System

Abstract

A system is provided.SOLUTION: The system includes a means for inputting an entrance condition from a user, a means for proposing an entrance destination suitable based on the inputted condition, a means for presenting the proposed entrance destination candidate to the user and receiving an additional condition, a means for narrowing down the entrance destination candidates based on the additional condition, and a means for performing a reservation procedure to the entrance destination selected by the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] ---

[0005] When selecting a school to attend, it is difficult to find the best one, considering a variety of factors. Users must consider a wide range of factors, such as deviation score, distance from home, club activities, career path after graduation, available qualifications, and budget, making it difficult to find a school that meets their individual needs. Furthermore, relying solely on one's own opinion or that of those around oneself can be unsettling, so a support system for selecting a school based on objective and diverse data is needed. [Means for solving the problem]

[0006] The present invention solves the above problem by providing a system that includes a means for a user to input educational requirements, a means for proposing suitable educational destinations based on the input requirements, a means for presenting the proposed educational destinations to the user and receiving additional requirements, a means for narrowing down the educational destinations based on the additional requirements, and a means for completing reservation procedures at the educational destination selected by the user.By using a generative AI model to make highly accurate suggestions based on the educational requirements and utilizing a database to manage attribute data of the educational destinations, the system enables users to easily find the optimal educational destination.

[0007] ---

[0008] "User" refers to an individual or organization that uses the system to select a school to attend.

[0009] "Conditions for further education" are the various elements that users specify for their desired school, including deviation score, area, club activities, career path after graduation, budget, etc.

[0010] "School destination" refers to the educational institution the user is considering attending, including university, high school, vocational school, etc.

[0011] "Suggestion" means that the system presents the most suitable school options based on the user's educational requirements.

[0012] "Additional conditions" refer to more specific requirements in addition to the conditions for admission initially entered by the user, such as the campus environment or the qualifications that can be obtained.

[0013] The "reservation procedure" is the process by which the user formally notifies the selected school of their intention to attend and secures their place.

[0014] A "generative AI model" is an artificial intelligence model used to suggest the most suitable school to attend based on the user's educational requirements.

[0015] A "database" is a collection of information that manages attribute data for schools and can be searched and updated through queries.

[0016] "Attribute data" is information associated with each school, including deviation scores, area, club activities, career paths after graduation, budget, and available qualifications. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] ---

[0039] The present invention relates to a system that proposes the selection of educational destinations based on the user's desired conditions, and in particular, describes a system that provides services as an educational destination concierge and a method for implementing the system.

[0040] First, this system consists of a server, a terminal, and a user. The user inputs their educational requirements, the server proposes suitable schools based on those requirements, and the terminal presents the results to the user. Below, we will explain the operation of each component in detail.

[0041] User Actions

[0042] The user starts the university entrance concierge application and inputs the conditions for the university they wish to attend. For example, they can input the following conditions:

[0043] Standard deviation: 60

[0044] Area: Tokyo

[0045] Club activities: Soccer

[0046] Post-graduation path: Employment

[0047] Budget: Under 3 million yen

[0048] After entering the information, the user presses the "Search" button to confirm the conditions.

[0049] Device behavior

[0050] The device receives the conditions entered by the user and sends them to the server, converting the data into the required format and communicating with the server using an API.

[0051] Server Operation

[0052] The server receives the user's requirements sent from the device and uses the generative AI model to search a database containing attribute data for each school (such as deviation score, area, club activities, post-graduation path, budget, and available qualifications), and generates an initial list of candidates based on this information.

[0053] The server returns the generated candidate list in JSON format to the terminal, presenting the user with potential schools.

[0054] Add user conditions and search again

[0055] The user checks the list of potential schools presented to them and enters more specific desired conditions (for example, "a good campus environment" or "the ability to obtain a specific qualification"). After entering the additional conditions, the user presses the "Search Again" button to resubmit the conditions.

[0056] Re-search and narrow down the servers

[0057] The server updates the candidate list based on the newly added criteria, generating a more refined list of candidates, and sends this updated candidate list back to the terminal for presentation to the user.

[0058] Finalist and booking process

[0059] Finally, the user selects the most suitable school from the presented options and completes the reservation procedure. When the user completes the reservation operation, the terminal sends the information to the server.

[0060] The server processes the reservation based on the received information and records it in the database. After the reservation is completed, the server sends a confirmation email to the user to notify them that the reservation has been completed.

[0061] Specific examples

[0062] For example, if a user enters the desired criteria of "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospect," the server will list multiple universities that fit this criteria. If the user then enters an additional criteria such as "a good campus environment," the server will further narrow down the candidates based on that criteria, generate a final list of suggestions, and support the user in making a reservation at the university of their choice.

[0063] The present invention allows users to easily find the best school to go to that meets their diverse needs, and reduces the anxiety and worries that come with selecting a school to go to.

[0064] The processing flow will be explained below.

[0065] ---

[0066] Step 1:

[0067] The user launches the university entrance concierge application.

[0068] Step 2:

[0069] The user inputs criteria for the school they wish to attend. For example, a deviation score of 60, living in Tokyo, playing soccer, getting a job, and a budget of 3 million yen or less.

[0070] Step 3:

[0071] The user presses the "Search" button to confirm the input conditions.

[0072] Step 4:

[0073] The terminal receives the user's input conditions and generates a request to send the data to the server.

[0074] Step 5:

[0075] The terminal sends the generated request to the server.

[0076] Step 6:

[0077] The server receives the request from the device and loads the generative AI model.

[0078] Step 7:

[0079] The server searches the database based on the user's criteria and generates a list of potential schools.

[0080] Step 8:

[0081] The server returns the generated list of potential schools to the device in JSON format.

[0082] Step 9:

[0083] The terminal analyzes the candidate list received from the server and prepares data for display on the user interface.

[0084] Step 10:

[0085] The device displays a list of potential schools to the user.

[0086] Step 11:

[0087] The user reviews the list of candidates and enters additional criteria, such as "good campus environment" or "ability to obtain specific qualifications."

[0088] Step 12:

[0089] After the user enters additional conditions, he or she presses the "Search Again" button.

[0090] Step 13:

[0091] The terminal receives the additional conditions and generates a request to transmit the data to the server.

[0092] Step 14:

[0093] The terminal sends the generated request to the server.

[0094] Step 15:

[0095] The server again receives the user's additional conditions and updates the existing candidate list using the generative AI model.

[0096] Step 16:

[0097] The server returns the updated list of potential schools to the device in JSON format.

[0098] Step 17:

[0099] The terminal analyzes the update list received from the server and displays it again on the user interface.

[0100] Step 18:

[0101] The user reviews the final school options and selects one.

[0102] Step 19:

[0103] The user presses a button to complete the reservation procedure for the selected school.

[0104] Step 20:

[0105] The terminal generates a request to transmit the selected information to the server.

[0106] Step 21:

[0107] The terminal sends the generated request to the server.

[0108] Step 22:

[0109] The server analyzes the received selection information and starts the reservation procedure.

[0110] Step 23:

[0111] The server completes the booking process and sends a confirmation email to the user.

[0112] Step 24:

[0113] The terminal receives a reservation completion notification from the server and displays it to the user.

[0114] Step 25:

[0115] Verify that the user receives a confirmation email.

[0116] ---

[0117] The above is the specific processing flow of the program, and the operations performed at each step have been explained in detail.

[0118] Example 1

[0119] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0120] When users have multiple requirements and preferences when selecting a school, it can be extremely difficult to find the right school on their own. Furthermore, the process can be time-consuming and difficult to obtain accurate information, which can increase stress. There is a need to solve these problems and enable users to quickly and accurately find the school that best suits them.

[0121] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0122] In this invention, the server includes means for allowing a user to input educational requirements, means for suggesting suitable educational destinations based on the input requirements, means for presenting the suggested educational destinations to the user and receiving additional requirements, means for narrowing down the list of educational destinations based on the additional requirements, means for completing a reservation procedure for the educational destination selected by the user, means for creating and updating a candidate list based on the educational requirements and additional requirements using a generative AI model, and means for recording the candidate list and final reservation information in a database and sending a confirmation by email. This allows users to quickly and accurately find the optimal educational destination based on various requirements for their educational destination selection.

[0123] A "user" is someone who inputs their educational requirements and uses the system to select the most suitable educational destination.

[0124] "Conditions for further education" refers to information entered by the user regarding their desired education, and specifically includes deviation score, area, club activities, career path after graduation, budget, etc.

[0125] "Means of suggestion" is a function in which the server lists and presents suitable schools based on the user's educational requirements.

[0126] "Additional conditions" refer to specific desired conditions that users enter after reviewing their initial list of potential schools, including the campus environment, available qualifications, etc.

[0127] The "narrowing down method" is a function that allows the server to update the list of potential schools based on new conditions added by the user, generating a more suitable list.

[0128] The "means of making reservations" is a function that confirms reservations at the school selected by the user and supports the process.

[0129] A "generative AI model" is an artificial intelligence model used to create and update a list of potential schools based on the school entry requirements and additional requirements.

[0130] A "database" is an information storage device managed by a server, and is responsible for storing various data, including attribute data on schools and user reservation information.

[0131] MODE FOR CARRYING OUT THE INVENTION

[0132] This invention relates to a system that suggests educational destinations based on the user's desired criteria, and in particular to a system that provides services as an educational destination concierge, and its implementation method. The system consists of a server, a terminal, and a user. The user inputs their educational destination criteria, the server suggests suitable educational destinations based on those criteria, and the terminal displays the results to the user.

[0133] User Actions

[0134] The user starts the university entrance concierge application and inputs the conditions for the university they wish to attend. For example, they can input the following conditions:

[0135] Standard deviation: 60

[0136] Area: Tokyo

[0137] Club activities: Soccer

[0138] Post-graduation path: Employment

[0139] Budget: Under 3 million yen

[0140] After entering the information, the user presses the "Search" button to confirm the conditions.

[0141] Device behavior

[0142] The device receives the conditions entered by the user and sends them to the server, where format conversion is performed and API is used to communicate with the server.

[0143] Server Operation

[0144] The server receives the user's requirements sent from the device. The server's backend contains a database linked to a generative AI model (e.g., GPT-4), which generates an initial candidate list based on the school's attribute data (standard deviation, area, club activities, post-graduation career path, budget, etc.). The generated candidate list is returned to the device in JSON format, and the user is presented with potential schools.

[0145] Add user conditions and search again

[0146] The user checks the list of potential schools presented to them and enters more specific desired conditions, such as "a good campus environment" or "the ability to obtain a specific qualification." After entering the additional conditions, the user clicks the "Search Again" button and resubmits the conditions.

[0147] Re-search and narrow down the servers

[0148] The server updates the candidate list based on the newly added criteria, generating a more refined list, and then sends the updated candidate list back to the terminal and presents it to the user.

[0149] Finalist and booking process

[0150] Finally, the user selects the most suitable school from the presented options and completes the reservation procedure. When the user completes the reservation operation, the terminal sends the information to the server. The server records the received reservation information in a database and sends the user a confirmation email that the reservation has been completed.

[0151] Specific examples

[0152] For example, if a user enters the desired criteria as "a university in Tokyo with a deviation score of 60, a soccer club, and a strong employment prospect," the process will be as follows:

[0153] 1. The user launches the application, enters the criteria for further education, and presses the search button.

[0154] 2. The device sends the conditions to the server.

[0155] 3. The server lists the universities that match the criteria and generates a candidate list.

[0156] 4. The user enters additional criteria such as "good campus environment" and presses the search again button.

[0157] 5. The server further refines the criteria and generates a final list of suggestions.

[0158] 6. The user selects the most suitable university and completes the reservation process.

[0159] 7. The server completes the booking process and sends a confirmation email.

[0160] Prompt Sentence Examples

[0161] The user entered "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospect" as their desired criteria. Furthermore, they entered "a good campus environment" as an additional condition. Please make a list of universities that meet these criteria and present it to the user.

[0162] The present invention allows users to easily find the best school to go to that meets their diverse needs, and reduces the anxiety and worries that come with selecting a school to go to.

[0163] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0164] Specific processing steps of the program

[0165] Step 1:

[0166] The user launches the university entrance concierge application and inputs the conditions for the university they wish to attend (e.g., deviation score, area, club activities, career path after graduation, budget, etc.). The conditions entered are temporarily saved as local data on the device. The user ID is also added to the input data, making it possible to identify the user in later processes.

[0167] Step 2:

[0168] The device converts the conditions for continuing education entered by the user into JSON format and sends it to the server using an HTTP POST request. At this time, all input data, including the user ID, is sent as parameters. Input data: conditions for continuing education, user ID. Output data: request to send to the server.

[0169] Step 3:

[0170] The server receives the user's conditions sent from the device and searches the database using a generative AI model (e.g., GPT-4). The database stores attribute data for each school (standard deviation, area, club activities, post-graduation career path, budget, etc.). The AI ​​model generates an initial list of candidates based on the entered conditions. Input data: School conditions in JSON format. Output data: Initial list of candidates.

[0171] Step 4:

[0172] The server converts the generated candidate list into JSON format and sends it to the terminal as an HTTP response. Input data: Initial candidate list. Output data: Send request to the terminal.

[0173] Step 5:

[0174] The terminal displays the received candidate list on the screen and presents it to the user. The user checks this list and enters more specific desired conditions (additional conditions). Input data: candidate list from the server. Output data: screen display.

[0175] Step 6:

[0176] The user checks the displayed list of potential schools and inputs additional conditions. For example, "the campus environment is good" or "a specific qualification can be obtained." Input data: Additional conditions. Output data: Notification of input completion to the terminal.

[0177] Step 7:

[0178] The terminal converts the data into JSON format again based on the additional conditions entered by the user and resends it to the server using an HTTP POST request. Input data: Additional conditions. Output data: Retransmission request to the server.

[0179] Step 8:

[0180] The server uses the generative AI model to narrow down the candidate list based on the additional criteria received again, generating an updated candidate list. It then re-queries the database to identify schools that meet the new criteria. Input data: Additional criteria. Output data: Updated candidate list.

[0181] Step 9:

[0182] The server converts the updated candidate list into JSON format and resends it to the terminal as an HTTP response. Input data: Updated candidate list. Output data: Send request to the terminal.

[0183] Step 10:

[0184] The terminal displays the narrowed candidate list on the screen again and presents it to the user. Input data: Updated candidate list from the server. Output data: Screen display.

[0185] Step 11:

[0186] The user selects the most suitable school from the presented options and presses the "Reserve" button to complete the reservation procedure. Input data: Selected school. Output data: Notification of input completion to the terminal.

[0187] Step 12:

[0188] The terminal converts the user's reservation information into JSON format and sends it to the server using an HTTP POST request. Input data: reservation information. Output data: request to send to the server.

[0189] Step 13:

[0190] The server records the received reservation information in a database, confirms the reservation, and sends a confirmation email to the user. Input data: Reservation information. Output data: Recorded in the database, sending a confirmation email.

[0191] By following the steps above, users can use this system to easily find the best school to go to that meets their diverse needs, reducing the anxiety and worries they may have when choosing a school to go to.

[0192] (Application example 1)

[0193] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0194] Conventional university selection systems only allow users to view information about proposed universities based on the criteria they enter in a list format, making it difficult to visually experience the actual campus and surrounding area. Furthermore, each time additional criteria are entered, users must re-filter, making the university selection process cumbersome. Furthermore, a separate reservation procedure is required, placing a significant burden on users. To solve these issues, a system is needed that allows users to select universities in a visual, interactive way and complete the reservation procedure simply and efficiently.

[0195] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0196] In this invention, the server includes means for allowing a user to input educational requirements, means for suggesting suitable destinations based on the input requirements, means for presenting the suggested destinations to the user and receiving additional requirements, means for narrowing down the destinations based on the additional requirements, means for completing a reservation procedure for the destination selected by the user, means for providing a virtual environment for the user to search for destinations in a virtual space, and means for displaying destination information based on the educational requirements as a 3D model in the virtual space. This allows the user to interactively narrow down the requirements while visually checking the destination environment and simplifies the reservation procedure, thereby reducing the burden of selecting a destination.

[0197] The "means for the user to input conditions for further education" refers to a device or method that provides an interface for the user to input desired conditions for further education into the system.

[0198] "Means for suggesting suitable educational destinations based on the input conditions" refers to a device or method that has the function of selecting and suggesting the most suitable educational destination based on the conditions input by the user.

[0199] "Means for presenting the proposed school candidates to the user and receiving additional conditions" refers to a device or method by which the system displays the proposed school candidates to the user and the user re-enters more detailed additional conditions.

[0200] The "means for narrowing down the candidate schools based on the additional conditions" refers to a device or method for further narrowing down the candidate schools based on the additional conditions newly input by the user.

[0201] The "means for making reservations for the school selected by the user" refers to a device or method that has the function of making reservations or applications for the school selected by the user.

[0202] "Means for providing a virtual environment for users to explore potential schools in a virtual space" refers to devices or methods that allow users to visually experience the campus and surrounding environment of their potential schools in a virtual reality space.

[0203] "Means for displaying information on schools based on the conditions for furthering education in a virtual space using a 3D model" refers to a device or method for displaying information on schools that meet the user's conditions for furthering education in a virtual reality space using a three-dimensional model.

[0204] MODE FOR CARRYING OUT THE INVENTION

[0205] This invention relates to a system that provides a virtual environment for users to use when searching for schools and supports their selection and reservation of schools. In particular, it provides a mechanism for suggesting school candidates using a generative AI model and interactively narrowing down the options.

[0206] System configuration

[0207] The system consists of the following main components:

[0208] 1. User device: smartphone, head-mounted display (HMD), etc.

[0209] 2. Server: Stores the generative AI model and the database of schools to go to, and processes data.

[0210] 3. 3D modeling tools: Tools for building virtual environments. Example: Blender.

[0211] 4. Game engine: Software for displaying virtual spaces. Example: Unity.

[0212] 5. Speech Recognition API: Used to receive additional conditions from the user. Example: Google Cloud Speech-to-Text.

[0213] System Operation

[0214] 1. User Action:

[0215] The user launches the university entrance concierge application using a smartphone or head-mounted display. The application provides a form for the user to enter university entrance criteria such as deviation score, area, club activities, post-graduation career path, and budget. The user enters these criteria and begins the search.

[0216] 2. Device behavior:

[0217] The user device converts the entered educational requirements into JSON format and sends it to the server via a RESTful API. While waiting for a response from the server, the device prepares to load the virtual space.

[0218] 3. Server Operation:

[0219] The server uses the generative AI model to search a database of schools based on the received conditions for further education. This database contains attribute data for each school (such as deviation score, area, club activities, post-graduation career path, budget, and available qualifications). The server returns the search results in JSON format to the user's device.

[0220] 4. Providing a virtual space:

[0221] The user device uses Unity to display 3D models in a virtual environment based on the data of potential schools received from the server, and the user can use a head-mounted display to walk around and visually check the virtual campus.

[0222] 5. Enter additional criteria and search again:

[0223] While exploring the virtual campus, users can add more specific preferences. For example, they can use a voice recognition API to input additional criteria such as "a good campus environment" or "the ability to obtain a specific qualification." These additional criteria are sent back to the server, which then performs a new search based on the new criteria and narrows down the candidates.

[0224] 6. Finalist and booking process:

[0225] The narrowed down list of candidates is displayed again on the user's device, and the user can select the most suitable school. After completing the selection, the user completes the reservation procedure, and the device sends the reservation information to the server. The server confirms the completion of the reservation procedure and sends a confirmation email to the user.

[0226] Specific examples

[0227] For example, if a user enters their desired criteria as "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospects," the server will generate a list of suitable universities based on this. If the user then voice-inputs additional criteria, such as "a good campus environment," in the virtual environment, the server will further narrow down the candidates based on the criteria, generating a final list of suggestions and presenting it to the user. The user can then select the most suitable university and complete the reservation process easily within the virtual space.

[0228] Prompt Sentence Examples

[0229] "Please limit your search to Tokyo as the area where you plan to study."

[0230] "Please show me schools that have soccer teams."

[0231] "Please tell me which university I would like to attend that has a good campus environment."

[0232] Based on the prompts described above, the system presents potential schools that specifically reflect the user's desired conditions, allowing the user to easily find a school that satisfies them.

[0233] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0234] Step 1:

[0235] User's entry of educational requirements

[0236] Users launch the university entrance concierge application using a smartphone or head-mounted display and enter information about university entrance requirements such as deviation score, area, club activities, career path after graduation, and budget.

[0237] Input: User's desired academic conditions (e.g., deviation score 60, area: Tokyo, club activity: soccer, career path after graduation: employment, budget: within 3 million yen)

[0238] Output: Data on academic qualifications (JSON format)

[0239] Step 2:

[0240] Sending admission conditions from the device to the server

[0241] The terminal converts the entered conditions for further education into JSON format and sends it to the server via a RESTful API.

[0242] Input: JSON format data on academic requirements

[0243] Output: Request to send admission requirements to the server

[0244] Step 3:

[0245] Server-based suggestions for potential schools

[0246] The server uses the generative AI model to search a database of schools based on the received school conditions, thereby generating a list of school candidates that meet the user's conditions.

[0247] Input: Admission requirements data

[0248] Output: A list of suitable schools (JSON format)

[0249] Step 4:

[0250] Loading the virtual world on your device

[0251] The device uses Unity to display 3D models of potential schools in a virtual environment based on the data received from the server, and users can use a head-mounted display to walk around the virtual campus and visually confirm their experiences.

[0252] Input: Data on potential schools (JSON format)

[0253] Output: 3D model display in virtual space

[0254] Step 5:

[0255] User-entered additional conditions

[0256] While exploring the virtual campus, users can input more specific requirements (e.g., a good campus environment, the ability to obtain specific qualifications) using a voice recognition API.

