system

Abstract

We provide the system. [Solution] A means of receiving financial information entered by the user, A method using a machine learning model that analyzes received information and performs a preliminary review, A means for generating a credit provision plan and repayment forecast suitable for the user based on the generated preliminary screening results, Information provision means for providing information in response to user requests, A means of managing the above means in conjunction and providing continuous support to users throughout the day, An interface means that allows repayment predictions to be intuitively visualized on the user's terminal, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When considering a housing loan, it is to eliminate the difficulty for an individual to select an optimal plan from the complicated procedures and numerous options faced, and to enable the financial institution to improve the efficiency of service provision and reduce costs. Also, it is necessary to provide appropriate information and educational support to users in order to prevent incorrect judgments due to fluctuations in the housing market and insufficient understanding of technical terms.

Means for Solving the Problems

[0005] This invention provides a system that can perform a preliminary loan assessment by receiving housing-related information input from a user and analyzing that information using an artificial intelligence model. Furthermore, it has means for generating an optimal loan plan and repayment simulation for the user based on the generated preliminary assessment results. In addition to providing information to accurately and timely provide the information requested by the user, the system can deepen the user's understanding of the information by selecting and providing educational content on fluctuations in the housing market. Moreover, it has means for collecting user feedback and using it to improve the system, thereby achieving continuous service improvement.

[0006] A "user" refers to an individual who uses the system to input information about their mortgage or to receive support.

[0007] "Housing-related information" refers to data necessary for evaluating a mortgage, such as annual income, desired loan amount, repayment period, and existing debt.

[0008] "Means of receiving information" refers to an interface for taking in user input and passing it to the system for analysis.

[0009] An "artificial intelligence model" refers to a machine learning algorithm used to analyze input information and generate preliminary approval results and loan plans.

[0010] "Preliminary review" refers to the process of assessing the likelihood of a mortgage application being provisionally approved.

[0011] A "loan plan" refers to a proposal that outlines repayment terms and schedules tailored to the user's situation.

[0012] A "repayment simulation" refers to a calculation process that predicts future repayment status and total payment amount based on a proposed loan plan.

[0013] "Information provision means" refers to a function within a system that collects information requested by the user, edits it appropriately, and presents it.

[0014] "Educational content" refers to materials prepared to clearly explain basic knowledge and market trends related to home loans to users.

[0015] "Feedback collection methods" refer to the process of gathering user reactions and opinions and using them to improve the system.

[0016] "24-hour customer support" refers to a system that allows users to receive support at any time throughout the day. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

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

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

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

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

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

[0025] [First Embodiment]

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

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

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

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

[0030] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

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

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

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

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

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

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

[0038] This invention is a system for streamlining mortgage-related procedures and improving customer convenience, and its main components are a user, a terminal, and a server. Specific embodiments thereof are described below.

[0039] First, the user uses a terminal to input housing-related information such as annual income, desired loan amount, and repayment period. The terminal converts this data into the appropriate format and sends it to the server. The server receives the data sent from the terminal and verifies its formal accuracy. Subsequently, it provides the correctly received information to an artificial intelligence model for a preliminary assessment.

[0040] The artificial intelligence model analyzes the input information and generates a preliminary screening result based on existing screening criteria. The server interprets the obtained result and sends it to the user's terminal. For users who pass the preliminary screening, the server uses the generated AI model to create and provide an optimal loan plan and repayment simulation.

[0041] In this system, when users want to know more or request additional support, the server provides detailed information on housing market trends and loan-related terminology as a means of providing information. This helps users make more effective decisions regarding repayment plans and loan selection.

[0042] Furthermore, educational content regarding fluctuations in the housing market and new loan plans is selected from the server and delivered to the user's device. This allows users to acquire the necessary knowledge and make more informed decisions.

[0043] Furthermore, feedback from users is collected and used to improve the system. This allows the system of the present invention to flexibly respond to user needs and be continuously optimized. In this way, the system provides users with 24 / 7 customer support, enabling faster and more efficient service.

[0044] As a concrete example, consider a case where a user applies for a loan with an annual income of 6 million yen, a desired loan amount of 25 million yen, and a repayment period of 30 years. This information is entered into a terminal and sent to the server. The server then performs a preliminary assessment using an artificial intelligence model and provides a suitable loan plan along with the results. The user can then make a final decision based on this information.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The user uses the terminal to input necessary housing-related information such as annual income, desired loan amount, and repayment period. The terminal then formats this information and makes it ready for transmission.

