System

Abstract

A system is provided.SOLUTION: The system includes a means for receiving performance information and interest information of the user, a means for performing analysis for recommending an optimal education institution and faculty on the basis of the performance information and interest information of the user, and a means for providing a list of recommended education institutions and faculties to the user on the basis of an analysis result.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] Traditionally, high school students have had to manually gather vast amounts of information when choosing a university, and the complexity of the application process places a significant burden on them. They also had to individually research each institution's research content and application requirements, which entailed significant time and mental costs. Furthermore, they often relied on educational counselors and teachers for reliable advice, making it difficult to efficiently prepare for college. Given these circumstances, there is a need for a system that can centrally and efficiently support the university selection and application process. [Means for solving the problem]

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

[0006] The system includes a means for receiving the user's grade information and interest information, a means for performing an analysis to recommend the most suitable educational institution and faculty based on the user's grade information and interest information, and a means for providing the user with a list of the recommended educational institutions and faculty based on the analysis results.

[0007] Furthermore, the system includes a means for receiving research content and keywords of interest to the user, a means for searching academic paper abstract databases of educational institutions to identify research fields that match the research content and keywords of interest, and a means for providing a list of recommended educational institutions and laboratories based on the identified research fields.

[0008] In addition, the system includes a means for receiving information on the educational institutions and departments to which the user wishes to apply, a means for obtaining application requirements for each educational institution and department and comparing them with the user's application information, a means for automatically generating a list of documents to be submitted and an application schedule based on the application requirements, and a means for providing the user with the list of documents to be submitted and the application schedule and setting reminder notifications for important deadlines.

[0009] "Academic performance information" refers to data that indicates a user's academic performance, including report cards and test results.

[0010] "Interest information" is data that indicates the user's interests and subjects of interest, and includes information such as desired academic fields, special skills, and extracurricular activities.

[0011] "Analysis" refers to the processing of data to identify the most suitable educational institution and department based on the entered grade and interest information.

[0012] "Recommendation" means presenting educational institutions and departments selected based on the analysis results to the user.

[0013] "Educational institutions" refers to facilities such as universities and vocational schools that provide higher education.

[0014] A "faculty" refers to an organization or department within an educational institution that provides education specializing in a particular field.

[0015] "Research content" refers to the research theme or outline of the research in a particular academic field.

[0016] A "paper abstract database" refers to a database that collects abstract information from papers published by educational institutions and research institutions.

[0017] "Application information" refers to information related to the educational institution or department to which the user is considering applying.

[0018] "Application requirements" refers to the conditions and documents required to apply to a particular educational institution or department.

[0019] A "checklist" is a list of documents and tasks required for application.

[0020] "Schedule" refers to a timeline showing important periods and deadlines throughout the application process.

[0021] "Reminder notification" refers to an alert function that notifies users of important deadlines and tasks. [Brief explanation of the drawings]

[0022] [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

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] The following describes in detail the mode for carrying out the present invention. The present invention is a system designed to streamline the information gathering and application process when selecting an educational institution. Based on the user's grades and interests, the system recommends the most suitable educational institutions and departments, and generates the checklists and schedules required for application. It also matches educational institutions based on research content.

[0044] Customized proposals for universities and departments using AI

[0045] 1. User data entry

[0046] Users: Enter information into the application, such as grades, interests, and extracurricular activities.

[0047] 2. Sending and Receiving Data

[0048] Terminal: Sends the entered data to the server.

[0049] 3. Data Analysis

[0050] Server: Analyzes the received grade and interest information and identifies the appropriate educational institution and department using an AI model.

[0051] 4. Generating and sending recommendation lists

[0052] Server: Generates a list of recommended educational institutions and departments based on the analysis results and sends it to the user's device.

[0053] 5. Display of recommendation results

[0054] Terminal: Displays the received recommendation list to the user.

[0055] Examples:

[0056] Let's say high school student Sato wants to study chemistry. Sato enters his grades and interest in chemistry into the app. The server performs AI analysis based on this information, creates a list of universities with excellent chemistry programs, and sends the recommendation results to Sato's device.

[0057] Research content matching

[0058] 1. Enter keywords

[0059] User: Enters research interests and keywords into the application.

[0060] 2. Sending and Receiving Data

[0061] Terminal: Sends the entered keyword information to the server.

[0062] 3. Research database collation

[0063] Server: Searches a database of paper abstracts to identify research fields that match the entered keywords.

[0064] 4. Generating and sending matching results

[0065] Server: Generates a list of recommended educational institutions and laboratories based on the identified research field and sends it to the user's device.

[0066] 5. Display of matching results

[0067] Terminal: Displays the received matching results to the user.

[0068] Examples:

[0069] Let's say Tanaka, who is interested in physics, wants to study "theory of relativity." Tanaka enters "theory of relativity" as a keyword into the app. The server searches a database of paper abstracts, identifies universities and laboratories conducting research on the theory of relativity, and sends a list of recommendations to Tanaka's device.

[0070] Auto-generated application checklists and schedules

[0071] 1. Enter application information

[0072] User: Enters information about the institution and department to which they wish to apply into the application.

[0073] 2. Sending and Receiving Data

[0074] Terminal: Sends the entered application information to the server.

[0075] 3. Analysis of application requirements

[0076] Server: Obtains application requirements for each educational institution and department and matches them with the user's application information.

[0077] 4. Generate checklists and schedules

[0078] Server: Automatically generates a list of documents to be submitted and an application schedule based on application requirements.

[0079] 5. Data transmission and display

[0080] Server: Sends the checklist and schedule to the user's device, which displays it to the user. It also sets reminder notifications.

[0081] Examples:

[0082] Suzuki, who is considering applying to multiple universities, enters the application information for each university into the app. The server retrieves the application requirements for each university, automatically generates a list of documents to be submitted, and an application schedule, which are then sent to Suzuki's device.

[0083] Continuous learning and improvement

[0084] 1. Enter and submit your feedback

[0085] User: Enters feedback about the service into the app and sends it from the device to the server.

[0086] 2. Analyzing feedback and updating the AI ​​model

[0087] Server: Analyzes the feedback and updates the AI ​​model. This update improves recommendation results and matching accuracy from the next time onwards.

[0088] summary

[0089] This invention allows high school students to efficiently select the appropriate educational institution and department, and smoothly progress through the application process. Furthermore, the system is continuously improved through feedback, enabling it to provide more accurate information. This system is realized through mutual cooperation between users, terminals, and servers.

[0090] The processing flow will be explained below.

[0091] Customized proposals for universities and departments using AI

[0092] Step 1:

[0093] Users: Enter information into the application, such as grades, interests, and extracurricular activities.

[0094] Step 2:

[0095] Terminal: Formats the entered data and generates a request to send to the server.

[0096] Step 3:

[0097] Server: Stores the received user performance information and interest information in a database and prepares for analysis.

[0098] Step 4:

[0099] Server: Uses AI models to analyze the user's grades and interests to identify the most suitable educational institution and department.

[0100] Step 5:

[0101] Server: Generates a list of recommended educational institutions and departments based on the analysis results.

[0102] Step 6:

[0103] Server: Sends the recommendation list to the user's device.

[0104] Step 7:

[0105] Terminal: Formats the received recommendation list and displays it to the user.

[0106] Research content matching

[0107] Step 1:

[0108] User: Enters research interests and keywords into the application.

[0109] Step 2:

[0110] Terminal: Formats the entered keywords and generates a request to send to the server.

[0111] Step 3:

[0112] Server: Searches the institution's paper abstract database based on the received keywords.

[0113] Step 4:

[0114] Server: Identifies research fields that match keywords from the search results and generates a recommendation list.

[0115] Step 5:

[0116] Server: Sends the generated recommendation list to the user's device.

[0117] Step 6:

[0118] Terminal: Formats the received recommendation list and displays it to the user.

[0119] Auto-generated application checklists and schedules

[0120] Step 1:

[0121] User: Enters information about the institution and department to which they wish to apply into the application.

[0122] Step 2:

[0123] Terminal: Formats the entered application information and generates a request to send to the server.

[0124] Step 3:

[0125] Server: Stores the received application information in a database and retrieves application requirements for each educational institution and department from the database.

[0126] Step 4:

[0127] Server: Compares the acquired application requirements with the user's application information and generates a list of documents to be submitted and an application schedule.

[0128] Step 5:

[0129] Server: Sends the generated list of submitted documents and application schedule to the user's terminal.

[0130] Step 6:

[0131] Terminal: Formats received submission lists and application schedules, displays them to the user, and sets reminder notifications.

[0132] Gathering feedback and updating the AI ​​model

[0133] Step 1:

[0134] Users: Enter feedback about the service into the application.

[0135] Step 2:

[0136] Terminal: Formats the input feedback and generates a request to send to the server.

[0137] Step 3:

[0138] Server: Stores the received feedback in a database and prepares it for analysis.

[0139] Step 4:

[0140] Server: Analyzes the feedback and extracts necessary improvements to the AI ​​model.

[0141] Step 5:

[0142] Server: Update the AI ​​model based on the improvements and improve recommendation accuracy from next time onwards.

[0143] The above is a specific process flow for implementing the present invention, which significantly streamlines the college selection and application process for high school students, their parents, and educational counselors.

[0144] Example 1

[0145] 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."

[0146] In the traditional graduate school and application process, users had difficulty selecting the appropriate educational institution and department from the vast amount of information available. It was also time-consuming to individually research each institution's application requirements and manage the necessary documents and schedules. Furthermore, matching educational institutions based on research content had to be done manually, which was time-consuming and labor-intensive.

[0147] 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.

[0148] In this invention, the server includes a means for receiving grade information and interest information, a means for performing analysis to recommend educational institutions and departments based on the grade information and interest information, a means for providing a list of educational institutions and departments based on the analysis results, and a means for receiving feedback and updating the analysis means, thereby enabling users to quickly and accurately select appropriate educational institutions and departments.

[0149] "Academic performance information" is data that indicates the user's academic performance and evaluation.

[0150] "Interest information" is data that indicates the fields or themes in which a user is interested.

[0151] "Educational institution" refers to a school or university providing higher education.

[0152] A "faculty" is a department within a university or educational institution that is responsible for a particular field of education or research.

[0153] The "analysis means" is a function that performs calculations to identify appropriate educational institutions and departments based on grade information and interest information.

[0154] The "recommended list" is a list of educational institutions and departments recommended based on the analysis results.

[0155] "Feedback" is data showing user evaluations and opinions, and is used to improve the system.

[0156] A "literature abstract database" is a database that collects summary information from academic papers.

[0157] "Research content" refers to academic issues or themes in a specific field.

[0158] A "research facility" is a department or laboratory within an educational institution that conducts specific research.

[0159] "Application requirements" refers to the conditions and documents that must be submitted when applying to an educational institution.

[0160] The "list of documents to be submitted" is a list of documents required for application.

[0161] An "application schedule" is a plan that outlines important dates and deadlines in the application process.

[0162] "Reminder Notification" is a feature that notifies you in advance of important deadlines and events.

[0163] The system of the present invention is designed to streamline the educational institution selection and application process. Through mutual cooperation between users, terminals, and servers, the system recommends appropriate educational institutions and departments, enabling a smooth application process. Specific embodiments of the system are described below.

[0164] 1. Entering user data

[0165] Users use a dedicated application to enter information such as grades, areas of interest, and extracurricular activities. This information is stored on the device as JSON format data. For example, a user might enter into the application that "I'm interested in physics and belong to the science club as an extracurricular activity."

[0166] 2. Sending and Receiving Data

[0167] The terminal sends the entered data to the server. This transmission uses an API call via the Internet. Specifically, when the user presses the "Send" button, the input data is converted into JSON format and sent to the server.

[0168] 3. Data Analysis

[0169] The server uses a generative AI model to analyze the received grade and interest information. This analysis is performed using cloud services such as Google Cloud AI and AWS SageMaker. The server preprocesses the parsed JSON data and converts it into a format suitable for the AI ​​model for analysis.

[0170] 4. Generate and send recommendation list

[0171] The server generates a list of recommended educational institutions and departments based on the analysis results and sends it to the device. Specifically, it converts the analysis results into JSON format, makes an API call to the user's device, and sends the list of recommendations.

[0172] 5. Display of recommendation results

[0173] The device parses the recommendation list received from the server and displays it on the application UI, allowing the user to view the recommended educational institutions and departments on the screen.

[0174] 6. Use of Feedback

[0175] Users input feedback about the recommendation list and services provided. The device then sends this feedback to the server. The server analyzes the received feedback and updates the AI ​​model to improve recommendation results and matching accuracy from the next time onwards.

[0176] Specific examples

[0177] Examples:

[0178] For example, if high school student Sato wants to study chemistry, he or she can enter his or her grades and interest in chemistry into the app. The server performs AI analysis based on this information, lists universities with excellent chemistry programs, and sends the recommendation results to Sato's device. Sato can then review the recommendation list and consider the career path that best suits his or her aspirations.

[0179] Generative AI model input example:

[0180] "I'm interested in chemistry and I'd like to know which universities have good chemistry programs."

[0181] "Please recommend a university where I can study the theory of relativity."

[0182] "Please tell me the documents and schedule required to apply to the university I want to attend."

[0183] This invention allows users to efficiently select appropriate educational institutions and departments, and smoothly progress through the application process. The system provides highly accurate information through mutual cooperation between users, terminals, and servers.

[0184] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0185] Step 1:

[0186] User Data Entry

[0187] User: Enters information such as grades, areas of interest, and extracurricular activities into the application. Specifically, the user enters the required information into a form in the dedicated application and presses the "Submit" button. This data is temporarily saved on the device in JSON format.

[0188] Input: Grades, interests, extracurricular activities

[0189] Output: JSON format data

[0190] Step 2:

[0191] Sending data

[0192] Terminal: Sends JSON format data to the server. Specifically, when the "Send" button is pressed, the terminal executes an API call to send the data to the server. SSL is used during communication to ensure data security.

[0193] Input: JSON format data

[0194] Output: API calls to the server and data sent

[0195] Step 3:

[0196] Receiving and Parsing Data

[0197] Server: Parses the received data from JSON format and converts it into an internal data structure. Specifically, it analyzes the received JSON data and organizes it into data objects according to grades, areas of interest, and extracurricular activities.

[0198] Input: JSON format data

[0199] Output: Analysis and object format data

[0200] Step 4:

[0201] Data analysis

[0202] Server: Uses the parsed data to input the generative AI model. Specifically, it uses Google Cloud AI or AWS SageMaker to analyze grade information and areas of interest to identify the most suitable educational institution and department for the user. It then applies the calculations and evaluation logic of the generative AI model to extract appropriate recommendations.

[0203] Input: Analysis and object-formatted data

[0204] Output: Analysis results (recommendation list)

[0205] Step 5:

[0206] Generating and sending recommendation lists

[0207] Server: The analysis results are converted back into JSON format and sent to the user's device. Specifically, the generated recommendation list is sent to the device via an API call.

[0208] Input: Analysis results

[0209] Output: Recommendation list in JSON format, and API calls to the device

[0210] Step 6:

[0211] Receiving and displaying recommendations

[0212] Device: Parses the recommendation list received from the server and displays it in a format suitable for the user interface. Specifically, it interprets the received data and displays it in a list view or dashboard.

[0213] Input: JSON formatted recommendation list from the server

[0214] Output: Recommendation list displayed in a user interface

[0215] Step 7:

[0216] Matching research content

[0217] User: Enters research interests and keywords (e.g., "quantum mechanics") into the application.

[0218] Terminal: Sends the entered keyword to the server.

[0219] Server: Searches the institution's literature abstract database to identify research areas that match the keywords entered.

[0220] Specifically, the server executes a database query to list relevant papers and research fields, converts the analysis results back into JSON format, and sends them to the user's device.

[0221] Terminal: Parses and displays the list of recommended fields of study and educational institutions.

[0222] Input: Research Keywords

[0223] Output: A list of educational institutions that match the field of study

[0224] Step 8:

[0225] Application information management

[0226] User: Enters information about the institution and department to which they wish to apply into the application.

[0227] Terminal: Sends the entered application information to the server.

[0228] Server: Acquires and collates application requirements. Specifically, it uses web scraping and APIs to collect application requirements from each educational institution and verifies that they match the user's application information. It automatically generates a list of documents to be submitted and an application schedule based on the application requirements, converts them back into JSON format, and sends them to the device.

[0229] Terminal: Parse and view automatically generated submission lists and application schedules, and set reminders for important deadlines.

[0230] Input: Application information

[0231] Output: Application requirements, list of documents to be submitted, application schedule, reminder notices

[0232] Step 9:

[0233] Feedback input and analysis

[0234] User: Enters feedback on the recommendations and services provided.

[0235] Terminal: Sends the entered feedback to the server.

[0236] Server: Analyzes the feedback and updates the AI ​​model. Specifically, it analyzes the feedback data and uses it as training data to improve the accuracy of the generative AI model.

[0237] Input: Feedback data

[0238] Output: Updated analysis method

[0239] This allows users to quickly and accurately select the appropriate educational institution and department, and smoothly progress through the application process.

[0240] (Application example 1)

[0241] 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."

[0242] Conventional educational institution recommendation systems simply recommend suitable universities and departments based on academic records and interests. However, they lack a means to provide users with customized educational institution advertisements that are optimal for them, making it difficult to provide information efficiently and effectively. There was also a need for a way to effectively promote educational institutions through advertisements while providing important information for the application process.

[0243] 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.

[0244] In this invention, the server includes means for receiving the user's grade information and interest information, means for performing analysis to recommend the most suitable educational institution based on the grade information and interest information, means for providing a list of the recommended educational institutions based on the analysis results, and means for generating advertising data and displaying advertisements for educational institutions optimized for the user's characteristics. This makes it possible to provide the user with information on the most suitable educational institution, and by displaying customized advertisements, enables effective promotional activities.

[0245] "Grade information" is data indicating grades and evaluations for each subject that a user has obtained at school or the like.

[0246] "Interest information" is information relating to academic fields or research themes in which a user is particularly interested.

[0247] "Educational institutions" are facilities or organizations that provide higher education, such as universities and vocational schools.

[0248] A "faculty" is an organization within an educational institution such as a university that conducts study and research in a specific academic field.

[0249] "Analysis" is the process of performing calculations and evaluations using mathematical models and algorithms based on received performance information and interest information.

[0250] The "list" is a table listing the names and information of recommended educational institutions, departments, and laboratories.

[0251] "Advertising Data" is digital data generated to promote a particular educational institution.

[0252] "Customized advertising" refers to promotional advertising whose content is tailored based on a user's characteristics and interests.

[0253] A "paper abstract database" is a data store that collects summaries of numerous papers and is used to search for research content.

[0254] "Application information" refers to information about the documents and procedures required when a user applies to enroll in a particular educational institution or faculty.

[0255] "Application requirements" refer to the conditions and documents that must be met in order to enter a particular educational institution or faculty.

[0256] "List of documents to be submitted" refers to a list of documents required for application.

[0257] An "application schedule" is a timeline that shows the deadlines and schedule for each step in the application process.

[0258] "Reminder notification" is a function that notifies users in advance so that they do not forget important deadlines.

[0259] This invention is a system that recommends optimal educational institutions and departments based on a user's grades and interests. It also matches laboratories and educational institutions based on the user's research interests and displays customized advertisements, thereby providing efficient information provision and promotion.

[0260] To realize this system, the following hardware and software are used.

[0261] Hardware: User's smartphone, server

[0262] Software: Python, REST API, JSON, Scikit-learn or TensorFlow

[0263] System configuration

[0264] User Data Entry

[0265] Users use a smartphone app to input their grades, areas of interest, and research keywords, and the application sends this information to the server in JSON format.

[0266] Data analysis

[0267] The server analyzes the received grades and interest information using AI models (based on Scikit-learn and TensorFlow) to identify the most suitable educational institutions and departments. The analysis results are generated as a recommendation list.

[0268] Generating a recommendation list

[0269] Based on the analysis results, a list of the most suitable educational institutions and departments is generated, which is sent in JSON format to the user's smartphone and displayed within the app.

[0270] Generate personalized ads

[0271] The server generates advertising data based on the analysis results and user characteristics, which includes information about the educational institution and is displayed in a customized format to the user.

[0272] Application information management

[0273] When a user inputs information about the educational institution and department to which they wish to apply, the server retrieves the application requirements and automatically generates a list of documents to be submitted and an application schedule, allowing users to efficiently proceed with their application.

[0274] Reminders

[0275] For important deadlines, smartphone apps can set reminder notifications to remind users not to forget about them.

[0276] Specific examples

[0277] Recommendations based on user performance information

[0278] High school students enter their grades (90 for math, 95 for science, 85 for English) and areas of interest (science, physics) into the app. This data is sent to a server, which analyzes it and generates a list of the most suitable universities and departments (e.g., universities with a strong science focus). This list is accompanied by corresponding customized university advertisements.

[0279] Prompt Sentence Examples

[0280] An example of a user prompt would be, "My grades are 90 in math, 95 in science, and 85 in English. My areas of interest are science and physics." The system will then recommend and display advertisements for the most suitable educational institutions.

[0281] In this way, the present invention makes it possible to provide users with information about educational institutions and to promote their advertisements efficiently and effectively.

[0282] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0283] Step 1:

[0284] The user's device is started, and the user opens the app and enters their grades, areas of interest, and research keywords. The input information (grades, areas of interest, and research keywords) is converted into JSON format and sent to the server.