[0257] Input: Voice input of additional conditions

[0258] Output: Additional condition data in text format

[0259] Step 6:

[0260] Resend additional condition data to the server

[0261] The device converts the additional condition data, which has been converted into text using the voice recognition API, back into JSON format and sends it to the server.

[0262] Input: Additional condition data in text format

[0263] Output: Request to send additional condition data to the server

[0264] Step 7:

[0265] Server-based re-search and refinement of potential schools

[0266] The server receives the additional condition data, searches the list of potential schools again based on the new conditions, and generates a further narrowed list.

[0267] Enter: Additional condition data

[0268] Output: A list of narrowed-down school candidates (JSON format)

[0269] Step 8:

[0270] Presentation and selection of the final candidate list

[0271] The terminal then presents the narrowed down list of potential schools received from the server to the user, who then selects the most suitable school.

[0272] Input: A list of narrowed-down school candidates (JSON format)

[0273] Output: User's chosen educational destination

[0274] Step 9:

[0275] Completing the reservation process

[0276] The user completes the reservation procedure for the selected school. The device sends the selection information to the server, which then completes the reservation procedure and sends a confirmation email to the user.

[0277] Input: User's selected school and reservation information

[0278] Output: Confirmation email of reservation completion

[0279] As described above, the present invention can provide a system that provides interactive and visual support for everything from selecting a school to completing the reservation procedures.

[0280] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0281] ---

[0282] This invention relates to a system that suggests educational destinations based on the user's wishes and emotions, and in particular to a system that provides a service as an educational destination concierge by combining an emotion engine, and a method for implementing the system.

[0283] First, this system consists of a server, a terminal, and a user, and also incorporates an emotion engine that recognizes the user's emotions. The user inputs their educational requirements, and the emotion engine analyzes their voice and facial expressions when they input them. The server then suggests suitable educational destinations based on the requirements and emotional information, and the terminal presents the results to the user. The operation of each component is described in detail below.

[0284] User Actions

[0285] The user starts the university entrance concierge application and inputs the conditions for the university they wish to attend. For example, they can input the following conditions:

[0286] Standard deviation: 60

[0287] Area: Tokyo

[0288] Club activities: Soccer

[0289] Post-graduation path: Employment

[0290] Budget: Under 3 million yen

[0291] When inputting, the user's voice and facial expressions are simultaneously recorded and analyzed by the emotion engine.

[0292] Device behavior

[0293] The device receives the conditions and emotion information entered by the user and generates a request to send the data to the server, converting the data into the required format and communicating with the server using an API.

[0294] Server Operation

[0295] The server receives the user's conditions and emotion information sent from the device and loads the generative AI model. It also takes into account the emotion analysis results provided by the emotion engine. The server searches the database based on the user's conditions and emotions and generates a list of potential schools.

[0296] If the emotional information is determined to be "nervous" or "anxious," the server will prioritize the schools in the list that will increase the user's sense of security (e.g., schools that are good for finding employment).

[0297] The generated candidate list is returned in JSON format to the terminal, and the results are presented to the user.

[0298] Add user conditions and search again

[0299] The user checks the list of potential schools presented to them and enters more specific desired conditions (for example, "a good campus environment" or "the ability to obtain a specific qualification"). After entering the additional conditions, the user presses the "Search Again" button and resubmits the conditions. At this time, the user's emotions are also recorded again.

[0300] Re-search and narrow down the servers

[0301] The server updates the candidate list based on the newly added conditions and emotion information. If the emotion is analyzed as "satisfied," the suggested list will be very close to that condition. The updated candidate list is then sent to the device again and presented to the user.

[0302] Finalist and booking process

[0303] Finally, the user selects the most suitable school from the presented options and completes the reservation procedure. When the user completes the reservation operation, the terminal sends the information to the server.

[0304] The server processes the reservation based on the received information and records it in the database. After the reservation is completed, the server sends a confirmation email to the user to notify them that the reservation has been completed.

[0305] Specific examples

[0306] For example, if a user enters their desired criteria as "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospects," and the emotion engine analyzes this as "I feel nervous," the server will prioritize universities that the user feels comfortable with in the initial candidate list. If the user then enters an additional criterion such as "a good campus environment" and the emotion is analyzed as "I feel comfortable," the server will further narrow down the candidate list based on this criteria and generate results that give the user a sense of security. The user can then smoothly complete the reservation process for the university they ultimately selected.

[0307] The present invention allows users to easily find the most suitable school to attend that takes into consideration not only their diverse needs but also their emotional information, further reducing the anxiety and worries that come with selecting a school to attend.

[0308] The processing flow will be explained below.

[0309] ---

[0310] Step 1:

[0311] The user launches the university entrance concierge application.

[0312] Step 2:

[0313] The user inputs the conditions for the school they wish to attend. For example, they can input the following conditions: deviation score 60, Tokyo, soccer club, employment, budget within 3 million yen.

[0314] Step 3:

[0315] When the user inputs a condition, the device records the user's voice and facial expressions, and sends this information to the emotion engine.

[0316] Step 4:

[0317] The emotion engine analyzes the user's voice and facial expression data to determine the user's emotions (e.g., "nervous" or "anxious").

[0318] Step 5:

[0319] The terminal generates a request to transmit the conditions for further education input by the user and the emotion information from the emotion engine together to the server.

[0320] Step 6:

[0321] The terminal sends the generated request to the server.

[0322] Step 7:

[0323] The server receives the user's educational requirements and emotional information sent from the device and reads the analysis results of the generative AI model and emotion engine.

[0324] Step 8:

[0325] The server searches the database based on the user's conditions and emotions to generate a list of potential schools. If the emotional information is determined to be "nervous," the server will prioritize suggesting schools that provide a sense of security, such as those with a strong job prospect.

[0326] Step 9:

[0327] The server returns the generated list of potential schools to the device in JSON format.

[0328] Step 10:

[0329] The terminal analyzes the candidate list received from the server and prepares data for display on the user interface.

[0330] Step 11:

[0331] The device displays a list of potential schools to the user.

[0332] Step 12:

[0333] The user reviews the list of candidates and enters additional criteria, such as "a good campus environment" or "the ability to obtain a specific qualification."

[0334] Step 13:

[0335] After the user enters additional conditions, they press the "Search Again" button, at which point the device again records the user's voice and facial expressions and sends them to the emotion engine.

[0336] Step 14:

[0337] The emotion engine again analyzes the user's voice and facial expression data to determine an updated emotion (e.g., "I feel relieved").

[0338] Step 15:

[0339] The terminal generates a request to transmit the added educational advancement conditions and new emotion information from the emotion engine together to the server.

[0340] Step 16:

[0341] The terminal sends the generated request to the server.

[0342] Step 17:

[0343] The server receives the user's additional conditions and emotion information again, updates the existing candidate list using the generative AI model, and makes suggestions that take the additional conditions into account based on the emotion information.

[0344] Step 18:

[0345] The server returns the updated list of potential schools to the device in JSON format.

[0346] Step 19:

[0347] The terminal again analyzes the updated list received from the server and displays it again on the user interface.

[0348] Step 20:

[0349] The user reviews the final school options and selects one.

[0350] Step 21:

[0351] The user presses a button to complete the reservation procedure for the selected school.

[0352] Step 22:

[0353] The terminal generates a request to transmit the selected information to the server.

[0354] Step 23:

[0355] The terminal sends the generated request to the server.

[0356] Step 24:

[0357] The server analyzes the received selection information and starts the reservation procedure.

[0358] Step 25:

[0359] The server completes the booking process and sends a confirmation email to the user.

[0360] Step 26:

[0361] The terminal receives a reservation completion notification from the server and displays it to the user.

[0362] Step 27:

[0363] Verify that the user receives a confirmation email.

[0364] ---

[0365] The above is the specific processing flow of the system that combines the emotion engine. The operations performed at each step have been explained in detail.

[0366] Example 2

[0367] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0368] Conventional university selection systems suggest schools based on the desired conditions entered by the user, but they are unable to take the user's emotional state into consideration, which means they are unable to fully provide the most suitable school for the user.In order to reduce users' anxiety and stress and make more personalized suggestions, it is necessary to suggest schools based on emotional information.

[0369] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for inputting educational conditions from the user, means for proposing suitable educational destinations based on the input conditions and the user's emotional information, means for presenting the proposed educational destination candidates to the user and receiving additional conditions and the user's emotional information, means for narrowing down the educational destination candidates based on the additional conditions and the user's emotional information, and means for completing the reservation procedure for the educational destination selected by the user. This makes it possible to propose optimal educational destinations taking the user's emotional state into consideration, reducing the user's anxiety and stress and enabling a more satisfying educational destination selection.

[0370] "Conditions for further education" refers to the criteria and requirements for the school the user wishes to attend. Examples include deviation score, area, club activities, career path after graduation, budget, etc.

[0371] "Emotional information" refers to data that analyzes the user's emotional state at the time of input and converts it into numerical or categorized data. Examples include states such as "tense" or "relieved."

[0372] "School to be attended" refers to the educational institution to which the user wishes to attend, including university, high school, vocational school, etc.

[0373] "Suggestion" means that the system presents the most suitable educational destination based on the user's educational requirements and emotional information.

[0374] "Additional conditions" are more specific desired conditions that are entered later in addition to the conditions for entering the university that the user initially entered. Examples include "a good campus environment" and "the ability to obtain a specific qualification."

[0375] The "reservation procedure" refers to the process by which a user formally applies for and enrols at the school of their choice.

[0376] A "generative AI model" is a model that uses artificial intelligence technology to analyze educational conditions and emotional information to suggest the most suitable educational destination for users.

[0377] A "database" is a data structure that manages various data related to the school of choice (attribute data, evaluation data, etc.) and is used for system searches and analysis.

[0378] MODE FOR CARRYING OUT THE INVENTION

[0379] This invention is a system for suggesting the selection of a school to attend based on the user's desired conditions and emotional information, and in particular, it combines an emotional engine to provide the user with the most suitable school. This system is composed of a server, a terminal, and a user, and uses the emotional engine to analyze the user's emotional state.

[0380] System configuration

[0381] The system uses the following hardware and software:

[0382] Terminal: A device that allows users to enter their educational requirements. Examples include computers and smartphones.

[0383] Server: A computer that analyzes the user's educational requirements and emotional information, and lists suitable schools. Example: Cloud services (AWS EC2, etc.).

[0384] Emotion engine: Technology for analyzing emotions from the user's voice and facial expressions. Example: Microsoft Azure Emotion API.

[0385] Generative AI model: An artificial intelligence technology that suggests the most suitable school to attend based on the user's educational requirements and emotional information. Example: GPT-4 (OpenAI).

[0386] Operating procedure

[0387] 1. The user enters their desired criteria for the school they wish to attend through the university entrance concierge app. For example, possible criteria include "standard deviation score 60," "area in Tokyo," "has a soccer club," and "budget within 3 million yen."

[0388] Example prompt sentence:

[0389] My desired conditions are a university in Tokyo with a deviation score of 60. I would like a place with a soccer club and a good job placement program. I'm a little nervous about my emotional situation.

[0390] 2. At the same time, the user's voice and facial expressions are recorded, and emotional information such as "nervous" or "relieved" is analyzed by the emotion engine.

[0391] 3. The device formats the input desired conditions and emotional information into JSON format and sends it to the server using an API.

[0392] 4. The server receives and analyzes the data sent from the device. Specifically, it uses a generative AI model based on the user's conditions and emotional information to generate an optimal list of potential schools.

[0393] At this time, attribute data for the school of choice is obtained from the database, and a list of candidates is generated based on the analysis results.

[0394] 5. The server returns the generated list of potential schools to the terminal, which presents the list to the user.

[0395] 6. The user can review the list of candidates presented and re-enter their search criteria with more specific details. By pressing the search again button, the data will be sent to the server again.

[0396] Example prompt sentence:

[0397] I also hope that the campus environment will be good and that I will be able to obtain certain qualifications.

[0398] 7. The server updates the list of potential schools again based on the additional desired conditions and the latest emotional information, and sends it to the terminal again.

[0399] 8. Finally, the user selects the most suitable school from the suggestions and completes the reservation procedure. Once the reservation is completed, the device sends the information to the server, which then completes the reservation procedure. Once the reservation is complete, a confirmation email is sent to the user.

[0400] Specific examples

[0401] For example, if a user enters their desired criteria as "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospects," and the emotion engine analyzes this as "I'm nervous," the server will prioritize universities that give them a sense of security in the initial candidate list. If the user then enters an additional criterion, such as "a good campus environment," and the emotion is analyzed as "I'm secure," the server will further narrow down the candidate list based on the new criteria and present it again. In this way, the user can select the most suitable university and proceed with the reservation process.

[0402] As described above, the present invention realizes optimal proposals for further education that take into consideration the user's desired conditions and emotional information, and provides a highly satisfying selection of further education while reducing the user's anxiety and stress.

[0403] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0404] Step 1:

[0405] Users simply launch the university entrance concierge app and input their desired criteria for the university they wish to attend. For example, they can input criteria such as "standard deviation score 60," "area Tokyo," "has a soccer club," and "budget within 3 million yen." As they input their information, the user's voice and facial expressions are simultaneously recorded and analyzed by the emotion engine.

[0406] Input: Conditions for entering university (standard score, area, club activities, budget, etc.), user's voice and facial expressions

[0407] Output: Data on conditions for continuing education, emotional information data

[0408] Specific operation: The user fills in the application's input form with their admission requirements and clicks the "Submit" button. The device's camera and microphone record the user's voice and facial expressions.

[0409] Step 2:

[0410] The device receives the conditions and emotion information entered by the user and generates a request to send the data to the server. During this process, the device converts the data into the required format (e.g., JSON format) and communicates with the server using an API.

[0411] Input: Data on conditions for continuing education, emotional information data

[0412] Output: API request in JSON format

[0413] Specific behavior: Converts input data into a JSON structure and executes an HTTP request to an API endpoint.

[0414] Step 3:

[0415] The server receives the data sent from the device, loads the generative AI model based on the received data, analyzes the user's conditions, and also takes into account the analysis results from the emotion engine.

[0416] Input: JSON format data on academic requirements and emotional information

[0417] Output: Analysis results

[0418] Specific operation: Analyzes JSON data and uses a generative AI model to analyze the user's desired conditions and emotional information, taking into account the results of the emotion engine.

[0419] Step 4:

[0420] The server generates a list of potential schools based on the analysis results. The priority of the list is adjusted according to the user's conditions and emotional information. For example, if the emotional information is determined to be "nervous," the server will prioritize schools that give a sense of security.

[0421] Input: Analysis results (desired conditions, emotional information)

[0422] Output: List of potential schools

[0423] Specific operation: Searches the database for attribute data of the school of choice, adjusts priorities using a generative AI model, and generates a list of candidates. The final list is compiled in JSON format.

[0424] Step 5:

[0425] The device receives the list of potential schools sent from the server and presents it to the user. The user can review the list and add more specific desired conditions. When the user presses the "Search Again" button, the conditions and emotional information are sent again from the device to the server.

[0426] Input: List of potential schools

[0427] Output: Additional preference, updated emotion information

[0428] Specific behavior: Display the candidate list to the user and provide a field for inputting additional desired conditions. Process the click event of the search again button and send new data to the server.

[0429] Step 6:

[0430] The server then updates the list of potential schools based on the additional conditions and the latest emotional information. It receives the data for the re-search, analyzes it again using the generative AI model, and generates a list of potential schools.

[0431] Input: Additional desired conditions, updated emotional information

[0432] Output: Updated school candidate list

[0433] Specific operation: Search the database again based on the new criteria, update the candidate list using the generative AI model, and return the new candidate list in JSON format to the device.

[0434] Step 7:

[0435] The user selects the most suitable school from the presented final candidate list. When the user completes the reservation procedure, the device sends the information to the server. The server then executes the reservation procedure based on the received information and sends a confirmation email to the user.

[0436] Input: Final candidate list, selected destination

[0437] Output: Notification of completion of reservation procedure

[0438] Specific operation: The user selects the school they wish to attend and clicks the reservation button. The reservation information is sent to the server, which then completes the reservation procedure. A confirmation email is sent to the user.

[0439] (Application example 2)

[0440] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0441] Conventional online shopping systems have been unable to take into account the emotional stress and anxiety that users face when selecting products. As a result, there have been cases where users are unable to choose the right product, resulting in a decrease in satisfaction. To solve this problem, a product suggestion system that takes users' emotions into account is required.

[0442] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's emotional information using an emotion engine and receiving purchase conditions from the user, means for proposing suitable products based on the input conditions and the analyzed emotional information, and means for presenting the proposed product candidates to the user and receiving additional conditions. This makes it possible to propose optimal products that take the user's emotions into consideration.

[0443] The "emotion engine" is a technology that analyzes the user's voice and facial expressions to extract emotional information in real time.

[0444] "Purchase conditions" are information that indicates the specific requirements and desires (price, functions, design, etc.) of the product that the user wishes to purchase.

[0445] A "suitable product" is a product that is determined to best meet the user's needs and satisfaction based on the user's purchasing conditions and emotional information.

[0446] "Additional conditions" is information that allows the user to add more detailed wishes or requirements after entering the initial conditions.

[0447] A "purchase procedure" is a series of operations and processes that a user performs to select a presented product and complete the purchase.

[0448] A "generative AI model" is an artificial intelligence model used to generate optimal product suggestions based on a user's purchasing conditions and emotional information.

[0449] A "database" is an information accumulation system that manages product information and attribute data and performs searches and updates as needed.

[0450] "Attribute data" is information about the characteristics and features (price, brand, performance, etc.) of each product.

[0451] This invention relates to a system that uses an emotion engine to analyze a user's emotions and recommend the most suitable products based on their purchasing criteria. This system reduces stress and anxiety, particularly when shopping online, and helps users select products that will give them high satisfaction. The operation of each component is described in detail below.

[0452] User behavior

[0453] The user installs the shopping assistant application on their smartphone and launches it. The user enters the conditions for the product they wish to purchase. For example, they can enter the following conditions:

[0454] Price: Under 20,000 yen

[0455] Category: Home appliances

[0456] Product: Cleaning robot

[0457] When entering text, the user's voice and facial expressions are simultaneously recorded and analyzed by the emotion engine.

[0458] Device behavior

[0459] The device receives the purchase conditions and emotion information entered by the user and generates a request to send the data to the server, which converts the data into an appropriate format (e.g., JSON) and communicates it to the server using an API.

[0460] Server Operation

[0461] The server receives the user's purchase conditions and emotion information sent from the device. The software used here includes a generative AI model (e.g., OpenAI's GPT-4) and an emotion analysis API (e.g., Microsoft Azure Cognitive Services' Emotion API). The server performs the following steps to suggest suitable products using the generative AI model:

[0462] 1. Analyze the received data and check the user's emotional state.

[0463] 2. Search the database based on the purchasing criteria to generate an initial shortlist.

[0464] 3. If the emotional information is determined to be "stressed," products that provide a sense of security (e.g., a highly rated cleaning robot) will be presented preferentially from the list.

[0465] Presenting Users and Receiving Additional Terms

[0466] The generated candidate list is sent back to the device in JSON format, and the results are presented to the user. The user can review the presented candidate list of products and enter more specific desired conditions (for example, "good design" or "specific functions"). After entering the additional conditions, the user presses the "Search Again" button to resubmit the conditions. At this time, the user's emotions are also recorded again.

[0467] Re-search and narrow down the servers

[0468] The server updates the candidate list based on the new condition and emotion information. If the emotion is analyzed as "satisfied," the suggested list will be very close to that condition. The updated candidate list is then sent back to the device and presented to the user.

[0469] Finalists and purchase process

[0470] Finally, the user selects the most suitable product from the presented options and completes the purchase process. When the user completes the purchase, the device sends the information to the server. The server then completes the purchase process based on the received information and records it in a database. After the purchase is complete, a confirmation email is sent to the user to notify them that the process has been completed.

[0471] Examples of specific examples and prompts

[0472] For example, if a user enters the following criteria:

[0473] Price: Under 20,000 yen

[0474] Category: Home appliances

[0475] Product: Cleaning robot

[0476] Emotional information: tension (analysis result)

[0477] The server inputs the following prompt sentence into the generative AI model:

[0478] First condition:

[0479] Price: Under 20,000 yen

[0480] Category: Home appliances

[0481] Product: Cleaning robot

[0482] Emotional information: nervous

[0483] This allows users to receive product suggestions that take into account their emotional state at the time.

[0484] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0485] Step 1:

[0486] The user launches the shopping assistant application on their smartphone and inputs the conditions for the product they wish to purchase (price, category, product name, etc.). During this process, the user's voice and facial expressions are simultaneously recorded. Input data (purchase conditions) and emotional information are generated and processed as input data.

[0487] Step 2:

[0488] The device receives the purchase conditions and recorded emotion information entered by the user, converts this data into an appropriate format such as JSON, and sends the converted data as an API request to the server, where the data is processed to transmit the purchase conditions and emotion information.

[0489] Step 3:

[0490] The server receives the purchase conditions and emotional information sent from the device. The server analyzes the received data and calls an emotion analysis API (e.g., Microsoft Azure Cognitive Services' Emotion API) to extract emotional information. The input data (purchase conditions and emotional information) is analyzed and emotional information (e.g., tension, anxiety, etc.) is extracted.

[0491] Step 4:

[0492] The server generates a list of product candidates using a generative AI model (e.g., OpenAI's GPT-4) based on the analyzed emotional information and purchasing conditions. At this stage, the model makes product suggestions based on the input data and generates suitable product candidates as output data in the form of a list.

