system

Abstract

We provide the system. [Solution] A means of receiving and storing user-entered household information in a database, A means by which artificial intelligence calculates admission points using an algorithm designed based on the received information, Based on the calculated score, a method is used to predict the probability of admission by referring to the historical difficulty level of each application facility, A means of visualizing the prediction results for the user, A means of listing the documents required for the application process and providing instructions on how to prepare them, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the modern social environment, enrolling a child in a childcare facility is a complex and stressful issue for many parents. Specifically, there are different enrollment criteria and point systems depending on each local government and childcare facility. Due to the opaque and unpredictable enrollment selection process, it is difficult for parents to determine which childcare facility to apply to. In addition, there is a lack of information to smoothly carry out the complicated application procedures, which has become a burden on parents. Under such circumstances, parents have no choice but to spend a great deal of time and effort. The purpose of this invention is to achieve transparent prediction of enrollment selection results and efficiency improvement of application procedures in order to solve these problems.

Means for Solving the Problems

[0005] The system of this invention improves the accuracy of predictions by utilizing user-entered household information and calculating admission points using artificial intelligence. Specifically, it has a function to receive information about the living environment provided by the user and record it in a database. Subsequently, based on a set algorithm, the artificial intelligence calculates points and, based on the results, refers to past admission performance data to predict whether admission to each applied facility will be possible. Furthermore, it visualizes the predicted admission probability and provides it to the user, giving them information to formulate the optimal application strategy. This system also has a function to list the documents required for application and guide the user through the creation procedure, helping the user to easily complete the application. In this way, it reduces anxiety and burden regarding admission to childcare facilities and realizes fair and efficient information provision.

[0006] A "user" is a parent who wishes to enroll their child in a childcare facility using the system, and is the entity that inputs personal information and data related to the family situation.

[0007] "Family information to be entered" refers to personal information provided by the user to the system, such as family structure, employment status, place of residence, and preferred childcare facility.

[0008] A "database" is a collection of information that stores data obtained from users and is used to calculate admission points and predict admission probabilities.

[0009] "Artificial intelligence" is a technology that uses a specific algorithm to calculate admission scores based on household information entered by the user, and predicts the probability of admission.

[0010] An "algorithm" is a set of procedures and rules for calculating admission points based on user input, and it defines the operation of artificial intelligence.

[0011] "Admission points" are a numerical representation of a user's employment status and home environment, based on standards set by each local government and childcare facility, and serve as an indicator for admission selection.

[0012] "Predicting the probability of admission" is the process of probabilistically estimating whether or not a user will be able to enter their desired facility, based on admission scores calculated by artificial intelligence and historical data of the facility.

[0013] "Visualization" refers to a method of presenting information to support decision-making by displaying the predicted probability of admission in a way that is easy for users to understand.

[0014] The "application process" refers to the series of steps involved in creating and submitting the necessary documents for a user to enroll in a childcare facility.

[0015] "Listing" refers to the process of organizing and listing the application documents required by the user, with the aim of assisting with the application process.

[0016] "Guidance on creation methods" refers to a guide function that provides users with the steps and necessary information for creating the listed documents, thereby facilitating the application process. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

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

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

[0021] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0025] [First Embodiment]

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

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

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

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

[0030] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

[0036] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0038] The system for implementing this invention mainly consists of a server, a terminal, and a user. The user here is a parent who wishes to enroll their child in a childcare facility and is the entity that provides the necessary information to the system. The terminal plays the role of providing an interface for the user to input information and receive results from the system. The server performs the central functions of this system, receiving, storing, processing, and providing results for information.

[0039] 1. Information gathering and input

[0040] Users access the system via a terminal and enter their household information. This information includes employment status, family structure, residential area, and preferred childcare facilities. The terminal sends this information to the server, which stores it in a database.

[0041] 2. Calculation of admission points

[0042] The server uses artificial intelligence to calculate admission points based on information stored in the database. The calculation uses algorithms based on standards set by each local government and facility, ensuring objective scoring.

[0043] 3. Predicting the probability of admission

[0044] Based on the calculated score, the server refers to past admission data and facility difficulty data to predict the user's probability of entering their desired facility. This prediction is then provided to the user via the terminal.

[0045] 4. Providing a guide for the application process.

[0046] Along with the prediction results, the server generates a list of documents required for the application and guides the user on how to create each document. This guidance is provided to the user via their terminal, allowing them to efficiently proceed with the application process.

[0047] As a concrete example, here is an example of a user.

[0048] Example: Suppose a parent is a full-time working parent of two children living in Tokyo. This parent logs into the system from their terminal and enters the necessary information. The server calculates admission points based on this information and then predicts the probability of admission to the desired childcare facility using past data. Along with the prediction results, it provides a guide on the necessary application documents and how to complete them. Through this process, parents can make the best choice based on their circumstances and reduce anxiety about admission.

[0049] The following describes the processing flow.

[0050] Step 1:

[0051] The user accesses the system's login page using their device, enters their authentication information, and logs into the system. After successful login, a screen appears where they can enter information about their household.

[0052] Step 2:

[0053] Users enter information such as their employment status, family structure, residential area, and preferred childcare facility into the terminal, and then click the "Submit" button. The entered information is sent from the terminal to the server.

[0054] Step 3:

[0055] The server stores user information received from the terminal in a database. This stored information is then used in subsequent processing.

[0056] Step 4:

[0057] The server retrieves user information from the database and uses an artificial intelligence algorithm to calculate the user's admission score. The calculation takes into account the evaluation criteria of each local government.

[0058] Step 5:

[0059] Based on the calculated admission score, the server retrieves past admission data and difficulty information for each facility from the database and predicts the probability of admission to the desired childcare facility.

[0060] Step 6:

[0061] The server generates a visualization of the predicted probability of park entry and sends the results to the user's device. The user can then view these results on their device.

[0062] Step 7:

[0063] The server will also list the necessary application documents and generate a guide for completing each document, if requested by the user. This information will be presented to the user on their terminal and provided as guidance for the application process.

[0064] (Example 1)

[0065] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0066] In the application process for childcare facilities, applicants often struggle to effectively manage necessary information and accurately predict their chances of admission. Furthermore, there is a lack of support in developing optimal strategies for facility selection and application preparation. These problems lead to parents wasting time and effort, and proceeding with the process while feeling anxious.

[0067] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0068] This invention includes a server that receives and stores user-inputted household information in an information collection, a machine learning technique that calculates admission points using an algorithm designed based on the received information, and a means that predicts the likelihood of admission based on the calculated points and by referring to the historical difficulty level of each facility applied for. This enables users to efficiently manage the information necessary for admission procedures and to make reliable predictions of admission likelihood. Furthermore, by utilizing historical data analysis by a generative AI model, it becomes possible to improve the probability of admission and formulate an optimal application strategy, thereby reducing the burden on the user.

[0069] A "user" is an entity that utilizes a service through an information system for a specific purpose.

[0070] An "information collection" refers to a recording medium or data storage where various information received from users is organized and stored.

[0071] "Machine learning techniques" is a general term for algorithms or methods that allow computers to analyze past data and perform pattern recognition and prediction.

[0072] "Admission points" are a numerical value used by users to determine whether or not their child is eligible for admission to a childcare facility. It is an evaluation indicator calculated based on available information.

[0073] "Historical difficulty" refers to the degree of difficulty in gaining admission to a particular facility, measured based on past admission data.

[0074] "Possibility of admission" refers to the probability or likelihood that a user will be admitted to the facility they wish to attend.

[0075] A "generative AI model" is a form of artificial intelligence, a mathematical structure or algorithm for generating new information from data.

[0076] This invention relates to an information system that assists with the enrollment process at childcare facilities. This system mainly consists of a server, terminals, and users.

[0077] Users access the system using a terminal and enter information about their family. This information includes family structure, employment status, residential area, and preferred childcare facilities. The terminal can then transmit the entered information to the server.

[0078] The server stores the received data as an information set and uses machine learning techniques based on it. Specifically, it calculates admission points by applying an algorithm based on the received data. In this process, a generative AI model is used in machine learning, and it predicts the likelihood of admission by referring to historical difficulty data.

[0079] The server also has the function of visualizing the predicted likelihood of admission and providing relevant information to the user via the terminal. This allows users to efficiently prepare the documents necessary for admission. The server reduces the burden on the user by acting as a guide for the application process, providing a list of necessary documents and instructions on how to create them.

[0080] As a concrete example, consider a full-time working parent of two children living in Tokyo using this system. This user enters their information through a terminal, and the server uses that information to calculate an admission score and predicts a 70% chance of admission. The server then shows the user a list of required application documents and instructions on how to prepare each document.

[0081] An example of a prompt for a generated AI model is: "Describe a system that helps a full-time working parent of two children living in Tokyo make the best choice for enrolling them in childcare facilities."

[0082] This invention helps users complete accurate and efficient admission procedures.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] Users log in to the system via a terminal and enter information such as family structure, employment status, residential area, and preferred childcare facility. This entered information is formatted by the terminal and sent to the server. The server verifies this information and stores it in a database. This stored data forms the basis for analysis in subsequent processing.

[0086] Step 2:

[0087] The server retrieves user information stored in the database and uses machine learning techniques to calculate admission scores. This process applies an algorithm based on the received information. Specifically, the server calculates weights for family structure and employment status, and uses these to generate an overall admission score. This score serves as a basis for evaluating the likelihood of admission.

[0088] Step 3:

[0089] The server uses the calculated admission score to refer to past admission data and historical difficulty data for the facility. It utilizes a generative AI model to predict the likelihood of admission. Based on this data, the server builds a probabilistic model and calculates the probability of admission to the user's desired facility. The result is output as a specific percentage.

[0090] Step 4:

[0091] The server provides prediction results to the user via the terminal. The terminal uses a visual interface to display the information in a way that is easy for the user to understand. Based on this, the user can consider a strategy for admission to the park.

[0092] Step 5:

[0093] The server generates a list of documents required for the application and provides instructions on how to create each document. The server organizes the necessary information and provides a detailed guide through the terminal. This guide helps users efficiently complete the application process.

[0094] (Application Example 1)

[0095] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0096] In modern urban areas, parents lack sufficient information to decide which childcare facility to apply to. Furthermore, the application process is often cumbersome, and there is a lack of efficient guidance.

[0097] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0098] This invention includes a server that receives and stores user-inputted household information in a database, a means for artificial intelligence to calculate admission points using an algorithm designed based on the received information, and a means for predicting the probability of admission based on the calculated points and referring to the historical difficulty level of each facility being applied to. This allows parents to determine the best option from multiple facilities and proceed with the application process efficiently.

[0099] A "user" is an individual who uses the system to check eligibility for admission to a childcare facility and proceed with the necessary application procedures.

[0100] "Family information" refers to data that users input into the system, such as employment status, family structure, and residential area.

[0101] A "database" is an information storage system that stores information received from users and allows it to be referenced as needed.

[0102] An "algorithm" is a calculation procedure used to determine admission points based on the received information.

[0103] "Artificial intelligence" is a technology that uses computers to calculate and predict admission scores and probabilities based on input data.

[0104] "Admission points" are numerical values ​​calculated to evaluate the likelihood of admission to each childcare facility based on information about the family.

[0105] "Probability of admission" is a numerical representation of the likelihood of a user being able to enroll their child in their desired childcare facility.

[0106] "Visualization" refers to displaying the prediction results calculated by the server in a way that is easy for the user to understand.

[0107] The "application process" refers to the process of completing the necessary procedures for a user to enroll in a childcare facility.

[0108] A "server device" is a device that performs processing to provide facility information and manages the entire system.

[0109] This invention is a system that allows parents to calculate their chances of admission to a childcare facility and determine the optimal application method via a device such as a smartphone. The system consists mainly of a user, a device, and a server.

[0110] The server receives the family information entered by the user and stores it in a database. Next, it uses an algorithm based on the received information to calculate admission points. Here, artificial intelligence technology from TENSORFLOW® is used for evaluation. Based on the calculated points, and referring to past data, the probability of admission to each applied facility is predicted. The predicted results are visualized on the user's terminal, allowing the user to make an appropriate decision.

[0111] Furthermore, the server lists the documents required for the application process to enroll and guides the user on how to complete each document. For the user, these guidelines are a useful tool for efficiently completing the application process.

[0112] A concrete example would be a full-time working parent accessing the system via smartphone and entering the necessary information. The server would then quickly calculate admission points based on the submitted information and return the results to the parent, thereby assisting in the selection of a childcare facility. By utilizing a generative AI model, this process can be streamlined.

[0113] An example of a prompt to a generated AI model is: "I would like to know the probability of getting my child into a daycare center in Minato Ward. I work full-time, and I have two children, aged 3 and 1. Please calculate my admission score and the probability." Using prompts like this allows users to gain more information to make informed decisions.

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The user uses a terminal to input and submit household information (employment status, family structure, residential area, etc.). This constitutes the input information. The terminal then transfers this information to the server. The output is the transmission of data to the server.