[0285] Step 2:

[0286] The server receives JSON-formatted data (grade information, areas of interest, research keywords) sent from the device. The server passes this data to an AI model (Scikit-learn or TensorFlow) for analysis. The AI ​​model identifies the most suitable educational institutions and departments based on the input data and generates a list of recommendations. The output is a list of recommended educational institutions and departments.

[0287] Step 3:

[0288] The server returns the generated recommendation list in JSON format to the device, which receives it and visually displays it to the user. The display is in list format, including detailed information about the recommended educational institutions and departments.

[0289] Step 4:

[0290] The server further generates customized advertising data based on the analysis results and the user's characteristics. The advertising data is configured in a manner optimized for the user and includes specific information and promotional content from the educational institution. The output is the customized advertising data.

[0291] Step 5:

[0292] The server transmits the generated advertisement data to the terminal, which receives it and displays the advertisement to the user along with the recommendation list. The advertisement is visually integrated into the interface and is designed to attract the user's attention.

[0293] Step 6:

[0294] Users enter their desired application information into the app. The device converts this information into JSON format and sends it to the server. This application information includes the desired educational institution and department.

[0295] Step 7:

[0296] The server receives the application information sent from the terminal and retrieves the application requirements of each educational institution and department from the database. The server uses this information to automatically generate a list of documents to be submitted and an application schedule. The output is a list of documents to be submitted and an application schedule.

[0297] Step 8:

[0298] The server sends the generated list of documents to be submitted and the application schedule to the terminal, which receives it and displays it in an easy-to-understand manner for the user. A reminder notification function is also set up to notify the user of important deadlines.

[0299] This flow allows users to receive recommendations for the most suitable educational institutions based on their academic records and interests, display customized advertisements, and streamline the application process, all within a single application.

[0300] 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.

[0301] The present invention provides a system for recommending educational institutions and departments based on a user's grades and interests, streamlining the application process, and also provides customized recommendation information based on the user's emotions by combining it with an emotion engine that recognizes the user's emotions.

[0302] Receiving and analyzing user performance and interest information

[0303] 1. User data entry

[0304] Users: Enter information into the application, such as grades, interests, and extracurricular activities.

[0305] 2. Sending and Receiving Data

[0306] Terminal: Formats the entered data and sends it to the server.

[0307] 3. Data Analysis

[0308] Server: Stores the received grade information and interest information in a database and prepares for analysis.

[0309] 4. AI-based analysis

[0310] Server: Uses AI models to analyze the user's grades and interests to identify the most suitable educational institution and department.

[0311] 5. Customization with Emotion Engine

[0312] Server: The AI ​​analysis results are further analyzed by the emotion engine to generate customized recommendations based on the user's emotional state.

[0313] 6. Generating and Sending Recommendation Lists

[0314] Server: Generates a recommendation list optimized by the emotion engine and sends it to the user's device.

[0315] 7. Display of recommendation results

[0316] Terminal: Displays the received recommendation list to the user.

[0317] Examples:

[0318] High school student Yamada enters his grades and interests into the app. The server receives and analyzes this information, and an AI model identifies the most suitable university and department. At the same time, an emotion engine analyzes Yamada's emotions when he enters the information, and if he is in a stressful situation, it recommends a university with a strong support system.

[0319] Research content matching

[0320] 1. Enter keywords

[0321] User: Enters research interests and keywords into the application.

[0322] 2. Sending and Receiving Data

[0323] Terminal: Formats the entered keywords and sends them to the server.

[0324] 3. Research database collation

[0325] Server: Searches a database of paper abstracts to identify research fields that match the entered keywords.

[0326] 4. Generating and sending matching results

[0327] Server: Generates a list of recommended educational institutions and laboratories based on the identified research field, customizes it according to the user's emotional state, and sends it to the user's device.

[0328] 5. Display of matching results

[0329] Terminal: Formats the received recommendation list and displays it to the user.

[0330] Examples:

[0331] Sato, who is interested in physics, enters "quantum mechanics" as a keyword. The server searches a database of paper abstracts based on the keyword and identifies universities and laboratories conducting relevant research. At the same time, the emotion engine takes Sato's emotional state into account and prioritizes recommending universities with low stress and good research environments.

[0332] Auto-generated application checklists and schedules

[0333] 1. Enter application information

[0334] User: Enters information about the institution and department to which they wish to apply into the application.

[0335] 2. Sending and Receiving Data

[0336] Terminal: Formats the entered application information and sends it to the server.

[0337] 3. Analysis of application requirements

[0338] Server: Obtains application requirements for each educational institution and department and matches them with the user's application information.

[0339] 4. Generate checklists and schedules

[0340] Server: Automatically generates a list of documents to be submitted and an application schedule based on the application requirements. It also takes into account the user's emotional state, allowing for flexibility in the schedule and adding explanations.

[0341] 5. Data transmission and display

[0342] Server: Sends the generated list of submitted documents and application schedule to the user's terminal, which displays it to the user and sets reminder notifications.

[0343] Examples:

[0344] Mr. Tanaka, who is considering applying to multiple universities, enters the application information for each university into the app. The server receives this information, obtains the application requirements for each university, and generates a list of documents to be submitted and an application schedule. The emotion engine takes Mr. Tanaka's emotional state into account and adds warnings and specific advice to areas where he is likely to feel anxious.

[0345] Gathering feedback and updating the AI ​​model

[0346] 1. Enter and submit your feedback

[0347] User: Enters feedback about the service into the application and sends it to the server from the terminal.

[0348] 2. Analyzing feedback and updating the AI ​​model

[0349] Server: Analyzes the received feedback, extracts necessary improvements to the AI ​​model and emotion engine, and updates the model.

[0350] Examples:

[0351] Users provide feedback after using the system, which the server reads, analyzes areas for improvement in the service, and updates the AI ​​model and emotion engine to provide better recommendations and research matching the next time users use the system.

[0352] As a result, the present invention provides an efficient and emotionally sensitive educational institution selection and application process.

[0353] The processing flow will be explained below.

[0354] Customized proposals for universities and departments using AI

[0355] Step 1:

[0356] Users: Enter information into the application, such as grades, interests, and extracurricular activities.

[0357] Step 2:

[0358] Terminal: Formats the entered data and generates a request to send to the server.

[0359] Step 3:

[0360] Server: Stores the received user performance information and interest information in a database and prepares for analysis.

[0361] Step 4:

[0362] Server: Uses AI models to analyze the user's grades and interests to identify the most suitable educational institution and department.

[0363] Step 5:

[0364] Server: Uses an emotion engine to analyze the emotion data of the user's input in real time and identify the emotional state.

[0365] Step 6:

[0366] Server: Based on the analysis results of the emotion engine, the recommendation results of the AI ​​model are adjusted to generate a recommendation list optimized for the user's emotional state.

[0367] Step 7:

[0368] Server: Sends the optimized recommendation list to the user's device.

[0369] Step 8:

[0370] Terminal: Formats the received recommendation list and displays it to the user.

[0371] Examples:

[0372] High school student Yamada enters his grades and interests into the app. The server receives and analyzes this information, and an AI model identifies the appropriate university and department. At the same time, an emotion engine analyzes Yamada's emotional state (for example, whether his stress level is high or low), generates a list of recommended universities with better support systems, and sends it to Yamada's device.

[0373] Research content matching

[0374] Step 1:

[0375] User: Enters research interests and keywords into the application.

[0376] Step 2:

[0377] Terminal: Formats the entered keywords and generates a request to send to the server.

[0378] Step 3:

[0379] Server: Searches the institution's paper abstract database based on the received keywords.

[0380] Step 4:

[0381] Server: From the search results, identify research fields that match the keywords and generate a list of recommendations.

[0382] Step 5:

[0383] Server: Uses an emotion engine to analyze the user's emotional state and match appropriate educational institutions and laboratories based on a recommended list of research fields.

[0384] Step 6:

[0385] Server: Sends the optimized research recommendation list to the user's device.

[0386] Step 7:

[0387] Terminal: Formats the received recommendation list and displays it to the user.

[0388] Examples:

[0389] Sato, who is interested in physics, enters "quantum mechanics" as a keyword. The server searches a database of paper abstracts based on the entered keywords and identifies suitable universities and research laboratories. At the same time, the emotion engine analyzes Sato's emotional state and generates a list of recommendations focusing on universities with low stress and good research environments, which is sent to Sato's device.

[0390] Auto-generated application checklists and schedules

[0391] Step 1:

[0392] User: Enters information about the institution and department to which they wish to apply into the application.

[0393] Step 2:

[0394] Terminal: Formats the entered application information and generates a request to send to the server.

[0395] Step 3:

[0396] Server: Stores the received application information in a database and obtains the application requirements of each educational institution and department.

[0397] Step 4:

[0398] Server: Compares the acquired application requirements with the user's application information and generates a list of documents to be submitted and an application schedule.

[0399] Step 5:

[0400] Server: Uses an emotion engine to analyze the user's emotional state and optimize the filing list and application schedule.

[0401] Step 6:

[0402] Server: Sends the optimized submission document list and application schedule to the user's terminal.

[0403] Step 7:

[0404] Terminal: Formats and displays received submission lists and filing schedules to the user, and sets reminders for important deadlines.

[0405] Examples:

[0406] Mr. Tanaka, who is considering applying to multiple universities, enters the application information for each university into the app. The server receives this information, obtains the application requirements for each university, and generates a list of documents to be submitted and an application schedule. The emotion engine analyzes Mr. Tanaka's emotional state and adds warnings and specific advice to areas where he is likely to feel anxious.

[0407] Gathering feedback and updating the AI ​​model

[0408] Step 1:

[0409] Users: Enter feedback about the service into the application.

[0410] Step 2:

[0411] Terminal: Formats the input feedback and generates a request to send to the server.

[0412] Step 3:

[0413] Server: Stores the received feedback in a database and prepares it for analysis.

[0414] Step 4:

[0415] Server: Analyzes the feedback and extracts necessary improvements to the AI ​​model and emotion engine.

[0416] Step 5:

[0417] Server: Update the AI ​​model and emotion engine based on the improvements, and improve the accuracy of recommendations from next time onwards.

[0418] The above is a specific processing flow for implementing the present invention, which significantly improves the efficiency of the university selection and application process for high school students, their parents, and educational counselors, while also enabling the provision of services that are sensitive to the user's emotions.

[0419] Example 2

[0420] 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."

[0421] Conventional educational institution recommendation systems are limited to simple recommendations based on users' grades and interests, and lack customization that takes into account the user's emotional state. Furthermore, in matching optimal research fields and the application process, efficient recommendations and schedule management that take into account the user's emotional state are lacking.

[0422] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving the user's grade information and interest information, a means for performing an analysis to recommend the most suitable educational institution and faculty based on the user's grade information and interest information, a means for further analyzing the analysis results with an emotion analysis engine and customizing the recommendation information based on the user's emotional state, and a means for providing the customized recommendation information to the user. This enables customized recommendations that take into account the user's emotional state in addition to the user's grade information and interest information.

[0423] "Academic achievement information" refers to data that represents a user's academic achievements at an educational institution, such as academic records, test results, and evaluation scores.

[0424] "Interest information" is information that indicates a user's personal interests, such as fields of interest, subjects, extracurricular activities, and future career paths.

[0425] "Analysis" refers to analyzing and processing data for a specific purpose based on received information.

[0426] "Educational institutions" refers to organizations and facilities that teach academic subjects or skills, such as universities, technical colleges, and vocational schools.

[0427] An "emotion analysis engine" refers to an algorithm or software tool that analyzes a user's emotional and psychological state based on user input data and behavioral data.

[0428] "Recommendation" refers to suggesting the best option to a user based on specific criteria.

[0429] A database is an information system that systematically organizes and stores large amounts of data, and efficiently searches and manages them.

[0430] "Application information" refers to data such as personal information and desired information required when applying to an educational institution or faculty of a user's choice.

[0431] "Document List" refers to the list of documents required for the application process at an educational institution.

[0432] An "application schedule" is a plan showing the various steps and deadlines required for filing an application.

[0433] "Reminder notification" refers to a notification function that notifies users when a specific deadline or event is approaching.

[0434] The present invention is a system that recommends educational institutions and departments based on a user's grades and interests, streamlining the application process. Furthermore, by combining it with an emotion analysis engine that recognizes the user's emotions, the system provides customized recommendation information based on the user's emotions.

[0435] Hardware and software used

[0436] This system uses the following hardware and software:

[0437] 1. Hardware

[0438] Terminal: A device used by a user to input information, such as a smartphone or computer.

[0439] Server: A cloud-based server for analyzing the received data and generating recommendation information.

[0440] 2. Software

[0441] Input forms: web and mobile applications that run on devices.

[0442] Database: A relational database such as MySQL.

[0443] Generative AI models: Python-based AI analysis tool.

[0444] Sentiment analysis engine: Algorithms and software (e.g., natural language processing tools and machine learning models) for analyzing a user's emotional state.

[0445] A concrete example of the processing flow

[0446] Receiving and analyzing user performance and interest information

[0447] 1. User data entry

[0448] A user enters his / her grades, areas of interest, extracurricular activities, etc. into an application input form. For example, a high school student enters his / her final exam grades and interest in chemistry.

[0449] 2. Sending and Receiving Data

[0450] The terminal converts the input data into JSON format and sends it to the server via an HTTP POST request, which the server receives and stores in a database.

[0451] 3. Data Analysis

[0452] The server uses a Python-based generative AI model to analyze the data it receives, identifying the best educational institution and department for the user based on grades and interests.

[0453] 4. Customization using sentiment analysis engine

[0454] The server inputs the analysis results into an emotion analysis engine to analyze the user's emotional state, and customizes recommendations based on this. For example, if a user is in a stressful situation, it might recommend universities with strong support systems.

[0455] 5. Generating and sending recommendation lists

[0456] The server generates a customized recommendation list and sends it to the user's terminal, which displays the received information to the user.

[0457] Prompt Sentence Examples

[0458] "Please enter your academic achievements, such as final exam scores and GPA."

[0459] "What academic subjects and extracurricular activities are you interested in? For example, chemistry, physics, basketball, etc."

[0460] "Tell me about your current mood or emotions. For example, are you feeling stressed or relaxed?"

[0461] As a result, this invention realizes an efficient and emotion-sensitive educational institution selection and application process. By providing optimal recommendations based not only on the user's grades and interests, but also using an emotion analysis engine, it is possible to provide the optimal learning environment and application support for the user.

[0462] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0463] Step 1: User Data Entry

[0464] Users enter their grades, interests, extracurricular activities, etc. into the application's input form. Specifically, the user fills in the application's form fields and presses the submit button. The input data includes the user's grades (e.g., GPA, test results), interests (e.g., chemistry, biology), and extracurricular activities (e.g., basketball, music).

[0465] Step 2: Sending and Receiving Data

[0466] The device formats the input data and sends it to the server. Specifically, it converts the input data into JSON format and sends it to the server using an HTTP POST request. The input includes the grades and interest information entered by the user, and the output is the data received by the server.

[0467] Step 3: Store the data

[0468] The server stores the received grade information and interest information in a database. Specifically, it saves the data in a relational database such as MySQL. In this step, the data received by the server is used as input, and the output is saved in the database.

[0469] Step 4: Analysis of performance and interest information

[0470] The server uses a generative AI model to analyze the received data. Specifically, the Python-based AI model takes grade information and interest information as input and performs data operations to identify the most suitable educational institutions and departments. The output is a list of the most suitable educational institutions and departments.

[0471] Step 5: Customizing with a sentiment analysis engine

[0472] The server further analyzes the AI ​​analysis results using an emotion analysis engine, customizing the results to take the user's emotional state into account. Specifically, the emotion analysis engine uses the results of the AI ​​model and the user's emotional data as input data, and generates customized recommendation information as output.

[0473] Step 6: Generate and submit a recommendation list

[0474] The server generates a customized recommendation list and sends it to the user's device. Specifically, it converts the recommendation list into text or JSON format and sends it as an HTTP response. In this step, the recommendation information customized by the sentiment analysis engine is used as input, and the output is the recommendation list sent to the user's device.

[0475] Step 7: Viewing Recommendations

[0476] The device displays the received recommendation list to the user. Specifically, it uses a UI component for visually displaying the received data to provide information to the user in an easy-to-read format. The input includes the recommendation list received from the server, and the output is the visually displayed recommendation results.

[0477] Specific working example:

[0478] High school students enter their grades and areas of interest into the app.

[0479] The app converts the input data into JSON format and sends it to the server.

[0480] The server stores the data in a database.

[0481] AI models analyze grade and interest information to identify the most suitable educational institutions and departments.

[0482] A sentiment analysis engine takes into account the user's stress level to customize recommendations.

[0483] The final recommendation list is sent to the user's terminal and displayed to the user.

[0484] (Application example 2)

[0485] 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."

[0486] Conventional recommendation systems for educational institutions and departments provide optimal options based on a user's grades and interests, but rarely take into account the user's emotional state. As a result, users may receive recommendation results while feeling stressed or anxious, which could lead to decisions that differ from their original intentions. Furthermore, the lack of reminder notifications for important deadlines can lead users to forget submission deadlines. These issues create a need for systems that can provide users with more accurate options.

[0487] 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.

[0488] In this invention, the server includes means for receiving the user's grade information and interest information, means for performing analysis to recommend the most suitable educational institution and department based on the user's grade information and interest information, means for providing the user with a list of recommended educational institutions and departments based on the analysis results, means for recognizing an emotional state associated with the received grade information and interest information, and means for generating customized recommendation information based on the emotional state. This enables the user to select the most suitable educational institution or department taking into consideration the user's emotional state, and makes it possible to realize recommendations that reduce stress and anxiety.

[0489] "Academic record information" refers to information about a user's academic performance at an educational institution, such as academic record, grade point average, and test results.

[0490] "Interest information" is information about the user's fields of interest, topics, academic interests, and extracurricular activities.

[0491] The "means for performing analysis" is a method of processing data to recommend the most suitable educational institution and faculty based on the user's grade information and interest information.

[0492] The "recommended list" is a list of educational institutions and faculties suitable for the user, generated based on the analysis results.

[0493] An "emotional state" is a state that represents a user's current mood or emotion, such as stress, anxiety, or joy.

[0494] An "emotion engine" is a device or software that recognizes a user's emotional state and customizes information based on that state.

[0495] "Customized recommendation information" refers to recommendation information for the most suitable educational institution or department that is generated by taking into consideration the user's emotional state in addition to their academic record and interest information.

[0496] A "paper abstract database" is a database that stores summary information on research papers, and allows searches for specific fields or keywords.

[0497] "Application requirements" refer to the conditions, documents to be submitted, schedules, etc. that must be met when applying to an educational institution or department.

[0498] "Reminder notification" is a notification function that automatically notifies users of important deadlines and schedules.

[0499] "Warning" refers to providing information to alert users to specific matters.

[0500] "Advice" is specific instructions or suggestions to help users make good decisions in applying and choosing educational institutions.

[0501] A specific embodiment of the present invention will be described below. This system recommends the most suitable educational institution and department based on the user's grades and interests. Furthermore, an emotion engine is used to analyze the user's emotional state and generate customized recommendation information.

[0502] System Program Overview

[0503] 1. Data entry: Users use a smartphone or head-mounted display to enter grade information and areas of interest into the application.

[0504] 2. Data transmission and reception: Data entered by the user is formatted and sent to the server.

[0505] 3. AI analysis: The server stores the received grade information and interest information in a database and analyzes it using a generative AI model.

[0506] 4. Emotion engine: The server analyzes the user's emotional state in real time using devices such as a webcam.

[0507] 5. Recommendation list generation: Based on the analysis results and emotional state, the server generates an optimized recommendation list of educational institutions and departments and sends it to the user's device.

[0508] 6. Display Results: The device displays the results to the user and provides reminders and alerts as special advice.

[0509] Hardware and software used

[0510] Hardware: Smartphone, head-mounted display, webcam

[0511] Software: Generative AI models for AI analysis, EmotionRecognition library for emotion analysis, database management system

[0512] Detailed processing instructions

[0513] The server first receives the user's grades and interests. This information is formatted and stored in a database. Next, a generative AI model is used to analyze the data and identify the most suitable educational institution and department for the user. At the same time, the server uses the EmotionRecognition library to analyze the user's emotional state in real time. This allows the server to generate customized recommendations that take into account the user's stress and anxiety.

[0514] For example, if a high school student inputs their grades and interest in "environmental science," the server will recognize their emotional state as stressed and prioritize recommendations for universities with strong support systems. Along with the recommendations, the user's device will display reminders and specific instructions about important deadlines.

[0515] Example prompt sentence:

[0516] A high school senior entered grade information of "4.2 GPA" and area of ​​interest of "environmental science." The system analyzed the student's emotional state as being high in stress and recommended an environmental science university with a strong support system.

[0517] As described above, the present invention supports users in selecting an educational institution that is optimal for them and takes into consideration their emotional state.

[0518] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0519] Step 1:

[0520] Users use a smartphone or head-mounted display to input grade and interest information into the application, including grade point averages, test results, academic interests, and themes. The input data is then formatted for consistency.

[0521] Input: Grade information, interest information

[0522] Output: Formatted grade and interest information

[0523] Step 2:

[0524] The device transmits formatted performance and interest information to a server, where the data is transmitted using a secure communications protocol.

[0525] Input: Formatted grade and interest information

[0526] Output: Send data to the server

[0527] Step 3:

[0528] The server stores the received grade information and interest information in a database, which accumulates data for each user and is used for later analysis.

[0529] Input: Achievement information and interest information sent to the server

[0530] Output: Information stored in a database

[0531] Step 4:

[0532] The server uses a generative AI model to analyze the grade and interest information stored in the database, which identifies the educational institutions and departments that are best suited to the user.