[0493] Step 5:

[0494] The server converts the generated product candidate list into JSON format and returns it to the terminal. The terminal analyzes the received data and presents the product candidate list to the user. Here, data conversion and display on the user interface are performed.

[0495] Step 6:

[0496] The user checks the presented product candidate list and enters more specific desired conditions (design, specific functions, etc.). After entering the additional conditions, the user presses the "Search Again" button, and the data is sent again to the server via the terminal. The additional conditions are added as input data.

[0497] Step 7:

[0498] The server re-searches and narrows down the candidate list based on the newly received additional conditions and the re-analyzed emotional information. If the emotional information is analyzed as "satisfied," products that more closely match the user's conditions are listed. The re-generated product candidate list becomes the output data.

[0499] Step 8:

[0500] The server converts the updated candidate list into JSON format and resends it to the device. The device again parses the received data and presents the updated product candidate list to the user. Here, data conversion and display on the UI are also performed.

[0501] Step 9:

[0502] The user selects the desired product from the final candidate list and completes the purchase procedure. The selection data is sent to the server via the terminal. The final selected product and purchase information are provided as input data.

[0503] Step 10:

[0504] The server processes the purchase procedure based on the received selection data. The purchase information is recorded in a database and a purchase completion email is sent to the user. Here, the purchase process is executed and confirmation data is sent.

[0505] This allows users to receive product suggestions that take their emotions into consideration and make purchases with peace of mind.

[0506] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0507] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0508] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0509] [Second embodiment]

[0510] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0511] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0512] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0513] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0514] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0515] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0516] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0517] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0518] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0519] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0520] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0521] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0522] ---

[0523] The present invention relates to a system that proposes the selection of educational destinations based on the user's desired conditions, and in particular, describes a system that provides services as an educational destination concierge and a method for implementing the system.

[0524] First, this system consists of a server, a terminal, and a user. The user inputs their educational requirements, the server proposes suitable schools based on those requirements, and the terminal presents the results to the user. Below, we will explain the operation of each component in detail.

[0525] User Actions

[0526] The user starts the university entrance concierge application and inputs the conditions for the university they wish to attend. For example, they can input the following conditions:

[0527] Standard deviation: 60

[0528] Area: Tokyo

[0529] Club activities: Soccer

[0530] Post-graduation path: Employment

[0531] Budget: Under 3 million yen

[0532] After entering the information, the user presses the "Search" button to confirm the conditions.

[0533] Device behavior

[0534] The device receives the conditions entered by the user and sends them to the server, converting the data into the required format and communicating with the server using an API.

[0535] Server Operation

[0536] The server receives the user's requirements sent from the device and uses the generative AI model to search a database containing attribute data for each school (such as deviation score, area, club activities, post-graduation path, budget, and available qualifications), and generates an initial list of candidates based on this information.

[0537] The server returns the generated candidate list in JSON format to the terminal, presenting the user with potential schools.

[0538] Add user conditions and search again

[0539] The user checks the list of potential schools presented to them and enters more specific desired conditions (for example, "a good campus environment" or "the ability to obtain a specific qualification"). After entering the additional conditions, the user presses the "Search Again" button to resubmit the conditions.

[0540] Re-search and narrow down the servers

[0541] The server updates the candidate list based on the newly added criteria, generating a more refined list of candidates, and sends this updated candidate list back to the terminal for presentation to the user.

[0542] Finalist and booking process

[0543] Finally, the user selects the most suitable school from the presented options and completes the reservation procedure. When the user completes the reservation operation, the terminal sends the information to the server.

[0544] The server processes the reservation based on the received information and records it in the database. After the reservation is completed, the server sends a confirmation email to the user to notify them that the reservation has been completed.

[0545] Specific examples

[0546] For example, if a user enters the desired criteria of "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospect," the server will list multiple universities that fit this criteria. If the user then enters an additional criteria such as "a good campus environment," the server will further narrow down the candidates based on that criteria, generate a final list of suggestions, and support the user in making a reservation at the university of their choice.

[0547] The present invention allows users to easily find the best school to go to that meets their diverse needs, and reduces the anxiety and worries that come with selecting a school to go to.

[0548] The processing flow will be explained below.

[0549] ---

[0550] Step 1:

[0551] The user launches the university entrance concierge application.

[0552] Step 2:

[0553] The user inputs criteria for the school they wish to attend. For example, a deviation score of 60, living in Tokyo, playing soccer, getting a job, and a budget of 3 million yen or less.

[0554] Step 3:

[0555] The user presses the "Search" button to confirm the input conditions.

[0556] Step 4:

[0557] The terminal receives the user's input conditions and generates a request to send the data to the server.

[0558] Step 5:

[0559] The terminal sends the generated request to the server.

[0560] Step 6:

[0561] The server receives the request from the device and loads the generative AI model.

[0562] Step 7:

[0563] The server searches the database based on the user's criteria and generates a list of potential schools.

[0564] Step 8:

[0565] The server returns the generated list of potential schools to the device in JSON format.

[0566] Step 9:

[0567] The terminal analyzes the candidate list received from the server and prepares data for display on the user interface.

[0568] Step 10:

[0569] The device displays a list of potential schools to the user.

[0570] Step 11:

[0571] The user reviews the list of candidates and enters additional criteria, such as "good campus environment" or "ability to obtain specific qualifications."

[0572] Step 12:

[0573] After the user enters additional conditions, he or she presses the "Search Again" button.

[0574] Step 13:

[0575] The terminal receives the additional conditions and generates a request to transmit the data to the server.

[0576] Step 14:

[0577] The terminal sends the generated request to the server.

[0578] Step 15:

[0579] The server again receives the user's additional conditions and updates the existing candidate list using the generative AI model.

[0580] Step 16:

[0581] The server returns the updated list of potential schools to the device in JSON format.

[0582] Step 17:

[0583] The terminal analyzes the update list received from the server and displays it again on the user interface.

[0584] Step 18:

[0585] The user reviews the final school options and selects one.

[0586] Step 19:

[0587] The user presses a button to complete the reservation procedure for the selected school.

[0588] Step 20:

[0589] The terminal generates a request to transmit the selected information to the server.

[0590] Step 21:

[0591] The terminal sends the generated request to the server.

[0592] Step 22:

[0593] The server analyzes the received selection information and starts the reservation procedure.

[0594] Step 23:

[0595] The server completes the booking process and sends a confirmation email to the user.

[0596] Step 24:

[0597] The terminal receives a reservation completion notification from the server and displays it to the user.

[0598] Step 25:

[0599] Verify that the user receives a confirmation email.

[0600] ---

[0601] The above is the specific processing flow of the program, and the operations performed at each step have been explained in detail.

[0602] Example 1

[0603] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0604] When users have multiple requirements and preferences when selecting a school, it can be extremely difficult to find the right school on their own. Furthermore, the process can be time-consuming and difficult to obtain accurate information, which can increase stress. There is a need to solve these problems and enable users to quickly and accurately find the school that best suits them.

[0605] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0606] In this invention, the server includes means for allowing a user to input educational requirements, means for suggesting suitable educational destinations based on the input requirements, means for presenting the suggested educational destinations to the user and receiving additional requirements, means for narrowing down the list of educational destinations based on the additional requirements, means for completing a reservation procedure for the educational destination selected by the user, means for creating and updating a candidate list based on the educational requirements and additional requirements using a generative AI model, and means for recording the candidate list and final reservation information in a database and sending a confirmation by email. This allows users to quickly and accurately find the optimal educational destination based on various requirements for their educational destination selection.

[0607] A "user" is someone who inputs their educational requirements and uses the system to select the most suitable educational destination.

[0608] "Conditions for further education" refers to information entered by the user regarding their desired education, and specifically includes deviation score, area, club activities, career path after graduation, budget, etc.

[0609] "Means of suggestion" is a function in which the server lists and presents suitable schools based on the user's educational requirements.

[0610] "Additional conditions" refer to specific desired conditions that users enter after reviewing their initial list of potential schools, including the campus environment, available qualifications, etc.

[0611] The "narrowing down method" is a function that allows the server to update the list of potential schools based on new conditions added by the user, generating a more suitable list.

[0612] The "means of making reservations" is a function that confirms reservations at the school selected by the user and supports the process.

[0613] A "generative AI model" is an artificial intelligence model used to create and update a list of potential schools based on the school entry requirements and additional requirements.

[0614] A "database" is an information storage device managed by a server, and is responsible for storing various data, including attribute data on schools and user reservation information.

[0615] MODE FOR CARRYING OUT THE INVENTION

[0616] This invention relates to a system that suggests educational destinations based on the user's desired criteria, and in particular to a system that provides services as an educational destination concierge, and its implementation method. The system consists of a server, a terminal, and a user. The user inputs their educational destination criteria, the server suggests suitable educational destinations based on those criteria, and the terminal displays the results to the user.

[0617] User Actions

[0618] The user starts the university entrance concierge application and inputs the conditions for the university they wish to attend. For example, they can input the following conditions:

[0619] Standard deviation: 60

[0620] Area: Tokyo

[0621] Club activities: Soccer

[0622] Post-graduation path: Employment

[0623] Budget: Under 3 million yen

[0624] After entering the information, the user presses the "Search" button to confirm the conditions.

[0625] Device behavior

[0626] The device receives the conditions entered by the user and sends them to the server, where format conversion is performed and API is used to communicate with the server.

[0627] Server Operation

[0628] The server receives the user's requirements sent from the device. The server's backend contains a database linked to a generative AI model (e.g., GPT-4), which generates an initial candidate list based on the school's attribute data (standard deviation, area, club activities, post-graduation career path, budget, etc.). The generated candidate list is returned to the device in JSON format, and the user is presented with potential schools.

[0629] Add user conditions and search again

[0630] The user checks the list of potential schools presented to them and enters more specific desired conditions, such as "a good campus environment" or "the ability to obtain a specific qualification." After entering the additional conditions, the user clicks the "Search Again" button and resubmits the conditions.

[0631] Re-search and narrow down the servers

[0632] The server updates the candidate list based on the newly added criteria, generating a more refined list, and then sends the updated candidate list back to the terminal and presents it to the user.

[0633] Finalist and booking process

[0634] Finally, the user selects the most suitable school from the presented options and completes the reservation procedure. When the user completes the reservation operation, the terminal sends the information to the server. The server records the received reservation information in a database and sends the user a confirmation email that the reservation has been completed.

[0635] Specific examples

[0636] For example, if a user enters the desired criteria as "a university in Tokyo with a deviation score of 60, a soccer club, and a strong employment prospect," the process will be as follows:

[0637] 1. The user launches the application, enters the criteria for further education, and presses the search button.

[0638] 2. The device sends the conditions to the server.

[0639] 3. The server lists the universities that match the criteria and generates a candidate list.

[0640] 4. The user enters additional criteria such as "good campus environment" and presses the search again button.

[0641] 5. The server further refines the criteria and generates a final list of suggestions.

[0642] 6. The user selects the most suitable university and completes the reservation process.

[0643] 7. The server completes the booking process and sends a confirmation email.

[0644] Prompt Sentence Examples

[0645] The user entered "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospect" as their desired criteria. Furthermore, they entered "a good campus environment" as an additional condition. Please make a list of universities that meet these criteria and present it to the user.

[0646] The present invention allows users to easily find the best school to go to that meets their diverse needs, and reduces the anxiety and worries that come with selecting a school to go to.

[0647] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0648] Specific processing steps of the program

[0649] Step 1:

[0650] The user launches the university entrance concierge application and inputs the conditions for the university they wish to attend (e.g., deviation score, area, club activities, career path after graduation, budget, etc.). The conditions entered are temporarily saved as local data on the device. The user ID is also added to the input data, making it possible to identify the user in later processes.

[0651] Step 2:

[0652] The device converts the conditions for continuing education entered by the user into JSON format and sends it to the server using an HTTP POST request. At this time, all input data, including the user ID, is sent as parameters. Input data: conditions for continuing education, user ID. Output data: request to send to the server.

[0653] Step 3:

[0654] The server receives the user's conditions sent from the device and searches the database using a generative AI model (e.g., GPT-4). The database stores attribute data for each school (standard deviation, area, club activities, post-graduation career path, budget, etc.). The AI ​​model generates an initial list of candidates based on the entered conditions. Input data: School conditions in JSON format. Output data: Initial list of candidates.

[0655] Step 4:

[0656] The server converts the generated candidate list into JSON format and sends it to the terminal as an HTTP response. Input data: Initial candidate list. Output data: Send request to the terminal.

[0657] Step 5:

[0658] The terminal displays the received candidate list on the screen and presents it to the user. The user checks this list and enters more specific desired conditions (additional conditions). Input data: candidate list from the server. Output data: screen display.

[0659] Step 6:

[0660] The user checks the displayed list of potential schools and inputs additional conditions. For example, "the campus environment is good" or "a specific qualification can be obtained." Input data: Additional conditions. Output data: Notification of input completion to the terminal.

[0661] Step 7:

[0662] The terminal converts the data into JSON format again based on the additional conditions entered by the user and resends it to the server using an HTTP POST request. Input data: Additional conditions. Output data: Retransmission request to the server.

[0663] Step 8:

[0664] The server uses the generative AI model to narrow down the candidate list based on the additional criteria received again, generating an updated candidate list. It then re-queries the database to identify schools that meet the new criteria. Input data: Additional criteria. Output data: Updated candidate list.

[0665] Step 9:

[0666] The server converts the updated candidate list into JSON format and resends it to the terminal as an HTTP response. Input data: Updated candidate list. Output data: Send request to the terminal.

[0667] Step 10:

[0668] The terminal displays the narrowed candidate list on the screen again and presents it to the user. Input data: Updated candidate list from the server. Output data: Screen display.

[0669] Step 11:

[0670] The user selects the most suitable school from the presented options and presses the "Reserve" button to complete the reservation procedure. Input data: Selected school. Output data: Notification of input completion to the terminal.

[0671] Step 12:

[0672] The terminal converts the user's reservation information into JSON format and sends it to the server using an HTTP POST request. Input data: reservation information. Output data: request to send to the server.

[0673] Step 13:

[0674] The server records the received reservation information in a database, confirms the reservation, and sends a confirmation email to the user. Input data: Reservation information. Output data: Recorded in the database, sending a confirmation email.

[0675] By following the steps above, users can use this system to easily find the best school to go to that meets their diverse needs, reducing the anxiety and worries they may have when choosing a school to go to.

[0676] (Application example 1)

[0677] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0678] Conventional university selection systems only allow users to view information about proposed universities based on the criteria they enter in a list format, making it difficult to visually experience the actual campus and surrounding area. Furthermore, each time additional criteria are entered, users must re-filter, making the university selection process cumbersome. Furthermore, a separate reservation procedure is required, placing a significant burden on users. To solve these issues, a system is needed that allows users to select universities in a visual, interactive way and complete the reservation procedure simply and efficiently.

[0679] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0680] In this invention, the server includes means for allowing a user to input educational requirements, means for suggesting suitable destinations based on the input requirements, means for presenting the suggested destinations to the user and receiving additional requirements, means for narrowing down the destinations based on the additional requirements, means for completing a reservation procedure for the destination selected by the user, means for providing a virtual environment for the user to search for destinations in a virtual space, and means for displaying destination information based on the educational requirements as a 3D model in the virtual space. This allows the user to interactively narrow down the requirements while visually checking the destination environment and simplifies the reservation procedure, thereby reducing the burden of selecting a destination.

[0681] The "means for the user to input conditions for further education" refers to a device or method that provides an interface for the user to input desired conditions for further education into the system.

[0682] "Means for suggesting suitable educational destinations based on the input conditions" refers to a device or method that has the function of selecting and suggesting the most suitable educational destination based on the conditions input by the user.

[0683] "Means for presenting the proposed school candidates to the user and receiving additional conditions" refers to a device or method by which the system displays the proposed school candidates to the user and the user re-enters more detailed additional conditions.

[0684] The "means for narrowing down the candidate schools based on the additional conditions" refers to a device or method for further narrowing down the candidate schools based on the additional conditions newly input by the user.

[0685] The "means for making reservations for the school selected by the user" refers to a device or method that has the function of making reservations or applications for the school selected by the user.

[0686] "Means for providing a virtual environment for users to explore potential schools in a virtual space" refers to devices or methods that allow users to visually experience the campus and surrounding environment of their potential schools in a virtual reality space.

[0687] "Means for displaying information on schools based on the conditions for furthering education in a virtual space using a 3D model" refers to a device or method for displaying information on schools that meet the user's conditions for furthering education in a virtual reality space using a three-dimensional model.

[0688] MODE FOR CARRYING OUT THE INVENTION

[0689] This invention relates to a system that provides a virtual environment for users to use when searching for schools and supports their selection and reservation of schools. In particular, it provides a mechanism for suggesting school candidates using a generative AI model and interactively narrowing down the options.

[0690] System configuration

[0691] The system consists of the following main components:

[0692] 1. User device: smartphone, head-mounted display (HMD), etc.

[0693] 2. Server: Stores the generative AI model and the database of schools to go to, and processes data.

[0694] 3. 3D modeling tools: Tools for building virtual environments. Example: Blender.

[0695] 4. Game engine: Software for displaying virtual spaces. Example: Unity.

[0696] 5. Speech Recognition API: Used to receive additional conditions from the user. Example: Google Cloud Speech-to-Text.

[0697] System Operation

[0698] 1. User Action:

[0699] The user launches the university entrance concierge application using a smartphone or head-mounted display. The application provides a form for the user to enter university entrance criteria such as deviation score, area, club activities, post-graduation career path, and budget. The user enters these criteria and begins the search.

[0700] 2. Device behavior:

[0701] The user device converts the entered educational requirements into JSON format and sends it to the server via a RESTful API. While waiting for a response from the server, the device prepares to load the virtual space.

[0702] 3. Server Operation:

[0703] The server uses the generative AI model to search a database of schools based on the received conditions for further education. This database contains attribute data for each school (such as deviation score, area, club activities, post-graduation career path, budget, and available qualifications). The server returns the search results in JSON format to the user's device.

[0704] 4. Providing a virtual space:

[0705] The user device uses Unity to display 3D models in a virtual environment based on the data of potential schools received from the server, and the user can use a head-mounted display to walk around and visually check the virtual campus.

[0706] 5. Enter additional criteria and search again:

[0707] While exploring the virtual campus, users can add more specific preferences. For example, they can use a voice recognition API to input additional criteria such as "a good campus environment" or "the ability to obtain a specific qualification." These additional criteria are sent back to the server, which then performs a new search based on the new criteria and narrows down the candidates.

[0708] 6. Finalist and booking process:

[0709] The narrowed down list of candidates is displayed again on the user's device, and the user can select the most suitable school. After completing the selection, the user completes the reservation procedure, and the device sends the reservation information to the server. The server confirms the completion of the reservation procedure and sends a confirmation email to the user.

[0710] Specific examples

[0711] For example, if a user enters their desired criteria as "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospects," the server will generate a list of suitable universities based on this. If the user then voice-inputs additional criteria, such as "a good campus environment," in the virtual environment, the server will further narrow down the candidates based on the criteria, generating a final list of suggestions and presenting it to the user. The user can then select the most suitable university and complete the reservation process easily within the virtual space.

[0712] Prompt Sentence Examples

[0713] "Please limit your search to Tokyo as the area where you plan to study."

[0714] "Please show me schools that have soccer teams."

[0715] "Please tell me which university I would like to attend that has a good campus environment."

[0716] Based on the prompts described above, the system presents potential schools that specifically reflect the user's desired conditions, allowing the user to easily find a school that satisfies them.

[0717] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0718] Step 1:

[0719] User's entry of educational requirements

[0720] Users launch the university entrance concierge application using a smartphone or head-mounted display and enter information about university entrance requirements such as deviation score, area, club activities, career path after graduation, and budget.

[0721] Input: User's desired academic conditions (e.g., deviation score 60, area: Tokyo, club activity: soccer, career path after graduation: employment, budget: within 3 million yen)

[0722] Output: Data on academic qualifications (JSON format)

[0723] Step 2:

[0724] Sending admission conditions from the device to the server

[0725] The terminal converts the entered conditions for further education into JSON format and sends it to the server via a RESTful API.

[0726] Input: JSON format data on academic requirements

[0727] Output: Request to send admission requirements to the server

[0728] Step 3:

[0729] Server-based suggestions for potential schools

[0730] The server uses the generative AI model to search a database of schools based on the received school conditions, thereby generating a list of school candidates that meet the user's conditions.

[0731] Input: Admission requirements data

[0732] Output: A list of suitable schools (JSON format)

[0733] Step 4:

[0734] Loading the virtual world on your device

[0735] The device uses Unity to display 3D models of potential schools in a virtual environment based on the data received from the server, and users can use a head-mounted display to walk around the virtual campus and visually confirm their experiences.

[0736] Input: Data on potential schools (JSON format)

[0737] Output: 3D model display in virtual space

[0738] Step 5:

[0739] User-entered additional conditions

[0740] While exploring the virtual campus, users can input more specific requirements (e.g., a good campus environment, the ability to obtain specific qualifications) using a voice recognition API.

[0741] Input: Voice input of additional conditions

[0742] Output: Additional condition data in text format

[0743] Step 6:

[0744] Resend additional condition data to the server

[0745] The device converts the additional condition data, which has been converted into text using the voice recognition API, back into JSON format and sends it to the server.

[0746] Input: Additional condition data in text format

[0747] Output: Request to send additional condition data to the server

[0748] Step 7:

[0749] Server-based re-search and refinement of potential schools

[0750] The server receives the additional condition data, searches the list of potential schools again based on the new conditions, and generates a further narrowed list.

