System

Abstract

A system is provided.SOLUTION: A system comprising: means for a user to input his / her attributes and financial status; means for the inputted user data to be transmitted to a server; means for the server to receive the user data and store it in a database; means for the server to pre-process the stored user data; means for a generated AI to match market data based on the pre-processed user data and generate an optimal mortgage option; means for the server to transmit the generated mortgage option to a terminal; and means for the terminal to display the mortgage option to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Choosing a mortgage is an important life decision for many people, requiring advanced financial knowledge and a great deal of time and effort. However, people who lack this knowledge and time find it difficult to select the appropriate loan. Furthermore, the mortgage market is complex and constantly changing, making it difficult to collect and analyze the most appropriate information. Given this background, there is a need for a system that streamlines the mortgage selection process and provides users with the best loan options. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for users to input their personal attributes and household financial situation and transmit them from a terminal to a server. The server stores the received user data in a database and has a means for preprocessing the data. The preprocessed user data is analyzed and matched with market data by a generative AI to generate optimal mortgage options. The server formats the generated loan options in a user-friendly format and transmits them back to the terminal, thereby displaying the loan options to the user. The user can also ask further questions or provide additional data, and the server reanalyzes it and makes new loan proposals, thereby achieving continuous optimization. This system allows users to easily select the optimal mortgage for themselves, even without specialized financial knowledge.

[0006] "User" refers to an individual or organization that uses the system.

[0007] "Attributes" refers to personal information such as a user's gender, age, place of employment, etc.

[0008] "Household finances" refers to financial information related to a user's financial assets, annual income, and mortgage.

[0009] "Terminal" refers to an electronic device, such as a computer or smartphone, that a user uses to input and transmit data.

[0010] "Server" refers to a central processing system for storing, processing, and analyzing data received from users.

[0011] A "database" refers to a system that systematically stores information such as user data and analysis results.

[0012] "Preprocessing" refers to the cleaning, formatting, and completion of received data to make it easier to analyze.

[0013] "Generative AI" refers to an artificial intelligence system that generates optimal mortgage options based on user and market data.

[0014] "Market Data" refers to market information such as mortgage products and interest rates.

[0015] "Mortgage Options" means the specific terms and packages of mortgage loans offered to a User.

[0016] "Reanalysis" refers to the process of re-analyzing based on new or additional data from the user to generate optimal suggestions.

[0017] "Loan Offer" refers to the optimal mortgage options presented to a user. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] The present invention relates to a system that automatically generates and proposes optimal housing loan options based on a user's input of their attributes and financial situation. The present invention is implemented in accordance with the following steps.

[0040] First, the user uses a device to access a web form or a dedicated app and enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.). This data is designed to be easily entered by the user, and the form has an intuitive, easy-to-understand interface.

[0041] The entered data is sent from the terminal to the server. The server verifies the received user data, performs any necessary formatting (standardizing the format and detecting and correcting outliers), and then stores it in the database. This process ensures the consistency and accuracy of the data.

[0042] The server then preprocesses the stored user data, which includes data cleaning (inserting missing values ​​and removing duplicate data), normalization (unifying different units and formats), and feature engineering (converting data into a format suitable for the model).

[0043] Once preprocessing is complete, the user data is input into the generation AI, which analyzes the user data and market data to generate mortgage options that best suit the user's attributes and financial situation. The market data includes the latest mortgage products, interest rates, repayment terms, and more, and the AI ​​comprehensively evaluates these.

[0044] The generated mortgage options are then formatted into a user-friendly format by the server and sent back to the terminal, where the user can view the proposed loan options. Specifically, the loan interest rate, repayment period, monthly payment amount, etc. are displayed in a visually understandable manner.

[0045] If the user has further questions or provides additional data based on the information provided, the device will send it back to the server, which will then receive the new information, reanalyze it, and generate a new, optimized loan proposal. This ensures that the user always has the best loan options based on the latest information.

[0046] Specific examples

[0047] Example 1: First-time home buyer

[0048] The user enters "annual income of 6 million yen, personal funds of 3 million yen, property value of 40 million yen, male, 35 years old." The device sends this information to the server, which stores the data in a database. The generating AI then analyzes the user data and market data, creates a reasonable repayment plan, and proposes a mortgage with a fixed interest rate of 2.0%. The device displays to the user, "Monthly repayment of 100,000 yen with a fixed interest rate of 2.0%."

[0049] Example 2: User considering refinancing

[0050] The user inputs "current balance of 20 million yen, variable interest rate of 2.5%, annual income of 8 million yen, 40-year-old female." The terminal again sends the new information to the server, which analyzes it using the generation AI. As a result, a proposal is generated that "refinancing to a loan with a fixed interest rate of 1.8% is possible," and the terminal notifies the user.

[0051] Through these steps, the system of the present invention allows users to select a home loan easily and efficiently, and provides optimal loan options.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] The user enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.) into a dedicated web form or app on their device.

[0055] Step 2:

[0056] The terminal collects the user's input data and sends the data to the server according to a standard format.

[0057] Step 3:

[0058] The server receives the user data sent from the terminal and first verifies the format and validity of the data, for example, whether all required data fields are filled in and whether the numeric format is appropriate.

[0059] Step 4:

[0060] The server stores the verified data in the database, performing transaction processing to maintain data consistency and integrity.

[0061] Step 5:

[0062] The server preprocesses the user data stored in the database, including missing value imputation, outlier detection and correction, and data normalization.

[0063] Step 6:

[0064] The server passes the preprocessed data to the generation AI, which performs analysis based on user data and market data.

[0065] Step 7:

[0066] The AI ​​generates mortgage options that best suit the user's attributes and financial situation, comparing interest rates and adjusting repayment periods based on mortgage products in market data.

[0067] Step 8:

[0068] The server formats the loan options returned by the generation AI into a user-friendly format, specifically, making loan interest rates, repayment periods, monthly payments, etc., visually easy to understand using tables and graphs.

[0069] Step 9:

[0070] The server sends the formatted loan option to the terminal.

[0071] Step 10:

[0072] The terminal displays the loan options received from the server to the user, who can then confirm the proposed loan terms.

[0073] Step 11:

[0074] If the user has the option to ask further questions or provide additional data about the proposed loan option, the terminal will again transmit this new data to the server.

[0075] Step 12:

[0076] The server re-analyzes the newly received data and invokes the generation AI to generate new loan proposals, ensuring that users are always provided with the best loan options based on the latest information.

[0077] Example 1

[0078] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0079] In conventional mortgage selection systems, even after users input their attributes and financial situation, it takes a long time to provide appropriate loan options, and the information provided to users is often insufficient. Furthermore, there is no mechanism to automatically regenerate consistent and appropriate loan proposals every time a user inputs new information. This makes it difficult for users to find the mortgage option that best suits them, and makes it difficult for them to make efficient decisions.

[0080] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0081] In this invention, the server includes means for receiving user data, checking the data format, detecting and correcting outliers, and storing the data in a database; means for preprocessing the stored user data, completing missing values, deleting duplicate data, and normalizing the data; and means for a generation AI to match the preprocessed user data with market data and generate optimal mortgage options. This allows users to efficiently and accurately find optimal mortgage options. Furthermore, even if the user enters new information, the system automatically reanalyzes the data and provides optimal loan options based on the latest information.

[0082] A "user" is someone who uses the system to input their attributes and financial situation to find the best mortgage option for them.

[0083] A "terminal" is a device used by a user to input information, and includes a PC, a smartphone, a tablet, and the like.

[0084] "Server" refers to a computer system that receives, processes, stores, and analyzes data sent by users.

[0085] "Attributes" refers to basic information that identifies an individual, such as a user's gender, age, place of employment, etc.

[0086] "Finance" refers to information about a user's financial assets, annual income, expenses, and other economic circumstances.

[0087] "Database" refers to an information management system that stores received user data and retrieves and uses it when necessary.

[0088] "Preprocessing" refers to checking the format of the received data, detecting and correcting outliers, filling in missing values, deleting duplicate data, normalizing data, and other processes to prepare the data in a format suitable for analysis.

[0089] "Generative AI" refers to an artificial intelligence model that analyzes data provided by users and market data to automatically generate optimal mortgage options.

[0090] "Market Data" refers to information about the mortgage market, including the latest mortgage products, interest rate information, and repayment terms.

[0091] A "prompt sentence" is a sentence that specifically describes instructions or questions for the generation AI, and refers to the input sentence that the AI ​​analyzes based on this and generates a result.

[0092] "Loan options" are the optimal mortgage options suggested by the generative AI based on the user's attributes and financial situation, and specifically include interest rates, repayment periods, and monthly payments.

[0093] The present invention relates to a system that automatically generates and proposes optimal mortgage options based on a user's input of their attributes and financial situation. This system is implemented using a server, a terminal, and a generative AI model.

[0094] Users access web forms or dedicated applications using devices (PCs, smartphones, tablets, etc.) and enter their personal attributes (gender, age, place of employment, etc.) and household financial situation (financial assets, annual income, etc.). This data is provided through an interface designed to allow users to enter it easily.

[0095] The entered data is sent from the terminal to the server, which checks the data format (e.g., JSON or XML format), detects and corrects outliers, and then stores the data in a database (e.g., a relational database such as MySQL or PostgreSQL).

[0096] The server preprocesses the user data stored in the database. This preprocessing includes missing value imputation, duplicate data removal, normalization for different units and formats, and feature engineering. Specifically, the server can use the Python Pandas library to manipulate data frames and perform these preprocessing operations.

[0097] Once the preprocessing is complete, the data is fed into a generative AI model (e.g., GPT-3 or another generative model) that analyzes the data based on a prompt and generates mortgage options that best fit the user's attributes and financial situation. The prompt has the following format:

[0098] User attributes: Age 35, Gender: Male, Workplace: Corporate, Annual income: 6 million yen. Household finances: Personal funds: 3 million yen, Property price: 40 million yen. Please suggest the best mortgage option.

[0099] The generated loan options are formatted in a user-friendly format by the server and sent to the terminal, which then visually displays the interest rate, repayment period, and monthly payment amount of the received loan options to the user.

[0100] For example, if a user enters "annual income of 6 million yen, personal funds of 3 million yen, property value of 40 million yen, 35-year-old male," the device sends this information to the server. The server verifies the data and stores it in a database. The generating AI then analyzes the user data and market data to propose a mortgage with a fixed interest rate of 2.0% as a reasonable repayment plan. This information is sent to the device and displayed as "monthly repayments of 100,000 yen with a fixed interest rate of 2.0%."

[0101] If the user enters new or additional information, the device sends that data back to the server, which then receives the new information, analyzes it again using the generative AI model, and generates a new, optimized loan proposal. This ensures that the user always has the most up-to-date information and the best loan options.

[0102] In this way, the system of the present invention allows users to select home loans efficiently and accurately.

[0103] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0104] Step 1:

[0105] User Data Entry

[0106] Users use their devices to access web forms or dedicated applications and enter their personal attributes (gender, age, place of employment, etc.) and household financial situation (financial assets, annual income, etc.). The data entered is designed to be easily entered into the device's form.

[0107] Input: Demographic and financial information entered by the user into the form.

[0108] Output: User data stored on the device in JSON or XML format.

[0109] Specific behavior: The user manually enters the required information into fields in a browser or application and presses the "Submit" button.

[0110] Step 2:

[0111] Data submission and validation

[0112] The terminal sends the entered data to the server. The data is encrypted before being sent, ensuring security.

[0113] Server operation: The server validates the data it receives. It checks the data format and required fields, and returns an error message if there are any errors.

[0114] Input: User data sent from the device in JSON or XML format.

[0115] Output: Validated and formatted user data.

[0116] Specific operation: A POST request is sent to the endpoint, and on the server side, the request is received by Flask or Django and the format is checked.

[0117] Step 3:

[0118] Data Formatting and Storage

[0119] The server formats the received data, standardizes the format, detects and corrects outliers, and then stores it in a database.

[0120] Input: Validated and formatted user data.

[0121] Output: Dataset stored in a database.

[0122] Specific operation: Use Pandas to format the data, correct outliers, and then insert it into a relational database using an ORM such as SQLAlchemy.

[0123] Step 4:

[0124] Preprocessing user data

[0125] The server preprocesses the user data stored in the database, including imputing missing values, removing duplicate data, normalizing for different units and formats, and feature engineering.

[0126] Input: Datasets stored in a database.

[0127] Output: A preprocessed and clean dataset.

[0128] Specific behavior: Manipulates data frames using the Pandas library, imputes missing values ​​with the mean, removes duplicates, and standardizes units.

[0129] Step 5:

[0130] Generative AI-powered loan option generation

[0131] The preprocessed data is fed into a generative AI model (such as GPT-3), which analyzes the prompt text and generates mortgage options that best fit the user's attributes and financial situation.

[0132] Input: A preprocessed, clean dataset, and a prompt statement.

[0133] Output: The generated mortgage options.

[0134] What it does: It feeds data into a trained GPT-3 model and gives it instructions using specific prompts (e.g., "What are the best loan options for a 35-year-old male with an annual income of $60,000?").

[0135] Step 6:

[0136] Formatting and displaying results

[0137] The server formats the generated loan options into a user-friendly format and sends them to the terminal.

[0138] Input: Generated mortgage options.

[0139] Output: Loan options formatted in a user-friendly format.

[0140] Specific operation: Displays the loan interest rate, repayment period, and monthly payment amount in a visually easy-to-understand manner using HTML and CSS.

[0141] Step 7:

[0142] Re-analysis (if necessary)

[0143] If the user enters new or additional information, the device sends the data back to the server, which receives the new information, re-analyzes it, and generates a new, optimized loan offer.

[0144] Input: New user data.

[0145] Output: The new reparsed mortgage options.

[0146] Specific behavior: A new prompt is generated and fed back into the generative AI model to generate loan options based on the latest information.

[0147] Through these steps, the system is able to provide efficient and accurate mortgage options to users.

[0148] (Application example 1)

[0149] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0150] Conventional mortgage loan selection systems lack the functionality to allow users to intuitively input data and quickly suggest optimal loan options. They also lack the functionality to re-suggest the latest loan options based on the user's further questions or additional information. This makes it difficult for users to easily find the optimal mortgage option. The present invention aims to solve these problems and provide a mortgage loan selection system that users can easily use.

[0151] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0152] In this invention, the server includes: means for a user to input his or her attributes and household financial situation; means for transmitting the input user data to the server; means for the server to receive the user data and store it in a database; means for the server to preprocess the stored user data; means for a generation AI to match the preprocessed user data with market data and generate optimal mortgage options; means for the server to transmit the generated mortgage options to a terminal; means for the terminal to visually display the loan options to the user in an easy-to-understand manner; means for the user to answer further questions or provide additional information; and means for the server to receive new information from the user, reanalyze, and generate new optimized loan proposals. This allows users to easily obtain optimal loan options based on the latest information at all times.

[0153] 1. "User" refers to an individual who uses the system to enter their own attributes and household financial situation.

[0154] 2. "Attributes" refers to personal information about a user, such as gender, age, place of employment, etc.

[0155] 3. "Household financial situation" refers to information about the user's financial situation, such as financial assets, annual income, property price, personal funds, and desired repayment period.

[0156] 4. "Server" refers to the equipment or platform for receiving user data, storing it in a database, and pre-processing it.

[0157] 5. "Database" means a collection of information for formatting and securely storing received User Data.

[0158] 6. "Preprocessing" refers to the process of converting received data into a form suitable for analysis by cleaning, normalizing, feature engineering, etc.

[0159] 7. “Generative AI” refers to an artificial intelligence model that analyzes user and market data to generate optimal mortgage options.

[0160] 8. "Market Data" refers to data including the latest mortgage products, interest rate information, and repayment terms.

[0161] 9. "Mortgage Options" refers to the optimal mortgage products and terms generated based on the user's attributes and financial situation.

[0162] 10. "Terminal" means the device (such as a smartphone or tablet) through which a User enters their data and views the generated mortgage options.

[0163] 11. "Visually easy to understand" means that the proposed mortgage options are visually presented on the terminal in a way that allows the user to intuitively understand them.

[0164] 12. "Answering a question or providing additional information" means that the user enters new data or further details into the system.

[0165] 13. "Reanalysis" refers to the process of conducting a new analysis based on new information provided by the user to generate new mortgage options.

[0166] 14. "Loan Option Rate" means the interest rate terms on a mortgage loan.

[0167] 15. "Repayment period" refers to the period until the total principal and interest of a mortgage is paid off.

[0168] 16. "Monthly payment" refers to the amount paid each month to repay a mortgage.

[0169] This invention relates to a system that allows users to input their attributes and financial situation and proposes optimal mortgage options. Since the main functions of this invention are a server, a terminal, and a generative AI model, specific embodiments of these are described below.

[0170] First, the user uses a terminal to input their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, property price, personal funds, desired repayment period, etc.). The terminal can be a smartphone or tablet, and provides an application designed to allow the user to input data intuitively. This data is then sent from the terminal to a server via the Internet.

[0171] When the server receives the data, it stores it in a database. A relational database such as MySQL or PostgreSQL is used for the database. The received data undergoes any necessary reformatting (standardizing the format and detecting and correcting outliers). For example, numerical data such as annual income or financial assets is converted into consistent units.

[0172] Next, the server performs preprocessing, which includes data cleaning (inserting missing values ​​and removing duplicate data), normalization (standardizing different units and formats), and feature engineering (converting data into a format suitable for the model). Once preprocessing is complete, the data is input into the generative AI.

[0173] The generative AI is built using machine learning frameworks such as TensorFlow and PyTorch, and analyzes user data and market data. Market data includes the latest mortgage products, interest rates, repayment terms, etc. The generative AI comprehensively evaluates this data to generate mortgage options that best suit the user's attributes and financial situation.

[0174] The generated mortgage options are sent from the server to the terminal, which provides the user with a visually-friendly interface that displays the loan interest rate, repayment period, monthly payment amount, etc. The user can then make a selection based on this information.

[0175] Furthermore, if the user provides additional information or answers further questions, the information is sent back to the server, which then re-analyzes the new information and provides a new set of optimal loan options.

[0176] Specific examples

[0177] Example 1: First-time home buyer

[0178] When a user inputs "annual income of 6 million yen, personal funds of 3 million yen, property value of 40 million yen, 35-year-old male," the AI ​​generator will create a reasonable repayment plan and propose a mortgage with a fixed interest rate of 2.0%. The terminal will display "Monthly repayment of 100,000 yen with a fixed interest rate of 2.0%."

[0179] Example 2: A user considering refinancing

[0180] When a user inputs "current balance of 20 million yen, variable interest rate of 2.5%, annual income of 8 million yen, 40-year-old female," the AI ​​generates a suggestion that "refinancing is possible to a loan with a fixed interest rate of 1.8%," and the user is notified via their device.

[0181] Prompt Sentence Examples

[0182] "Gender: Male" "Age: 35" "Employer: ABC Co., Ltd." "Financial assets: 3 million yen" "Annual income: 6 million yen" "Property price: 40 million yen" "Own funds: 3 million yen" "Repayment period: 35 years"

[0183] By integrating these steps and elements, the present invention allows users to easily access the best mortgage options based on the most up-to-date information.

[0184] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0185] Step 1:

[0186] Users use the device to enter their attributes and household financial situation. This includes information such as gender, age, place of employment, financial assets, annual income, property price, personal funds, and desired repayment period. The entered data can be intuitively operated via a dedicated application on the device or a web form. The entered data is temporarily stored on the device and then sent to the server.

[0187] Input: User demographic information and household financial situation.

[0188] Output: User data sent to the server.

[0189] Step 2:

[0190] The server receives user data sent from the device and stores it in a database. A relational database such as MySQL or PostgreSQL is used for the database. The received data is first verified, and any formatting and any outliers are detected and corrected. At this stage, the consistency and accuracy of the data are guaranteed.