[0533] Input: Grades and interest information stored in the database

[0534] Output: Analysis results for recommendations (list format)

[0535] Step 5:

[0536] The server analyzes the user's emotional state in real time using a webcam and the EmotionRecognition library for emotion analysis. The results of the emotion analysis are also saved as data.

[0537] Input: Real-time video of user

[0538] Output: User's emotional state data

[0539] Step 6:

[0540] The server generates an optimized list of recommended educational institutions and departments based on the analysis results and emotional state data. Taking into account the emotional state, it recommends educational institutions with strong support systems for users who are under stress.

[0541] Input: Analysis results, emotional state data

[0542] Output: A customized recommendation list

[0543] Step 7:

[0544] The server then transmits the generated customized recommendation list to the user's device using a secure communication protocol.

[0545] Input: Customized recommendation list

[0546] Output: sent to the user's device

[0547] Step 8:

[0548] The device receives and displays the recommendations to the user, and also provides reminders and specific reminders for important deadlines.

[0549] Input: Customized recommendation list

[0550] Output: Display of recommendation list, notification of reminders and reminders

[0551] Through the above processing steps, the user can receive recommendations for the most suitable educational institution and department that take into consideration the user's emotional state.

[0552] 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.

[0553] 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.

[0554] 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.

[0555] [Second embodiment]

[0556] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0557] 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.

[0558] 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).

[0559] 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.

[0560] 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.

[0561] 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).

[0562] 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.

[0563] 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.

[0564] 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.

[0565] 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.

[0566] 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.

[0567] 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."

[0568] The following describes in detail the mode for carrying out the present invention. The present invention is a system designed to streamline the information gathering and application process when selecting an educational institution. Based on the user's grades and interests, the system recommends the most suitable educational institutions and departments, and generates the checklists and schedules required for application. It also matches educational institutions based on research content.

[0569] Customized proposals for universities and departments using AI

[0570] 1. User data entry

[0571] Users: Enter information into the application, such as grades, interests, and extracurricular activities.

[0572] 2. Sending and Receiving Data

[0573] Terminal: Sends the entered data to the server.

[0574] 3. Data Analysis

[0575] Server: Analyzes the received grade and interest information and identifies the appropriate educational institution and department using an AI model.

[0576] 4. Generating and sending recommendation lists

[0577] Server: Generates a list of recommended educational institutions and departments based on the analysis results and sends it to the user's device.

[0578] 5. Display of recommendation results

[0579] Terminal: Displays the received recommendation list to the user.

[0580] Examples:

[0581] Let's say high school student Sato wants to study chemistry. Sato enters his grades and interest in chemistry into the app. The server performs AI analysis based on this information, creates a list of universities with excellent chemistry programs, and sends the recommendation results to Sato's device.

[0582] Research content matching

[0583] 1. Enter keywords

[0584] User: Enters research interests and keywords into the application.

[0585] 2. Sending and Receiving Data

[0586] Terminal: Sends the entered keyword information to the server.

[0587] 3. Research database collation

[0588] Server: Searches a database of paper abstracts to identify research fields that match the entered keywords.

[0589] 4. Generating and sending matching results

[0590] Server: Generates a list of recommended educational institutions and laboratories based on the identified research field and sends it to the user's device.

[0591] 5. Display of matching results

[0592] Terminal: Displays the received matching results to the user.

[0593] Examples:

[0594] Let's say Tanaka, who is interested in physics, wants to study "theory of relativity." Tanaka enters "theory of relativity" as a keyword into the app. The server searches a database of paper abstracts, identifies universities and laboratories conducting research on the theory of relativity, and sends a list of recommendations to Tanaka's device.

[0595] Auto-generated application checklists and schedules

[0596] 1. Enter application information

[0597] User: Enters information about the institution and department to which they wish to apply into the application.

[0598] 2. Sending and Receiving Data

[0599] Terminal: Sends the entered application information to the server.

[0600] 3. Analysis of application requirements

[0601] Server: Obtains application requirements for each educational institution and department and matches them with the user's application information.

[0602] 4. Generate checklists and schedules

[0603] Server: Automatically generates a list of documents to be submitted and an application schedule based on application requirements.

[0604] 5. Data transmission and display

[0605] Server: Sends the checklist and schedule to the user's device, which displays it to the user. It also sets reminder notifications.

[0606] Examples:

[0607] Suzuki, who is considering applying to multiple universities, enters the application information for each university into the app. The server retrieves the application requirements for each university, automatically generates a list of documents to be submitted, and an application schedule, which are then sent to Suzuki's device.

[0608] Continuous learning and improvement

[0609] 1. Enter and submit your feedback

[0610] User: Enters feedback about the service into the app and sends it from the device to the server.

[0611] 2. Analyzing feedback and updating the AI ​​model

[0612] Server: Analyzes the feedback and updates the AI ​​model. This update improves recommendation results and matching accuracy from the next time onwards.

[0613] summary

[0614] This invention allows high school students to efficiently select the appropriate educational institution and department, and smoothly progress through the application process. Furthermore, the system is continuously improved through feedback, enabling it to provide more accurate information. This system is realized through mutual cooperation between users, terminals, and servers.

[0615] The processing flow will be explained below.

[0616] Customized proposals for universities and departments using AI

[0617] Step 1:

[0618] Users: Enter information into the application, such as grades, interests, and extracurricular activities.

[0619] Step 2:

[0620] Terminal: Formats the entered data and generates a request to send to the server.

[0621] Step 3:

[0622] Server: Stores the received user performance information and interest information in a database and prepares for analysis.

[0623] Step 4:

[0624] Server: Uses AI models to analyze the user's grades and interests to identify the most suitable educational institution and department.

[0625] Step 5:

[0626] Server: Generates a list of recommended educational institutions and departments based on the analysis results.

[0627] Step 6:

[0628] Server: Sends the recommendation list to the user's device.

[0629] Step 7:

[0630] Terminal: Formats the received recommendation list and displays it to the user.

[0631] Research content matching

[0632] Step 1:

[0633] User: Enters research interests and keywords into the application.

[0634] Step 2:

[0635] Terminal: Formats the entered keywords and generates a request to send to the server.

[0636] Step 3:

[0637] Server: Searches the institution's paper abstract database based on the received keywords.

[0638] Step 4:

[0639] Server: Identifies research fields that match keywords from the search results and generates a recommendation list.

[0640] Step 5:

[0641] Server: Sends the generated recommendation list to the user's device.

[0642] Step 6:

[0643] Terminal: Formats the received recommendation list and displays it to the user.

[0644] Auto-generated application checklists and schedules

[0645] Step 1:

[0646] User: Enters information about the institution and department to which they wish to apply into the application.

[0647] Step 2:

[0648] Terminal: Formats the entered application information and generates a request to send to the server.

[0649] Step 3:

[0650] Server: Stores the received application information in a database and retrieves application requirements for each educational institution and department from the database.

[0651] Step 4:

[0652] Server: Compares the acquired application requirements with the user's application information and generates a list of documents to be submitted and an application schedule.

[0653] Step 5:

[0654] Server: Sends the generated list of submitted documents and application schedule to the user's terminal.

[0655] Step 6:

[0656] Terminal: Formats received submission lists and application schedules, displays them to the user, and sets reminder notifications.

[0657] Gathering feedback and updating the AI ​​model

[0658] Step 1:

[0659] Users: Enter feedback about the service into the application.

[0660] Step 2:

[0661] Terminal: Formats the input feedback and generates a request to send to the server.

[0662] Step 3:

[0663] Server: Stores the received feedback in a database and prepares it for analysis.

[0664] Step 4:

[0665] Server: Analyzes the feedback and extracts necessary improvements to the AI ​​model.

[0666] Step 5:

[0667] Server: Update the AI ​​model based on the improvements and improve recommendation accuracy from next time onwards.

[0668] The above is a specific process flow for implementing the present invention, which significantly streamlines the college selection and application process for high school students, their parents, and educational counselors.

[0669] Example 1

[0670] 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."

[0671] In the traditional graduate school and application process, users had difficulty selecting the appropriate educational institution and department from the vast amount of information available. It was also time-consuming to individually research each institution's application requirements and manage the necessary documents and schedules. Furthermore, matching educational institutions based on research content had to be done manually, which was time-consuming and labor-intensive.

[0672] 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.

[0673] In this invention, the server includes a means for receiving grade information and interest information, a means for performing analysis to recommend educational institutions and departments based on the grade information and interest information, a means for providing a list of educational institutions and departments based on the analysis results, and a means for receiving feedback and updating the analysis means, thereby enabling users to quickly and accurately select appropriate educational institutions and departments.

[0674] "Academic performance information" is data that indicates the user's academic performance and evaluation.

[0675] "Interest information" is data that indicates the fields or themes in which a user is interested.

[0676] "Educational institution" refers to a school or university providing higher education.

[0677] A "faculty" is a department within a university or educational institution that is responsible for a particular field of education or research.

[0678] The "analysis means" is a function that performs calculations to identify appropriate educational institutions and departments based on grade information and interest information.

[0679] The "recommended list" is a list of educational institutions and departments recommended based on the analysis results.

[0680] "Feedback" is data showing user evaluations and opinions, and is used to improve the system.

[0681] A "literature abstract database" is a database that collects summary information from academic papers.

[0682] "Research content" refers to academic issues or themes in a specific field.

[0683] A "research facility" is a department or laboratory within an educational institution that conducts specific research.

[0684] "Application requirements" refers to the conditions and documents that must be submitted when applying to an educational institution.

[0685] The "list of documents to be submitted" is a list of documents required for application.

[0686] An "application schedule" is a plan that outlines important dates and deadlines in the application process.

[0687] "Reminder Notification" is a feature that notifies you in advance of important deadlines and events.

[0688] The system of the present invention is designed to streamline the educational institution selection and application process. Through mutual cooperation between users, terminals, and servers, the system recommends appropriate educational institutions and departments, enabling a smooth application process. Specific embodiments of the system are described below.

[0689] 1. Entering user data

[0690] Users use a dedicated application to enter information such as grades, areas of interest, and extracurricular activities. This information is stored on the device as JSON format data. For example, a user might enter into the application that "I'm interested in physics and belong to the science club as an extracurricular activity."

[0691] 2. Sending and Receiving Data

[0692] The terminal sends the entered data to the server. This transmission uses an API call via the Internet. Specifically, when the user presses the "Send" button, the input data is converted into JSON format and sent to the server.

[0693] 3. Data Analysis

[0694] The server uses a generative AI model to analyze the received grade and interest information. This analysis is performed using cloud services such as Google Cloud AI and AWS SageMaker. The server preprocesses the parsed JSON data and converts it into a format suitable for the AI ​​model for analysis.

[0695] 4. Generate and send recommendation list

[0696] The server generates a list of recommended educational institutions and departments based on the analysis results and sends it to the device. Specifically, it converts the analysis results into JSON format, makes an API call to the user's device, and sends the list of recommendations.

[0697] 5. Display of recommendation results

[0698] The device parses the recommendation list received from the server and displays it on the application UI, allowing the user to view the recommended educational institutions and departments on the screen.

[0699] 6. Use of Feedback

[0700] Users input feedback about the recommendation list and services provided. The device then sends this feedback to the server. The server analyzes the received feedback and updates the AI ​​model to improve recommendation results and matching accuracy from the next time onwards.

[0701] Specific examples

[0702] Examples:

[0703] For example, if high school student Sato wants to study chemistry, he or she can enter his or her grades and interest in chemistry into the app. The server performs AI analysis based on this information, lists universities with excellent chemistry programs, and sends the recommendation results to Sato's device. Sato can then review the recommendation list and consider the career path that best suits his or her aspirations.

[0704] Generative AI model input example:

[0705] "I'm interested in chemistry and I'd like to know which universities have good chemistry programs."

[0706] "Please recommend a university where I can study the theory of relativity."

[0707] "Please tell me the documents and schedule required to apply to the university I want to attend."

[0708] This invention allows users to efficiently select appropriate educational institutions and departments, and smoothly progress through the application process. The system provides highly accurate information through mutual cooperation between users, terminals, and servers.

[0709] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0710] Step 1:

[0711] User Data Entry

[0712] User: Enters information such as grades, areas of interest, and extracurricular activities into the application. Specifically, the user enters the required information into a form in the dedicated application and presses the "Submit" button. This data is temporarily saved on the device in JSON format.

[0713] Input: Grades, interests, extracurricular activities

[0714] Output: JSON format data

[0715] Step 2:

[0716] Sending data

[0717] Terminal: Sends JSON format data to the server. Specifically, when the "Send" button is pressed, the terminal executes an API call to send the data to the server. SSL is used during communication to ensure data security.

[0718] Input: JSON format data

[0719] Output: API calls to the server and data sent

[0720] Step 3:

[0721] Receiving and Parsing Data

[0722] Server: Parses the received data from JSON format and converts it into an internal data structure. Specifically, it analyzes the received JSON data and organizes it into data objects according to grades, areas of interest, and extracurricular activities.

[0723] Input: JSON format data

[0724] Output: Analysis and object format data

[0725] Step 4:

[0726] Data analysis

[0727] Server: Uses the parsed data to input the generative AI model. Specifically, it uses Google Cloud AI or AWS SageMaker to analyze grade information and areas of interest to identify the most suitable educational institution and department for the user. It then applies the calculations and evaluation logic of the generative AI model to extract appropriate recommendations.

[0728] Input: Analysis and object-formatted data

[0729] Output: Analysis results (recommendation list)

[0730] Step 5:

[0731] Generating and sending recommendation lists

[0732] Server: The analysis results are converted back into JSON format and sent to the user's device. Specifically, the generated recommendation list is sent to the device via an API call.

[0733] Input: Analysis results

[0734] Output: Recommendation list in JSON format, and API calls to the device

[0735] Step 6:

[0736] Receiving and displaying recommendations

[0737] Device: Parses the recommendation list received from the server and displays it in a format suitable for the user interface. Specifically, it interprets the received data and displays it in a list view or dashboard.

[0738] Input: JSON formatted recommendation list from the server

[0739] Output: Recommendation list displayed in a user interface

[0740] Step 7:

[0741] Matching research content

[0742] User: Enters research interests and keywords (e.g., "quantum mechanics") into the application.

[0743] Terminal: Sends the entered keyword to the server.

[0744] Server: Searches the institution's literature abstract database to identify research areas that match the keywords entered.

[0745] Specifically, the server executes a database query to list relevant papers and research fields, converts the analysis results back into JSON format, and sends them to the user's device.

[0746] Terminal: Parses and displays the list of recommended fields of study and educational institutions.

[0747] Input: Research Keywords

[0748] Output: A list of educational institutions that match the field of study

[0749] Step 8:

[0750] Application information management

[0751] User: Enters information about the institution and department to which they wish to apply into the application.

[0752] Terminal: Sends the entered application information to the server.

[0753] Server: Acquires and collates application requirements. Specifically, it uses web scraping and APIs to collect application requirements from each educational institution and verifies that they match the user's application information. It automatically generates a list of documents to be submitted and an application schedule based on the application requirements, converts them back into JSON format, and sends them to the device.

[0754] Terminal: Parse and view automatically generated submission lists and application schedules, and set reminders for important deadlines.

[0755] Input: Application information

[0756] Output: Application requirements, list of documents to be submitted, application schedule, reminder notices

[0757] Step 9:

[0758] Feedback input and analysis

[0759] User: Enters feedback on the recommendations and services provided.

[0760] Terminal: Sends the entered feedback to the server.

[0761] Server: Analyzes the feedback and updates the AI ​​model. Specifically, it analyzes the feedback data and uses it as training data to improve the accuracy of the generative AI model.

[0762] Input: Feedback data

[0763] Output: Updated analysis method

[0764] This allows users to quickly and accurately select the appropriate educational institution and department, and smoothly progress through the application process.

[0765] (Application example 1)

[0766] 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."

[0767] Conventional educational institution recommendation systems simply recommend suitable universities and departments based on academic records and interests. However, they lack a means to provide users with customized educational institution advertisements that are optimal for them, making it difficult to provide information efficiently and effectively. There was also a need for a way to effectively promote educational institutions through advertisements while providing important information for the application process.

[0768] 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.

[0769] In this invention, the server includes means for receiving the user's grade information and interest information, means for performing analysis to recommend the most suitable educational institution based on the grade information and interest information, means for providing a list of the recommended educational institutions based on the analysis results, and means for generating advertising data and displaying advertisements for educational institutions optimized for the user's characteristics. This makes it possible to provide the user with information on the most suitable educational institution, and by displaying customized advertisements, enables effective promotional activities.

[0770] "Grade information" is data indicating grades and evaluations for each subject that a user has obtained at school or the like.

[0771] "Interest information" is information relating to academic fields or research themes in which a user is particularly interested.

[0772] "Educational institutions" are facilities or organizations that provide higher education, such as universities and vocational schools.

[0773] A "faculty" is an organization within an educational institution such as a university that conducts study and research in a specific academic field.

[0774] "Analysis" is the process of performing calculations and evaluations using mathematical models and algorithms based on received performance information and interest information.

[0775] The "list" is a table listing the names and information of recommended educational institutions, departments, and laboratories.

[0776] "Advertising Data" is digital data generated to promote a particular educational institution.

[0777] "Customized advertising" refers to promotional advertising whose content is tailored based on a user's characteristics and interests.

[0778] A "paper abstract database" is a data store that collects summaries of numerous papers and is used to search for research content.

[0779] "Application information" refers to information about the documents and procedures required when a user applies to enroll in a particular educational institution or faculty.

[0780] "Application requirements" refer to the conditions and documents that must be met in order to enter a particular educational institution or faculty.

[0781] "List of documents to be submitted" refers to a list of documents required for application.

[0782] An "application schedule" is a timeline that shows the deadlines and schedule for each step in the application process.

[0783] "Reminder notification" is a function that notifies users in advance so that they do not forget important deadlines.

[0784] This invention is a system that recommends optimal educational institutions and departments based on a user's grades and interests. It also matches laboratories and educational institutions based on the user's research interests and displays customized advertisements, thereby providing efficient information provision and promotion.

[0785] To realize this system, the following hardware and software are used.

[0786] Hardware: User's smartphone, server

[0787] Software: Python, REST API, JSON, Scikit-learn or TensorFlow

[0788] System configuration

[0789] User Data Entry

[0790] Users use a smartphone app to input their grades, areas of interest, and research keywords, and the application sends this information to the server in JSON format.

[0791] Data analysis

[0792] The server analyzes the received grades and interest information using AI models (based on Scikit-learn and TensorFlow) to identify the most suitable educational institutions and departments. The analysis results are generated as a recommendation list.

[0793] Generating a recommendation list

[0794] Based on the analysis results, a list of the most suitable educational institutions and departments is generated, which is sent in JSON format to the user's smartphone and displayed within the app.

[0795] Generate personalized ads

[0796] The server generates advertising data based on the analysis results and user characteristics, which includes information about the educational institution and is displayed in a customized format to the user.

[0797] Application information management

[0798] When a user inputs information about the educational institution and department to which they wish to apply, the server retrieves the application requirements and automatically generates a list of documents to be submitted and an application schedule, allowing users to efficiently proceed with their application.

[0799] Reminders

[0800] For important deadlines, smartphone apps can set reminder notifications to remind users not to forget about them.

[0801] Specific examples

[0802] Recommendations based on user performance information

[0803] High school students enter their grades (90 for math, 95 for science, 85 for English) and areas of interest (science, physics) into the app. This data is sent to a server, which analyzes it and generates a list of the most suitable universities and departments (e.g., universities with a strong science focus). This list is accompanied by corresponding customized university advertisements.

[0804] Prompt Sentence Examples

[0805] An example of a user prompt would be, "My grades are 90 in math, 95 in science, and 85 in English. My areas of interest are science and physics." The system will then recommend and display advertisements for the most suitable educational institutions.

[0806] In this way, the present invention makes it possible to provide users with information about educational institutions and to promote their advertisements efficiently and effectively.

[0807] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0808] Step 1:

[0809] The user's device is started, and the user opens the app and enters their grades, areas of interest, and research keywords. The input information (grades, areas of interest, and research keywords) is converted into JSON format and sent to the server.

[0810] Step 2:

[0811] The server receives JSON-formatted data (grade information, areas of interest, research keywords) sent from the device. The server passes this data to an AI model (Scikit-learn or TensorFlow) for analysis. The AI ​​model identifies the most suitable educational institutions and departments based on the input data and generates a list of recommendations. The output is a list of recommended educational institutions and departments.

[0812] Step 3:

[0813] The server returns the generated recommendation list in JSON format to the device, which receives it and visually displays it to the user. The display is in list format, including detailed information about the recommended educational institutions and departments.

[0814] Step 4:

[0815] The server further generates customized advertising data based on the analysis results and the user's characteristics. The advertising data is configured in a manner optimized for the user and includes specific information and promotional content from the educational institution. The output is the customized advertising data.

[0816] Step 5:

[0817] The server transmits the generated advertisement data to the terminal, which receives it and displays the advertisement to the user along with the recommendation list. The advertisement is visually integrated into the interface and is designed to attract the user's attention.

[0818] Step 6:

[0819] Users enter their desired application information into the app. The device converts this information into JSON format and sends it to the server. This application information includes the desired educational institution and department.

[0820] Step 7:

[0821] The server receives the application information sent from the terminal and retrieves the application requirements of each educational institution and department from the database. The server uses this information to automatically generate a list of documents to be submitted and an application schedule. The output is a list of documents to be submitted and an application schedule.