[0751] Enter: Additional condition data

[0752] Output: A list of narrowed-down school candidates (JSON format)

[0753] Step 8:

[0754] Presentation and selection of the final candidate list

[0755] The terminal then presents the narrowed down list of potential schools received from the server to the user, who then selects the most suitable school.

[0756] Input: A list of narrowed-down school candidates (JSON format)

[0757] Output: User's chosen educational destination

[0758] Step 9:

[0759] Completing the reservation process

[0760] The user completes the reservation procedure for the selected school. The device sends the selection information to the server, which then completes the reservation procedure and sends a confirmation email to the user.

[0761] Input: User's selected school and reservation information

[0762] Output: Confirmation email of reservation completion

[0763] As described above, the present invention can provide a system that provides interactive and visual support for everything from selecting a school to completing the reservation procedures.

[0764] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0765] ---

[0766] This invention relates to a system that suggests educational destinations based on the user's wishes and emotions, and in particular to a system that provides a service as an educational destination concierge by combining an emotion engine, and a method for implementing the system.

[0767] First, this system consists of a server, a terminal, and a user, and also incorporates an emotion engine that recognizes the user's emotions. The user inputs their educational requirements, and the emotion engine analyzes their voice and facial expressions when they input them. The server then suggests suitable educational destinations based on the requirements and emotional information, and the terminal presents the results to the user. The operation of each component is described in detail below.

[0768] User Actions

[0769] The user starts the university entrance concierge application and inputs the conditions for the university they wish to attend. For example, they can input the following conditions:

[0770] Standard deviation: 60

[0771] Area: Tokyo

[0772] Club activities: Soccer

[0773] Post-graduation path: Employment

[0774] Budget: Under 3 million yen

[0775] When inputting, the user's voice and facial expressions are simultaneously recorded and analyzed by the emotion engine.

[0776] Device behavior

[0777] The device receives the conditions and emotion information entered by the user and generates a request to send the data to the server, converting the data into the required format and communicating with the server using an API.

[0778] Server Operation

[0779] The server receives the user's conditions and emotion information sent from the device and loads the generative AI model. It also takes into account the emotion analysis results provided by the emotion engine. The server searches the database based on the user's conditions and emotions and generates a list of potential schools.

[0780] If the emotional information is determined to be "nervous" or "anxious," the server will prioritize the schools in the list that will increase the user's sense of security (e.g., schools that are good for finding employment).

[0781] The generated candidate list is returned in JSON format to the terminal, and the results are presented to the user.

[0782] Add user conditions and search again

[0783] The user checks the list of potential schools presented to them and enters more specific desired conditions (for example, "a good campus environment" or "the ability to obtain a specific qualification"). After entering the additional conditions, the user presses the "Search Again" button and resubmits the conditions. At this time, the user's emotions are also recorded again.

[0784] Re-search and narrow down the servers

[0785] The server updates the candidate list based on the newly added conditions and emotion information. If the emotion is analyzed as "satisfied," the suggested list will be very close to that condition. The updated candidate list is then sent to the device again and presented to the user.

[0786] Finalist and booking process

[0787] Finally, the user selects the most suitable school from the presented options and completes the reservation procedure. When the user completes the reservation operation, the terminal sends the information to the server.

[0788] The server processes the reservation based on the received information and records it in the database. After the reservation is completed, the server sends a confirmation email to the user to notify them that the reservation has been completed.

[0789] Specific examples

[0790] For example, if a user enters their desired criteria as "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospects," and the emotion engine analyzes this as "I feel nervous," the server will prioritize universities that the user feels comfortable with in the initial candidate list. If the user then enters an additional criterion such as "a good campus environment" and the emotion is analyzed as "I feel comfortable," the server will further narrow down the candidate list based on this criteria and generate results that give the user a sense of security. The user can then smoothly complete the reservation process for the university they ultimately selected.

[0791] The present invention allows users to easily find the most suitable school to attend that takes into consideration not only their diverse needs but also their emotional information, further reducing the anxiety and worries that come with selecting a school to attend.

[0792] The processing flow will be explained below.

[0793] ---

[0794] Step 1:

[0795] The user launches the university entrance concierge application.

[0796] Step 2:

[0797] The user inputs the conditions for the school they wish to attend. For example, they can input the following conditions: deviation score 60, Tokyo, soccer club, employment, budget within 3 million yen.

[0798] Step 3:

[0799] When the user inputs a condition, the device records the user's voice and facial expressions, and sends this information to the emotion engine.

[0800] Step 4:

[0801] The emotion engine analyzes the user's voice and facial expression data to determine the user's emotions (e.g., "nervous" or "anxious").

[0802] Step 5:

[0803] The terminal generates a request to transmit the conditions for further education input by the user and the emotion information from the emotion engine together to the server.

[0804] Step 6:

[0805] The terminal sends the generated request to the server.

[0806] Step 7:

[0807] The server receives the user's educational requirements and emotional information sent from the device and reads the analysis results of the generative AI model and emotion engine.

[0808] Step 8:

[0809] The server searches the database based on the user's conditions and emotions to generate a list of potential schools. If the emotional information is determined to be "nervous," the server will prioritize suggesting schools that provide a sense of security, such as those with a strong job prospect.

[0810] Step 9:

[0811] The server returns the generated list of potential schools to the device in JSON format.

[0812] Step 10:

[0813] The terminal analyzes the candidate list received from the server and prepares data for display on the user interface.

[0814] Step 11:

[0815] The device displays a list of potential schools to the user.

[0816] Step 12:

[0817] The user reviews the list of candidates and enters additional criteria, such as "a good campus environment" or "the ability to obtain a specific qualification."

[0818] Step 13:

[0819] After the user enters additional conditions, they press the "Search Again" button, at which point the device again records the user's voice and facial expressions and sends them to the emotion engine.

[0820] Step 14:

[0821] The emotion engine again analyzes the user's voice and facial expression data to determine an updated emotion (e.g., "I feel relieved").

[0822] Step 15:

[0823] The terminal generates a request to transmit the added educational advancement conditions and new emotion information from the emotion engine together to the server.

[0824] Step 16:

[0825] The terminal sends the generated request to the server.

[0826] Step 17:

[0827] The server receives the user's additional conditions and emotion information again, updates the existing candidate list using the generative AI model, and makes suggestions that take the additional conditions into account based on the emotion information.

[0828] Step 18:

[0829] The server returns the updated list of potential schools to the device in JSON format.

[0830] Step 19:

[0831] The terminal again analyzes the updated list received from the server and displays it again on the user interface.

[0832] Step 20:

[0833] The user reviews the final school options and selects one.

[0834] Step 21:

[0835] The user presses a button to complete the reservation procedure for the selected school.

[0836] Step 22:

[0837] The terminal generates a request to transmit the selected information to the server.

[0838] Step 23:

[0839] The terminal sends the generated request to the server.

[0840] Step 24:

[0841] The server analyzes the received selection information and starts the reservation procedure.

[0842] Step 25:

[0843] The server completes the booking process and sends a confirmation email to the user.

[0844] Step 26:

[0845] The terminal receives a reservation completion notification from the server and displays it to the user.

[0846] Step 27:

[0847] Verify that the user receives a confirmation email.

[0848] ---

[0849] The above is the specific processing flow of the system that combines the emotion engine. The operations performed at each step have been explained in detail.

[0850] Example 2

[0851] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0852] Conventional university selection systems suggest schools based on the desired conditions entered by the user, but they are unable to take the user's emotional state into consideration, which means they are unable to fully provide the most suitable school for the user.In order to reduce users' anxiety and stress and make more personalized suggestions, it is necessary to suggest schools based on emotional information.

[0853] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for inputting educational conditions from the user, means for proposing suitable educational destinations based on the input conditions and the user's emotional information, means for presenting the proposed educational destination candidates to the user and receiving additional conditions and the user's emotional information, means for narrowing down the educational destination candidates based on the additional conditions and the user's emotional information, and means for completing the reservation procedure for the educational destination selected by the user. This makes it possible to propose optimal educational destinations taking the user's emotional state into consideration, reducing the user's anxiety and stress and enabling a more satisfying educational destination selection.

[0854] "Conditions for further education" refers to the criteria and requirements for the school the user wishes to attend. Examples include deviation score, area, club activities, career path after graduation, budget, etc.

[0855] "Emotional information" refers to data that analyzes the user's emotional state at the time of input and converts it into numerical or categorized data. Examples include states such as "tense" or "relieved."

[0856] "School to be attended" refers to the educational institution to which the user wishes to attend, including university, high school, vocational school, etc.

[0857] "Suggestion" means that the system presents the most suitable educational destination based on the user's educational requirements and emotional information.

[0858] "Additional conditions" are more specific desired conditions that are entered later in addition to the conditions for entering the university that the user initially entered. Examples include "a good campus environment" and "the ability to obtain a specific qualification."

[0859] The "reservation procedure" refers to the process by which a user formally applies for and enrols at the school of their choice.

[0860] A "generative AI model" is a model that uses artificial intelligence technology to analyze educational conditions and emotional information to suggest the most suitable educational destination for users.

[0861] A "database" is a data structure that manages various data related to the school of choice (attribute data, evaluation data, etc.) and is used for system searches and analysis.

[0862] MODE FOR CARRYING OUT THE INVENTION

[0863] This invention is a system for suggesting the selection of a school to attend based on the user's desired conditions and emotional information, and in particular, it combines an emotional engine to provide the user with the most suitable school. This system is composed of a server, a terminal, and a user, and uses the emotional engine to analyze the user's emotional state.

[0864] System configuration

[0865] The system uses the following hardware and software:

[0866] Terminal: A device that allows users to enter their educational requirements. Examples include computers and smartphones.

[0867] Server: A computer that analyzes the user's educational requirements and emotional information, and lists suitable schools. Example: Cloud services (AWS EC2, etc.).

[0868] Emotion engine: Technology for analyzing emotions from the user's voice and facial expressions. Example: Microsoft Azure Emotion API.

[0869] Generative AI model: An artificial intelligence technology that suggests the most suitable school to attend based on the user's educational requirements and emotional information. Example: GPT-4 (OpenAI).

[0870] Operating procedure

[0871] 1. The user enters their desired criteria for the school they wish to attend through the university entrance concierge app. For example, possible criteria include "standard deviation score 60," "area in Tokyo," "has a soccer club," and "budget within 3 million yen."

[0872] Example prompt sentence:

[0873] My desired conditions are a university in Tokyo with a deviation score of 60. I would like a place with a soccer club and a good job placement program. I'm a little nervous about my emotional situation.

[0874] 2. At the same time, the user's voice and facial expressions are recorded, and emotional information such as "nervous" or "relieved" is analyzed by the emotion engine.

[0875] 3. The device formats the input desired conditions and emotional information into JSON format and sends it to the server using an API.

[0876] 4. The server receives and analyzes the data sent from the device. Specifically, it uses a generative AI model based on the user's conditions and emotional information to generate an optimal list of potential schools.

[0877] At this time, attribute data for the school of choice is obtained from the database, and a list of candidates is generated based on the analysis results.

[0878] 5. The server returns the generated list of potential schools to the terminal, which presents the list to the user.

[0879] 6. The user can review the list of candidates presented and re-enter their search criteria with more specific details. By pressing the search again button, the data will be sent to the server again.

[0880] Example prompt sentence:

[0881] I also hope that the campus environment will be good and that I will be able to obtain certain qualifications.

[0882] 7. The server updates the list of potential schools again based on the additional desired conditions and the latest emotional information, and sends it to the terminal again.

[0883] 8. Finally, the user selects the most suitable school from the suggestions and completes the reservation procedure. Once the reservation is completed, the device sends the information to the server, which then completes the reservation procedure. Once the reservation is complete, a confirmation email is sent to the user.

[0884] Specific examples

[0885] For example, if a user enters their desired criteria as "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospects," and the emotion engine analyzes this as "I'm nervous," the server will prioritize universities that give them a sense of security in the initial candidate list. If the user then enters an additional criterion, such as "a good campus environment," and the emotion is analyzed as "I'm secure," the server will further narrow down the candidate list based on the new criteria and present it again. In this way, the user can select the most suitable university and proceed with the reservation process.

[0886] As described above, the present invention realizes optimal proposals for further education that take into consideration the user's desired conditions and emotional information, and provides a highly satisfying selection of further education while reducing the user's anxiety and stress.

[0887] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0888] Step 1:

[0889] Users simply launch the university entrance concierge app and input their desired criteria for the university they wish to attend. For example, they can input criteria such as "standard deviation score 60," "area Tokyo," "has a soccer club," and "budget within 3 million yen." As they input their information, the user's voice and facial expressions are simultaneously recorded and analyzed by the emotion engine.

[0890] Input: Conditions for entering university (standard score, area, club activities, budget, etc.), user's voice and facial expressions

[0891] Output: Data on conditions for continuing education, emotional information data

[0892] Specific operation: The user fills in the application's input form with their admission requirements and clicks the "Submit" button. The device's camera and microphone record the user's voice and facial expressions.

[0893] Step 2:

[0894] The device receives the conditions and emotion information entered by the user and generates a request to send the data to the server. During this process, the device converts the data into the required format (e.g., JSON format) and communicates with the server using an API.

[0895] Input: Data on conditions for continuing education, emotional information data

[0896] Output: API request in JSON format

[0897] Specific behavior: Converts input data into a JSON structure and executes an HTTP request to an API endpoint.

[0898] Step 3:

[0899] The server receives the data sent from the device, loads the generative AI model based on the received data, analyzes the user's conditions, and also takes into account the analysis results from the emotion engine.

[0900] Input: JSON format data on academic requirements and emotional information

[0901] Output: Analysis results

[0902] Specific operation: Analyzes JSON data and uses a generative AI model to analyze the user's desired conditions and emotional information, taking into account the results of the emotion engine.

[0903] Step 4:

[0904] The server generates a list of potential schools based on the analysis results. The priority of the list is adjusted according to the user's conditions and emotional information. For example, if the emotional information is determined to be "nervous," the server will prioritize schools that give a sense of security.

[0905] Input: Analysis results (desired conditions, emotional information)

[0906] Output: List of potential schools

[0907] Specific operation: Searches the database for attribute data of the school of choice, adjusts priorities using a generative AI model, and generates a list of candidates. The final list is compiled in JSON format.

[0908] Step 5:

[0909] The device receives the list of potential schools sent from the server and presents it to the user. The user can review the list and add more specific desired conditions. When the user presses the "Search Again" button, the conditions and emotional information are sent again from the device to the server.

[0910] Input: List of potential schools

[0911] Output: Additional preference, updated emotion information

[0912] Specific behavior: Display the candidate list to the user and provide a field for inputting additional desired conditions. Process the click event of the search again button and send new data to the server.

[0913] Step 6:

[0914] The server then updates the list of potential schools based on the additional conditions and the latest emotional information. It receives the data for the re-search, analyzes it again using the generative AI model, and generates a list of potential schools.

[0915] Input: Additional desired conditions, updated emotional information

[0916] Output: Updated school candidate list

[0917] Specific operation: Search the database again based on the new criteria, update the candidate list using the generative AI model, and return the new candidate list in JSON format to the device.

[0918] Step 7:

[0919] The user selects the most suitable school from the presented final candidate list. When the user completes the reservation procedure, the device sends the information to the server. The server then executes the reservation procedure based on the received information and sends a confirmation email to the user.

[0920] Input: Final candidate list, selected destination

[0921] Output: Notification of completion of reservation procedure

[0922] Specific operation: The user selects the school they wish to attend and clicks the reservation button. The reservation information is sent to the server, which then completes the reservation procedure. A confirmation email is sent to the user.

[0923] (Application example 2)

[0924] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0925] Conventional online shopping systems have been unable to take into account the emotional stress and anxiety that users face when selecting products. As a result, there have been cases where users are unable to choose the right product, resulting in a decrease in satisfaction. To solve this problem, a product suggestion system that takes users' emotions into account is required.

[0926] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's emotional information using an emotion engine and receiving purchase conditions from the user, means for proposing suitable products based on the input conditions and the analyzed emotional information, and means for presenting the proposed product candidates to the user and receiving additional conditions. This makes it possible to propose optimal products that take the user's emotions into consideration.

[0927] The "emotion engine" is a technology that analyzes the user's voice and facial expressions to extract emotional information in real time.

[0928] "Purchase conditions" are information that indicates the specific requirements and desires (price, functions, design, etc.) of the product that the user wishes to purchase.

[0929] A "suitable product" is a product that is determined to best meet the user's needs and satisfaction based on the user's purchasing conditions and emotional information.

[0930] "Additional conditions" is information that allows the user to add more detailed wishes or requirements after entering the initial conditions.

[0931] A "purchase procedure" is a series of operations and processes that a user performs to select a presented product and complete the purchase.

[0932] A "generative AI model" is an artificial intelligence model used to generate optimal product suggestions based on a user's purchasing conditions and emotional information.

[0933] A "database" is an information accumulation system that manages product information and attribute data and performs searches and updates as needed.

[0934] "Attribute data" is information about the characteristics and features (price, brand, performance, etc.) of each product.

[0935] This invention relates to a system that uses an emotion engine to analyze a user's emotions and recommend the most suitable products based on their purchasing criteria. This system reduces stress and anxiety, particularly when shopping online, and helps users select products that will give them high satisfaction. The operation of each component is described in detail below.

[0936] User behavior

[0937] The user installs the shopping assistant application on their smartphone and launches it. The user enters the conditions for the product they wish to purchase. For example, they can enter the following conditions:

[0938] Price: Under 20,000 yen

[0939] Category: Home appliances

[0940] Product: Cleaning robot

[0941] When entering text, the user's voice and facial expressions are simultaneously recorded and analyzed by the emotion engine.

[0942] Device behavior

[0943] The device receives the purchase conditions and emotion information entered by the user and generates a request to send the data to the server, which converts the data into an appropriate format (e.g., JSON) and communicates it to the server using an API.

[0944] Server Operation

[0945] The server receives the user's purchase conditions and emotion information sent from the device. The software used here includes a generative AI model (e.g., OpenAI's GPT-4) and an emotion analysis API (e.g., Microsoft Azure Cognitive Services' Emotion API). The server performs the following steps to suggest suitable products using the generative AI model:

[0946] 1. Analyze the received data and check the user's emotional state.

[0947] 2. Search the database based on the purchasing criteria to generate an initial shortlist.

[0948] 3. If the emotional information is determined to be "stressed," products that provide a sense of security (e.g., a highly rated cleaning robot) will be presented preferentially from the list.

[0949] Presenting Users and Receiving Additional Terms

[0950] The generated candidate list is sent back to the device in JSON format, and the results are presented to the user. The user can review the presented candidate list of products and enter more specific desired conditions (for example, "good design" or "specific functions"). After entering the additional conditions, the user presses the "Search Again" button to resubmit the conditions. At this time, the user's emotions are also recorded again.

[0951] Re-search and narrow down the servers

[0952] The server updates the candidate list based on the new condition and emotion information. If the emotion is analyzed as "satisfied," the suggested list will be very close to that condition. The updated candidate list is then sent back to the device and presented to the user.

[0953] Finalists and purchase process

[0954] Finally, the user selects the most suitable product from the presented options and completes the purchase process. When the user completes the purchase, the device sends the information to the server. The server then completes the purchase process based on the received information and records it in a database. After the purchase is complete, a confirmation email is sent to the user to notify them that the process has been completed.

[0955] Examples of specific examples and prompts

[0956] For example, if a user enters the following criteria:

[0957] Price: Under 20,000 yen

[0958] Category: Home appliances

[0959] Product: Cleaning robot

[0960] Emotional information: tension (analysis result)

[0961] The server inputs the following prompt sentence into the generative AI model:

[0962] First condition:

[0963] Price: Under 20,000 yen

[0964] Category: Home appliances

[0965] Product: Cleaning robot

[0966] Emotional information: nervous

[0967] This allows users to receive product suggestions that take into account their emotional state at the time.

[0968] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0969] Step 1:

[0970] The user launches the shopping assistant application on their smartphone and inputs the conditions for the product they wish to purchase (price, category, product name, etc.). During this process, the user's voice and facial expressions are simultaneously recorded. Input data (purchase conditions) and emotional information are generated and processed as input data.

[0971] Step 2:

[0972] The device receives the purchase conditions and recorded emotion information entered by the user, converts this data into an appropriate format such as JSON, and sends the converted data as an API request to the server, where the data is processed to transmit the purchase conditions and emotion information.

[0973] Step 3:

[0974] The server receives the purchase conditions and emotional information sent from the device. The server analyzes the received data and calls an emotion analysis API (e.g., Microsoft Azure Cognitive Services' Emotion API) to extract emotional information. The input data (purchase conditions and emotional information) is analyzed and emotional information (e.g., tension, anxiety, etc.) is extracted.

[0975] Step 4:

[0976] The server generates a list of product candidates using a generative AI model (e.g., OpenAI's GPT-4) based on the analyzed emotional information and purchasing conditions. At this stage, the model makes product suggestions based on the input data and generates suitable product candidates as output data in the form of a list.

[0977] Step 5:

[0978] The server converts the generated product candidate list into JSON format and returns it to the terminal. The terminal analyzes the received data and presents the product candidate list to the user. Here, data conversion and display on the user interface are performed.

[0979] Step 6:

[0980] The user checks the presented product candidate list and enters more specific desired conditions (design, specific functions, etc.). After entering the additional conditions, the user presses the "Search Again" button, and the data is sent again to the server via the terminal. The additional conditions are added as input data.

[0981] Step 7:

[0982] The server re-searches and narrows down the candidate list based on the newly received additional conditions and the re-analyzed emotional information. If the emotional information is analyzed as "satisfied," products that more closely match the user's conditions are listed. The re-generated product candidate list becomes the output data.