[0117] Step 2:

[0118] The server stores the user's home information received in a database. The input is the home information received from the terminal, and by storing this input information in the database, centralized information management is achieved. The output is the saving of data to the database.

[0119] Step 3:

[0120] The server uses a generative AI model to calculate admission points based on stored information. The input is family information retrieved from a database. TensorFlow is used to perform calculations based on this data and calculate admission points. The output is the calculated admission points.

[0121] Step 4:

[0122] The server uses the previously calculated admission score and references past admission data to predict the probability of admission. The inputs are the calculated admission score and past data. The output is the predicted probability calculated based on the admission probability calculation.

[0123] Step 5:

[0124] The server sends the prediction results to the user's device in a visualized format. The input is the predicted probability of admission, and a visual design is created to display it clearly on the user's device. The output is the visualized data provided to the device.

[0125] Step 6:

[0126] The server generates a list of application documents required by the user and provides a guide on how to create each document. The input consists of prediction results and user information, and the generated document list and its creation guide are output. This is then sent back to the terminal and provided to the user.

[0127] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0128] The system implementing this invention comprises a server, a terminal, a user, and an emotion engine. The user is the entity that wishes to enroll in a childcare facility and provides information about their family situation and the desired facility. The terminal serves as an interface for the user to input information and receive results. The server is responsible for processing and analyzing the information, and the emotion engine recognizes the user's emotions and performs corresponding processing.

[0129] 1. Information gathering and input

[0130] Users access the system through a terminal and enter their household information. This information includes employment status, family structure, residential area, and desired facilities. The terminal sends the entered information to the server, which stores this information in a database.

[0131] 2. Calculation of admission points

[0132] The server retrieves user information from the database and uses artificial intelligence to calculate admission points. The calculation of points uses algorithms based on the standards of each local government.

[0133] 3. Predicting the probability of admission

[0134] Based on the calculated score, the server uses past data to predict the probability of entering the desired facility. This prediction is provided from the server to the terminal in real time and visualized for the user.

[0135] 4. Emotional analysis and feedback

[0136] The server uses an emotion engine to recognize emotions from text and voice data entered by the user. The recognized emotion information is used to present admission strategies and adjust the interface. For example, if the user is feeling anxious, the server visually presents explanations and options to help them feel more at ease.

[0137] 5. Support for the application process

[0138] Based on the predicted probability of admission, the server presents the user with the optimal application strategy. Furthermore, it lists the documents the user needs and provides a guide through the terminal. The emotion engine optimizes the content and delivery method of the guide according to the user's emotional state.

[0139] Specific example:

[0140] One user is looking for a daycare center to care for their child while they work. When this user accesses the system via smartphone and enters their situation, the server uses an emotion engine to analyze the user's current emotions from the entered text and voice. For example, if the user is feeling stressed, the server reduces their anxiety by presenting detailed options regarding daycare selection and guides emphasizing the simplicity of the process. In this way, the user can make better decisions and proceed with confidence.

[0141] The following describes the processing flow.

[0142] Step 1:

[0143] Users log in to the system using their device and access a screen to enter their family information. This information includes details about the user's employment status, residential area, and preferred childcare facilities.

[0144] Step 2:

[0145] The terminal sends the information entered by the user to the server. The transmitted information is stored in a database on the server.

[0146] Step 3:

[0147] The server retrieves the user's family information from the database, and artificial intelligence calculates the admission score using a pre-configured algorithm. The evaluation criteria of the local government are applied to this score calculation.

[0148] Step 4:

[0149] Based on the calculated admission score, the server refers to past admission data for childcare facilities and predicts the probability of admission to each desired facility. The server sends these prediction results to the terminal in real time.

[0150] Step 5:

[0151] The terminal visually displays the predicted probability of park entry received from the server to the user. Charts and graphs are used in the display to ensure that the information is intuitively understandable.

[0152] Step 6:

[0153] If a user requests support for a park admission strategy based on prediction results, the server uses an emotion engine to analyze the user's emotions, recognizing them from text and voice data.

[0154] Step 7:

[0155] The server considers the results of the emotion engine's analysis and generates the optimal application strategy and guide based on the user's situation and emotions, providing it to the user through the terminal. For example, if the user is feeling anxious, the system will provide detailed explanations and encouraging messages.

[0156] Step 8:

[0157] The server adjusts the interface according to the user's emotional state and optimizes the list of documents required for the application process and the guide on how to create them, presenting them to the terminal to improve the user experience.

[0158] (Example 2)

[0159] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0160] Systems designed to streamline the selection of application destinations and the application process based on household attribute information were traditionally often manual, lacking accuracy and efficiency. Furthermore, information was presented without considering the user's emotional state, making it difficult to provide appropriate feedback and application strategies. As a result, users were prone to anxiety and struggled to make optimal choices.

[0161] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0162] In this invention, the server includes means for receiving basic attribute information entered by the user and storing it in an information aggregation device, means for an information processing device to calculate an evaluation value using a processing method designed based on the received information, and means including an emotion recognition device that extracts emotions from the user's input information and adjusts the feedback. As a result, the user can build an effective application strategy based on a probabilistic pass / fail prediction and receive emotion-appropriate feedback, enabling them to proceed with the procedure with peace of mind.

[0163] "Basic attribute information" refers to basic information about the user's household, such as family structure, address, employment status, and desired facilities.

[0164] An "information storage device" refers to a function within a system for storing information received from users, and generally functions as a database.

[0165] "Processing method" refers to the algorithms and calculation methods used by the server to analyze the information it receives and calculate evaluation values.

[0166] An "information processing device" refers to a device or program designed to calculate evaluation values ​​from received data.

[0167] "Evaluation score" refers to a numerical value calculated from the user's basic attribute information, and is an indicator used to evaluate the probability of admission.

[0168] An "emotion recognition device" refers to a mechanism or program that extracts emotions from user input information and adjusts feedback based on that information.

[0169] "Feedback" refers to information and advice provided to the user as a result of adjustments made by an emotion recognition device, and is presented in a way that takes the user's emotions into consideration.

[0170] The system implementing this invention consists of an information processing device (server), an information presentation device (terminal), and an information provider (user). The server starts by receiving basic attribute information entered by the user and storing this information in an information aggregation device.

[0171] The server uses a generated AI model based on the received information to analyze the received data. In this analysis, it uses processing methods to calculate evaluation values ​​from user attribute information. The server can use a database management system or an AI analysis platform in this process.

[0172] Next, the server references historical data and predicts the probability of passing or failing based on the evaluation score. This prediction utilizes statistical methods and machine learning techniques and can be performed in real time. The prediction results are provided to the user visually through the terminal. The terminal is equipped with a graphical user interface (GUI) and presents information in a way that is easy for the user to understand.

[0173] Furthermore, the server utilizes an emotion recognition device to extract emotions from the information entered by the user. For example, it analyzes the user's text and voice data to identify emotions such as stress and a sense of security. Based on this, the server adjusts the content of the feedback to provide the user with the most appropriate information. Natural language processing and speech analysis technologies are used to adjust this emotional feedback.

[0174] To give a specific example, when a user is entering information into the system to decide on a daycare center for their child, if the emotion recognition device detects the user's anxiety, the server can alleviate the user's anxiety by displaying a guide on the terminal that carefully explains the procedure.

[0175] The following prompt statements can be used as input to the generative AI model:

[0176] "I have entered information regarding childcare facilities. Please tell us your current feelings and your preferred childcare facility choice."

[0177] This allows users to consider options more smoothly and make acceptable decisions.

[0178] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0179] Step 1:

[0180] Users input basic attribute information through their device. This input data includes family structure, address, employment status, and preferred facilities. This data is sent from the device to the server via HTTP requests, etc. Specifically, the user enters the information into the interface of their smartphone or computer and completes the process by clicking the submit button.

[0181] Step 2:

[0182] The server stores basic attribute information received from the terminal in a database. During this process, the server checks data integrity and performs data cleaning as needed. Specifically, a database management system (DBMS) is used to ensure stable data storage. Input data consists of information from the user, and output is the information stored in the database.

[0183] Step 3:

[0184] The server retrieves information stored in the database and calculates evaluation scores using a generative AI model. The server uses an algorithm to quantify and process each data point. Specifically, a machine learning model is executed on the AI ​​processing platform. User information from the database is taken as input, and an evaluation score for admission is obtained as output.

[0185] Step 4:

[0186] The server uses historical data to predict the likelihood of admission based on evaluation scores. This utilizes a machine learning model based on the historical dataset. This model generates probabilities and sends them to the terminal. The inputs are evaluation scores and historical data, and the output is the admission probability. The data calculation involves running the prediction model.

[0187] Step 5:

[0188] The server uses an emotion recognition device to analyze text and voice data entered by the user and identify the user's emotions. Specific operations include natural language processing (NLP) and speech analysis techniques. Input includes the user's voice and text data, and output is data related to emotions.

[0189] Step 6:

[0190] The server adjusts the feedback based on the analysis results and provides it to the terminal. The feedback is tailored to the user's emotional state, providing reassuring guidance or information, for example. Specifically, a feedback message is generated and displayed on the user interface. Emotional data is used as input, and the adjusted feedback is obtained as output.

[0191] Step 7:

[0192] The server proposes the optimal application strategy, lists the necessary documents, and provides instructions on how to create them. This information is displayed on the terminal to support the user in taking efficient action. Specifically, it automatically generates a guidance guide and applies it to the terminal's display screen. The input is the predicted admission probability and evaluation value, and the output is a strategic guide.

[0193] (Application Example 2)

[0194] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0195] When it comes to the application process for childcare facilities, users often experience anxiety due to the complex information gathering and procedures involved. In such situations, it is difficult for users to develop accurate and efficient strategies for admission, and emotional support is needed.

[0196] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0197] In this invention, the server includes means for receiving and storing user-inputted household information in a database; means for artificial intelligence to calculate admission points using an algorithm designed based on the received information; means for predicting the probability of admission based on the calculated points and referring to the historical difficulty level of each facility applied for; means for analyzing the user's emotions and optimizing information provision based on the emotion analysis results; and means for a household robot to respond to user queries and provide feedback to alleviate user anxiety. This enables the user to receive information and support to proceed with the admission process with peace of mind.

[0198] "Family information" refers to data provided by users regarding their living situation, including information such as employment status, family structure, residential area, and preferred childcare facilities.

[0199] "Artificial intelligence" is a knowledge processing technology implemented by computer programs that automatically calculates admission points based on user input.

[0200] "Admission points" are a numerical value that quantifies the likelihood of admission to a childcare facility based on information provided by the user, and serve as a criterion for determining whether or not admission is possible.

[0201] The "probability of admission" is a predicted value that indicates the likelihood of being admitted to a particular childcare facility, based on the calculated admission score and past data.

[0202] "Sentiment analysis" is a technology that analyzes user input data to identify the user's emotions and psychological state, and then provides appropriate information based on that state.

[0203] A "household robot" is a device designed to assist with daily life, providing support services through dialogue within the user's home.

[0204] "Feedback" refers to information and suggestions for actions provided by a system to a user, intended to help the user make better decisions and take better actions.

[0205] To implement this invention, the user first inputs household information into the system using a smartphone or home robot. The terminal receives this information and stores it in a management database. On the server side, artificial intelligence is used to calculate admission points based on the information obtained from the database. In doing so, historical admission difficulty data for each region is also taken into consideration to predict the probability of admission.

[0206] The server utilizes a generative AI model to perform sentiment analysis on text and voice data entered by the user. Based on the analysis results, it provides information tailored to the user's current psychological state. This process utilizes sentiment analysis engines such as Microsoft's Azure Emotion API.

[0207] Following the sentiment analysis, the robot responds to user questions and provides feedback on predictions and procedures. The content and method of feedback are customized depending on the user's emotional state. If the user is particularly anxious, additional information and support are provided to convey reassurance.

[0208] For example, a user might enter a prompt such as, "I'm feeling stressed about applying for my child's admission to a daycare facility. What should I do?" In this case, the system can perform sentiment analysis and then provide information to reassure the user, as well as guidance on simplifying the process.

[0209] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0210] Step 1:

[0211] Users input household information using their smartphones or home robots. The device receives the input information and sends it to the server. The data entered includes employment status, family structure, and information about desired childcare facilities.

[0212] Step 2:

[0213] The server stores the received family information in a management database. This data is referenced in subsequent processing and used to calculate appropriate admission points. Database storage is performed using SQL or NoSQL.

[0214] Step 3:

[0215] The server retrieves household information from the database and uses artificial intelligence to calculate admission points. The AI ​​model used here applies algorithms to the pre-processed data and calculates points corresponding to each information item. Programming languages ​​such as Python and R are used for this calculation. As a result of the calculation, a user-specific admission point is output.

[0216] Step 4:

[0217] The server uses admission points to reference past data on the difficulty of admission to each facility and predicts the probability of admission to each childcare facility. This prediction uses a machine learning algorithm to build a probability model based on past data and outputs a probability based on the new data. The output admission probability is displayed to the user.

