2)

[1669] The suggestions based on the areas of expertise reflect the question trends of the school or department based on past question analysis data.

[1670] 10. The system of claim 1.

[1671] (Claim 3)

[1672] The suggestion means suggests a desired school and department taking into consideration the examination schedule.

[1673] 10. The system of claim 1.

[1674] "Example 1"

[1675] (Claim 1)

[1676] A means for inputting and transmitting mock test result data and desired domain data from a terminal;

[1677] means for receiving and storing the result data of the simulation test and the desired area data;

[1678] A means for identifying a student's specialty area using a generative AI model that analyzes the mock test result data and desired domain data;

[1679] A method to suggest the most suitable school and faculty based on your area of ​​expertise, taking into consideration past exam analysis data and exam dates.

[1680] A system including:

[1681] (Claim 2)

[1682] The generative AI model used in the proposed method reflects the question trends of schools and departments based on past question analysis data.

[1683] 10. The system of claim 1.

[1684] (Claim 3)

[1685] The suggestion means suggests a desired school and department taking into consideration the examination schedule.

[1686] 10. The system of claim 1.

[1687] "Application Example 1"

[1688] (Claim 1)

[1689] means for receiving and storing mock test result data;

[1690] A means for analyzing the result data of the mock test and identifying the areas of expertise of the student;

[1691] A means to suggest the most suitable educational destination and specialization based on the student's area of ​​expertise;

[1692] A means for inputting the mock test results into a smartphone or tablet interface;

[1693] A means for a user to view detailed information about the school and specialty using a virtual reality headset;

[1694] A system including:

[1695] (Claim 2)

[1696] The suggestions based on the areas of expertise reflect the selection trends of educational institutions and specializations based on past problem analysis data.

[1697] 10. The system of claim 1.

[1698] (Claim 3)

[1699] The suggestion means suggests future schools and fields of specialization taking into consideration entrance examination dates.

[1700] 10. The system of claim 1.

[1701] "Example 2: Combining Emotion Engines"

[1702] (Claim 1)

[1703] means for receiving and storing mock test result data;

[1704] A means for analyzing the result data of the mock test and identifying the areas of expertise of the student;

[1705] A method to suggest the best schools and departments to apply to based on your areas of expertise,

[1706] means for analyzing a user's emotions and generating suggestions according to the user's emotional state;

[1707] ...

[1708] A system including:

[1709] (Claim 2)

[1710] The suggestions based on the areas of expertise reflect the question trends of the school or department based on past question analysis data.

[1711] 10. The system of claim 1.

[1712] (Claim 3)

[1713] The suggestion means suggests a desired school and department taking into consideration the examination schedule.

[1714] 10. The system of claim 1.

[1715] "Application example 2 when combining emotion engines"

[1716] (Claim 1)

[1717] means for receiving and storing mock test result data;

[1718] A means for analyzing the result data of the mock test and identifying the areas of expertise of the student;

[1719] A means to suggest the most suitable school and faculty based on your field of expertise,

[1720] means for recognizing and storing user emotion data;

[1721] means for analyzing the emotion data and adjusting the content of the suggestions based on the user's emotional state;

[1722] A system including:

[1723] (Claim 2)

[1724] The suggestions based on the areas of expertise reflect the question trends of the school or department based on past question analysis data.

[1725] 10. The system of claim 1.

[1726] (Claim 3)

[1727] The suggestion means suggests a desired school and department taking into consideration the examination schedule.

[1728] 10. The system of claim 1.

[1729] (Claim 4)

[1730] The means for analyzing the emotional data recognizes the user's facial expressions and voice and identifies a positive or negative emotional state.

[1731] 10. The system of claim 1.

[1732] (Claim 5)

[1733] A means for using a generative AI model to identify the most suitable school and department based on the user's areas of expertise and generate prompt sentences;

[1734] 10. The system of claim 1. [Explanation of symbols]

[1735] 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. means for receiving and storing mock test result data; A means for analyzing the result data of the mock test and identifying the areas of expertise of the student; A means to suggest the most suitable school and faculty based on your field of expertise, A system including:

2. The suggestions based on the areas of expertise reflect the question trends of the school or department based on past question analysis data. The system of claim 1 .

3. The suggestion means suggests a desired school and department taking into consideration the examination schedule. The system of claim 1 .

Images