[0983] Step 8:

[0984] The server converts the updated candidate list into JSON format and resends it to the device. The device again parses the received data and presents the updated product candidate list to the user. Here, data conversion and display on the UI are also performed.

[0985] Step 9:

[0986] The user selects the desired product from the final candidate list and completes the purchase procedure. The selection data is sent to the server via the terminal. The final selected product and purchase information are provided as input data.

[0987] Step 10:

[0988] The server processes the purchase procedure based on the received selection data. The purchase information is recorded in a database and a purchase completion email is sent to the user. Here, the purchase process is executed and confirmation data is sent.

[0989] This allows users to receive product suggestions that take their emotions into consideration and make purchases with peace of mind.

[0990] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0991] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0992] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0993] [Third embodiment]

[0994] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0995] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0996] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0997] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0998] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0999] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1000] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1001] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1002] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1003] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1004] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1005] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1006] ---

[1007] The present invention relates to a system that proposes the selection of educational destinations based on the user's desired conditions, and in particular, describes a system that provides services as an educational destination concierge and a method for implementing the system.

[1008] First, this system consists of a server, a terminal, and a user. The user inputs their educational requirements, the server proposes suitable schools based on those requirements, and the terminal presents the results to the user. Below, we will explain the operation of each component in detail.

[1009] User Actions

[1010] The user starts the university entrance concierge application and inputs the conditions for the university they wish to attend. For example, they can input the following conditions:

[1011] Standard deviation: 60

[1012] Area: Tokyo

[1013] Club activities: Soccer

[1014] Post-graduation path: Employment

[1015] Budget: Under 3 million yen

[1016] After entering the information, the user presses the "Search" button to confirm the conditions.

[1017] Device behavior

[1018] The device receives the conditions entered by the user and sends them to the server, converting the data into the required format and communicating with the server using an API.

[1019] Server Operation

[1020] The server receives the user's requirements sent from the device and uses the generative AI model to search a database containing attribute data for each school (such as deviation score, area, club activities, post-graduation path, budget, and available qualifications), and generates an initial list of candidates based on this information.

[1021] The server returns the generated candidate list in JSON format to the terminal, presenting the user with potential schools.

[1022] Add user conditions and search again

[1023] The user checks the list of potential schools presented to them and enters more specific desired conditions (for example, "a good campus environment" or "the ability to obtain a specific qualification"). After entering the additional conditions, the user presses the "Search Again" button to resubmit the conditions.

[1024] Re-search and narrow down the servers

[1025] The server updates the candidate list based on the newly added criteria, generating a more refined list of candidates, and sends this updated candidate list back to the terminal for presentation to the user.

[1026] Finalist and booking process

[1027] Finally, the user selects the most suitable school from the presented options and completes the reservation procedure. When the user completes the reservation operation, the terminal sends the information to the server.

[1028] The server processes the reservation based on the received information and records it in the database. After the reservation is completed, the server sends a confirmation email to the user to notify them that the reservation has been completed.

[1029] Specific examples

[1030] For example, if a user enters the desired criteria of "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospect," the server will list multiple universities that fit this criteria. If the user then enters an additional criteria such as "a good campus environment," the server will further narrow down the candidates based on that criteria, generate a final list of suggestions, and support the user in making a reservation at the university of their choice.

[1031] The present invention allows users to easily find the best school to go to that meets their diverse needs, and reduces the anxiety and worries that come with selecting a school to go to.

[1032] The processing flow will be explained below.

[1033] ---

[1034] Step 1:

[1035] The user launches the university entrance concierge application.

[1036] Step 2:

[1037] The user inputs criteria for the school they wish to attend. For example, a deviation score of 60, living in Tokyo, playing soccer, getting a job, and a budget of 3 million yen or less.

[1038] Step 3:

[1039] The user presses the "Search" button to confirm the input conditions.

[1040] Step 4:

[1041] The terminal receives the user's input conditions and generates a request to send the data to the server.

[1042] Step 5:

[1043] The terminal sends the generated request to the server.

[1044] Step 6:

[1045] The server receives the request from the device and loads the generative AI model.

[1046] Step 7:

[1047] The server searches the database based on the user's criteria and generates a list of potential schools.

[1048] Step 8:

[1049] The server returns the generated list of potential schools to the device in JSON format.

[1050] Step 9:

[1051] The terminal analyzes the candidate list received from the server and prepares data for display on the user interface.

[1052] Step 10:

[1053] The device displays a list of potential schools to the user.

[1054] Step 11:

[1055] The user reviews the list of candidates and enters additional criteria, such as "good campus environment" or "ability to obtain specific qualifications."

[1056] Step 12:

[1057] After the user enters additional conditions, he or she presses the "Search Again" button.

[1058] Step 13:

[1059] The terminal receives the additional conditions and generates a request to transmit the data to the server.

[1060] Step 14:

[1061] The terminal sends the generated request to the server.

[1062] Step 15:

[1063] The server again receives the user's additional conditions and updates the existing candidate list using the generative AI model.

[1064] Step 16:

[1065] The server returns the updated list of potential schools to the device in JSON format.

[1066] Step 17:

[1067] The terminal analyzes the update list received from the server and displays it again on the user interface.

[1068] Step 18:

[1069] The user reviews the final school options and selects one.

[1070] Step 19:

[1071] The user presses a button to complete the reservation procedure for the selected school.

[1072] Step 20:

[1073] The terminal generates a request to transmit the selected information to the server.

[1074] Step 21:

[1075] The terminal sends the generated request to the server.

[1076] Step 22:

[1077] The server analyzes the received selection information and starts the reservation procedure.

[1078] Step 23:

[1079] The server completes the booking process and sends a confirmation email to the user.

[1080] Step 24:

[1081] The terminal receives a reservation completion notification from the server and displays it to the user.

[1082] Step 25:

[1083] Verify that the user receives a confirmation email.

[1084] ---

[1085] The above is the specific processing flow of the program, and the operations performed at each step have been explained in detail.

[1086] Example 1

[1087] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1088] When users have multiple requirements and preferences when selecting a school, it can be extremely difficult to find the right school on their own. Furthermore, the process can be time-consuming and difficult to obtain accurate information, which can increase stress. There is a need to solve these problems and enable users to quickly and accurately find the school that best suits them.

[1089] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1090] In this invention, the server includes means for allowing a user to input educational requirements, means for suggesting suitable educational destinations based on the input requirements, means for presenting the suggested educational destinations to the user and receiving additional requirements, means for narrowing down the list of educational destinations based on the additional requirements, means for completing a reservation procedure for the educational destination selected by the user, means for creating and updating a candidate list based on the educational requirements and additional requirements using a generative AI model, and means for recording the candidate list and final reservation information in a database and sending a confirmation by email. This allows users to quickly and accurately find the optimal educational destination based on various requirements for their educational destination selection.

[1091] A "user" is someone who inputs their educational requirements and uses the system to select the most suitable educational destination.

[1092] "Conditions for further education" refers to information entered by the user regarding their desired education, and specifically includes deviation score, area, club activities, career path after graduation, budget, etc.

[1093] "Means of suggestion" is a function in which the server lists and presents suitable schools based on the user's educational requirements.

[1094] "Additional conditions" refer to specific desired conditions that users enter after reviewing their initial list of potential schools, including the campus environment, available qualifications, etc.

[1095] The "narrowing down method" is a function that allows the server to update the list of potential schools based on new conditions added by the user, generating a more suitable list.

[1096] The "means of making reservations" is a function that confirms reservations at the school selected by the user and supports the process.

[1097] A "generative AI model" is an artificial intelligence model used to create and update a list of potential schools based on the school entry requirements and additional requirements.

[1098] A "database" is an information storage device managed by a server, and is responsible for storing various data, including attribute data on schools and user reservation information.

[1099] MODE FOR CARRYING OUT THE INVENTION

[1100] This invention relates to a system that suggests educational destinations based on the user's desired criteria, and in particular to a system that provides services as an educational destination concierge, and its implementation method. The system consists of a server, a terminal, and a user. The user inputs their educational destination criteria, the server suggests suitable educational destinations based on those criteria, and the terminal displays the results to the user.

[1101] User Actions

[1102] The user starts the university entrance concierge application and inputs the conditions for the university they wish to attend. For example, they can input the following conditions:

[1103] Standard deviation: 60

[1104] Area: Tokyo

[1105] Club activities: Soccer

[1106] Post-graduation path: Employment

[1107] Budget: Under 3 million yen

[1108] After entering the information, the user presses the "Search" button to confirm the conditions.

[1109] Device behavior

[1110] The device receives the conditions entered by the user and sends them to the server, where format conversion is performed and API is used to communicate with the server.

[1111] Server Operation

[1112] The server receives the user's requirements sent from the device. The server's backend contains a database linked to a generative AI model (e.g., GPT-4), which generates an initial candidate list based on the school's attribute data (standard deviation, area, club activities, post-graduation career path, budget, etc.). The generated candidate list is returned to the device in JSON format, and the user is presented with potential schools.

[1113] Add user conditions and search again

[1114] The user checks the list of potential schools presented to them and enters more specific desired conditions, such as "a good campus environment" or "the ability to obtain a specific qualification." After entering the additional conditions, the user clicks the "Search Again" button and resubmits the conditions.

[1115] Re-search and narrow down the servers

[1116] The server updates the candidate list based on the newly added criteria, generating a more refined list, and then sends the updated candidate list back to the terminal and presents it to the user.

[1117] Finalist and booking process

[1118] Finally, the user selects the most suitable school from the presented options and completes the reservation procedure. When the user completes the reservation operation, the terminal sends the information to the server. The server records the received reservation information in a database and sends the user a confirmation email that the reservation has been completed.

[1119] Specific examples

[1120] For example, if a user enters the desired criteria as "a university in Tokyo with a deviation score of 60, a soccer club, and a strong employment prospect," the process will be as follows:

[1121] 1. The user launches the application, enters the criteria for further education, and presses the search button.

[1122] 2. The device sends the conditions to the server.

[1123] 3. The server lists the universities that match the criteria and generates a candidate list.

[1124] 4. The user enters additional criteria such as "good campus environment" and presses the search again button.

[1125] 5. The server further refines the criteria and generates a final list of suggestions.

[1126] 6. The user selects the most suitable university and completes the reservation process.

[1127] 7. The server completes the booking process and sends a confirmation email.

[1128] Prompt Sentence Examples

[1129] The user entered "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospect" as their desired criteria. Furthermore, they entered "a good campus environment" as an additional condition. Please make a list of universities that meet these criteria and present it to the user.

[1130] The present invention allows users to easily find the best school to go to that meets their diverse needs, and reduces the anxiety and worries that come with selecting a school to go to.

[1131] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1132] Specific processing steps of the program

[1133] Step 1:

[1134] The user launches the university entrance concierge application and inputs the conditions for the university they wish to attend (e.g., deviation score, area, club activities, career path after graduation, budget, etc.). The conditions entered are temporarily saved as local data on the device. The user ID is also added to the input data, making it possible to identify the user in later processes.

[1135] Step 2:

[1136] The device converts the conditions for continuing education entered by the user into JSON format and sends it to the server using an HTTP POST request. At this time, all input data, including the user ID, is sent as parameters. Input data: conditions for continuing education, user ID. Output data: request to send to the server.

[1137] Step 3:

[1138] The server receives the user's conditions sent from the device and searches the database using a generative AI model (e.g., GPT-4). The database stores attribute data for each school (standard deviation, area, club activities, post-graduation career path, budget, etc.). The AI ​​model generates an initial list of candidates based on the entered conditions. Input data: School conditions in JSON format. Output data: Initial list of candidates.

[1139] Step 4:

[1140] The server converts the generated candidate list into JSON format and sends it to the terminal as an HTTP response. Input data: Initial candidate list. Output data: Send request to the terminal.

[1141] Step 5:

[1142] The terminal displays the received candidate list on the screen and presents it to the user. The user checks this list and enters more specific desired conditions (additional conditions). Input data: candidate list from the server. Output data: screen display.

[1143] Step 6:

[1144] The user checks the displayed list of potential schools and inputs additional conditions. For example, "the campus environment is good" or "a specific qualification can be obtained." Input data: Additional conditions. Output data: Notification of input completion to the terminal.

[1145] Step 7:

[1146] The terminal converts the data into JSON format again based on the additional conditions entered by the user and resends it to the server using an HTTP POST request. Input data: Additional conditions. Output data: Retransmission request to the server.

[1147] Step 8:

[1148] The server uses the generative AI model to narrow down the candidate list based on the additional criteria received again, generating an updated candidate list. It then re-queries the database to identify schools that meet the new criteria. Input data: Additional criteria. Output data: Updated candidate list.

[1149] Step 9:

[1150] The server converts the updated candidate list into JSON format and resends it to the terminal as an HTTP response. Input data: Updated candidate list. Output data: Send request to the terminal.

[1151] Step 10:

[1152] The terminal displays the narrowed candidate list on the screen again and presents it to the user. Input data: Updated candidate list from the server. Output data: Screen display.

[1153] Step 11:

[1154] The user selects the most suitable school from the presented options and presses the "Reserve" button to complete the reservation procedure. Input data: Selected school. Output data: Notification of input completion to the terminal.

[1155] Step 12:

[1156] The terminal converts the user's reservation information into JSON format and sends it to the server using an HTTP POST request. Input data: reservation information. Output data: request to send to the server.

[1157] Step 13:

[1158] The server records the received reservation information in a database, confirms the reservation, and sends a confirmation email to the user. Input data: Reservation information. Output data: Recorded in the database, sending a confirmation email.

[1159] By following the steps above, users can use this system to easily find the best school to go to that meets their diverse needs, reducing the anxiety and worries they may have when choosing a school to go to.

[1160] (Application example 1)

[1161] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1162] Conventional university selection systems only allow users to view information about proposed universities based on the criteria they enter in a list format, making it difficult to visually experience the actual campus and surrounding area. Furthermore, each time additional criteria are entered, users must re-filter, making the university selection process cumbersome. Furthermore, a separate reservation procedure is required, placing a significant burden on users. To solve these issues, a system is needed that allows users to select universities in a visual, interactive way and complete the reservation procedure simply and efficiently.

[1163] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1164] In this invention, the server includes means for allowing a user to input educational requirements, means for suggesting suitable destinations based on the input requirements, means for presenting the suggested destinations to the user and receiving additional requirements, means for narrowing down the destinations based on the additional requirements, means for completing a reservation procedure for the destination selected by the user, means for providing a virtual environment for the user to search for destinations in a virtual space, and means for displaying destination information based on the educational requirements as a 3D model in the virtual space. This allows the user to interactively narrow down the requirements while visually checking the destination environment and simplifies the reservation procedure, thereby reducing the burden of selecting a destination.

[1165] The "means for the user to input conditions for further education" refers to a device or method that provides an interface for the user to input desired conditions for further education into the system.

[1166] "Means for suggesting suitable educational destinations based on the input conditions" refers to a device or method that has the function of selecting and suggesting the most suitable educational destination based on the conditions input by the user.

[1167] "Means for presenting the proposed school candidates to the user and receiving additional conditions" refers to a device or method by which the system displays the proposed school candidates to the user and the user re-enters more detailed additional conditions.

[1168] The "means for narrowing down the candidate schools based on the additional conditions" refers to a device or method for further narrowing down the candidate schools based on the additional conditions newly input by the user.

[1169] The "means for making reservations for the school selected by the user" refers to a device or method that has the function of making reservations or applications for the school selected by the user.

[1170] "Means for providing a virtual environment for users to explore potential schools in a virtual space" refers to devices or methods that allow users to visually experience the campus and surrounding environment of their potential schools in a virtual reality space.

[1171] "Means for displaying information on schools based on the conditions for furthering education in a virtual space using a 3D model" refers to a device or method for displaying information on schools that meet the user's conditions for furthering education in a virtual reality space using a three-dimensional model.

[1172] MODE FOR CARRYING OUT THE INVENTION

[1173] This invention relates to a system that provides a virtual environment for users to use when searching for schools and supports their selection and reservation of schools. In particular, it provides a mechanism for suggesting school candidates using a generative AI model and interactively narrowing down the options.

[1174] System configuration

[1175] The system consists of the following main components:

[1176] 1. User device: smartphone, head-mounted display (HMD), etc.

[1177] 2. Server: Stores the generative AI model and the database of schools to go to, and processes data.

[1178] 3. 3D modeling tools: Tools for building virtual environments. Example: Blender.

[1179] 4. Game engine: Software for displaying virtual spaces. Example: Unity.

[1180] 5. Speech Recognition API: Used to receive additional conditions from the user. Example: Google Cloud Speech-to-Text.

[1181] System Operation

[1182] 1. User Action:

[1183] The user launches the university entrance concierge application using a smartphone or head-mounted display. The application provides a form for the user to enter university entrance criteria such as deviation score, area, club activities, post-graduation career path, and budget. The user enters these criteria and begins the search.

[1184] 2. Device behavior:

[1185] The user device converts the entered educational requirements into JSON format and sends it to the server via a RESTful API. While waiting for a response from the server, the device prepares to load the virtual space.

[1186] 3. Server Operation:

[1187] The server uses the generative AI model to search a database of schools based on the received conditions for further education. This database contains attribute data for each school (such as deviation score, area, club activities, post-graduation career path, budget, and available qualifications). The server returns the search results in JSON format to the user's device.

[1188] 4. Providing a virtual space:

[1189] The user device uses Unity to display 3D models in a virtual environment based on the data of potential schools received from the server, and the user can use a head-mounted display to walk around and visually check the virtual campus.

[1190] 5. Enter additional criteria and search again:

[1191] While exploring the virtual campus, users can add more specific preferences. For example, they can use a voice recognition API to input additional criteria such as "a good campus environment" or "the ability to obtain a specific qualification." These additional criteria are sent back to the server, which then performs a new search based on the new criteria and narrows down the candidates.

[1192] 6. Finalist and booking process:

[1193] The narrowed down list of candidates is displayed again on the user's device, and the user can select the most suitable school. After completing the selection, the user completes the reservation procedure, and the device sends the reservation information to the server. The server confirms the completion of the reservation procedure and sends a confirmation email to the user.

[1194] Specific examples

[1195] For example, if a user enters their desired criteria as "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospects," the server will generate a list of suitable universities based on this. If the user then voice-inputs additional criteria, such as "a good campus environment," in the virtual environment, the server will further narrow down the candidates based on the criteria, generating a final list of suggestions and presenting it to the user. The user can then select the most suitable university and complete the reservation process easily within the virtual space.

[1196] Prompt Sentence Examples

[1197] "Please limit your search to Tokyo as the area where you plan to study."

[1198] "Please show me schools that have soccer teams."

[1199] "Please tell me which university I would like to attend that has a good campus environment."

[1200] Based on the prompts described above, the system presents potential schools that specifically reflect the user's desired conditions, allowing the user to easily find a school that satisfies them.

[1201] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1202] Step 1:

[1203] User's entry of educational requirements

[1204] Users launch the university entrance concierge application using a smartphone or head-mounted display and enter information about university entrance requirements such as deviation score, area, club activities, career path after graduation, and budget.

[1205] Input: User's desired academic conditions (e.g., deviation score 60, area: Tokyo, club activity: soccer, career path after graduation: employment, budget: within 3 million yen)

[1206] Output: Data on academic qualifications (JSON format)

[1207] Step 2:

[1208] Sending admission conditions from the device to the server

[1209] The terminal converts the entered conditions for further education into JSON format and sends it to the server via a RESTful API.

[1210] Input: JSON format data on academic requirements

[1211] Output: Request to send admission requirements to the server

[1212] Step 3:

[1213] Server-based suggestions for potential schools

[1214] The server uses the generative AI model to search a database of schools based on the received school conditions, thereby generating a list of school candidates that meet the user's conditions.

[1215] Input: Admission requirements data

[1216] Output: A list of suitable schools (JSON format)

[1217] Step 4:

[1218] Loading the virtual world on your device

[1219] The device uses Unity to display 3D models of potential schools in a virtual environment based on the data received from the server, and users can use a head-mounted display to walk around the virtual campus and visually confirm their experiences.

[1220] Input: Data on potential schools (JSON format)

[1221] Output: 3D model display in virtual space

[1222] Step 5:

[1223] User-entered additional conditions

[1224] While exploring the virtual campus, users can input more specific requirements (e.g., a good campus environment, the ability to obtain specific qualifications) using a voice recognition API.

[1225] Input: Voice input of additional conditions

[1226] Output: Additional condition data in text format

[1227] Step 6:

[1228] Resend additional condition data to the server

[1229] The device converts the additional condition data, which has been converted into text using the voice recognition API, back into JSON format and sends it to the server.

[1230] Input: Additional condition data in text format

[1231] Output: Request to send additional condition data to the server

[1232] Step 7:

[1233] Server-based re-search and refinement of potential schools

[1234] The server receives the additional condition data, searches the list of potential schools again based on the new conditions, and generates a further narrowed list.

[1235] Enter: Additional condition data

[1236] Output: A list of narrowed-down school candidates (JSON format)

[1237] Step 8:

[1238] Presentation and selection of the final candidate list

[1239] The terminal then presents the narrowed down list of potential schools received from the server to the user, who then selects the most suitable school.

[1240] Input: A list of narrowed-down school candidates (JSON format)

[1241] Output: User's chosen educational destination

[1242] Step 9:

[1243] Completing the reservation process

[1244] The user completes the reservation procedure for the selected school. The device sends the selection information to the server, which then completes the reservation procedure and sends a confirmation email to the user.

[1245] Input: User's selected school and reservation information

[1246] Output: Confirmation email of reservation completion

[1247] As described above, the present invention can provide a system that provides interactive and visual support for everything from selecting a school to completing the reservation procedures.