[0218] Step 5:

[0219] Users input questions or concerns into their device in text or voice format. The server processes the input text or voice data using an emotion recognition engine. Microsoft's Azure Emotion API, among others, is used to analyze the user's emotions. The analysis results are output as data indicating the user's emotional state.

[0220] Step 6:

[0221] The server uses the results of sentiment analysis to prepare to generate and provide information tailored to the user's psychological state. The generated information and feedback are further customized using a generative AI model and output as an answer that directly addresses the user's query. Consider the case where the prompt is an input such as, "I'm feeling stressed about applying for my child's admission to a daycare facility. What should I do?"

[0222] Step 7:

[0223] The device provides the user with emotion-optimized feedback, either visually or audibly. This feedback includes specific application procedures and reassuring information to help the user make better decisions. The outputted feedback includes detailed guides and options to alleviate user anxiety.

[0224] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0225] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0226] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0227] [Second Embodiment]

[0228] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0229] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0230] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0231] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0232] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0233] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0234] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0235] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0236] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0237] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0238] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0239] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0240] The system for implementing this invention mainly consists of a server, a terminal, and a user. The user here is a parent who wishes to enroll their child in a childcare facility and is the entity that provides the necessary information to the system. The terminal plays the role of providing an interface for the user to input information and receive results from the system. The server performs the central functions of this system, receiving, storing, processing, and providing results for information.

[0241] 1. Information gathering and input

[0242] Users access the system via a terminal and enter their household information. This information includes employment status, family structure, residential area, and preferred childcare facilities. The terminal sends this information to the server, which stores it in a database.

[0243] 2. Calculation of admission points

[0244] The server uses artificial intelligence to calculate admission points based on information stored in the database. The calculation uses algorithms based on standards set by each local government and facility, ensuring objective scoring.

[0245] 3. Predicting the probability of admission

[0246] Based on the calculated score, the server refers to past admission data and facility difficulty data to predict the user's probability of entering their desired facility. This prediction is then provided to the user via the terminal.

[0247] 4. Providing a guide for the application process.

[0248] Along with the prediction results, the server generates a list of documents required for the application and guides the user on how to create each document. This guidance is provided to the user via their terminal, allowing them to efficiently proceed with the application process.

[0249] As a concrete example, here is an example of a user.

[0250] Example: Suppose a parent is a full-time working parent of two children living in Tokyo. This parent logs into the system from their terminal and enters the necessary information. The server calculates admission points based on this information and then predicts the probability of admission to the desired childcare facility using past data. Along with the prediction results, it provides a guide on the necessary application documents and how to complete them. Through this process, parents can make the best choice based on their circumstances and reduce anxiety about admission.

[0251] The following describes the processing flow.

[0252] Step 1:

[0253] The user accesses the system's login page using their device, enters their authentication information, and logs into the system. After successful login, a screen appears where they can enter information about their household.

[0254] Step 2:

[0255] Users enter information such as their employment status, family structure, residential area, and preferred childcare facility into the terminal, and then click the "Submit" button. The entered information is sent from the terminal to the server.

[0256] Step 3:

[0257] The server stores user information received from the terminal in a database. This stored information is then used in subsequent processing.

[0258] Step 4:

[0259] The server retrieves user information from the database and uses an artificial intelligence algorithm to calculate the user's admission score. The calculation takes into account the evaluation criteria of each local government.

[0260] Step 5:

[0261] Based on the calculated admission score, the server retrieves past admission data and difficulty information for each facility from the database and predicts the probability of admission to the desired childcare facility.

[0262] Step 6:

[0263] The server generates a visualization of the predicted probability of park entry and sends the results to the user's device. The user can then view these results on their device.

[0264] Step 7:

[0265] The server will also list the necessary application documents and generate a guide for completing each document, if requested by the user. This information will be presented to the user on their terminal and provided as guidance for the application process.

[0266] (Example 1)

[0267] Next, we will describe Example 1. 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."

[0268] In the application process for childcare facilities, applicants often struggle to effectively manage necessary information and accurately predict their chances of admission. Furthermore, there is a lack of support in developing optimal strategies for facility selection and application preparation. These problems lead to parents wasting time and effort, and proceeding with the process while feeling anxious.

[0269] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0270] This invention includes a server that receives and stores user-inputted household information in an information collection, a machine learning technique that calculates admission points using an algorithm designed based on the received information, and a means that predicts the likelihood of admission based on the calculated points and by referring to the historical difficulty level of each facility applied for. This enables users to efficiently manage the information necessary for admission procedures and to make reliable predictions of admission likelihood. Furthermore, by utilizing historical data analysis by a generative AI model, it becomes possible to improve the probability of admission and formulate an optimal application strategy, thereby reducing the burden on the user.

[0271] A "user" is an entity that utilizes a service through an information system for a specific purpose.

[0272] An "information collection" refers to a recording medium or data storage where various information received from users is organized and stored.

[0273] "Machine learning techniques" is a general term for algorithms or methods that allow computers to analyze past data and perform pattern recognition and prediction.

[0274] "Admission points" are a numerical value used by users to determine whether or not their child is eligible for admission to a childcare facility. It is an evaluation indicator calculated based on available information.

[0275] "Historical difficulty" refers to the degree of difficulty in gaining admission to a particular facility, measured based on past admission data.

[0276] "Possibility of admission" refers to the probability or likelihood that a user will be admitted to the facility they wish to attend.

[0277] A "generative AI model" is a form of artificial intelligence, a mathematical structure or algorithm for generating new information from data.

[0278] This invention relates to an information system that assists with the enrollment process at childcare facilities. This system mainly consists of a server, terminals, and users.

[0279] Users access the system using a terminal and enter information about their family. This information includes family structure, employment status, residential area, and preferred childcare facilities. The terminal can then transmit the entered information to the server.

[0280] The server stores the received data as an information set and uses machine learning techniques based on it. Specifically, it calculates admission points by applying an algorithm based on the received data. In this process, a generative AI model is used in machine learning, and it predicts the likelihood of admission by referring to historical difficulty data.

[0281] In addition, the server has a function of visualizing the predicted入园可能性 (the probability of entering the nursery) and providing the relevant information to the user through the terminal. As a result, the user can efficiently prepare the documents required for the入园手続き (the admission procedure). The server guides the user as a guide for the application procedure, reducing the burden on the user by presenting a list of required documents and how to create them.

[0282] As a specific example, consider the case where a parent with two children living in Tokyo who works full-time uses this system. When this user inputs their information through the terminal, the server calculates the入园点数 (the admission score) based on this information and predicts a 70% probability of entering the nursery. Subsequently, the server shows the user a list of required application documents and how to prepare each document.

[0283] As an example of the prompt sentence for the generative AI model, "Please explain a system that supports a parent with two children living in Tokyo who works full-time in making the optimal choice for nursery admission" can be cited.

[0284] Thus, the present invention supports the user in performing an accurate and efficient admission procedure.

[0285] The flow of the specific process in Example 1 will be described using FIG. 11.

[0286] Step 1:

[0287] The user logs in to the system via the terminal and inputs information such as family composition, employment status, residential area, and desired nursery. These inputted information are formatted by the terminal and sent to the server. The server confirms this information and saves it in the database. This saved data serves as the basis for subsequent analysis.

[0288] Step 2:

[0289] It should be noted that the term "入园可能性" and "入园手続き" are specific to the original text and may need to be further adjusted according to the actual context. Here, rough translations are provided for the purpose of translation requirements.The server retrieves user information stored in the database and uses machine learning techniques to calculate admission scores. This process applies an algorithm based on the received information. Specifically, the server calculates weights for family structure and employment status, and uses these to generate an overall admission score. This score serves as a basis for evaluating the likelihood of admission.

[0290] Step 3:

[0291] The server uses the calculated admission score to refer to past admission data and historical difficulty data for the facility. It utilizes a generative AI model to predict the likelihood of admission. Based on this data, the server builds a probabilistic model and calculates the probability of admission to the user's desired facility. The result is output as a specific percentage.

[0292] Step 4:

[0293] The server provides prediction results to the user via the terminal. The terminal uses a visual interface to display the information in a way that is easy for the user to understand. Based on this, the user can consider a strategy for admission to the park.

[0294] Step 5:

[0295] The server generates a list of documents required for the application and provides instructions on how to create each document. The server organizes the necessary information and provides a detailed guide through the terminal. This guide helps users efficiently complete the application process.

[0296] (Application Example 1)

[0297] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0298] In modern urban areas, parents lack sufficient information to decide which childcare facility to apply to. Furthermore, the application process is often cumbersome, and there is a lack of efficient guidance.

[0299] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0300] This invention includes a server that receives and stores user-inputted household information in a database, a means for artificial intelligence to calculate admission points using an algorithm designed based on the received information, and a means for predicting the probability of admission based on the calculated points and referring to the historical difficulty level of each facility being applied to. This allows parents to determine the best option from multiple facilities and proceed with the application process efficiently.

[0301] A "user" is an individual who uses the system to check eligibility for admission to a childcare facility and proceed with the necessary application procedures.

[0302] "Family information" refers to data that users input into the system, such as employment status, family structure, and residential area.

[0303] A "database" is an information storage system that stores information received from users and allows it to be referenced as needed.

[0304] An "algorithm" is a calculation procedure used to determine admission points based on the received information.

[0305] "Artificial intelligence" is a technology that uses computers to calculate and predict admission scores and probabilities based on input data.

[0306] "Admission points" are numerical values ​​calculated to evaluate the likelihood of admission to each childcare facility based on information about the family.

[0307] The "probability of admission" is a quantification of the possibility for a user to be admitted to a childcare facility that the user desires.

[0308] "Visualization" refers to presenting the prediction results calculated by the server in a form that is easy for the user to understand.

[0309] The "application procedure" is a process in which a user performs the procedures necessary to be admitted to a childcare facility.

[0310] The "server device" is a device that performs processing to provide facility information and manages the entire system.

[0311] This invention is a system that allows a guardian to calculate the possibility of admission to a childcare facility and grasp the optimal application method via a terminal such as a smartphone. The system is mainly composed of a user, a terminal, and a server.

[0312] The server receives the information of the user's family entered by the user and stores it in the database. Next, based on the received information, an algorithm is used to calculate the admission score. Here, the artificial intelligence technology of TensorFlow is used for evaluation. Based on the calculated score, while referring to past data, the probability of admission to each application facility is predicted. The predicted result is visualized on the user's terminal, and the user can make an appropriate judgment by viewing it.

[0313] Furthermore, the server lists up the documents for the application procedures required for admission and guides the user on how to create each document. This guideline is a useful means for the user to efficiently execute the application procedures.

[0314] A concrete example would be a full-time working parent accessing the system via smartphone and entering the necessary information. The server would then quickly calculate admission points based on the submitted information and return the results to the parent, thereby assisting in the selection of a childcare facility. By utilizing a generative AI model, this process can be streamlined.

[0315] An example of a prompt to a generated AI model is: "I would like to know the probability of getting my child into a daycare center in Minato Ward. I work full-time, and I have two children, aged 3 and 1. Please calculate my admission score and the probability." Using prompts like this allows users to gain more information to make informed decisions.

[0316] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0317] Step 1:

[0318] The user uses a terminal to input and submit household information (employment status, family structure, residential area, etc.). This constitutes the input information. The terminal then transfers this information to the server. The output is the transmission of data to the server.

[0319] Step 2:

[0320] The server stores the user's home information received in a database. The input is the home information received from the terminal, and by storing this input information in the database, centralized information management is achieved. The output is the saving of data to the database.

[0321] Step 3:

[0322] The server uses a generative AI model to calculate admission points based on stored information. The input is family information retrieved from a database. TensorFlow is used to perform calculations based on this data and calculate admission points. The output is the calculated admission points.

[0323] Step 4:

[0324] The server uses the previously calculated admission score and references past admission data to predict the probability of admission. The inputs are the calculated admission score and past data. The output is the predicted probability calculated based on the admission probability calculation.

[0325] Step 5:

[0326] The server sends the prediction results to the user's device in a visualized format. The input is the predicted probability of admission, and a visual design is created to display it clearly on the user's device. The output is the visualized data provided to the device.

[0327] Step 6:

[0328] The server generates a list of application documents required by the user and provides a guide on how to create each document. The input consists of prediction results and user information, and the generated document list and its creation guide are output. This is then sent back to the terminal and provided to the user.

[0329] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0330] The system implementing this invention comprises a server, a terminal, a user, and an emotion engine. The user is the entity that wishes to enroll in a childcare facility and provides information about their family situation and the desired facility. The terminal serves as an interface for the user to input information and receive results. The server is responsible for processing and analyzing the information, and the emotion engine recognizes the user's emotions and performs corresponding processing.

[0331] 1. Information gathering and input

[0332] Users access the system through a terminal and enter their household information. This information includes employment status, family structure, residential area, and desired facilities. The terminal sends the entered information to the server, which stores this information in a database.

[0333] 2. Calculation of admission points

[0334] The server retrieves user information from the database and uses artificial intelligence to calculate admission points. The calculation of points uses algorithms based on the standards of each local government.