[0191] Input: User data sent from the device.

[0192] Output: Validated data stored in a database.

[0193] Step 3:

[0194] The server preprocesses the stored user data. Preprocessing includes data cleaning (inserting missing values ​​and removing duplicate data), data normalization (standardizing different units and formats), and feature engineering (converting data into a format suitable for the model). This prepares the data for input into the generative AI model.

[0195] Input: User data stored in the database.

[0196] Output: Preprocessed user data.

[0197] Step 4:

[0198] Based on the preprocessed user data, the server uses a generative AI model to match it with market data and generate optimal mortgage options. The generative AI model is built using machine learning frameworks such as TensorFlow and PyTorch. Market data includes the latest mortgage products, interest rates, repayment terms, etc., and comprehensively evaluates these to generate the optimal option for each user.

[0199] Input: Preprocessed user and market data.

[0200] Output: The generated mortgage options.

[0201] Step 5:

[0202] The server sends the generated mortgage options to the terminal, which provides the user with a visual interface that displays the loan interest rate, repayment period, monthly payment amount, etc. The user can review the options and proceed with their selection.

[0203] Input: The generated mortgage option.

[0204] Output: Loan options displayed on the terminal.

[0205] Step 6:

[0206] If the user answers further questions or provides additional information, the new information is sent via the device to the server, which receives this new information, reanalyzes it, and re-uses the generative AI model to generate new, optimized loan offers. The regenerated loan options are again sent to the device and displayed to the user.

[0207] Input: User data based on additional information or new questions.

[0208] Output: Regenerated loan options.

[0209] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0210] The present invention relates to a system that automatically generates and proposes optimal mortgage options based on the user's input of their attributes and financial situation. In particular, the present invention achieves more personalized proposals by incorporating an emotion engine that recognizes the user's emotions.

[0211] First, the user uses a device to access a web form or a dedicated app and enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.). This input data is collected using an interface designed to allow users to enter data easily.

[0212] The entered data is sent from the terminal to the server. The server verifies the received user data, formats it, and stores it in a database. At this time, the data is cleaned and formatted to maintain data integrity.

[0213] The server then preprocesses the data stored in the database, including filling in missing values, correcting outliers, and normalizing the data. Once preprocessed, the data is fed into a generative AI, which generates optimal mortgage options based on user and market data.

[0214] The generated mortgage options are then formatted into a user-friendly format by the server and sent to the terminal, which displays the proposed loan options to the user, including the loan interest rate, repayment period, and monthly payment amount.

[0215] A distinctive feature of the present invention is the inclusion of an emotion engine. The emotion engine analyzes the user's input data and daily usage patterns to identify the user's current emotional state. For example, by analyzing the user's input text, click patterns, and input speed, it determines whether the user is currently feeling stressed or relaxed.

[0216] Once the emotion engine identifies the user's emotional state, that information is fed back to the generative AI to customize the loan option recommendations and presentation. For example, if the user is stressed, they will receive more concise and easy-to-understand recommendations, while if they are relaxed, they will receive more detailed information.

[0217] Specific examples

[0218] Example 1: First-time home buyer

[0219] The user inputs "annual income of 6 million yen, personal funds of 3 million yen, property value of 40 million yen, 35-year-old male." The emotion engine analyzes input speed and keystroke patterns to determine that the user is feeling somewhat anxious. The generative AI then creates a reasonable repayment plan and proposes a mortgage with a fixed interest rate of 2.0%. The proposal is displayed concretely and simply: "Monthly repayments of 100,000 yen with a fixed interest rate of 2.0%."

[0220] Example 2: User considering refinancing

[0221] The user enters "current balance of 20 million yen, variable interest rate of 2.5%, annual income of 8 million yen, 40-year-old female." The emotion engine determines that the user is relaxed based on their click patterns and time spent on the site. The generation AI displays a proposal with detailed information, such as "refinancing to a fixed interest rate of 1.8% will save you 100,000 yen per year."

[0222] By implementing the present invention, users can easily select loan options that are best suited to them and that correspond to their emotional state without requiring specialized financial knowledge, thereby improving user satisfaction and realizing an efficient loan selection process.

[0223] The processing flow will be explained below.

[0224] Step 1:

[0225] The user enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.) into a dedicated web form or app on their device.

[0226] Step 2:

[0227] The terminal collects the user's input data and sends the data to the server according to a standard format.

[0228] Step 3:

[0229] The server receives the user data sent from the terminal and first verifies the format and validity of the data, for example, whether all required fields are filled in and whether the numeric format is appropriate.

[0230] Step 4:

[0231] The server stores the verified data in the database, performing transaction processing to ensure data consistency and integrity.

[0232] Step 5:

[0233] The server preprocesses the user data stored in the database, including filling in missing values, correcting outliers, and normalizing the data (unifying different units and formats).

[0234] Step 6:

[0235] The server passes the preprocessed data to the generation AI, which then performs analysis based on user data and market data.

[0236] Step 7:

[0237] Generative AI generates mortgage options that best suit the user's attributes and financial situation, comparing interest rates and adjusting repayment periods based on mortgage products in market data.

[0238] Step 8:

[0239] The server formats the loan options returned by the generation AI into a user-friendly format, specifically, making loan interest rates, repayment periods, monthly payments, etc., visually easy to understand using tables and graphs.

[0240] Step 9:

[0241] The server sends the formatted loan option to the terminal.

[0242] Step 10:

[0243] The terminal displays the loan options received from the server to the user, who can then confirm the proposed loan terms.

[0244] Step 11:

[0245] The emotion engine analyzes the user's input data, click patterns, typing speed, etc. to determine the user's current emotional state. For example, if the user takes a long time to type, the emotion engine will determine that the user is feeling stressed.

[0246] Step 12:

[0247] The emotion engine identifies the user's emotional state and feeds it back to the generative AI to adjust the content and presentation of the suggestions. For example, if the user is feeling stressed, the suggestions will be made more concise.

[0248] Step 13:

[0249] The terminal then presents the user with customized loan options again, allowing them to make the best choice based on concise and easy-to-understand information.

[0250] Step 14:

[0251] If the user asks further questions about the suggestions or provides additional data, the terminal transmits the new data to the server again.

[0252] Step 15:

[0253] The server aggregates the newly received data and the results of the emotion engine's analysis of the emotional state, and then reanalyzes it with the generative AI, which then generates a new loan proposal.

[0254] Step 16:

[0255] The server then formats the reparsed loan options into a user-friendly format and sends it to the terminal, where the user can review the new offers.

[0256] These steps allow users to easily and efficiently find the best mortgage option that suits their needs.

[0257] Example 2

[0258] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0259] Conventional mortgage option proposal systems have difficulty making optimal proposals based on a user's individual attributes and financial situation, and are unable to make proposals that take into account the user's emotional state. This causes users to feel a great deal of stress when selecting the optimal loan option. Furthermore, it is difficult to quickly reanalyze the system when the entered user data is inaccurate or when market data is updated.

[0260] The specification processing by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input their own attributes and household financial situation; means for transmitting the input user data to an information processing device; means for the information processing device to receive the user data and store it in a storage medium; means for the information processing device to preprocess the stored user data; means for a machine learning model to match the preprocessed user data with market data and generate optimal mortgage options; means for the information processing device to transmit the generated mortgage options to an output device; means for the output device to display the loan options to the user; and means for analyzing the user's emotional state using an emotion analysis engine and customizing the generated mortgage options based on the user's emotional state. As a result, the user is offered optimal mortgage options based on their attributes and household financial situation, and further receives personalized offers according to the user's emotional state, which makes the selection process easier and improves the user experience.

[0261] "User" refers to any individual or entity that utilizes this system to receive mortgage options.

[0262] "Attributes" refers to personal information such as a user's gender, age, place of employment, etc.

[0263] "Household finances" refers to economic information such as a user's financial assets, annual income, and expenses.

[0264] "Information processing device" refers to a device that receives, processes, and analyzes data sent by a user.

[0265] "Storage medium" refers to a data storage device used by an information processing device to store user data.

[0266] "Preprocessing" refers to performing processes such as missing value completion, outlier correction, and normalization on user data.

[0267] "Machine learning model" refers to an algorithm that uses pre-processed data and market data to generate optimal mortgage options.

[0268] "Market data" refers to external data such as interest rates and property prices, including information used by machine learning models.

[0269] "Output device" refers to a device for displaying generated mortgage options to a user.

[0270] An "emotion analysis engine" refers to algorithms or software for analyzing a user's emotional state.

[0271] The present invention relates to a system that automatically generates and proposes optimal mortgage options based on a user's input of their attributes and financial situation. This system achieves more personalized proposals by incorporating an emotion engine that recognizes the user's emotions. Specific embodiments are described below.

[0272] First, the user uses a device to access a web form or a dedicated app and enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.). This input is done through an intuitive user interface created with React.js or Vue.js. For example, it is expected that the user will enter "annual income of 6 million yen," "self-funding of 3 million yen," and "property price of 40 million yen."

[0273] The device then sends the entered data to the server via a REST API. The server receives the data using Node.js or Express.js and uses the validation framework Joi.js to verify that the input format is correct. For example, it checks that the "annual income" field is in numeric format.

[0274] The server validates the received data, formats it, and then stores it in a database, typically using MongoDB or PostgreSQL. After storing the data, the server preprocesses it using Python scripts and Pandas. This preprocessing includes imputing missing values, correcting outliers, and normalizing the data.

[0275] Once the preprocessing is complete, the data is input into a generative AI model. Machine learning frameworks such as TensorFlow and PyTorch are used for the generative AI model. The prompt for the generative AI model is in the following format: "The user's annual income is 6 million yen, their own funds are 3 million yen, and the property price is 40 million yen. Please suggest the best mortgage option."

[0276] The server receives the optimal mortgage option output by the generative AI model and formats it into a user-friendly format using a template engine (e.g., EJS, Handlebars). The formatted loan option is then sent back to the terminal and presented to the user. At this time, the terminal displays a user-friendly message such as "Fixed interest rate of 2.0%, monthly repayment plan of 100,000 yen."

[0277] Furthermore, the present invention incorporates an emotion engine to identify the user's emotional state, and the generative AI model customizes the suggestions based on this. The emotion engine analyzes input speed, click patterns, dwell time, etc. to determine whether the user is stressed or relaxed. For example, if the user is feeling anxious, the suggestions will be more concise and easy to understand.

[0278] As a concrete example, if a first-time home buyer enters "annual income of 6 million yen, personal funds of 3 million yen, property price of 40 million yen, 35-year-old male," the emotion engine will determine from the keystroke pattern and typing speed that the user is feeling somewhat anxious. The generative AI model will then create a reasonable repayment plan and propose a mortgage with a fixed interest rate of 2.0%. The proposal is displayed in a specific and simple way: "Monthly repayments of 100,000 yen with a fixed interest rate of 2.0%."

[0279] The system allows users to easily select the loan option that best suits them without requiring specialized financial knowledge, and facilitates the selection process by receiving personalized suggestions based on their emotional state, improving the user experience and realizing an efficient loan selection process.

[0280] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0281] Step 1: The user enters their attributes and household financial situation

[0282] Users use their device to access a web form or a dedicated app and enter their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.).

[0283] Specific operation: The user opens a browser or app and enters information such as "annual income of 6 million yen," "personal funds of 3 million yen," and "property price of 40 million yen" into a form.

[0284] Input: User attributes and household financial situation data

[0285] Output: User data entered into the terminal

[0286] Step 2: Submit and verify data

[0287] The terminal sends the input data to the server via the REST API, and the server validates the received data using the validation framework.

[0288] What happens: The device sends data to the API endpoint, the server receives the data using Node.js and Express.js, and the server verifies the item format using Joi.js.

[0289] Input: User data sent from the terminal

[0290] Output: Verified user data

[0291] Step 3: Saving and formatting the data

[0292] The server stores the validated data in a database and reformats the data as needed.

[0293] Specific operation: The server stores the data in MongoDB or PostgreSQL and cleans it to unify the data format.

[0294] Input: Validated user data

[0295] Output: Formatted user data stored in the database

[0296] Step 4: Preprocessing the data

[0297] The server retrieves the data from the database and pre-processes it.

[0298] What it does: The server uses Python scripts and Pandas to impute missing values ​​in the data, correct outliers, and normalize the data.

[0299] Input: Preformatted user data stored in the database

[0300] Output: Preprocessed user data

[0301] Step 5: Input to the generative AI model

[0302] The server inputs the preprocessed data into the generative AI model.

[0303] Specific operation: The server uses a Python script to input preprocessed data into a generative AI model built with TensorFlow and PyTorch. The prompt statement is, "The user's annual income is 6 million yen, their own funds are 3 million yen, and the property price is 40 million yen. Please suggest the best mortgage option."

[0304] Input: Preprocessed user data

[0305] Output: Optimal mortgage options from a generative AI model

[0306] Step 6: Format and submit your loan option

[0307] The server formats the optimal mortgage options output by the generative AI model and sends them to the terminal.

[0308] Specific operation: The server uses a template engine (EJS, Handlebars) to format the data into a user-friendly format, and then sends the formatted data to the device.

[0309] Input: Loan option data output by the generative AI model

[0310] Output: Formatted loan option data

[0311] Step 7: View loan options

[0312] The terminal displays the loan options received from the server to the user.

[0313] Specific operation: The device displays information such as "Fixed interest rate 2.0%, monthly repayment plan of 100,000 yen" on a web page or app.

[0314] Input: Formatted loan option data

[0315] Output: Loan options displayed to the user

[0316] Step 8: Applying the Sentiment Analysis Engine

[0317] The server uses an emotion analysis engine to analyze the user's emotional state and provides feedback to the generative AI model.

[0318] How it works: The server analyzes the user's typing speed and click patterns to determine their state of stress or relaxation. The analysis results are fed back to the generative AI model to customize the suggestions.

[0319] Input: User input data and usage patterns

[0320] Output: Customized loan options based on the user's emotional state

[0321] (Application example 2)

[0322] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0323] In today's world, it is not easy for consumers to find the best products and services for them from the vast amount of information available. Furthermore, consumers often require different recommendations depending on their emotional state. Furthermore, there is a demand for systems that allow them to receive personalized recommendations regardless of time or location.

[0324] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0325] In this invention, the server includes: means for a user to input their attributes and household financial situation; means for transmitting the input user data to the server; means for the server to receive the user data and store it in a database; means for the server to preprocess the stored user data; means for a generation AI to match the preprocessed user data with market data and generate optimal mortgage options; means for the server to transmit the generated mortgage options to a terminal; means for the terminal to display the loan options to the user; and means for using a smart device in a physical store to analyze the user's attributes and emotional state and suggest optimal products and services based on the results. This allows users to easily find the products and services that are best suited to them and also allows them to receive personalized suggestions based on their emotional state.

[0326] "User attributes" is a general term for personal information such as a user's age, gender, occupation, purchasing history, etc.

[0327] "Finance situation" refers to a user's financial assets, annual income, expenses and other financial information.

[0328] A "server" is a computer system that receives, stores, and processes data sent by users.

[0329] A "database" is a structured collection of data for storing collected user data.

[0330] "Preprocessing" refers to cleaning and standardizing the format of data before analyzing it, such as imputing missing values ​​and normalizing data.

[0331] "Generative AI" refers to technology that uses artificial intelligence models to generate optimal recommendations based on user and market data.

[0332] "Smart devices" refers to devices such as smartphones and smart glasses that have internet connectivity and can acquire and process data.

[0333] "Physical store" refers to a physical sales or service location.

[0334] "Emotional state" refers to the user's current psychological state, including the degree of stress or relaxation.

[0335] "Suggestion" refers to a recommendation or option offered to a user.

[0336] This system uses smart devices in a brick-and-mortar store to analyze a user's attributes and emotional state to suggest optimal products and services. The system consists of a user, a server, a smart device, and a terminal.

[0337] First, the user puts on a smart device such as smart glasses in a physical store. The camera and sensors installed in the smart device recognize the user's face and collect data in real time. This allows the user's attributes (age, gender, occupation, purchasing history, etc.) and emotional state (stress, relaxation, etc.) to be analyzed.

[0338] The collected data is sent to a server, which stores the received data in a database and performs preprocessing. Preprocessing includes cleaning the data, standardizing the format, and filling in missing values. The preprocessed data is then input into the generative AI.

[0339] Generative AI uses user and market data to suggest optimal products and services. For example, if a user is feeling stressed, it might suggest relaxation products or books. On the other hand, if a user is feeling relaxed, it might suggest the latest electronics or sports equipment.

[0340] The generated proposals are sent via the server to the smart device, which then displays the proposals in a user-friendly format, including product or service descriptions, prices, sales information, coupons, etc.

[0341] As a concrete example of this system, the following prompt sentence is input to the generation AI:

[0342] Example prompt for a generative AI model:

[0343] User ID_001 (male, 35 years old) has purchased electrical appliances and sports equipment in the past. Currently, the user is feeling stressed, so we recommend relaxation products and books. Please display the suggestions in a user-friendly format.

[0344] This system allows users to enjoy shopping in brick-and-mortar stores in an efficient and personalized way. The suggestions are dynamically adjusted according to the user's emotional state, so the system always provides the most suitable products and services for the user.

[0345] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0346] Step 1:

[0347] A user puts on the smart glasses.

[0348] Input: Putting on smart glasses, activating cameras and sensors.

[0349] How it works: When a user enters a physical store and puts on the smart glasses, the smart glasses' camera and sensors are activated, allowing the smart device to detect the user's face and begin collecting data in real time.

[0350] Step 2:

[0351] The smart device recognizes the user's face and analyzes their attributes and emotional state.

[0352] Input: Facial image data and other sensor data.

[0353] Output: User demographics and emotional state data.

[0354] How it works: Using facial image data captured by the camera and biometric data from sensors, the system runs a facial recognition algorithm and emotion recognition model to identify the user's demographic information, such as age, gender, and past purchase history, as well as their current emotional state (such as stress level).

[0355] Step 3:

[0356] The smart device sends the acquired data to the server.

[0357] Input: User demographic information and emotional state data.

[0358] Output: User data sent to the server.

[0359] Specific operation: The smart glasses collect user attribute information and emotional state data and send it to the server. The data is encrypted and transmitted securely.

[0360] Step 4:

[0361] The server stores the received data in a database and performs preprocessing.

[0362] Input: The retrieved user data.

[0363] Output: Preprocessed user data.

[0364] Specific operation: The server first stores the received data in a database, then performs preprocessing such as filling in missing values, correcting outliers, and normalizing the data. The preprocessed data is then formatted into a format suitable for analysis.

[0365] Step 5:

[0366] Based on the pre-processed data, generative AI suggests optimal products and services.

[0367] Input: Preprocessed user and market data.

[0368] Output: Recommendations for the best products and services.

[0369] Specific operation: Preprocessed user data and market data are input into the Generative AI, which then runs the algorithm to generate the best products and services for the user. Specifically, if the user is feeling stressed, it will suggest relaxation products, and if they are feeling relaxed, it will suggest the latest electronic appliances.

[0370] Step 6:

[0371] The server sends the generated proposal to the smart device.

[0372] Input: Generated product or service proposals.

[0373] Output: Proposal data sent to smart device.

[0374] How it works: The server receives the proposed data from the generative AI model, converts it into a user-friendly format, and then securely transmits it to the smart glasses.

[0375] Step 7:

[0376] The smart device displays the suggestions to the user.

[0377] Input: Proposal data sent by the server.

[0378] Output: The suggested products or services displayed to the user.

[0379] How it works: The smart glasses display information about suggested products and services on the screen, including product descriptions, prices, sales information, coupons, etc. This information allows users to efficiently select products in the store.

