system

Abstract

The system according to this embodiment aims to automate the management of applicants' applications and the collection of pass / fail results, thereby efficiently adjusting the number of successful candidates. [Solution] The system according to the embodiment comprises a reception unit, a distribution unit, a collection unit, an analysis unit, and a proposal unit. The reception unit receives applicants' applications at a temporary counter. The distribution unit automatically distributes the applications received by the reception unit to each university. The collection unit collects acceptance / rejection results from each university in real time based on the applications distributed by the distribution unit. The analysis unit analyzes the preference order and intention to enroll based on the acceptance / rejection results collected by the collection unit. The proposal unit proposes an appropriate number of successful applicants based on the preference order and intention to enroll analyzed by the analysis unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that the management of application forms of examinees and the collection of pass / fail results are performed manually, and it is difficult to efficiently adjust the number of qualified candidates.

[0005] The system according to the embodiment aims to automate the management of application forms of examinees and the collection of pass / fail results, and efficiently adjust the number of qualified candidates.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a distribution unit, a collection unit, an analysis unit, and a proposal unit. The reception unit receives applicants' applications at a temporary counter. The distribution unit automatically distributes the applications received by the reception unit to each university. The collection unit collects acceptance / rejection results from each university in real time based on the applications distributed by the distribution unit. The analysis unit analyzes the preference order and intention to enroll based on the acceptance / rejection results collected by the collection unit. The proposal unit proposes an appropriate number of successful applicants based on the preference order and intention to enroll analyzed by the analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can automate the management of applicants' applications and the collection of pass / fail results, and efficiently adjust the number of successful candidates. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

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

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

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

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

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

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

[0028] (Example of form 1) The system according to an embodiment of the present invention is a system that receives applicants' applications at a central counter, an AI agent automatically distributes them to each university, collects acceptance / rejection results in real time, and allows each university to adjust the number of accepted students. This system receives applicants' applications at a central counter, an AI agent automatically distributes the received applications to each university, collects acceptance / rejection results from each university in real time, and allows each university to adjust the number of accepted students. The AI ​​agent analyzes the applicants' preference rankings and intentions to enroll through communication and proposes the optimal number of accepted students. First, applicants' applications are received at a central counter. At this time, applicants can submit applications to multiple universities at once. For example, if an applicant submits applications to University A, University B, and University C, they can be received at the central counter all at once. Next, the AI ​​agent automatically distributes the received applications to each university. The AI ​​agent analyzes the applicants' application information and distributes it to each university in the appropriate format. For example, it can distribute it to University A in PDF format and to University B in Excel format. Furthermore, the AI ​​agent collects acceptance / rejection results from each university in real time. The AI ​​agent automatically collects and centrally manages acceptance / rejection results from each university. This allows applicants to check acceptance / rejection results from multiple universities at once. The AI ​​agent analyzes applicants' preference rankings and enrollment intentions through communication. For example, if an applicant is accepted to their first-choice university, they can indicate their intention not to enroll in their second-choice or lower-choice universities. This allows each university to adjust the number of accepted students. Finally, the AI ​​agent proposes the optimal number of accepted students. The AI ​​agent analyzes applicants' preference rankings and enrollment intentions and proposes the optimal number of accepted students for each university. This reduces the risk of exceeding enrollment quotas and cuts to subsidies for each university. As a result, the system can efficiently receive, distribute, collect, analyze, and propose applicant applications.

[0029] The system according to this embodiment comprises a reception unit, a distribution unit, a collection unit, an analysis unit, and a proposal unit. The reception unit receives applicants' applications at a temporary counter. Applicants' applications include, but are not limited to, handwritten applications and digital applications. The reception unit digitizes and accepts handwritten applications using scanning technology. The reception unit can also directly accept applications submitted in digital format. Furthermore, the reception unit can read printed applications using OCR technology. For example, the reception unit scans handwritten applications with a high-resolution scanner and converts them into text information using OCR technology. Digital applications can be directly accepted if submitted in a specific file format. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The distribution unit uses AI to automatically distribute the applications received by the reception unit to each university. Distribution is carried out by, but is not limited to, email, distribution through a dedicated system, etc. For example, the distribution department analyzes applicants' application information and distributes it to each university in the appropriate format. For instance, it can distribute it to University A in PDF format and to University B in Excel format. The distribution department can also adjust the level of detail in the distribution based on the importance of each university. For example, it can distribute application forms with detailed information to highly important universities and application forms with concise information to less important universities. The collection department uses AI to collect acceptance / rejection results from each university in real time based on the application forms distributed by the distribution department. Collection is carried out by methods such as data collection using APIs or periodic polling, but is not limited to these examples. For example, the collection department automatically collects and centrally manages acceptance / rejection results from each university. This allows applicants to check acceptance / rejection results from multiple universities at once. The collection department can also improve the accuracy of collection by considering the interrelationships between universities. For example, it can analyze the interrelationships between universities and collect acceptance / rejection results from related universities simultaneously. The analysis department uses AI to analyze preference rankings and enrollment intentions based on the acceptance / rejection results collected by the collection department. Analysis may be performed using methods such as survey results or historical data analysis, but is not limited to these examples.For example, the analysis department analyzes applicants' preference rankings and enrollment intentions through communication with them. For instance, if an applicant is accepted to their first-choice university, they may indicate that they do not intend to attend their second-choice or lower-ranked universities. The analysis department can also predict current trends by referring to past data when analyzing preference rankings and enrollment intentions. For example, it can analyze past preference ranking data to predict current trends. The proposal department uses AI to propose the optimal number of accepted students based on the preference rankings and enrollment intentions analyzed by the analysis department. Proposals are based on, but are not limited to, university capacity and past acceptance data. For example, the proposal department analyzes applicants' preference rankings and enrollment intentions and proposes the optimal number of accepted students for each university. This allows universities to mitigate the risks of exceeding their enrollment capacity or having subsidy cuts. The proposal department can also improve the accuracy of its proposals by considering the interrelationships between universities. For example, it can analyze the interrelationships between universities and simultaneously propose the number of accepted students for related universities. This enables the system according to the embodiment to efficiently receive, distribute, collect, analyze, and propose information based on applicants' applications.

[0030] The reception desk accepts applicants' applications at a temporary counter. These applications may include, but are not limited to, handwritten or digital forms. The reception desk may, for example, digitize handwritten applications using scanning technology and accept them. It can also directly accept digitally submitted applications. Furthermore, the reception desk can read printed applications using OCR technology. For example, the reception desk may scan handwritten applications with a high-resolution scanner and convert them into text information using OCR technology. Digital applications can be directly accepted if submitted in a specific file format. OCR technology accurately recognizes printed characters and converts them into digital text. The reception desk uses a combination of the latest scanning and OCR technologies to efficiently process the diverse formats of applications submitted by applicants. Handwritten applications are captured as high-resolution images using a scanner and then converted into text information using OCR technology. This process allows for the accurate conversion of both handwritten and printed characters into digital data. Digital applications are often submitted in common file formats such as PDF, Word, and Excel, and the application department directly receives these files and stores them in its database. Furthermore, the application department can provide a web portal that allows applicants to submit their applications online. This web portal allows applicants to enter their information and upload necessary documents. The application department receives and processes this data in real time. This allows applicants to easily submit their applications from home, and the application department can manage the data efficiently. Additionally, the application department has a function to review the submitted applications and notify applicants if there are any deficiencies. For example, if necessary documents are missing or there are errors in the information provided, the application department can automatically notify the applicant and prompt them to make corrections. This improves the efficiency of the application department's work, as applicants can review and correct their submitted applications.

[0031] The distribution department uses AI to automatically distribute application forms received by the reception department to each university. Distribution is carried out by methods such as email or through a dedicated system, but is not limited to these examples. For example, the distribution department analyzes the applicant's application information and distributes it to each university in the appropriate format. For example, it can distribute it to University A in PDF format and to University B in Excel format. The distribution department can also adjust the level of detail in the distribution based on the importance of each university. For example, it can distribute application forms with detailed information to high-priority universities and application forms with concise information to low-priority universities. Because the distribution department uses AI to distribute applicants' applications to each university in the most optimal format, it can be customized to meet the requirements of each university. For example, one university may prefer PDF application forms, while another may prefer Excel data. The distribution department understands these requirements in advance and converts applicants' applications to the appropriate format before distribution. Furthermore, the distribution department can consider the importance of each university and adjust the level of detail in the distribution. For example, the distribution department will send application forms containing detailed information about applicants to universities of high importance, and to universities of lower importance, it will send concise application forms containing only basic information. In this way, the distribution department will achieve flexible distribution tailored to the needs of each university. It is also important for the distribution department to take security measures during distribution. For example, encryption technology will be used to protect data so that the contents of application forms are not leaked to third parties. Furthermore, the distribution department will record the distribution history so that it can be reviewed later. This will enable a quick response even if problems occur during distribution. The distribution department will use AI to efficiently distribute applicants' application forms and achieve flexible responses tailored to the needs of each university.