[1248] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1249] ---

[1250] This invention relates to a system that suggests educational destinations based on the user's wishes and emotions, and in particular to a system that provides a service as an educational destination concierge by combining an emotion engine, and a method for implementing the system.

[1251] First, this system consists of a server, a terminal, and a user, and also incorporates an emotion engine that recognizes the user's emotions. The user inputs their educational requirements, and the emotion engine analyzes their voice and facial expressions when they input them. The server then suggests suitable educational destinations based on the requirements and emotional information, and the terminal presents the results to the user. The operation of each component is described in detail below.

[1252] User Actions

[1253] The user starts the university entrance concierge application and inputs the conditions for the university they wish to attend. For example, they can input the following conditions:

[1254] Standard deviation: 60

[1255] Area: Tokyo

[1256] Club activities: Soccer

[1257] Post-graduation path: Employment

[1258] Budget: Under 3 million yen

[1259] When inputting, the user's voice and facial expressions are simultaneously recorded and analyzed by the emotion engine.

[1260] Device behavior

[1261] The device receives the conditions and emotion information entered by the user and generates a request to send the data to the server, converting the data into the required format and communicating with the server using an API.

[1262] Server Operation

[1263] The server receives the user's conditions and emotion information sent from the device and loads the generative AI model. It also takes into account the emotion analysis results provided by the emotion engine. The server searches the database based on the user's conditions and emotions and generates a list of potential schools.

[1264] If the emotional information is determined to be "nervous" or "anxious," the server will prioritize the schools in the list that will increase the user's sense of security (e.g., schools that are good for finding employment).

[1265] The generated candidate list is returned in JSON format to the terminal, and the results are presented to the user.

[1266] Add user conditions and search again

[1267] The user checks the list of potential schools presented to them and enters more specific desired conditions (for example, "a good campus environment" or "the ability to obtain a specific qualification"). After entering the additional conditions, the user presses the "Search Again" button and resubmits the conditions. At this time, the user's emotions are also recorded again.

[1268] Re-search and narrow down the servers

[1269] The server updates the candidate list based on the newly added conditions and emotion information. If the emotion is analyzed as "satisfied," the suggested list will be very close to that condition. The updated candidate list is then sent to the device again and presented to the user.

[1270] Finalist and booking process

[1271] Finally, the user selects the most suitable school from the presented options and completes the reservation procedure. When the user completes the reservation operation, the terminal sends the information to the server.

[1272] The server processes the reservation based on the received information and records it in the database. After the reservation is completed, the server sends a confirmation email to the user to notify them that the reservation has been completed.

[1273] Specific examples

[1274] For example, if a user enters their desired criteria as "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospects," and the emotion engine analyzes this as "I feel nervous," the server will prioritize universities that the user feels comfortable with in the initial candidate list. If the user then enters an additional criterion such as "a good campus environment" and the emotion is analyzed as "I feel comfortable," the server will further narrow down the candidate list based on this criteria and generate results that give the user a sense of security. The user can then smoothly complete the reservation process for the university they ultimately selected.

[1275] The present invention allows users to easily find the most suitable school to attend that takes into consideration not only their diverse needs but also their emotional information, further reducing the anxiety and worries that come with selecting a school to attend.

[1276] The processing flow will be explained below.

[1277] ---

[1278] Step 1:

[1279] The user launches the university entrance concierge application.

[1280] Step 2:

[1281] The user inputs the conditions for the school they wish to attend. For example, they can input the following conditions: deviation score 60, Tokyo, soccer club, employment, budget within 3 million yen.

[1282] Step 3:

[1283] When the user inputs a condition, the device records the user's voice and facial expressions, and sends this information to the emotion engine.

[1284] Step 4:

[1285] The emotion engine analyzes the user's voice and facial expression data to determine the user's emotions (e.g., "nervous" or "anxious").

[1286] Step 5:

[1287] The terminal generates a request to transmit the conditions for further education input by the user and the emotion information from the emotion engine together to the server.

[1288] Step 6:

[1289] The terminal sends the generated request to the server.

[1290] Step 7:

[1291] The server receives the user's educational requirements and emotional information sent from the device and reads the analysis results of the generative AI model and emotion engine.

[1292] Step 8:

[1293] The server searches the database based on the user's conditions and emotions to generate a list of potential schools. If the emotional information is determined to be "nervous," the server will prioritize suggesting schools that provide a sense of security, such as those with a strong job prospect.

[1294] Step 9:

[1295] The server returns the generated list of potential schools to the device in JSON format.

[1296] Step 10:

[1297] The terminal analyzes the candidate list received from the server and prepares data for display on the user interface.

[1298] Step 11:

[1299] The device displays a list of potential schools to the user.

[1300] Step 12:

[1301] The user reviews the list of candidates and enters additional criteria, such as "a good campus environment" or "the ability to obtain a specific qualification."

[1302] Step 13:

[1303] After the user enters additional conditions, they press the "Search Again" button, at which point the device again records the user's voice and facial expressions and sends them to the emotion engine.

[1304] Step 14:

[1305] The emotion engine again analyzes the user's voice and facial expression data to determine an updated emotion (e.g., "I feel relieved").

[1306] Step 15:

[1307] The terminal generates a request to transmit the added educational advancement conditions and new emotion information from the emotion engine together to the server.

[1308] Step 16:

[1309] The terminal sends the generated request to the server.

[1310] Step 17:

[1311] The server receives the user's additional conditions and emotion information again, updates the existing candidate list using the generative AI model, and makes suggestions that take the additional conditions into account based on the emotion information.

[1312] Step 18:

[1313] The server returns the updated list of potential schools to the device in JSON format.

[1314] Step 19:

[1315] The terminal again analyzes the updated list received from the server and displays it again on the user interface.

[1316] Step 20:

[1317] The user reviews the final school options and selects one.

[1318] Step 21:

[1319] The user presses a button to complete the reservation procedure for the selected school.

[1320] Step 22:

[1321] The terminal generates a request to transmit the selected information to the server.

[1322] Step 23:

[1323] The terminal sends the generated request to the server.

[1324] Step 24:

[1325] The server analyzes the received selection information and starts the reservation procedure.

[1326] Step 25:

[1327] The server completes the booking process and sends a confirmation email to the user.

[1328] Step 26:

[1329] The terminal receives a reservation completion notification from the server and displays it to the user.

[1330] Step 27:

[1331] Verify that the user receives a confirmation email.

[1332] ---

[1333] The above is the specific processing flow of the system that combines the emotion engine. The operations performed at each step have been explained in detail.

[1334] Example 2

[1335] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1336] Conventional university selection systems suggest schools based on the desired conditions entered by the user, but they are unable to take the user's emotional state into consideration, which means they are unable to fully provide the most suitable school for the user.In order to reduce users' anxiety and stress and make more personalized suggestions, it is necessary to suggest schools based on emotional information.

[1337] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for inputting educational conditions from the user, means for proposing suitable educational destinations based on the input conditions and the user's emotional information, means for presenting the proposed educational destination candidates to the user and receiving additional conditions and the user's emotional information, means for narrowing down the educational destination candidates based on the additional conditions and the user's emotional information, and means for completing the reservation procedure for the educational destination selected by the user. This makes it possible to propose optimal educational destinations taking the user's emotional state into consideration, reducing the user's anxiety and stress and enabling a more satisfying educational destination selection.

[1338] "Conditions for further education" refers to the criteria and requirements for the school the user wishes to attend. Examples include deviation score, area, club activities, career path after graduation, budget, etc.

[1339] "Emotional information" refers to data that analyzes the user's emotional state at the time of input and converts it into numerical or categorized data. Examples include states such as "tense" or "relieved."

[1340] "School to be attended" refers to the educational institution to which the user wishes to attend, including university, high school, vocational school, etc.

[1341] "Suggestion" means that the system presents the most suitable educational destination based on the user's educational requirements and emotional information.

[1342] "Additional conditions" are more specific desired conditions that are entered later in addition to the conditions for entering the university that the user initially entered. Examples include "a good campus environment" and "the ability to obtain a specific qualification."

[1343] The "reservation procedure" refers to the process by which a user formally applies for and enrols at the school of their choice.

[1344] A "generative AI model" is a model that uses artificial intelligence technology to analyze educational conditions and emotional information to suggest the most suitable educational destination for users.

[1345] A "database" is a data structure that manages various data related to the school of choice (attribute data, evaluation data, etc.) and is used for system searches and analysis.

[1346] MODE FOR CARRYING OUT THE INVENTION

[1347] This invention is a system for suggesting the selection of a school to attend based on the user's desired conditions and emotional information, and in particular, it combines an emotional engine to provide the user with the most suitable school. This system is composed of a server, a terminal, and a user, and uses the emotional engine to analyze the user's emotional state.

[1348] System configuration

[1349] The system uses the following hardware and software:

[1350] Terminal: A device that allows users to enter their educational requirements. Examples include computers and smartphones.

[1351] Server: A computer that analyzes the user's educational requirements and emotional information, and lists suitable schools. Example: Cloud services (AWS EC2, etc.).

[1352] Emotion engine: Technology for analyzing emotions from the user's voice and facial expressions. Example: Microsoft Azure Emotion API.

[1353] Generative AI model: An artificial intelligence technology that suggests the most suitable school to attend based on the user's educational requirements and emotional information. Example: GPT-4 (OpenAI).

[1354] Operating procedure

[1355] 1. The user enters their desired criteria for the school they wish to attend through the university entrance concierge app. For example, possible criteria include "standard deviation score 60," "area in Tokyo," "has a soccer club," and "budget within 3 million yen."

[1356] Example prompt sentence:

[1357] My desired conditions are a university in Tokyo with a deviation score of 60. I would like a place with a soccer club and a good job placement program. I'm a little nervous about my emotional situation.

[1358] 2. At the same time, the user's voice and facial expressions are recorded, and emotional information such as "nervous" or "relieved" is analyzed by the emotion engine.

[1359] 3. The device formats the input desired conditions and emotional information into JSON format and sends it to the server using an API.

[1360] 4. The server receives and analyzes the data sent from the device. Specifically, it uses a generative AI model based on the user's conditions and emotional information to generate an optimal list of potential schools.

[1361] At this time, attribute data for the school of choice is obtained from the database, and a list of candidates is generated based on the analysis results.

[1362] 5. The server returns the generated list of potential schools to the terminal, which presents the list to the user.

[1363] 6. The user can review the list of candidates presented and re-enter their search criteria with more specific details. By pressing the search again button, the data will be sent to the server again.

[1364] Example prompt sentence:

[1365] I also hope that the campus environment will be good and that I will be able to obtain certain qualifications.

[1366] 7. The server updates the list of potential schools again based on the additional desired conditions and the latest emotional information, and sends it to the terminal again.

[1367] 8. Finally, the user selects the most suitable school from the suggestions and completes the reservation procedure. Once the reservation is completed, the device sends the information to the server, which then completes the reservation procedure. Once the reservation is complete, a confirmation email is sent to the user.

[1368] Specific examples

[1369] For example, if a user enters their desired criteria as "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospects," and the emotion engine analyzes this as "I'm nervous," the server will prioritize universities that give them a sense of security in the initial candidate list. If the user then enters an additional criterion, such as "a good campus environment," and the emotion is analyzed as "I'm secure," the server will further narrow down the candidate list based on the new criteria and present it again. In this way, the user can select the most suitable university and proceed with the reservation process.

[1370] As described above, the present invention realizes optimal proposals for further education that take into consideration the user's desired conditions and emotional information, and provides a highly satisfying selection of further education while reducing the user's anxiety and stress.

[1371] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1372] Step 1:

[1373] Users simply launch the university entrance concierge app and input their desired criteria for the university they wish to attend. For example, they can input criteria such as "standard deviation score 60," "area Tokyo," "has a soccer club," and "budget within 3 million yen." As they input their information, the user's voice and facial expressions are simultaneously recorded and analyzed by the emotion engine.

[1374] Input: Conditions for entering university (standard score, area, club activities, budget, etc.), user's voice and facial expressions

[1375] Output: Data on conditions for continuing education, emotional information data

[1376] Specific operation: The user fills in the application's input form with their admission requirements and clicks the "Submit" button. The device's camera and microphone record the user's voice and facial expressions.

[1377] Step 2:

[1378] The device receives the conditions and emotion information entered by the user and generates a request to send the data to the server. During this process, the device converts the data into the required format (e.g., JSON format) and communicates with the server using an API.

[1379] Input: Data on conditions for continuing education, emotional information data

[1380] Output: API request in JSON format

[1381] Specific behavior: Converts input data into a JSON structure and executes an HTTP request to an API endpoint.

[1382] Step 3:

[1383] The server receives the data sent from the device, loads the generative AI model based on the received data, analyzes the user's conditions, and also takes into account the analysis results from the emotion engine.

[1384] Input: JSON format data on academic requirements and emotional information

[1385] Output: Analysis results

[1386] Specific operation: Analyzes JSON data and uses a generative AI model to analyze the user's desired conditions and emotional information, taking into account the results of the emotion engine.

[1387] Step 4:

[1388] The server generates a list of potential schools based on the analysis results. The priority of the list is adjusted according to the user's conditions and emotional information. For example, if the emotional information is determined to be "nervous," the server will prioritize schools that give a sense of security.

[1389] Input: Analysis results (desired conditions, emotional information)

[1390] Output: List of potential schools

[1391] Specific operation: Searches the database for attribute data of the school of choice, adjusts priorities using a generative AI model, and generates a list of candidates. The final list is compiled in JSON format.

[1392] Step 5:

[1393] The device receives the list of potential schools sent from the server and presents it to the user. The user can review the list and add more specific desired conditions. When the user presses the "Search Again" button, the conditions and emotional information are sent again from the device to the server.

[1394] Input: List of potential schools

[1395] Output: Additional preference, updated emotion information

[1396] Specific behavior: Display the candidate list to the user and provide a field for inputting additional desired conditions. Process the click event of the search again button and send new data to the server.

[1397] Step 6:

[1398] The server then updates the list of potential schools based on the additional conditions and the latest emotional information. It receives the data for the re-search, analyzes it again using the generative AI model, and generates a list of potential schools.

[1399] Input: Additional desired conditions, updated emotional information

[1400] Output: Updated school candidate list

[1401] Specific operation: Search the database again based on the new criteria, update the candidate list using the generative AI model, and return the new candidate list in JSON format to the device.

[1402] Step 7:

[1403] The user selects the most suitable school from the presented final candidate list. When the user completes the reservation procedure, the device sends the information to the server. The server then executes the reservation procedure based on the received information and sends a confirmation email to the user.

[1404] Input: Final candidate list, selected destination

[1405] Output: Notification of completion of reservation procedure

[1406] Specific operation: The user selects the school they wish to attend and clicks the reservation button. The reservation information is sent to the server, which then completes the reservation procedure. A confirmation email is sent to the user.

[1407] (Application example 2)

[1408] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1409] Conventional online shopping systems have been unable to take into account the emotional stress and anxiety that users face when selecting products. As a result, there have been cases where users are unable to choose the right product, resulting in a decrease in satisfaction. To solve this problem, a product suggestion system that takes users' emotions into account is required.

[1410] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's emotional information using an emotion engine and receiving purchase conditions from the user, means for proposing suitable products based on the input conditions and the analyzed emotional information, and means for presenting the proposed product candidates to the user and receiving additional conditions. This makes it possible to propose optimal products that take the user's emotions into consideration.

[1411] The "emotion engine" is a technology that analyzes the user's voice and facial expressions to extract emotional information in real time.

[1412] "Purchase conditions" are information that indicates the specific requirements and desires (price, functions, design, etc.) of the product that the user wishes to purchase.

[1413] A "suitable product" is a product that is determined to best meet the user's needs and satisfaction based on the user's purchasing conditions and emotional information.

[1414] "Additional conditions" is information that allows the user to add more detailed wishes or requirements after entering the initial conditions.

[1415] A "purchase procedure" is a series of operations and processes that a user performs to select a presented product and complete the purchase.

[1416] A "generative AI model" is an artificial intelligence model used to generate optimal product suggestions based on a user's purchasing conditions and emotional information.

[1417] A "database" is an information accumulation system that manages product information and attribute data and performs searches and updates as needed.

[1418] "Attribute data" is information about the characteristics and features (price, brand, performance, etc.) of each product.

[1419] This invention relates to a system that uses an emotion engine to analyze a user's emotions and recommend the most suitable products based on their purchasing criteria. This system reduces stress and anxiety, particularly when shopping online, and helps users select products that will give them high satisfaction. The operation of each component is described in detail below.

[1420] User behavior

[1421] The user installs the shopping assistant application on their smartphone and launches it. The user enters the conditions for the product they wish to purchase. For example, they can enter the following conditions:

[1422] Price: Under 20,000 yen

[1423] Category: Home appliances

[1424] Product: Cleaning robot

[1425] When entering text, the user's voice and facial expressions are simultaneously recorded and analyzed by the emotion engine.

[1426] Device behavior

[1427] The device receives the purchase conditions and emotion information entered by the user and generates a request to send the data to the server, which converts the data into an appropriate format (e.g., JSON) and communicates it to the server using an API.

[1428] Server Operation

[1429] The server receives the user's purchase conditions and emotion information sent from the device. The software used here includes a generative AI model (e.g., OpenAI's GPT-4) and an emotion analysis API (e.g., Microsoft Azure Cognitive Services' Emotion API). The server performs the following steps to suggest suitable products using the generative AI model:

[1430] 1. Analyze the received data and check the user's emotional state.

[1431] 2. Search the database based on the purchasing criteria to generate an initial shortlist.

[1432] 3. If the emotional information is determined to be "stressed," products that provide a sense of security (e.g., a highly rated cleaning robot) will be presented preferentially from the list.

[1433] Presenting Users and Receiving Additional Terms

[1434] The generated candidate list is sent back to the device in JSON format, and the results are presented to the user. The user can review the presented candidate list of products and enter more specific desired conditions (for example, "good design" or "specific functions"). After entering the additional conditions, the user presses the "Search Again" button to resubmit the conditions. At this time, the user's emotions are also recorded again.

[1435] Re-search and narrow down the servers

[1436] The server updates the candidate list based on the new condition and emotion information. If the emotion is analyzed as "satisfied," the suggested list will be very close to that condition. The updated candidate list is then sent back to the device and presented to the user.

[1437] Finalists and purchase process

[1438] Finally, the user selects the most suitable product from the presented options and completes the purchase process. When the user completes the purchase, the device sends the information to the server. The server then completes the purchase process based on the received information and records it in a database. After the purchase is complete, a confirmation email is sent to the user to notify them that the process has been completed.

[1439] Examples of specific examples and prompts

[1440] For example, if a user enters the following criteria:

[1441] Price: Under 20,000 yen

[1442] Category: Home appliances

[1443] Product: Cleaning robot

[1444] Emotional information: tension (analysis result)

[1445] The server inputs the following prompt sentence into the generative AI model:

[1446] First condition:

[1447] Price: Under 20,000 yen

[1448] Category: Home appliances

[1449] Product: Cleaning robot

[1450] Emotional information: nervous

[1451] This allows users to receive product suggestions that take into account their emotional state at the time.

[1452] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1453] Step 1:

[1454] The user launches the shopping assistant application on their smartphone and inputs the conditions for the product they wish to purchase (price, category, product name, etc.). During this process, the user's voice and facial expressions are simultaneously recorded. Input data (purchase conditions) and emotional information are generated and processed as input data.

[1455] Step 2:

[1456] The device receives the purchase conditions and recorded emotion information entered by the user, converts this data into an appropriate format such as JSON, and sends the converted data as an API request to the server, where the data is processed to transmit the purchase conditions and emotion information.

[1457] Step 3:

[1458] The server receives the purchase conditions and emotional information sent from the device. The server analyzes the received data and calls an emotion analysis API (e.g., Microsoft Azure Cognitive Services' Emotion API) to extract emotional information. The input data (purchase conditions and emotional information) is analyzed and emotional information (e.g., tension, anxiety, etc.) is extracted.

[1459] Step 4:

[1460] The server generates a list of product candidates using a generative AI model (e.g., OpenAI's GPT-4) based on the analyzed emotional information and purchasing conditions. At this stage, the model makes product suggestions based on the input data and generates suitable product candidates as output data in the form of a list.

[1461] Step 5:

[1462] The server converts the generated product candidate list into JSON format and returns it to the terminal. The terminal analyzes the received data and presents the product candidate list to the user. Here, data conversion and display on the user interface are performed.

[1463] Step 6:

[1464] The user checks the presented product candidate list and enters more specific desired conditions (design, specific functions, etc.). After entering the additional conditions, the user presses the "Search Again" button, and the data is sent again to the server via the terminal. The additional conditions are added as input data.

[1465] Step 7:

[1466] The server re-searches and narrows down the candidate list based on the newly received additional conditions and the re-analyzed emotional information. If the emotional information is analyzed as "satisfied," products that more closely match the user's conditions are listed. The re-generated product candidate list becomes the output data.

[1467] Step 8:

[1468] The server converts the updated candidate list into JSON format and resends it to the device. The device again parses the received data and presents the updated product candidate list to the user. Here, data conversion and display on the UI are also performed.

[1469] Step 9:

[1470] The user selects the desired product from the final candidate list and completes the purchase procedure. The selection data is sent to the server via the terminal. The final selected product and purchase information are provided as input data.

[1471] Step 10:

[1472] The server processes the purchase procedure based on the received selection data. The purchase information is recorded in a database and a purchase completion email is sent to the user. Here, the purchase process is executed and confirmation data is sent.

[1473] This allows users to receive product suggestions that take their emotions into consideration and make purchases with peace of mind.