[0048] Step 2:

[0049] The terminal sends user input information to the server. The server receives the data and checks the format and required fields. If there are any problems, it generates an error message and returns it to the terminal.

[0050] Step 3:

[0051] The server passes correctly formatted information to the generating AI model and requests a preliminary review. The generating AI model analyzes the data and evaluates whether the user's loan application is eligible for pre-approval.

[0052] Step 4:

[0053] The generating AI model returns the preliminary review results to the server. The server interprets the results and sends them to the user's device in a format that is easy for the user to understand.

[0054] Step 5:

[0055] Based on the preliminary screening results, the server requests an AI model to generate the optimal loan plan and repayment simulation for the user.

[0056] Step 6:

[0057] The user receives loan plans and simulations provided by the server. If they want more detailed information or other options, they can submit additional questions from their device.

[0058] Step 7:

[0059] The server receives additional requests from users, prepares appropriate information using an AI model, and sends it back to the terminal. This information includes data on educational content and market trends.

[0060] Step 8:

[0061] Users review the provided information and make their final decisions. They can also send feedback to the server via their device.

[0062] Step 9:

[0063] The server collects user feedback and uses it to improve the system. This allows the system to be continuously optimized to meet user needs.

[0064] (Example 1)

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

[0066] Traditional financial procedures, including those for mortgages, have often been inefficient in terms of complex processes and information provision, placing a significant burden on users. In particular, there is a need for rapid and accurate information processing and the presentation of financial plans tailored to individual users. The challenge lies in resolving this issue and improving user convenience and efficiency.

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

[0068] In this invention, the server includes a device for receiving financial information input from a user, a device that uses an intelligent model to analyze the received information and perform a preliminary evaluation, and a device that selects and provides educational information on market trends to the user. This enables the user to efficiently receive a preliminary evaluation and be presented with an appropriate financial plan.

[0069] "Financial information" refers to all economic data related to loans and asset management, specifically including annual income, desired loan amount, and repayment period.

[0070] A "data structure" is an organized form used to efficiently manage and manipulate information, and is intended to maintain the consistency and integrity of that information.

[0071] An "intelligent model" refers to an algorithm or program designed to learn from past data and experience, and to analyze and make judgments based on the information it receives.

[0072] A "financial plan" provides optimized loan and investment strategies based on the user's specific financial situation and goals.

[0073] A "computational model" refers to a mathematical framework used to simulate specific repayment plans and risk assessments in various financial scenarios.

[0074] An "information distribution device" is a system or program that provides users with timely and relevant knowledge and data.

[0075] A "feedback collection device" refers to a system used to collect user feedback and opinions and utilize them to improve the system.

[0076] This invention relates to a system that streamlines financial procedures and improves user convenience. It mainly consists of three elements: a server, a terminal, and a user.

[0077] The terminal provides an interface for users to input financial information. On the terminal, users input information such as annual income, desired loan amount, and repayment period, and this information is immediately converted into a data structure. Data processing libraries, such as those using Python, are often used for data formatting.

[0078] The server analyzes the received information using an intelligent model. This intelligent model typically employs machine learning frameworks such as TENSORFLOW® or PyTorch, performing preliminary evaluations based on historical data. The server also has a function to select and provide educational information on market trends to users. This educational information is regularly updated by the server to improve users' knowledge and support more appropriate financial decisions.

[0079] For example, when a user inputs information such as "annual income of 6 million yen, desired loan amount of 25 million yen, repayment period of 30 years" into their device, this data is sent to an intelligent model by the server. The server analyzes this data and sends a preliminary evaluation result, such as "a 35-year repayment plan is optimal," back to the user's device.

[0080] As an example of a prompt, you can instruct the generating AI model in the following format: "User A has an annual income of 6 million yen, desires a loan amount of 25 million yen, and wants a repayment period of 30 years. Please conduct a preliminary assessment based on this information and provide the results."

[0081] These processes allow users to receive appropriate financial plans quickly and make efficient decisions. This system implementation enables 24 / 7 customer support and supports users' future financial activities.

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The user enters financial information using a terminal. The terminal receives information such as annual income, desired loan amount, and repayment period, and converts it into a data structure. This conversion formats the input into JSON format, preparing it for the next processing step.