[0335] 3. Predicting the probability of admission

[0336] Based on the calculated score, the server uses past data to predict the probability of entering the desired facility. This prediction is provided from the server to the terminal in real time and visualized for the user.

[0337] 4. Emotional analysis and feedback

[0338] The server uses an emotion engine to recognize emotions from text and voice data entered by the user. The recognized emotion information is used to present admission strategies and adjust the interface. For example, if the user is feeling anxious, the server visually presents explanations and options to help them feel more at ease.

[0339] 5. Support for the application process

[0340] Based on the predicted probability of admission, the server presents the user with the optimal application strategy. Furthermore, it lists the documents the user needs and provides a guide through the terminal. The emotion engine optimizes the content and delivery method of the guide according to the user's emotional state.

[0341] Specific example:

[0342] One user is looking for a daycare center to care for their child while they work. When this user accesses the system via smartphone and enters their situation, the server uses an emotion engine to analyze the user's current emotions from the entered text and voice. For example, if the user is feeling stressed, the server reduces their anxiety by presenting detailed options regarding daycare selection and guides emphasizing the simplicity of the process. In this way, the user can make better decisions and proceed with confidence.

[0343] The following describes the processing flow.

[0344] Step 1:

[0345] Users log in to the system using their device and access a screen to enter their family information. This information includes details about the user's employment status, residential area, and preferred childcare facilities.

[0346] Step 2:

[0347] The terminal sends the information entered by the user to the server. The transmitted information is stored in a database on the server.

[0348] Step 3:

[0349] The server retrieves the user's family information from the database, and artificial intelligence calculates admission points using a pre-configured algorithm. The evaluation criteria of the local government are applied to this point calculation.

[0350] Step 4:

[0351] Based on the calculated admission score, the server refers to past admission data for childcare facilities and predicts the probability of admission to each desired facility. The server sends these prediction results to the terminal in real time.

[0352] Step 5:

[0353] The terminal visually displays the predicted probability of park entry received from the server to the user. Charts and graphs are used in the display to ensure that the information is intuitively understandable.

[0354] Step 6:

[0355] If a user requests support for a park admission strategy based on prediction results, the server uses an emotion engine to analyze the user's emotions, recognizing them from text and voice data.

[0356] Step 7:

[0357] The server considers the results of the emotion engine's analysis and generates the optimal application strategy and guide based on the user's situation and emotions, providing it to the user through the terminal. For example, if the user is feeling anxious, the system will provide detailed explanations and encouraging messages.

[0358] Step 8:

[0359] The server adjusts the interface according to the user's emotional state and optimizes the list of documents required for the application process and the guide on how to create them, presenting them to the terminal to improve the user experience.

[0360] (Example 2)

[0361] Next, we will describe Example 2. 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".

[0362] Systems designed to streamline the selection of application destinations and the application process based on household attribute information were traditionally often manual, lacking accuracy and efficiency. Furthermore, information was presented without considering the user's emotional state, making it difficult to provide appropriate feedback and application strategies. As a result, users were prone to anxiety and struggled to make optimal choices.

[0363] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0364] In this invention, the server includes means for receiving basic attribute information entered by the user and storing it in an information aggregation device, means for an information processing device to calculate an evaluation value using a processing method designed based on the received information, and means including an emotion recognition device that extracts emotions from the user's input information and adjusts the feedback. As a result, the user can build an effective application strategy based on a probabilistic pass / fail prediction and receive emotion-appropriate feedback, enabling them to proceed with the procedure with peace of mind.

[0365] "Basic attribute information" refers to basic information about the user's household, such as family structure, address, employment status, and desired facilities.

[0366] An "information storage device" refers to a function within a system for storing information received from users, and generally functions as a database.

[0367] "Processing method" refers to the algorithms and calculation methods used by the server to analyze the information it receives and calculate evaluation values.

[0368] An "information processing device" refers to a device or program designed to calculate evaluation values ​​from received data.

[0369] "Evaluation score" refers to a numerical value calculated from the user's basic attribute information, and is an indicator used to evaluate the probability of admission.

[0370] An "emotion recognition device" refers to a mechanism or program that extracts emotions from user input information and adjusts feedback based on that information.

[0371] "Feedback" refers to information and advice provided to the user as a result of adjustments made by an emotion recognition device, and is presented in a way that takes the user's emotions into consideration.

[0372] The system implementing this invention consists of an information processing device (server), an information presentation device (terminal), and an information provider (user). The server starts by receiving basic attribute information entered by the user and storing this information in an information aggregation device.

[0373] The server uses a generated AI model based on the received information to analyze the received data. In this analysis, it uses processing methods to calculate evaluation values ​​from user attribute information. The server can use a database management system or an AI analysis platform in this process.

[0374] Next, the server references historical data and predicts the probability of passing or failing based on the evaluation score. This prediction utilizes statistical methods and machine learning techniques and can be performed in real time. The prediction results are provided to the user visually through the terminal. The terminal is equipped with a graphical user interface (GUI) and presents information in a way that is easy for the user to understand.

[0375] Furthermore, the server utilizes an emotion recognition device to extract emotions from the information entered by the user. For example, it analyzes the user's text and voice data to identify emotions such as stress and a sense of security. Based on this, the server adjusts the content of the feedback to provide the user with the most appropriate information. Natural language processing and speech analysis technologies are used to adjust this emotional feedback.

[0376] To give a specific example, when a user is entering information into the system to decide on a daycare center for their child, if the emotion recognition device detects the user's anxiety, the server can alleviate the user's anxiety by displaying a guide on the terminal that carefully explains the procedure.

[0377] The following prompt statements can be used as input to the generative AI model:

[0378] "I have entered information regarding childcare facilities. Please tell us your current feelings and your preferred childcare facility choice."

[0379] This allows users to consider options more smoothly and make acceptable decisions.

[0380] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0381] Step 1:

[0382] Users input basic attribute information through their device. This input data includes family structure, address, employment status, and preferred facilities. This data is sent from the device to the server via HTTP requests, etc. Specifically, the user enters the information into the interface of their smartphone or computer and completes the process by clicking the submit button.

[0383] Step 2:

[0384] The server stores basic attribute information received from the terminal in a database. During this process, the server checks data integrity and performs data cleaning as needed. Specifically, a database management system (DBMS) is used to ensure stable data storage. Input data consists of information from the user, and output is the information stored in the database.

[0385] Step 3:

[0386] The server retrieves information stored in the database and calculates evaluation scores using a generative AI model. The server uses an algorithm to quantify and process each data point. Specifically, a machine learning model is executed on the AI ​​processing platform. User information from the database is taken as input, and an evaluation score for admission is obtained as output.

[0387] Step 4:

[0388] The server uses historical data to predict the likelihood of admission based on evaluation scores. This utilizes a machine learning model based on the historical dataset. This model generates probabilities and sends them to the terminal. The inputs are evaluation scores and historical data, and the output is the admission probability. The data calculation involves running the prediction model.

[0389] Step 5:

[0390] The server uses an emotion recognition device to analyze text and voice data entered by the user and identify the user's emotions. Specific operations include natural language processing (NLP) and speech analysis techniques. Input includes the user's voice and text data, and output is data related to emotions.

[0391] Step 6:

[0392] The server adjusts the feedback based on the analysis results and provides it to the terminal. The feedback is tailored to the user's emotional state, providing reassuring guidance or information, for example. Specifically, a feedback message is generated and displayed on the user interface. Emotional data is used as input, and the adjusted feedback is obtained as output.

[0393] Step 7:

[0394] The server proposes the optimal application strategy, lists the necessary documents, and provides instructions on how to create them. This information is displayed on the terminal to support the user in taking efficient action. Specifically, it automatically generates a guidance guide and applies it to the terminal's display screen. The input is the predicted admission probability and evaluation value, and the output is a strategic guide.

[0395] (Application Example 2)

[0396] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0397] When it comes to the application process for childcare facilities, users often experience anxiety due to the complex information gathering and procedures involved. In such situations, it is difficult for users to develop accurate and efficient strategies for admission, and emotional support is needed.

[0398] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0399] In this invention, the server includes means for receiving and storing user-inputted household information in a database; means for artificial intelligence to calculate admission points using an algorithm designed based on the received information; means for predicting the probability of admission based on the calculated points and referring to the historical difficulty level of each facility applied for; means for analyzing the user's emotions and optimizing information provision based on the emotion analysis results; and means for a household robot to respond to user queries and provide feedback to alleviate user anxiety. This enables the user to receive information and support to proceed with the admission process with peace of mind.

[0400] "Family information" refers to data provided by users regarding their living situation, including information such as employment status, family structure, residential area, and preferred childcare facilities.

[0401] "Artificial intelligence" is a knowledge processing technology implemented by computer programs that automatically calculates admission points based on user input.

[0402] "Admission points" are a numerical value that quantifies the likelihood of admission to a childcare facility based on information provided by the user, and serve as a criterion for determining whether or not admission is possible.

[0403] The "probability of admission" is a predicted value that indicates the likelihood of being admitted to a particular childcare facility, based on the calculated admission score and past data.

[0404] "Sentiment analysis" is a technology that analyzes user input data to identify the user's emotions and psychological state, and then provides appropriate information based on that state.

[0405] A "household robot" is a device designed to assist with daily life, providing support services through dialogue within the user's home.

[0406] "Feedback" refers to information and suggestions for actions provided by a system to a user, intended to help the user make better decisions and take better actions.

[0407] To implement this invention, the user first inputs household information into the system using a smartphone or home robot. The terminal receives this information and stores it in a management database. On the server side, artificial intelligence is used to calculate admission points based on the information obtained from the database. In doing so, historical admission difficulty data for each region is also taken into consideration to predict the probability of admission.

[0408] The server utilizes a generative AI model to perform sentiment analysis on text and voice data entered by the user. Based on the analysis results, it provides information tailored to the user's current psychological state. This process utilizes sentiment analysis engines such as Microsoft's Azure Emotion API.

[0409] Following the sentiment analysis, the robot responds to user questions and provides feedback on predictions and procedures. The content and method of feedback are customized depending on the user's emotional state. If the user is particularly anxious, additional information and support are provided to convey reassurance.

[0410] For example, a user might enter a prompt such as, "I'm feeling stressed about applying for my child's admission to a daycare facility. What should I do?" In this case, the system can perform sentiment analysis and then provide information to reassure the user, as well as guidance on simplifying the process.

[0411] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0412] Step 1:

[0413] Users input household information using their smartphones or home robots. The device receives the input information and sends it to the server. The data entered includes employment status, family structure, and information about desired childcare facilities.

[0414] Step 2:

[0415] The server stores the received family information in a management database. This data is referenced in subsequent processing and used to calculate appropriate admission points. Database storage is performed using SQL or NoSQL.

[0416] Step 3:

[0417] The server retrieves household information from the database and uses artificial intelligence to calculate admission points. The AI ​​model used here applies algorithms to the pre-processed data and calculates points corresponding to each information item. Programming languages ​​such as Python and R are used for this calculation. As a result of the calculation, a user-specific admission point is output.

[0418] Step 4:

[0419] The server uses admission points to reference past data on the difficulty of admission to each facility and predicts the probability of admission to each childcare facility. This prediction uses a machine learning algorithm to build a probability model based on past data and outputs a probability based on the new data. The output admission probability is displayed to the user.

[0420] Step 5:

[0421] Users input questions or concerns into their device in text or voice format. The server processes the input text or voice data using an emotion recognition engine. Microsoft's Azure Emotion API, among others, is used to analyze the user's emotions. The analysis results are output as data indicating the user's emotional state.

[0422] Step 6:

[0423] The server uses the results of sentiment analysis to prepare to generate and provide information tailored to the user's psychological state. The generated information and feedback are further customized using a generative AI model and output as an answer that directly addresses the user's query. Consider the case where the prompt is an input such as, "I'm feeling stressed about applying for my child's admission to a daycare facility. What should I do?"

[0424] Step 7:

[0425] The device provides the user with emotion-optimized feedback, either visually or audibly. This feedback includes specific application procedures and reassuring information to help the user make better decisions. The outputted feedback includes detailed guides and options to alleviate user anxiety.

[0426] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0427] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0428] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0429] [Third Embodiment]

[0430] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0431] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0432] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0433] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0434] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0435] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0436] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0437] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0438] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0439] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0440] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0441] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0442] The system for implementing this invention mainly consists of a server, a terminal, and a user. The user here is a parent who wishes to enroll their child in a childcare facility and is the entity that provides the necessary information to the system. The terminal plays the role of providing an interface for the user to input information and receive results from the system. The server performs the central functions of this system, receiving, storing, processing, and providing results for information.

[0443] 1. Information gathering and input

[0444] Users access the system via a terminal and enter their household information. This information includes employment status, family structure, residential area, and preferred childcare facilities. The terminal sends this information to the server, which stores it in a database.

[0445] 2. Calculation of admission points

[0446] The server uses artificial intelligence to calculate admission points based on information stored in the database. The calculation uses algorithms based on standards set by each local government and facility, ensuring objective scoring.