[0032] The data collection unit uses AI to collect admission results from each university in real time based on applications distributed by the distribution unit. Data collection is carried out using methods such as API-based data collection and periodic polling, but is not limited to these examples. For instance, the data collection unit automatically collects and centrally manages admission results from each university. This allows applicants to check admission results from multiple universities simultaneously. The data collection unit can also improve the accuracy of data collection by considering the interrelationships between universities. For example, it can analyze interrelationships between universities and collect admission results from related universities simultaneously. The data collection unit plays a crucial role in efficiently collecting admission results from each university using AI and providing them quickly to applicants. Specifically, the data collection unit integrates with each university's system and automatically retrieves admission results via API. Using APIs, the data collection unit can obtain data in real time and provide applicants with the latest information. Periodic polling also allows for timely updates when admission results are updated. The data collection unit centrally manages the collected admission results, enabling applicants to check admission results from multiple universities simultaneously. This eliminates the need for applicants to individually check the admission results of each university. Furthermore, the data collection unit can improve the accuracy of its collection by considering the interrelationships between universities. For example, if a group of universities announce their admission results at the same time, the unit can collect these results simultaneously and provide them to applicants all at once. In addition, the unit can analyze the collected data to understand trends and patterns in admission results. This allows for the provision of more detailed information to applicants, which can be used as a reference when making career choices. By utilizing AI to efficiently and accurately collect admission results and provide them quickly to applicants, the unit improves convenience for them.

[0033] The analysis department uses AI to analyze preference rankings and enrollment intentions based on the pass / fail results collected by the data collection department. Analysis is performed using methods such as survey results and historical data analysis, but is not limited to these examples. For instance, the analysis department analyzes preference rankings and enrollment intentions through communication with applicants. For example, if an applicant is accepted into their first-choice university, they may indicate that they do not intend to attend their second-choice or lower-ranked universities. Furthermore, the analysis department can predict current trends by referencing past data when analyzing preference rankings and enrollment intentions. For example, it may analyze past preference ranking data to predict current trends. The analysis department plays a crucial role in understanding applicants' preference rankings and enrollment intentions by meticulously analyzing the pass / fail results collected using AI. Specifically, the analysis department analyzes applicants' preference rankings and enrollment intentions based on survey results and historical data submitted by applicants. For example, if an applicant is accepted into their first-choice university, they often indicate that they do not intend to attend their second-choice or lower-ranked universities. Based on this information, the analysis department can accurately grasp applicants' preferred rankings and predict their intention to enroll. Furthermore, the analysis department can predict current trends by referring to past data. For example, by analyzing past preferred ranking data and predicting current trends among applicants, it can grasp future preference trends. The analysis department can efficiently analyze the collected data using AI and accurately grasp applicants' preferred rankings and intentions to enroll, enabling it to provide appropriate advice to applicants. In addition, the analysis department can gain a more detailed understanding of preferred rankings and intentions to enroll through communication with applicants. For example, it can conduct surveys with applicants to collect information on preferred rankings and intentions to enroll. Based on this information, the analysis department can analyze applicants' preference trends in detail and provide appropriate advice to applicants. The analysis department can efficiently analyze the collected data using AI and accurately grasp applicants' preferred rankings and intentions to enroll, enabling it to provide appropriate advice to applicants.

[0034] The proposal department uses AI to suggest the optimal number of admitted students based on the preference rankings and enrollment intentions analyzed by the analysis department. The suggestions are based on, but are not limited to, university enrollment capacity and past admission data. For example, the proposal department analyzes applicants' preference rankings and enrollment intentions and suggests the optimal number of admitted students for each university. This allows universities to mitigate the risks of exceeding enrollment limits and subsidy cuts. Furthermore, the proposal department can improve the accuracy of its suggestions by considering the interrelationships between universities. For example, it can analyze the interrelationships between universities and simultaneously suggest the number of admitted students for related universities. The proposal department plays a crucial role in suggesting the optimal number of admitted students for each university based on data analyzed by the analysis department using AI. Specifically, the proposal department suggests the optimal number of admitted students based on university enrollment capacity and past admission data, taking into account applicants' preference rankings and enrollment intentions. This allows universities to mitigate the risks of exceeding enrollment limits and subsidy cuts. Furthermore, the proposal department can improve the accuracy of its suggestions by considering the interrelationships between universities. For example, if a group of universities announce their number of successful applicants at the same time, the proposal department can simultaneously propose the optimal number of successful applicants for these universities, taking into account the trends in applicants' preferences. It is also important for the proposal department to consider the characteristics of each university and past data when making proposals. For example, if a particular university has strengths in a specific field, the proposal department will propose the number of successful applicants considering the number of applicants who aspire to study that field. This allows each university to secure a number of successful applicants that leverages its strengths. By using AI and based on data analyzed by the analysis department, the proposal department can propose the optimal number of successful applicants for each university, thereby mitigating the risks of quota management and subsidy cuts for each university, and providing applicants with an appropriate number of successful applicants.

[0035] The notification unit can provide notifications regarding pass / fail results and the next steps. The notification unit can provide notifications by methods such as email, SMS, and app notifications. For example, the notification unit can notify examinees of their pass / fail results via email. The notification unit can also notify examinees of information regarding the next steps via SMS. For example, the notification unit can provide examinees with detailed information regarding the next steps via app notifications. This allows for the rapid provision of information to examinees by providing notifications regarding pass / fail results and the next steps. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input pass / fail results into an AI model and use an AI model to generate notification content to provide notifications.

[0036] The reception department can analyze an applicant's past application submission history and select the most suitable application method. For example, the reception department can analyze the format of applications previously submitted by the applicant and accept applications in a similar format. It can also analyze the time of day when applications were previously submitted by the applicant and accept applications at a similar time. Furthermore, the reception department can analyze the method of application submission (online, mail, etc.) previously used by the applicant and accept applications using the most suitable method. In this way, by analyzing past application submission history, the reception department can provide applicants with the most suitable application method. Some or all of the above processes in the reception department may be performed using AI or not. For example, the reception department can input past application submission history data into an AI model and use that AI model to select the most suitable application method.

[0037] The application department can filter applications based on the applicant's current learning status and areas of interest. For example, the department can analyze the applicant's learning status and prioritize applications to appropriate universities. It can also analyze the applicant's areas of interest and prioritize applications to relevant universities. Furthermore, the department can comprehensively analyze the applicant's learning status and areas of interest to prioritize applications to the most suitable universities. This allows for priority acceptance of applications to appropriate universities by filtering based on the applicant's learning status and areas of interest. Some or all of the above processing in the application department may be performed using AI or not. For example, the application department can input the applicant's learning status data and areas of interest data into an AI model and use that AI model to perform filtering.

[0038] The application department can prioritize accepting applications that are highly relevant to the applicant, taking into account the applicant's geographical location. For example, the department can prioritize applications to universities close to the applicant's place of residence. It can also prioritize applications to universities within commuting distance of the applicant. Furthermore, the department can prioritize applications to universities that are highly relevant based on the applicant's geographical location. This allows for the priority acceptance of applications to highly relevant universities by considering the applicant's geographical location. Some or all of the above processing in the application department may be performed using AI or not. For example, the application department can input the applicant's geographical location data into an AI model and use that AI model to prioritize applications that are highly relevant to determine the priority order.

[0039] The application department can analyze applicants' social media activity when receiving applications and accept relevant applications. For example, the department can analyze applicants' social media activity and prioritize applications to universities of high interest. It can also analyze applicants' social media posts and prioritize applications to relevant universities. Furthermore, the department can prioritize applications to highly relevant universities based on applicants' social media activity history. This allows for prioritizing applications to universities of high interest by analyzing applicants' social media activity. Some or all of the above processes in the application department may be performed using AI or not. For example, the application department can input applicants' social media activity data into an AI model and use that AI model to determine priorities for accepting relevant applications.

[0040] The distribution department can adjust the level of detail in application forms distributed based on the importance of the universities. For example, the distribution department can distribute application forms containing detailed information to universities of high importance. Conversely, it can also distribute application forms containing concise information to universities of low importance. Furthermore, the distribution department can adjust the level of detail in the application forms distributed according to the importance of the universities. This allows for the provision of appropriate information by adjusting the level of detail in distribution based on the importance of the universities. Some or all of the above processing in the distribution department may be performed using AI or not. For example, the distribution department can input university importance data into an AI model and use that AI model to determine the level of detail in distribution.

[0041] The distribution unit can apply different distribution algorithms based on the university category when distributing applications. For example, the distribution unit can apply a distribution algorithm specialized for science and engineering to science and engineering universities. It can also apply a distribution algorithm specialized for humanities and social science universities. Furthermore, the distribution unit can apply the most suitable distribution algorithm according to the university category. This enables effective distribution by applying the most suitable distribution algorithm according to the university category. Some or all of the above processing in the distribution unit may be performed using AI or not. For example, the distribution unit can input university category data into an AI model and select an algorithm using an AI model that applies distribution algorithms.

[0042] The distribution department can determine the priority of application distribution based on the university's submission deadline. For example, the distribution department can prioritize distribution to universities with earlier submission deadlines. It can also postpone distribution to universities with later submission deadlines. Furthermore, the distribution department can determine the priority of distribution based on the university's submission deadline. This allows for the distribution of applications at the appropriate time by determining the priority of distribution based on the university's submission deadline. Some or all of the above processing in the distribution department may be performed using AI or not. For example, the distribution department can input university submission deadline data into an AI model and use that AI model to determine the priority of distribution.

[0043] The distribution unit can adjust the order of application distribution based on the relevance of the universities. For example, the distribution unit can prioritize distributing applications to universities that are highly ranked by the applicants. It can also postpone distributing applications to universities that are less highly ranked by the applicants. Furthermore, the distribution unit can adjust the order of distribution based on the relevance of the universities. This allows for priority distribution of applications to universities that are important to the applicants. Some or all of the above processing in the distribution unit may be performed using AI or not. For example, the distribution unit can input university relevance data into an AI model and use that AI model to determine the order of distribution.