[0085] Step 2:

[0086] The terminal sends formatted financial data to the server. The server parses the received JSON data and formally verifies that all necessary items are present. Once verification is complete, the data proceeds to the preliminary evaluation process.

[0087] Step 3:

[0088] The server provides the received data to an intelligent model and performs a preliminary review. The intelligent model uses machine learning frameworks such as TensorFlow or PyTorch to analyze historical data and generate a risk assessment and loan plan based on the input information. This then outputs the preliminary review results.

[0089] Step 4:

[0090] The server converts the generated preliminary assessment results into a format that is easy for the user to understand. The converted data is then sent to the user's device along with the repayment plan and applicable conditions. This allows the user to understand the plan that is best suited to them.

[0091] Step 5:

[0092] The user reviews the preliminary review results received through the device. The device provides an interface for the user to send requests to the server if they require more detailed information or additional support. This allows for further information retrieval and feedback submission.

[0093] (Application Example 1)

[0094] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] Modern borrowers demand fast, transparent, and personalized credit plans. However, the procedures in the traditional financial system are cumbersome, making it difficult for users to easily find a plan that suits them. Furthermore, there is a lack of support for understanding market trends and developing repayment plans that adapt to changes.

[0096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0097] In this invention, the server includes means for using a machine learning model to analyze received information and perform a preliminary assessment, means for generating a credit provision plan and repayment forecast suitable for the user based on the generated preliminary assessment results, and means for providing information in response to the user's requests. This allows the user to quickly access a credit provision plan suitable for them and to receive repayment forecasts based on financial market trends.

[0098] "Financial information" refers to data about a user's economic situation, such as annual income, assets, and liabilities, which is necessary when a user applies for credit.

[0099] A "machine learning model" is a collection of algorithms that learn patterns and relationships based on past data and use them to make predictions and classifications on new data.

[0100] A "credit provision plan" is a proposal outlining loan or financing terms and repayment schedules optimized according to the user's financial situation and needs.

[0101] "Repayment forecast" is an estimate of future repayment amounts and repayment periods based on the user's credit provision plan.

[0102] "Information provision means" refers to a device or program for collecting, analyzing, and presenting appropriate information in response to a user's request.

[0103] "Continuous support throughout the day" refers to a service delivery model that provides constant support to users without time constraints.

[0104] An "interface means" is a visual or manipulative component that enables the input and output of information between a user and a system.

[0105] "Financial market trends" refer to the movements in the market that are influenced by changes in the economic environment, policies, interest rates, exchange rates, and other factors.

[0106] A "response collection means" is a method or apparatus for efficiently collecting and analyzing evaluations and opinions from users.

[0107] This embodiment begins with the user inputting financial information. The user uses a smartphone or other device to input information such as annual income and assets into the system. The device then formats this data appropriately and sends it to the server.

[0108] The server uses a machine learning model to perform a preliminary assessment based on the received information. This model is built using TensorFlow and learns assessment criteria based on historical data, allowing it to quickly evaluate the user's credit risk.

[0109] Based on the preliminary assessment results, the server generates the optimal credit plan for the user. Furthermore, it uses a React Native application to calculate a corresponding repayment forecast and visually present it on the user's terminal interface.

[0110] Based on the information provided, users can select the loan plan that best suits their needs. Upon user request, the server will immediately provide additional information related to financial market trends and plans, guaranteeing continuous support throughout the day.

[0111] For example, if a user applies with an annual income of 6 million yen, a desired loan amount of 25 million yen, and a repayment period of 30 years, the server can create a repayment simulation that takes interest rate fluctuations into account and present it to the user based on an interest rate increase scenario. In this case, an example of a prompt message using the generated AI model would be, "Please generate the most suitable mortgage plan based on the user's annual income and desired amount, and perform a repayment simulation that takes interest rate fluctuations into account." This allows the user to obtain sufficient information and criteria to make an informed decision about selecting an appropriate loan plan.

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The terminal receives financial information entered by the user (e.g., annual income, desired loan amount, repayment period). This information is converted to JSON format and prepared for transmission to the server. This conversion ensures a consistent data structure, making it easier to analyze on the server.