[0822] Step 8:

[0823] The server sends the generated list of documents to be submitted and the application schedule to the terminal, which receives it and displays it in an easy-to-understand manner for the user. A reminder notification function is also set up to notify the user of important deadlines.

[0824] This flow allows users to receive recommendations for the most suitable educational institutions based on their academic records and interests, display customized advertisements, and streamline the application process, all within a single application.

[0825] 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.

[0826] The present invention provides a system for recommending educational institutions and departments based on a user's grades and interests, streamlining the application process, and also provides customized recommendation information based on the user's emotions by combining it with an emotion engine that recognizes the user's emotions.

[0827] Receiving and analyzing user performance and interest information

[0828] 1. User data entry

[0829] Users: Enter information into the application, such as grades, interests, and extracurricular activities.

[0830] 2. Sending and Receiving Data

[0831] Terminal: Formats the entered data and sends it to the server.

[0832] 3. Data Analysis

[0833] Server: Stores the received grade information and interest information in a database and prepares for analysis.

[0834] 4. AI-based analysis

[0835] Server: Uses AI models to analyze the user's grades and interests to identify the most suitable educational institution and department.

[0836] 5. Customization with Emotion Engine

[0837] Server: The AI ​​analysis results are further analyzed by the emotion engine to generate customized recommendations based on the user's emotional state.

[0838] 6. Generating and Sending Recommendation Lists

[0839] Server: Generates a recommendation list optimized by the emotion engine and sends it to the user's device.

[0840] 7. Display of recommendation results

[0841] Terminal: Displays the received recommendation list to the user.

[0842] Examples:

[0843] High school student Yamada enters his grades and interests into the app. The server receives and analyzes this information, and an AI model identifies the most suitable university and department. At the same time, an emotion engine analyzes Yamada's emotions when he enters the information, and if he is in a stressful situation, it recommends a university with a strong support system.

[0844] Research content matching

[0845] 1. Enter keywords

[0846] User: Enters research interests and keywords into the application.

[0847] 2. Sending and Receiving Data

[0848] Terminal: Formats the entered keywords and sends them to the server.

[0849] 3. Research database collation

[0850] Server: Searches a database of paper abstracts to identify research fields that match the entered keywords.

[0851] 4. Generating and sending matching results

[0852] Server: Generates a list of recommended educational institutions and laboratories based on the identified research field, customizes it according to the user's emotional state, and sends it to the user's device.

[0853] 5. Display of matching results

[0854] Terminal: Formats the received recommendation list and displays it to the user.

[0855] Examples:

[0856] Sato, who is interested in physics, enters "quantum mechanics" as a keyword. The server searches a database of paper abstracts based on the keyword and identifies universities and laboratories conducting relevant research. At the same time, the emotion engine takes Sato's emotional state into account and prioritizes recommending universities with low stress and good research environments.

[0857] Auto-generated application checklists and schedules

[0858] 1. Enter application information

[0859] User: Enters information about the institution and department to which they wish to apply into the application.

[0860] 2. Sending and Receiving Data

[0861] Terminal: Formats the entered application information and sends it to the server.

[0862] 3. Analysis of application requirements

[0863] Server: Obtains application requirements for each educational institution and department and matches them with the user's application information.

[0864] 4. Generate checklists and schedules

[0865] Server: Automatically generates a list of documents to be submitted and an application schedule based on the application requirements. It also takes into account the user's emotional state, allowing for flexibility in the schedule and adding explanations.

[0866] 5. Data transmission and display

[0867] Server: Sends the generated list of submitted documents and application schedule to the user's terminal, which displays it to the user and sets reminder notifications.

[0868] Examples:

[0869] Mr. Tanaka, who is considering applying to multiple universities, enters the application information for each university into the app. The server receives this information, obtains the application requirements for each university, and generates a list of documents to be submitted and an application schedule. The emotion engine takes Mr. Tanaka's emotional state into account and adds warnings and specific advice to areas where he is likely to feel anxious.

[0870] Gathering feedback and updating the AI ​​model

[0871] 1. Enter and submit your feedback

[0872] User: Enters feedback about the service into the application and sends it to the server from the terminal.

[0873] 2. Analyzing feedback and updating the AI ​​model

[0874] Server: Analyzes the received feedback, extracts necessary improvements to the AI ​​model and emotion engine, and updates the model.

[0875] Examples:

[0876] Users provide feedback after using the system, which the server reads, analyzes areas for improvement in the service, and updates the AI ​​model and emotion engine to provide better recommendations and research matching the next time users use the system.

[0877] As a result, the present invention provides an efficient and emotionally sensitive educational institution selection and application process.

[0878] The processing flow will be explained below.

[0879] Customized proposals for universities and departments using AI

[0880] Step 1:

[0881] Users: Enter information into the application, such as grades, interests, and extracurricular activities.

[0882] Step 2:

[0883] Terminal: Formats the entered data and generates a request to send to the server.

[0884] Step 3:

[0885] Server: Stores the received user performance information and interest information in a database and prepares for analysis.

[0886] Step 4:

[0887] Server: Uses AI models to analyze the user's grades and interests to identify the most suitable educational institution and department.

[0888] Step 5:

[0889] Server: Uses an emotion engine to analyze the emotion data of the user's input in real time and identify the emotional state.

[0890] Step 6:

[0891] Server: Based on the analysis results of the emotion engine, the recommendation results of the AI ​​model are adjusted to generate a recommendation list optimized for the user's emotional state.

[0892] Step 7:

[0893] Server: Sends the optimized recommendation list to the user's device.

[0894] Step 8:

[0895] Terminal: Formats the received recommendation list and displays it to the user.

[0896] Examples:

[0897] High school student Yamada enters his grades and interests into the app. The server receives and analyzes this information, and an AI model identifies the appropriate university and department. At the same time, an emotion engine analyzes Yamada's emotional state (for example, whether his stress level is high or low), generates a list of recommended universities with better support systems, and sends it to Yamada's device.

[0898] Research content matching

[0899] Step 1:

[0900] User: Enters research interests and keywords into the application.

[0901] Step 2:

[0902] Terminal: Formats the entered keywords and generates a request to send to the server.

[0903] Step 3:

[0904] Server: Searches the institution's paper abstract database based on the received keywords.

[0905] Step 4:

[0906] Server: From the search results, identify research fields that match the keywords and generate a list of recommendations.

[0907] Step 5:

[0908] Server: Uses an emotion engine to analyze the user's emotional state and match appropriate educational institutions and laboratories based on a recommended list of research fields.

[0909] Step 6:

[0910] Server: Sends the optimized research recommendation list to the user's device.

[0911] Step 7:

[0912] Terminal: Formats the received recommendation list and displays it to the user.

[0913] Examples:

[0914] Sato, who is interested in physics, enters "quantum mechanics" as a keyword. The server searches a database of paper abstracts based on the entered keywords and identifies suitable universities and research laboratories. At the same time, the emotion engine analyzes Sato's emotional state and generates a list of recommendations focusing on universities with low stress and good research environments, which is sent to Sato's device.

[0915] Auto-generated application checklists and schedules

[0916] Step 1:

[0917] User: Enters information about the institution and department to which they wish to apply into the application.

[0918] Step 2:

[0919] Terminal: Formats the entered application information and generates a request to send to the server.

[0920] Step 3:

[0921] Server: Stores the received application information in a database and obtains the application requirements of each educational institution and department.

[0922] Step 4:

[0923] Server: Compares the acquired application requirements with the user's application information and generates a list of documents to be submitted and an application schedule.

[0924] Step 5:

[0925] Server: Uses an emotion engine to analyze the user's emotional state and optimize the filing list and application schedule.

[0926] Step 6:

[0927] Server: Sends the optimized submission document list and application schedule to the user's terminal.

[0928] Step 7:

[0929] Terminal: Formats and displays received submission lists and filing schedules to the user, and sets reminders for important deadlines.

[0930] Examples:

[0931] Mr. Tanaka, who is considering applying to multiple universities, enters the application information for each university into the app. The server receives this information, obtains the application requirements for each university, and generates a list of documents to be submitted and an application schedule. The emotion engine analyzes Mr. Tanaka's emotional state and adds warnings and specific advice to areas where he is likely to feel anxious.

[0932] Gathering feedback and updating the AI ​​model

[0933] Step 1:

[0934] Users: Enter feedback about the service into the application.

[0935] Step 2:

[0936] Terminal: Formats the input feedback and generates a request to send to the server.

[0937] Step 3:

[0938] Server: Stores the received feedback in a database and prepares it for analysis.

[0939] Step 4:

[0940] Server: Analyzes the feedback and extracts necessary improvements to the AI ​​model and emotion engine.

[0941] Step 5:

[0942] Server: Update the AI ​​model and emotion engine based on the improvements, and improve the accuracy of recommendations from next time onwards.

[0943] The above is a specific processing flow for implementing the present invention, which significantly improves the efficiency of the university selection and application process for high school students, their parents, and educational counselors, while also enabling the provision of services that are sensitive to the user's emotions.

[0944] Example 2

[0945] 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."

[0946] Conventional educational institution recommendation systems are limited to simple recommendations based on users' grades and interests, and lack customization that takes into account the user's emotional state. Furthermore, in matching optimal research fields and the application process, efficient recommendations and schedule management that take into account the user's emotional state are lacking.

[0947] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving the user's grade information and interest information, a means for performing an analysis to recommend the most suitable educational institution and faculty based on the user's grade information and interest information, a means for further analyzing the analysis results with an emotion analysis engine and customizing the recommendation information based on the user's emotional state, and a means for providing the customized recommendation information to the user. This enables customized recommendations that take into account the user's emotional state in addition to the user's grade information and interest information.

[0948] "Academic achievement information" refers to data that represents a user's academic achievements at an educational institution, such as academic records, test results, and evaluation scores.

[0949] "Interest information" is information that indicates a user's personal interests, such as fields of interest, subjects, extracurricular activities, and future career paths.

[0950] "Analysis" refers to analyzing and processing data for a specific purpose based on received information.

[0951] "Educational institutions" refers to organizations and facilities that teach academic subjects or skills, such as universities, technical colleges, and vocational schools.

[0952] An "emotion analysis engine" refers to an algorithm or software tool that analyzes a user's emotional and psychological state based on user input data and behavioral data.

[0953] "Recommendation" refers to suggesting the best option to a user based on specific criteria.

[0954] A database is an information system that systematically organizes and stores large amounts of data, and efficiently searches and manages them.

[0955] "Application information" refers to data such as personal information and desired information required when applying to an educational institution or faculty of a user's choice.

[0956] "Document List" refers to the list of documents required for the application process at an educational institution.

[0957] An "application schedule" is a plan showing the various steps and deadlines required for filing an application.

[0958] "Reminder notification" refers to a notification function that notifies users when a specific deadline or event is approaching.

[0959] The present invention is a system that recommends educational institutions and departments based on a user's grades and interests, streamlining the application process. Furthermore, by combining it with an emotion analysis engine that recognizes the user's emotions, the system provides customized recommendation information based on the user's emotions.

[0960] Hardware and software used

[0961] This system uses the following hardware and software:

[0962] 1. Hardware

[0963] Terminal: A device used by a user to input information, such as a smartphone or computer.

[0964] Server: A cloud-based server for analyzing the received data and generating recommendation information.

[0965] 2. Software

[0966] Input forms: web and mobile applications that run on devices.

[0967] Database: A relational database such as MySQL.

[0968] Generative AI models: Python-based AI analysis tool.

[0969] Sentiment analysis engine: Algorithms and software (e.g., natural language processing tools and machine learning models) for analyzing a user's emotional state.

[0970] A concrete example of the processing flow

[0971] Receiving and analyzing user performance and interest information

[0972] 1. User data entry

[0973] A user enters his / her grades, areas of interest, extracurricular activities, etc. into an application input form. For example, a high school student enters his / her final exam grades and interest in chemistry.

[0974] 2. Sending and Receiving Data

[0975] The terminal converts the input data into JSON format and sends it to the server via an HTTP POST request, which the server receives and stores in a database.

[0976] 3. Data Analysis

[0977] The server uses a Python-based generative AI model to analyze the data it receives, identifying the best educational institution and department for the user based on grades and interests.

[0978] 4. Customization using sentiment analysis engine

[0979] The server inputs the analysis results into an emotion analysis engine to analyze the user's emotional state, and customizes recommendations based on this. For example, if a user is in a stressful situation, it might recommend universities with strong support systems.

[0980] 5. Generating and sending recommendation lists

[0981] The server generates a customized recommendation list and sends it to the user's terminal, which displays the received information to the user.

[0982] Prompt Sentence Examples

[0983] "Please enter your academic achievements, such as final exam scores and GPA."

[0984] "What academic subjects and extracurricular activities are you interested in? For example, chemistry, physics, basketball, etc."

[0985] "Tell me about your current mood or emotions. For example, are you feeling stressed or relaxed?"

[0986] As a result, this invention realizes an efficient and emotion-sensitive educational institution selection and application process. By providing optimal recommendations based not only on the user's grades and interests, but also using an emotion analysis engine, it is possible to provide the optimal learning environment and application support for the user.

[0987] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0988] Step 1: User Data Entry

[0989] Users enter their grades, interests, extracurricular activities, etc. into the application's input form. Specifically, the user fills in the application's form fields and presses the submit button. The input data includes the user's grades (e.g., GPA, test results), interests (e.g., chemistry, biology), and extracurricular activities (e.g., basketball, music).

[0990] Step 2: Sending and Receiving Data

[0991] The device formats the input data and sends it to the server. Specifically, it converts the input data into JSON format and sends it to the server using an HTTP POST request. The input includes the grades and interest information entered by the user, and the output is the data received by the server.

[0992] Step 3: Store the data

[0993] The server stores the received grade information and interest information in a database. Specifically, it saves the data in a relational database such as MySQL. In this step, the data received by the server is used as input, and the output is saved in the database.

[0994] Step 4: Analysis of performance and interest information

[0995] The server uses a generative AI model to analyze the received data. Specifically, the Python-based AI model takes grade information and interest information as input and performs data operations to identify the most suitable educational institutions and departments. The output is a list of the most suitable educational institutions and departments.

[0996] Step 5: Customizing with a sentiment analysis engine

[0997] The server further analyzes the AI ​​analysis results using an emotion analysis engine, customizing the results to take the user's emotional state into account. Specifically, the emotion analysis engine uses the results of the AI ​​model and the user's emotional data as input data, and generates customized recommendation information as output.

[0998] Step 6: Generate and submit a recommendation list

[0999] The server generates a customized recommendation list and sends it to the user's device. Specifically, it converts the recommendation list into text or JSON format and sends it as an HTTP response. In this step, the recommendation information customized by the sentiment analysis engine is used as input, and the output is the recommendation list sent to the user's device.

[1000] Step 7: Viewing Recommendations

[1001] The device displays the received recommendation list to the user. Specifically, it uses a UI component for visually displaying the received data to provide information to the user in an easy-to-read format. The input includes the recommendation list received from the server, and the output is the visually displayed recommendation results.

[1002] Specific working example:

[1003] High school students enter their grades and areas of interest into the app.

[1004] The app converts the input data into JSON format and sends it to the server.

[1005] The server stores the data in a database.

[1006] AI models analyze grade and interest information to identify the most suitable educational institutions and departments.

[1007] A sentiment analysis engine takes into account the user's stress level to customize recommendations.

[1008] The final recommendation list is sent to the user's terminal and displayed to the user.

[1009] (Application example 2)

[1010] 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."

[1011] Conventional recommendation systems for educational institutions and departments provide optimal options based on a user's grades and interests, but rarely take into account the user's emotional state. As a result, users may receive recommendation results while feeling stressed or anxious, which could lead to decisions that differ from their original intentions. Furthermore, the lack of reminder notifications for important deadlines can lead users to forget submission deadlines. These issues create a need for systems that can provide users with more accurate options.

[1012] 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.

[1013] In this invention, the server includes means for receiving the user's grade information and interest information, means for performing analysis to recommend the most suitable educational institution and department based on the user's grade information and interest information, means for providing the user with a list of recommended educational institutions and departments based on the analysis results, means for recognizing an emotional state associated with the received grade information and interest information, and means for generating customized recommendation information based on the emotional state. This enables the user to select the most suitable educational institution or department taking into consideration the user's emotional state, and makes it possible to realize recommendations that reduce stress and anxiety.

[1014] "Academic record information" refers to information about a user's academic performance at an educational institution, such as academic record, grade point average, and test results.

[1015] "Interest information" is information about the user's fields of interest, topics, academic interests, and extracurricular activities.

[1016] The "means for performing analysis" is a method of processing data to recommend the most suitable educational institution and faculty based on the user's grade information and interest information.

[1017] The "recommended list" is a list of educational institutions and faculties suitable for the user, generated based on the analysis results.

[1018] An "emotional state" is a state that represents a user's current mood or emotion, such as stress, anxiety, or joy.

[1019] An "emotion engine" is a device or software that recognizes a user's emotional state and customizes information based on that state.

[1020] "Customized recommendation information" refers to recommendation information for the most suitable educational institution or department that is generated by taking into consideration the user's emotional state in addition to their academic record and interest information.

[1021] A "paper abstract database" is a database that stores summary information on research papers, and allows searches for specific fields or keywords.

[1022] "Application requirements" refer to the conditions, documents to be submitted, schedules, etc. that must be met when applying to an educational institution or department.

[1023] "Reminder notification" is a notification function that automatically notifies users of important deadlines and schedules.

[1024] "Warning" refers to providing information to alert users to specific matters.

[1025] "Advice" is specific instructions or suggestions to help users make good decisions in applying and choosing educational institutions.

[1026] A specific embodiment of the present invention will be described below. This system recommends the most suitable educational institution and department based on the user's grades and interests. Furthermore, an emotion engine is used to analyze the user's emotional state and generate customized recommendation information.

[1027] System Program Overview

[1028] 1. Data entry: Users use a smartphone or head-mounted display to enter grade information and areas of interest into the application.

[1029] 2. Data transmission and reception: Data entered by the user is formatted and sent to the server.

[1030] 3. AI analysis: The server stores the received grade information and interest information in a database and analyzes it using a generative AI model.

[1031] 4. Emotion engine: The server analyzes the user's emotional state in real time using devices such as a webcam.

[1032] 5. Recommendation list generation: Based on the analysis results and emotional state, the server generates an optimized recommendation list of educational institutions and departments and sends it to the user's device.

[1033] 6. Display Results: The device displays the results to the user and provides reminders and alerts as special advice.

[1034] Hardware and software used

[1035] Hardware: Smartphone, head-mounted display, webcam

[1036] Software: Generative AI models for AI analysis, EmotionRecognition library for emotion analysis, database management system

[1037] Detailed processing instructions

[1038] The server first receives the user's grades and interests. This information is formatted and stored in a database. Next, a generative AI model is used to analyze the data and identify the most suitable educational institution and department for the user. At the same time, the server uses the EmotionRecognition library to analyze the user's emotional state in real time. This allows the server to generate customized recommendations that take into account the user's stress and anxiety.

[1039] For example, if a high school student inputs their grades and interest in "environmental science," the server will recognize their emotional state as stressed and prioritize recommendations for universities with strong support systems. Along with the recommendations, the user's device will display reminders and specific instructions about important deadlines.

[1040] Example prompt sentence:

[1041] A high school senior entered grade information of "4.2 GPA" and area of ​​interest of "environmental science." The system analyzed the student's emotional state as being high in stress and recommended an environmental science university with a strong support system.

[1042] As described above, the present invention supports users in selecting an educational institution that is optimal for them and takes into consideration their emotional state.

[1043] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1044] Step 1:

[1045] Users use a smartphone or head-mounted display to input grade and interest information into the application, including grade point averages, test results, academic interests, and themes. The input data is then formatted for consistency.

[1046] Input: Grade information, interest information

[1047] Output: Formatted grade and interest information

[1048] Step 2:

[1049] The device transmits formatted performance and interest information to a server, where the data is transmitted using a secure communications protocol.

[1050] Input: Formatted grade and interest information

[1051] Output: Send data to the server

[1052] Step 3:

[1053] The server stores the received grade information and interest information in a database, which accumulates data for each user and is used for later analysis.

[1054] Input: Achievement information and interest information sent to the server

[1055] Output: Information stored in a database

[1056] Step 4:

[1057] The server uses a generative AI model to analyze the grade and interest information stored in the database, which identifies the educational institutions and departments that are best suited to the user.

[1058] Input: Grades and interest information stored in the database

[1059] Output: Analysis results for recommendations (list format)

[1060] Step 5:

[1061] The server analyzes the user's emotional state in real time using a webcam and the EmotionRecognition library for emotion analysis. The results of the emotion analysis are also saved as data.

[1062] Input: Real-time video of user

[1063] Output: User's emotional state data

[1064] Step 6:

[1065] The server generates an optimized list of recommended educational institutions and departments based on the analysis results and emotional state data. Taking into account the emotional state, it recommends educational institutions with strong support systems for users who are under stress.

[1066] Input: Analysis results, emotional state data

[1067] Output: A customized recommendation list

[1068] Step 7:

[1069] The server then transmits the generated customized recommendation list to the user's device using a secure communication protocol.

[1070] Input: Customized recommendation list

[1071] Output: sent to the user's device

[1072] Step 8:

[1073] The device receives and displays the recommendations to the user, and also provides reminders and specific reminders for important deadlines.

[1074] Input: Customized recommendation list

[1075] Output: Display of recommendation list, notification of reminders and reminders

[1076] Through the above processing steps, the user can receive recommendations for the most suitable educational institution and department that take into consideration the user's emotional state.

[1077] 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.

[1078] 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.

[1079] 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.