[0380] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0381] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0382] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0383] [Second embodiment]

[0384] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0385] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0386] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0387] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0388] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0389] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0390] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0391] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0392] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0393] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0394] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0395] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0396] The present invention relates to a system that automatically generates and proposes optimal housing loan options based on a user's input of their attributes and financial situation. The present invention is implemented in accordance with the following steps.

[0397] First, the user uses a device to access a web form or a dedicated app and enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.). This data is designed to be easily entered by the user, and the form has an intuitive, easy-to-understand interface.

[0398] The entered data is sent from the terminal to the server. The server verifies the received user data, performs any necessary formatting (standardizing the format and detecting and correcting outliers), and then stores it in the database. This process ensures the consistency and accuracy of the data.

[0399] The server then preprocesses the stored user data, which includes data cleaning (inserting missing values ​​and removing duplicate data), normalization (unifying different units and formats), and feature engineering (converting data into a format suitable for the model).

[0400] Once preprocessing is complete, the user data is input into the generation AI, which analyzes the user data and market data to generate mortgage options that best suit the user's attributes and financial situation. The market data includes the latest mortgage products, interest rates, repayment terms, and more, and the AI ​​comprehensively evaluates these.

[0401] The generated mortgage options are then formatted into a user-friendly format by the server and sent back to the terminal, where the user can view the proposed loan options. Specifically, the loan interest rate, repayment period, monthly payment amount, etc. are displayed in a visually understandable manner.

[0402] If the user has further questions or provides additional data based on the information provided, the device will send it back to the server, which will then receive the new information, reanalyze it, and generate a new, optimized loan proposal. This ensures that the user always has the best loan options based on the latest information.

[0403] Specific examples

[0404] Example 1: First-time home buyer

[0405] The user enters "annual income of 6 million yen, personal funds of 3 million yen, property value of 40 million yen, male, 35 years old." The device sends this information to the server, which stores the data in a database. The generating AI then analyzes the user data and market data, creates a reasonable repayment plan, and proposes a mortgage with a fixed interest rate of 2.0%. The device displays to the user, "Monthly repayment of 100,000 yen with a fixed interest rate of 2.0%."

[0406] Example 2: User considering refinancing

[0407] The user inputs "current balance of 20 million yen, variable interest rate of 2.5%, annual income of 8 million yen, 40-year-old female." The terminal again sends the new information to the server, which analyzes it using the generation AI. As a result, a proposal is generated that "refinancing to a loan with a fixed interest rate of 1.8% is possible," and the terminal notifies the user.

[0408] Through these steps, the system of the present invention allows users to select a home loan easily and efficiently, and provides optimal loan options.

[0409] The processing flow will be explained below.

[0410] Step 1:

[0411] The user enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.) into a dedicated web form or app on their device.

[0412] Step 2:

[0413] The terminal collects the user's input data and sends the data to the server according to a standard format.

[0414] Step 3:

[0415] The server receives the user data sent from the terminal and first verifies the format and validity of the data, for example, whether all required data fields are filled in and whether the numeric format is appropriate.

[0416] Step 4:

[0417] The server stores the verified data in the database, performing transaction processing to maintain data consistency and integrity.

[0418] Step 5:

[0419] The server preprocesses the user data stored in the database, including missing value imputation, outlier detection and correction, and data normalization.

[0420] Step 6:

[0421] The server passes the preprocessed data to the generation AI, which performs analysis based on user data and market data.

[0422] Step 7:

[0423] The AI ​​generates mortgage options that best suit the user's attributes and financial situation, comparing interest rates and adjusting repayment periods based on mortgage products in market data.

[0424] Step 8:

[0425] The server formats the loan options returned by the generation AI into a user-friendly format, specifically, making loan interest rates, repayment periods, monthly payments, etc., visually easy to understand using tables and graphs.

[0426] Step 9:

[0427] The server sends the formatted loan option to the terminal.

[0428] Step 10:

[0429] The terminal displays the loan options received from the server to the user, who can then confirm the proposed loan terms.

[0430] Step 11:

[0431] If the user has the option to ask further questions or provide additional data about the proposed loan option, the terminal will again transmit this new data to the server.

[0432] Step 12:

[0433] The server re-analyzes the newly received data and invokes the generation AI to generate new loan proposals, ensuring that users are always provided with the best loan options based on the latest information.

[0434] Example 1

[0435] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0436] In conventional mortgage selection systems, even after users input their attributes and financial situation, it takes a long time to provide appropriate loan options, and the information provided to users is often insufficient. Furthermore, there is no mechanism to automatically regenerate consistent and appropriate loan proposals every time a user inputs new information. This makes it difficult for users to find the mortgage option that best suits them, and makes it difficult for them to make efficient decisions.

[0437] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0438] In this invention, the server includes means for receiving user data, checking the data format, detecting and correcting outliers, and storing the data in a database; means for preprocessing the stored user data, completing missing values, deleting duplicate data, and normalizing the data; and means for a generation AI to match the preprocessed user data with market data and generate optimal mortgage options. This allows users to efficiently and accurately find optimal mortgage options. Furthermore, even if the user enters new information, the system automatically reanalyzes the data and provides optimal loan options based on the latest information.

[0439] A "user" is someone who uses the system to input their attributes and financial situation to find the best mortgage option for them.

[0440] A "terminal" is a device used by a user to input information, and includes a PC, a smartphone, a tablet, and the like.

[0441] "Server" refers to a computer system that receives, processes, stores, and analyzes data sent by users.

[0442] "Attributes" refers to basic information that identifies an individual, such as a user's gender, age, place of employment, etc.

[0443] "Finance" refers to information about a user's financial assets, annual income, expenses, and other economic circumstances.

[0444] "Database" refers to an information management system that stores received user data and retrieves and uses it when necessary.

[0445] "Preprocessing" refers to checking the format of the received data, detecting and correcting outliers, filling in missing values, deleting duplicate data, normalizing data, and other processes to prepare the data in a format suitable for analysis.

[0446] "Generative AI" refers to an artificial intelligence model that analyzes data provided by users and market data to automatically generate optimal mortgage options.

[0447] "Market Data" refers to information about the mortgage market, including the latest mortgage products, interest rate information, and repayment terms.

[0448] A "prompt sentence" is a sentence that specifically describes instructions or questions for the generation AI, and refers to the input sentence that the AI ​​analyzes based on this and generates a result.

[0449] "Loan options" are the optimal mortgage options suggested by the generative AI based on the user's attributes and financial situation, and specifically include interest rates, repayment periods, and monthly payments.

[0450] The present invention relates to a system that automatically generates and proposes optimal mortgage options based on a user's input of their attributes and financial situation. This system is implemented using a server, a terminal, and a generative AI model.

[0451] Users access web forms or dedicated applications using devices (PCs, smartphones, tablets, etc.) and enter their personal attributes (gender, age, place of employment, etc.) and household financial situation (financial assets, annual income, etc.). This data is provided through an interface designed to allow users to enter it easily.

[0452] The entered data is sent from the terminal to the server, which checks the data format (e.g., JSON or XML format), detects and corrects outliers, and then stores the data in a database (e.g., a relational database such as MySQL or PostgreSQL).

[0453] The server preprocesses the user data stored in the database. This preprocessing includes missing value imputation, duplicate data removal, normalization for different units and formats, and feature engineering. Specifically, the server can use the Python Pandas library to manipulate data frames and perform these preprocessing operations.

[0454] Once the preprocessing is complete, the data is fed into a generative AI model (e.g., GPT-3 or another generative model) that analyzes the data based on a prompt and generates mortgage options that best fit the user's attributes and financial situation. The prompt has the following format:

[0455] User attributes: Age 35, Gender: Male, Workplace: Corporate, Annual income: 6 million yen. Household finances: Personal funds: 3 million yen, Property price: 40 million yen. Please suggest the best mortgage option.

[0456] The generated loan options are formatted in a user-friendly format by the server and sent to the terminal, which then visually displays the interest rate, repayment period, and monthly payment amount of the received loan options to the user.

[0457] For example, if a user enters "annual income of 6 million yen, personal funds of 3 million yen, property value of 40 million yen, 35-year-old male," the device sends this information to the server. The server verifies the data and stores it in a database. The generating AI then analyzes the user data and market data to propose a mortgage with a fixed interest rate of 2.0% as a reasonable repayment plan. This information is sent to the device and displayed as "monthly repayments of 100,000 yen with a fixed interest rate of 2.0%."

[0458] If the user enters new or additional information, the device sends that data back to the server, which then receives the new information, analyzes it again using the generative AI model, and generates a new, optimized loan proposal. This ensures that the user always has the most up-to-date information and the best loan options.

[0459] In this way, the system of the present invention allows users to select home loans efficiently and accurately.

[0460] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0461] Step 1:

[0462] User Data Entry

[0463] Users use their devices to access web forms or dedicated applications and enter their personal attributes (gender, age, place of employment, etc.) and household financial situation (financial assets, annual income, etc.). The data entered is designed to be easily entered into the device's form.

[0464] Input: Demographic and financial information entered by the user into the form.

[0465] Output: User data stored on the device in JSON or XML format.

[0466] Specific behavior: The user manually enters the required information into fields in a browser or application and presses the "Submit" button.

[0467] Step 2:

[0468] Data submission and validation

[0469] The terminal sends the entered data to the server. The data is encrypted before being sent, ensuring security.

[0470] Server operation: The server validates the data it receives. It checks the data format and required fields, and returns an error message if there are any errors.

[0471] Input: User data sent from the device in JSON or XML format.

[0472] Output: Validated and formatted user data.

[0473] Specific operation: A POST request is sent to the endpoint, and on the server side, the request is received by Flask or Django and the format is checked.

[0474] Step 3:

[0475] Data Formatting and Storage

[0476] The server formats the received data, standardizes the format, detects and corrects outliers, and then stores it in a database.

[0477] Input: Validated and formatted user data.

[0478] Output: Dataset stored in a database.

[0479] Specific operation: Use Pandas to format the data, correct outliers, and then insert it into a relational database using an ORM such as SQLAlchemy.

[0480] Step 4:

[0481] Preprocessing user data

[0482] The server preprocesses the user data stored in the database, including imputing missing values, removing duplicate data, normalizing for different units and formats, and feature engineering.

[0483] Input: Datasets stored in a database.

[0484] Output: A preprocessed and clean dataset.

[0485] Specific behavior: Manipulates data frames using the Pandas library, imputes missing values ​​with the mean, removes duplicates, and standardizes units.

[0486] Step 5:

[0487] Generative AI-powered loan option generation

[0488] The preprocessed data is fed into a generative AI model (such as GPT-3), which analyzes the prompt text and generates mortgage options that best fit the user's attributes and financial situation.

[0489] Input: A preprocessed, clean dataset, and a prompt statement.

[0490] Output: The generated mortgage options.

[0491] What it does: It feeds data into a trained GPT-3 model and gives it instructions using specific prompts (e.g., "What are the best loan options for a 35-year-old male with an annual income of $60,000?").

[0492] Step 6:

[0493] Formatting and displaying results

[0494] The server formats the generated loan options into a user-friendly format and sends them to the terminal.

[0495] Input: Generated mortgage options.

[0496] Output: Loan options formatted in a user-friendly format.

[0497] Specific operation: Displays the loan interest rate, repayment period, and monthly payment amount in a visually easy-to-understand manner using HTML and CSS.

[0498] Step 7:

[0499] Re-analysis (if necessary)

[0500] If the user enters new or additional information, the device sends the data back to the server, which receives the new information, re-analyzes it, and generates a new, optimized loan offer.

[0501] Input: New user data.

[0502] Output: The new reparsed mortgage options.

[0503] Specific behavior: A new prompt is generated and fed back into the generative AI model to generate loan options based on the latest information.

[0504] Through these steps, the system is able to provide efficient and accurate mortgage options to users.

[0505] (Application example 1)

[0506] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0507] Conventional mortgage loan selection systems lack the functionality to allow users to intuitively input data and quickly suggest optimal loan options. They also lack the functionality to re-suggest the latest loan options based on the user's further questions or additional information. This makes it difficult for users to easily find the optimal mortgage option. The present invention aims to solve these problems and provide a mortgage loan selection system that users can easily use.

[0508] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0509] In this invention, the server includes: means for a user to input his or her attributes and household financial situation; means for transmitting the input user data to the server; means for the server to receive the user data and store it in a database; means for the server to preprocess the stored user data; means for a generation AI to match the preprocessed user data with market data and generate optimal mortgage options; means for the server to transmit the generated mortgage options to a terminal; means for the terminal to visually display the loan options to the user in an easy-to-understand manner; means for the user to answer further questions or provide additional information; and means for the server to receive new information from the user, reanalyze, and generate new optimized loan proposals. This allows users to easily obtain optimal loan options based on the latest information at all times.

[0510] 1. "User" refers to an individual who uses the system to enter their own attributes and household financial situation.

[0511] 2. "Attributes" refers to personal information about a user, such as gender, age, place of employment, etc.

[0512] 3. "Household financial situation" refers to information about the user's financial situation, such as financial assets, annual income, property price, personal funds, and desired repayment period.

[0513] 4. "Server" refers to the equipment or platform for receiving user data, storing it in a database, and pre-processing it.

[0514] 5. "Database" means a collection of information for formatting and securely storing received User Data.

[0515] 6. "Preprocessing" refers to the process of converting received data into a form suitable for analysis by cleaning, normalizing, feature engineering, etc.

[0516] 7. “Generative AI” refers to an artificial intelligence model that analyzes user and market data to generate optimal mortgage options.

[0517] 8. "Market Data" refers to data including the latest mortgage products, interest rate information, and repayment terms.

[0518] 9. "Mortgage Options" refers to the optimal mortgage products and terms generated based on the user's attributes and financial situation.

[0519] 10. "Terminal" means the device (such as a smartphone or tablet) through which a User enters their data and views the generated mortgage options.

[0520] 11. "Visually easy to understand" means that the proposed mortgage options are visually presented on the terminal in a way that allows the user to intuitively understand them.

[0521] 12. "Answering a question or providing additional information" means that the user enters new data or further details into the system.

[0522] 13. "Reanalysis" refers to the process of conducting a new analysis based on new information provided by the user to generate new mortgage options.

[0523] 14. "Loan Option Rate" means the interest rate terms on a mortgage loan.

[0524] 15. "Repayment period" refers to the period until the total principal and interest of a mortgage is paid off.

[0525] 16. "Monthly payment" refers to the amount paid each month to repay a mortgage.

[0526] This invention relates to a system that allows users to input their attributes and financial situation and proposes optimal mortgage options. Since the main functions of this invention are a server, a terminal, and a generative AI model, specific embodiments of these are described below.

[0527] First, the user uses a terminal to input their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, property price, personal funds, desired repayment period, etc.). The terminal can be a smartphone or tablet, and provides an application designed to allow the user to input data intuitively. This data is then sent from the terminal to a server via the Internet.

[0528] When the server receives the data, it stores it in a database. A relational database such as MySQL or PostgreSQL is used for the database. The received data undergoes any necessary reformatting (standardizing the format and detecting and correcting outliers). For example, numerical data such as annual income or financial assets is converted into consistent units.

[0529] Next, the server performs preprocessing, which includes data cleaning (inserting missing values ​​and removing duplicate data), normalization (standardizing different units and formats), and feature engineering (converting data into a format suitable for the model). Once preprocessing is complete, the data is input into the generative AI.

[0530] The generative AI is built using machine learning frameworks such as TensorFlow and PyTorch, and analyzes user data and market data. Market data includes the latest mortgage products, interest rates, repayment terms, etc. The generative AI comprehensively evaluates this data to generate mortgage options that best suit the user's attributes and financial situation.

[0531] The generated mortgage options are sent from the server to the terminal, which provides the user with a visually-friendly interface that displays the loan interest rate, repayment period, monthly payment amount, etc. The user can then make a selection based on this information.

[0532] Furthermore, if the user provides additional information or answers further questions, the information is sent back to the server, which then re-analyzes the new information and provides a new set of optimal loan options.

[0533] Specific examples

[0534] Example 1: First-time home buyer

[0535] When a user inputs "annual income of 6 million yen, personal funds of 3 million yen, property value of 40 million yen, 35-year-old male," the AI ​​generator will create a reasonable repayment plan and propose a mortgage with a fixed interest rate of 2.0%. The terminal will display "Monthly repayment of 100,000 yen with a fixed interest rate of 2.0%."

[0536] Example 2: A user considering refinancing

[0537] When a user inputs "current balance of 20 million yen, variable interest rate of 2.5%, annual income of 8 million yen, 40-year-old female," the AI ​​generates a suggestion that "refinancing is possible to a loan with a fixed interest rate of 1.8%," and the user is notified via their device.

[0538] Prompt Sentence Examples

[0539] "Gender: Male" "Age: 35" "Employer: ABC Co., Ltd." "Financial assets: 3 million yen" "Annual income: 6 million yen" "Property price: 40 million yen" "Own funds: 3 million yen" "Repayment period: 35 years"

[0540] By integrating these steps and elements, the present invention allows users to easily access the best mortgage options based on the most up-to-date information.

[0541] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0542] Step 1:

[0543] Users use the device to enter their attributes and household financial situation. This includes information such as gender, age, place of employment, financial assets, annual income, property price, personal funds, and desired repayment period. The entered data can be intuitively operated via a dedicated application on the device or a web form. The entered data is temporarily stored on the device and then sent to the server.

[0544] Input: User demographic information and household financial situation.

[0545] Output: User data sent to the server.

[0546] Step 2:

[0547] The server receives user data sent from the device and stores it in a database. A relational database such as MySQL or PostgreSQL is used for the database. The received data is first verified, and any formatting and any outliers are detected and corrected. At this stage, the consistency and accuracy of the data are guaranteed.

[0548] Input: User data sent from the device.

[0549] Output: Validated data stored in a database.

[0550] Step 3:

[0551] The server preprocesses the stored user data. Preprocessing includes data cleaning (inserting missing values ​​and removing duplicate data), data normalization (standardizing different units and formats), and feature engineering (converting data into a format suitable for the model). This prepares the data for input into the generative AI model.

[0552] Input: User data stored in the database.

[0553] Output: Preprocessed user data.

[0554] Step 4:

[0555] Based on the preprocessed user data, the server uses a generative AI model to match it with market data and generate optimal mortgage options. The generative AI model is built using machine learning frameworks such as TensorFlow and PyTorch. Market data includes the latest mortgage products, interest rates, repayment terms, etc., and comprehensively evaluates these to generate the optimal option for each user.

[0556] Input: Preprocessed user and market data.

[0557] Output: The generated mortgage options.

[0558] Step 5:

[0559] The server sends the generated mortgage options to the terminal, which provides the user with a visual interface that displays the loan interest rate, repayment period, monthly payment amount, etc. The user can review the options and proceed with their selection.

[0560] Input: The generated mortgage option.

[0561] Output: Loan options displayed on the terminal.

[0562] Step 6:

[0563] If the user answers further questions or provides additional information, the new information is sent via the device to the server, which receives this new information, reanalyzes it, and re-uses the generative AI model to generate new, optimized loan offers. The regenerated loan options are again sent to the device and displayed to the user.

[0564] Input: User data based on additional information or new questions.

[0565] Output: Regenerated loan options.

[0566] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0567] The present invention relates to a system that automatically generates and proposes optimal mortgage options based on the user's input of their attributes and financial situation. In particular, the present invention achieves more personalized proposals by incorporating an emotion engine that recognizes the user's emotions.

[0568] First, the user uses a device to access a web form or a dedicated app and enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.). This input data is collected using an interface designed to allow users to enter data easily.