[0115] Step 2:

[0116] The server receives data in JSON format sent from the terminal. This data is then validated, field by field, to check for missing or invalid data. Once validated, the data is prepared as input for a machine learning model.

[0117] Step 3:

[0118] The server inputs information into a machine learning model (using TensorFlow) and performs a preliminary screening. The model analyzes the input data, assesses the user's credit risk, and generates a preliminary screening result based on their creditworthiness. The output is the user's credit score and whether or not they passed the preliminary screening.

[0119] Step 4:

[0120] The server creates an optimal credit plan and repayment forecast for the user based on the preliminary assessment results. This generation applies a plan creation algorithm and incorporates various loan conditions and market interest rate information. The output of this process is a loan plan including key conditions and a visualized repayment forecast.

[0121] Step 5:

[0122] The server sends the generated credit plan and repayment forecast to the device. The device then presents the information to the user visually through a React Native application. The user can review the plan details and manipulate the provisional repayment plan through an interactive interface.

[0123] Step 6:

[0124] If the user requests further information after reviewing the details, the server searches for financial market trends and relevant educational content, and sends the necessary information to the user's device. This process allows the user to gain a deeper understanding of the loan plan.

[0125] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0126] This invention provides more personalized support by combining a system that provides mortgage-related information and conducts preliminary screening with an emotion engine that recognizes the user's emotions. A specific embodiment is described below.

[0127] First, the user enters housing-related information through an interface on their device. The device formats this information and sends it to the server. The server receives the input information and performs a preliminary assessment using an artificial intelligence model. The preliminary assessment results are then communicated to the user along with a suitable loan plan and repayment simulation.

[0128] This system incorporates an emotion engine that analyzes user input, feedback, and interaction history to assess their emotional state. Based on the emotion engine's results, the server adjusts the tone of information and notifications to match the user's emotions. For example, if the user is feeling anxious, the system will provide more detailed and easily understandable information and offer additional support.

[0129] Furthermore, housing market trends and educational content are individually customized according to the user's interests and preferences and delivered to the user through their device. If the emotion engine detects signs of stress or questions from the user's responses and behavior, the server will provide the user with additional support in real time.

[0130] For example, if a user expresses anxiety about a mortgage, the emotion engine detects that emotion, and the server delivers additional explanatory videos or FAQ sessions to the device. It also highlights a chat link to support staff, allowing users to easily obtain additional information.

[0131] This system operates 24 / 7, continuously collecting user feedback to improve the system. This ensures users always receive appropriate and timely support and enjoy a highly customized mortgage experience.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The user uses the terminal to input housing-related information such as their annual income, desired loan amount, and repayment period. The terminal receives this information, formats it, and prepares it for transmission to the server.

[0135] Step 2:

[0136] The server receives the information sent from the terminal and verifies the integrity and completeness of the input data. If the data is appropriate, the server proceeds with further processing and performs a preliminary review using an artificial intelligence model.

[0137] Step 3:

[0138] The server performs a preliminary review using an artificial intelligence model and generates results. These results include a preliminary assessment of the likelihood of loan approval and related risk assessments.

[0139] Step 4:

[0140] Based on the generated preliminary screening results, the server creates an optimal loan plan and repayment simulation for the user. This includes options for fixed and variable interest rates, as well as simulations for different repayment periods.

[0141] Step 5:

[0142] The server uses an emotion engine to analyze the user's emotional state from past inputs and feedback. The emotion engine evaluates the user's stress level, anxiety, level of interest, etc., and instructs the server on the most appropriate response.

[0143] Step 6:

[0144] Based on the analysis results of the emotion engine, the server adjusts the tone and content of the information presented on the device. For example, if anxiety is detected, the server provides the device with additional information, including explanations that emphasize the details and benefits of the loan, as well as FAQ links.

[0145] Step 7:

[0146] Users receive preliminary screening results, loan plans, and supplementary information from the server via their device. Emotionally responsive communication allows users to confidently make decisions about proceeding to the next step.

[0147] Step 8:

[0148] Users can input feedback into their devices as needed and send it to the server via their devices. The server collects this feedback and uses it to further improve the system.

[0149] Step 9:

[0150] Based on the collected feedback and sentiment data, the server optimizes overall system service and individual customizations. The system is then prepared to provide more precise support the next time the user accesses it.