[1080] [Third embodiment]

[1081] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1082] 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.

[1083] 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).

[1084] 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.

[1085] 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.

[1086] 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).

[1087] 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.

[1088] 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.

[1089] 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.

[1090] 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.

[1091] 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.

[1092] 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."

[1093] The following describes in detail the mode for carrying out the present invention. The present invention is a system designed to streamline the information gathering and application process when selecting an educational institution. Based on the user's grades and interests, the system recommends the most suitable educational institutions and departments, and generates the checklists and schedules required for application. It also matches educational institutions based on research content.

[1094] Customized proposals for universities and departments using AI

[1095] 1. User data entry

[1096] Users: Enter information into the application, such as grades, interests, and extracurricular activities.

[1097] 2. Sending and Receiving Data

[1098] Terminal: Sends the entered data to the server.

[1099] 3. Data Analysis

[1100] Server: Analyzes the received grade and interest information and identifies the appropriate educational institution and department using an AI model.

[1101] 4. Generating and sending recommendation lists

[1102] Server: Generates a list of recommended educational institutions and departments based on the analysis results and sends it to the user's device.

[1103] 5. Display of recommendation results

[1104] Terminal: Displays the received recommendation list to the user.

[1105] Examples:

[1106] Let's say high school student Sato wants to study chemistry. Sato enters his grades and interest in chemistry into the app. The server performs AI analysis based on this information, creates a list of universities with excellent chemistry programs, and sends the recommendation results to Sato's device.

[1107] Research content matching

[1108] 1. Enter keywords

[1109] User: Enters research interests and keywords into the application.

[1110] 2. Sending and Receiving Data

[1111] Terminal: Sends the entered keyword information to the server.

[1112] 3. Research database collation

[1113] Server: Searches a database of paper abstracts to identify research fields that match the entered keywords.

[1114] 4. Generating and sending matching results

[1115] Server: Generates a list of recommended educational institutions and laboratories based on the identified research field and sends it to the user's device.

[1116] 5. Display of matching results

[1117] Terminal: Displays the received matching results to the user.

[1118] Examples:

[1119] Let's say Tanaka, who is interested in physics, wants to study "theory of relativity." Tanaka enters "theory of relativity" as a keyword into the app. The server searches a database of paper abstracts, identifies universities and laboratories conducting research on the theory of relativity, and sends a list of recommendations to Tanaka's device.

[1120] Auto-generated application checklists and schedules

[1121] 1. Enter application information

[1122] User: Enters information about the institution and department to which they wish to apply into the application.

[1123] 2. Sending and Receiving Data

[1124] Terminal: Sends the entered application information to the server.

[1125] 3. Analysis of application requirements

[1126] Server: Obtains application requirements for each educational institution and department and matches them with the user's application information.

[1127] 4. Generate checklists and schedules

[1128] Server: Automatically generates a list of documents to be submitted and an application schedule based on application requirements.

[1129] 5. Data transmission and display

[1130] Server: Sends the checklist and schedule to the user's device, which displays it to the user. It also sets reminder notifications.

[1131] Examples:

[1132] Suzuki, who is considering applying to multiple universities, enters the application information for each university into the app. The server retrieves the application requirements for each university, automatically generates a list of documents to be submitted, and an application schedule, which are then sent to Suzuki's device.

[1133] Continuous learning and improvement

[1134] 1. Enter and submit your feedback

[1135] User: Enters feedback about the service into the app and sends it from the device to the server.

[1136] 2. Analyzing feedback and updating the AI ​​model

[1137] Server: Analyzes the feedback and updates the AI ​​model. This update improves recommendation results and matching accuracy from the next time onwards.

[1138] summary

[1139] This invention allows high school students to efficiently select the appropriate educational institution and department, and smoothly progress through the application process. Furthermore, the system is continuously improved through feedback, enabling it to provide more accurate information. This system is realized through mutual cooperation between users, terminals, and servers.

[1140] The processing flow will be explained below.

[1141] Customized proposals for universities and departments using AI

[1142] Step 1:

[1143] Users: Enter information into the application, such as grades, interests, and extracurricular activities.

[1144] Step 2:

[1145] Terminal: Formats the entered data and generates a request to send to the server.

[1146] Step 3:

[1147] Server: Stores the received user performance information and interest information in a database and prepares for analysis.

[1148] Step 4:

[1149] Server: Uses AI models to analyze the user's grades and interests to identify the most suitable educational institution and department.

[1150] Step 5:

[1151] Server: Generates a list of recommended educational institutions and departments based on the analysis results.

[1152] Step 6:

[1153] Server: Sends the recommendation list to the user's device.

[1154] Step 7:

[1155] Terminal: Formats the received recommendation list and displays it to the user.

[1156] Research content matching

[1157] Step 1:

[1158] User: Enters research interests and keywords into the application.

[1159] Step 2:

[1160] Terminal: Formats the entered keywords and generates a request to send to the server.

[1161] Step 3:

[1162] Server: Searches the institution's paper abstract database based on the received keywords.

[1163] Step 4:

[1164] Server: Identifies research fields that match keywords from the search results and generates a recommendation list.

[1165] Step 5:

[1166] Server: Sends the generated recommendation list to the user's device.

[1167] Step 6:

[1168] Terminal: Formats the received recommendation list and displays it to the user.

[1169] Auto-generated application checklists and schedules

[1170] Step 1:

[1171] User: Enters information about the institution and department to which they wish to apply into the application.

[1172] Step 2:

[1173] Terminal: Formats the entered application information and generates a request to send to the server.

[1174] Step 3:

[1175] Server: Stores the received application information in a database and retrieves application requirements for each educational institution and department from the database.

[1176] Step 4:

[1177] Server: Compares the acquired application requirements with the user's application information and generates a list of documents to be submitted and an application schedule.

[1178] Step 5:

[1179] Server: Sends the generated list of submitted documents and application schedule to the user's terminal.

[1180] Step 6:

[1181] Terminal: Formats received submission lists and application schedules, displays them to the user, and sets reminder notifications.

[1182] Gathering feedback and updating the AI ​​model

[1183] Step 1:

[1184] Users: Enter feedback about the service into the application.

[1185] Step 2:

[1186] Terminal: Formats the input feedback and generates a request to send to the server.

[1187] Step 3:

[1188] Server: Stores the received feedback in a database and prepares it for analysis.

[1189] Step 4:

[1190] Server: Analyzes the feedback and extracts necessary improvements to the AI ​​model.

[1191] Step 5:

[1192] Server: Update the AI ​​model based on the improvements and improve recommendation accuracy from next time onwards.

[1193] The above is a specific process flow for implementing the present invention, which significantly streamlines the college selection and application process for high school students, their parents, and educational counselors.

[1194] Example 1

[1195] 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."

[1196] In the traditional graduate school and application process, users had difficulty selecting the appropriate educational institution and department from the vast amount of information available. It was also time-consuming to individually research each institution's application requirements and manage the necessary documents and schedules. Furthermore, matching educational institutions based on research content had to be done manually, which was time-consuming and labor-intensive.

[1197] 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.

[1198] In this invention, the server includes a means for receiving grade information and interest information, a means for performing analysis to recommend educational institutions and departments based on the grade information and interest information, a means for providing a list of educational institutions and departments based on the analysis results, and a means for receiving feedback and updating the analysis means, thereby enabling users to quickly and accurately select appropriate educational institutions and departments.

[1199] "Academic performance information" is data that indicates the user's academic performance and evaluation.

[1200] "Interest information" is data that indicates the fields or themes in which a user is interested.

[1201] "Educational institution" refers to a school or university providing higher education.

[1202] A "faculty" is a department within a university or educational institution that is responsible for a particular field of education or research.

[1203] The "analysis means" is a function that performs calculations to identify appropriate educational institutions and departments based on grade information and interest information.

[1204] The "recommended list" is a list of educational institutions and departments recommended based on the analysis results.

[1205] "Feedback" is data showing user evaluations and opinions, and is used to improve the system.

[1206] A "literature abstract database" is a database that collects summary information from academic papers.

[1207] "Research content" refers to academic issues or themes in a specific field.

[1208] A "research facility" is a department or laboratory within an educational institution that conducts specific research.

[1209] "Application requirements" refers to the conditions and documents that must be submitted when applying to an educational institution.

[1210] The "list of documents to be submitted" is a list of documents required for application.

[1211] An "application schedule" is a plan that outlines important dates and deadlines in the application process.

[1212] "Reminder Notification" is a feature that notifies you in advance of important deadlines and events.

[1213] The system of the present invention is designed to streamline the educational institution selection and application process. Through mutual cooperation between users, terminals, and servers, the system recommends appropriate educational institutions and departments, enabling a smooth application process. Specific embodiments of the system are described below.

[1214] 1. Entering user data

[1215] Users use a dedicated application to enter information such as grades, areas of interest, and extracurricular activities. This information is stored on the device as JSON format data. For example, a user might enter into the application that "I'm interested in physics and belong to the science club as an extracurricular activity."

[1216] 2. Sending and Receiving Data

[1217] The terminal sends the entered data to the server. This transmission uses an API call via the Internet. Specifically, when the user presses the "Send" button, the input data is converted into JSON format and sent to the server.

[1218] 3. Data Analysis

[1219] The server uses a generative AI model to analyze the received grade and interest information. This analysis is performed using cloud services such as Google Cloud AI and AWS SageMaker. The server preprocesses the parsed JSON data and converts it into a format suitable for the AI ​​model for analysis.

[1220] 4. Generate and send recommendation list

[1221] The server generates a list of recommended educational institutions and departments based on the analysis results and sends it to the device. Specifically, it converts the analysis results into JSON format, makes an API call to the user's device, and sends the list of recommendations.

[1222] 5. Display of recommendation results

[1223] The device parses the recommendation list received from the server and displays it on the application UI, allowing the user to view the recommended educational institutions and departments on the screen.

[1224] 6. Use of Feedback

[1225] Users input feedback about the recommendation list and services provided. The device then sends this feedback to the server. The server analyzes the received feedback and updates the AI ​​model to improve recommendation results and matching accuracy from the next time onwards.

[1226] Specific examples

[1227] Examples:

[1228] For example, if high school student Sato wants to study chemistry, he or she can enter his or her grades and interest in chemistry into the app. The server performs AI analysis based on this information, lists universities with excellent chemistry programs, and sends the recommendation results to Sato's device. Sato can then review the recommendation list and consider the career path that best suits his or her aspirations.

[1229] Generative AI model input example:

[1230] "I'm interested in chemistry and I'd like to know which universities have good chemistry programs."

[1231] "Please recommend a university where I can study the theory of relativity."

[1232] "Please tell me the documents and schedule required to apply to the university I want to attend."

[1233] This invention allows users to efficiently select appropriate educational institutions and departments, and smoothly progress through the application process. The system provides highly accurate information through mutual cooperation between users, terminals, and servers.

[1234] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1235] Step 1:

[1236] User Data Entry

[1237] User: Enters information such as grades, areas of interest, and extracurricular activities into the application. Specifically, the user enters the required information into a form in the dedicated application and presses the "Submit" button. This data is temporarily saved on the device in JSON format.

[1238] Input: Grades, interests, extracurricular activities

[1239] Output: JSON format data

[1240] Step 2:

[1241] Sending data

[1242] Terminal: Sends JSON format data to the server. Specifically, when the "Send" button is pressed, the terminal executes an API call to send the data to the server. SSL is used during communication to ensure data security.

[1243] Input: JSON format data

[1244] Output: API calls to the server and data sent

[1245] Step 3:

[1246] Receiving and Parsing Data

[1247] Server: Parses the received data from JSON format and converts it into an internal data structure. Specifically, it analyzes the received JSON data and organizes it into data objects according to grades, areas of interest, and extracurricular activities.

[1248] Input: JSON format data

[1249] Output: Analysis and object format data

[1250] Step 4:

[1251] Data analysis

[1252] Server: Uses the parsed data to input the generative AI model. Specifically, it uses Google Cloud AI or AWS SageMaker to analyze grade information and areas of interest to identify the most suitable educational institution and department for the user. It then applies the calculations and evaluation logic of the generative AI model to extract appropriate recommendations.

[1253] Input: Analysis and object-formatted data

[1254] Output: Analysis results (recommendation list)

[1255] Step 5:

[1256] Generating and sending recommendation lists

[1257] Server: The analysis results are converted back into JSON format and sent to the user's device. Specifically, the generated recommendation list is sent to the device via an API call.

[1258] Input: Analysis results

[1259] Output: Recommendation list in JSON format, and API calls to the device

[1260] Step 6:

[1261] Receiving and displaying recommendations

[1262] Device: Parses the recommendation list received from the server and displays it in a format suitable for the user interface. Specifically, it interprets the received data and displays it in a list view or dashboard.

[1263] Input: JSON formatted recommendation list from the server

[1264] Output: Recommendation list displayed in a user interface

[1265] Step 7:

[1266] Matching research content

[1267] User: Enters research interests and keywords (e.g., "quantum mechanics") into the application.

[1268] Terminal: Sends the entered keyword to the server.

[1269] Server: Searches the institution's literature abstract database to identify research areas that match the keywords entered.

[1270] Specifically, the server executes a database query to list relevant papers and research fields, converts the analysis results back into JSON format, and sends them to the user's device.

[1271] Terminal: Parses and displays the list of recommended fields of study and educational institutions.

[1272] Input: Research Keywords

[1273] Output: A list of educational institutions that match the field of study

[1274] Step 8:

[1275] Application information management

[1276] User: Enters information about the institution and department to which they wish to apply into the application.

[1277] Terminal: Sends the entered application information to the server.

[1278] Server: Acquires and collates application requirements. Specifically, it uses web scraping and APIs to collect application requirements from each educational institution and verifies that they match the user's application information. It automatically generates a list of documents to be submitted and an application schedule based on the application requirements, converts them back into JSON format, and sends them to the device.

[1279] Terminal: Parse and view automatically generated submission lists and application schedules, and set reminders for important deadlines.

[1280] Input: Application information

[1281] Output: Application requirements, list of documents to be submitted, application schedule, reminder notices

[1282] Step 9:

[1283] Feedback input and analysis

[1284] User: Enters feedback on the recommendations and services provided.

[1285] Terminal: Sends the entered feedback to the server.

[1286] Server: Analyzes the feedback and updates the AI ​​model. Specifically, it analyzes the feedback data and uses it as training data to improve the accuracy of the generative AI model.

[1287] Input: Feedback data

[1288] Output: Updated analysis method

[1289] This allows users to quickly and accurately select the appropriate educational institution and department, and smoothly progress through the application process.

[1290] (Application example 1)

[1291] 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."

[1292] Conventional educational institution recommendation systems simply recommend suitable universities and departments based on academic records and interests. However, they lack a means to provide users with customized educational institution advertisements that are optimal for them, making it difficult to provide information efficiently and effectively. There was also a need for a way to effectively promote educational institutions through advertisements while providing important information for the application process.

[1293] 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.

[1294] In this invention, the server includes means for receiving the user's grade information and interest information, means for performing analysis to recommend the most suitable educational institution based on the grade information and interest information, means for providing a list of the recommended educational institutions based on the analysis results, and means for generating advertising data and displaying advertisements for educational institutions optimized for the user's characteristics. This makes it possible to provide the user with information on the most suitable educational institution, and by displaying customized advertisements, enables effective promotional activities.

[1295] "Grade information" is data indicating grades and evaluations for each subject that a user has obtained at school or the like.

[1296] "Interest information" is information relating to academic fields or research themes in which a user is particularly interested.

[1297] "Educational institutions" are facilities or organizations that provide higher education, such as universities and vocational schools.

[1298] A "faculty" is an organization within an educational institution such as a university that conducts study and research in a specific academic field.

[1299] "Analysis" is the process of performing calculations and evaluations using mathematical models and algorithms based on received performance information and interest information.

[1300] The "list" is a table listing the names and information of recommended educational institutions, departments, and laboratories.

[1301] "Advertising Data" is digital data generated to promote a particular educational institution.

[1302] "Customized advertising" refers to promotional advertising whose content is tailored based on a user's characteristics and interests.

[1303] A "paper abstract database" is a data store that collects summaries of numerous papers and is used to search for research content.

[1304] "Application information" refers to information about the documents and procedures required when a user applies to enroll in a particular educational institution or faculty.

[1305] "Application requirements" refer to the conditions and documents that must be met in order to enter a particular educational institution or faculty.

[1306] "List of documents to be submitted" refers to a list of documents required for application.

[1307] An "application schedule" is a timeline that shows the deadlines and schedule for each step in the application process.

[1308] "Reminder notification" is a function that notifies users in advance so that they do not forget important deadlines.

[1309] This invention is a system that recommends optimal educational institutions and departments based on a user's grades and interests. It also matches laboratories and educational institutions based on the user's research interests and displays customized advertisements, thereby providing efficient information provision and promotion.

[1310] To realize this system, the following hardware and software are used.

[1311] Hardware: User's smartphone, server

[1312] Software: Python, REST API, JSON, Scikit-learn or TensorFlow

[1313] System configuration

[1314] User Data Entry

[1315] Users use a smartphone app to input their grades, areas of interest, and research keywords, and the application sends this information to the server in JSON format.

[1316] Data analysis

[1317] The server analyzes the received grades and interest information using AI models (based on Scikit-learn and TensorFlow) to identify the most suitable educational institutions and departments. The analysis results are generated as a recommendation list.

[1318] Generating a recommendation list

[1319] Based on the analysis results, a list of the most suitable educational institutions and departments is generated, which is sent in JSON format to the user's smartphone and displayed within the app.

[1320] Generate personalized ads

[1321] The server generates advertising data based on the analysis results and user characteristics, which includes information about the educational institution and is displayed in a customized format to the user.

[1322] Application information management

[1323] When a user inputs information about the educational institution and department to which they wish to apply, the server retrieves the application requirements and automatically generates a list of documents to be submitted and an application schedule, allowing users to efficiently proceed with their application.

[1324] Reminders

[1325] For important deadlines, smartphone apps can set reminder notifications to remind users not to forget about them.

[1326] Specific examples

[1327] Recommendations based on user performance information

[1328] High school students enter their grades (90 for math, 95 for science, 85 for English) and areas of interest (science, physics) into the app. This data is sent to a server, which analyzes it and generates a list of the most suitable universities and departments (e.g., universities with a strong science focus). This list is accompanied by corresponding customized university advertisements.

[1329] Prompt Sentence Examples

[1330] An example of a user prompt would be, "My grades are 90 in math, 95 in science, and 85 in English. My areas of interest are science and physics." The system will then recommend and display advertisements for the most suitable educational institutions.

[1331] In this way, the present invention makes it possible to provide users with information about educational institutions and to promote their advertisements efficiently and effectively.

[1332] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1333] Step 1:

[1334] The user's device is started, and the user opens the app and enters their grades, areas of interest, and research keywords. The input information (grades, areas of interest, and research keywords) is converted into JSON format and sent to the server.

[1335] Step 2:

[1336] The server receives JSON-formatted data (grade information, areas of interest, research keywords) sent from the device. The server passes this data to an AI model (Scikit-learn or TensorFlow) for analysis. The AI ​​model identifies the most suitable educational institutions and departments based on the input data and generates a list of recommendations. The output is a list of recommended educational institutions and departments.

[1337] Step 3:

[1338] The server returns the generated recommendation list in JSON format to the device, which receives it and visually displays it to the user. The display is in list format, including detailed information about the recommended educational institutions and departments.

[1339] Step 4:

[1340] The server further generates customized advertising data based on the analysis results and the user's characteristics. The advertising data is configured in a manner optimized for the user and includes specific information and promotional content from the educational institution. The output is the customized advertising data.

[1341] Step 5:

[1342] The server transmits the generated advertisement data to the terminal, which receives it and displays the advertisement to the user along with the recommendation list. The advertisement is visually integrated into the interface and is designed to attract the user's attention.

[1343] Step 6:

[1344] Users enter their desired application information into the app. The device converts this information into JSON format and sends it to the server. This application information includes the desired educational institution and department.

[1345] Step 7:

[1346] The server receives the application information sent from the terminal and retrieves the application requirements of each educational institution and department from the database. The server uses this information to automatically generate a list of documents to be submitted and an application schedule. The output is a list of documents to be submitted and an application schedule.

[1347] Step 8:

[1348] The server sends the generated list of documents to be submitted and the application schedule to the terminal, which receives it and displays it in an easy-to-understand manner for the user. A reminder notification function is also set up to notify the user of important deadlines.

[1349] This flow allows users to receive recommendations for the most suitable educational institutions based on their academic records and interests, display customized advertisements, and streamline the application process, all within a single application.

[1350] 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.

[1351] The present invention provides a system for recommending educational institutions and departments based on a user's grades and interests, streamlining the application process, and also provides customized recommendation information based on the user's emotions by combining it with an emotion engine that recognizes the user's emotions.

[1352] Receiving and analyzing user performance and interest information

[1353] 1. User data entry

[1354] Users: Enter information into the application, such as grades, interests, and extracurricular activities.

[1355] 2. Sending and Receiving Data

[1356] Terminal: Formats the entered data and sends it to the server.

[1357] 3. Data Analysis

[1358] Server: Stores the received grade information and interest information in a database and prepares for analysis.

[1359] 4. AI-based analysis

[1360] Server: Uses AI models to analyze the user's grades and interests to identify the most suitable educational institution and department.

[1361] 5. Customization with Emotion Engine

[1362] Server: The AI ​​analysis results are further analyzed by the emotion engine to generate customized recommendations based on the user's emotional state.