[0044] The data collection unit can improve the accuracy of data collection based on the interrelationships between universities when collecting pass / fail results. For example, the data collection unit can analyze the interrelationships between universities and simultaneously collect the pass / fail results of related universities. The data collection unit can also determine the priority of data collection by considering the interrelationships between universities. Furthermore, the data collection unit can improve the accuracy of data collection based on the interrelationships between universities. This allows for the efficient collection of pass / fail results of related universities by considering the interrelationships between universities. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input interrelationship data between universities into an AI model and use the AI ​​model to improve the accuracy of data collection to determine the priority of data collection.

[0045] The data collection unit can collect pass / fail results based on university attribute information. For example, the data collection unit can analyze university attribute information and prioritize the collection of relevant pass / fail results. The data collection unit can also determine the order of collection based on university attribute information. Furthermore, the data collection unit can improve the accuracy of collection by considering university attribute information. This allows for the efficient collection of relevant pass / fail results by considering university attribute information. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input university attribute information data into an AI model and use that AI model to determine the order of collection.

[0046] The data collection unit can collect pass / fail results based on the geographical distribution of universities. For example, the data collection unit can analyze the geographical distribution of universities and prioritize the collection of relevant pass / fail results. The data collection unit can also determine the order of collection based on the geographical distribution of universities. Furthermore, the data collection unit can improve the accuracy of collection by considering the geographical distribution of universities. This allows for the efficient collection of relevant pass / fail results by considering the geographical distribution of universities. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the geographical distribution data of universities into an AI model and use that AI model to determine the order of collection.

[0047] The data collection unit can improve the accuracy of data collection by referring to relevant university literature when collecting pass / fail results. For example, the data collection unit can analyze relevant university literature and prioritize the collection of relevant pass / fail results. The data collection unit can also determine the order of collection based on the relevant university literature. Furthermore, the data collection unit can improve the accuracy of collection by referring to relevant university literature. This means that the accuracy of collection can be improved by referring to relevant university literature. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the relevant university literature data into an AI model and use the AI ​​model that determines the order of collection to determine the order.

[0048] The analysis unit can predict current trends based on past data when analyzing preference rankings and enrollment intentions. For example, the analysis unit can analyze past preference ranking data to predict current trends. The analysis unit can also refer to past enrollment intention data to predict current trends. Furthermore, the analysis unit can predict changes in preference rankings and enrollment intentions based on past data. This makes it easier to predict current trends by referring to past data. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input past data into an AI model and use that AI model to predict current trends to predict trends.

[0049] The analysis unit can apply different analysis methods based on the university category when analyzing preference rankings and enrollment intentions. For example, the analysis unit can apply a science-specific analysis method to science universities. It can also apply a humanities-specific analysis method to humanities universities. Furthermore, the analysis unit can apply the most suitable analysis method for each university category. This improves the accuracy of the analysis by applying the most suitable analysis method for each university category. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input university category data into an AI model and select an analysis method using an AI model that applies analysis methods.

[0050] The analysis unit can analyze changes in trends based on the submission period for each university when analyzing preference rankings and enrollment intentions. For example, the analysis unit can analyze the submission period for each university and predict trends in preference rankings and enrollment intentions. The analysis unit can also analyze fluctuations in preference rankings and enrollment intentions based on the submission period. Furthermore, the analysis unit can predict trends in preference rankings and enrollment intentions by taking into account the submission period for each university. This makes it easier to predict fluctuations in preference rankings and enrollment intentions by analyzing changes in trends based on the submission period for each university. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input university submission period data into an AI model and use the AI ​​model, which analyzes changes in trends, to predict changes.

[0051] The analysis unit can analyze trends based on relevant market data for universities when analyzing preference rankings and enrollment intentions. For example, the analysis unit can analyze relevant market data for universities and predict trends in preference rankings and enrollment intentions. The analysis unit can also analyze fluctuations in preference rankings and enrollment intentions based on market data. Furthermore, the analysis unit can predict trends in preference rankings and enrollment intentions by referring to relevant market data for universities. This makes it easier to predict trends in preference rankings and enrollment intentions by referring to relevant market data for universities. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input relevant market data for universities into an AI model and use the AI ​​model to analyze trends and predict trends.

[0052] The proposal department can improve the accuracy of its proposals regarding the number of successful applicants based on the interrelationships between universities. For example, the proposal department can analyze the interrelationships between universities and simultaneously propose the number of successful applicants for the relevant universities. The proposal department can also determine the priority of proposals by considering the interrelationships between universities. Furthermore, the proposal department can improve the accuracy of proposals based on the interrelationships between universities. This allows for the efficient proposal of the number of successful applicants for relevant universities by considering the interrelationships between universities. Some or all of the above processing in the proposal department may be performed using AI or not. For example, the proposal department can input interrelationship data between universities into an AI model and use that AI model to improve the accuracy of proposals and determine the priority of proposals.

[0053] The proposal department can make proposals based on university attribute information when proposing the number of successful applicants. For example, the proposal department can analyze university attribute information and prioritize proposing the number of successful applicants relevant to that university. The proposal department can also determine the order of proposals based on university attribute information. Furthermore, the proposal department can improve the accuracy of proposals by considering university attribute information. This allows for efficient proposal of relevant number of successful applicants by considering university attribute information. Some or all of the above processing in the proposal department may be performed using AI or not. For example, the proposal department can input university attribute information data into an AI model and use that AI model to determine the order of proposals.

[0054] The proposal unit can make proposals for the number of successful applicants based on the geographical distribution of universities. For example, the proposal unit can analyze the geographical distribution of universities and prioritize proposing the relevant number of successful applicants. The proposal unit can also determine the order of proposals based on the geographical distribution of universities. Furthermore, the proposal unit can improve the accuracy of its proposals by considering the geographical distribution of universities. This allows for the efficient proposal of relevant number of successful applicants by considering the geographical distribution of universities. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can input the geographical distribution data of universities into an AI model and use that AI model to determine the order of proposals.

[0055] The proposal department can improve the accuracy of its proposals when suggesting the number of successful candidates by referring to relevant university literature. For example, the proposal department can analyze relevant university literature and prioritize suggesting the number of successful candidates that are relevant. The proposal department can also determine the order of proposals based on relevant university literature. Furthermore, the proposal department can improve the accuracy of its proposals by referring to relevant university literature. In this way, the accuracy of proposals can be improved by referring to relevant university literature. Some or all of the above processing in the proposal department may be performed using AI or not. For example, the proposal department can input university literature data into an AI model and use that AI model to determine the order of proposals.

[0056] The notification unit can select an appropriate notification method based on the examinee's past notification history when sending a notification. For example, the notification unit can analyze the examinee's past notification history and select the optimal notification method. The notification unit can also prioritize notification methods that the examinee has previously preferred (email, SMS, etc.). Furthermore, the notification unit can select the optimal notification timing based on the examinee's past notification history. This allows the optimal notification method to be selected by referring to the examinee's past notification history. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input past notification history data into an AI model and use that AI model to determine the notification method.

[0057] The notification unit can select the optimal notification method when sending a notification, taking into account the examinee's device information. For example, if the examinee is using a smartphone, the notification unit will prioritize push notifications. It can also prioritize email notifications if the examinee is using a tablet. Furthermore, the notification unit can select the optimal notification method based on the examinee's device information. This allows the system to select the most suitable notification method by considering the examinee's device information. Some or all of the above processing in the notification unit may be performed using AI, or without AI. For example, the notification unit can input the examinee's device information data into an AI model and use that AI model to determine the notification method.

[0058] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0059] The application department can analyze an applicant's past learning history and suggest the most suitable application submission method. For example, if an applicant has previously submitted an application online, online submission will be prioritized. Similarly, if an applicant has previously submitted an application by mail, mail submission can be suggested. Furthermore, the application department can schedule application submissions for specific time slots based on the applicant's learning history. This allows the department to provide the most optimal application submission method by considering the applicant's past learning history.

[0060] The distribution department can analyze applicants' learning styles and propose the most suitable application distribution method. For example, if an applicant has a visual learning style, the application can include visual content. If an applicant has an auditory learning style, an application with audio guidance can be distributed. Furthermore, if an applicant has a practical learning style, an interactive application can be distributed. This allows the department to provide the most suitable application distribution method tailored to each applicant's learning style.

[0061] The data collection unit can monitor the study progress of test-takers in real time and adjust the timing of collecting pass / fail results. For example, if a test-taker is behind in their study progress, the collection of pass / fail results can be delayed. Conversely, if a test-taker is progressing well, the pass / fail results can be collected at the normal time. Furthermore, if a test-taker is progressing quickly, the pass / fail results can be collected earlier. This allows for the collection of pass / fail results at a timing that matches the test-taker's study progress.

[0062] The analysis unit can analyze applicants' learning patterns and improve the accuracy of its analysis of preferred university rankings and enrollment intentions. For example, it can analyze what kind of learning patterns applicants have had in the past and predict their current preferred university rankings and enrollment intentions. It can also predict future changes in preferred university rankings and enrollment intentions based on applicants' learning patterns. Furthermore, it can propose optimal preferred university rankings and enrollment intentions, taking into account applicants' learning patterns. This enables highly accurate analysis based on applicants' learning patterns.

[0063] The proposal department can suggest the optimal number of successful applicants based on the learning history of each applicant. For example, it can analyze the past learning history of each applicant and suggest the optimal number of successful applicants for each university. It can also predict future learning motivation based on the applicant's learning history and adjust the number of successful applicants accordingly. Furthermore, it can suggest a number of successful applicants that is appropriate for each university's capacity, taking into account the applicant's learning history. This makes it possible to suggest the optimal number of successful applicants based on the applicant's learning history.

[0064] The following briefly describes the processing flow for example form 1.