[0447] 3. Predicting the probability of admission

[0448] Based on the calculated score, the server refers to past admission data and facility difficulty data to predict the user's probability of entering their desired facility. This prediction is then provided to the user via the terminal.

[0449] 4. Providing a guide for the application process.

[0450] Along with the prediction results, the server generates a list of documents required for the application and guides the user on how to create each document. This guidance is provided to the user via their terminal, allowing them to efficiently proceed with the application process.

[0451] As a concrete example, here is an example of a user.

[0452] Example: Suppose a parent is a full-time working parent of two children living in Tokyo. This parent logs into the system from their terminal and enters the necessary information. The server calculates admission points based on this information and then predicts the probability of admission to the desired childcare facility using past data. Along with the prediction results, it provides a guide on the necessary application documents and how to complete them. Through this process, parents can make the best choice based on their circumstances and reduce anxiety about admission.

[0453] The following describes the processing flow.

[0454] Step 1:

[0455] The user accesses the system's login page using their device, enters their authentication information, and logs into the system. After successful login, a screen appears where they can enter information about their household.

[0456] Step 2:

[0457] Users enter information such as their employment status, family structure, residential area, and preferred childcare facility into the terminal, and then click the "Submit" button. The entered information is sent from the terminal to the server.

[0458] Step 3:

[0459] The server stores user information received from the terminal in a database. This stored information is then used in subsequent processing.

[0460] Step 4:

[0461] The server retrieves user information from the database and uses an artificial intelligence algorithm to calculate the user's admission score. The calculation takes into account the evaluation criteria of each local government.

[0462] Step 5:

[0463] Based on the calculated admission score, the server retrieves past admission data and difficulty information for each facility from the database and predicts the probability of admission to the desired childcare facility.

[0464] Step 6:

[0465] The server generates a visualization of the predicted probability of park entry and sends the results to the user's device. The user can then view these results on their device.

[0466] Step 7:

[0467] The server will also list the necessary application documents and generate a guide for completing each document, if requested by the user. This information will be presented to the user on their terminal and provided as guidance for the application process.

[0468] (Example 1)

[0469] Next, we will describe Example 1. 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."

[0470] In the application process for childcare facilities, applicants often struggle to effectively manage necessary information and accurately predict their chances of admission. Furthermore, there is a lack of support in developing optimal strategies for facility selection and application preparation. These problems lead to parents wasting time and effort, and proceeding with the process while feeling anxious.

[0471] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0472] This invention includes a server that receives and stores user-inputted household information in an information collection, a machine learning technique that calculates admission points using an algorithm designed based on the received information, and a means that predicts the likelihood of admission based on the calculated points and by referring to the historical difficulty level of each facility applied for. This enables users to efficiently manage the information necessary for admission procedures and to make reliable predictions of admission likelihood. Furthermore, by utilizing historical data analysis by a generative AI model, it becomes possible to improve the probability of admission and formulate an optimal application strategy, thereby reducing the burden on the user.

[0473] A "user" is an entity that utilizes a service through an information system for a specific purpose.

[0474] An "information collection" refers to a recording medium or data storage where various information received from users is organized and stored.

[0475] "Machine learning techniques" is a general term for algorithms or methods that allow computers to analyze past data and perform pattern recognition and prediction.

[0476] "Admission points" are a numerical value used by users to determine whether or not their child is eligible for admission to a childcare facility. It is an evaluation indicator calculated based on available information.

[0477] "Historical difficulty" refers to the degree of difficulty in gaining admission to a particular facility, measured based on past admission data.

[0478] "Possibility of admission" refers to the probability or likelihood that a user will be admitted to the facility they wish to attend.

[0479] A "generative AI model" is a form of artificial intelligence, a mathematical structure or algorithm for generating new information from data.

[0480] This invention relates to an information system that assists with the enrollment process at childcare facilities. This system mainly consists of a server, terminals, and users.

[0481] Users access the system using a terminal and enter information about their family. This information includes family structure, employment status, residential area, and preferred childcare facilities. The terminal can then transmit the entered information to the server.

[0482] The server stores the received data as an information set and uses machine learning techniques based on it. Specifically, it calculates admission points by applying an algorithm based on the received data. In this process, a generative AI model is used in machine learning, and it predicts the likelihood of admission by referring to historical difficulty data.

[0483] The server also has the function of visualizing the predicted likelihood of admission and providing relevant information to the user via the terminal. This allows users to efficiently prepare the documents necessary for admission. The server reduces the burden on the user by acting as a guide for the application process, providing a list of necessary documents and instructions on how to create them.

[0484] As a concrete example, consider a full-time working parent of two children living in Tokyo using this system. This user enters their information through a terminal, and the server uses that information to calculate an admission score and predicts a 70% chance of admission. The server then shows the user a list of required application documents and instructions on how to prepare each document.

[0485] An example of a prompt for a generated AI model is: "Describe a system that helps a full-time working parent of two children living in Tokyo make the best choice for enrolling them in childcare facilities."

[0486] This invention helps users complete accurate and efficient admission procedures.

[0487] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0488] Step 1:

[0489] Users log in to the system via a terminal and enter information such as family structure, employment status, residential area, and preferred childcare facility. This entered information is formatted by the terminal and sent to the server. The server verifies this information and stores it in a database. This stored data forms the basis for analysis in subsequent processing.

[0490] Step 2:

[0491] The server retrieves user information stored in the database and uses machine learning techniques to calculate admission scores. This process applies an algorithm based on the received information. Specifically, the server calculates weights for family structure and employment status, and uses these to generate an overall admission score. This score serves as a basis for evaluating the likelihood of admission.

[0492] Step 3:

[0493] The server uses the calculated admission score to refer to past admission data and historical difficulty data for the facility. It utilizes a generative AI model to predict the likelihood of admission. Based on this data, the server builds a probabilistic model and calculates the probability of admission to the user's desired facility. The result is output as a specific percentage.

[0494] Step 4:

[0495] The server provides prediction results to the user via the terminal. The terminal uses a visual interface to display the information in a way that is easy for the user to understand. Based on this, the user can consider a strategy for admission to the park.

[0496] Step 5:

[0497] The server generates a list of documents required for the application and provides instructions on how to create each document. The server organizes the necessary information and provides a detailed guide through the terminal. This guide helps users efficiently complete the application process.

[0498] (Application Example 1)

[0499] Next, we will explain Application Example 1. In the following explanation, 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."

[0500] In modern urban areas, parents lack sufficient information to decide which childcare facility to apply to. Furthermore, the application process is often cumbersome, and there is a lack of efficient guidance.

[0501] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0502] This invention includes a server that receives and stores user-inputted household information in a database, a means for artificial intelligence to calculate admission points using an algorithm designed based on the received information, and a means for predicting the probability of admission based on the calculated points and referring to the historical difficulty level of each facility being applied to. This allows parents to determine the best option from multiple facilities and proceed with the application process efficiently.

[0503] A "user" is an individual who uses the system to check eligibility for admission to a childcare facility and proceed with the necessary application procedures.

[0504] "Family information" refers to data that users input into the system, such as employment status, family structure, and residential area.

[0505] A "database" is an information storage system that stores information received from users and allows it to be referenced as needed.

[0506] An "algorithm" is a calculation procedure used to determine admission points based on the received information.

[0507] "Artificial intelligence" is a technology that uses computers to calculate and predict admission scores and probabilities based on input data.

[0508] "Admission points" are numerical values ​​calculated to evaluate the likelihood of admission to each childcare facility based on information about the family.

[0509] "Probability of admission" is a numerical representation of the likelihood of a user being able to enroll their child in their desired childcare facility.

[0510] "Visualization" refers to displaying the prediction results calculated by the server in a way that is easy for the user to understand.

[0511] The "application process" refers to the process of completing the necessary procedures for a user to enroll in a childcare facility.

[0512] A "server device" is a device that performs processing to provide facility information and manages the entire system.

[0513] This invention is a system that allows parents to calculate their chances of admission to a childcare facility and determine the optimal application method via a device such as a smartphone. The system consists mainly of a user, a device, and a server.

[0514] The server receives the family information entered by the user and stores it in a database. Next, it uses an algorithm based on the received information to calculate admission points. Here, artificial intelligence technology using TensorFlow is used for evaluation. Based on the calculated points, and referring to past data, the probability of admission to each applied facility is predicted. The predicted results are visualized on the user's terminal, allowing the user to make an appropriate decision.

[0515] Furthermore, the server lists the documents required for the application process to enroll and guides the user on how to complete each document. For the user, these guidelines are a useful tool for efficiently completing the application process.

[0516] A concrete example would be a full-time working parent accessing the system via smartphone and entering the necessary information. The server would then quickly calculate admission points based on the submitted information and return the results to the parent, thereby assisting in the selection of a childcare facility. By utilizing a generative AI model, this process can be streamlined.

[0517] An example of a prompt to a generated AI model is: "I would like to know the probability of getting my child into a daycare center in Minato Ward. I work full-time, and I have two children, aged 3 and 1. Please calculate my admission score and the probability." Using prompts like this allows users to gain more information to make informed decisions.

[0518] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0519] Step 1:

[0520] The user uses a terminal to input and submit household information (employment status, family structure, residential area, etc.). This constitutes the input information. The terminal then transfers this information to the server. The output is the transmission of data to the server.

[0521] Step 2:

[0522] The server stores the user's home information received in a database. The input is the home information received from the terminal, and by storing this input information in the database, centralized information management is achieved. The output is the saving of data to the database.

[0523] Step 3:

[0524] The server uses a generative AI model to calculate admission points based on stored information. The input is family information retrieved from a database. TensorFlow is used to perform calculations based on this data and calculate admission points. The output is the calculated admission points.

[0525] Step 4:

[0526] The server uses the previously calculated admission score and references past admission data to predict the probability of admission. The inputs are the calculated admission score and past data. The output is the predicted probability calculated based on the admission probability calculation.

[0527] Step 5:

[0528] The server sends the prediction results to the user's device in a visualized format. The input is the predicted probability of admission, and a visual design is created to display it clearly on the user's device. The output is the visualized data provided to the device.

[0529] Step 6:

[0530] The server generates a list of application documents required by the user and provides a guide on how to create each document. The input consists of prediction results and user information, and the generated document list and its creation guide are output. This is then sent back to the terminal and provided to the user.

[0531] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0532] The system implementing this invention comprises a server, a terminal, a user, and an emotion engine. The user is the entity that wishes to enroll in a childcare facility and provides information about their family situation and the desired facility. The terminal serves as an interface for the user to input information and receive results. The server is responsible for processing and analyzing the information, and the emotion engine recognizes the user's emotions and performs corresponding processing.

[0533] 1. Information gathering and input

[0534] Users access the system through a terminal and enter their household information. This information includes employment status, family structure, residential area, and desired facilities. The terminal sends the entered information to the server, which stores this information in a database.

[0535] 2. Calculation of admission points

[0536] The server retrieves user information from the database and uses artificial intelligence to calculate admission points. The calculation of points uses algorithms based on the standards of each local government.

[0537] 3. Predicting the probability of admission

[0538] Based on the calculated score, the server uses past data to predict the probability of entering the desired facility. This prediction is provided from the server to the terminal in real time and visualized for the user.

[0539] 4. Emotional analysis and feedback

[0540] The server uses an emotion engine to recognize emotions from text and voice data entered by the user. The recognized emotion information is used to present admission strategies and adjust the interface. For example, if the user is feeling anxious, the server visually presents explanations and options to help them feel more at ease.

[0541] 5. Support for the application process

[0542] Based on the predicted probability of admission, the server presents the user with the optimal application strategy. Furthermore, it lists the documents the user needs and provides a guide through the terminal. The emotion engine optimizes the content and delivery method of the guide according to the user's emotional state.

[0543] Specific example:

[0544] One user is looking for a daycare center to care for their child while they work. When this user accesses the system via smartphone and enters their situation, the server uses an emotion engine to analyze the user's current emotions from the entered text and voice. For example, if the user is feeling stressed, the server reduces their anxiety by presenting detailed options regarding daycare selection and guides emphasizing the simplicity of the process. In this way, the user can make better decisions and proceed with confidence.

[0545] The following describes the processing flow.

[0546] Step 1:

[0547] Users log in to the system using their device and access a screen to enter their family information. This information includes details about the user's employment status, residential area, and preferred childcare facilities.

[0548] Step 2:

[0549] The terminal sends the information entered by the user to the server. The transmitted information is stored in a database on the server.

[0550] Step 3:

[0551] The server retrieves the user's family information from the database, and artificial intelligence calculates admission points using a pre-configured algorithm. The evaluation criteria of the local government are applied to this point calculation.

[0552] Step 4:

[0553] Based on the calculated admission score, the server refers to past admission data for childcare facilities and predicts the probability of admission to each desired facility. The server sends these prediction results to the terminal in real time.

[0554] Step 5:

[0555] The terminal visually displays the predicted probability of park entry received from the server to the user. Charts and graphs are used in the display to ensure that the information is intuitively understandable.

[0556] Step 6:

[0557] If a user requests support for a park admission strategy based on prediction results, the server uses an emotion engine to analyze the user's emotions, recognizing them from text and voice data.