[1363] 6. Generating and Sending Recommendation Lists

[1364] Server: Generates a recommendation list optimized by the emotion engine and sends it to the user's device.

[1365] 7. Display of recommendation results

[1366] Terminal: Displays the received recommendation list to the user.

[1367] Examples:

[1368] High school student Yamada enters his grades and interests into the app. The server receives and analyzes this information, and an AI model identifies the most suitable university and department. At the same time, an emotion engine analyzes Yamada's emotions when he enters the information, and if he is in a stressful situation, it recommends a university with a strong support system.

[1369] Research content matching

[1370] 1. Enter keywords

[1371] User: Enters research interests and keywords into the application.

[1372] 2. Sending and Receiving Data

[1373] Terminal: Formats the entered keywords and sends them to the server.

[1374] 3. Research database collation

[1375] Server: Searches a database of paper abstracts to identify research fields that match the entered keywords.

[1376] 4. Generating and sending matching results

[1377] Server: Generates a list of recommended educational institutions and laboratories based on the identified research field, customizes it according to the user's emotional state, and sends it to the user's device.

[1378] 5. Display of matching results

[1379] Terminal: Formats the received recommendation list and displays it to the user.

[1380] Examples:

[1381] Sato, who is interested in physics, enters "quantum mechanics" as a keyword. The server searches a database of paper abstracts based on the keyword and identifies universities and laboratories conducting relevant research. At the same time, the emotion engine takes Sato's emotional state into account and prioritizes recommending universities with low stress and good research environments.

[1382] Auto-generated application checklists and schedules

[1383] 1. Enter application information

[1384] User: Enters information about the institution and department to which they wish to apply into the application.

[1385] 2. Sending and Receiving Data

[1386] Terminal: Formats the entered application information and sends it to the server.

[1387] 3. Analysis of application requirements

[1388] Server: Obtains application requirements for each educational institution and department and matches them with the user's application information.

[1389] 4. Generate checklists and schedules

[1390] Server: Automatically generates a list of documents to be submitted and an application schedule based on the application requirements. It also takes into account the user's emotional state, allowing for flexibility in the schedule and adding explanations.

[1391] 5. Data transmission and display

[1392] Server: Sends the generated list of submitted documents and application schedule to the user's terminal, which displays it to the user and sets reminder notifications.

[1393] Examples:

[1394] Mr. Tanaka, who is considering applying to multiple universities, enters the application information for each university into the app. The server receives this information, obtains the application requirements for each university, and generates a list of documents to be submitted and an application schedule. The emotion engine takes Mr. Tanaka's emotional state into account and adds warnings and specific advice to areas where he is likely to feel anxious.

[1395] Gathering feedback and updating the AI ​​model

[1396] 1. Enter and submit your feedback

[1397] User: Enters feedback about the service into the application and sends it to the server from the terminal.

[1398] 2. Analyzing feedback and updating the AI ​​model

[1399] Server: Analyzes the received feedback, extracts necessary improvements to the AI ​​model and emotion engine, and updates the model.

[1400] Examples:

[1401] Users provide feedback after using the system, which the server reads, analyzes areas for improvement in the service, and updates the AI ​​model and emotion engine to provide better recommendations and research matching the next time users use the system.

[1402] As a result, the present invention provides an efficient and emotionally sensitive educational institution selection and application process.

[1403] The processing flow will be explained below.

[1404] Customized proposals for universities and departments using AI

[1405] Step 1:

[1406] Users: Enter information into the application, such as grades, interests, and extracurricular activities.

[1407] Step 2:

[1408] Terminal: Formats the entered data and generates a request to send to the server.

[1409] Step 3:

[1410] Server: Stores the received user performance information and interest information in a database and prepares for analysis.

[1411] Step 4:

[1412] Server: Uses AI models to analyze the user's grades and interests to identify the most suitable educational institution and department.

[1413] Step 5:

[1414] Server: Uses an emotion engine to analyze the emotion data of the user's input in real time and identify the emotional state.

[1415] Step 6:

[1416] Server: Based on the analysis results of the emotion engine, the recommendation results of the AI ​​model are adjusted to generate a recommendation list optimized for the user's emotional state.

[1417] Step 7:

[1418] Server: Sends the optimized recommendation list to the user's device.

[1419] Step 8:

[1420] Terminal: Formats the received recommendation list and displays it to the user.

[1421] Examples:

[1422] High school student Yamada enters his grades and interests into the app. The server receives and analyzes this information, and an AI model identifies the appropriate university and department. At the same time, an emotion engine analyzes Yamada's emotional state (for example, whether his stress level is high or low), generates a list of recommended universities with better support systems, and sends it to Yamada's device.

[1423] Research content matching

[1424] Step 1:

[1425] User: Enters research interests and keywords into the application.

[1426] Step 2:

[1427] Terminal: Formats the entered keywords and generates a request to send to the server.

[1428] Step 3:

[1429] Server: Searches the institution's paper abstract database based on the received keywords.

[1430] Step 4:

[1431] Server: From the search results, identify research fields that match the keywords and generate a list of recommendations.

[1432] Step 5:

[1433] Server: Uses an emotion engine to analyze the user's emotional state and match appropriate educational institutions and laboratories based on a recommended list of research fields.

[1434] Step 6:

[1435] Server: Sends the optimized research recommendation list to the user's device.

[1436] Step 7:

[1437] Terminal: Formats the received recommendation list and displays it to the user.

[1438] Examples:

[1439] Sato, who is interested in physics, enters "quantum mechanics" as a keyword. The server searches a database of paper abstracts based on the entered keywords and identifies suitable universities and research laboratories. At the same time, the emotion engine analyzes Sato's emotional state and generates a list of recommendations focusing on universities with low stress and good research environments, which is sent to Sato's device.

[1440] Auto-generated application checklists and schedules

[1441] Step 1:

[1442] User: Enters information about the institution and department to which they wish to apply into the application.

[1443] Step 2:

[1444] Terminal: Formats the entered application information and generates a request to send to the server.

[1445] Step 3:

[1446] Server: Stores the received application information in a database and obtains the application requirements of each educational institution and department.

[1447] Step 4:

[1448] Server: Compares the acquired application requirements with the user's application information and generates a list of documents to be submitted and an application schedule.

[1449] Step 5:

[1450] Server: Uses an emotion engine to analyze the user's emotional state and optimize the filing list and application schedule.

[1451] Step 6:

[1452] Server: Sends the optimized submission document list and application schedule to the user's terminal.

[1453] Step 7:

[1454] Terminal: Formats and displays received submission lists and filing schedules to the user, and sets reminders for important deadlines.

[1455] Examples:

[1456] Mr. Tanaka, who is considering applying to multiple universities, enters the application information for each university into the app. The server receives this information, obtains the application requirements for each university, and generates a list of documents to be submitted and an application schedule. The emotion engine analyzes Mr. Tanaka's emotional state and adds warnings and specific advice to areas where he is likely to feel anxious.

[1457] Gathering feedback and updating the AI ​​model

[1458] Step 1:

[1459] Users: Enter feedback about the service into the application.

[1460] Step 2:

[1461] Terminal: Formats the input feedback and generates a request to send to the server.

[1462] Step 3:

[1463] Server: Stores the received feedback in a database and prepares it for analysis.

[1464] Step 4:

[1465] Server: Analyzes the feedback and extracts necessary improvements to the AI ​​model and emotion engine.

[1466] Step 5:

[1467] Server: Update the AI ​​model and emotion engine based on the improvements, and improve the accuracy of recommendations from next time onwards.

[1468] The above is a specific processing flow for implementing the present invention, which significantly improves the efficiency of the university selection and application process for high school students, their parents, and educational counselors, while also enabling the provision of services that are sensitive to the user's emotions.

[1469] Example 2

[1470] 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."

[1471] Conventional educational institution recommendation systems are limited to simple recommendations based on users' grades and interests, and lack customization that takes into account the user's emotional state. Furthermore, in matching optimal research fields and the application process, efficient recommendations and schedule management that take into account the user's emotional state are lacking.

[1472] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving the user's grade information and interest information, a means for performing an analysis to recommend the most suitable educational institution and faculty based on the user's grade information and interest information, a means for further analyzing the analysis results with an emotion analysis engine and customizing the recommendation information based on the user's emotional state, and a means for providing the customized recommendation information to the user. This enables customized recommendations that take into account the user's emotional state in addition to the user's grade information and interest information.

[1473] "Academic achievement information" refers to data that represents a user's academic achievements at an educational institution, such as academic records, test results, and evaluation scores.

[1474] "Interest information" is information that indicates a user's personal interests, such as fields of interest, subjects, extracurricular activities, and future career paths.

[1475] "Analysis" refers to analyzing and processing data for a specific purpose based on received information.

[1476] "Educational institutions" refers to organizations and facilities that teach academic subjects or skills, such as universities, technical colleges, and vocational schools.

[1477] An "emotion analysis engine" refers to an algorithm or software tool that analyzes a user's emotional and psychological state based on user input data and behavioral data.

[1478] "Recommendation" refers to suggesting the best option to a user based on specific criteria.

[1479] A database is an information system that systematically organizes and stores large amounts of data, and efficiently searches and manages them.

[1480] "Application information" refers to data such as personal information and desired information required when applying to an educational institution or faculty of a user's choice.

[1481] "Document List" refers to the list of documents required for the application process at an educational institution.

[1482] An "application schedule" is a plan showing the various steps and deadlines required for filing an application.

[1483] "Reminder notification" refers to a notification function that notifies users when a specific deadline or event is approaching.

[1484] The present invention is a system that recommends educational institutions and departments based on a user's grades and interests, streamlining the application process. Furthermore, by combining it with an emotion analysis engine that recognizes the user's emotions, the system provides customized recommendation information based on the user's emotions.

[1485] Hardware and software used

[1486] This system uses the following hardware and software:

[1487] 1. Hardware

[1488] Terminal: A device used by a user to input information, such as a smartphone or computer.

[1489] Server: A cloud-based server for analyzing the received data and generating recommendation information.

[1490] 2. Software

[1491] Input forms: web and mobile applications that run on devices.

[1492] Database: A relational database such as MySQL.

[1493] Generative AI models: Python-based AI analysis tool.

[1494] Sentiment analysis engine: Algorithms and software (e.g., natural language processing tools and machine learning models) for analyzing a user's emotional state.

[1495] A concrete example of the processing flow

[1496] Receiving and analyzing user performance and interest information

[1497] 1. User data entry

[1498] A user enters his / her grades, areas of interest, extracurricular activities, etc. into an application input form. For example, a high school student enters his / her final exam grades and interest in chemistry.

[1499] 2. Sending and Receiving Data

[1500] The terminal converts the input data into JSON format and sends it to the server via an HTTP POST request, which the server receives and stores in a database.

[1501] 3. Data Analysis

[1502] The server uses a Python-based generative AI model to analyze the data it receives, identifying the best educational institution and department for the user based on grades and interests.

[1503] 4. Customization using sentiment analysis engine

[1504] The server inputs the analysis results into an emotion analysis engine to analyze the user's emotional state, and customizes recommendations based on this. For example, if a user is in a stressful situation, it might recommend universities with strong support systems.

[1505] 5. Generating and sending recommendation lists

[1506] The server generates a customized recommendation list and sends it to the user's terminal, which displays the received information to the user.

[1507] Prompt Sentence Examples

[1508] "Please enter your academic achievements, such as final exam scores and GPA."

[1509] "What academic subjects and extracurricular activities are you interested in? For example, chemistry, physics, basketball, etc."

[1510] "Tell me about your current mood or emotions. For example, are you feeling stressed or relaxed?"

[1511] As a result, this invention realizes an efficient and emotion-sensitive educational institution selection and application process. By providing optimal recommendations based not only on the user's grades and interests, but also using an emotion analysis engine, it is possible to provide the optimal learning environment and application support for the user.

[1512] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1513] Step 1: User Data Entry

[1514] Users enter their grades, interests, extracurricular activities, etc. into the application's input form. Specifically, the user fills in the application's form fields and presses the submit button. The input data includes the user's grades (e.g., GPA, test results), interests (e.g., chemistry, biology), and extracurricular activities (e.g., basketball, music).

[1515] Step 2: Sending and Receiving Data

[1516] The device formats the input data and sends it to the server. Specifically, it converts the input data into JSON format and sends it to the server using an HTTP POST request. The input includes the grades and interest information entered by the user, and the output is the data received by the server.

[1517] Step 3: Store the data

[1518] The server stores the received grade information and interest information in a database. Specifically, it saves the data in a relational database such as MySQL. In this step, the data received by the server is used as input, and the output is saved in the database.

[1519] Step 4: Analysis of performance and interest information

[1520] The server uses a generative AI model to analyze the received data. Specifically, the Python-based AI model takes grade information and interest information as input and performs data operations to identify the most suitable educational institutions and departments. The output is a list of the most suitable educational institutions and departments.

[1521] Step 5: Customizing with a sentiment analysis engine

[1522] The server further analyzes the AI ​​analysis results using an emotion analysis engine, customizing the results to take the user's emotional state into account. Specifically, the emotion analysis engine uses the results of the AI ​​model and the user's emotional data as input data, and generates customized recommendation information as output.

[1523] Step 6: Generate and submit a recommendation list

[1524] The server generates a customized recommendation list and sends it to the user's device. Specifically, it converts the recommendation list into text or JSON format and sends it as an HTTP response. In this step, the recommendation information customized by the sentiment analysis engine is used as input, and the output is the recommendation list sent to the user's device.

[1525] Step 7: Viewing Recommendations

[1526] The device displays the received recommendation list to the user. Specifically, it uses a UI component for visually displaying the received data to provide information to the user in an easy-to-read format. The input includes the recommendation list received from the server, and the output is the visually displayed recommendation results.

[1527] Specific working example:

[1528] High school students enter their grades and areas of interest into the app.

[1529] The app converts the input data into JSON format and sends it to the server.

[1530] The server stores the data in a database.

[1531] AI models analyze grade and interest information to identify the most suitable educational institutions and departments.

[1532] A sentiment analysis engine takes into account the user's stress level to customize recommendations.

[1533] The final recommendation list is sent to the user's terminal and displayed to the user.

[1534] (Application example 2)

[1535] 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."

[1536] Conventional recommendation systems for educational institutions and departments provide optimal options based on a user's grades and interests, but rarely take into account the user's emotional state. As a result, users may receive recommendation results while feeling stressed or anxious, which could lead to decisions that differ from their original intentions. Furthermore, the lack of reminder notifications for important deadlines can lead users to forget submission deadlines. These issues create a need for systems that can provide users with more accurate options.

[1537] 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.

[1538] In this invention, the server includes means for receiving the user's grade information and interest information, means for performing analysis to recommend the most suitable educational institution and department based on the user's grade information and interest information, means for providing the user with a list of recommended educational institutions and departments based on the analysis results, means for recognizing an emotional state associated with the received grade information and interest information, and means for generating customized recommendation information based on the emotional state. This enables the user to select the most suitable educational institution or department taking into consideration the user's emotional state, and makes it possible to realize recommendations that reduce stress and anxiety.

[1539] "Academic record information" refers to information about a user's academic performance at an educational institution, such as academic record, grade point average, and test results.

[1540] "Interest information" is information about the user's fields of interest, topics, academic interests, and extracurricular activities.

[1541] The "means for performing analysis" is a method of processing data to recommend the most suitable educational institution and faculty based on the user's grade information and interest information.

[1542] The "recommended list" is a list of educational institutions and faculties suitable for the user, generated based on the analysis results.

[1543] An "emotional state" is a state that represents a user's current mood or emotion, such as stress, anxiety, or joy.

[1544] An "emotion engine" is a device or software that recognizes a user's emotional state and customizes information based on that state.

[1545] "Customized recommendation information" refers to recommendation information for the most suitable educational institution or department that is generated by taking into consideration the user's emotional state in addition to their academic record and interest information.

[1546] A "paper abstract database" is a database that stores summary information on research papers, and allows searches for specific fields or keywords.

[1547] "Application requirements" refer to the conditions, documents to be submitted, schedules, etc. that must be met when applying to an educational institution or department.

[1548] "Reminder notification" is a notification function that automatically notifies users of important deadlines and schedules.

[1549] "Warning" refers to providing information to alert users to specific matters.

[1550] "Advice" is specific instructions or suggestions to help users make good decisions in applying and choosing educational institutions.

[1551] A specific embodiment of the present invention will be described below. This system recommends the most suitable educational institution and department based on the user's grades and interests. Furthermore, an emotion engine is used to analyze the user's emotional state and generate customized recommendation information.

[1552] System Program Overview

[1553] 1. Data entry: Users use a smartphone or head-mounted display to enter grade information and areas of interest into the application.

[1554] 2. Data transmission and reception: Data entered by the user is formatted and sent to the server.

[1555] 3. AI analysis: The server stores the received grade information and interest information in a database and analyzes it using a generative AI model.

[1556] 4. Emotion engine: The server analyzes the user's emotional state in real time using devices such as a webcam.

[1557] 5. Recommendation list generation: Based on the analysis results and emotional state, the server generates an optimized recommendation list of educational institutions and departments and sends it to the user's device.

[1558] 6. Display Results: The device displays the results to the user and provides reminders and alerts as special advice.

[1559] Hardware and software used

[1560] Hardware: Smartphone, head-mounted display, webcam

[1561] Software: Generative AI models for AI analysis, EmotionRecognition library for emotion analysis, database management system

[1562] Detailed processing instructions

[1563] The server first receives the user's grades and interests. This information is formatted and stored in a database. Next, a generative AI model is used to analyze the data and identify the most suitable educational institution and department for the user. At the same time, the server uses the EmotionRecognition library to analyze the user's emotional state in real time. This allows the server to generate customized recommendations that take into account the user's stress and anxiety.

[1564] For example, if a high school student inputs their grades and interest in "environmental science," the server will recognize their emotional state as stressed and prioritize recommendations for universities with strong support systems. Along with the recommendations, the user's device will display reminders and specific instructions about important deadlines.

[1565] Example prompt sentence:

[1566] A high school senior entered grade information of "4.2 GPA" and area of ​​interest of "environmental science." The system analyzed the student's emotional state as being high in stress and recommended an environmental science university with a strong support system.

[1567] As described above, the present invention supports users in selecting an educational institution that is optimal for them and takes into consideration their emotional state.

[1568] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1569] Step 1:

[1570] Users use a smartphone or head-mounted display to input grade and interest information into the application, including grade point averages, test results, academic interests, and themes. The input data is then formatted for consistency.

[1571] Input: Grade information, interest information

[1572] Output: Formatted grade and interest information

[1573] Step 2:

[1574] The device transmits formatted performance and interest information to a server, where the data is transmitted using a secure communications protocol.

[1575] Input: Formatted grade and interest information

[1576] Output: Send data to the server

[1577] Step 3:

[1578] The server stores the received grade information and interest information in a database, which accumulates data for each user and is used for later analysis.

[1579] Input: Achievement information and interest information sent to the server

[1580] Output: Information stored in a database

[1581] Step 4:

[1582] The server uses a generative AI model to analyze the grade and interest information stored in the database, which identifies the educational institutions and departments that are best suited to the user.

[1583] Input: Grades and interest information stored in the database

[1584] Output: Analysis results for recommendations (list format)

[1585] Step 5:

[1586] The server analyzes the user's emotional state in real time using a webcam and the EmotionRecognition library for emotion analysis. The results of the emotion analysis are also saved as data.

[1587] Input: Real-time video of user

[1588] Output: User's emotional state data

[1589] Step 6:

[1590] The server generates an optimized list of recommended educational institutions and departments based on the analysis results and emotional state data. Taking into account the emotional state, it recommends educational institutions with strong support systems for users who are under stress.

[1591] Input: Analysis results, emotional state data

[1592] Output: A customized recommendation list

[1593] Step 7:

[1594] The server then transmits the generated customized recommendation list to the user's device using a secure communication protocol.

[1595] Input: Customized recommendation list

[1596] Output: sent to the user's device

[1597] Step 8:

[1598] The device receives and displays the recommendations to the user, and also provides reminders and specific reminders for important deadlines.

[1599] Input: Customized recommendation list

[1600] Output: Display of recommendation list, notification of reminders and reminders

[1601] Through the above processing steps, the user can receive recommendations for the most suitable educational institution and department that take into consideration the user's emotional state.

[1602] 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.

[1603] 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.

[1604] 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.

[1605] [Fourth embodiment]

[1606] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1607] 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.

[1608] 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).

[1609] 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.

[1610] 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.

[1611] 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).

[1612] 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.

[1613] 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.

[1614] 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.

[1615] 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.

[1616] 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.

[1617] 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.

[1618] 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."

[1619] The following describes in detail the mode for carrying out the present invention. The present invention is a system designed to streamline the information gathering and application process when selecting an educational institution. Based on the user's grades and interests, the system recommends the most suitable educational institutions and departments, and generates the checklists and schedules required for application. It also matches educational institutions based on research content.

[1620] Customized proposals for universities and departments using AI

[1621] 1. User data entry

[1622] Users: Enter information into the application, such as grades, interests, and extracurricular activities.

[1623] 2. Sending and Receiving Data

[1624] Terminal: Sends the entered data to the server.

[1625] 3. Data Analysis

[1626] Server: Analyzes the received grade and interest information and identifies the appropriate educational institution and department using an AI model.

[1627] 4. Generating and sending recommendation lists

[1628] Server: Generates a list of recommended educational institutions and departments based on the analysis results and sends it to the user's device.

[1629] 5. Display of recommendation results

[1630] Terminal: Displays the received recommendation list to the user.