[0065] Step 1: The reception desk accepts applicants' applications at a temporary counter. These applications include handwritten and digital forms. The reception desk digitizes handwritten applications using scanning technology and accepts them. It can also directly accept digitally submitted applications. Furthermore, it can read printed applications using OCR technology. Step 2: The distribution department uses AI to automatically distribute the applications received by the reception department to each university. Distribution is done via methods such as email and a dedicated system. The distribution department analyzes the applicant's application information and distributes it to each university in the appropriate format. For example, it can distribute it to University A in PDF format and to University B in Excel format. The distribution department can also adjust the level of detail in the distribution based on the importance of each university. Step 3: The collection unit uses AI to collect acceptance / rejection results from each university in real time based on the applications distributed by the distribution unit. Collection is carried out using methods such as data collection via API and periodic polling. The collection unit automatically collects and centrally manages acceptance / rejection results from each university. This allows applicants to check acceptance / rejection results from multiple universities at once. The collection unit can also improve the accuracy of collection by considering the interrelationships between universities. Step 4: The analysis unit uses AI to analyze preference rankings and enrollment intentions based on the pass / fail results collected by the data collection unit. The analysis is performed using methods such as survey results and historical data analysis. The analysis unit analyzes preference rankings and enrollment intentions through communication with applicants. For example, if an applicant is accepted into their first-choice university, they may indicate that they do not intend to attend their second-choice or lower-ranked universities. The analysis unit can also predict current trends by referring to past data. Step 5: The proposal department uses AI to suggest the optimal number of admitted students based on the preference rankings and enrollment intentions analyzed by the analysis department. The suggestions are based on the university's enrollment capacity, past admission data, etc. The proposal department analyzes applicants' preference rankings and enrollment intentions and proposes the optimal number of admitted students for each university. This allows each university to reduce the risk of exceeding its enrollment capacity or having its subsidies cut. The proposal department can also improve the accuracy of its suggestions by considering the interrelationships between universities.

[0066] (Example of form 2) The system according to an embodiment of the present invention is a system that receives applicants' applications at a central counter, an AI agent automatically distributes them to each university, collects acceptance / rejection results in real time, and allows each university to adjust the number of accepted students. This system receives applicants' applications at a central counter, an AI agent automatically distributes the received applications to each university, collects acceptance / rejection results from each university in real time, and allows each university to adjust the number of accepted students. The AI ​​agent analyzes the applicants' preference rankings and intentions to enroll through communication and proposes the optimal number of accepted students. First, applicants' applications are received at a central counter. At this time, applicants can submit applications to multiple universities at once. For example, if an applicant submits applications to University A, University B, and University C, they can be received at the central counter all at once. Next, the AI ​​agent automatically distributes the received applications to each university. The AI ​​agent analyzes the applicants' application information and distributes it to each university in the appropriate format. For example, it can distribute it to University A in PDF format and to University B in Excel format. Furthermore, the AI ​​agent collects acceptance / rejection results from each university in real time. The AI ​​agent automatically collects and centrally manages acceptance / rejection results from each university. This allows applicants to check acceptance / rejection results from multiple universities at once. The AI ​​agent analyzes applicants' preference rankings and enrollment intentions through communication. For example, if an applicant is accepted to their first-choice university, they can indicate their intention not to enroll in their second-choice or lower-choice universities. This allows each university to adjust the number of accepted students. Finally, the AI ​​agent proposes the optimal number of accepted students. The AI ​​agent analyzes applicants' preference rankings and enrollment intentions and proposes the optimal number of accepted students for each university. This reduces the risk of exceeding enrollment quotas and cuts to subsidies for each university. As a result, the system can efficiently receive, distribute, collect, analyze, and propose applicant applications.

[0067] The system according to this embodiment comprises a reception unit, a distribution unit, a collection unit, an analysis unit, and a proposal unit. The reception unit receives applicants' applications at a temporary counter. Applicants' applications include, but are not limited to, handwritten applications and digital applications. The reception unit digitizes and accepts handwritten applications using scanning technology. The reception unit can also directly accept applications submitted in digital format. Furthermore, the reception unit can read printed applications using OCR technology. For example, the reception unit scans handwritten applications with a high-resolution scanner and converts them into text information using OCR technology. Digital applications can be directly accepted if submitted in a specific file format. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The distribution unit uses AI to automatically distribute the applications received by the reception unit to each university. Distribution is carried out by, but is not limited to, email, distribution through a dedicated system, etc. For example, the distribution department analyzes applicants' application information and distributes it to each university in the appropriate format. For instance, it can distribute it to University A in PDF format and to University B in Excel format. The distribution department can also adjust the level of detail in the distribution based on the importance of each university. For example, it can distribute application forms with detailed information to highly important universities and application forms with concise information to less important universities. The collection department uses AI to collect acceptance / rejection results from each university in real time based on the application forms distributed by the distribution department. Collection is carried out by methods such as data collection using APIs or periodic polling, but is not limited to these examples. For example, the collection department automatically collects and centrally manages acceptance / rejection results from each university. This allows applicants to check acceptance / rejection results from multiple universities at once. The collection department can also improve the accuracy of collection by considering the interrelationships between universities. For example, it can analyze the interrelationships between universities and collect acceptance / rejection results from related universities simultaneously. The analysis department uses AI to analyze preference rankings and enrollment intentions based on the acceptance / rejection results collected by the collection department. Analysis may be performed using methods such as survey results or historical data analysis, but is not limited to these examples.For example, the analysis department analyzes applicants' preference rankings and enrollment intentions through communication with them. For instance, if an applicant is accepted to their first-choice university, they may indicate that they do not intend to attend their second-choice or lower-ranked universities. The analysis department can also predict current trends by referring to past data when analyzing preference rankings and enrollment intentions. For example, it can analyze past preference ranking data to predict current trends. The proposal department uses AI to propose the optimal number of accepted students based on the preference rankings and enrollment intentions analyzed by the analysis department. Proposals are based on, but are not limited to, university capacity and past acceptance data. For example, the proposal department analyzes applicants' preference rankings and enrollment intentions and proposes the optimal number of accepted students for each university. This allows universities to mitigate the risks of exceeding their enrollment capacity or having subsidy cuts. The proposal department can also improve the accuracy of its proposals by considering the interrelationships between universities. For example, it can analyze the interrelationships between universities and simultaneously propose the number of accepted students for related universities. This enables the system according to the embodiment to efficiently receive, distribute, collect, analyze, and propose information based on applicants' applications.

[0068] The reception desk accepts applicants' applications at a temporary counter. These applications may include, but are not limited to, handwritten or digital forms. The reception desk may, for example, digitize handwritten applications using scanning technology and accept them. It can also directly accept digitally submitted applications. Furthermore, the reception desk can read printed applications using OCR technology. For example, the reception desk may scan handwritten applications with a high-resolution scanner and convert them into text information using OCR technology. Digital applications can be directly accepted if submitted in a specific file format. OCR technology accurately recognizes printed characters and converts them into digital text. The reception desk uses a combination of the latest scanning and OCR technologies to efficiently process the diverse formats of applications submitted by applicants. Handwritten applications are captured as high-resolution images using a scanner and then converted into text information using OCR technology. This process allows for the accurate conversion of both handwritten and printed characters into digital data. Digital applications are often submitted in common file formats such as PDF, Word, and Excel, and the application department directly receives these files and stores them in its database. Furthermore, the application department can provide a web portal that allows applicants to submit their applications online. This web portal allows applicants to enter their information and upload necessary documents. The application department receives and processes this data in real time. This allows applicants to easily submit their applications from home, and the application department can manage the data efficiently. Additionally, the application department has a function to review the submitted applications and notify applicants if there are any deficiencies. For example, if necessary documents are missing or there are errors in the information provided, the application department can automatically notify the applicant and prompt them to make corrections. This improves the efficiency of the application department's work, as applicants can review and correct their submitted applications.

[0069] The distribution department uses AI to automatically distribute application forms received by the reception department to each university. Distribution is carried out by methods such as email or through a dedicated system, but is not limited to these examples. For example, the distribution department analyzes the applicant's application information and distributes it to each university in the appropriate format. For example, it can distribute it to University A in PDF format and to University B in Excel format. The distribution department can also adjust the level of detail in the distribution based on the importance of each university. For example, it can distribute application forms with detailed information to high-priority universities and application forms with concise information to low-priority universities. Because the distribution department uses AI to distribute applicants' applications to each university in the most optimal format, it can be customized to meet the requirements of each university. For example, one university may prefer PDF application forms, while another may prefer Excel data. The distribution department understands these requirements in advance and converts applicants' applications to the appropriate format before distribution. Furthermore, the distribution department can consider the importance of each university and adjust the level of detail in the distribution. For example, the distribution department will send application forms containing detailed information about applicants to universities of high importance, and to universities of lower importance, it will send concise application forms containing only basic information. In this way, the distribution department will achieve flexible distribution tailored to the needs of each university. It is also important for the distribution department to take security measures during distribution. For example, encryption technology will be used to protect data so that the contents of application forms are not leaked to third parties. Furthermore, the distribution department will record the distribution history so that it can be reviewed later. This will enable a quick response even if problems occur during distribution. The distribution department will use AI to efficiently distribute applicants' application forms and achieve flexible responses tailored to the needs of each university.