[0558] Step 7:

[0559] The server considers the results of the emotion engine's analysis and generates the optimal application strategy and guide based on the user's situation and emotions, providing it to the user through the terminal. For example, if the user is feeling anxious, the system will provide detailed explanations and encouraging messages.

[0560] Step 8:

[0561] The server adjusts the interface according to the user's emotional state and optimizes the list of documents required for the application process and the guide on how to create them, presenting them to the terminal to improve the user experience.

[0562] (Example 2)

[0563] Next, we will describe Example 2. 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."

[0564] Systems designed to streamline the selection of application destinations and the application process based on household attribute information were traditionally often manual, lacking accuracy and efficiency. Furthermore, information was presented without considering the user's emotional state, making it difficult to provide appropriate feedback and application strategies. As a result, users were prone to anxiety and struggled to make optimal choices.

[0565] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0566] In this invention, the server includes means for receiving basic attribute information entered by the user and storing it in an information aggregation device, means for an information processing device to calculate an evaluation value using a processing method designed based on the received information, and means including an emotion recognition device that extracts emotions from the user's input information and adjusts the feedback. As a result, the user can build an effective application strategy based on a probabilistic pass / fail prediction and receive emotion-appropriate feedback, enabling them to proceed with the procedure with peace of mind.

[0567] "Basic attribute information" refers to basic information about the user's household, such as family structure, address, employment status, and desired facilities.

[0568] An "information storage device" refers to a function within a system for storing information received from users, and generally functions as a database.

[0569] "Processing method" refers to the algorithms and calculation methods used by the server to analyze the information it receives and calculate evaluation values.

[0570] An "information processing device" refers to a device or program designed to calculate evaluation values ​​from received data.

[0571] "Evaluation score" refers to a numerical value calculated from the user's basic attribute information, and is an indicator used to evaluate the probability of admission.

[0572] An "emotion recognition device" refers to a mechanism or program that extracts emotions from user input information and adjusts feedback based on that information.

[0573] "Feedback" refers to information and advice provided to the user as a result of adjustments made by an emotion recognition device, and is presented in a way that takes the user's emotions into consideration.

[0574] The system implementing this invention consists of an information processing device (server), an information presentation device (terminal), and an information provider (user). The server starts by receiving basic attribute information entered by the user and storing this information in an information aggregation device.

[0575] The server uses a generated AI model based on the received information to analyze the received data. In this analysis, it uses processing methods to calculate evaluation values ​​from user attribute information. The server can use a database management system or an AI analysis platform in this process.

[0576] Next, the server references historical data and predicts the probability of passing or failing based on the evaluation score. This prediction utilizes statistical methods and machine learning techniques and can be performed in real time. The prediction results are provided to the user visually through the terminal. The terminal is equipped with a graphical user interface (GUI) and presents information in a way that is easy for the user to understand.

[0577] Furthermore, the server utilizes an emotion recognition device to extract emotions from the information entered by the user. For example, it analyzes the user's text and voice data to identify emotions such as stress and a sense of security. Based on this, the server adjusts the content of the feedback to provide the user with the most appropriate information. Natural language processing and speech analysis technologies are used to adjust this emotional feedback.

[0578] To give a specific example, when a user is entering information into the system to decide on a daycare center for their child, if the emotion recognition device detects the user's anxiety, the server can alleviate the user's anxiety by displaying a guide on the terminal that carefully explains the procedure.

[0579] The following prompt statements can be used as input to the generative AI model:

[0580] "I have entered information regarding childcare facilities. Please tell us your current feelings and your preferred childcare facility choice."

[0581] This allows users to consider options more smoothly and make acceptable decisions.

[0582] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0583] Step 1:

[0584] Users input basic attribute information through their device. This input data includes family structure, address, employment status, and preferred facilities. This data is sent from the device to the server via HTTP requests, etc. Specifically, the user enters the information into the interface of their smartphone or computer and completes the process by clicking the submit button.

[0585] Step 2:

[0586] The server stores basic attribute information received from the terminal in a database. During this process, the server checks data integrity and performs data cleaning as needed. Specifically, a database management system (DBMS) is used to ensure stable data storage. Input data consists of information from the user, and output is the information stored in the database.

[0587] Step 3:

[0588] The server retrieves information stored in the database and calculates evaluation scores using a generative AI model. The server uses an algorithm to quantify and process each data point. Specifically, a machine learning model is executed on the AI ​​processing platform. User information from the database is taken as input, and an evaluation score for admission is obtained as output.

[0589] Step 4:

[0590] The server uses historical data to predict the likelihood of admission based on evaluation scores. This utilizes a machine learning model based on the historical dataset. This model generates probabilities and sends them to the terminal. The inputs are evaluation scores and historical data, and the output is the admission probability. The data calculation involves running the prediction model.

[0591] Step 5:

[0592] The server uses an emotion recognition device to analyze text and voice data entered by the user and identify the user's emotions. Specific operations include natural language processing (NLP) and speech analysis techniques. Input includes the user's voice and text data, and output is data related to emotions.

[0593] Step 6:

[0594] The server adjusts the feedback based on the analysis results and provides it to the terminal. The feedback is tailored to the user's emotional state, providing reassuring guidance or information, for example. Specifically, a feedback message is generated and displayed on the user interface. Emotional data is used as input, and the adjusted feedback is obtained as output.

[0595] Step 7:

[0596] The server proposes the optimal application strategy, lists the necessary documents, and provides instructions on how to create them. This information is displayed on the terminal to support the user in taking efficient action. Specifically, it automatically generates a guidance guide and applies it to the terminal's display screen. The input is the predicted admission probability and evaluation value, and the output is a strategic guide.

[0597] (Application Example 2)

[0598] Next, we will explain application example 2. In the following explanation, 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."

[0599] When it comes to the application process for childcare facilities, users often experience anxiety due to the complex information gathering and procedures involved. In such situations, it is difficult for users to develop accurate and efficient strategies for admission, and emotional support is needed.

[0600] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0601] In this invention, the server includes means for receiving and storing user-inputted household information in a database; means for artificial intelligence to calculate admission points using an algorithm designed based on the received information; means for predicting the probability of admission based on the calculated points and referring to the historical difficulty level of each facility applied for; means for analyzing the user's emotions and optimizing information provision based on the emotion analysis results; and means for a household robot to respond to user queries and provide feedback to alleviate user anxiety. This enables the user to receive information and support to proceed with the admission process with peace of mind.

[0602] "Family information" refers to data provided by users regarding their living situation, including information such as employment status, family structure, residential area, and preferred childcare facilities.

[0603] "Artificial intelligence" is a knowledge processing technology implemented by computer programs that automatically calculates admission points based on user input.

[0604] "Admission points" are a numerical value that quantifies the likelihood of admission to a childcare facility based on information provided by the user, and serve as a criterion for determining whether or not admission is possible.

[0605] The "probability of admission" is a predicted value that indicates the likelihood of being admitted to a particular childcare facility, based on the calculated admission score and past data.

[0606] "Sentiment analysis" is a technology that analyzes user input data to identify the user's emotions and psychological state, and then provides appropriate information based on that state.

[0607] A "household robot" is a device designed to assist with daily life, providing support services through dialogue within the user's home.

[0608] "Feedback" refers to information and suggestions for actions provided by a system to a user, intended to help the user make better decisions and take better actions.

[0609] To implement this invention, the user first inputs household information into the system using a smartphone or home robot. The terminal receives this information and stores it in a management database. On the server side, artificial intelligence is used to calculate admission points based on the information obtained from the database. In doing so, historical admission difficulty data for each region is also taken into consideration to predict the probability of admission.

[0610] The server utilizes a generative AI model to perform sentiment analysis on text and voice data entered by the user. Based on the analysis results, it provides information tailored to the user's current psychological state. This process utilizes sentiment analysis engines such as Microsoft's Azure Emotion API.

[0611] Following the sentiment analysis, the robot responds to user questions and provides feedback on predictions and procedures. The content and method of feedback are customized depending on the user's emotional state. If the user is particularly anxious, additional information and support are provided to convey reassurance.

[0612] For example, a user might enter a prompt such as, "I'm feeling stressed about applying for my child's admission to a daycare facility. What should I do?" In this case, the system can perform sentiment analysis and then provide information to reassure the user, as well as guidance on simplifying the process.

[0613] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0614] Step 1:

[0615] Users input household information using their smartphones or home robots. The device receives the input information and sends it to the server. The data entered includes employment status, family structure, and information about desired childcare facilities.

[0616] Step 2:

[0617] The server stores the received family information in a management database. This data is referenced in subsequent processing and used to calculate appropriate admission points. Database storage is performed using SQL or NoSQL.

[0618] Step 3:

[0619] The server retrieves household information from the database and uses artificial intelligence to calculate admission points. The AI ​​model used here applies algorithms to the pre-processed data and calculates points corresponding to each information item. Programming languages ​​such as Python and R are used for this calculation. As a result of the calculation, a user-specific admission point is output.

[0620] Step 4:

[0621] The server uses admission points to reference past data on the difficulty of admission to each facility and predicts the probability of admission to each childcare facility. This prediction uses a machine learning algorithm to build a probability model based on past data and outputs a probability based on the new data. The output admission probability is displayed to the user.

[0622] Step 5:

[0623] Users input questions or concerns into their device in text or voice format. The server processes the input text or voice data using an emotion recognition engine. Microsoft's Azure Emotion API, among others, is used to analyze the user's emotions. The analysis results are output as data indicating the user's emotional state.

[0624] Step 6:

[0625] The server uses the results of sentiment analysis to prepare to generate and provide information tailored to the user's psychological state. The generated information and feedback are further customized using a generative AI model and output as an answer that directly addresses the user's query. Consider the case where the prompt is an input such as, "I'm feeling stressed about applying for my child's admission to a daycare facility. What should I do?"

[0626] Step 7:

[0627] The device provides the user with emotion-optimized feedback, either visually or audibly. This feedback includes specific application procedures and reassuring information to help the user make better decisions. The outputted feedback includes detailed guides and options to alleviate user anxiety.

[0628] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0629] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0630] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0631] [Fourth Embodiment]

[0632] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0633] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0634] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0635] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0636] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0637] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0638] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0639] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0640] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0641] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0642] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0643] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0644] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0645] The system for implementing this invention mainly consists of a server, a terminal, and a user. The user here is a parent who wishes to enroll their child in a childcare facility and is the entity that provides the necessary information to the system. The terminal plays the role of providing an interface for the user to input information and receive results from the system. The server performs the central functions of this system, receiving, storing, processing, and providing results for information.

[0646] 1. Information gathering and input

[0647] Users access the system via a terminal and enter their household information. This information includes employment status, family structure, residential area, and preferred childcare facilities. The terminal sends this information to the server, which stores it in a database.

[0648] 2. Calculation of admission points

[0649] The server uses artificial intelligence to calculate admission points based on information stored in the database. The calculation uses algorithms based on standards set by each local government and facility, ensuring objective scoring.

[0650] 3. Predicting the probability of admission

[0651] Based on the calculated score, the server refers to past admission data and facility difficulty data to predict the user's probability of entering their desired facility. This prediction is then provided to the user via the terminal.

[0652] 4. Providing a guide for the application process.

[0653] Along with the prediction results, the server generates a list of documents required for the application and guides the user on how to create each document. This guidance is provided to the user via their terminal, allowing them to efficiently proceed with the application process.

[0654] As a concrete example, here is an example of a user.

[0655] Example: Suppose a parent is a full-time working parent of two children living in Tokyo. This parent logs into the system from their terminal and enters the necessary information. The server calculates admission points based on this information and then predicts the probability of admission to the desired childcare facility using past data. Along with the prediction results, it provides a guide on the necessary application documents and how to complete them. Through this process, parents can make the best choice based on their circumstances and reduce anxiety about admission.

[0656] The following describes the processing flow.

[0657] Step 1:

[0658] The user accesses the system's login page using their device, enters their authentication information, and logs into the system. After successful login, a screen appears where they can enter information about their household.

[0659] Step 2:

[0660] Users enter information such as their employment status, family structure, residential area, and preferred childcare facility into the terminal, and then click the "Submit" button. The entered information is sent from the terminal to the server.

[0661] Step 3:

[0662] The server stores user information received from the terminal in a database. This stored information is then used in subsequent processing.

[0663] Step 4:

[0664] The server retrieves user information from the database and uses an artificial intelligence algorithm to calculate the user's admission score. The calculation takes into account the evaluation criteria of each local government.

[0665] Step 5:

[0666] Based on the calculated admission score, the server retrieves past admission data and difficulty information for each facility from the database and predicts the probability of admission to the desired childcare facility.

[0667] Step 6:

[0668] The server generates a visualization of the predicted probability of park entry and sends the results to the user's device. The user can then view these results on their device.

[0669] Step 7:

[0670] The server will also list the necessary application documents and generate a guide for completing each document, if requested by the user. This information will be presented to the user on their terminal and provided as guidance for the application process.