[1631] Examples:

[1632] Let's say high school student Sato wants to study chemistry. Sato enters his grades and interest in chemistry into the app. The server performs AI analysis based on this information, creates a list of universities with excellent chemistry programs, and sends the recommendation results to Sato's device.

[1633] Research content matching

[1634] 1. Enter keywords

[1635] User: Enters research interests and keywords into the application.

[1636] 2. Sending and Receiving Data

[1637] Terminal: Sends the entered keyword information to the server.

[1638] 3. Research database collation

[1639] Server: Searches a database of paper abstracts to identify research fields that match the entered keywords.

[1640] 4. Generating and sending matching results

[1641] Server: Generates a list of recommended educational institutions and laboratories based on the identified research field and sends it to the user's device.

[1642] 5. Display of matching results

[1643] Terminal: Displays the received matching results to the user.

[1644] Examples:

[1645] Let's say Tanaka, who is interested in physics, wants to study "theory of relativity." Tanaka enters "theory of relativity" as a keyword into the app. The server searches a database of paper abstracts, identifies universities and laboratories conducting research on the theory of relativity, and sends a list of recommendations to Tanaka's device.

[1646] Auto-generated application checklists and schedules

[1647] 1. Enter application information

[1648] User: Enters information about the institution and department to which they wish to apply into the application.

[1649] 2. Sending and Receiving Data

[1650] Terminal: Sends the entered application information to the server.

[1651] 3. Analysis of application requirements

[1652] Server: Obtains application requirements for each educational institution and department and matches them with the user's application information.

[1653] 4. Generate checklists and schedules

[1654] Server: Automatically generates a list of documents to be submitted and an application schedule based on application requirements.

[1655] 5. Data transmission and display

[1656] Server: Sends the checklist and schedule to the user's device, which displays it to the user. It also sets reminder notifications.

[1657] Examples:

[1658] Suzuki, who is considering applying to multiple universities, enters the application information for each university into the app. The server retrieves the application requirements for each university, automatically generates a list of documents to be submitted, and an application schedule, which are then sent to Suzuki's device.

[1659] Continuous learning and improvement

[1660] 1. Enter and submit your feedback

[1661] User: Enters feedback about the service into the app and sends it from the device to the server.

[1662] 2. Analyzing feedback and updating the AI ​​model

[1663] Server: Analyzes the feedback and updates the AI ​​model. This update improves recommendation results and matching accuracy from the next time onwards.

[1664] summary

[1665] This invention allows high school students to efficiently select the appropriate educational institution and department, and smoothly progress through the application process. Furthermore, the system is continuously improved through feedback, enabling it to provide more accurate information. This system is realized through mutual cooperation between users, terminals, and servers.

[1666] The processing flow will be explained below.

[1667] Customized proposals for universities and departments using AI

[1668] Step 1:

[1669] Users: Enter information into the application, such as grades, interests, and extracurricular activities.

[1670] Step 2:

[1671] Terminal: Formats the entered data and generates a request to send to the server.

[1672] Step 3:

[1673] Server: Stores the received user performance information and interest information in a database and prepares for analysis.

[1674] Step 4:

[1675] Server: Uses AI models to analyze the user's grades and interests to identify the most suitable educational institution and department.

[1676] Step 5:

[1677] Server: Generates a list of recommended educational institutions and departments based on the analysis results.

[1678] Step 6:

[1679] Server: Sends the recommendation list to the user's device.

[1680] Step 7:

[1681] Terminal: Formats the received recommendation list and displays it to the user.

[1682] Research content matching

[1683] Step 1:

[1684] User: Enters research interests and keywords into the application.

[1685] Step 2:

[1686] Terminal: Formats the entered keywords and generates a request to send to the server.

[1687] Step 3:

[1688] Server: Searches the institution's paper abstract database based on the received keywords.

[1689] Step 4:

[1690] Server: Identifies research fields that match keywords from the search results and generates a recommendation list.

[1691] Step 5:

[1692] Server: Sends the generated recommendation list to the user's device.

[1693] Step 6:

[1694] Terminal: Formats the received recommendation list and displays it to the user.

[1695] Auto-generated application checklists and schedules

[1696] Step 1:

[1697] User: Enters information about the institution and department to which they wish to apply into the application.

[1698] Step 2:

[1699] Terminal: Formats the entered application information and generates a request to send to the server.

[1700] Step 3:

[1701] Server: Stores the received application information in a database and retrieves application requirements for each educational institution and department from the database.

[1702] Step 4:

[1703] Server: Compares the acquired application requirements with the user's application information and generates a list of documents to be submitted and an application schedule.

[1704] Step 5:

[1705] Server: Sends the generated list of submitted documents and application schedule to the user's terminal.

[1706] Step 6:

[1707] Terminal: Formats received submission lists and application schedules, displays them to the user, and sets reminder notifications.

[1708] Gathering feedback and updating the AI ​​model

[1709] Step 1:

[1710] Users: Enter feedback about the service into the application.

[1711] Step 2:

[1712] Terminal: Formats the input feedback and generates a request to send to the server.

[1713] Step 3:

[1714] Server: Stores the received feedback in a database and prepares it for analysis.

[1715] Step 4:

[1716] Server: Analyzes the feedback and extracts necessary improvements to the AI ​​model.

[1717] Step 5:

[1718] Server: Update the AI ​​model based on the improvements and improve recommendation accuracy from next time onwards.

[1719] The above is a specific process flow for implementing the present invention, which significantly streamlines the college selection and application process for high school students, their parents, and educational counselors.

[1720] Example 1

[1721] 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."

[1722] In the traditional graduate school and application process, users had difficulty selecting the appropriate educational institution and department from the vast amount of information available. It was also time-consuming to individually research each institution's application requirements and manage the necessary documents and schedules. Furthermore, matching educational institutions based on research content had to be done manually, which was time-consuming and labor-intensive.

[1723] 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.

[1724] In this invention, the server includes a means for receiving grade information and interest information, a means for performing analysis to recommend educational institutions and departments based on the grade information and interest information, a means for providing a list of educational institutions and departments based on the analysis results, and a means for receiving feedback and updating the analysis means, thereby enabling users to quickly and accurately select appropriate educational institutions and departments.

[1725] "Academic performance information" is data that indicates the user's academic performance and evaluation.

[1726] "Interest information" is data that indicates the fields or themes in which a user is interested.

[1727] "Educational institution" refers to a school or university providing higher education.

[1728] A "faculty" is a department within a university or educational institution that is responsible for a particular field of education or research.

[1729] The "analysis means" is a function that performs calculations to identify appropriate educational institutions and departments based on grade information and interest information.

[1730] The "recommended list" is a list of educational institutions and departments recommended based on the analysis results.

[1731] "Feedback" is data showing user evaluations and opinions, and is used to improve the system.

[1732] A "literature abstract database" is a database that collects summary information from academic papers.

[1733] "Research content" refers to academic issues or themes in a specific field.

[1734] A "research facility" is a department or laboratory within an educational institution that conducts specific research.

[1735] "Application requirements" refers to the conditions and documents that must be submitted when applying to an educational institution.

[1736] The "list of documents to be submitted" is a list of documents required for application.

[1737] An "application schedule" is a plan that outlines important dates and deadlines in the application process.

[1738] "Reminder Notification" is a feature that notifies you in advance of important deadlines and events.

[1739] The system of the present invention is designed to streamline the educational institution selection and application process. Through mutual cooperation between users, terminals, and servers, the system recommends appropriate educational institutions and departments, enabling a smooth application process. Specific embodiments of the system are described below.

[1740] 1. Entering user data

[1741] Users use a dedicated application to enter information such as grades, areas of interest, and extracurricular activities. This information is stored on the device as JSON format data. For example, a user might enter into the application that "I'm interested in physics and belong to the science club as an extracurricular activity."

[1742] 2. Sending and Receiving Data

[1743] The terminal sends the entered data to the server. This transmission uses an API call via the Internet. Specifically, when the user presses the "Send" button, the input data is converted into JSON format and sent to the server.

[1744] 3. Data Analysis

[1745] The server uses a generative AI model to analyze the received grade and interest information. This analysis is performed using cloud services such as Google Cloud AI and AWS SageMaker. The server preprocesses the parsed JSON data and converts it into a format suitable for the AI ​​model for analysis.

[1746] 4. Generate and send recommendation list

[1747] The server generates a list of recommended educational institutions and departments based on the analysis results and sends it to the device. Specifically, it converts the analysis results into JSON format, makes an API call to the user's device, and sends the list of recommendations.

[1748] 5. Display of recommendation results

[1749] The device parses the recommendation list received from the server and displays it on the application UI, allowing the user to view the recommended educational institutions and departments on the screen.

[1750] 6. Use of Feedback

[1751] Users input feedback about the recommendation list and services provided. The device then sends this feedback to the server. The server analyzes the received feedback and updates the AI ​​model to improve recommendation results and matching accuracy from the next time onwards.

[1752] Specific examples

[1753] Examples:

[1754] For example, if high school student Sato wants to study chemistry, he or she can enter his or her grades and interest in chemistry into the app. The server performs AI analysis based on this information, lists universities with excellent chemistry programs, and sends the recommendation results to Sato's device. Sato can then review the recommendation list and consider the career path that best suits his or her aspirations.

[1755] Generative AI model input example:

[1756] "I'm interested in chemistry and I'd like to know which universities have good chemistry programs."

[1757] "Please recommend a university where I can study the theory of relativity."

[1758] "Please tell me the documents and schedule required to apply to the university I want to attend."

[1759] This invention allows users to efficiently select appropriate educational institutions and departments, and smoothly progress through the application process. The system provides highly accurate information through mutual cooperation between users, terminals, and servers.

[1760] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1761] Step 1:

[1762] User Data Entry

[1763] User: Enters information such as grades, areas of interest, and extracurricular activities into the application. Specifically, the user enters the required information into a form in the dedicated application and presses the "Submit" button. This data is temporarily saved on the device in JSON format.

[1764] Input: Grades, interests, extracurricular activities

[1765] Output: JSON format data

[1766] Step 2:

[1767] Sending data

[1768] Terminal: Sends JSON format data to the server. Specifically, when the "Send" button is pressed, the terminal executes an API call to send the data to the server. SSL is used during communication to ensure data security.

[1769] Input: JSON format data

[1770] Output: API calls to the server and data sent

[1771] Step 3:

[1772] Receiving and Parsing Data

[1773] Server: Parses the received data from JSON format and converts it into an internal data structure. Specifically, it analyzes the received JSON data and organizes it into data objects according to grades, areas of interest, and extracurricular activities.

[1774] Input: JSON format data

[1775] Output: Analysis and object format data

[1776] Step 4:

[1777] Data analysis

[1778] Server: Uses the parsed data to input the generative AI model. Specifically, it uses Google Cloud AI or AWS SageMaker to analyze grade information and areas of interest to identify the most suitable educational institution and department for the user. It then applies the calculations and evaluation logic of the generative AI model to extract appropriate recommendations.

[1779] Input: Analysis and object-formatted data

[1780] Output: Analysis results (recommendation list)

[1781] Step 5:

[1782] Generating and sending recommendation lists

[1783] Server: The analysis results are converted back into JSON format and sent to the user's device. Specifically, the generated recommendation list is sent to the device via an API call.

[1784] Input: Analysis results

[1785] Output: Recommendation list in JSON format, and API calls to the device

[1786] Step 6:

[1787] Receiving and displaying recommendations

[1788] Device: Parses the recommendation list received from the server and displays it in a format suitable for the user interface. Specifically, it interprets the received data and displays it in a list view or dashboard.

[1789] Input: JSON formatted recommendation list from the server

[1790] Output: Recommendation list displayed in a user interface

[1791] Step 7:

[1792] Matching research content

[1793] User: Enters research interests and keywords (e.g., "quantum mechanics") into the application.

[1794] Terminal: Sends the entered keyword to the server.

[1795] Server: Searches the institution's literature abstract database to identify research areas that match the keywords entered.

[1796] Specifically, the server executes a database query to list relevant papers and research fields, converts the analysis results back into JSON format, and sends them to the user's device.

[1797] Terminal: Parses and displays the list of recommended fields of study and educational institutions.

[1798] Input: Research Keywords

[1799] Output: A list of educational institutions that match the field of study

[1800] Step 8:

[1801] Application information management

[1802] User: Enters information about the institution and department to which they wish to apply into the application.

[1803] Terminal: Sends the entered application information to the server.

[1804] Server: Acquires and collates application requirements. Specifically, it uses web scraping and APIs to collect application requirements from each educational institution and verifies that they match the user's application information. It automatically generates a list of documents to be submitted and an application schedule based on the application requirements, converts them back into JSON format, and sends them to the device.

[1805] Terminal: Parse and view automatically generated submission lists and application schedules, and set reminders for important deadlines.

[1806] Input: Application information

[1807] Output: Application requirements, list of documents to be submitted, application schedule, reminder notices

[1808] Step 9:

[1809] Feedback input and analysis

[1810] User: Enters feedback on the recommendations and services provided.

[1811] Terminal: Sends the entered feedback to the server.

[1812] Server: Analyzes the feedback and updates the AI ​​model. Specifically, it analyzes the feedback data and uses it as training data to improve the accuracy of the generative AI model.

[1813] Input: Feedback data

[1814] Output: Updated analysis method

[1815] This allows users to quickly and accurately select the appropriate educational institution and department, and smoothly progress through the application process.

[1816] (Application example 1)

[1817] 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."

[1818] Conventional educational institution recommendation systems simply recommend suitable universities and departments based on academic records and interests. However, they lack a means to provide users with customized educational institution advertisements that are optimal for them, making it difficult to provide information efficiently and effectively. There was also a need for a way to effectively promote educational institutions through advertisements while providing important information for the application process.

[1819] 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.

[1820] In this invention, the server includes means for receiving the user's grade information and interest information, means for performing analysis to recommend the most suitable educational institution based on the grade information and interest information, means for providing a list of the recommended educational institutions based on the analysis results, and means for generating advertising data and displaying advertisements for educational institutions optimized for the user's characteristics. This makes it possible to provide the user with information on the most suitable educational institution, and by displaying customized advertisements, enables effective promotional activities.

[1821] "Grade information" is data indicating grades and evaluations for each subject that a user has obtained at school or the like.

[1822] "Interest information" is information relating to academic fields or research themes in which a user is particularly interested.

[1823] "Educational institutions" are facilities or organizations that provide higher education, such as universities and vocational schools.

[1824] A "faculty" is an organization within an educational institution such as a university that conducts study and research in a specific academic field.

[1825] "Analysis" is the process of performing calculations and evaluations using mathematical models and algorithms based on received performance information and interest information.

[1826] The "list" is a table listing the names and information of recommended educational institutions, departments, and laboratories.

[1827] "Advertising Data" is digital data generated to promote a particular educational institution.

[1828] "Customized advertising" refers to promotional advertising whose content is tailored based on a user's characteristics and interests.

[1829] A "paper abstract database" is a data store that collects summaries of numerous papers and is used to search for research content.

[1830] "Application information" refers to information about the documents and procedures required when a user applies to enroll in a particular educational institution or faculty.

[1831] "Application requirements" refer to the conditions and documents that must be met in order to enter a particular educational institution or faculty.

[1832] "List of documents to be submitted" refers to a list of documents required for application.

[1833] An "application schedule" is a timeline that shows the deadlines and schedule for each step in the application process.

[1834] "Reminder notification" is a function that notifies users in advance so that they do not forget important deadlines.

[1835] This invention is a system that recommends optimal educational institutions and departments based on a user's grades and interests. It also matches laboratories and educational institutions based on the user's research interests and displays customized advertisements, thereby providing efficient information provision and promotion.

[1836] To realize this system, the following hardware and software are used.

[1837] Hardware: User's smartphone, server

[1838] Software: Python, REST API, JSON, Scikit-learn or TensorFlow

[1839] System configuration

[1840] User Data Entry

[1841] Users use a smartphone app to input their grades, areas of interest, and research keywords, and the application sends this information to the server in JSON format.

[1842] Data analysis

[1843] The server analyzes the received grades and interest information using AI models (based on Scikit-learn and TensorFlow) to identify the most suitable educational institutions and departments. The analysis results are generated as a recommendation list.

[1844] Generating a recommendation list

[1845] Based on the analysis results, a list of the most suitable educational institutions and departments is generated, which is sent in JSON format to the user's smartphone and displayed within the app.

[1846] Generate personalized ads

[1847] The server generates advertising data based on the analysis results and user characteristics, which includes information about the educational institution and is displayed in a customized format to the user.

[1848] Application information management

[1849] When a user inputs information about the educational institution and department to which they wish to apply, the server retrieves the application requirements and automatically generates a list of documents to be submitted and an application schedule, allowing users to efficiently proceed with their application.

[1850] Reminders

[1851] For important deadlines, smartphone apps can set reminder notifications to remind users not to forget about them.

[1852] Specific examples

[1853] Recommendations based on user performance information

[1854] High school students enter their grades (90 for math, 95 for science, 85 for English) and areas of interest (science, physics) into the app. This data is sent to a server, which analyzes it and generates a list of the most suitable universities and departments (e.g., universities with a strong science focus). This list is accompanied by corresponding customized university advertisements.

[1855] Prompt Sentence Examples

[1856] An example of a user prompt would be, "My grades are 90 in math, 95 in science, and 85 in English. My areas of interest are science and physics." The system will then recommend and display advertisements for the most suitable educational institutions.

[1857] In this way, the present invention makes it possible to provide users with information about educational institutions and to promote their advertisements efficiently and effectively.

[1858] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1859] Step 1:

[1860] The user's device is started, and the user opens the app and enters their grades, areas of interest, and research keywords. The input information (grades, areas of interest, and research keywords) is converted into JSON format and sent to the server.

[1861] Step 2:

[1862] The server receives JSON-formatted data (grade information, areas of interest, research keywords) sent from the device. The server passes this data to an AI model (Scikit-learn or TensorFlow) for analysis. The AI ​​model identifies the most suitable educational institutions and departments based on the input data and generates a list of recommendations. The output is a list of recommended educational institutions and departments.

[1863] Step 3:

[1864] The server returns the generated recommendation list in JSON format to the device, which receives it and visually displays it to the user. The display is in list format, including detailed information about the recommended educational institutions and departments.

[1865] Step 4:

[1866] The server further generates customized advertising data based on the analysis results and the user's characteristics. The advertising data is configured in a manner optimized for the user and includes specific information and promotional content from the educational institution. The output is the customized advertising data.

[1867] Step 5:

[1868] The server transmits the generated advertisement data to the terminal, which receives it and displays the advertisement to the user along with the recommendation list. The advertisement is visually integrated into the interface and is designed to attract the user's attention.

[1869] Step 6:

[1870] Users enter their desired application information into the app. The device converts this information into JSON format and sends it to the server. This application information includes the desired educational institution and department.

[1871] Step 7:

[1872] The server receives the application information sent from the terminal and retrieves the application requirements of each educational institution and department from the database. The server uses this information to automatically generate a list of documents to be submitted and an application schedule. The output is a list of documents to be submitted and an application schedule.

[1873] Step 8:

[1874] The server sends the generated list of documents to be submitted and the application schedule to the terminal, which receives it and displays it in an easy-to-understand manner for the user. A reminder notification function is also set up to notify the user of important deadlines.

[1875] This flow allows users to receive recommendations for the most suitable educational institutions based on their academic records and interests, display customized advertisements, and streamline the application process, all within a single application.

[1876] 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.

[1877] The present invention provides a system for recommending educational institutions and departments based on a user's grades and interests, streamlining the application process, and also provides customized recommendation information based on the user's emotions by combining it with an emotion engine that recognizes the user's emotions.

[1878] Receiving and analyzing user performance and interest information

[1879] 1. User data entry

[1880] Users: Enter information into the application, such as grades, interests, and extracurricular activities.

[1881] 2. Sending and Receiving Data

[1882] Terminal: Formats the entered data and sends it to the server.

[1883] 3. Data Analysis

[1884] Server: Stores the received grade information and interest information in a database and prepares for analysis.

[1885] 4. AI-based analysis

[1886] Server: Uses AI models to analyze the user's grades and interests to identify the most suitable educational institution and department.

[1887] 5. Customization with Emotion Engine

[1888] Server: The AI ​​analysis results are further analyzed by the emotion engine to generate customized recommendations based on the user's emotional state.

[1889] 6. Generating and Sending Recommendation Lists

[1890] Server: Generates a recommendation list optimized by the emotion engine and sends it to the user's device.

[1891] 7. Display of recommendation results

[1892] Terminal: Displays the received recommendation list to the user.

[1893] Examples:

[1894] High school student Yamada enters his grades and interests into the app. The server receives and analyzes this information, and an AI model identifies the most suitable university and department. At the same time, an emotion engine analyzes Yamada's emotions when he enters the information, and if he is in a stressful situation, it recommends a university with a strong support system.

[1895] Research content matching

[1896] 1. Enter keywords

[1897] User: Enters research interests and keywords into the application.

[1898] 2. Sending and Receiving Data

[1899] Terminal: Formats the entered keywords and sends them to the server.

[1900] 3. Research database collation

[1901] Server: Searches a database of paper abstracts to identify research fields that match the entered keywords.

[1902] 4. Generating and sending matching results

[1903] Server: Generates a list of recommended educational institutions and laboratories based on the identified research field, customizes it according to the user's emotional state, and sends it to the user's device.

[1904] 5. Display of matching results

[1905] Terminal: Formats the received recommendation list and displays it to the user.

[1906] Examples:

[1907] Sato, who is interested in physics, enters "quantum mechanics" as a keyword. The server searches a database of paper abstracts based on the keyword and identifies universities and laboratories conducting relevant research. At the same time, the emotion engine takes Sato's emotional state into account and prioritizes recommending universities with low stress and good research environments.