[0569] The entered data is sent from the terminal to the server. The server verifies the received user data, formats it, and stores it in a database. At this time, the data is cleaned and formatted to maintain data integrity.

[0570] The server then preprocesses the data stored in the database, including filling in missing values, correcting outliers, and normalizing the data. Once preprocessed, the data is fed into a generative AI, which generates optimal mortgage options based on user and market data.

[0571] The generated mortgage options are then formatted into a user-friendly format by the server and sent to the terminal, which displays the proposed loan options to the user, including the loan interest rate, repayment period, and monthly payment amount.

[0572] A distinctive feature of the present invention is the inclusion of an emotion engine. The emotion engine analyzes the user's input data and daily usage patterns to identify the user's current emotional state. For example, by analyzing the user's input text, click patterns, and input speed, it determines whether the user is currently feeling stressed or relaxed.

[0573] Once the emotion engine identifies the user's emotional state, that information is fed back to the generative AI to customize the loan option recommendations and presentation. For example, if the user is stressed, they will receive more concise and easy-to-understand recommendations, while if they are relaxed, they will receive more detailed information.

[0574] Specific examples

[0575] Example 1: First-time home buyer

[0576] The user inputs "annual income of 6 million yen, personal funds of 3 million yen, property value of 40 million yen, 35-year-old male." The emotion engine analyzes input speed and keystroke patterns to determine that the user is feeling somewhat anxious. The generative AI then creates a reasonable repayment plan and proposes a mortgage with a fixed interest rate of 2.0%. The proposal is displayed concretely and simply: "Monthly repayments of 100,000 yen with a fixed interest rate of 2.0%."

[0577] Example 2: User considering refinancing

[0578] The user enters "current balance of 20 million yen, variable interest rate of 2.5%, annual income of 8 million yen, 40-year-old female." The emotion engine determines that the user is relaxed based on their click patterns and time spent on the site. The generation AI displays a proposal with detailed information, such as "refinancing to a fixed interest rate of 1.8% will save you 100,000 yen per year."

[0579] By implementing the present invention, users can easily select loan options that are best suited to them and that correspond to their emotional state without requiring specialized financial knowledge, thereby improving user satisfaction and realizing an efficient loan selection process.

[0580] The processing flow will be explained below.

[0581] Step 1:

[0582] The user enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.) into a dedicated web form or app on their device.

[0583] Step 2:

[0584] The terminal collects the user's input data and sends the data to the server according to a standard format.

[0585] Step 3:

[0586] The server receives the user data sent from the terminal and first verifies the format and validity of the data, for example, whether all required fields are filled in and whether the numeric format is appropriate.

[0587] Step 4:

[0588] The server stores the verified data in the database, performing transaction processing to ensure data consistency and integrity.

[0589] Step 5:

[0590] The server preprocesses the user data stored in the database, including filling in missing values, correcting outliers, and normalizing the data (unifying different units and formats).

[0591] Step 6:

[0592] The server passes the preprocessed data to the generation AI, which then performs analysis based on user data and market data.

[0593] Step 7:

[0594] Generative AI generates mortgage options that best suit the user's attributes and financial situation, comparing interest rates and adjusting repayment periods based on mortgage products in market data.

[0595] Step 8:

[0596] The server formats the loan options returned by the generation AI into a user-friendly format, specifically, making loan interest rates, repayment periods, monthly payments, etc., visually easy to understand using tables and graphs.

[0597] Step 9:

[0598] The server sends the formatted loan option to the terminal.

[0599] Step 10:

[0600] The terminal displays the loan options received from the server to the user, who can then confirm the proposed loan terms.

[0601] Step 11:

[0602] The emotion engine analyzes the user's input data, click patterns, typing speed, etc. to determine the user's current emotional state. For example, if the user takes a long time to type, the emotion engine will determine that the user is feeling stressed.

[0603] Step 12:

[0604] The emotion engine identifies the user's emotional state and feeds it back to the generative AI to adjust the content and presentation of the suggestions. For example, if the user is feeling stressed, the suggestions will be made more concise.

[0605] Step 13:

[0606] The terminal then presents the user with customized loan options again, allowing them to make the best choice based on concise and easy-to-understand information.

[0607] Step 14:

[0608] If the user asks further questions about the suggestions or provides additional data, the terminal transmits the new data to the server again.

[0609] Step 15:

[0610] The server aggregates the newly received data and the results of the emotion engine's analysis of the emotional state, and then reanalyzes it with the generative AI, which then generates a new loan proposal.

[0611] Step 16:

[0612] The server then formats the reparsed loan options into a user-friendly format and sends it to the terminal, where the user can review the new offers.

[0613] These steps allow users to easily and efficiently find the best mortgage option that suits their needs.

[0614] Example 2

[0615] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0616] Conventional mortgage option proposal systems have difficulty making optimal proposals based on a user's individual attributes and financial situation, and are unable to make proposals that take into account the user's emotional state. This causes users to feel a great deal of stress when selecting the optimal loan option. Furthermore, it is difficult to quickly reanalyze the system when the entered user data is inaccurate or when market data is updated.

[0617] The specification processing by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input their own attributes and household financial situation; means for transmitting the input user data to an information processing device; means for the information processing device to receive the user data and store it in a storage medium; means for the information processing device to preprocess the stored user data; means for a machine learning model to match the preprocessed user data with market data and generate optimal mortgage options; means for the information processing device to transmit the generated mortgage options to an output device; means for the output device to display the loan options to the user; and means for analyzing the user's emotional state using an emotion analysis engine and customizing the generated mortgage options based on the user's emotional state. As a result, the user is offered optimal mortgage options based on their attributes and household financial situation, and further receives personalized offers according to the user's emotional state, which makes the selection process easier and improves the user experience.

[0618] "User" refers to any individual or entity that utilizes this system to receive mortgage options.

[0619] "Attributes" refers to personal information such as a user's gender, age, place of employment, etc.

[0620] "Household finances" refers to economic information such as a user's financial assets, annual income, and expenses.

[0621] "Information processing device" refers to a device that receives, processes, and analyzes data sent by a user.

[0622] "Storage medium" refers to a data storage device used by an information processing device to store user data.

[0623] "Preprocessing" refers to performing processes such as missing value completion, outlier correction, and normalization on user data.

[0624] "Machine learning model" refers to an algorithm that uses pre-processed data and market data to generate optimal mortgage options.

[0625] "Market data" refers to external data such as interest rates and property prices, including information used by machine learning models.

[0626] "Output device" refers to a device for displaying generated mortgage options to a user.

[0627] An "emotion analysis engine" refers to algorithms or software for analyzing a user's emotional state.

[0628] The present invention relates to a system that automatically generates and proposes optimal mortgage options based on a user's input of their attributes and financial situation. This system achieves more personalized proposals by incorporating an emotion engine that recognizes the user's emotions. Specific embodiments are described below.

[0629] First, the user uses a device to access a web form or a dedicated app and enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.). This input is done through an intuitive user interface created with React.js or Vue.js. For example, it is expected that the user will enter "annual income of 6 million yen," "self-funding of 3 million yen," and "property price of 40 million yen."

[0630] The device then sends the entered data to the server via a REST API. The server receives the data using Node.js or Express.js and uses the validation framework Joi.js to verify that the input format is correct. For example, it checks that the "annual income" field is in numeric format.

[0631] The server validates the received data, formats it, and then stores it in a database, typically using MongoDB or PostgreSQL. After storing the data, the server preprocesses it using Python scripts and Pandas. This preprocessing includes imputing missing values, correcting outliers, and normalizing the data.

[0632] Once the preprocessing is complete, the data is input into a generative AI model. Machine learning frameworks such as TensorFlow and PyTorch are used for the generative AI model. The prompt for the generative AI model is in the following format: "The user's annual income is 6 million yen, their own funds are 3 million yen, and the property price is 40 million yen. Please suggest the best mortgage option."

[0633] The server receives the optimal mortgage option output by the generative AI model and formats it into a user-friendly format using a template engine (e.g., EJS, Handlebars). The formatted loan option is then sent back to the terminal and presented to the user. At this time, the terminal displays a user-friendly message such as "Fixed interest rate of 2.0%, monthly repayment plan of 100,000 yen."

[0634] Furthermore, the present invention incorporates an emotion engine to identify the user's emotional state, and the generative AI model customizes the suggestions based on this. The emotion engine analyzes input speed, click patterns, dwell time, etc. to determine whether the user is stressed or relaxed. For example, if the user is feeling anxious, the suggestions will be more concise and easy to understand.

[0635] As a concrete example, if a first-time home buyer enters "annual income of 6 million yen, personal funds of 3 million yen, property price of 40 million yen, 35-year-old male," the emotion engine will determine from the keystroke pattern and typing speed that the user is feeling somewhat anxious. The generative AI model will then create a reasonable repayment plan and propose a mortgage with a fixed interest rate of 2.0%. The proposal is displayed in a specific and simple way: "Monthly repayments of 100,000 yen with a fixed interest rate of 2.0%."

[0636] The system allows users to easily select the loan option that best suits them without requiring specialized financial knowledge, and facilitates the selection process by receiving personalized suggestions based on their emotional state, improving the user experience and realizing an efficient loan selection process.

[0637] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0638] Step 1: The user enters their attributes and household financial situation

[0639] Users use their device to access a web form or a dedicated app and enter their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.).

[0640] Specific operation: The user opens a browser or app and enters information such as "annual income of 6 million yen," "personal funds of 3 million yen," and "property price of 40 million yen" into a form.

[0641] Input: User attributes and household financial situation data

[0642] Output: User data entered into the terminal

[0643] Step 2: Submit and verify data

[0644] The terminal sends the input data to the server via the REST API, and the server validates the received data using the validation framework.

[0645] What happens: The device sends data to the API endpoint, the server receives the data using Node.js and Express.js, and the server verifies the item format using Joi.js.

[0646] Input: User data sent from the terminal

[0647] Output: Verified user data

[0648] Step 3: Saving and formatting the data

[0649] The server stores the validated data in a database and reformats the data as needed.

[0650] Specific operation: The server stores the data in MongoDB or PostgreSQL and cleans it to unify the data format.

[0651] Input: Validated user data

[0652] Output: Formatted user data stored in the database

[0653] Step 4: Preprocessing the data

[0654] The server retrieves the data from the database and pre-processes it.

[0655] What it does: The server uses Python scripts and Pandas to impute missing values ​​in the data, correct outliers, and normalize the data.

[0656] Input: Preformatted user data stored in the database

[0657] Output: Preprocessed user data

[0658] Step 5: Input to the generative AI model

[0659] The server inputs the preprocessed data into the generative AI model.

[0660] Specific operation: The server uses a Python script to input preprocessed data into a generative AI model built with TensorFlow and PyTorch. The prompt statement is, "The user's annual income is 6 million yen, their own funds are 3 million yen, and the property price is 40 million yen. Please suggest the best mortgage option."

[0661] Input: Preprocessed user data

[0662] Output: Optimal mortgage options from a generative AI model

[0663] Step 6: Format and submit your loan option

[0664] The server formats the optimal mortgage options output by the generative AI model and sends them to the terminal.

[0665] Specific operation: The server uses a template engine (EJS, Handlebars) to format the data into a user-friendly format, and then sends the formatted data to the device.

[0666] Input: Loan option data output by the generative AI model

[0667] Output: Formatted loan option data

[0668] Step 7: View loan options

[0669] The terminal displays the loan options received from the server to the user.

[0670] Specific operation: The device displays information such as "Fixed interest rate 2.0%, monthly repayment plan of 100,000 yen" on a web page or app.

[0671] Input: Formatted loan option data

[0672] Output: Loan options displayed to the user

[0673] Step 8: Applying the Sentiment Analysis Engine

[0674] The server uses an emotion analysis engine to analyze the user's emotional state and provides feedback to the generative AI model.

[0675] How it works: The server analyzes the user's typing speed and click patterns to determine their state of stress or relaxation. The analysis results are fed back to the generative AI model to customize the suggestions.

[0676] Input: User input data and usage patterns

[0677] Output: Customized loan options based on the user's emotional state

[0678] (Application example 2)

[0679] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0680] In today's world, it is not easy for consumers to find the best products and services for them from the vast amount of information available. Furthermore, consumers often require different recommendations depending on their emotional state. Furthermore, there is a demand for systems that allow them to receive personalized recommendations regardless of time or location.

[0681] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0682] In this invention, the server includes: means for a user to input their attributes and household financial situation; means for transmitting the input user data to the server; means for the server to receive the user data and store it in a database; means for the server to preprocess the stored user data; means for a generation AI to match the preprocessed user data with market data and generate optimal mortgage options; means for the server to transmit the generated mortgage options to a terminal; means for the terminal to display the loan options to the user; and means for using a smart device in a physical store to analyze the user's attributes and emotional state and suggest optimal products and services based on the results. This allows users to easily find the products and services that are best suited to them and also allows them to receive personalized suggestions based on their emotional state.

[0683] "User attributes" is a general term for personal information such as a user's age, gender, occupation, purchasing history, etc.

[0684] "Finance situation" refers to a user's financial assets, annual income, expenses and other financial information.

[0685] A "server" is a computer system that receives, stores, and processes data sent by users.

[0686] A "database" is a structured collection of data for storing collected user data.

[0687] "Preprocessing" refers to cleaning and standardizing the format of data before analyzing it, such as imputing missing values ​​and normalizing data.

[0688] "Generative AI" refers to technology that uses artificial intelligence models to generate optimal recommendations based on user and market data.

[0689] "Smart devices" refers to devices such as smartphones and smart glasses that have internet connectivity and can acquire and process data.

[0690] "Physical store" refers to a physical sales or service location.

[0691] "Emotional state" refers to the user's current psychological state, including the degree of stress or relaxation.

[0692] "Suggestion" refers to a recommendation or option offered to a user.

[0693] This system uses smart devices in a brick-and-mortar store to analyze a user's attributes and emotional state to suggest optimal products and services. The system consists of a user, a server, a smart device, and a terminal.

[0694] First, the user puts on a smart device such as smart glasses in a physical store. The camera and sensors installed in the smart device recognize the user's face and collect data in real time. This allows the user's attributes (age, gender, occupation, purchasing history, etc.) and emotional state (stress, relaxation, etc.) to be analyzed.

[0695] The collected data is sent to a server, which stores the received data in a database and performs preprocessing. Preprocessing includes cleaning the data, standardizing the format, and filling in missing values. The preprocessed data is then input into the generative AI.

[0696] Generative AI uses user and market data to suggest optimal products and services. For example, if a user is feeling stressed, it might suggest relaxation products or books. On the other hand, if a user is feeling relaxed, it might suggest the latest electronics or sports equipment.

[0697] The generated proposals are sent via the server to the smart device, which then displays the proposals in a user-friendly format, including product or service descriptions, prices, sales information, coupons, etc.

[0698] As a concrete example of this system, the following prompt sentence is input to the generation AI:

[0699] Example prompt for a generative AI model:

[0700] User ID_001 (male, 35 years old) has purchased electrical appliances and sports equipment in the past. Currently, the user is feeling stressed, so we recommend relaxation products and books. Please display the suggestions in a user-friendly format.

[0701] This system allows users to enjoy shopping in brick-and-mortar stores in an efficient and personalized way. The suggestions are dynamically adjusted according to the user's emotional state, so the system always provides the most suitable products and services for the user.

[0702] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0703] Step 1:

[0704] A user puts on the smart glasses.

[0705] Input: Putting on smart glasses, activating cameras and sensors.

[0706] How it works: When a user enters a physical store and puts on the smart glasses, the smart glasses' camera and sensors are activated, allowing the smart device to detect the user's face and begin collecting data in real time.

[0707] Step 2:

[0708] The smart device recognizes the user's face and analyzes their attributes and emotional state.

[0709] Input: Facial image data and other sensor data.

[0710] Output: User demographics and emotional state data.

[0711] How it works: Using facial image data captured by the camera and biometric data from sensors, the system runs a facial recognition algorithm and emotion recognition model to identify the user's demographic information, such as age, gender, and past purchase history, as well as their current emotional state (such as stress level).

[0712] Step 3:

[0713] The smart device sends the acquired data to the server.

[0714] Input: User demographic information and emotional state data.

[0715] Output: User data sent to the server.

[0716] Specific operation: The smart glasses collect user attribute information and emotional state data and send it to the server. The data is encrypted and transmitted securely.

[0717] Step 4:

[0718] The server stores the received data in a database and performs preprocessing.

[0719] Input: The retrieved user data.

[0720] Output: Preprocessed user data.

[0721] Specific operation: The server first stores the received data in a database, then performs preprocessing such as filling in missing values, correcting outliers, and normalizing the data. The preprocessed data is then formatted into a format suitable for analysis.

[0722] Step 5:

[0723] Based on the pre-processed data, generative AI suggests optimal products and services.

[0724] Input: Preprocessed user and market data.

[0725] Output: Recommendations for the best products and services.

[0726] Specific operation: Preprocessed user data and market data are input into the Generative AI, which then runs the algorithm to generate the best products and services for the user. Specifically, if the user is feeling stressed, it will suggest relaxation products, and if they are feeling relaxed, it will suggest the latest electronic appliances.

[0727] Step 6:

[0728] The server sends the generated proposal to the smart device.

[0729] Input: Generated product or service proposals.

[0730] Output: Proposal data sent to smart device.

[0731] How it works: The server receives the proposed data from the generative AI model, converts it into a user-friendly format, and then securely transmits it to the smart glasses.

[0732] Step 7:

[0733] The smart device displays the suggestions to the user.

[0734] Input: Proposal data sent by the server.

[0735] Output: The suggested products or services displayed to the user.

[0736] How it works: The smart glasses display information about suggested products and services on the screen, including product descriptions, prices, sales information, coupons, etc. This information allows users to efficiently select products in the store.

[0737] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0738] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0739] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0740] [Third embodiment]

[0741] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0742] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0743] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0744] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0745] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0746] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0747] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0748] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0749] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0750] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0751] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0752] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0753] The present invention relates to a system that automatically generates and proposes optimal housing loan options based on a user's input of their attributes and financial situation. The present invention is implemented in accordance with the following steps.

[0754] First, the user uses a device to access a web form or a dedicated app and enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.). This data is designed to be easily entered by the user, and the form has an intuitive, easy-to-understand interface.

[0755] The entered data is sent from the terminal to the server. The server verifies the received user data, performs any necessary formatting (standardizing the format and detecting and correcting outliers), and then stores it in the database. This process ensures the consistency and accuracy of the data.

[0756] The server then preprocesses the stored user data, which includes data cleaning (inserting missing values ​​and removing duplicate data), normalization (unifying different units and formats), and feature engineering (converting data into a format suitable for the model).

[0757] Once preprocessing is complete, the user data is input into the generation AI, which analyzes the user data and market data to generate mortgage options that best suit the user's attributes and financial situation. The market data includes the latest mortgage products, interest rates, repayment terms, and more, and the AI ​​comprehensively evaluates these.

[0758] The generated mortgage options are then formatted into a user-friendly format by the server and sent back to the terminal, where the user can view the proposed loan options. Specifically, the loan interest rate, repayment period, monthly payment amount, etc. are displayed in a visually understandable manner.

[0759] If the user has further questions or provides additional data based on the information provided, the device will send it back to the server, which will then receive the new information, reanalyze it, and generate a new, optimized loan proposal. This ensures that the user always has the best loan options based on the latest information.

[0760] Specific examples

[0761] Example 1: First-time home buyer

[0762] The user enters "annual income of 6 million yen, personal funds of 3 million yen, property value of 40 million yen, male, 35 years old." The device sends this information to the server, which stores the data in a database. The generating AI then analyzes the user data and market data, creates a reasonable repayment plan, and proposes a mortgage with a fixed interest rate of 2.0%. The device displays to the user, "Monthly repayment of 100,000 yen with a fixed interest rate of 2.0%."