[0671] (Example 1)

[0672] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0673] In the application process for childcare facilities, applicants often struggle to effectively manage necessary information and accurately predict their chances of admission. Furthermore, there is a lack of support in developing optimal strategies for facility selection and application preparation. These problems lead to parents wasting time and effort, and proceeding with the process while feeling anxious.

[0674] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0675] This invention includes a server that receives and stores user-inputted household information in an information collection, a machine learning technique that calculates admission points using an algorithm designed based on the received information, and a means that predicts the likelihood of admission based on the calculated points and by referring to the historical difficulty level of each facility applied for. This enables users to efficiently manage the information necessary for admission procedures and to make reliable predictions of admission likelihood. Furthermore, by utilizing historical data analysis by a generative AI model, it becomes possible to improve the probability of admission and formulate an optimal application strategy, thereby reducing the burden on the user.

[0676] A "user" is an entity that utilizes a service through an information system for a specific purpose.

[0677] An "information collection" refers to a recording medium or data storage where various information received from users is organized and stored.

[0678] "Machine learning techniques" is a general term for algorithms or methods that allow computers to analyze past data and perform pattern recognition and prediction.

[0679] "Admission points" are a numerical value used by users to determine whether or not their child is eligible for admission to a childcare facility. It is an evaluation indicator calculated based on available information.

[0680] "Historical difficulty" refers to the degree of difficulty in gaining admission to a particular facility, measured based on past admission data.

[0681] "Possibility of admission" refers to the probability or likelihood that a user will be admitted to the facility they wish to attend.

[0682] A "generative AI model" is a form of artificial intelligence, a mathematical structure or algorithm for generating new information from data.

[0683] This invention relates to an information system that assists with the enrollment process at childcare facilities. This system mainly consists of a server, terminals, and users.

[0684] Users access the system using a terminal and enter information about their family. This information includes family structure, employment status, residential area, and preferred childcare facilities. The terminal can then transmit the entered information to the server.

[0685] The server stores the received data as an information set and uses machine learning techniques based on it. Specifically, it calculates admission points by applying an algorithm based on the received data. In this process, a generative AI model is used in machine learning, and it predicts the likelihood of admission by referring to historical difficulty data.

[0686] The server also has the function of visualizing the predicted likelihood of admission and providing relevant information to the user via the terminal. This allows users to efficiently prepare the documents necessary for admission. The server reduces the burden on the user by acting as a guide for the application process, providing a list of necessary documents and instructions on how to create them.

[0687] As a concrete example, consider a full-time working parent of two children living in Tokyo using this system. This user enters their information through a terminal, and the server uses that information to calculate an admission score and predicts a 70% chance of admission. The server then shows the user a list of required application documents and instructions on how to prepare each document.

[0688] An example of a prompt for a generated AI model is: "Describe a system that helps a full-time working parent of two children living in Tokyo make the best choice for enrolling them in childcare facilities."

[0689] This invention helps users complete accurate and efficient admission procedures.

[0690] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0691] Step 1:

[0692] Users log in to the system via a terminal and enter information such as family structure, employment status, residential area, and preferred childcare facility. This entered information is formatted by the terminal and sent to the server. The server verifies this information and stores it in a database. This stored data forms the basis for analysis in subsequent processing.

[0693] Step 2:

[0694] The server retrieves user information stored in the database and uses machine learning techniques to calculate admission scores. This process applies an algorithm based on the received information. Specifically, the server calculates weights for family structure and employment status, and uses these to generate an overall admission score. This score serves as a basis for evaluating the likelihood of admission.

[0695] Step 3:

[0696] The server uses the calculated admission score to refer to past admission data and historical difficulty data for the facility. It utilizes a generative AI model to predict the likelihood of admission. Based on this data, the server builds a probabilistic model and calculates the probability of admission to the user's desired facility. The result is output as a specific percentage.

[0697] Step 4:

[0698] The server provides prediction results to the user via the terminal. The terminal uses a visual interface to display the information in a way that is easy for the user to understand. Based on this, the user can consider a strategy for admission to the park.

[0699] Step 5:

[0700] The server generates a list of documents required for the application and provides instructions on how to create each document. The server organizes the necessary information and provides a detailed guide through the terminal. This guide helps users efficiently complete the application process.

[0701] (Application Example 1)

[0702] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0703] In modern urban areas, parents lack sufficient information to decide which childcare facility to apply to. Furthermore, the application process is often cumbersome, and there is a lack of efficient guidance.

[0704] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0705] This invention includes a server that receives and stores user-inputted household information in a database, a means for artificial intelligence to calculate admission points using an algorithm designed based on the received information, and a means for predicting the probability of admission based on the calculated points and referring to the historical difficulty level of each facility being applied to. This allows parents to determine the best option from multiple facilities and proceed with the application process efficiently.

[0706] A "user" is an individual who uses the system to check eligibility for admission to a childcare facility and proceed with the necessary application procedures.

[0707] "Family information" refers to data that users input into the system, such as employment status, family structure, and residential area.

[0708] A "database" is an information storage system that stores information received from users and allows it to be referenced as needed.

[0709] An "algorithm" is a calculation procedure used to determine admission points based on the received information.

[0710] "Artificial intelligence" is a technology that uses computers to calculate and predict admission scores and probabilities based on input data.

[0711] "Admission points" are numerical values ​​calculated to evaluate the likelihood of admission to each childcare facility based on information about the family.

[0712] "Probability of admission" is a numerical representation of the likelihood of a user being able to enroll their child in their desired childcare facility.

[0713] "Visualization" refers to displaying the prediction results calculated by the server in a way that is easy for the user to understand.

[0714] The "application process" refers to the process of completing the necessary procedures for a user to enroll in a childcare facility.

[0715] A "server device" is a device that performs processing to provide facility information and manages the entire system.

[0716] This invention is a system that allows parents to calculate their chances of admission to a childcare facility and determine the optimal application method via a device such as a smartphone. The system consists mainly of a user, a device, and a server.

[0717] The server receives the family information entered by the user and stores it in a database. Next, it uses an algorithm based on the received information to calculate admission points. Here, artificial intelligence technology using TensorFlow is used for evaluation. Based on the calculated points, and referring to past data, the probability of admission to each applied facility is predicted. The predicted results are visualized on the user's terminal, allowing the user to make an appropriate decision.

[0718] Furthermore, the server lists the documents required for the application process to enroll and guides the user on how to complete each document. For the user, these guidelines are a useful tool for efficiently completing the application process.

[0719] A concrete example would be a full-time working parent accessing the system via smartphone and entering the necessary information. The server would then quickly calculate admission points based on the submitted information and return the results to the parent, thereby assisting in the selection of a childcare facility. By utilizing a generative AI model, this process can be streamlined.

[0720] An example of a prompt to a generated AI model is: "I would like to know the probability of getting my child into a daycare center in Minato Ward. I work full-time, and I have two children, aged 3 and 1. Please calculate my admission score and the probability." Using prompts like this allows users to gain more information to make informed decisions.

[0721] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0722] Step 1:

[0723] The user uses a terminal to input and submit household information (employment status, family structure, residential area, etc.). This constitutes the input information. The terminal then transfers this information to the server. The output is the transmission of data to the server.

[0724] Step 2:

[0725] The server stores the user's home information received in a database. The input is the home information received from the terminal, and by storing this input information in the database, centralized information management is achieved. The output is the saving of data to the database.

[0726] Step 3:

[0727] The server uses a generative AI model to calculate admission points based on stored information. The input is family information retrieved from a database. TensorFlow is used to perform calculations based on this data and calculate admission points. The output is the calculated admission points.

[0728] Step 4:

[0729] The server uses the previously calculated admission score and references past admission data to predict the probability of admission. The inputs are the calculated admission score and past data. The output is the predicted probability calculated based on the admission probability calculation.

[0730] Step 5:

[0731] The server sends the prediction results to the user's device in a visualized format. The input is the predicted probability of admission, and a visual design is created to display it clearly on the user's device. The output is the visualized data provided to the device.

[0732] Step 6:

[0733] The server generates a list of application documents required by the user and provides a guide on how to create each document. The input consists of prediction results and user information, and the generated document list and its creation guide are output. This is then sent back to the terminal and provided to the user.

[0734] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0735] The system implementing this invention comprises a server, a terminal, a user, and an emotion engine. The user is the entity that wishes to enroll in a childcare facility and provides information about their family situation and the desired facility. The terminal serves as an interface for the user to input information and receive results. The server is responsible for processing and analyzing the information, and the emotion engine recognizes the user's emotions and performs corresponding processing.

[0736] 1. Information gathering and input

[0737] Users access the system through a terminal and enter their household information. This information includes employment status, family structure, residential area, and desired facilities. The terminal sends the entered information to the server, which stores this information in a database.

[0738] 2. Calculation of admission points

[0739] The server retrieves user information from the database and uses artificial intelligence to calculate admission points. The calculation of points uses algorithms based on the standards of each local government.

[0740] 3. Predicting the probability of admission

[0741] Based on the calculated score, the server uses past data to predict the probability of entering the desired facility. This prediction is provided from the server to the terminal in real time and visualized for the user.

[0742] 4. Emotional analysis and feedback

[0743] The server uses an emotion engine to recognize emotions from text and voice data entered by the user. The recognized emotion information is used to present admission strategies and adjust the interface. For example, if the user is feeling anxious, the server visually presents explanations and options to help them feel more at ease.

[0744] 5. Support for the application process

[0745] Based on the predicted probability of admission, the server presents the user with the optimal application strategy. Furthermore, it lists the documents the user needs and provides a guide through the terminal. The emotion engine optimizes the content and delivery method of the guide according to the user's emotional state.

[0746] Specific example:

[0747] One user is looking for a daycare center to care for their child while they work. When this user accesses the system via smartphone and enters their situation, the server uses an emotion engine to analyze the user's current emotions from the entered text and voice. For example, if the user is feeling stressed, the server reduces their anxiety by presenting detailed options regarding daycare selection and guides emphasizing the simplicity of the process. In this way, the user can make better decisions and proceed with confidence.

[0748] The following describes the processing flow.

[0749] Step 1:

[0750] Users log in to the system using their device and access a screen to enter their family information. This information includes details about the user's employment status, residential area, and preferred childcare facilities.

[0751] Step 2:

[0752] The terminal sends the information entered by the user to the server. The transmitted information is stored in a database on the server.

[0753] Step 3:

[0754] The server retrieves the user's family information from the database, and artificial intelligence calculates the admission score using a pre-configured algorithm. The evaluation criteria of the local government are applied to this score calculation.

[0755] Step 4:

[0756] Based on the calculated admission score, the server refers to past admission data for childcare facilities and predicts the probability of admission to each desired facility. The server sends these prediction results to the terminal in real time.

[0757] Step 5:

[0758] The terminal visually displays the predicted probability of park entry received from the server to the user. Charts and graphs are used in the display to ensure that the information is intuitively understandable.

[0759] Step 6:

[0760] If a user requests support for a park admission strategy based on prediction results, the server uses an emotion engine to analyze the user's emotions, recognizing them from text and voice data.

[0761] Step 7:

[0762] The server considers the results of the emotion engine's analysis and generates the optimal application strategy and guide based on the user's situation and emotions, providing it to the user through the terminal. For example, if the user is feeling anxious, the system will provide detailed explanations and encouraging messages.

[0763] Step 8:

[0764] The server adjusts the interface according to the user's emotional state and optimizes the list of documents required for the application process and the guide on how to create them, presenting them to the terminal to improve the user experience.

[0765] (Example 2)

[0766] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0767] Systems designed to streamline the selection of application destinations and the application process based on household attribute information were traditionally often manual, lacking accuracy and efficiency. Furthermore, information was presented without considering the user's emotional state, making it difficult to provide appropriate feedback and application strategies. As a result, users were prone to anxiety and struggled to make optimal choices.

[0768] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0769] In this invention, the server includes means for receiving basic attribute information entered by the user and storing it in an information aggregation device, means for an information processing device to calculate an evaluation value using a processing method designed based on the received information, and means including an emotion recognition device that extracts emotions from the user's input information and adjusts the feedback. As a result, the user can build an effective application strategy based on a probabilistic pass / fail prediction and receive emotion-appropriate feedback, enabling them to proceed with the procedure with peace of mind.

[0770] "Basic attribute information" refers to basic information about the user's household, such as family structure, address, employment status, and desired facilities.

[0771] An "information storage device" refers to a function within a system for storing information received from users, and generally functions as a database.

[0772] "Processing method" refers to the algorithms and calculation methods used by the server to analyze the information it receives and calculate evaluation values.

[0773] An "information processing device" refers to a device or program designed to calculate evaluation values ​​from received data.

[0774] "Evaluation score" refers to a numerical value calculated from the user's basic attribute information, and is an indicator used to evaluate the probability of admission.

[0775] An "emotion recognition device" refers to a mechanism or program that extracts emotions from user input information and adjusts feedback based on that information.

[0776] "Feedback" refers to information and advice provided to the user as a result of adjustments made by an emotion recognition device, and is presented in a way that takes the user's emotions into consideration.