[0070] The data collection unit uses AI to collect admission results from each university in real time based on applications distributed by the distribution unit. Data collection is carried out using methods such as API-based data collection and periodic polling, but is not limited to these examples. For instance, the data collection unit automatically collects and centrally manages admission results from each university. This allows applicants to check admission results from multiple universities simultaneously. The data collection unit can also improve the accuracy of data collection by considering the interrelationships between universities. For example, it can analyze interrelationships between universities and collect admission results from related universities simultaneously. The data collection unit plays a crucial role in efficiently collecting admission results from each university using AI and providing them quickly to applicants. Specifically, the data collection unit integrates with each university's system and automatically retrieves admission results via API. Using APIs, the data collection unit can obtain data in real time and provide applicants with the latest information. Periodic polling also allows for timely updates when admission results are updated. The data collection unit centrally manages the collected admission results, enabling applicants to check admission results from multiple universities simultaneously. This eliminates the need for applicants to individually check the admission results of each university. Furthermore, the data collection unit can improve the accuracy of its collection by considering the interrelationships between universities. For example, if a group of universities announce their admission results at the same time, the unit can collect these results simultaneously and provide them to applicants all at once. In addition, the unit can analyze the collected data to understand trends and patterns in admission results. This allows for the provision of more detailed information to applicants, which can be used as a reference when making career choices. By utilizing AI to efficiently and accurately collect admission results and provide them quickly to applicants, the unit improves convenience for them.

[0071] The analysis department uses AI to analyze preference rankings and enrollment intentions based on the pass / fail results collected by the data collection department. Analysis is performed using methods such as survey results and historical data analysis, but is not limited to these examples. For instance, the analysis department analyzes preference rankings and enrollment intentions through communication with applicants. For example, if an applicant is accepted into their first-choice university, they may indicate that they do not intend to attend their second-choice or lower-ranked universities. Furthermore, the analysis department can predict current trends by referencing past data when analyzing preference rankings and enrollment intentions. For example, it may analyze past preference ranking data to predict current trends. The analysis department plays a crucial role in understanding applicants' preference rankings and enrollment intentions by meticulously analyzing the pass / fail results collected using AI. Specifically, the analysis department analyzes applicants' preference rankings and enrollment intentions based on survey results and historical data submitted by applicants. For example, if an applicant is accepted into their first-choice university, they often indicate that they do not intend to attend their second-choice or lower-ranked universities. Based on this information, the analysis department can accurately grasp applicants' preferred rankings and predict their intention to enroll. Furthermore, the analysis department can predict current trends by referring to past data. For example, by analyzing past preferred ranking data and predicting current trends among applicants, it can grasp future preference trends. The analysis department can efficiently analyze the collected data using AI and accurately grasp applicants' preferred rankings and intentions to enroll, enabling it to provide appropriate advice to applicants. In addition, the analysis department can gain a more detailed understanding of preferred rankings and intentions to enroll through communication with applicants. For example, it can conduct surveys with applicants to collect information on preferred rankings and intentions to enroll. Based on this information, the analysis department can analyze applicants' preference trends in detail and provide appropriate advice to applicants. The analysis department can efficiently analyze the collected data using AI and accurately grasp applicants' preferred rankings and intentions to enroll, enabling it to provide appropriate advice to applicants.

[0072] The proposal department uses AI to suggest the optimal number of admitted students based on the preference rankings and enrollment intentions analyzed by the analysis department. The suggestions are based on, but are not limited to, university enrollment capacity and past admission data. For example, the proposal department analyzes applicants' preference rankings and enrollment intentions and suggests the optimal number of admitted students for each university. This allows universities to mitigate the risks of exceeding enrollment limits and subsidy cuts. Furthermore, the proposal department can improve the accuracy of its suggestions by considering the interrelationships between universities. For example, it can analyze the interrelationships between universities and simultaneously suggest the number of admitted students for related universities. The proposal department plays a crucial role in suggesting the optimal number of admitted students for each university based on data analyzed by the analysis department using AI. Specifically, the proposal department suggests the optimal number of admitted students based on university enrollment capacity and past admission data, taking into account applicants' preference rankings and enrollment intentions. This allows universities to mitigate the risks of exceeding enrollment limits and subsidy cuts. Furthermore, the proposal department can improve the accuracy of its suggestions by considering the interrelationships between universities. For example, if a group of universities announce their number of successful applicants at the same time, the proposal department can simultaneously propose the optimal number of successful applicants for these universities, taking into account the trends in applicants' preferences. It is also important for the proposal department to consider the characteristics of each university and past data when making proposals. For example, if a particular university has strengths in a specific field, the proposal department will propose the number of successful applicants considering the number of applicants who aspire to study that field. This allows each university to secure a number of successful applicants that leverages its strengths. By using AI and based on data analyzed by the analysis department, the proposal department can propose the optimal number of successful applicants for each university, thereby mitigating the risks of quota management and subsidy cuts for each university, and providing applicants with an appropriate number of successful applicants.

[0073] The notification unit can provide notifications regarding pass / fail results and the next steps. The notification unit can provide notifications by methods such as email, SMS, and app notifications. For example, the notification unit can notify examinees of their pass / fail results via email. The notification unit can also notify examinees of information regarding the next steps via SMS. For example, the notification unit can provide examinees with detailed information regarding the next steps via app notifications. This allows for the rapid provision of information to examinees by providing notifications regarding pass / fail results and the next steps. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input pass / fail results into an AI model and use an AI model to generate notification content to provide notifications.

[0074] The reception desk can estimate the emotions of applicants and adjust the timing of application submission based on the estimated emotions. For example, if an applicant is nervous, the reception desk can submit the application at a time when they can relax. If an applicant is anxious, the reception desk can submit the application quickly. Furthermore, if an applicant is calm, the reception desk can submit the application at the normal time. This allows for adjustment of the application submission timing according to the applicant's emotions, thereby reducing their stress. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the applicant's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0075] The reception department can analyze an applicant's past application submission history and select the most suitable application method. For example, the reception department can analyze the format of applications previously submitted by the applicant and accept applications in a similar format. It can also analyze the time of day when applications were previously submitted by the applicant and accept applications at a similar time. Furthermore, the reception department can analyze the method of application submission (online, mail, etc.) previously used by the applicant and accept applications using the most suitable method. In this way, by analyzing past application submission history, the reception department can provide applicants with the most suitable application method. Some or all of the above processes in the reception department may be performed using AI or not. For example, the reception department can input past application submission history data into an AI model and use that AI model to select the most suitable application method.

[0076] The application department can filter applications based on the applicant's current learning status and areas of interest. For example, the department can analyze the applicant's learning status and prioritize applications to appropriate universities. It can also analyze the applicant's areas of interest and prioritize applications to relevant universities. Furthermore, the department can comprehensively analyze the applicant's learning status and areas of interest to prioritize applications to the most suitable universities. This allows for priority acceptance of applications to appropriate universities by filtering based on the applicant's learning status and areas of interest. Some or all of the above processing in the application department may be performed using AI or not. For example, the application department can input the applicant's learning status data and areas of interest data into an AI model and use that AI model to perform filtering.

[0077] The reception desk can estimate the emotions of applicants and determine the priority of applications to be received based on those estimated emotions. For example, if an applicant is nervous, the reception desk will prioritize receiving their application. If an applicant is relaxed, the reception desk can also process applications in the normal order. Furthermore, if an applicant is anxious, the reception desk can process their application quickly. This reduces stress on applicants by prioritizing applications according to their emotions. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input applicant emotion data into an AI model and use that AI model to determine the priority of applications.

[0078] The application department can prioritize accepting applications that are highly relevant to the applicant, taking into account the applicant's geographical location. For example, the department can prioritize applications to universities close to the applicant's place of residence. It can also prioritize applications to universities within commuting distance of the applicant. Furthermore, the department can prioritize applications to universities that are highly relevant based on the applicant's geographical location. This allows for the priority acceptance of applications to highly relevant universities by considering the applicant's geographical location. Some or all of the above processing in the application department may be performed using AI or not. For example, the application department can input the applicant's geographical location data into an AI model and use that AI model to prioritize applications that are highly relevant to determine the priority order.

[0079] The application department can analyze applicants' social media activity when receiving applications and accept relevant applications. For example, the department can analyze applicants' social media activity and prioritize applications to universities of high interest. It can also analyze applicants' social media posts and prioritize applications to relevant universities. Furthermore, the department can prioritize applications to highly relevant universities based on applicants' social media activity history. This allows for prioritizing applications to universities of high interest by analyzing applicants' social media activity. Some or all of the above processes in the application department may be performed using AI or not. For example, the application department can input applicants' social media activity data into an AI model and use that AI model to determine priorities for accepting relevant applications.

[0080] The distribution unit can estimate the emotions of applicants and adjust the presentation of the application based on the estimated emotions. For example, if an applicant is nervous, the distribution unit will deliver the application in a simple and easy-to-understand manner. If an applicant is relaxed, the distribution unit can deliver the application in a manner that includes detailed information. Furthermore, if an applicant is anxious, the distribution unit can deliver the application in a manner that can be quickly understood. By adjusting the presentation of the application according to the emotions of the applicant, it becomes possible to deliver the application in a way that is easy for the applicant to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the distribution unit may be performed using AI or not. For example, the distribution unit can input applicant emotion data into a generative AI and have the generative AI execute the presentation of the delivery.

[0081] The distribution department can adjust the level of detail in application forms distributed based on the importance of the universities. For example, the distribution department can distribute application forms containing detailed information to universities of high importance. Conversely, it can also distribute application forms containing concise information to universities of low importance. Furthermore, the distribution department can adjust the level of detail in the application forms distributed according to the importance of the universities. This allows for the provision of appropriate information by adjusting the level of detail in distribution based on the importance of the universities. Some or all of the above processing in the distribution department may be performed using AI or not. For example, the distribution department can input university importance data into an AI model and use that AI model to determine the level of detail in distribution.