[0763] Example 2: User considering refinancing

[0764] The user inputs "current balance of 20 million yen, variable interest rate of 2.5%, annual income of 8 million yen, 40-year-old female." The terminal again sends the new information to the server, which analyzes it using the generation AI. As a result, a proposal is generated that "refinancing to a loan with a fixed interest rate of 1.8% is possible," and the terminal notifies the user.

[0765] Through these steps, the system of the present invention allows users to select a home loan easily and efficiently, and provides optimal loan options.

[0766] The processing flow will be explained below.

[0767] Step 1:

[0768] The user enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.) into a dedicated web form or app on their device.

[0769] Step 2:

[0770] The terminal collects the user's input data and sends the data to the server according to a standard format.

[0771] Step 3:

[0772] The server receives the user data sent from the terminal and first verifies the format and validity of the data, for example, whether all required data fields are filled in and whether the numeric format is appropriate.

[0773] Step 4:

[0774] The server stores the verified data in the database, performing transaction processing to maintain data consistency and integrity.

[0775] Step 5:

[0776] The server preprocesses the user data stored in the database, including missing value imputation, outlier detection and correction, and data normalization.

[0777] Step 6:

[0778] The server passes the preprocessed data to the generation AI, which performs analysis based on user data and market data.

[0779] Step 7:

[0780] The AI ​​generates mortgage options that best suit the user's attributes and financial situation, comparing interest rates and adjusting repayment periods based on mortgage products in market data.

[0781] Step 8:

[0782] The server formats the loan options returned by the generation AI into a user-friendly format, specifically, making loan interest rates, repayment periods, monthly payments, etc., visually easy to understand using tables and graphs.

[0783] Step 9:

[0784] The server sends the formatted loan option to the terminal.

[0785] Step 10:

[0786] The terminal displays the loan options received from the server to the user, who can then confirm the proposed loan terms.

[0787] Step 11:

[0788] If the user has the option to ask further questions or provide additional data about the proposed loan option, the terminal will again transmit this new data to the server.

[0789] Step 12:

[0790] The server re-analyzes the newly received data and invokes the generation AI to generate new loan proposals, ensuring that users are always provided with the best loan options based on the latest information.

[0791] Example 1

[0792] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0793] In conventional mortgage selection systems, even after users input their attributes and financial situation, it takes a long time to provide appropriate loan options, and the information provided to users is often insufficient. Furthermore, there is no mechanism to automatically regenerate consistent and appropriate loan proposals every time a user inputs new information. This makes it difficult for users to find the mortgage option that best suits them, and makes it difficult for them to make efficient decisions.

[0794] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0795] In this invention, the server includes means for receiving user data, checking the data format, detecting and correcting outliers, and storing the data in a database; means for preprocessing the stored user data, completing missing values, deleting duplicate data, and normalizing the data; and means for a generation AI to match the preprocessed user data with market data and generate optimal mortgage options. This allows users to efficiently and accurately find optimal mortgage options. Furthermore, even if the user enters new information, the system automatically reanalyzes the data and provides optimal loan options based on the latest information.

[0796] A "user" is someone who uses the system to input their attributes and financial situation to find the best mortgage option for them.

[0797] A "terminal" is a device used by a user to input information, and includes a PC, a smartphone, a tablet, and the like.

[0798] "Server" refers to a computer system that receives, processes, stores, and analyzes data sent by users.

[0799] "Attributes" refers to basic information that identifies an individual, such as a user's gender, age, place of employment, etc.

[0800] "Finance" refers to information about a user's financial assets, annual income, expenses, and other economic circumstances.

[0801] "Database" refers to an information management system that stores received user data and retrieves and uses it when necessary.

[0802] "Preprocessing" refers to checking the format of the received data, detecting and correcting outliers, filling in missing values, deleting duplicate data, normalizing data, and other processes to prepare the data in a format suitable for analysis.

[0803] "Generative AI" refers to an artificial intelligence model that analyzes data provided by users and market data to automatically generate optimal mortgage options.

[0804] "Market Data" refers to information about the mortgage market, including the latest mortgage products, interest rate information, and repayment terms.

[0805] A "prompt sentence" is a sentence that specifically describes instructions or questions for the generation AI, and refers to the input sentence that the AI ​​analyzes based on this and generates a result.

[0806] "Loan options" are the optimal mortgage options suggested by the generative AI based on the user's attributes and financial situation, and specifically include interest rates, repayment periods, and monthly payments.

[0807] The present invention relates to a system that automatically generates and proposes optimal mortgage options based on a user's input of their attributes and financial situation. This system is implemented using a server, a terminal, and a generative AI model.

[0808] Users access web forms or dedicated applications using devices (PCs, smartphones, tablets, etc.) and enter their personal attributes (gender, age, place of employment, etc.) and household financial situation (financial assets, annual income, etc.). This data is provided through an interface designed to allow users to enter it easily.

[0809] The entered data is sent from the terminal to the server, which checks the data format (e.g., JSON or XML format), detects and corrects outliers, and then stores the data in a database (e.g., a relational database such as MySQL or PostgreSQL).

[0810] The server preprocesses the user data stored in the database. This preprocessing includes missing value imputation, duplicate data removal, normalization for different units and formats, and feature engineering. Specifically, the server can use the Python Pandas library to manipulate data frames and perform these preprocessing operations.

[0811] Once the preprocessing is complete, the data is fed into a generative AI model (e.g., GPT-3 or another generative model) that analyzes the data based on a prompt and generates mortgage options that best fit the user's attributes and financial situation. The prompt has the following format:

[0812] User attributes: Age 35, Gender: Male, Workplace: Corporate, Annual income: 6 million yen. Household finances: Personal funds: 3 million yen, Property price: 40 million yen. Please suggest the best mortgage option.

[0813] The generated loan options are formatted in a user-friendly format by the server and sent to the terminal, which then visually displays the interest rate, repayment period, and monthly payment amount of the received loan options to the user.

[0814] For example, if a user enters "annual income of 6 million yen, personal funds of 3 million yen, property value of 40 million yen, 35-year-old male," the device sends this information to the server. The server verifies the data and stores it in a database. The generating AI then analyzes the user data and market data to propose a mortgage with a fixed interest rate of 2.0% as a reasonable repayment plan. This information is sent to the device and displayed as "monthly repayments of 100,000 yen with a fixed interest rate of 2.0%."

[0815] If the user enters new or additional information, the device sends that data back to the server, which then receives the new information, analyzes it again using the generative AI model, and generates a new, optimized loan proposal. This ensures that the user always has the most up-to-date information and the best loan options.

[0816] In this way, the system of the present invention allows users to select home loans efficiently and accurately.

[0817] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0818] Step 1:

[0819] User Data Entry

[0820] Users use their devices to access web forms or dedicated applications and enter their personal attributes (gender, age, place of employment, etc.) and household financial situation (financial assets, annual income, etc.). The data entered is designed to be easily entered into the device's form.

[0821] Input: Demographic and financial information entered by the user into the form.

[0822] Output: User data stored on the device in JSON or XML format.

[0823] Specific behavior: The user manually enters the required information into fields in a browser or application and presses the "Submit" button.

[0824] Step 2:

[0825] Data submission and validation

[0826] The terminal sends the entered data to the server. The data is encrypted before being sent, ensuring security.

[0827] Server operation: The server validates the data it receives. It checks the data format and required fields, and returns an error message if there are any errors.

[0828] Input: User data sent from the device in JSON or XML format.

[0829] Output: Validated and formatted user data.

[0830] Specific operation: A POST request is sent to the endpoint, and on the server side, the request is received by Flask or Django and the format is checked.

[0831] Step 3:

[0832] Data Formatting and Storage

[0833] The server formats the received data, standardizes the format, detects and corrects outliers, and then stores it in a database.

[0834] Input: Validated and formatted user data.

[0835] Output: Dataset stored in a database.

[0836] Specific operation: Use Pandas to format the data, correct outliers, and then insert it into a relational database using an ORM such as SQLAlchemy.

[0837] Step 4:

[0838] Preprocessing user data

[0839] The server preprocesses the user data stored in the database, including imputing missing values, removing duplicate data, normalizing for different units and formats, and feature engineering.

[0840] Input: Datasets stored in a database.

[0841] Output: A preprocessed and clean dataset.

[0842] Specific behavior: Manipulates data frames using the Pandas library, imputes missing values ​​with the mean, removes duplicates, and standardizes units.

[0843] Step 5:

[0844] Generative AI-powered loan option generation

[0845] The preprocessed data is fed into a generative AI model (such as GPT-3), which analyzes the prompt text and generates mortgage options that best fit the user's attributes and financial situation.

[0846] Input: A preprocessed, clean dataset, and a prompt statement.

[0847] Output: The generated mortgage options.

[0848] What it does: It feeds data into a trained GPT-3 model and gives it instructions using specific prompts (e.g., "What are the best loan options for a 35-year-old male with an annual income of $60,000?").

[0849] Step 6:

[0850] Formatting and displaying results

[0851] The server formats the generated loan options into a user-friendly format and sends them to the terminal.

[0852] Input: Generated mortgage options.

[0853] Output: Loan options formatted in a user-friendly format.

[0854] Specific operation: Displays the loan interest rate, repayment period, and monthly payment amount in a visually easy-to-understand manner using HTML and CSS.

[0855] Step 7:

[0856] Re-analysis (if necessary)

[0857] If the user enters new or additional information, the device sends the data back to the server, which receives the new information, re-analyzes it, and generates a new, optimized loan offer.

[0858] Input: New user data.

[0859] Output: The new reparsed mortgage options.

[0860] Specific behavior: A new prompt is generated and fed back into the generative AI model to generate loan options based on the latest information.

[0861] Through these steps, the system is able to provide efficient and accurate mortgage options to users.

[0862] (Application example 1)

[0863] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0864] Conventional mortgage loan selection systems lack the functionality to allow users to intuitively input data and quickly suggest optimal loan options. They also lack the functionality to re-suggest the latest loan options based on the user's further questions or additional information. This makes it difficult for users to easily find the optimal mortgage option. The present invention aims to solve these problems and provide a mortgage loan selection system that users can easily use.

[0865] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0866] In this invention, the server includes: means for a user to input his or her attributes and household financial situation; means for transmitting the input user data to the server; means for the server to receive the user data and store it in a database; means for the server to preprocess the stored user data; means for a generation AI to match the preprocessed user data with market data and generate optimal mortgage options; means for the server to transmit the generated mortgage options to a terminal; means for the terminal to visually display the loan options to the user in an easy-to-understand manner; means for the user to answer further questions or provide additional information; and means for the server to receive new information from the user, reanalyze, and generate new optimized loan proposals. This allows users to easily obtain optimal loan options based on the latest information at all times.

[0867] 1. "User" refers to an individual who uses the system to enter their own attributes and household financial situation.

[0868] 2. "Attributes" refers to personal information about a user, such as gender, age, place of employment, etc.

[0869] 3. "Household financial situation" refers to information about the user's financial situation, such as financial assets, annual income, property price, personal funds, and desired repayment period.

[0870] 4. "Server" refers to the equipment or platform for receiving user data, storing it in a database, and pre-processing it.

[0871] 5. "Database" means a collection of information for formatting and securely storing received User Data.

[0872] 6. "Preprocessing" refers to the process of converting received data into a form suitable for analysis by cleaning, normalizing, feature engineering, etc.

[0873] 7. “Generative AI” refers to an artificial intelligence model that analyzes user and market data to generate optimal mortgage options.

[0874] 8. "Market Data" refers to data including the latest mortgage products, interest rate information, and repayment terms.

[0875] 9. "Mortgage Options" refers to the optimal mortgage products and terms generated based on the user's attributes and financial situation.

[0876] 10. "Terminal" means the device (such as a smartphone or tablet) through which a User enters their data and views the generated mortgage options.

[0877] 11. "Visually easy to understand" means that the proposed mortgage options are visually presented on the terminal in a way that allows the user to intuitively understand them.

[0878] 12. "Answering a question or providing additional information" means that the user enters new data or further details into the system.

[0879] 13. "Reanalysis" refers to the process of conducting a new analysis based on new information provided by the user to generate new mortgage options.

[0880] 14. "Loan Option Rate" means the interest rate terms on a mortgage loan.

[0881] 15. "Repayment period" refers to the period until the total principal and interest of a mortgage is paid off.

[0882] 16. "Monthly payment" refers to the amount paid each month to repay a mortgage.

[0883] This invention relates to a system that allows users to input their attributes and financial situation and proposes optimal mortgage options. Since the main functions of this invention are a server, a terminal, and a generative AI model, specific embodiments of these are described below.

[0884] First, the user uses a terminal to input their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, property price, personal funds, desired repayment period, etc.). The terminal can be a smartphone or tablet, and provides an application designed to allow the user to input data intuitively. This data is then sent from the terminal to a server via the Internet.

[0885] When the server receives the data, it stores it in a database. A relational database such as MySQL or PostgreSQL is used for the database. The received data undergoes any necessary reformatting (standardizing the format and detecting and correcting outliers). For example, numerical data such as annual income or financial assets is converted into consistent units.

[0886] Next, the server performs preprocessing, which includes data cleaning (inserting missing values ​​and removing duplicate data), normalization (standardizing different units and formats), and feature engineering (converting data into a format suitable for the model). Once preprocessing is complete, the data is input into the generative AI.

[0887] The generative AI is built using machine learning frameworks such as TensorFlow and PyTorch, and analyzes user data and market data. Market data includes the latest mortgage products, interest rates, repayment terms, etc. The generative AI comprehensively evaluates this data to generate mortgage options that best suit the user's attributes and financial situation.

[0888] The generated mortgage options are sent from the server to the terminal, which provides the user with a visually-friendly interface that displays the loan interest rate, repayment period, monthly payment amount, etc. The user can then make a selection based on this information.

[0889] Furthermore, if the user provides additional information or answers further questions, the information is sent back to the server, which then re-analyzes the new information and provides a new set of optimal loan options.

[0890] Specific examples

[0891] Example 1: First-time home buyer

[0892] When a user inputs "annual income of 6 million yen, personal funds of 3 million yen, property value of 40 million yen, 35-year-old male," the AI ​​generator will create a reasonable repayment plan and propose a mortgage with a fixed interest rate of 2.0%. The terminal will display "Monthly repayment of 100,000 yen with a fixed interest rate of 2.0%."

[0893] Example 2: A user considering refinancing

[0894] When a user inputs "current balance of 20 million yen, variable interest rate of 2.5%, annual income of 8 million yen, 40-year-old female," the AI ​​generates a suggestion that "refinancing is possible to a loan with a fixed interest rate of 1.8%," and the user is notified via their device.

[0895] Prompt Sentence Examples

[0896] "Gender: Male" "Age: 35" "Employer: ABC Co., Ltd." "Financial assets: 3 million yen" "Annual income: 6 million yen" "Property price: 40 million yen" "Own funds: 3 million yen" "Repayment period: 35 years"

[0897] By integrating these steps and elements, the present invention allows users to easily access the best mortgage options based on the most up-to-date information.

[0898] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0899] Step 1:

[0900] Users use the device to enter their attributes and household financial situation. This includes information such as gender, age, place of employment, financial assets, annual income, property price, personal funds, and desired repayment period. The entered data can be intuitively operated via a dedicated application on the device or a web form. The entered data is temporarily stored on the device and then sent to the server.

[0901] Input: User demographic information and household financial situation.

[0902] Output: User data sent to the server.

[0903] Step 2:

[0904] The server receives user data sent from the device and stores it in a database. A relational database such as MySQL or PostgreSQL is used for the database. The received data is first verified, and any formatting and any outliers are detected and corrected. At this stage, the consistency and accuracy of the data are guaranteed.

[0905] Input: User data sent from the device.

[0906] Output: Validated data stored in a database.

[0907] Step 3:

[0908] The server preprocesses the stored user data. Preprocessing includes data cleaning (inserting missing values ​​and removing duplicate data), data normalization (standardizing different units and formats), and feature engineering (converting data into a format suitable for the model). This prepares the data for input into the generative AI model.

[0909] Input: User data stored in the database.

[0910] Output: Preprocessed user data.

[0911] Step 4:

[0912] Based on the preprocessed user data, the server uses a generative AI model to match it with market data and generate optimal mortgage options. The generative AI model is built using machine learning frameworks such as TensorFlow and PyTorch. Market data includes the latest mortgage products, interest rates, repayment terms, etc., and comprehensively evaluates these to generate the optimal option for each user.

[0913] Input: Preprocessed user and market data.

[0914] Output: The generated mortgage options.

[0915] Step 5:

[0916] The server sends the generated mortgage options to the terminal, which provides the user with a visual interface that displays the loan interest rate, repayment period, monthly payment amount, etc. The user can review the options and proceed with their selection.

[0917] Input: The generated mortgage option.

[0918] Output: Loan options displayed on the terminal.

[0919] Step 6:

[0920] If the user answers further questions or provides additional information, the new information is sent via the device to the server, which receives this new information, reanalyzes it, and re-uses the generative AI model to generate new, optimized loan offers. The regenerated loan options are again sent to the device and displayed to the user.

[0921] Input: User data based on additional information or new questions.

[0922] Output: Regenerated loan options.

[0923] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0924] The present invention relates to a system that automatically generates and proposes optimal mortgage options based on the user's input of their attributes and financial situation. In particular, the present invention achieves more personalized proposals by incorporating an emotion engine that recognizes the user's emotions.

[0925] First, the user uses a device to access a web form or a dedicated app and enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.). This input data is collected using an interface designed to allow users to enter data easily.

[0926] The entered data is sent from the terminal to the server. The server verifies the received user data, formats it, and stores it in a database. At this time, the data is cleaned and formatted to maintain data integrity.

[0927] The server then preprocesses the data stored in the database, including filling in missing values, correcting outliers, and normalizing the data. Once preprocessed, the data is fed into a generative AI, which generates optimal mortgage options based on user and market data.

[0928] The generated mortgage options are then formatted into a user-friendly format by the server and sent to the terminal, which displays the proposed loan options to the user, including the loan interest rate, repayment period, and monthly payment amount.

[0929] A distinctive feature of the present invention is the inclusion of an emotion engine. The emotion engine analyzes the user's input data and daily usage patterns to identify the user's current emotional state. For example, by analyzing the user's input text, click patterns, and input speed, it determines whether the user is currently feeling stressed or relaxed.

[0930] Once the emotion engine identifies the user's emotional state, that information is fed back to the generative AI to customize the loan option recommendations and presentation. For example, if the user is stressed, they will receive more concise and easy-to-understand recommendations, while if they are relaxed, they will receive more detailed information.

[0931] Specific examples

[0932] Example 1: First-time home buyer

[0933] The user inputs "annual income of 6 million yen, personal funds of 3 million yen, property value of 40 million yen, 35-year-old male." The emotion engine analyzes input speed and keystroke patterns to determine that the user is feeling somewhat anxious. The generative AI then creates a reasonable repayment plan and proposes a mortgage with a fixed interest rate of 2.0%. The proposal is displayed concretely and simply: "Monthly repayments of 100,000 yen with a fixed interest rate of 2.0%."

[0934] Example 2: User considering refinancing

[0935] The user enters "current balance of 20 million yen, variable interest rate of 2.5%, annual income of 8 million yen, 40-year-old female." The emotion engine determines that the user is relaxed based on their click patterns and time spent on the site. The generation AI displays a proposal with detailed information, such as "refinancing to a fixed interest rate of 1.8% will save you 100,000 yen per year."

[0936] By implementing the present invention, users can easily select loan options that are best suited to them and that correspond to their emotional state without requiring specialized financial knowledge, thereby improving user satisfaction and realizing an efficient loan selection process.