[1474] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1475] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1476] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1477] [Fourth embodiment]

[1478] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1479] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1480] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1481] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1482] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1483] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1484] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1485] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1486] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1487] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1488] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1489] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1490] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1491] ---

[1492] The present invention relates to a system that proposes the selection of educational destinations based on the user's desired conditions, and in particular, describes a system that provides services as an educational destination concierge and a method for implementing the system.

[1493] First, this system consists of a server, a terminal, and a user. The user inputs their educational requirements, the server proposes suitable schools based on those requirements, and the terminal presents the results to the user. Below, we will explain the operation of each component in detail.

[1494] User Actions

[1495] The user starts the university entrance concierge application and inputs the conditions for the university they wish to attend. For example, they can input the following conditions:

[1496] Standard deviation: 60

[1497] Area: Tokyo

[1498] Club activities: Soccer

[1499] Post-graduation path: Employment

[1500] Budget: Under 3 million yen

[1501] After entering the information, the user presses the "Search" button to confirm the conditions.

[1502] Device behavior

[1503] The device receives the conditions entered by the user and sends them to the server, converting the data into the required format and communicating with the server using an API.

[1504] Server Operation

[1505] The server receives the user's requirements sent from the device and uses the generative AI model to search a database containing attribute data for each school (such as deviation score, area, club activities, post-graduation path, budget, and available qualifications), and generates an initial list of candidates based on this information.

[1506] The server returns the generated candidate list in JSON format to the terminal, presenting the user with potential schools.

[1507] Add user conditions and search again

[1508] The user checks the list of potential schools presented to them and enters more specific desired conditions (for example, "a good campus environment" or "the ability to obtain a specific qualification"). After entering the additional conditions, the user presses the "Search Again" button to resubmit the conditions.

[1509] Re-search and narrow down the servers

[1510] The server updates the candidate list based on the newly added criteria, generating a more refined list of candidates, and sends this updated candidate list back to the terminal for presentation to the user.

[1511] Finalist and booking process

[1512] Finally, the user selects the most suitable school from the presented options and completes the reservation procedure. When the user completes the reservation operation, the terminal sends the information to the server.

[1513] The server processes the reservation based on the received information and records it in the database. After the reservation is completed, the server sends a confirmation email to the user to notify them that the reservation has been completed.

[1514] Specific examples

[1515] For example, if a user enters the desired criteria of "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospect," the server will list multiple universities that fit this criteria. If the user then enters an additional criteria such as "a good campus environment," the server will further narrow down the candidates based on that criteria, generate a final list of suggestions, and support the user in making a reservation at the university of their choice.

[1516] The present invention allows users to easily find the best school to go to that meets their diverse needs, and reduces the anxiety and worries that come with selecting a school to go to.

[1517] The processing flow will be explained below.

[1518] ---

[1519] Step 1:

[1520] The user launches the university entrance concierge application.

[1521] Step 2:

[1522] The user inputs criteria for the school they wish to attend. For example, a deviation score of 60, living in Tokyo, playing soccer, getting a job, and a budget of 3 million yen or less.

[1523] Step 3:

[1524] The user presses the "Search" button to confirm the input conditions.

[1525] Step 4:

[1526] The terminal receives the user's input conditions and generates a request to send the data to the server.

[1527] Step 5:

[1528] The terminal sends the generated request to the server.

[1529] Step 6:

[1530] The server receives the request from the device and loads the generative AI model.

[1531] Step 7:

[1532] The server searches the database based on the user's criteria and generates a list of potential schools.

[1533] Step 8:

[1534] The server returns the generated list of potential schools to the device in JSON format.

[1535] Step 9:

[1536] The terminal analyzes the candidate list received from the server and prepares data for display on the user interface.

[1537] Step 10:

[1538] The device displays a list of potential schools to the user.

[1539] Step 11:

[1540] The user reviews the list of candidates and enters additional criteria, such as "good campus environment" or "ability to obtain specific qualifications."

[1541] Step 12:

[1542] After the user enters additional conditions, he or she presses the "Search Again" button.

[1543] Step 13:

[1544] The terminal receives the additional conditions and generates a request to transmit the data to the server.

[1545] Step 14:

[1546] The terminal sends the generated request to the server.

[1547] Step 15:

[1548] The server again receives the user's additional conditions and updates the existing candidate list using the generative AI model.

[1549] Step 16:

[1550] The server returns the updated list of potential schools to the device in JSON format.

[1551] Step 17:

[1552] The terminal analyzes the update list received from the server and displays it again on the user interface.

[1553] Step 18:

[1554] The user reviews the final school options and selects one.

[1555] Step 19:

[1556] The user presses a button to complete the reservation procedure for the selected school.

[1557] Step 20:

[1558] The terminal generates a request to transmit the selected information to the server.

[1559] Step 21:

[1560] The terminal sends the generated request to the server.

[1561] Step 22:

[1562] The server analyzes the received selection information and starts the reservation procedure.

[1563] Step 23:

[1564] The server completes the booking process and sends a confirmation email to the user.

[1565] Step 24:

[1566] The terminal receives a reservation completion notification from the server and displays it to the user.

[1567] Step 25:

[1568] Verify that the user receives a confirmation email.

[1569] ---

[1570] The above is the specific processing flow of the program, and the operations performed at each step have been explained in detail.

[1571] Example 1

[1572] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1573] When users have multiple requirements and preferences when selecting a school, it can be extremely difficult to find the right school on their own. Furthermore, the process can be time-consuming and difficult to obtain accurate information, which can increase stress. There is a need to solve these problems and enable users to quickly and accurately find the school that best suits them.

[1574] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1575] In this invention, the server includes means for allowing a user to input educational requirements, means for suggesting suitable educational destinations based on the input requirements, means for presenting the suggested educational destinations to the user and receiving additional requirements, means for narrowing down the list of educational destinations based on the additional requirements, means for completing a reservation procedure for the educational destination selected by the user, means for creating and updating a candidate list based on the educational requirements and additional requirements using a generative AI model, and means for recording the candidate list and final reservation information in a database and sending a confirmation by email. This allows users to quickly and accurately find the optimal educational destination based on various requirements for their educational destination selection.

[1576] A "user" is someone who inputs their educational requirements and uses the system to select the most suitable educational destination.

[1577] "Conditions for further education" refers to information entered by the user regarding their desired education, and specifically includes deviation score, area, club activities, career path after graduation, budget, etc.

[1578] "Means of suggestion" is a function in which the server lists and presents suitable schools based on the user's educational requirements.

[1579] "Additional conditions" refer to specific desired conditions that users enter after reviewing their initial list of potential schools, including the campus environment, available qualifications, etc.

[1580] The "narrowing down method" is a function that allows the server to update the list of potential schools based on new conditions added by the user, generating a more suitable list.

[1581] The "means of making reservations" is a function that confirms reservations at the school selected by the user and supports the process.

[1582] A "generative AI model" is an artificial intelligence model used to create and update a list of potential schools based on the school entry requirements and additional requirements.

[1583] A "database" is an information storage device managed by a server, and is responsible for storing various data, including attribute data on schools and user reservation information.

[1584] MODE FOR CARRYING OUT THE INVENTION

[1585] This invention relates to a system that suggests educational destinations based on the user's desired criteria, and in particular to a system that provides services as an educational destination concierge, and its implementation method. The system consists of a server, a terminal, and a user. The user inputs their educational destination criteria, the server suggests suitable educational destinations based on those criteria, and the terminal displays the results to the user.

[1586] User Actions

[1587] The user starts the university entrance concierge application and inputs the conditions for the university they wish to attend. For example, they can input the following conditions:

[1588] Standard deviation: 60

[1589] Area: Tokyo

[1590] Club activities: Soccer

[1591] Post-graduation path: Employment

[1592] Budget: Under 3 million yen

[1593] After entering the information, the user presses the "Search" button to confirm the conditions.

[1594] Device behavior

[1595] The device receives the conditions entered by the user and sends them to the server, where format conversion is performed and API is used to communicate with the server.

[1596] Server Operation

[1597] The server receives the user's requirements sent from the device. The server's backend contains a database linked to a generative AI model (e.g., GPT-4), which generates an initial candidate list based on the school's attribute data (standard deviation, area, club activities, post-graduation career path, budget, etc.). The generated candidate list is returned to the device in JSON format, and the user is presented with potential schools.

[1598] Add user conditions and search again

[1599] The user checks the list of potential schools presented to them and enters more specific desired conditions, such as "a good campus environment" or "the ability to obtain a specific qualification." After entering the additional conditions, the user clicks the "Search Again" button and resubmits the conditions.

[1600] Re-search and narrow down the servers

[1601] The server updates the candidate list based on the newly added criteria, generating a more refined list, and then sends the updated candidate list back to the terminal and presents it to the user.

[1602] Finalist and booking process

[1603] Finally, the user selects the most suitable school from the presented options and completes the reservation procedure. When the user completes the reservation operation, the terminal sends the information to the server. The server records the received reservation information in a database and sends the user a confirmation email that the reservation has been completed.

[1604] Specific examples

[1605] For example, if a user enters the desired criteria as "a university in Tokyo with a deviation score of 60, a soccer club, and a strong employment prospect," the process will be as follows:

[1606] 1. The user launches the application, enters the criteria for further education, and presses the search button.

[1607] 2. The device sends the conditions to the server.

[1608] 3. The server lists the universities that match the criteria and generates a candidate list.

[1609] 4. The user enters additional criteria such as "good campus environment" and presses the search again button.

[1610] 5. The server further refines the criteria and generates a final list of suggestions.

[1611] 6. The user selects the most suitable university and completes the reservation process.

[1612] 7. The server completes the booking process and sends a confirmation email.

[1613] Prompt Sentence Examples

[1614] The user entered "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospect" as their desired criteria. Furthermore, they entered "a good campus environment" as an additional condition. Please make a list of universities that meet these criteria and present it to the user.

[1615] The present invention allows users to easily find the best school to go to that meets their diverse needs, and reduces the anxiety and worries that come with selecting a school to go to.

[1616] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1617] Specific processing steps of the program

[1618] Step 1:

[1619] The user launches the university entrance concierge application and inputs the conditions for the university they wish to attend (e.g., deviation score, area, club activities, career path after graduation, budget, etc.). The conditions entered are temporarily saved as local data on the device. The user ID is also added to the input data, making it possible to identify the user in later processes.

[1620] Step 2:

[1621] The device converts the conditions for continuing education entered by the user into JSON format and sends it to the server using an HTTP POST request. At this time, all input data, including the user ID, is sent as parameters. Input data: conditions for continuing education, user ID. Output data: request to send to the server.

[1622] Step 3:

[1623] The server receives the user's conditions sent from the device and searches the database using a generative AI model (e.g., GPT-4). The database stores attribute data for each school (standard deviation, area, club activities, post-graduation career path, budget, etc.). The AI ​​model generates an initial list of candidates based on the entered conditions. Input data: School conditions in JSON format. Output data: Initial list of candidates.

[1624] Step 4:

[1625] The server converts the generated candidate list into JSON format and sends it to the terminal as an HTTP response. Input data: Initial candidate list. Output data: Send request to the terminal.

[1626] Step 5:

[1627] The terminal displays the received candidate list on the screen and presents it to the user. The user checks this list and enters more specific desired conditions (additional conditions). Input data: candidate list from the server. Output data: screen display.

[1628] Step 6:

[1629] The user checks the displayed list of potential schools and inputs additional conditions. For example, "the campus environment is good" or "a specific qualification can be obtained." Input data: Additional conditions. Output data: Notification of input completion to the terminal.

[1630] Step 7:

[1631] The terminal converts the data into JSON format again based on the additional conditions entered by the user and resends it to the server using an HTTP POST request. Input data: Additional conditions. Output data: Retransmission request to the server.

[1632] Step 8:

[1633] The server uses the generative AI model to narrow down the candidate list based on the additional criteria received again, generating an updated candidate list. It then re-queries the database to identify schools that meet the new criteria. Input data: Additional criteria. Output data: Updated candidate list.

[1634] Step 9:

[1635] The server converts the updated candidate list into JSON format and resends it to the terminal as an HTTP response. Input data: Updated candidate list. Output data: Send request to the terminal.

[1636] Step 10:

[1637] The terminal displays the narrowed candidate list on the screen again and presents it to the user. Input data: Updated candidate list from the server. Output data: Screen display.

[1638] Step 11:

[1639] The user selects the most suitable school from the presented options and presses the "Reserve" button to complete the reservation procedure. Input data: Selected school. Output data: Notification of input completion to the terminal.

[1640] Step 12:

[1641] The terminal converts the user's reservation information into JSON format and sends it to the server using an HTTP POST request. Input data: reservation information. Output data: request to send to the server.

[1642] Step 13:

[1643] The server records the received reservation information in a database, confirms the reservation, and sends a confirmation email to the user. Input data: Reservation information. Output data: Recorded in the database, sending a confirmation email.

[1644] By following the steps above, users can use this system to easily find the best school to go to that meets their diverse needs, reducing the anxiety and worries they may have when choosing a school to go to.

[1645] (Application example 1)

[1646] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1647] Conventional university selection systems only allow users to view information about proposed universities based on the criteria they enter in a list format, making it difficult to visually experience the actual campus and surrounding area. Furthermore, each time additional criteria are entered, users must re-filter, making the university selection process cumbersome. Furthermore, a separate reservation procedure is required, placing a significant burden on users. To solve these issues, a system is needed that allows users to select universities in a visual, interactive way and complete the reservation procedure simply and efficiently.

[1648] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1649] In this invention, the server includes means for allowing a user to input educational requirements, means for suggesting suitable destinations based on the input requirements, means for presenting the suggested destinations to the user and receiving additional requirements, means for narrowing down the destinations based on the additional requirements, means for completing a reservation procedure for the destination selected by the user, means for providing a virtual environment for the user to search for destinations in a virtual space, and means for displaying destination information based on the educational requirements as a 3D model in the virtual space. This allows the user to interactively narrow down the requirements while visually checking the destination environment and simplifies the reservation procedure, thereby reducing the burden of selecting a destination.

[1650] The "means for the user to input conditions for further education" refers to a device or method that provides an interface for the user to input desired conditions for further education into the system.

[1651] "Means for suggesting suitable educational destinations based on the input conditions" refers to a device or method that has the function of selecting and suggesting the most suitable educational destination based on the conditions input by the user.

[1652] "Means for presenting the proposed school candidates to the user and receiving additional conditions" refers to a device or method by which the system displays the proposed school candidates to the user and the user re-enters more detailed additional conditions.

[1653] The "means for narrowing down the candidate schools based on the additional conditions" refers to a device or method for further narrowing down the candidate schools based on the additional conditions newly input by the user.

[1654] The "means for making reservations for the school selected by the user" refers to a device or method that has the function of making reservations or applications for the school selected by the user.

[1655] "Means for providing a virtual environment for users to explore potential schools in a virtual space" refers to devices or methods that allow users to visually experience the campus and surrounding environment of their potential schools in a virtual reality space.

[1656] "Means for displaying information on schools based on the conditions for furthering education in a virtual space using a 3D model" refers to a device or method for displaying information on schools that meet the user's conditions for furthering education in a virtual reality space using a three-dimensional model.

[1657] MODE FOR CARRYING OUT THE INVENTION

[1658] This invention relates to a system that provides a virtual environment for users to use when searching for schools and supports their selection and reservation of schools. In particular, it provides a mechanism for suggesting school candidates using a generative AI model and interactively narrowing down the options.

[1659] System configuration

[1660] The system consists of the following main components:

[1661] 1. User device: smartphone, head-mounted display (HMD), etc.

[1662] 2. Server: Stores the generative AI model and the database of schools to go to, and processes data.

[1663] 3. 3D modeling tools: Tools for building virtual environments. Example: Blender.

[1664] 4. Game engine: Software for displaying virtual spaces. Example: Unity.

[1665] 5. Speech Recognition API: Used to receive additional conditions from the user. Example: Google Cloud Speech-to-Text.

[1666] System Operation

[1667] 1. User Action:

[1668] The user launches the university entrance concierge application using a smartphone or head-mounted display. The application provides a form for the user to enter university entrance criteria such as deviation score, area, club activities, post-graduation career path, and budget. The user enters these criteria and begins the search.

[1669] 2. Device behavior:

[1670] The user device converts the entered educational requirements into JSON format and sends it to the server via a RESTful API. While waiting for a response from the server, the device prepares to load the virtual space.

[1671] 3. Server Operation:

[1672] The server uses the generative AI model to search a database of schools based on the received conditions for further education. This database contains attribute data for each school (such as deviation score, area, club activities, post-graduation career path, budget, and available qualifications). The server returns the search results in JSON format to the user's device.

[1673] 4. Providing a virtual space:

[1674] The user device uses Unity to display 3D models in a virtual environment based on the data of potential schools received from the server, and the user can use a head-mounted display to walk around and visually check the virtual campus.

[1675] 5. Enter additional criteria and search again:

[1676] While exploring the virtual campus, users can add more specific preferences. For example, they can use a voice recognition API to input additional criteria such as "a good campus environment" or "the ability to obtain a specific qualification." These additional criteria are sent back to the server, which then performs a new search based on the new criteria and narrows down the candidates.

[1677] 6. Finalist and booking process:

[1678] The narrowed down list of candidates is displayed again on the user's device, and the user can select the most suitable school. After completing the selection, the user completes the reservation procedure, and the device sends the reservation information to the server. The server confirms the completion of the reservation procedure and sends a confirmation email to the user.

[1679] Specific examples

[1680] For example, if a user enters their desired criteria as "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospects," the server will generate a list of suitable universities based on this. If the user then voice-inputs additional criteria, such as "a good campus environment," in the virtual environment, the server will further narrow down the candidates based on the criteria, generating a final list of suggestions and presenting it to the user. The user can then select the most suitable university and complete the reservation process easily within the virtual space.

[1681] Prompt Sentence Examples

[1682] "Please limit your search to Tokyo as the area where you plan to study."

[1683] "Please show me schools that have soccer teams."

[1684] "Please tell me which university I would like to attend that has a good campus environment."

[1685] Based on the prompts described above, the system presents potential schools that specifically reflect the user's desired conditions, allowing the user to easily find a school that satisfies them.

[1686] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1687] Step 1:

[1688] User's entry of educational requirements

[1689] Users launch the university entrance concierge application using a smartphone or head-mounted display and enter information about university entrance requirements such as deviation score, area, club activities, career path after graduation, and budget.

[1690] Input: User's desired academic conditions (e.g., deviation score 60, area: Tokyo, club activity: soccer, career path after graduation: employment, budget: within 3 million yen)

[1691] Output: Data on academic qualifications (JSON format)

[1692] Step 2:

[1693] Sending admission conditions from the device to the server

[1694] The terminal converts the entered conditions for further education into JSON format and sends it to the server via a RESTful API.

[1695] Input: JSON format data on academic requirements

[1696] Output: Request to send admission requirements to the server

[1697] Step 3:

[1698] Server-based suggestions for potential schools

[1699] The server uses the generative AI model to search a database of schools based on the received school conditions, thereby generating a list of school candidates that meet the user's conditions.

[1700] Input: Admission requirements data

[1701] Output: A list of suitable schools (JSON format)

[1702] Step 4:

[1703] Loading the virtual world on your device

[1704] The device uses Unity to display 3D models of potential schools in a virtual environment based on the data received from the server, and users can use a head-mounted display to walk around the virtual campus and visually confirm their experiences.

[1705] Input: Data on potential schools (JSON format)

[1706] Output: 3D model display in virtual space

[1707] Step 5:

[1708] User-entered additional conditions

[1709] While exploring the virtual campus, users can input more specific requirements (e.g., a good campus environment, the ability to obtain specific qualifications) using a voice recognition API.

[1710] Input: Voice input of additional conditions

[1711] Output: Additional condition data in text format

[1712] Step 6:

[1713] Resend additional condition data to the server

[1714] The device converts the additional condition data, which has been converted into text using the voice recognition API, back into JSON format and sends it to the server.

[1715] Input: Additional condition data in text format

[1716] Output: Request to send additional condition data to the server

[1717] Step 7:

[1718] Server-based re-search and refinement of potential schools

[1719] The server receives the additional condition data, searches the list of potential schools again based on the new conditions, and generates a further narrowed list.

[1720] Enter: Additional condition data

[1721] Output: A list of narrowed-down school candidates (JSON format)

[1722] Step 8:

[1723] Presentation and selection of the final candidate list

[1724] The terminal then presents the narrowed down list of potential schools received from the server to the user, who then selects the most suitable school.

[1725] Input: A list of narrowed-down school candidates (JSON format)

[1726] Output: User's chosen educational destination

[1727] Step 9:

[1728] Completing the reservation process

[1729] The user completes the reservation procedure for the selected school. The device sends the selection information to the server, which then completes the reservation procedure and sends a confirmation email to the user.

[1730] Input: User's selected school and reservation information

[1731] Output: Confirmation email of reservation completion

[1732] As described above, the present invention can provide a system that provides interactive and visual support for everything from selecting a school to completing the reservation procedures.

[1733] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1734] ---

[1735] This invention relates to a system that suggests educational destinations based on the user's wishes and emotions, and in particular to a system that provides a service as an educational destination concierge by combining an emotion engine, and a method for implementing the system.

[1736] First, this system consists of a server, a terminal, and a user, and also incorporates an emotion engine that recognizes the user's emotions. The user inputs their educational requirements, and the emotion engine analyzes their voice and facial expressions when they input them. The server then suggests suitable educational destinations based on the requirements and emotional information, and the terminal presents the results to the user. The operation of each component is described in detail below.