[0151] (Example 2)

[0152] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0153] Traditional information systems for mortgages and other financial products often provide a uniform response without considering the individual emotional state of each user. As a result, users often fail to receive the optimal information and support tailored to their specific circumstances and needs. Furthermore, systems that do not properly utilize feedback can lead to delays in service improvement and decreased user satisfaction.

[0154] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0155] In this invention, the server includes means for receiving financial data input from the user, means for using a machine learning model to analyze the received data and perform a preliminary review, and means for analyzing the user's emotional state and adjusting the tone of information provided. This enables personalized information provision tailored to each user's emotional state and needs, and continuous improvement of the service through the use of appropriate feedback.

[0156] A "user" refers to a person who uses the system to input financial data and receives information and support.

[0157] "Financial data" refers to information related to mortgages and financial services, such as property prices, down payments, and income information entered by the user.

[0158] "Means of receiving" refers to the devices and processes used to send data entered by the user from the terminal to the server, and for the server to receive that data.

[0159] A "machine learning model that analyzes and performs preliminary screening" refers to a learning program that runs on a server, analyzes received data, and provisionally evaluates a financial plan suitable for the user.

[0160] "Emotional analysis means" refers to algorithms and devices that analyze the emotional state based on user input and feedback, and adjust the method of information provision accordingly.

[0161] "Information distribution means" refers to communication methods used to provide users with appropriate information based on sentiment analysis results and preliminary screening results.

[0162] "Feedback collection methods" refer to the methods and processes used to obtain opinions and evaluations from users and utilize them for system improvement.

[0163] A "server" refers to a central computer system that processes data from users and generates and distributes information.

[0164] This invention provides a system that allows users to access mortgages and other financial services more intuitively and individually. The system aims to provide personalized information by taking into account the user's emotional state.

[0165] Users enter detailed mortgage-related data through their devices. This includes property price, down payment, annual income, and other financial conditions, entered via the system interface. The device formats this data and sends it to the server. The protocol used by the device is typically secure HTTPS communication.

[0166] The server utilizes generative AI models to analyze the received data. Machine learning platforms such as TensorFlow and PyTorch are used for this analysis. The model presents the user with a preliminary loan plan and provides a repayment simulation tailored to the user's financial situation.

[0167] Furthermore, the system integrates an emotion analysis engine that evaluates the user's emotional state based on their input and feedback. Natural language processing libraries such as NLTK and DeepMoji are used for this purpose. The analysis results are then used to adjust the tone of information and notifications provided to the user.

[0168] For example, if a user types "I'm worried about rising interest rates," the emotion engine detects the anxiety, and the server provides additional easy-to-understand explanatory videos and FAQs. At this point, the user can easily access additional support through a chat link highlighted on their device.

[0169] Examples of prompts for a generative AI model include concise and specific requests such as, "Please provide additional information about concerns regarding mortgages."

[0170] This system operates 24 hours a day, systematically collecting user feedback, which is then analyzed and stored on the server. This feedback is used to improve the system, enabling us to provide optimal support to users over the long term.

[0171] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0172] Step 1:

[0173] The user enters information about their mortgage into the terminal's input interface. This information includes financial details such as the property price, down payment, and annual income. The terminal receives this information and converts it into a data format, such as JSON. The converted data is then sent to the server.

[0174] Step 2:

[0175] The server receives data sent from the terminal. The received data is analyzed using a machine learning model. Frameworks such as TensorFlow and PyTorch are used for this analysis. The purpose of the analysis is to pre-screen a loan plan suitable for the user based on the input data and generate a repayment simulation based on that plan. The analysis results are output as a loan plan and simulation data.

[0176] Step 3:

[0177] The server provides feedback to the user based on the generated loan plan and simulation data. During this process, it monitors the user's emotional state using sentiment analysis tools. Specifically, sentiment analysis is performed using tools such as NLTK and DeepMoji, based on the user's input and additional feedback received previously. The analysis results are used as input to adjust the tone and content of the information provided.

[0178] Step 4:

[0179] The device receives feedback and analysis results sent from the server. After making adjustments based on the user's emotional state, it displays details of the loan plan and the results of the repayment simulation. The user can then decide on further actions based on this information. Links to additional materials and FAQs are displayed as needed to aid the user's understanding.

[0180] Step 5:

[0181] When a user enters feedback or asks additional questions, the device sends it to the server. The server collects this feedback and stores it in a database for future system improvements. The feedback helps improve the user experience and the accuracy of the generated AI model.