[0937] The processing flow will be explained below.

[0938] Step 1:

[0939] The user enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.) into a dedicated web form or app on their device.

[0940] Step 2:

[0941] The terminal collects the user's input data and sends the data to the server according to a standard format.

[0942] Step 3:

[0943] The server receives the user data sent from the terminal and first verifies the format and validity of the data, for example, whether all required fields are filled in and whether the numeric format is appropriate.

[0944] Step 4:

[0945] The server stores the verified data in the database, performing transaction processing to ensure data consistency and integrity.

[0946] Step 5:

[0947] The server preprocesses the user data stored in the database, including filling in missing values, correcting outliers, and normalizing the data (unifying different units and formats).

[0948] Step 6:

[0949] The server passes the preprocessed data to the generation AI, which then performs analysis based on user data and market data.

[0950] Step 7:

[0951] Generative AI generates mortgage options that best suit the user's attributes and financial situation, comparing interest rates and adjusting repayment periods based on mortgage products in market data.

[0952] Step 8:

[0953] The server formats the loan options returned by the generation AI into a user-friendly format, specifically, making loan interest rates, repayment periods, monthly payments, etc., visually easy to understand using tables and graphs.

[0954] Step 9:

[0955] The server sends the formatted loan option to the terminal.

[0956] Step 10:

[0957] The terminal displays the loan options received from the server to the user, who can then confirm the proposed loan terms.

[0958] Step 11:

[0959] The emotion engine analyzes the user's input data, click patterns, typing speed, etc. to determine the user's current emotional state. For example, if the user takes a long time to type, the emotion engine will determine that the user is feeling stressed.

[0960] Step 12:

[0961] The emotion engine identifies the user's emotional state and feeds it back to the generative AI to adjust the content and presentation of the suggestions. For example, if the user is feeling stressed, the suggestions will be made more concise.

[0962] Step 13:

[0963] The terminal then presents the user with customized loan options again, allowing them to make the best choice based on concise and easy-to-understand information.

[0964] Step 14:

[0965] If the user asks further questions about the suggestions or provides additional data, the terminal transmits the new data to the server again.

[0966] Step 15:

[0967] The server aggregates the newly received data and the results of the emotion engine's analysis of the emotional state, and then reanalyzes it with the generative AI, which then generates a new loan proposal.

[0968] Step 16:

[0969] The server then formats the reparsed loan options into a user-friendly format and sends it to the terminal, where the user can review the new offers.

[0970] These steps allow users to easily and efficiently find the best mortgage option that suits their needs.

[0971] Example 2

[0972] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0973] Conventional mortgage option proposal systems have difficulty making optimal proposals based on a user's individual attributes and financial situation, and are unable to make proposals that take into account the user's emotional state. This causes users to feel a great deal of stress when selecting the optimal loan option. Furthermore, it is difficult to quickly reanalyze the system when the entered user data is inaccurate or when market data is updated.

[0974] The specification processing by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input their own attributes and household financial situation; means for transmitting the input user data to an information processing device; means for the information processing device to receive the user data and store it in a storage medium; means for the information processing device to preprocess the stored user data; means for a machine learning model to match the preprocessed user data with market data and generate optimal mortgage options; means for the information processing device to transmit the generated mortgage options to an output device; means for the output device to display the loan options to the user; and means for analyzing the user's emotional state using an emotion analysis engine and customizing the generated mortgage options based on the user's emotional state. As a result, the user is offered optimal mortgage options based on their attributes and household financial situation, and further receives personalized offers according to the user's emotional state, which makes the selection process easier and improves the user experience.

[0975] "User" refers to any individual or entity that utilizes this system to receive mortgage options.

[0976] "Attributes" refers to personal information such as a user's gender, age, place of employment, etc.

[0977] "Household finances" refers to economic information such as a user's financial assets, annual income, and expenses.

[0978] "Information processing device" refers to a device that receives, processes, and analyzes data sent by a user.

[0979] "Storage medium" refers to a data storage device used by an information processing device to store user data.

[0980] "Preprocessing" refers to performing processes such as missing value completion, outlier correction, and normalization on user data.

[0981] "Machine learning model" refers to an algorithm that uses pre-processed data and market data to generate optimal mortgage options.

[0982] "Market data" refers to external data such as interest rates and property prices, including information used by machine learning models.

[0983] "Output device" refers to a device for displaying generated mortgage options to a user.

[0984] An "emotion analysis engine" refers to algorithms or software for analyzing a user's emotional state.

[0985] The present invention relates to a system that automatically generates and proposes optimal mortgage options based on a user's input of their attributes and financial situation. This system achieves more personalized proposals by incorporating an emotion engine that recognizes the user's emotions. Specific embodiments are described below.

[0986] First, the user uses a device to access a web form or a dedicated app and enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.). This input is done through an intuitive user interface created with React.js or Vue.js. For example, it is expected that the user will enter "annual income of 6 million yen," "self-funding of 3 million yen," and "property price of 40 million yen."

[0987] The device then sends the entered data to the server via a REST API. The server receives the data using Node.js or Express.js and uses the validation framework Joi.js to verify that the input format is correct. For example, it checks that the "annual income" field is in numeric format.

[0988] The server validates the received data, formats it, and then stores it in a database, typically using MongoDB or PostgreSQL. After storing the data, the server preprocesses it using Python scripts and Pandas. This preprocessing includes imputing missing values, correcting outliers, and normalizing the data.

[0989] Once the preprocessing is complete, the data is input into a generative AI model. Machine learning frameworks such as TensorFlow and PyTorch are used for the generative AI model. The prompt for the generative AI model is in the following format: "The user's annual income is 6 million yen, their own funds are 3 million yen, and the property price is 40 million yen. Please suggest the best mortgage option."

[0990] The server receives the optimal mortgage option output by the generative AI model and formats it into a user-friendly format using a template engine (e.g., EJS, Handlebars). The formatted loan option is then sent back to the terminal and presented to the user. At this time, the terminal displays a user-friendly message such as "Fixed interest rate of 2.0%, monthly repayment plan of 100,000 yen."

[0991] Furthermore, the present invention incorporates an emotion engine to identify the user's emotional state, and the generative AI model customizes the suggestions based on this. The emotion engine analyzes input speed, click patterns, dwell time, etc. to determine whether the user is stressed or relaxed. For example, if the user is feeling anxious, the suggestions will be more concise and easy to understand.

[0992] As a concrete example, if a first-time home buyer enters "annual income of 6 million yen, personal funds of 3 million yen, property price of 40 million yen, 35-year-old male," the emotion engine will determine from the keystroke pattern and typing speed that the user is feeling somewhat anxious. The generative AI model will then create a reasonable repayment plan and propose a mortgage with a fixed interest rate of 2.0%. The proposal is displayed in a specific and simple way: "Monthly repayments of 100,000 yen with a fixed interest rate of 2.0%."

[0993] The system allows users to easily select the loan option that best suits them without requiring specialized financial knowledge, and facilitates the selection process by receiving personalized suggestions based on their emotional state, improving the user experience and realizing an efficient loan selection process.

[0994] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0995] Step 1: The user enters their attributes and household financial situation

[0996] Users use their device to access a web form or a dedicated app and enter their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.).

[0997] Specific operation: The user opens a browser or app and enters information such as "annual income of 6 million yen," "personal funds of 3 million yen," and "property price of 40 million yen" into a form.

[0998] Input: User attributes and household financial situation data

[0999] Output: User data entered into the terminal

[1000] Step 2: Submit and verify data

[1001] The terminal sends the input data to the server via the REST API, and the server validates the received data using the validation framework.

[1002] What happens: The device sends data to the API endpoint, the server receives the data using Node.js and Express.js, and the server verifies the item format using Joi.js.

[1003] Input: User data sent from the terminal

[1004] Output: Verified user data

[1005] Step 3: Saving and formatting the data

[1006] The server stores the validated data in a database and reformats the data as needed.

[1007] Specific operation: The server stores the data in MongoDB or PostgreSQL and cleans it to unify the data format.

[1008] Input: Validated user data

[1009] Output: Formatted user data stored in the database

[1010] Step 4: Preprocessing the data

[1011] The server retrieves the data from the database and pre-processes it.

[1012] What it does: The server uses Python scripts and Pandas to impute missing values ​​in the data, correct outliers, and normalize the data.

[1013] Input: Preformatted user data stored in the database

[1014] Output: Preprocessed user data

[1015] Step 5: Input to the generative AI model

[1016] The server inputs the preprocessed data into the generative AI model.

[1017] Specific operation: The server uses a Python script to input preprocessed data into a generative AI model built with TensorFlow and PyTorch. The prompt statement is, "The user's annual income is 6 million yen, their own funds are 3 million yen, and the property price is 40 million yen. Please suggest the best mortgage option."

[1018] Input: Preprocessed user data

[1019] Output: Optimal mortgage options from a generative AI model

[1020] Step 6: Format and submit your loan option

[1021] The server formats the optimal mortgage options output by the generative AI model and sends them to the terminal.

[1022] Specific operation: The server uses a template engine (EJS, Handlebars) to format the data into a user-friendly format, and then sends the formatted data to the device.

[1023] Input: Loan option data output by the generative AI model

[1024] Output: Formatted loan option data

[1025] Step 7: View loan options

[1026] The terminal displays the loan options received from the server to the user.

[1027] Specific operation: The device displays information such as "Fixed interest rate 2.0%, monthly repayment plan of 100,000 yen" on a web page or app.

[1028] Input: Formatted loan option data

[1029] Output: Loan options displayed to the user

[1030] Step 8: Applying the Sentiment Analysis Engine

[1031] The server uses an emotion analysis engine to analyze the user's emotional state and provides feedback to the generative AI model.

[1032] How it works: The server analyzes the user's typing speed and click patterns to determine their state of stress or relaxation. The analysis results are fed back to the generative AI model to customize the suggestions.

[1033] Input: User input data and usage patterns

[1034] Output: Customized loan options based on the user's emotional state

[1035] (Application example 2)

[1036] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1037] In today's world, it is not easy for consumers to find the best products and services for them from the vast amount of information available. Furthermore, consumers often require different recommendations depending on their emotional state. Furthermore, there is a demand for systems that allow them to receive personalized recommendations regardless of time or location.

[1038] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1039] In this invention, the server includes: means for a user to input their attributes and household financial situation; means for transmitting the input user data to the server; means for the server to receive the user data and store it in a database; means for the server to preprocess the stored user data; means for a generation AI to match the preprocessed user data with market data and generate optimal mortgage options; means for the server to transmit the generated mortgage options to a terminal; means for the terminal to display the loan options to the user; and means for using a smart device in a physical store to analyze the user's attributes and emotional state and suggest optimal products and services based on the results. This allows users to easily find the products and services that are best suited to them and also allows them to receive personalized suggestions based on their emotional state.

[1040] "User attributes" is a general term for personal information such as a user's age, gender, occupation, purchasing history, etc.

[1041] "Finance situation" refers to a user's financial assets, annual income, expenses and other financial information.

[1042] A "server" is a computer system that receives, stores, and processes data sent by users.

[1043] A "database" is a structured collection of data for storing collected user data.

[1044] "Preprocessing" refers to cleaning and standardizing the format of data before analyzing it, such as imputing missing values ​​and normalizing data.

[1045] "Generative AI" refers to technology that uses artificial intelligence models to generate optimal recommendations based on user and market data.

[1046] "Smart devices" refers to devices such as smartphones and smart glasses that have internet connectivity and can acquire and process data.

[1047] "Physical store" refers to a physical sales or service location.

[1048] "Emotional state" refers to the user's current psychological state, including the degree of stress or relaxation.

[1049] "Suggestion" refers to a recommendation or option offered to a user.

[1050] This system uses smart devices in a brick-and-mortar store to analyze a user's attributes and emotional state to suggest optimal products and services. The system consists of a user, a server, a smart device, and a terminal.

[1051] First, the user puts on a smart device such as smart glasses in a physical store. The camera and sensors installed in the smart device recognize the user's face and collect data in real time. This allows the user's attributes (age, gender, occupation, purchasing history, etc.) and emotional state (stress, relaxation, etc.) to be analyzed.

[1052] The collected data is sent to a server, which stores the received data in a database and performs preprocessing. Preprocessing includes cleaning the data, standardizing the format, and filling in missing values. The preprocessed data is then input into the generative AI.

[1053] Generative AI uses user and market data to suggest optimal products and services. For example, if a user is feeling stressed, it might suggest relaxation products or books. On the other hand, if a user is feeling relaxed, it might suggest the latest electronics or sports equipment.

[1054] The generated proposals are sent via the server to the smart device, which then displays the proposals in a user-friendly format, including product or service descriptions, prices, sales information, coupons, etc.

[1055] As a concrete example of this system, the following prompt sentence is input to the generation AI:

[1056] Example prompt for a generative AI model:

[1057] User ID_001 (male, 35 years old) has purchased electrical appliances and sports equipment in the past. Currently, the user is feeling stressed, so we recommend relaxation products and books. Please display the suggestions in a user-friendly format.

[1058] This system allows users to enjoy shopping in brick-and-mortar stores in an efficient and personalized way. The suggestions are dynamically adjusted according to the user's emotional state, so the system always provides the most suitable products and services for the user.

[1059] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1060] Step 1:

[1061] A user puts on the smart glasses.

[1062] Input: Putting on smart glasses, activating cameras and sensors.

[1063] How it works: When a user enters a physical store and puts on the smart glasses, the smart glasses' camera and sensors are activated, allowing the smart device to detect the user's face and begin collecting data in real time.

[1064] Step 2:

[1065] The smart device recognizes the user's face and analyzes their attributes and emotional state.

[1066] Input: Facial image data and other sensor data.

[1067] Output: User demographics and emotional state data.

[1068] How it works: Using facial image data captured by the camera and biometric data from sensors, the system runs a facial recognition algorithm and emotion recognition model to identify the user's demographic information, such as age, gender, and past purchase history, as well as their current emotional state (such as stress level).

[1069] Step 3:

[1070] The smart device sends the acquired data to the server.

[1071] Input: User demographic information and emotional state data.

[1072] Output: User data sent to the server.

[1073] Specific operation: The smart glasses collect user attribute information and emotional state data and send it to the server. The data is encrypted and transmitted securely.

[1074] Step 4:

[1075] The server stores the received data in a database and performs preprocessing.

[1076] Input: The retrieved user data.

[1077] Output: Preprocessed user data.

[1078] Specific operation: The server first stores the received data in a database, then performs preprocessing such as filling in missing values, correcting outliers, and normalizing the data. The preprocessed data is then formatted into a format suitable for analysis.

[1079] Step 5:

[1080] Based on the pre-processed data, generative AI suggests optimal products and services.

[1081] Input: Preprocessed user and market data.

[1082] Output: Recommendations for the best products and services.

[1083] Specific operation: Preprocessed user data and market data are input into the Generative AI, which then runs the algorithm to generate the best products and services for the user. Specifically, if the user is feeling stressed, it will suggest relaxation products, and if they are feeling relaxed, it will suggest the latest electronic appliances.

[1084] Step 6:

[1085] The server sends the generated proposal to the smart device.

[1086] Input: Generated product or service proposals.

[1087] Output: Proposal data sent to smart device.

[1088] How it works: The server receives the proposed data from the generative AI model, converts it into a user-friendly format, and then securely transmits it to the smart glasses.

[1089] Step 7:

[1090] The smart device displays the suggestions to the user.

[1091] Input: Proposal data sent by the server.

[1092] Output: The suggested products or services displayed to the user.

[1093] How it works: The smart glasses display information about suggested products and services on the screen, including product descriptions, prices, sales information, coupons, etc. This information allows users to efficiently select products in the store.

[1094] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1095] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1096] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1097] [Fourth embodiment]

[1098] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1099] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1100] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1101] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1102] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1103] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1104] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1105] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1106] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1107] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1108] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1109] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1110] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1111] The present invention relates to a system that automatically generates and proposes optimal housing loan options based on a user's input of their attributes and financial situation. The present invention is implemented in accordance with the following steps.

[1112] First, the user uses a device to access a web form or a dedicated app and enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.). This data is designed to be easily entered by the user, and the form has an intuitive, easy-to-understand interface.

[1113] The entered data is sent from the terminal to the server. The server verifies the received user data, performs any necessary formatting (standardizing the format and detecting and correcting outliers), and then stores it in the database. This process ensures the consistency and accuracy of the data.

[1114] The server then preprocesses the stored user data, which includes data cleaning (inserting missing values ​​and removing duplicate data), normalization (unifying different units and formats), and feature engineering (converting data into a format suitable for the model).

[1115] Once preprocessing is complete, the user data is input into the generation AI, which analyzes the user data and market data to generate mortgage options that best suit the user's attributes and financial situation. The market data includes the latest mortgage products, interest rates, repayment terms, and more, and the AI ​​comprehensively evaluates these.

[1116] The generated mortgage options are then formatted into a user-friendly format by the server and sent back to the terminal, where the user can view the proposed loan options. Specifically, the loan interest rate, repayment period, monthly payment amount, etc. are displayed in a visually understandable manner.

[1117] If the user has further questions or provides additional data based on the information provided, the device will send it back to the server, which will then receive the new information, reanalyze it, and generate a new, optimized loan proposal. This ensures that the user always has the best loan options based on the latest information.

[1118] Specific examples

[1119] Example 1: First-time home buyer

[1120] The user enters "annual income of 6 million yen, personal funds of 3 million yen, property value of 40 million yen, male, 35 years old." The device sends this information to the server, which stores the data in a database. The generating AI then analyzes the user data and market data, creates a reasonable repayment plan, and proposes a mortgage with a fixed interest rate of 2.0%. The device displays to the user, "Monthly repayment of 100,000 yen with a fixed interest rate of 2.0%."

[1121] Example 2: User considering refinancing

[1122] The user inputs "current balance of 20 million yen, variable interest rate of 2.5%, annual income of 8 million yen, 40-year-old female." The terminal again sends the new information to the server, which analyzes it using the generation AI. As a result, a proposal is generated that "refinancing to a loan with a fixed interest rate of 1.8% is possible," and the terminal notifies the user.

[1123] Through these steps, the system of the present invention allows users to select a home loan easily and efficiently, and provides optimal loan options.

[1124] The processing flow will be explained below.

[1125] Step 1:

[1126] The user enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.) into a dedicated web form or app on their device.

[1127] Step 2:

[1128] The terminal collects the user's input data and sends the data to the server according to a standard format.

[1129] Step 3:

[1130] The server receives the user data sent from the terminal and first verifies the format and validity of the data, for example, whether all required data fields are filled in and whether the numeric format is appropriate.

[1131] Step 4:

[1132] The server stores the verified data in the database, performing transaction processing to maintain data consistency and integrity.

[1133] Step 5:

[1134] The server preprocesses the user data stored in the database, including missing value imputation, outlier detection and correction, and data normalization.

[1135] Step 6:

[1136] The server passes the preprocessed data to the generation AI, which performs analysis based on user data and market data.

[1137] Step 7:

[1138] The AI ​​generates mortgage options that best suit the user's attributes and financial situation, comparing interest rates and adjusting repayment periods based on mortgage products in market data.

[1139] Step 8:

[1140] The server formats the loan options returned by the generation AI into a user-friendly format, specifically, making loan interest rates, repayment periods, monthly payments, etc., visually easy to understand using tables and graphs.

[1141] Step 9:

[1142] The server sends the formatted loan option to the terminal.

[1143] Step 10:

[1144] The terminal displays the loan options received from the server to the user, who can then confirm the proposed loan terms.

[1145] Step 11:

[1146] If the user has the option to ask further questions or provide additional data about the proposed loan option, the terminal will again transmit this new data to the server.