[0082] The distribution unit can apply different distribution algorithms based on the university category when distributing applications. For example, the distribution unit can apply a distribution algorithm specialized for science and engineering to science and engineering universities. It can also apply a distribution algorithm specialized for humanities and social science universities. Furthermore, the distribution unit can apply the most suitable distribution algorithm according to the university category. This enables effective distribution by applying the most suitable distribution algorithm according to the university category. Some or all of the above processing in the distribution unit may be performed using AI or not. For example, the distribution unit can input university category data into an AI model and select an algorithm using an AI model that applies distribution algorithms.

[0083] The delivery unit can estimate the emotions of test-takers and adjust the length of the delivery based on the estimated emotions. For example, if a test-taker is nervous, the delivery unit can deliver a short, concise delivery. If a test-taker is relaxed, the delivery unit can deliver a longer delivery containing more detailed information. Furthermore, if a test-taker is anxious, the delivery unit can deliver a short, easily understandable delivery. By adjusting the length of the delivery according to the test-taker's emotions, the delivery unit can provide the appropriate amount of information to the test-taker. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can input test-taker emotion data into a generative AI and have the generative AI determine the length of the delivery.

[0084] The distribution department can determine the priority of application distribution based on the university's submission deadline. For example, the distribution department can prioritize distribution to universities with earlier submission deadlines. It can also postpone distribution to universities with later submission deadlines. Furthermore, the distribution department can determine the priority of distribution based on the university's submission deadline. This allows for the distribution of applications at the appropriate time by determining the priority of distribution based on the university's submission deadline. Some or all of the above processing in the distribution department may be performed using AI or not. For example, the distribution department can input university submission deadline data into an AI model and use that AI model to determine the priority of distribution.

[0085] The distribution unit can adjust the order of application distribution based on the relevance of the universities. For example, the distribution unit can prioritize distributing applications to universities that are highly ranked by the applicants. It can also postpone distributing applications to universities that are less highly ranked by the applicants. Furthermore, the distribution unit can adjust the order of distribution based on the relevance of the universities. This allows for priority distribution of applications to universities that are important to the applicants. Some or all of the above processing in the distribution unit may be performed using AI or not. For example, the distribution unit can input university relevance data into an AI model and use that AI model to determine the order of distribution.

[0086] The data collection unit can estimate the emotions of test-takers and adjust the criteria for collecting pass / fail results based on the estimated emotions. For example, if a test-taker is nervous, the data collection unit will quickly collect the pass / fail results. If a test-taker is relaxed, the data collection unit can also collect the pass / fail results using normal criteria. Furthermore, if a test-taker is anxious, the data collection unit can prioritize collecting the pass / fail results. This allows the system to collect pass / fail results at an appropriate time for the test-taker by adjusting the criteria for collecting pass / fail results according to their emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input test-taker emotion data into a generative AI and have the generative AI execute the criteria for collecting pass / fail results.

[0087] The data collection unit can improve the accuracy of data collection based on the interrelationships between universities when collecting pass / fail results. For example, the data collection unit can analyze the interrelationships between universities and simultaneously collect the pass / fail results of related universities. The data collection unit can also determine the priority of data collection by considering the interrelationships between universities. Furthermore, the data collection unit can improve the accuracy of data collection based on the interrelationships between universities. This allows for the efficient collection of pass / fail results of related universities by considering the interrelationships between universities. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input interrelationship data between universities into an AI model and use the AI ​​model to improve the accuracy of data collection to determine the priority of data collection.

[0088] The data collection unit can collect pass / fail results based on university attribute information. For example, the data collection unit can analyze university attribute information and prioritize the collection of relevant pass / fail results. The data collection unit can also determine the order of collection based on university attribute information. Furthermore, the data collection unit can improve the accuracy of collection by considering university attribute information. This allows for the efficient collection of relevant pass / fail results by considering university attribute information. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input university attribute information data into an AI model and use that AI model to determine the order of collection.

[0089] The data collection unit can estimate the emotions of test-takers and adjust the display order of the collected results based on the estimated emotions. For example, if a test-taker is nervous, the data collection unit can prioritize displaying important pass / fail results. If a test-taker is relaxed, the data collection unit can also display the pass / fail results in the normal order. Furthermore, if a test-taker is anxious, the data collection unit can display the pass / fail results in an order that allows for quick review. In this way, by adjusting the display order of the collected results according to the emotions of the test-taker, information important to the test-taker can be prioritized. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the test-taker's emotion data into a generative AI and have the generative AI execute the display order of the collected results.

[0090] The data collection unit can collect pass / fail results based on the geographical distribution of universities. For example, the data collection unit can analyze the geographical distribution of universities and prioritize the collection of relevant pass / fail results. The data collection unit can also determine the order of collection based on the geographical distribution of universities. Furthermore, the data collection unit can improve the accuracy of collection by considering the geographical distribution of universities. This allows for the efficient collection of relevant pass / fail results by considering the geographical distribution of universities. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the geographical distribution data of universities into an AI model and use that AI model to determine the order of collection.

[0091] The data collection unit can improve the accuracy of data collection by referring to relevant university literature when collecting pass / fail results. For example, the data collection unit can analyze relevant university literature and prioritize the collection of relevant pass / fail results. The data collection unit can also determine the order of collection based on the relevant university literature. Furthermore, the data collection unit can improve the accuracy of collection by referring to relevant university literature. This means that the accuracy of collection can be improved by referring to relevant university literature. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the relevant university literature data into an AI model and use the AI ​​model that determines the order of collection to determine the order.

[0092] The analysis unit can estimate the emotions of applicants and adjust the display method for their preference ranking and intention to enroll based on the estimated emotions. For example, if an applicant is nervous, the analysis unit can provide a simple and highly visible display method. If an applicant is relaxed, the analysis unit can also provide a display method that includes detailed information. Furthermore, if an applicant is anxious, the analysis unit can provide a display method that can be quickly understood. By adjusting the display method for preference ranking and intention to enroll according to the applicant's emotions, it becomes possible to provide a display that is easy for applicants to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the analysis unit may be performed using AI or not using AI. For example, the analysis unit can input applicant emotion data into a generative AI and have the generative AI execute the display method.

[0093] The analysis unit can predict current trends based on past data when analyzing preference rankings and enrollment intentions. For example, the analysis unit can analyze past preference ranking data to predict current trends. The analysis unit can also refer to past enrollment intention data to predict current trends. Furthermore, the analysis unit can predict changes in preference rankings and enrollment intentions based on past data. This makes it easier to predict current trends by referring to past data. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input past data into an AI model and use that AI model to predict current trends to predict trends.

[0094] The analysis unit can apply different analysis methods based on the university category when analyzing preference rankings and enrollment intentions. For example, the analysis unit can apply a science-specific analysis method to science universities. It can also apply a humanities-specific analysis method to humanities universities. Furthermore, the analysis unit can apply the most suitable analysis method for each university category. This improves the accuracy of the analysis by applying the most suitable analysis method for each university category. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input university category data into an AI model and select an analysis method using an AI model that applies analysis methods.

[0095] The analysis unit can estimate the emotions of applicants and adjust the importance of their preferred rankings and intentions to enroll based on those estimated emotions. For example, if an applicant is nervous, the analysis unit will prioritize displaying important preferred rankings and intentions to enroll. If an applicant is relaxed, the analysis unit can also display preferred rankings and intentions to enroll in the normal order. Furthermore, if an applicant is anxious, the analysis unit can display preferred rankings and intentions to enroll in an order that allows for quick review. This allows the system to prioritize displaying information important to the applicant by adjusting the importance of preferred rankings and intentions to enroll according to their emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input applicant emotion data into a generative AI and determine importance using an AI model that adjusts importance.

[0096] The analysis unit can analyze changes in trends based on the submission period for each university when analyzing preference rankings and enrollment intentions. For example, the analysis unit can analyze the submission period for each university and predict trends in preference rankings and enrollment intentions. The analysis unit can also analyze fluctuations in preference rankings and enrollment intentions based on the submission period. Furthermore, the analysis unit can predict trends in preference rankings and enrollment intentions by taking into account the submission period for each university. This makes it easier to predict fluctuations in preference rankings and enrollment intentions by analyzing changes in trends based on the submission period for each university. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input university submission period data into an AI model and use the AI ​​model, which analyzes changes in trends, to predict changes.

[0097] The analysis unit can analyze trends based on relevant market data for universities when analyzing preference rankings and enrollment intentions. For example, the analysis unit can analyze relevant market data for universities and predict trends in preference rankings and enrollment intentions. The analysis unit can also analyze fluctuations in preference rankings and enrollment intentions based on market data. Furthermore, the analysis unit can predict trends in preference rankings and enrollment intentions by referring to relevant market data for universities. This makes it easier to predict trends in preference rankings and enrollment intentions by referring to relevant market data for universities. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input relevant market data for universities into an AI model and use the AI ​​model to analyze trends and predict trends.

[0098] The suggestion unit can estimate the emotions of test-takers and determine the priority of the number of successful candidates to suggest based on the estimated emotions. For example, if a test-taker is nervous, the suggestion unit will prioritize suggesting important numbers of successful candidates. If a test-taker is relaxed, the suggestion unit can also suggest numbers of successful candidates in the usual order. Furthermore, if a test-taker is anxious, the suggestion unit can suggest numbers of successful candidates in an order that can be quickly reviewed. In this way, by prioritizing the number of successful candidates according to the emotions of the test-taker, information that is important to the test-taker can be displayed preferentially. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input test-taker emotion data into a generative AI and determine the priority using an AI model that determines the priority.