[0777] The system implementing this invention consists of an information processing device (server), an information presentation device (terminal), and an information provider (user). The server starts by receiving basic attribute information entered by the user and storing this information in an information aggregation device.

[0778] The server uses a generated AI model based on the received information to analyze the received data. In this analysis, it uses processing methods to calculate evaluation values ​​from user attribute information. The server can use a database management system or an AI analysis platform in this process.

[0779] Next, the server references historical data and predicts the probability of passing or failing based on the evaluation score. This prediction utilizes statistical methods and machine learning techniques and can be performed in real time. The prediction results are provided to the user visually through the terminal. The terminal is equipped with a graphical user interface (GUI) and presents information in a way that is easy for the user to understand.

[0780] Furthermore, the server utilizes an emotion recognition device to extract emotions from the information entered by the user. For example, it analyzes the user's text and voice data to identify emotions such as stress and a sense of security. Based on this, the server adjusts the content of the feedback to provide the user with the most appropriate information. Natural language processing and speech analysis technologies are used to adjust this emotional feedback.

[0781] To give a specific example, when a user is entering information into the system to decide on a daycare center for their child, if the emotion recognition device detects the user's anxiety, the server can alleviate the user's anxiety by displaying a guide on the terminal that carefully explains the procedure.

[0782] The following prompt statements can be used as input to the generative AI model:

[0783] "I have entered information regarding childcare facilities. Please tell us your current feelings and your preferred childcare facility choice."

[0784] This allows users to consider options more smoothly and make acceptable decisions.

[0785] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0786] Step 1:

[0787] Users input basic attribute information through their device. This input data includes family structure, address, employment status, and preferred facilities. This data is sent from the device to the server via HTTP requests, etc. Specifically, the user enters the information into the interface of their smartphone or computer and completes the process by clicking the submit button.

[0788] Step 2:

[0789] The server stores basic attribute information received from the terminal in a database. During this process, the server checks data integrity and performs data cleaning as needed. Specifically, a database management system (DBMS) is used to ensure stable data storage. Input data consists of information from the user, and output is the information stored in the database.

[0790] Step 3:

[0791] The server retrieves information stored in the database and calculates evaluation scores using a generative AI model. The server uses an algorithm to quantify and process each data point. Specifically, a machine learning model is executed on the AI ​​processing platform. User information from the database is taken as input, and an evaluation score for admission is obtained as output.

[0792] Step 4:

[0793] The server uses historical data to predict the likelihood of admission based on evaluation scores. This utilizes a machine learning model based on the historical dataset. This model generates probabilities and sends them to the terminal. The inputs are evaluation scores and historical data, and the output is the admission probability. The data calculation involves running the prediction model.

[0794] Step 5:

[0795] The server uses an emotion recognition device to analyze text and voice data entered by the user and identify the user's emotions. Specific operations include natural language processing (NLP) and speech analysis techniques. Input includes the user's voice and text data, and output is data related to emotions.

[0796] Step 6:

[0797] The server adjusts the feedback based on the analysis results and provides it to the terminal. The feedback is tailored to the user's emotional state, providing reassuring guidance or information, for example. Specifically, a feedback message is generated and displayed on the user interface. Emotional data is used as input, and the adjusted feedback is obtained as output.

[0798] Step 7:

[0799] The server proposes the optimal application strategy, lists the necessary documents, and provides instructions on how to create them. This information is displayed on the terminal to support the user in taking efficient action. Specifically, it automatically generates a guidance guide and applies it to the terminal's display screen. The input is the predicted admission probability and evaluation value, and the output is a strategic guide.

[0800] (Application Example 2)

[0801] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0802] When it comes to the application process for childcare facilities, users often experience anxiety due to the complex information gathering and procedures involved. In such situations, it is difficult for users to develop accurate and efficient strategies for admission, and emotional support is needed.

[0803] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0804] In this invention, the server includes means for receiving and storing user-inputted household information in a database; means for artificial intelligence to calculate admission points using an algorithm designed based on the received information; means for predicting the probability of admission based on the calculated points and referring to the historical difficulty level of each facility applied for; means for analyzing the user's emotions and optimizing information provision based on the emotion analysis results; and means for a household robot to respond to user queries and provide feedback to alleviate user anxiety. This enables the user to receive information and support to proceed with the admission process with peace of mind.

[0805] "Family information" refers to data provided by users regarding their living situation, including information such as employment status, family structure, residential area, and preferred childcare facilities.

[0806] "Artificial intelligence" is a knowledge processing technology implemented by computer programs that automatically calculates admission points based on user input.

[0807] "Admission points" are a numerical value that quantifies the likelihood of admission to a childcare facility based on information provided by the user, and serve as a criterion for determining whether or not admission is possible.

[0808] The "probability of admission" is a predicted value that indicates the likelihood of being admitted to a particular childcare facility, based on the calculated admission score and past data.

[0809] "Sentiment analysis" is a technology that analyzes user input data to identify the user's emotions and psychological state, and then provides appropriate information based on that state.

[0810] A "household robot" is a device designed to assist with daily life, providing support services through dialogue within the user's home.

[0811] "Feedback" refers to information and suggestions for actions provided by a system to a user, intended to help the user make better decisions and take better actions.

[0812] To implement this invention, the user first inputs household information into the system using a smartphone or home robot. The terminal receives this information and stores it in a management database. On the server side, artificial intelligence is used to calculate admission points based on the information obtained from the database. In doing so, historical admission difficulty data for each region is also taken into consideration to predict the probability of admission.

[0813] The server utilizes a generative AI model to perform sentiment analysis on text and voice data entered by the user. Based on the analysis results, it provides information tailored to the user's current psychological state. This process utilizes sentiment analysis engines such as Microsoft's Azure Emotion API.

[0814] Following the sentiment analysis, the robot responds to user questions and provides feedback on predictions and procedures. The content and method of feedback are customized depending on the user's emotional state. If the user is particularly anxious, additional information and support are provided to convey reassurance.

[0815] For example, a user might enter a prompt such as, "I'm feeling stressed about applying for my child's admission to a daycare facility. What should I do?" In this case, the system can perform sentiment analysis and then provide information to reassure the user, as well as guidance on simplifying the process.

[0816] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0817] Step 1:

[0818] Users input household information using their smartphones or home robots. The device receives the input information and sends it to the server. The data entered includes employment status, family structure, and information about desired childcare facilities.

[0819] Step 2:

[0820] The server stores the received family information in a management database. This data is referenced in subsequent processing and used to calculate appropriate admission points. Database storage is performed using SQL or NoSQL.

[0821] Step 3:

[0822] The server retrieves household information from the database and uses artificial intelligence to calculate admission points. The AI ​​model used here applies algorithms to the pre-processed data and calculates points corresponding to each information item. Programming languages ​​such as Python and R are used for this calculation. As a result of the calculation, a user-specific admission point is output.

[0823] Step 4:

[0824] The server uses admission points to reference past data on the difficulty of admission to each facility and predicts the probability of admission to each childcare facility. This prediction uses a machine learning algorithm to build a probability model based on past data and outputs a probability based on the new data. The output admission probability is displayed to the user.

[0825] Step 5:

[0826] Users input questions or concerns into their device in text or voice format. The server processes the input text or voice data using an emotion recognition engine. Microsoft's Azure Emotion API, among others, is used to analyze the user's emotions. The analysis results are output as data indicating the user's emotional state.

[0827] Step 6:

[0828] The server uses the results of sentiment analysis to prepare to generate and provide information tailored to the user's psychological state. The generated information and feedback are further customized using a generative AI model and output as an answer that directly addresses the user's query. Consider the case where the prompt is an input such as, "I'm feeling stressed about applying for my child's admission to a daycare facility. What should I do?"

[0829] Step 7:

[0830] The device provides the user with emotion-optimized feedback, either visually or audibly. This feedback includes specific application procedures and reassuring information to help the user make better decisions. The outputted feedback includes detailed guides and options to alleviate user anxiety.

[0831] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0832] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0833] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0834] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0835] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0836] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0837] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0838] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0839] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0840] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0841] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0842] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0843] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0844] 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.

[0845] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0846] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0847] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0848] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0849] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0850] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0851] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0852] The following is further disclosed regarding the embodiments described above.

[0853] (Claim 1)

[0854] A means of receiving and storing user-entered household information in a database,

[0855] A means by which artificial intelligence calculates admission points using an algorithm designed based on the received information,

[0856] Based on the calculated score, a method is used to predict the probability of admission by referring to the historical difficulty level of each application facility,

[0857] A means of visualizing the prediction results for the user,

[0858] A means of listing the documents required for the application process and providing instructions on how to prepare them,

[0859] A system that includes this.

[0860] (Claim 2)

[0861] The system according to claim 1, which analyzes the park occupancy status for each region based on the user's residential area information and reflects this in probability predictions.

[0862] (Claim 3)

[0863] The system according to claim 1, which presents the user with an optimal application strategy based on the predicted probability of admission.

[0864] "Example 1"

[0865] (Claim 1)

[0866] A means of receiving household information entered by users and storing it in an information collection,

[0867] A means by which machine learning technology calculates admission points using an algorithm designed based on the received information,

[0868] A method for predicting the likelihood of admission by referring to the historical difficulty level of each application facility based on the calculated score,

[0869] A means of visualizing the prediction results for the user,

[0870] A means of displaying a list of documents required for the application process and providing instructions on how to prepare them,

[0871] By analyzing past information and user data using a generated AI model, a means to improve the probability of park entry is being developed.

[0872] A system that includes this.

[0873] (Claim 2)

[0874] The system according to claim 1, which evaluates the park occupancy status for each area based on the user's residential area information and reflects this in probability prediction.

[0875] (Claim 3)

[0876] The system according to claim 1, which presents the user with the optimal application strategy based on the predicted likelihood of admission.

[0877] "Application Example 1"

[0878] (Claim 1)

[0879] A means of receiving and storing user-entered household information in a database,

[0880] A means by which artificial intelligence calculates admission points using an algorithm designed based on the received information,

[0881] Based on the calculated score, a method is used to predict the probability of admission by referring to the historical difficulty level of each application facility,

[0882] A means of visualizing the prediction results for the user,

[0883] A means of listing the documents required for the application process and providing instructions on how to prepare them,

[0884] A device for users to input information,

[0885] A server device that processes information to provide facility information,

[0886] A system that includes this.

[0887] (Claim 2)

[0888] The system according to claim 1, which analyzes the park occupancy status for each region based on the user's residential area information and reflects this in probability predictions.

[0889] (Claim 3)

[0890] The system according to claim 1, which presents the user with an optimal application strategy based on the predicted probability of admission.

[0891] "Example 2 of combining an emotion engine"

[0892] (Claim 1)

[0893] A means for receiving basic attribute information entered by a user and storing it in an information accumulating device,

[0894] A means by which an information processing device calculates an evaluation value using a processing method designed based on the received information,

[0895] A method for predicting the probability of passing or failing based on the calculated evaluation score and referring to the historical difficulty of each application location,

[0896] A means of visualizing the prediction results to the user using an information display device,

[0897] A means of listing the documents required for the application process and providing instructions on how to prepare them,

[0898] Means including an emotion recognition device that extracts emotions from user input information and adjusts feedback,

[0899] A system that includes this.

[0900] (Claim 2)

[0901] The system according to claim 1, which analyzes the pass rate for each region based on the user's location-related information and reflects this in the probability prediction.

[0902] (Claim 3)

[0903] The system according to claim 1, which presents the user with the optimal application strategy based on the predicted probability of passing or failing.

[0904] "Application example 2 when combining with an emotional engine"

[0905] (Claim 1)

[0906] A means of receiving and storing user-entered household information in a database,

[0907] A means by which artificial intelligence calculates admission points using an algorithm designed based on the received information,

[0908] Based on the calculated score, a method is used to predict the probability of admission by referring to the historical difficulty level of each application facility,

[0909] A means of visualizing the prediction results for the user,

[0910] A means of listing the documents required for the application process and providing instructions on how to prepare them,

[0911] A means of analyzing user emotions and optimizing information provision based on the results of the emotion analysis,

[0912] A means of responding to user queries using a home robot and providing feedback to alleviate user anxiety,

[0913] A system that includes this.

[0914] (Claim 2)

[0915] The system according to claim 1, which analyzes the park occupancy status for each region based on the user's residential area information and reflects this in probability predictions.

[0916] (Claim 3)

[0917] The system according to claim 1, which presents the user with an optimal application strategy based on the predicted probability of admission. [Explanation of symbols]

[0918] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving and storing user-entered household information in a database, A means by which artificial intelligence calculates admission points using an algorithm designed based on the received information, Based on the calculated score, a method is used to predict the probability of admission by referring to the historical difficulty level of each application facility, A means of visualizing the prediction results for the user, A means of listing the documents required for the application process and providing instructions on how to prepare them, A system that includes this.

2. The system according to claim 1, which analyzes the park's attendance status by region based on the user's residential area information and reflects this in probability predictions.

3. The system according to claim 1, which presents the user with an optimal application strategy based on the predicted probability of admission.

Images