[1147] Step 12:

[1148] The server re-analyzes the newly received data and invokes the generation AI to generate new loan proposals, ensuring that users are always provided with the best loan options based on the latest information.

[1149] Example 1

[1150] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1151] In conventional mortgage selection systems, even after users input their attributes and financial situation, it takes a long time to provide appropriate loan options, and the information provided to users is often insufficient. Furthermore, there is no mechanism to automatically regenerate consistent and appropriate loan proposals every time a user inputs new information. This makes it difficult for users to find the mortgage option that best suits them, and makes it difficult for them to make efficient decisions.

[1152] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1153] In this invention, the server includes means for receiving user data, checking the data format, detecting and correcting outliers, and storing the data in a database; means for preprocessing the stored user data, completing missing values, deleting duplicate data, and normalizing the data; and means for a generation AI to match the preprocessed user data with market data and generate optimal mortgage options. This allows users to efficiently and accurately find optimal mortgage options. Furthermore, even if the user enters new information, the system automatically reanalyzes the data and provides optimal loan options based on the latest information.

[1154] A "user" is someone who uses the system to input their attributes and financial situation to find the best mortgage option for them.

[1155] A "terminal" is a device used by a user to input information, and includes a PC, a smartphone, a tablet, and the like.

[1156] "Server" refers to a computer system that receives, processes, stores, and analyzes data sent by users.

[1157] "Attributes" refers to basic information that identifies an individual, such as a user's gender, age, place of employment, etc.

[1158] "Finance" refers to information about a user's financial assets, annual income, expenses, and other economic circumstances.

[1159] "Database" refers to an information management system that stores received user data and retrieves and uses it when necessary.

[1160] "Preprocessing" refers to checking the format of the received data, detecting and correcting outliers, filling in missing values, deleting duplicate data, normalizing data, and other processes to prepare the data in a format suitable for analysis.

[1161] "Generative AI" refers to an artificial intelligence model that analyzes data provided by users and market data to automatically generate optimal mortgage options.

[1162] "Market Data" refers to information about the mortgage market, including the latest mortgage products, interest rate information, and repayment terms.

[1163] A "prompt sentence" is a sentence that specifically describes instructions or questions for the generation AI, and refers to the input sentence that the AI ​​analyzes based on this and generates a result.

[1164] "Loan options" are the optimal mortgage options suggested by the generative AI based on the user's attributes and financial situation, and specifically include interest rates, repayment periods, and monthly payments.

[1165] The present invention relates to a system that automatically generates and proposes optimal mortgage options based on a user's input of their attributes and financial situation. This system is implemented using a server, a terminal, and a generative AI model.

[1166] Users access web forms or dedicated applications using devices (PCs, smartphones, tablets, etc.) and enter their personal attributes (gender, age, place of employment, etc.) and household financial situation (financial assets, annual income, etc.). This data is provided through an interface designed to allow users to enter it easily.

[1167] The entered data is sent from the terminal to the server, which checks the data format (e.g., JSON or XML format), detects and corrects outliers, and then stores the data in a database (e.g., a relational database such as MySQL or PostgreSQL).

[1168] The server preprocesses the user data stored in the database. This preprocessing includes missing value imputation, duplicate data removal, normalization for different units and formats, and feature engineering. Specifically, the server can use the Python Pandas library to manipulate data frames and perform these preprocessing operations.

[1169] Once the preprocessing is complete, the data is fed into a generative AI model (e.g., GPT-3 or another generative model) that analyzes the data based on a prompt and generates mortgage options that best fit the user's attributes and financial situation. The prompt has the following format:

[1170] User attributes: Age 35, Gender: Male, Workplace: Corporate, Annual income: 6 million yen. Household finances: Personal funds: 3 million yen, Property price: 40 million yen. Please suggest the best mortgage option.

[1171] The generated loan options are formatted in a user-friendly format by the server and sent to the terminal, which then visually displays the interest rate, repayment period, and monthly payment amount of the received loan options to the user.

[1172] For example, if a user enters "annual income of 6 million yen, personal funds of 3 million yen, property value of 40 million yen, 35-year-old male," the device sends this information to the server. The server verifies the data and stores it in a database. The generating AI then analyzes the user data and market data to propose a mortgage with a fixed interest rate of 2.0% as a reasonable repayment plan. This information is sent to the device and displayed as "monthly repayments of 100,000 yen with a fixed interest rate of 2.0%."

[1173] If the user enters new or additional information, the device sends that data back to the server, which then receives the new information, analyzes it again using the generative AI model, and generates a new, optimized loan proposal. This ensures that the user always has the most up-to-date information and the best loan options.

[1174] In this way, the system of the present invention allows users to select home loans efficiently and accurately.

[1175] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1176] Step 1:

[1177] User Data Entry

[1178] Users use their devices to access web forms or dedicated applications and enter their personal attributes (gender, age, place of employment, etc.) and household financial situation (financial assets, annual income, etc.). The data entered is designed to be easily entered into the device's form.

[1179] Input: Demographic and financial information entered by the user into the form.

[1180] Output: User data stored on the device in JSON or XML format.

[1181] Specific behavior: The user manually enters the required information into fields in a browser or application and presses the "Submit" button.

[1182] Step 2:

[1183] Data submission and validation

[1184] The terminal sends the entered data to the server. The data is encrypted before being sent, ensuring security.

[1185] Server operation: The server validates the data it receives. It checks the data format and required fields, and returns an error message if there are any errors.

[1186] Input: User data sent from the device in JSON or XML format.

[1187] Output: Validated and formatted user data.

[1188] Specific operation: A POST request is sent to the endpoint, and on the server side, the request is received by Flask or Django and the format is checked.

[1189] Step 3:

[1190] Data Formatting and Storage

[1191] The server formats the received data, standardizes the format, detects and corrects outliers, and then stores it in a database.

[1192] Input: Validated and formatted user data.

[1193] Output: Dataset stored in a database.

[1194] Specific operation: Use Pandas to format the data, correct outliers, and then insert it into a relational database using an ORM such as SQLAlchemy.

[1195] Step 4:

[1196] Preprocessing user data

[1197] The server preprocesses the user data stored in the database, including imputing missing values, removing duplicate data, normalizing for different units and formats, and feature engineering.

[1198] Input: Datasets stored in a database.

[1199] Output: A preprocessed and clean dataset.

[1200] Specific behavior: Manipulates data frames using the Pandas library, imputes missing values ​​with the mean, removes duplicates, and standardizes units.

[1201] Step 5:

[1202] Generative AI-powered loan option generation

[1203] The preprocessed data is fed into a generative AI model (such as GPT-3), which analyzes the prompt text and generates mortgage options that best fit the user's attributes and financial situation.

[1204] Input: A preprocessed, clean dataset, and a prompt statement.

[1205] Output: The generated mortgage options.

[1206] What it does: It feeds data into a trained GPT-3 model and gives it instructions using specific prompts (e.g., "What are the best loan options for a 35-year-old male with an annual income of $60,000?").

[1207] Step 6:

[1208] Formatting and displaying results

[1209] The server formats the generated loan options into a user-friendly format and sends them to the terminal.

[1210] Input: Generated mortgage options.

[1211] Output: Loan options formatted in a user-friendly format.

[1212] Specific operation: Displays the loan interest rate, repayment period, and monthly payment amount in a visually easy-to-understand manner using HTML and CSS.

[1213] Step 7:

[1214] Re-analysis (if necessary)

[1215] If the user enters new or additional information, the device sends the data back to the server, which receives the new information, re-analyzes it, and generates a new, optimized loan offer.

[1216] Input: New user data.

[1217] Output: The new reparsed mortgage options.

[1218] Specific behavior: A new prompt is generated and fed back into the generative AI model to generate loan options based on the latest information.

[1219] Through these steps, the system is able to provide efficient and accurate mortgage options to users.

[1220] (Application example 1)

[1221] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1222] Conventional mortgage loan selection systems lack the functionality to allow users to intuitively input data and quickly suggest optimal loan options. They also lack the functionality to re-suggest the latest loan options based on the user's further questions or additional information. This makes it difficult for users to easily find the optimal mortgage option. The present invention aims to solve these problems and provide a mortgage loan selection system that users can easily use.

[1223] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1224] In this invention, the server includes: means for a user to input his or her attributes and household financial situation; means for transmitting the input user data to the server; means for the server to receive the user data and store it in a database; means for the server to preprocess the stored user data; means for a generation AI to match the preprocessed user data with market data and generate optimal mortgage options; means for the server to transmit the generated mortgage options to a terminal; means for the terminal to visually display the loan options to the user in an easy-to-understand manner; means for the user to answer further questions or provide additional information; and means for the server to receive new information from the user, reanalyze, and generate new optimized loan proposals. This allows users to easily obtain optimal loan options based on the latest information at all times.

[1225] 1. "User" refers to an individual who uses the system to enter their own attributes and household financial situation.

[1226] 2. "Attributes" refers to personal information about a user, such as gender, age, place of employment, etc.

[1227] 3. "Household financial situation" refers to information about the user's financial situation, such as financial assets, annual income, property price, personal funds, and desired repayment period.

[1228] 4. "Server" refers to the equipment or platform for receiving user data, storing it in a database, and pre-processing it.

[1229] 5. "Database" means a collection of information for formatting and securely storing received User Data.

[1230] 6. "Preprocessing" refers to the process of converting received data into a form suitable for analysis by cleaning, normalizing, feature engineering, etc.

[1231] 7. “Generative AI” refers to an artificial intelligence model that analyzes user and market data to generate optimal mortgage options.

[1232] 8. "Market Data" refers to data including the latest mortgage products, interest rate information, and repayment terms.

[1233] 9. "Mortgage Options" refers to the optimal mortgage products and terms generated based on the user's attributes and financial situation.

[1234] 10. "Terminal" means the device (such as a smartphone or tablet) through which a User enters their data and views the generated mortgage options.

[1235] 11. "Visually easy to understand" means that the proposed mortgage options are visually presented on the terminal in a way that allows the user to intuitively understand them.

[1236] 12. "Answering a question or providing additional information" means that the user enters new data or further details into the system.

[1237] 13. "Reanalysis" refers to the process of conducting a new analysis based on new information provided by the user to generate new mortgage options.

[1238] 14. "Loan Option Rate" means the interest rate terms on a mortgage loan.

[1239] 15. "Repayment period" refers to the period until the total principal and interest of a mortgage is paid off.

[1240] 16. "Monthly payment" refers to the amount paid each month to repay a mortgage.

[1241] This invention relates to a system that allows users to input their attributes and financial situation and proposes optimal mortgage options. Since the main functions of this invention are a server, a terminal, and a generative AI model, specific embodiments of these are described below.

[1242] First, the user uses a terminal to input their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, property price, personal funds, desired repayment period, etc.). The terminal can be a smartphone or tablet, and provides an application designed to allow the user to input data intuitively. This data is then sent from the terminal to a server via the Internet.

[1243] When the server receives the data, it stores it in a database. A relational database such as MySQL or PostgreSQL is used for the database. The received data undergoes any necessary reformatting (standardizing the format and detecting and correcting outliers). For example, numerical data such as annual income or financial assets is converted into consistent units.

[1244] Next, the server performs preprocessing, which includes data cleaning (inserting missing values ​​and removing duplicate data), normalization (standardizing different units and formats), and feature engineering (converting data into a format suitable for the model). Once preprocessing is complete, the data is input into the generative AI.

[1245] The generative AI is built using machine learning frameworks such as TensorFlow and PyTorch, and analyzes user data and market data. Market data includes the latest mortgage products, interest rates, repayment terms, etc. The generative AI comprehensively evaluates this data to generate mortgage options that best suit the user's attributes and financial situation.

[1246] The generated mortgage options are sent from the server to the terminal, which provides the user with a visually-friendly interface that displays the loan interest rate, repayment period, monthly payment amount, etc. The user can then make a selection based on this information.

[1247] Furthermore, if the user provides additional information or answers further questions, the information is sent back to the server, which then re-analyzes the new information and provides a new set of optimal loan options.

[1248] Specific examples

[1249] Example 1: First-time home buyer

[1250] When a user inputs "annual income of 6 million yen, personal funds of 3 million yen, property value of 40 million yen, 35-year-old male," the AI ​​generator will create a reasonable repayment plan and propose a mortgage with a fixed interest rate of 2.0%. The terminal will display "Monthly repayment of 100,000 yen with a fixed interest rate of 2.0%."

[1251] Example 2: A user considering refinancing

[1252] When a user inputs "current balance of 20 million yen, variable interest rate of 2.5%, annual income of 8 million yen, 40-year-old female," the AI ​​generates a suggestion that "refinancing is possible to a loan with a fixed interest rate of 1.8%," and the user is notified via their device.

[1253] Prompt Sentence Examples

[1254] "Gender: Male" "Age: 35" "Employer: ABC Co., Ltd." "Financial assets: 3 million yen" "Annual income: 6 million yen" "Property price: 40 million yen" "Own funds: 3 million yen" "Repayment period: 35 years"

[1255] By integrating these steps and elements, the present invention allows users to easily access the best mortgage options based on the most up-to-date information.

[1256] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1257] Step 1:

[1258] Users use the device to enter their attributes and household financial situation. This includes information such as gender, age, place of employment, financial assets, annual income, property price, personal funds, and desired repayment period. The entered data can be intuitively operated via a dedicated application on the device or a web form. The entered data is temporarily stored on the device and then sent to the server.

[1259] Input: User demographic information and household financial situation.

[1260] Output: User data sent to the server.

[1261] Step 2:

[1262] The server receives user data sent from the device and stores it in a database. A relational database such as MySQL or PostgreSQL is used for the database. The received data is first verified, and any formatting and any outliers are detected and corrected. At this stage, the consistency and accuracy of the data are guaranteed.

[1263] Input: User data sent from the device.

[1264] Output: Validated data stored in a database.

[1265] Step 3:

[1266] The server preprocesses the stored user data. Preprocessing includes data cleaning (inserting missing values ​​and removing duplicate data), data normalization (standardizing different units and formats), and feature engineering (converting data into a format suitable for the model). This prepares the data for input into the generative AI model.

[1267] Input: User data stored in the database.

[1268] Output: Preprocessed user data.

[1269] Step 4:

[1270] Based on the preprocessed user data, the server uses a generative AI model to match it with market data and generate optimal mortgage options. The generative AI model is built using machine learning frameworks such as TensorFlow and PyTorch. Market data includes the latest mortgage products, interest rates, repayment terms, etc., and comprehensively evaluates these to generate the optimal option for each user.

[1271] Input: Preprocessed user and market data.

[1272] Output: The generated mortgage options.

[1273] Step 5:

[1274] The server sends the generated mortgage options to the terminal, which provides the user with a visual interface that displays the loan interest rate, repayment period, monthly payment amount, etc. The user can review the options and proceed with their selection.

[1275] Input: The generated mortgage option.

[1276] Output: Loan options displayed on the terminal.

[1277] Step 6:

[1278] If the user answers further questions or provides additional information, the new information is sent via the device to the server, which receives this new information, reanalyzes it, and re-uses the generative AI model to generate new, optimized loan offers. The regenerated loan options are again sent to the device and displayed to the user.

[1279] Input: User data based on additional information or new questions.

[1280] Output: Regenerated loan options.

[1281] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1282] The present invention relates to a system that automatically generates and proposes optimal mortgage options based on the user's input of their attributes and financial situation. In particular, the present invention achieves more personalized proposals by incorporating an emotion engine that recognizes the user's emotions.

[1283] First, the user uses a device to access a web form or a dedicated app and enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.). This input data is collected using an interface designed to allow users to enter data easily.

[1284] The entered data is sent from the terminal to the server. The server verifies the received user data, formats it, and stores it in a database. At this time, the data is cleaned and formatted to maintain data integrity.

[1285] The server then preprocesses the data stored in the database, including filling in missing values, correcting outliers, and normalizing the data. Once preprocessed, the data is fed into a generative AI, which generates optimal mortgage options based on user and market data.

[1286] The generated mortgage options are then formatted into a user-friendly format by the server and sent to the terminal, which displays the proposed loan options to the user, including the loan interest rate, repayment period, and monthly payment amount.

[1287] A distinctive feature of the present invention is the inclusion of an emotion engine. The emotion engine analyzes the user's input data and daily usage patterns to identify the user's current emotional state. For example, by analyzing the user's input text, click patterns, and input speed, it determines whether the user is currently feeling stressed or relaxed.

[1288] Once the emotion engine identifies the user's emotional state, that information is fed back to the generative AI to customize the loan option recommendations and presentation. For example, if the user is stressed, they will receive more concise and easy-to-understand recommendations, while if they are relaxed, they will receive more detailed information.

[1289] Specific examples

[1290] Example 1: First-time home buyer

[1291] The user inputs "annual income of 6 million yen, personal funds of 3 million yen, property value of 40 million yen, 35-year-old male." The emotion engine analyzes input speed and keystroke patterns to determine that the user is feeling somewhat anxious. The generative AI then creates a reasonable repayment plan and proposes a mortgage with a fixed interest rate of 2.0%. The proposal is displayed concretely and simply: "Monthly repayments of 100,000 yen with a fixed interest rate of 2.0%."

[1292] Example 2: User considering refinancing

[1293] The user enters "current balance of 20 million yen, variable interest rate of 2.5%, annual income of 8 million yen, 40-year-old female." The emotion engine determines that the user is relaxed based on their click patterns and time spent on the site. The generation AI displays a proposal with detailed information, such as "refinancing to a fixed interest rate of 1.8% will save you 100,000 yen per year."

[1294] By implementing the present invention, users can easily select loan options that are best suited to them and that correspond to their emotional state without requiring specialized financial knowledge, thereby improving user satisfaction and realizing an efficient loan selection process.

[1295] The processing flow will be explained below.

[1296] Step 1:

[1297] The user enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.) into a dedicated web form or app on their device.

[1298] Step 2:

[1299] The terminal collects the user's input data and sends the data to the server according to a standard format.

[1300] Step 3:

[1301] The server receives the user data sent from the terminal and first verifies the format and validity of the data, for example, whether all required fields are filled in and whether the numeric format is appropriate.

[1302] Step 4:

[1303] The server stores the verified data in the database, performing transaction processing to ensure data consistency and integrity.

[1304] Step 5:

[1305] The server preprocesses the user data stored in the database, including filling in missing values, correcting outliers, and normalizing the data (unifying different units and formats).

[1306] Step 6:

[1307] The server passes the preprocessed data to the generation AI, which then performs analysis based on user data and market data.

[1308] Step 7:

[1309] Generative AI generates mortgage options that best suit the user's attributes and financial situation, comparing interest rates and adjusting repayment periods based on mortgage products in market data.

[1310] Step 8:

[1311] The server formats the loan options returned by the generation AI into a user-friendly format, specifically, making loan interest rates, repayment periods, monthly payments, etc., visually easy to understand using tables and graphs.

[1312] Step 9:

[1313] The server sends the formatted loan option to the terminal.

[1314] Step 10:

[1315] The terminal displays the loan options received from the server to the user, who can then confirm the proposed loan terms.

[1316] Step 11:

[1317] The emotion engine analyzes the user's input data, click patterns, typing speed, etc. to determine the user's current emotional state. For example, if the user takes a long time to type, the emotion engine will determine that the user is feeling stressed.

[1318] Step 12:

[1319] The emotion engine identifies the user's emotional state and feeds it back to the generative AI to adjust the content and presentation of the suggestions. For example, if the user is feeling stressed, the suggestions will be made more concise.

[1320] Step 13:

[1321] The terminal then presents the user with customized loan options again, allowing them to make the best choice based on concise and easy-to-understand information.