[0099] The proposal department can improve the accuracy of its proposals regarding the number of successful applicants based on the interrelationships between universities. For example, the proposal department can analyze the interrelationships between universities and simultaneously propose the number of successful applicants for the relevant universities. The proposal department can also determine the priority of proposals by considering the interrelationships between universities. Furthermore, the proposal department can improve the accuracy of proposals based on the interrelationships between universities. This allows for the efficient proposal of the number of successful applicants for relevant universities by considering the interrelationships between universities. Some or all of the above processing in the proposal department may be performed using AI or not. For example, the proposal department can input interrelationship data between universities into an AI model and use that AI model to improve the accuracy of proposals and determine the priority of proposals.

[0100] The proposal department can make proposals based on university attribute information when proposing the number of successful applicants. For example, the proposal department can analyze university attribute information and prioritize proposing the number of successful applicants relevant to that university. The proposal department can also determine the order of proposals based on university attribute information. Furthermore, the proposal department can improve the accuracy of proposals by considering university attribute information. This allows for efficient proposal of relevant number of successful applicants by considering university attribute information. Some or all of the above processing in the proposal department may be performed using AI or not. For example, the proposal department can input university attribute information data into an AI model and use that AI model to determine the order of proposals.

[0101] The proposal unit can estimate the emotions of test-takers and adjust the display method for the number of successful candidates based on the estimated emotions. For example, if a test-taker is nervous, the proposal unit can provide a simple and highly visible display method. If a test-taker is relaxed, the proposal unit can also provide a display method that includes detailed information. Furthermore, if a test-taker is anxious, the proposal unit can provide a display method that can be quickly understood. By adjusting the display method for the number of successful candidates according to the emotions of the test-takers, it becomes possible to provide a display that is easy for test-takers to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the proposal unit may be performed using AI or not using AI. For example, the proposal unit can input test-taker emotion data into a generative AI and have the generative AI execute the display method.

[0102] The proposal unit can make proposals for the number of successful applicants based on the geographical distribution of universities. For example, the proposal unit can analyze the geographical distribution of universities and prioritize proposing the relevant number of successful applicants. The proposal unit can also determine the order of proposals based on the geographical distribution of universities. Furthermore, the proposal unit can improve the accuracy of its proposals by considering the geographical distribution of universities. This allows for the efficient proposal of relevant number of successful applicants by considering the geographical distribution of universities. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can input the geographical distribution data of universities into an AI model and use that AI model to determine the order of proposals.

[0103] The proposal department can improve the accuracy of its proposals when suggesting the number of successful candidates by referring to relevant university literature. For example, the proposal department can analyze relevant university literature and prioritize suggesting the number of successful candidates that are relevant. The proposal department can also determine the order of proposals based on relevant university literature. Furthermore, the proposal department can improve the accuracy of its proposals by referring to relevant university literature. In this way, the accuracy of proposals can be improved by referring to relevant university literature. Some or all of the above processing in the proposal department may be performed using AI or not. For example, the proposal department can input university literature data into an AI model and use that AI model to determine the order of proposals.

[0104] The notification unit can estimate the emotions of test-takers and adjust the timing of notifications based on the estimated emotions. For example, if a test-taker is nervous, the notification unit will send a notification during a time when they can relax. If the test-taker is relaxed, the notification unit can also send a notification at the usual time. Furthermore, if the test-taker is anxious, the notification unit can send a notification quickly. This allows the notification to be sent at an appropriate time for the test-taker by adjusting the timing according to their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input the test-taker's emotion data into a generative AI and have the generative AI determine the timing of the notification.

[0105] The notification unit can select an appropriate notification method based on the examinee's past notification history when sending a notification. For example, the notification unit can analyze the examinee's past notification history and select the optimal notification method. The notification unit can also prioritize notification methods that the examinee has previously preferred (email, SMS, etc.). Furthermore, the notification unit can select the optimal notification timing based on the examinee's past notification history. This allows the optimal notification method to be selected by referring to the examinee's past notification history. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input past notification history data into an AI model and use that AI model to determine the notification method.

[0106] The notification unit can estimate the examinee's emotions and determine the priority of notifications based on the estimated emotions. For example, if the examinee is nervous, the notification unit will prioritize important notifications. If the examinee is relaxed, the notification unit can also deliver notifications in the normal order. Furthermore, if the examinee is anxious, the notification unit can deliver notifications in an order that allows for quick review. In this way, by determining the priority of notifications according to the examinee's emotions, important information can be delivered to the examinee first. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input the examinee's emotion data into a generative AI and have the generative AI prioritize notifications.

[0107] The notification unit can select the optimal notification method when sending a notification, taking into account the examinee's device information. For example, if the examinee is using a smartphone, the notification unit will prioritize push notifications. It can also prioritize email notifications if the examinee is using a tablet. Furthermore, the notification unit can select the optimal notification method based on the examinee's device information. This allows the system to select the most suitable notification method by considering the examinee's device information. Some or all of the above processing in the notification unit may be performed using AI, or without AI. For example, the notification unit can input the examinee's device information data into an AI model and use that AI model to determine the notification method.

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

[0109] The application department can analyze an applicant's past learning history and suggest the most suitable application submission method. For example, if an applicant has previously submitted an application online, online submission will be prioritized. Similarly, if an applicant has previously submitted an application by mail, mail submission can be suggested. Furthermore, the application department can schedule application submissions for specific time slots based on the applicant's learning history. This allows the department to provide the most optimal application submission method by considering the applicant's past learning history.

[0110] The distribution department can analyze applicants' learning styles and propose the most suitable application distribution method. For example, if an applicant has a visual learning style, the application can include visual content. If an applicant has an auditory learning style, an application with audio guidance can be distributed. Furthermore, if an applicant has a practical learning style, an interactive application can be distributed. This allows the department to provide the most suitable application distribution method tailored to each applicant's learning style.

[0111] The data collection unit can monitor the study progress of test-takers in real time and adjust the timing of collecting pass / fail results. For example, if a test-taker is behind in their study progress, the collection of pass / fail results can be delayed. Conversely, if a test-taker is progressing well, the pass / fail results can be collected at the normal time. Furthermore, if a test-taker is progressing quickly, the pass / fail results can be collected earlier. This allows for the collection of pass / fail results at a timing that matches the test-taker's study progress.

[0112] The analysis unit can analyze applicants' learning patterns and improve the accuracy of its analysis of preferred university rankings and enrollment intentions. For example, it can analyze what kind of learning patterns applicants have had in the past and predict their current preferred university rankings and enrollment intentions. It can also predict future changes in preferred university rankings and enrollment intentions based on applicants' learning patterns. Furthermore, it can propose optimal preferred university rankings and enrollment intentions, taking into account applicants' learning patterns. This enables highly accurate analysis based on applicants' learning patterns.

[0113] The proposal department can suggest the optimal number of successful applicants based on the learning history of each applicant. For example, it can analyze the past learning history of each applicant and suggest the optimal number of successful applicants for each university. It can also predict future learning motivation based on the applicant's learning history and adjust the number of successful applicants accordingly. Furthermore, it can suggest a number of successful applicants that is appropriate for each university's capacity, taking into account the applicant's learning history. This makes it possible to suggest the optimal number of successful applicants based on the applicant's learning history.

[0114] The application processing system can estimate the applicant's emotions and adjust the application interface based on those estimates. For example, if the applicant is nervous, it can provide a simple and intuitive interface. If the applicant is relaxed, it can provide an interface with more detailed information. Furthermore, if the applicant is anxious, it can provide a quick and easy interface. This allows the system to provide the most suitable application processing interface for each applicant's emotional state.

[0115] The distribution system can estimate the emotions of applicants and adjust the timing of application distribution based on those estimates. For example, if an applicant is nervous, the application can be distributed during a time when they can relax. If the applicant is relaxed, the application can be distributed at the usual time. Furthermore, if the applicant is anxious, the application can be distributed quickly. This allows the system to provide the optimal application distribution timing tailored to the emotions of each applicant.

[0116] The data collection unit can estimate the emotions of test-takers and adjust the notification method for pass / fail results based on the estimated emotions. For example, if a test-taker is nervous, a simple and easy-to-understand notification method can be provided. If a test-taker is relaxed, a notification method including detailed information can be provided. Furthermore, if a test-taker is anxious, a notification method that can be quickly understood can be provided. This allows for the provision of the most appropriate pass / fail result notification method according to the emotions of the test-taker.

[0117] The analysis unit can estimate the emotions of test-takers and adjust the display method for analyzing their preference rankings and intention to enroll based on those estimated emotions. For example, if a test-taker is nervous, it can provide a simple and highly visible display method. If a test-taker is relaxed, it can provide a display method that includes detailed information. Furthermore, if a test-taker is anxious, it can provide a display method that can be quickly understood. This allows the system to provide the optimal display method for analysis results tailored to the test-taker's emotions.

[0118] The proposal system can estimate the emotions of test-takers and adjust the method of proposing the number of successful candidates based on those estimated emotions. For example, if a test-taker is nervous, it can provide a simple and highly visual proposal method. If a test-taker is relaxed, it can provide a proposal method that includes detailed information. Furthermore, if a test-taker is anxious, it can provide a proposal method that can be quickly understood. This allows the system to provide the optimal method of proposing the number of successful candidates according to the emotions of the test-takers.

[0119] The following briefly describes the processing flow for example form 2.