[1908] Auto-generated application checklists and schedules

[1909] 1. Enter application information

[1910] User: Enters information about the institution and department to which they wish to apply into the application.

[1911] 2. Sending and Receiving Data

[1912] Terminal: Formats the entered application information and sends it to the server.

[1913] 3. Analysis of application requirements

[1914] Server: Obtains application requirements for each educational institution and department and matches them with the user's application information.

[1915] 4. Generate checklists and schedules

[1916] Server: Automatically generates a list of documents to be submitted and an application schedule based on the application requirements. It also takes into account the user's emotional state, allowing for flexibility in the schedule and adding explanations.

[1917] 5. Data transmission and display

[1918] Server: Sends the generated list of submitted documents and application schedule to the user's terminal, which displays it to the user and sets reminder notifications.

[1919] Examples:

[1920] Mr. Tanaka, who is considering applying to multiple universities, enters the application information for each university into the app. The server receives this information, obtains the application requirements for each university, and generates a list of documents to be submitted and an application schedule. The emotion engine takes Mr. Tanaka's emotional state into account and adds warnings and specific advice to areas where he is likely to feel anxious.

[1921] Gathering feedback and updating the AI ​​model

[1922] 1. Enter and submit your feedback

[1923] User: Enters feedback about the service into the application and sends it to the server from the terminal.

[1924] 2. Analyzing feedback and updating the AI ​​model

[1925] Server: Analyzes the received feedback, extracts necessary improvements to the AI ​​model and emotion engine, and updates the model.

[1926] Examples:

[1927] Users provide feedback after using the system, which the server reads, analyzes areas for improvement in the service, and updates the AI ​​model and emotion engine to provide better recommendations and research matching the next time users use the system.

[1928] As a result, the present invention provides an efficient and emotionally sensitive educational institution selection and application process.

[1929] The processing flow will be explained below.

[1930] Customized proposals for universities and departments using AI

[1931] Step 1:

[1932] Users: Enter information into the application, such as grades, interests, and extracurricular activities.

[1933] Step 2:

[1934] Terminal: Formats the entered data and generates a request to send to the server.

[1935] Step 3:

[1936] Server: Stores the received user performance information and interest information in a database and prepares for analysis.

[1937] Step 4:

[1938] Server: Uses AI models to analyze the user's grades and interests to identify the most suitable educational institution and department.

[1939] Step 5:

[1940] Server: Uses an emotion engine to analyze the emotion data of the user's input in real time and identify the emotional state.

[1941] Step 6:

[1942] Server: Based on the analysis results of the emotion engine, the recommendation results of the AI ​​model are adjusted to generate a recommendation list optimized for the user's emotional state.

[1943] Step 7:

[1944] Server: Sends the optimized recommendation list to the user's device.

[1945] Step 8:

[1946] Terminal: Formats the received recommendation list and displays it to the user.

[1947] Examples:

[1948] High school student Yamada enters his grades and interests into the app. The server receives and analyzes this information, and an AI model identifies the appropriate university and department. At the same time, an emotion engine analyzes Yamada's emotional state (for example, whether his stress level is high or low), generates a list of recommended universities with better support systems, and sends it to Yamada's device.

[1949] Research content matching

[1950] Step 1:

[1951] User: Enters research interests and keywords into the application.

[1952] Step 2:

[1953] Terminal: Formats the entered keywords and generates a request to send to the server.

[1954] Step 3:

[1955] Server: Searches the institution's paper abstract database based on the received keywords.

[1956] Step 4:

[1957] Server: From the search results, identify research fields that match the keywords and generate a list of recommendations.

[1958] Step 5:

[1959] Server: Uses an emotion engine to analyze the user's emotional state and match appropriate educational institutions and laboratories based on a recommended list of research fields.

[1960] Step 6:

[1961] Server: Sends the optimized research recommendation list to the user's device.

[1962] Step 7:

[1963] Terminal: Formats the received recommendation list and displays it to the user.

[1964] Examples:

[1965] Sato, who is interested in physics, enters "quantum mechanics" as a keyword. The server searches a database of paper abstracts based on the entered keywords and identifies suitable universities and research laboratories. At the same time, the emotion engine analyzes Sato's emotional state and generates a list of recommendations focusing on universities with low stress and good research environments, which is sent to Sato's device.

[1966] Auto-generated application checklists and schedules

[1967] Step 1:

[1968] User: Enters information about the institution and department to which they wish to apply into the application.

[1969] Step 2:

[1970] Terminal: Formats the entered application information and generates a request to send to the server.

[1971] Step 3:

[1972] Server: Stores the received application information in a database and obtains the application requirements of each educational institution and department.

[1973] Step 4:

[1974] Server: Compares the acquired application requirements with the user's application information and generates a list of documents to be submitted and an application schedule.

[1975] Step 5:

[1976] Server: Uses an emotion engine to analyze the user's emotional state and optimize the filing list and application schedule.

[1977] Step 6:

[1978] Server: Sends the optimized submission document list and application schedule to the user's terminal.

[1979] Step 7:

[1980] Terminal: Formats and displays received submission lists and filing schedules to the user, and sets reminders for important deadlines.

[1981] Examples:

[1982] Mr. Tanaka, who is considering applying to multiple universities, enters the application information for each university into the app. The server receives this information, obtains the application requirements for each university, and generates a list of documents to be submitted and an application schedule. The emotion engine analyzes Mr. Tanaka's emotional state and adds warnings and specific advice to areas where he is likely to feel anxious.

[1983] Gathering feedback and updating the AI ​​model

[1984] Step 1:

[1985] Users: Enter feedback about the service into the application.

[1986] Step 2:

[1987] Terminal: Formats the input feedback and generates a request to send to the server.

[1988] Step 3:

[1989] Server: Stores the received feedback in a database and prepares it for analysis.

[1990] Step 4:

[1991] Server: Analyzes the feedback and extracts necessary improvements to the AI ​​model and emotion engine.

[1992] Step 5:

[1993] Server: Update the AI ​​model and emotion engine based on the improvements, and improve the accuracy of recommendations from next time onwards.

[1994] The above is a specific processing flow for implementing the present invention, which significantly improves the efficiency of the university selection and application process for high school students, their parents, and educational counselors, while also enabling the provision of services that are sensitive to the user's emotions.

[1995] Example 2

[1996] 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."

[1997] Conventional educational institution recommendation systems are limited to simple recommendations based on users' grades and interests, and lack customization that takes into account the user's emotional state. Furthermore, in matching optimal research fields and the application process, efficient recommendations and schedule management that take into account the user's emotional state are lacking.

[1998] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving the user's grade information and interest information, a means for performing an analysis to recommend the most suitable educational institution and faculty based on the user's grade information and interest information, a means for further analyzing the analysis results with an emotion analysis engine and customizing the recommendation information based on the user's emotional state, and a means for providing the customized recommendation information to the user. This enables customized recommendations that take into account the user's emotional state in addition to the user's grade information and interest information.

[1999] "Academic achievement information" refers to data that represents a user's academic achievements at an educational institution, such as academic records, test results, and evaluation scores.

[2000] "Interest information" is information that indicates a user's personal interests, such as fields of interest, subjects, extracurricular activities, and future career paths.

[2001] "Analysis" refers to analyzing and processing data for a specific purpose based on received information.

[2002] "Educational institutions" refers to organizations and facilities that teach academic subjects or skills, such as universities, technical colleges, and vocational schools.

[2003] An "emotion analysis engine" refers to an algorithm or software tool that analyzes a user's emotional and psychological state based on user input data and behavioral data.

[2004] "Recommendation" refers to suggesting the best option to a user based on specific criteria.

[2005] A database is an information system that systematically organizes and stores large amounts of data, and efficiently searches and manages them.

[2006] "Application information" refers to data such as personal information and desired information required when applying to an educational institution or faculty of a user's choice.

[2007] "Document List" refers to the list of documents required for the application process at an educational institution.

[2008] An "application schedule" is a plan showing the various steps and deadlines required for filing an application.

[2009] "Reminder notification" refers to a notification function that notifies users when a specific deadline or event is approaching.

[2010] The present invention is a system that recommends educational institutions and departments based on a user's grades and interests, streamlining the application process. Furthermore, by combining it with an emotion analysis engine that recognizes the user's emotions, the system provides customized recommendation information based on the user's emotions.

[2011] Hardware and software used

[2012] This system uses the following hardware and software:

[2013] 1. Hardware

[2014] Terminal: A device used by a user to input information, such as a smartphone or computer.

[2015] Server: A cloud-based server for analyzing the received data and generating recommendation information.

[2016] 2. Software

[2017] Input forms: web and mobile applications that run on devices.

[2018] Database: A relational database such as MySQL.

[2019] Generative AI models: Python-based AI analysis tool.

[2020] Sentiment analysis engine: Algorithms and software (e.g., natural language processing tools and machine learning models) for analyzing a user's emotional state.

[2021] A concrete example of the processing flow

[2022] Receiving and analyzing user performance and interest information

[2023] 1. User data entry

[2024] A user enters his / her grades, areas of interest, extracurricular activities, etc. into an application input form. For example, a high school student enters his / her final exam grades and interest in chemistry.

[2025] 2. Sending and Receiving Data

[2026] The terminal converts the input data into JSON format and sends it to the server via an HTTP POST request, which the server receives and stores in a database.

[2027] 3. Data Analysis

[2028] The server uses a Python-based generative AI model to analyze the data it receives, identifying the best educational institution and department for the user based on grades and interests.

[2029] 4. Customization using sentiment analysis engine

[2030] The server inputs the analysis results into an emotion analysis engine to analyze the user's emotional state, and customizes recommendations based on this. For example, if a user is in a stressful situation, it might recommend universities with strong support systems.

[2031] 5. Generating and sending recommendation lists

[2032] The server generates a customized recommendation list and sends it to the user's terminal, which displays the received information to the user.

[2033] Prompt Sentence Examples

[2034] "Please enter your academic achievements, such as final exam scores and GPA."

[2035] "What academic subjects and extracurricular activities are you interested in? For example, chemistry, physics, basketball, etc."

[2036] "Tell me about your current mood or emotions. For example, are you feeling stressed or relaxed?"

[2037] As a result, this invention realizes an efficient and emotion-sensitive educational institution selection and application process. By providing optimal recommendations based not only on the user's grades and interests, but also using an emotion analysis engine, it is possible to provide the optimal learning environment and application support for the user.

[2038] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2039] Step 1: User Data Entry

[2040] Users enter their grades, interests, extracurricular activities, etc. into the application's input form. Specifically, the user fills in the application's form fields and presses the submit button. The input data includes the user's grades (e.g., GPA, test results), interests (e.g., chemistry, biology), and extracurricular activities (e.g., basketball, music).

[2041] Step 2: Sending and Receiving Data

[2042] The device formats the input data and sends it to the server. Specifically, it converts the input data into JSON format and sends it to the server using an HTTP POST request. The input includes the grades and interest information entered by the user, and the output is the data received by the server.

[2043] Step 3: Store the data

[2044] The server stores the received grade information and interest information in a database. Specifically, it saves the data in a relational database such as MySQL. In this step, the data received by the server is used as input, and the output is saved in the database.

[2045] Step 4: Analysis of performance and interest information

[2046] The server uses a generative AI model to analyze the received data. Specifically, the Python-based AI model takes grade information and interest information as input and performs data operations to identify the most suitable educational institutions and departments. The output is a list of the most suitable educational institutions and departments.

[2047] Step 5: Customizing with a sentiment analysis engine

[2048] The server further analyzes the AI ​​analysis results using an emotion analysis engine, customizing the results to take the user's emotional state into account. Specifically, the emotion analysis engine uses the results of the AI ​​model and the user's emotional data as input data, and generates customized recommendation information as output.

[2049] Step 6: Generate and submit a recommendation list

[2050] The server generates a customized recommendation list and sends it to the user's device. Specifically, it converts the recommendation list into text or JSON format and sends it as an HTTP response. In this step, the recommendation information customized by the sentiment analysis engine is used as input, and the output is the recommendation list sent to the user's device.

[2051] Step 7: Viewing Recommendations

[2052] The device displays the received recommendation list to the user. Specifically, it uses a UI component for visually displaying the received data to provide information to the user in an easy-to-read format. The input includes the recommendation list received from the server, and the output is the visually displayed recommendation results.

[2053] Specific working example:

[2054] High school students enter their grades and areas of interest into the app.

[2055] The app converts the input data into JSON format and sends it to the server.

[2056] The server stores the data in a database.

[2057] AI models analyze grade and interest information to identify the most suitable educational institutions and departments.

[2058] A sentiment analysis engine takes into account the user's stress level to customize recommendations.

[2059] The final recommendation list is sent to the user's terminal and displayed to the user.

[2060] (Application example 2)

[2061] 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."

[2062] Conventional recommendation systems for educational institutions and departments provide optimal options based on a user's grades and interests, but rarely take into account the user's emotional state. As a result, users may receive recommendation results while feeling stressed or anxious, which could lead to decisions that differ from their original intentions. Furthermore, the lack of reminder notifications for important deadlines can lead users to forget submission deadlines. These issues create a need for systems that can provide users with more accurate options.

[2063] 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.

[2064] In this invention, the server includes means for receiving the user's grade information and interest information, means for performing analysis to recommend the most suitable educational institution and department based on the user's grade information and interest information, means for providing the user with a list of recommended educational institutions and departments based on the analysis results, means for recognizing an emotional state associated with the received grade information and interest information, and means for generating customized recommendation information based on the emotional state. This enables the user to select the most suitable educational institution or department taking into consideration the user's emotional state, and makes it possible to realize recommendations that reduce stress and anxiety.

[2065] "Academic record information" refers to information about a user's academic performance at an educational institution, such as academic record, grade point average, and test results.

[2066] "Interest information" is information about the user's fields of interest, topics, academic interests, and extracurricular activities.

[2067] The "means for performing analysis" is a method of processing data to recommend the most suitable educational institution and faculty based on the user's grade information and interest information.

[2068] The "recommended list" is a list of educational institutions and faculties suitable for the user, generated based on the analysis results.

[2069] An "emotional state" is a state that represents a user's current mood or emotion, such as stress, anxiety, or joy.

[2070] An "emotion engine" is a device or software that recognizes a user's emotional state and customizes information based on that state.

[2071] "Customized recommendation information" refers to recommendation information for the most suitable educational institution or department that is generated by taking into consideration the user's emotional state in addition to their academic record and interest information.

[2072] A "paper abstract database" is a database that stores summary information on research papers, and allows searches for specific fields or keywords.

[2073] "Application requirements" refer to the conditions, documents to be submitted, schedules, etc. that must be met when applying to an educational institution or department.

[2074] "Reminder notification" is a notification function that automatically notifies users of important deadlines and schedules.

[2075] "Warning" refers to providing information to alert users to specific matters.

[2076] "Advice" is specific instructions or suggestions to help users make good decisions in applying and choosing educational institutions.

[2077] A specific embodiment of the present invention will be described below. This system recommends the most suitable educational institution and department based on the user's grades and interests. Furthermore, an emotion engine is used to analyze the user's emotional state and generate customized recommendation information.

[2078] System Program Overview

[2079] 1. Data entry: Users use a smartphone or head-mounted display to enter grade information and areas of interest into the application.

[2080] 2. Data transmission and reception: Data entered by the user is formatted and sent to the server.

[2081] 3. AI analysis: The server stores the received grade information and interest information in a database and analyzes it using a generative AI model.

[2082] 4. Emotion engine: The server analyzes the user's emotional state in real time using devices such as a webcam.

[2083] 5. Recommendation list generation: Based on the analysis results and emotional state, the server generates an optimized recommendation list of educational institutions and departments and sends it to the user's device.

[2084] 6. Display Results: The device displays the results to the user and provides reminders and alerts as special advice.

[2085] Hardware and software used

[2086] Hardware: Smartphone, head-mounted display, webcam

[2087] Software: Generative AI models for AI analysis, EmotionRecognition library for emotion analysis, database management system

[2088] Detailed processing instructions

[2089] The server first receives the user's grades and interests. This information is formatted and stored in a database. Next, a generative AI model is used to analyze the data and identify the most suitable educational institution and department for the user. At the same time, the server uses the EmotionRecognition library to analyze the user's emotional state in real time. This allows the server to generate customized recommendations that take into account the user's stress and anxiety.

[2090] For example, if a high school student inputs their grades and interest in "environmental science," the server will recognize their emotional state as stressed and prioritize recommendations for universities with strong support systems. Along with the recommendations, the user's device will display reminders and specific instructions about important deadlines.

[2091] Example prompt sentence:

[2092] A high school senior entered grade information of "4.2 GPA" and area of ​​interest of "environmental science." The system analyzed the student's emotional state as being high in stress and recommended an environmental science university with a strong support system.

[2093] As described above, the present invention supports users in selecting an educational institution that is optimal for them and takes into consideration their emotional state.

[2094] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2095] Step 1:

[2096] Users use a smartphone or head-mounted display to input grade and interest information into the application, including grade point averages, test results, academic interests, and themes. The input data is then formatted for consistency.

[2097] Input: Grade information, interest information

[2098] Output: Formatted grade and interest information

[2099] Step 2:

[2100] The device transmits formatted performance and interest information to a server, where the data is transmitted using a secure communications protocol.

[2101] Input: Formatted grade and interest information

[2102] Output: Send data to the server

[2103] Step 3:

[2104] The server stores the received grade information and interest information in a database, which accumulates data for each user and is used for later analysis.

[2105] Input: Achievement information and interest information sent to the server

[2106] Output: Information stored in a database

[2107] Step 4:

[2108] The server uses a generative AI model to analyze the grade and interest information stored in the database, which identifies the educational institutions and departments that are best suited to the user.

[2109] Input: Grades and interest information stored in the database

[2110] Output: Analysis results for recommendations (list format)

[2111] Step 5:

[2112] The server analyzes the user's emotional state in real time using a webcam and the EmotionRecognition library for emotion analysis. The results of the emotion analysis are also saved as data.

[2113] Input: Real-time video of user

[2114] Output: User's emotional state data

[2115] Step 6:

[2116] The server generates an optimized list of recommended educational institutions and departments based on the analysis results and emotional state data. Taking into account the emotional state, it recommends educational institutions with strong support systems for users who are under stress.

[2117] Input: Analysis results, emotional state data

[2118] Output: A customized recommendation list

[2119] Step 7:

[2120] The server then transmits the generated customized recommendation list to the user's device using a secure communication protocol.

[2121] Input: Customized recommendation list

[2122] Output: sent to the user's device

[2123] Step 8:

[2124] The device receives and displays the recommendations to the user, and also provides reminders and specific reminders for important deadlines.

[2125] Input: Customized recommendation list

[2126] Output: Display of recommendation list, notification of reminders and reminders

[2127] Through the above processing steps, the user can receive recommendations for the most suitable educational institution and department that take into consideration the user's emotional state.

[2128] 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.

[2129] 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.

[2130] 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.

[2131] 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.

[2132] 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.

[2133] 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.

[2134] 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).

[2135] 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.

[2136] 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."

[2137] 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.

[2138] 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).

[2139] 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.

[2140] 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.

[2141] 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.

[2142] 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.

[2143] 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.

[2144] 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.

[2145] 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.

[2146] 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.

[2147] 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.

[2148] 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.

[2149] The following is further disclosed regarding the above embodiment.

[2150] (Claim 1)

[2151] means for receiving performance information and interest information of the user;

[2152] A means for performing analysis to recommend the most suitable educational institution and faculty based on the user's grade information and interest information;

[2153] a means for providing the user with a list of recommended educational institutions and departments based on the analysis results;

[2154] A system including:

[2155] (Claim 2)

[2156] A means of receiving research topics and keywords that interest the user, and

[2157] A means of searching your institution's database of research abstracts to identify areas of research that match your research interests and keywords;

[2158] A means of providing a list of recommended educational institutions and laboratories based on the identified research areas;

[2159] 10. The system of claim 1, comprising:

[2160] (Claim 3)

[2161] means for receiving information about the educational institution and department to which the user wishes to apply;

[2162] A means of obtaining application requirements for each educational institution and department and matching them with the user's application information;

[2163] A means for automatically generating a submission document list and an application schedule based on application requirements;

[2164] Providing users with a submission list and filing schedule, and the means to set reminders for important deadlines;

[2165] 10. The system of claim 1, comprising:

[2166] "Example 1"

[2167] (Claim 1)

[2168] means for receiving performance information and interest information of the user;

[2169] A means for performing analysis to recommend appropriate educational institutions and departments based on the user's grade information and interest information;

[2170] a means for providing the user with a list of recommended educational institutions and departments based on the analysis results;

[2171] ...

Claims

1. means for receiving performance information and interest information of the user; A means for performing analysis to recommend the most suitable educational institution and faculty based on the user's grade information and interest information; a means for providing the user with a list of recommended educational institutions and departments based on the analysis results; A system including:

2. A means of receiving research topics and keywords that interest the user, and A means of searching your institution's database of research abstracts to identify areas of research that match your research interests and keywords; A means of providing a list of recommended educational institutions and laboratories based on the identified research areas; The system of claim 1 , comprising:

3. means for receiving information about the educational institution and department to which the user wishes to apply; A means of obtaining application requirements for each educational institution and department and matching them with the user's application information; A means for automatically generating a submission document list and an application schedule based on application requirements; Providing users with a submission list and filing schedule, and the means to set reminders for important deadlines; The system of claim 1 , comprising:

Images