[1322] Step 14:

[1323] If the user asks further questions about the suggestions or provides additional data, the terminal transmits the new data to the server again.

[1324] Step 15:

[1325] The server aggregates the newly received data and the results of the emotion engine's analysis of the emotional state, and then reanalyzes it with the generative AI, which then generates a new loan proposal.

[1326] Step 16:

[1327] The server then formats the reparsed loan options into a user-friendly format and sends it to the terminal, where the user can review the new offers.

[1328] These steps allow users to easily and efficiently find the best mortgage option that suits their needs.

[1329] Example 2

[1330] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1331] Conventional mortgage option proposal systems have difficulty making optimal proposals based on a user's individual attributes and financial situation, and are unable to make proposals that take into account the user's emotional state. This causes users to feel a great deal of stress when selecting the optimal loan option. Furthermore, it is difficult to quickly reanalyze the system when the entered user data is inaccurate or when market data is updated.

[1332] The specification processing by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input their own attributes and household financial situation; means for transmitting the input user data to an information processing device; means for the information processing device to receive the user data and store it in a storage medium; means for the information processing device to preprocess the stored user data; means for a machine learning model to match the preprocessed user data with market data and generate optimal mortgage options; means for the information processing device to transmit the generated mortgage options to an output device; means for the output device to display the loan options to the user; and means for analyzing the user's emotional state using an emotion analysis engine and customizing the generated mortgage options based on the user's emotional state. As a result, the user is offered optimal mortgage options based on their attributes and household financial situation, and further receives personalized offers according to the user's emotional state, which makes the selection process easier and improves the user experience.

[1333] "User" refers to any individual or entity that utilizes this system to receive mortgage options.

[1334] "Attributes" refers to personal information such as a user's gender, age, place of employment, etc.

[1335] "Household finances" refers to economic information such as a user's financial assets, annual income, and expenses.

[1336] "Information processing device" refers to a device that receives, processes, and analyzes data sent by a user.

[1337] "Storage medium" refers to a data storage device used by an information processing device to store user data.

[1338] "Preprocessing" refers to performing processes such as missing value completion, outlier correction, and normalization on user data.

[1339] "Machine learning model" refers to an algorithm that uses pre-processed data and market data to generate optimal mortgage options.

[1340] "Market data" refers to external data such as interest rates and property prices, including information used by machine learning models.

[1341] "Output device" refers to a device for displaying generated mortgage options to a user.

[1342] An "emotion analysis engine" refers to algorithms or software for analyzing a user's emotional state.

[1343] The present invention relates to a system that automatically generates and proposes optimal mortgage options based on a user's input of their attributes and financial situation. This system achieves more personalized proposals by incorporating an emotion engine that recognizes the user's emotions. Specific embodiments are described below.

[1344] First, the user uses a device to access a web form or a dedicated app and enters their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.). This input is done through an intuitive user interface created with React.js or Vue.js. For example, it is expected that the user will enter "annual income of 6 million yen," "self-funding of 3 million yen," and "property price of 40 million yen."

[1345] The device then sends the entered data to the server via a REST API. The server receives the data using Node.js or Express.js and uses the validation framework Joi.js to verify that the input format is correct. For example, it checks that the "annual income" field is in numeric format.

[1346] The server validates the received data, formats it, and then stores it in a database, typically using MongoDB or PostgreSQL. After storing the data, the server preprocesses it using Python scripts and Pandas. This preprocessing includes imputing missing values, correcting outliers, and normalizing the data.

[1347] Once the preprocessing is complete, the data is input into a generative AI model. Machine learning frameworks such as TensorFlow and PyTorch are used for the generative AI model. The prompt for the generative AI model is in the following format: "The user's annual income is 6 million yen, their own funds are 3 million yen, and the property price is 40 million yen. Please suggest the best mortgage option."

[1348] The server receives the optimal mortgage option output by the generative AI model and formats it into a user-friendly format using a template engine (e.g., EJS, Handlebars). The formatted loan option is then sent back to the terminal and presented to the user. At this time, the terminal displays a user-friendly message such as "Fixed interest rate of 2.0%, monthly repayment plan of 100,000 yen."

[1349] Furthermore, the present invention incorporates an emotion engine to identify the user's emotional state, and the generative AI model customizes the suggestions based on this. The emotion engine analyzes input speed, click patterns, dwell time, etc. to determine whether the user is stressed or relaxed. For example, if the user is feeling anxious, the suggestions will be more concise and easy to understand.

[1350] As a concrete example, if a first-time home buyer enters "annual income of 6 million yen, personal funds of 3 million yen, property price of 40 million yen, 35-year-old male," the emotion engine will determine from the keystroke pattern and typing speed that the user is feeling somewhat anxious. The generative AI model will then create a reasonable repayment plan and propose a mortgage with a fixed interest rate of 2.0%. The proposal is displayed in a specific and simple way: "Monthly repayments of 100,000 yen with a fixed interest rate of 2.0%."

[1351] The system allows users to easily select the loan option that best suits them without requiring specialized financial knowledge, and facilitates the selection process by receiving personalized suggestions based on their emotional state, improving the user experience and realizing an efficient loan selection process.

[1352] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1353] Step 1: The user enters their attributes and household financial situation

[1354] Users use their device to access a web form or a dedicated app and enter their attributes (gender, age, place of employment, etc.) and household situation (financial assets, annual income, etc.).

[1355] Specific operation: The user opens a browser or app and enters information such as "annual income of 6 million yen," "personal funds of 3 million yen," and "property price of 40 million yen" into a form.

[1356] Input: User attributes and household financial situation data

[1357] Output: User data entered into the terminal

[1358] Step 2: Submit and verify data

[1359] The terminal sends the input data to the server via the REST API, and the server validates the received data using the validation framework.

[1360] What happens: The device sends data to the API endpoint, the server receives the data using Node.js and Express.js, and the server verifies the item format using Joi.js.

[1361] Input: User data sent from the terminal

[1362] Output: Verified user data

[1363] Step 3: Saving and formatting the data

[1364] The server stores the validated data in a database and reformats the data as needed.

[1365] Specific operation: The server stores the data in MongoDB or PostgreSQL and cleans it to unify the data format.

[1366] Input: Validated user data

[1367] Output: Formatted user data stored in the database

[1368] Step 4: Preprocessing the data

[1369] The server retrieves the data from the database and pre-processes it.

[1370] What it does: The server uses Python scripts and Pandas to impute missing values ​​in the data, correct outliers, and normalize the data.

[1371] Input: Preformatted user data stored in the database

[1372] Output: Preprocessed user data

[1373] Step 5: Input to the generative AI model

[1374] The server inputs the preprocessed data into the generative AI model.

[1375] Specific operation: The server uses a Python script to input preprocessed data into a generative AI model built with TensorFlow and PyTorch. The prompt statement is, "The user's annual income is 6 million yen, their own funds are 3 million yen, and the property price is 40 million yen. Please suggest the best mortgage option."

[1376] Input: Preprocessed user data

[1377] Output: Optimal mortgage options from a generative AI model

[1378] Step 6: Format and submit your loan option

[1379] The server formats the optimal mortgage options output by the generative AI model and sends them to the terminal.

[1380] Specific operation: The server uses a template engine (EJS, Handlebars) to format the data into a user-friendly format, and then sends the formatted data to the device.

[1381] Input: Loan option data output by the generative AI model

[1382] Output: Formatted loan option data

[1383] Step 7: View loan options

[1384] The terminal displays the loan options received from the server to the user.

[1385] Specific operation: The device displays information such as "Fixed interest rate 2.0%, monthly repayment plan of 100,000 yen" on a web page or app.

[1386] Input: Formatted loan option data

[1387] Output: Loan options displayed to the user

[1388] Step 8: Applying the Sentiment Analysis Engine

[1389] The server uses an emotion analysis engine to analyze the user's emotional state and provides feedback to the generative AI model.

[1390] How it works: The server analyzes the user's typing speed and click patterns to determine their state of stress or relaxation. The analysis results are fed back to the generative AI model to customize the suggestions.

[1391] Input: User input data and usage patterns

[1392] Output: Customized loan options based on the user's emotional state

[1393] (Application example 2)

[1394] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1395] In today's world, it is not easy for consumers to find the best products and services for them from the vast amount of information available. Furthermore, consumers often require different recommendations depending on their emotional state. Furthermore, there is a demand for systems that allow them to receive personalized recommendations regardless of time or location.

[1396] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1397] In this invention, the server includes: means for a user to input their attributes and household financial situation; means for transmitting the input user data to the server; means for the server to receive the user data and store it in a database; means for the server to preprocess the stored user data; means for a generation AI to match the preprocessed user data with market data and generate optimal mortgage options; means for the server to transmit the generated mortgage options to a terminal; means for the terminal to display the loan options to the user; and means for using a smart device in a physical store to analyze the user's attributes and emotional state and suggest optimal products and services based on the results. This allows users to easily find the products and services that are best suited to them and also allows them to receive personalized suggestions based on their emotional state.

[1398] "User attributes" is a general term for personal information such as a user's age, gender, occupation, purchasing history, etc.

[1399] "Finance situation" refers to a user's financial assets, annual income, expenses and other financial information.

[1400] A "server" is a computer system that receives, stores, and processes data sent by users.

[1401] A "database" is a structured collection of data for storing collected user data.

[1402] "Preprocessing" refers to cleaning and standardizing the format of data before analyzing it, such as imputing missing values ​​and normalizing data.

[1403] "Generative AI" refers to technology that uses artificial intelligence models to generate optimal recommendations based on user and market data.

[1404] "Smart devices" refers to devices such as smartphones and smart glasses that have internet connectivity and can acquire and process data.

[1405] "Physical store" refers to a physical sales or service location.

[1406] "Emotional state" refers to the user's current psychological state, including the degree of stress or relaxation.

[1407] "Suggestion" refers to a recommendation or option offered to a user.

[1408] This system uses smart devices in a brick-and-mortar store to analyze a user's attributes and emotional state to suggest optimal products and services. The system consists of a user, a server, a smart device, and a terminal.

[1409] First, the user puts on a smart device such as smart glasses in a physical store. The camera and sensors installed in the smart device recognize the user's face and collect data in real time. This allows the user's attributes (age, gender, occupation, purchasing history, etc.) and emotional state (stress, relaxation, etc.) to be analyzed.

[1410] The collected data is sent to a server, which stores the received data in a database and performs preprocessing. Preprocessing includes cleaning the data, standardizing the format, and filling in missing values. The preprocessed data is then input into the generative AI.

[1411] Generative AI uses user and market data to suggest optimal products and services. For example, if a user is feeling stressed, it might suggest relaxation products or books. On the other hand, if a user is feeling relaxed, it might suggest the latest electronics or sports equipment.

[1412] The generated proposals are sent via the server to the smart device, which then displays the proposals in a user-friendly format, including product or service descriptions, prices, sales information, coupons, etc.

[1413] As a concrete example of this system, the following prompt sentence is input to the generation AI:

[1414] Example prompt for a generative AI model:

[1415] User ID_001 (male, 35 years old) has purchased electrical appliances and sports equipment in the past. Currently, the user is feeling stressed, so we recommend relaxation products and books. Please display the suggestions in a user-friendly format.

[1416] This system allows users to enjoy shopping in brick-and-mortar stores in an efficient and personalized way. The suggestions are dynamically adjusted according to the user's emotional state, so the system always provides the most suitable products and services for the user.

[1417] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1418] Step 1:

[1419] A user puts on the smart glasses.

[1420] Input: Putting on smart glasses, activating cameras and sensors.

[1421] How it works: When a user enters a physical store and puts on the smart glasses, the smart glasses' camera and sensors are activated, allowing the smart device to detect the user's face and begin collecting data in real time.

[1422] Step 2:

[1423] The smart device recognizes the user's face and analyzes their attributes and emotional state.

[1424] Input: Facial image data and other sensor data.

[1425] Output: User demographics and emotional state data.

[1426] How it works: Using facial image data captured by the camera and biometric data from sensors, the system runs a facial recognition algorithm and emotion recognition model to identify the user's demographic information, such as age, gender, and past purchase history, as well as their current emotional state (such as stress level).

[1427] Step 3:

[1428] The smart device sends the acquired data to the server.

[1429] Input: User demographic information and emotional state data.

[1430] Output: User data sent to the server.

[1431] Specific operation: The smart glasses collect user attribute information and emotional state data and send it to the server. The data is encrypted and transmitted securely.

[1432] Step 4:

[1433] The server stores the received data in a database and performs preprocessing.

[1434] Input: The retrieved user data.

[1435] Output: Preprocessed user data.

[1436] Specific operation: The server first stores the received data in a database, then performs preprocessing such as filling in missing values, correcting outliers, and normalizing the data. The preprocessed data is then formatted into a format suitable for analysis.

[1437] Step 5:

[1438] Based on the pre-processed data, generative AI suggests optimal products and services.

[1439] Input: Preprocessed user and market data.

[1440] Output: Recommendations for the best products and services.

[1441] Specific operation: Preprocessed user data and market data are input into the Generative AI, which then runs the algorithm to generate the best products and services for the user. Specifically, if the user is feeling stressed, it will suggest relaxation products, and if they are feeling relaxed, it will suggest the latest electronic appliances.

[1442] Step 6:

[1443] The server sends the generated proposal to the smart device.

[1444] Input: Generated product or service proposals.

[1445] Output: Proposal data sent to smart device.

[1446] How it works: The server receives the proposed data from the generative AI model, converts it into a user-friendly format, and then securely transmits it to the smart glasses.

[1447] Step 7:

[1448] The smart device displays the suggestions to the user.

[1449] Input: Proposal data sent by the server.

[1450] Output: The suggested products or services displayed to the user.

[1451] How it works: The smart glasses display information about suggested products and services on the screen, including product descriptions, prices, sales information, coupons, etc. This information allows users to efficiently select products in the store.

[1452] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1453] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1454] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1455] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1456] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1457] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1458] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1459] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1460] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1461] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1462] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1463] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1464] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1465] 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.

[1466] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1467] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1468] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1469] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1470] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1471] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1472] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1473] The following is further disclosed regarding the above embodiment.

[1474] (Claim 1)

[1475] A means for a user to input his / her attributes and household financial situation;

[1476] means for transmitting the input user data to a server;

[1477] means for the server to receive the user data and store it in a database;

[1478] means for the server to preprocess stored user data;

[1479] A means for AI to match pre-processed user data with market data to generate optimal mortgage options;

[1480] means for the server to transmit the generated mortgage option to a terminal;

[1481] means for the terminal to display the loan options to a user;

[1482] A system including:

[1483] (Claim 2)

[1484] 10. The system of claim 1, wherein the server receives new input data or additional data from the user, reanalyzes the data, and regenerates optimal mortgage options.

[1485] (Claim 3)

[1486] The system of claim 1, wherein the generation AI generates optimal loan options based on the interest rate, repayment period, and monthly payment amount of the loan options.

[1487] "Example 1"

[1488] (Claim 1)

[1489] A means for a user to input his / her attributes and household financial situation;

[1490] means for transmitting the input user data from the terminal to a server;

[1491] a means for the server to receive the user data, check the data format, detect and correct abnormal values, and store the data in a database;

[1492] means for the server to preprocess the stored user data, performing missing value imputation, duplicate data removal, and normalization;

[1493] A means for AI to match pre-processed user data with market data to generate optimal mortgage options;

[1494] means for the server to format the generated mortgage options into a user-friendly format and transmit the format to a terminal;

[1495] means for the terminal to visually display the interest rate, repayment period and monthly payment amount of the loan option to the user in an easy-to-understand manner;

[1496] A system including:

[1497] (Claim 2)

[1498] 10. The system of claim 1, wherein the server receives new input data or additional data from the user, reanalyzes the data, and regenerates optimal mortgage options.

[1499] (Claim 3)

[1500] 2. The system of claim 1, wherein the generative AI uses a generative AI model to optimize and generate interest rates, repayment periods, and monthly payments for loan options based on prompt statements.

[1501] "Application Example 1"

[1502] (Claim 1)

[1503] A means for a user to input his / her attributes and household financial situation;

[1504] means for transmitting the input user data to a server;

[1505] means for the server to receive the user data and store it in a database;

[1506] means for the server to preprocess stored user data;

[1507] A means for AI to match pre-processed user data with market data to generate optimal mortgage options;

[1508] means for the server to transmit the generated mortgage option to a terminal;

[1509] means for the terminal to visually display the loan options to the user in an easily understandable manner;

[1510] a means for the user to answer further questions or provide additional information;

[1511] means for the server to receive new information from the user, reanalyze, and generate a new optimized loan offer;

[1512] A system including:

[1513] (Claim 2)

[1514] 10. The system of claim 1, wherein the server receives new input data or additional data from the user, reanalyzes the data, and regenerates optimal mortgage options.

[1515] (Claim 3)

[1516] The system of claim 1, wherein the generation AI not only generates optimal loan options based on the interest rate, repayment period, and monthly payment amount of the loan options, but also generates loan options taking into account the latest interest rate information and repayment conditions based on market data.

[1517] "Example 2: Combining Emotion Engines"

[1518] (Claim 1)

[1519] A means for a user to input his / her attributes and household financial situation;

[1520] means for transmitting the input user data to an information processing device;

[1521] a means for receiving the user data by the information processing device and storing the user data in a storage medium;

[1522] means for preprocessing user data stored in the information processing device;

[1523] A machine learning model matches market data based on pre-processed user data to generate optimal mortgage options; and

[1524] means for transmitting the generated mortgage options to an output device by the information processing device;

[1525] means for the output device to display the loan options to a user;

[1526] means for analyzing the emotional state of the user using a sentiment analysis engine and customizing the generated mortgage options based on the emotional state of the user;

[1527] A system including:

[1528] (Claim 2)

[1529] 10. The system of claim 1, wherein the information processing device receives new input data or additional data from the user, reanalyzes the data, and regenerates optimal mortgage options.

[1530] (Claim 3)

[1531] 2. The system of claim 1, wherein the machine learning model generates optimal loan options based on interest rates, repayment periods, and monthly payments of the loan options.

[1532] "Application example 2 when combining emotion engines"

[1533] (Claim 1)

[1534] A means for a user to input his / her attributes and household financial situation;

[1535] means for transmitting the input user data to a server;

[1536] means for the server to receive the user data and store it in a database;

[1537] means for the server to preprocess stored user data;

[1538] A means for AI to match pre-processed user data with market data to generate optimal mortgage options;

[1539] means for the server to transmit the generated mortgage option to a terminal;

[1540] means for the terminal to display the loan options to a user;

[1541] A method for using smart devices in physical stores to analyze users' attributes and emotional state and then suggest optimal products and services based on that information.

[1542] A system including:

[1543] (Claim 2)

[1544] 10. The system of claim 1, wherein the server receives new input data or additional data from the user, reanalyzes the data, and regenerates optimal mortgage options.

[1545] (Claim 3)

[1546] The system of claim 1, wherein the generation AI has a means for generating the optimal loan option based on the interest rate, repayment period, and monthly payment amount of the loan option, and dynamically suggests optimal products and services to the user based on the suggestions made at the physical store. [Explanation of symbols]

[1547] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for a user to input his / her attributes and household financial situation; means for transmitting the input user data to a server; means for the server to receive the user data and store it in a database; means for the server to preprocess stored user data; A means for AI to match pre-processed user data with market data to generate optimal mortgage options; means for the server to transmit the generated mortgage option to a terminal; means for the terminal to display the loan options to a user; A system including:

2. 10. The system of claim 1, wherein the server receives new input data or additional data from the user, reanalyzes the data, and regenerates optimal mortgage options.

3. The system of claim 1 , wherein the generation AI generates optimal loan options based on interest rates, repayment periods, and monthly payments of the loan options.

Images