[1737] User Actions

[1738] The user starts the university entrance concierge application and inputs the conditions for the university they wish to attend. For example, they can input the following conditions:

[1739] Standard deviation: 60

[1740] Area: Tokyo

[1741] Club activities: Soccer

[1742] Post-graduation path: Employment

[1743] Budget: Under 3 million yen

[1744] When inputting, the user's voice and facial expressions are simultaneously recorded and analyzed by the emotion engine.

[1745] Device behavior

[1746] The device receives the conditions and emotion information entered by the user and generates a request to send the data to the server, converting the data into the required format and communicating with the server using an API.

[1747] Server Operation

[1748] The server receives the user's conditions and emotion information sent from the device and loads the generative AI model. It also takes into account the emotion analysis results provided by the emotion engine. The server searches the database based on the user's conditions and emotions and generates a list of potential schools.

[1749] If the emotional information is determined to be "nervous" or "anxious," the server will prioritize the schools in the list that will increase the user's sense of security (e.g., schools that are good for finding employment).

[1750] The generated candidate list is returned in JSON format to the terminal, and the results are presented to the user.

[1751] Add user conditions and search again

[1752] The user checks the list of potential schools presented to them and enters more specific desired conditions (for example, "a good campus environment" or "the ability to obtain a specific qualification"). After entering the additional conditions, the user presses the "Search Again" button and resubmits the conditions. At this time, the user's emotions are also recorded again.

[1753] Re-search and narrow down the servers

[1754] The server updates the candidate list based on the newly added conditions and emotion information. If the emotion is analyzed as "satisfied," the suggested list will be very close to that condition. The updated candidate list is then sent to the device again and presented to the user.

[1755] Finalist and booking process

[1756] Finally, the user selects the most suitable school from the presented options and completes the reservation procedure. When the user completes the reservation operation, the terminal sends the information to the server.

[1757] The server processes the reservation based on the received information and records it in the database. After the reservation is completed, the server sends a confirmation email to the user to notify them that the reservation has been completed.

[1758] Specific examples

[1759] For example, if a user enters their desired criteria as "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospects," and the emotion engine analyzes this as "I feel nervous," the server will prioritize universities that the user feels comfortable with in the initial candidate list. If the user then enters an additional criterion such as "a good campus environment" and the emotion is analyzed as "I feel comfortable," the server will further narrow down the candidate list based on this criteria and generate results that give the user a sense of security. The user can then smoothly complete the reservation process for the university they ultimately selected.

[1760] The present invention allows users to easily find the most suitable school to attend that takes into consideration not only their diverse needs but also their emotional information, further reducing the anxiety and worries that come with selecting a school to attend.

[1761] The processing flow will be explained below.

[1762] ---

[1763] Step 1:

[1764] The user launches the university entrance concierge application.

[1765] Step 2:

[1766] The user inputs the conditions for the school they wish to attend. For example, they can input the following conditions: deviation score 60, Tokyo, soccer club, employment, budget within 3 million yen.

[1767] Step 3:

[1768] When the user inputs a condition, the device records the user's voice and facial expressions, and sends this information to the emotion engine.

[1769] Step 4:

[1770] The emotion engine analyzes the user's voice and facial expression data to determine the user's emotions (e.g., "nervous" or "anxious").

[1771] Step 5:

[1772] The terminal generates a request to transmit the conditions for further education input by the user and the emotion information from the emotion engine together to the server.

[1773] Step 6:

[1774] The terminal sends the generated request to the server.

[1775] Step 7:

[1776] The server receives the user's educational requirements and emotional information sent from the device and reads the analysis results of the generative AI model and emotion engine.

[1777] Step 8:

[1778] The server searches the database based on the user's conditions and emotions to generate a list of potential schools. If the emotional information is determined to be "nervous," the server will prioritize suggesting schools that provide a sense of security, such as those with a strong job prospect.

[1779] Step 9:

[1780] The server returns the generated list of potential schools to the device in JSON format.

[1781] Step 10:

[1782] The terminal analyzes the candidate list received from the server and prepares data for display on the user interface.

[1783] Step 11:

[1784] The device displays a list of potential schools to the user.

[1785] Step 12:

[1786] The user reviews the list of candidates and enters additional criteria, such as "a good campus environment" or "the ability to obtain a specific qualification."

[1787] Step 13:

[1788] After the user enters additional conditions, they press the "Search Again" button, at which point the device again records the user's voice and facial expressions and sends them to the emotion engine.

[1789] Step 14:

[1790] The emotion engine again analyzes the user's voice and facial expression data to determine an updated emotion (e.g., "I feel relieved").

[1791] Step 15:

[1792] The terminal generates a request to transmit the added educational advancement conditions and new emotion information from the emotion engine together to the server.

[1793] Step 16:

[1794] The terminal sends the generated request to the server.

[1795] Step 17:

[1796] The server receives the user's additional conditions and emotion information again, updates the existing candidate list using the generative AI model, and makes suggestions that take the additional conditions into account based on the emotion information.

[1797] Step 18:

[1798] The server returns the updated list of potential schools to the device in JSON format.

[1799] Step 19:

[1800] The terminal again analyzes the updated list received from the server and displays it again on the user interface.

[1801] Step 20:

[1802] The user reviews the final school options and selects one.

[1803] Step 21:

[1804] The user presses a button to complete the reservation procedure for the selected school.

[1805] Step 22:

[1806] The terminal generates a request to transmit the selected information to the server.

[1807] Step 23:

[1808] The terminal sends the generated request to the server.

[1809] Step 24:

[1810] The server analyzes the received selection information and starts the reservation procedure.

[1811] Step 25:

[1812] The server completes the booking process and sends a confirmation email to the user.

[1813] Step 26:

[1814] The terminal receives a reservation completion notification from the server and displays it to the user.

[1815] Step 27:

[1816] Verify that the user receives a confirmation email.

[1817] ---

[1818] The above is the specific processing flow of the system that combines the emotion engine. The operations performed at each step have been explained in detail.

[1819] Example 2

[1820] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1821] Conventional university selection systems suggest schools based on the desired conditions entered by the user, but they are unable to take the user's emotional state into consideration, which means they are unable to fully provide the most suitable school for the user.In order to reduce users' anxiety and stress and make more personalized suggestions, it is necessary to suggest schools based on emotional information.

[1822] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for inputting educational conditions from the user, means for proposing suitable educational destinations based on the input conditions and the user's emotional information, means for presenting the proposed educational destination candidates to the user and receiving additional conditions and the user's emotional information, means for narrowing down the educational destination candidates based on the additional conditions and the user's emotional information, and means for completing the reservation procedure for the educational destination selected by the user. This makes it possible to propose optimal educational destinations taking the user's emotional state into consideration, reducing the user's anxiety and stress and enabling a more satisfying educational destination selection.

[1823] "Conditions for further education" refers to the criteria and requirements for the school the user wishes to attend. Examples include deviation score, area, club activities, career path after graduation, budget, etc.

[1824] "Emotional information" refers to data that analyzes the user's emotional state at the time of input and converts it into numerical or categorized data. Examples include states such as "tense" or "relieved."

[1825] "School to be attended" refers to the educational institution to which the user wishes to attend, including university, high school, vocational school, etc.

[1826] "Suggestion" means that the system presents the most suitable educational destination based on the user's educational requirements and emotional information.

[1827] "Additional conditions" are more specific desired conditions that are entered later in addition to the conditions for entering the university that the user initially entered. Examples include "a good campus environment" and "the ability to obtain a specific qualification."

[1828] The "reservation procedure" refers to the process by which a user formally applies for and enrols at the school of their choice.

[1829] A "generative AI model" is a model that uses artificial intelligence technology to analyze educational conditions and emotional information to suggest the most suitable educational destination for users.

[1830] A "database" is a data structure that manages various data related to the school of choice (attribute data, evaluation data, etc.) and is used for system searches and analysis.

[1831] MODE FOR CARRYING OUT THE INVENTION

[1832] This invention is a system for suggesting the selection of a school to attend based on the user's desired conditions and emotional information, and in particular, it combines an emotional engine to provide the user with the most suitable school. This system is composed of a server, a terminal, and a user, and uses the emotional engine to analyze the user's emotional state.

[1833] System configuration

[1834] The system uses the following hardware and software:

[1835] Terminal: A device that allows users to enter their educational requirements. Examples include computers and smartphones.

[1836] Server: A computer that analyzes the user's educational requirements and emotional information, and lists suitable schools. Example: Cloud services (AWS EC2, etc.).

[1837] Emotion engine: Technology for analyzing emotions from the user's voice and facial expressions. Example: Microsoft Azure Emotion API.

[1838] Generative AI model: An artificial intelligence technology that suggests the most suitable school to attend based on the user's educational requirements and emotional information. Example: GPT-4 (OpenAI).

[1839] Operating procedure

[1840] 1. The user enters their desired criteria for the school they wish to attend through the university entrance concierge app. For example, possible criteria include "standard deviation score 60," "area in Tokyo," "has a soccer club," and "budget within 3 million yen."

[1841] Example prompt sentence:

[1842] My desired conditions are a university in Tokyo with a deviation score of 60. I would like a place with a soccer club and a good job placement program. I'm a little nervous about my emotional situation.

[1843] 2. At the same time, the user's voice and facial expressions are recorded, and emotional information such as "nervous" or "relieved" is analyzed by the emotion engine.

[1844] 3. The device formats the input desired conditions and emotional information into JSON format and sends it to the server using an API.

[1845] 4. The server receives and analyzes the data sent from the device. Specifically, it uses a generative AI model based on the user's conditions and emotional information to generate an optimal list of potential schools.

[1846] At this time, attribute data for the school of choice is obtained from the database, and a list of candidates is generated based on the analysis results.

[1847] 5. The server returns the generated list of potential schools to the terminal, which presents the list to the user.

[1848] 6. The user can review the list of candidates presented and re-enter their search criteria with more specific details. By pressing the search again button, the data will be sent to the server again.

[1849] Example prompt sentence:

[1850] I also hope that the campus environment will be good and that I will be able to obtain certain qualifications.

[1851] 7. The server updates the list of potential schools again based on the additional desired conditions and the latest emotional information, and sends it to the terminal again.

[1852] 8. Finally, the user selects the most suitable school from the suggestions and completes the reservation procedure. Once the reservation is completed, the device sends the information to the server, which then completes the reservation procedure. Once the reservation is complete, a confirmation email is sent to the user.

[1853] Specific examples

[1854] For example, if a user enters their desired criteria as "a university in Tokyo with a deviation score of 60, a soccer team, and a strong employment prospects," and the emotion engine analyzes this as "I'm nervous," the server will prioritize universities that give them a sense of security in the initial candidate list. If the user then enters an additional criterion, such as "a good campus environment," and the emotion is analyzed as "I'm secure," the server will further narrow down the candidate list based on the new criteria and present it again. In this way, the user can select the most suitable university and proceed with the reservation process.

[1855] As described above, the present invention realizes optimal proposals for further education that take into consideration the user's desired conditions and emotional information, and provides a highly satisfying selection of further education while reducing the user's anxiety and stress.

[1856] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1857] Step 1:

[1858] Users simply launch the university entrance concierge app and input their desired criteria for the university they wish to attend. For example, they can input criteria such as "standard deviation score 60," "area Tokyo," "has a soccer club," and "budget within 3 million yen." As they input their information, the user's voice and facial expressions are simultaneously recorded and analyzed by the emotion engine.

[1859] Input: Conditions for entering university (standard score, area, club activities, budget, etc.), user's voice and facial expressions

[1860] Output: Data on conditions for continuing education, emotional information data

[1861] Specific operation: The user fills in the application's input form with their admission requirements and clicks the "Submit" button. The device's camera and microphone record the user's voice and facial expressions.

[1862] Step 2:

[1863] The device receives the conditions and emotion information entered by the user and generates a request to send the data to the server. During this process, the device converts the data into the required format (e.g., JSON format) and communicates with the server using an API.

[1864] Input: Data on conditions for continuing education, emotional information data

[1865] Output: API request in JSON format

[1866] Specific behavior: Converts input data into a JSON structure and executes an HTTP request to an API endpoint.

[1867] Step 3:

[1868] The server receives the data sent from the device, loads the generative AI model based on the received data, analyzes the user's conditions, and also takes into account the analysis results from the emotion engine.

[1869] Input: JSON format data on academic requirements and emotional information

[1870] Output: Analysis results

[1871] Specific operation: Analyzes JSON data and uses a generative AI model to analyze the user's desired conditions and emotional information, taking into account the results of the emotion engine.

[1872] Step 4:

[1873] The server generates a list of potential schools based on the analysis results. The priority of the list is adjusted according to the user's conditions and emotional information. For example, if the emotional information is determined to be "nervous," the server will prioritize schools that give a sense of security.

[1874] Input: Analysis results (desired conditions, emotional information)

[1875] Output: List of potential schools

[1876] Specific operation: Searches the database for attribute data of the school of choice, adjusts priorities using a generative AI model, and generates a list of candidates. The final list is compiled in JSON format.

[1877] Step 5:

[1878] The device receives the list of potential schools sent from the server and presents it to the user. The user can review the list and add more specific desired conditions. When the user presses the "Search Again" button, the conditions and emotional information are sent again from the device to the server.

[1879] Input: List of potential schools

[1880] Output: Additional preference, updated emotion information

[1881] Specific behavior: Display the candidate list to the user and provide a field for inputting additional desired conditions. Process the click event of the search again button and send new data to the server.

[1882] Step 6:

[1883] The server then updates the list of potential schools based on the additional conditions and the latest emotional information. It receives the data for the re-search, analyzes it again using the generative AI model, and generates a list of potential schools.

[1884] Input: Additional desired conditions, updated emotional information

[1885] Output: Updated school candidate list

[1886] Specific operation: Search the database again based on the new criteria, update the candidate list using the generative AI model, and return the new candidate list in JSON format to the device.

[1887] Step 7:

[1888] The user selects the most suitable school from the presented final candidate list. When the user completes the reservation procedure, the device sends the information to the server. The server then executes the reservation procedure based on the received information and sends a confirmation email to the user.

[1889] Input: Final candidate list, selected destination

[1890] Output: Notification of completion of reservation procedure

[1891] Specific operation: The user selects the school they wish to attend and clicks the reservation button. The reservation information is sent to the server, which then completes the reservation procedure. A confirmation email is sent to the user.

[1892] (Application example 2)

[1893] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1894] Conventional online shopping systems have been unable to take into account the emotional stress and anxiety that users face when selecting products. As a result, there have been cases where users are unable to choose the right product, resulting in a decrease in satisfaction. To solve this problem, a product suggestion system that takes users' emotions into account is required.

[1895] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's emotional information using an emotion engine and receiving purchase conditions from the user, means for proposing suitable products based on the input conditions and the analyzed emotional information, and means for presenting the proposed product candidates to the user and receiving additional conditions. This makes it possible to propose optimal products that take the user's emotions into consideration.

[1896] The "emotion engine" is a technology that analyzes the user's voice and facial expressions to extract emotional information in real time.

[1897] "Purchase conditions" are information that indicates the specific requirements and desires (price, functions, design, etc.) of the product that the user wishes to purchase.

[1898] A "suitable product" is a product that is determined to best meet the user's needs and satisfaction based on the user's purchasing conditions and emotional information.

[1899] "Additional conditions" is information that allows the user to add more detailed wishes or requirements after entering the initial conditions.

[1900] A "purchase procedure" is a series of operations and processes that a user performs to select a presented product and complete the purchase.

[1901] A "generative AI model" is an artificial intelligence model used to generate optimal product suggestions based on a user's purchasing conditions and emotional information.

[1902] A "database" is an information accumulation system that manages product information and attribute data and performs searches and updates as needed.

[1903] "Attribute data" is information about the characteristics and features (price, brand, performance, etc.) of each product.

[1904] This invention relates to a system that uses an emotion engine to analyze a user's emotions and recommend the most suitable products based on their purchasing criteria. This system reduces stress and anxiety, particularly when shopping online, and helps users select products that will give them high satisfaction. The operation of each component is described in detail below.

[1905] User behavior

[1906] The user installs the shopping assistant application on their smartphone and launches it. The user enters the conditions for the product they wish to purchase. For example, they can enter the following conditions:

[1907] Price: Under 20,000 yen

[1908] Category: Home appliances

[1909] Product: Cleaning robot

[1910] When entering text, the user's voice and facial expressions are simultaneously recorded and analyzed by the emotion engine.

[1911] Device behavior

[1912] The device receives the purchase conditions and emotion information entered by the user and generates a request to send the data to the server, which converts the data into an appropriate format (e.g., JSON) and communicates it to the server using an API.

[1913] Server Operation

[1914] The server receives the user's purchase conditions and emotion information sent from the device. The software used here includes a generative AI model (e.g., OpenAI's GPT-4) and an emotion analysis API (e.g., Microsoft Azure Cognitive Services' Emotion API). The server performs the following steps to suggest suitable products using the generative AI model:

[1915] 1. Analyze the received data and check the user's emotional state.

[1916] 2. Search the database based on the purchasing criteria to generate an initial shortlist.

[1917] 3. If the emotional information is determined to be "stressed," products that provide a sense of security (e.g., a highly rated cleaning robot) will be presented preferentially from the list.

[1918] Presenting Users and Receiving Additional Terms

[1919] The generated candidate list is sent back to the device in JSON format, and the results are presented to the user. The user can review the presented candidate list of products and enter more specific desired conditions (for example, "good design" or "specific functions"). After entering the additional conditions, the user presses the "Search Again" button to resubmit the conditions. At this time, the user's emotions are also recorded again.

[1920] Re-search and narrow down the servers

[1921] The server updates the candidate list based on the new condition and emotion information. If the emotion is analyzed as "satisfied," the suggested list will be very close to that condition. The updated candidate list is then sent back to the device and presented to the user.

[1922] Finalists and purchase process

[1923] Finally, the user selects the most suitable product from the presented options and completes the purchase process. When the user completes the purchase, the device sends the information to the server. The server then completes the purchase process based on the received information and records it in a database. After the purchase is complete, a confirmation email is sent to the user to notify them that the process has been completed.

[1924] Examples of specific examples and prompts

[1925] For example, if a user enters the following criteria:

[1926] Price: Under 20,000 yen

[1927] Category: Home appliances

[1928] Product: Cleaning robot

[1929] Emotional information: tension (analysis result)

[1930] The server inputs the following prompt sentence into the generative AI model:

[1931] First condition:

[1932] Price: Under 20,000 yen

[1933] Category: Home appliances

[1934] Product: Cleaning robot

[1935] Emotional information: nervous

[1936] This allows users to receive product suggestions that take into account their emotional state at the time.

[1937] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1938] Step 1:

[1939] The user launches the shopping assistant application on their smartphone and inputs the conditions for the product they wish to purchase (price, category, product name, etc.). During this process, the user's voice and facial expressions are simultaneously recorded. Input data (purchase conditions) and emotional information are generated and processed as input data.

[1940] Step 2:

[1941] The device receives the purchase conditions and recorded emotion information entered by the user, converts this data into an appropriate format such as JSON, and sends the converted data as an API request to the server, where the data is processed to transmit the purchase conditions and emotion information.

[1942] Step 3:

[1943] The server receives the purchase conditions and emotional information sent from the device. The server analyzes the received data and calls an emotion analysis API (e.g., Microsoft Azure Cognitive Services' Emotion API) to extract emotional information. The input data (purchase conditions and emotional information) is analyzed and emotional information (e.g., tension, anxiety, etc.) is extracted.

[1944] Step 4:

[1945] The server generates a list of product candidates using a generative AI model (e.g., OpenAI's GPT-4) based on the analyzed emotional information and purchasing conditions. At this stage, the model makes product suggestions based on the input data and generates suitable product candidates as output data in the form of a list.

[1946] Step 5:

[1947] The server converts the generated product candidate list into JSON format and returns it to the terminal. The terminal analyzes the received data and presents the product candidate list to the user. Here, data conversion and display on the user interface are performed.

[1948] Step 6:

[1949] The user checks the presented product candidate list and enters more specific desired conditions (design, specific functions, etc.). After entering the additional conditions, the user presses the "Search Again" button, and the data is sent again to the server via the terminal. The additional conditions are added as input data.

[1950] Step 7:

[1951] The server re-searches and narrows down the candidate list based on the newly received additional conditions and the re-analyzed emotional information. If the emotional information is analyzed as "satisfied," products that more closely match the user's conditions are listed. The re-generated product candidate list becomes the output data.

[1952] Step 8:

[1953] The server converts the updated candidate list into JSON format and resends it to the device. The device again parses the received data and presents the updated product candidate list to the user. Here, data conversion and display on the UI are also performed.

[1954] Step 9:

[1955] The user selects the desired product from the final candidate list and completes the purchase procedure. The selection data is sent to the server via the terminal. The final selected product and purchase information are provided as input data.

[1956] Step 10:

[1957] The server processes the purchase procedure based on the received selection data. The purchase information is recorded in a database and a purchase completion email is sent to the user. Here, the purchase process is executed and confirmation data is sent.

[1958] This allows users to receive product suggestions that take their emotions into consideration and make purchases with peace of mind.

[1959] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1960] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1961] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1962] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1963] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1964] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1965] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1966] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1967] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1968] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1969] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1970] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1971] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1972] 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.

[1973] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1974] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1975] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of mu...

Claims

1. A means for users to input their educational requirements, A means for suggesting suitable educational destinations based on the input conditions; means for presenting the proposed educational destinations to a user and receiving additional requirements; A means for narrowing down the candidates for further education based on the additional conditions; A means for users to make reservations at their chosen destination; A system including:

2. The system according to claim 1, which uses a generative AI model to suggest further education destinations based on the conditions for further education.

3. 2. The system according to claim 1, wherein attribute data of the educational institution is managed using a database, and a search is performed based on said conditions.

Images