[0120] Step 1: The reception desk accepts applicants' applications at a temporary counter. These applications include handwritten and digital forms. The reception desk digitizes handwritten applications using scanning technology and accepts them. It can also directly accept digitally submitted applications. Furthermore, it can read printed applications using OCR technology. Step 2: The distribution department uses AI to automatically distribute the applications received by the reception department to each university. Distribution is done via methods such as email and a dedicated system. The distribution department analyzes the applicant's application information and distributes it to each university in the appropriate format. For example, it can distribute it to University A in PDF format and to University B in Excel format. The distribution department can also adjust the level of detail in the distribution based on the importance of each university. Step 3: The collection unit uses AI to collect acceptance / rejection results from each university in real time based on the applications distributed by the distribution unit. Collection is carried out using methods such as data collection via API and periodic polling. The collection unit automatically collects and centrally manages acceptance / rejection results from each university. This allows applicants to check acceptance / rejection results from multiple universities at once. The collection unit can also improve the accuracy of collection by considering the interrelationships between universities. Step 4: The analysis unit uses AI to analyze preference rankings and enrollment intentions based on the pass / fail results collected by the data collection unit. The analysis is performed using methods such as survey results and historical data analysis. The analysis unit analyzes preference rankings and enrollment intentions through communication with applicants. For example, if an applicant is accepted into their first-choice university, they may indicate that they do not intend to attend their second-choice or lower-ranked universities. The analysis unit can also predict current trends by referring to past data. Step 5: The proposal department uses AI to suggest the optimal number of admitted students based on the preference rankings and enrollment intentions analyzed by the analysis department. The suggestions are based on the university's enrollment capacity, past admission data, etc. The proposal department analyzes applicants' preference rankings and enrollment intentions and proposes the optimal number of admitted students for each university. This allows each university to reduce the risk of exceeding its enrollment capacity or having its subsidies cut. The proposal department can also improve the accuracy of its suggestions by considering the interrelationships between universities.

[0121] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0122] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0123] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0124] Each of the multiple elements described above, including the reception unit, distribution unit, collection unit, analysis unit, proposal unit, and notification unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and receives applicants' applications at a temporary counter. The distribution unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and automatically distributes the received applications to each university. The collection unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and collects acceptance / rejection results from each university in real time. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes preference rankings and intentions to enroll. The proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes the optimal number of successful applicants. The notification unit is implemented by, for example, the control unit 46A of the smart device 14 and provides notifications regarding acceptance / rejection results and the next steps. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

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

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

[0127] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0128] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0129] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0130] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0131] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0132] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0133] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

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

[0136] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0137] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0138] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0139] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0140] Each of the multiple elements described above, including the reception unit, distribution unit, collection unit, analysis unit, proposal unit, and notification unit, is implemented by, for example, at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and receives applicants' applications at a temporary counter. The distribution unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and automatically distributes the received applications to each university. The collection unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and collects acceptance / rejection results from each university in real time. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes preference rankings and intentions to enroll. The proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes the optimal number of successful applicants. The notification unit is implemented by, for example, the control unit 46A of the smart glasses 214 and provides notifications regarding acceptance / rejection results and the next steps. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

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

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

[0143] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0144] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0145] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0147] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0148] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0149] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

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

[0152] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0153] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0154] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0155] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0156] Each of the multiple elements described above, including the reception unit, distribution unit, collection unit, analysis unit, proposal unit, and notification unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and receives applicants' applications at a temporary counter. The distribution unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and automatically distributes the received applications to each university. The collection unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and collects acceptance / rejection results from each university in real time. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes preference rankings and intentions to enroll. The proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes the optimal number of successful applicants. The notification unit is implemented by, for example, the control unit 46A of the headset terminal 314 and provides notifications regarding acceptance / rejection results and the next steps. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

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

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

[0159] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0160] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0161] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0162] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0163] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0164] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0165] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0166] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0168] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0169] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0170] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0171] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0172] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0173] Each of the multiple elements described above, including the reception unit, distribution unit, collection unit, analysis unit, proposal unit, and notification unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and receives applicants' applications at a temporary counter. The distribution unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and automatically distributes the received applications to each university. The collection unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and collects acceptance / rejection results from each university in real time. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes preference rankings and intentions to enroll. The proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes the optimal number of successful applicants. The notification unit is implemented by, for example, the control unit 46A of the robot 414 and provides notifications regarding acceptance / rejection results and the next steps. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0174] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0175] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0176] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0177] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0178] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0179] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0180] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0181] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0182] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

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

[0184] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0185] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0186] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0187] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0188] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0189] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0190] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0191] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0192] (Note 1) The reception desk accepts applications from applicants at the temporary counter, The distribution department automatically distributes the application forms received by the aforementioned reception department to each university, A collection unit collects acceptance / rejection results from each university in real time based on the application forms distributed by the aforementioned distribution unit, An analysis unit analyzes the preference ranking and intention to enroll based on the pass / fail results collected by the aforementioned collection unit, The system includes a proposal unit that proposes an appropriate number of successful applicants based on the preference ranking and intention to enroll analyzed by the aforementioned analysis unit. A system characterized by the following features. (Note 2) It includes a notification unit that notifies the pass / fail result and the next steps. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned reception unit is We estimate the emotions of applicants and adjust the timing of application submission based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned reception unit is Analyze the past application submission history of applicants and select the appropriate application method. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned reception unit is When receiving applications, applicants will be filtered based on their current academic status and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is The system estimates the emotions of applicants and determines the priority of applications to be accepted based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is When accepting applications, priority will be given to applications that are highly relevant based on the applicant's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is When accepting applications, we will accept applications based on the applicant's social media activity. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned distribution unit, We estimate the emotions of the applicants and adjust the wording of the application form based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned distribution unit, When distributing application forms, the level of detail in the distribution will be adjusted based on the importance of the university. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned distribution unit, When distributing applications, different distribution algorithms are applied based on the university's category. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned distribution unit, The system estimates the emotions of test-takers and adjusts the length of the delivery based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned distribution unit, When distributing application forms, the priority of distribution will be determined based on the university's submission deadline. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned distribution unit, When distributing application forms, the order of distribution will be adjusted based on the relevance of the universities. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned collection unit is We estimate the emotions of the test-takers and adjust the criteria for collecting pass / fail results based on the estimated emotions of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned collection unit is When collecting admission results, improve the accuracy of the collection based on the relationships between universities. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned collection unit is When collecting admission results, the data will be collected based on the university's attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned collection unit is The system estimates the emotions of test-takers and adjusts the display order of the collected results based on the estimated emotions of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned collection unit is When collecting admission results, the data will be collected based on the geographical distribution of universities. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned collection unit is When collecting pass / fail results, we improve the accuracy of the collection based on relevant university literature. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned analysis unit, The system estimates the emotions of applicants and adjusts how they display their preference rankings and intention to enroll based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned analysis unit, When analyzing preference rankings and enrollment intentions, we predict current trends based on past data. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned analysis unit, When analyzing preference rankings and enrollment intentions, different analytical methods are applied based on the university category. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned analysis unit, The system estimates the emotions of applicants and adjusts their preference ranking and the importance of their intention to enroll based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned analysis unit, When analyzing preference rankings and enrollment intentions, we analyze changes in trends based on the timing of university submissions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned analysis unit, When analyzing preference rankings and enrollment intentions, trends are analyzed based on relevant market data for universities. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned proposal section is, The system estimates the emotions of the test-takers and determines the priority of the proposed number of successful candidates based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned proposal section is, When proposing the number of successful applicants, we will improve the accuracy of the proposal based on the interrelationships between universities. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned proposal section is, When proposing the number of successful applicants, the proposal should be based on the university's attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned proposal section is, We estimate the emotions of test-takers and adjust the display method for the number of successful candidates based on the estimated emotions of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned proposal section is, When proposing the number of successful applicants, the proposal should be based on the geographical distribution of universities. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned proposal section is, When proposing the number of successful candidates, improve the accuracy of the proposal based on relevant university literature. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned notification unit, The system estimates the emotions of test-takers and adjusts the timing of notifications based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned notification unit, When notifying applicants, the appropriate notification method will be selected based on their past notification history. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned notification unit, The system estimates the emotions of test-takers and determines the priority of notifications based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned notification unit, When notifying, the system will select the appropriate notification method based on the test taker's device information. The system described in Appendix 2, characterized by the features described herein. [Explanation of symbols]

[0193] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The reception desk accepts applications from applicants at the temporary counter, The distribution department automatically distributes the application forms received by the aforementioned reception department to each university, A collection unit collects acceptance / rejection results from each university in real time based on the application forms distributed by the aforementioned distribution unit, An analysis unit analyzes the preference ranking and intention to enroll based on the pass / fail results collected by the aforementioned collection unit, The system includes a proposal unit that proposes an appropriate number of successful applicants based on the preference ranking and intention to enroll analyzed by the aforementioned analysis unit. A system characterized by the following features.

2. It includes a notification unit that notifies the pass / fail result and the next steps. The system according to feature 1.

3. The aforementioned reception unit is We estimate the emotions of applicants and adjust the timing of application submission based on those estimated emotions. The system according to feature 1.

4. The aforementioned reception unit is Analyze the past application submission history of applicants and select the appropriate application method. The system according to feature 1.

5. The aforementioned reception unit is When receiving applications, applicants will be filtered based on their current academic status and areas of interest. The system according to feature 1.

6. The aforementioned reception unit is The system estimates the emotions of applicants and determines the priority of applications to be accepted based on those estimated emotions. The system according to feature 1.

7. The aforementioned reception unit is When accepting applications, priority will be given to applications that are highly relevant based on the applicant's geographical location. The system according to feature 1.

8. The aforementioned reception unit is When accepting applications, we will accept applications based on the applicant's social media activity. The system according to feature 1.

Images