[0182] (Application Example 2)

[0183] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0184] There is a need to alleviate the anxiety and stress experienced by mortgage borrowers and to provide more personalized loan information and support. However, conventional systems struggle to provide flexible support that responds to users' emotional states. Therefore, the challenge is to provide an environment where users can manage their mortgages with peace of mind.

[0185] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0186] In this invention, the server includes means for receiving housing-related information input by the user, means for using a machine learning model that analyzes the received information and performs a preliminary review, and means for using an emotion analysis function that analyzes the user's input data and dialogue history and evaluates their emotional state. This makes it possible to provide information and support that is tailored to the user's emotions.

[0187] A "user" is someone who uses the system to receive housing-related information and loan support.

[0188] "Means for receiving housing-related information" refers to a function that incorporates information related to home purchases and loans entered by users into the system.

[0189] A "machine learning model" is a model based on artificial intelligence technology that is used to analyze user input information and perform preliminary screening.

[0190] The "emotion analysis function" is a feature that analyzes user input data and conversation history to evaluate the user's emotional state.

[0191] "Means for evaluating emotional state" refers to methods used by a system to determine a user's emotions and adjust the level of support provided.

[0192] "Means of adjusting the tone of information provision and notifications" refers to a function that changes the way information is presented and the content of notifications based on the user's emotional state.

[0193] "Means of providing 24-hour customer support" refers to means of responding to user inquiries at any time and providing necessary information and support.

[0194] "Means of providing support information" refers to means of presenting appropriate support information in response to the anxieties and questions that users may have.

[0195] This invention develops a system that incorporates sentiment analysis capabilities to provide personalized support to mortgage borrowers. The system has a server-terminal and user-centric structure.

[0196] The server includes the following steps: First, the user inputs information about their home via a terminal. The terminal converts the input information into a digital format and sends it to the server. Next, the server uses a machine learning model to analyze the input information and conduct a preliminary assessment of the mortgage. At this time, the system also implements a function that uses Google® Cloud AI's natural language API to perform sentiment analysis on the user's text data and evaluate their emotional state. Depending on the emotional state, the tone of information provided and notifications is adjusted, and the user is provided with a customized loan plan and support information.

[0197] The application is designed for smartphones, with the frontend developed using React Native and the backend using Ruby on Rails. This structure allows users to manage their mortgage information intuitively and efficiently.

[0198] Through the process described above, the sentiment analysis function detects the user's level of anxiety based on text entered by the user, such as "I'm worried because I've been behind on payments lately." In this case, the server provides specific advice and additional support information to alleviate the anxiety. Additionally, a contact link to support staff is put into standby mode, allowing the user to contact them immediately.

[0199] Examples of prompt statements used for generative AI models are as follows:

[0200] "Analyze the user's sentiment from the following text and determine if they need support: 'I'm worried because I've been behind on payments lately.'"

[0201] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0202] Step 1:

[0203] The terminal provides a user interface for entering mortgage information. The user enters information such as the desired purchase price, annual income, and desired loan term. This information is converted into a digital format and sent to the server.

[0204] Step 2:

[0205] The server receives housing-related information from the terminal. Based on the received information, it performs a preliminary assessment using a machine learning model. This generates a preliminary loan assessment based on the user's eligibility and conditions.

[0206] Step 3:

[0207] The server uses sentiment analysis functionality to evaluate the user's emotional state. It utilizes additional data and text input provided by the user, leveraging Google Cloud AI's natural language API to perform sentiment analysis. This process extracts emotional information such as the user's anxiety and worries.

[0208] Step 4:

[0209] The server integrates the preliminary assessment results and sentiment analysis results, and adjusts the tone of information and notifications accordingly. For example, if the user is feeling anxious, detailed and concise support information and video guides are provided. This information is sent to the device and displayed to the user.

[0210] Step 5:

[0211] The terminal displays information and support details sent from the server to the user. If necessary, a contact link to support staff is highlighted, allowing the user to easily request additional support.

[0212] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0213] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0214] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0215] [Second Embodiment]

[0216] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0217] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0218] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0219] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0220] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0221] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0222] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0223] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0224] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0225] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0226] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0227] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0228] This invention is a system for streamlining mortgage-related procedures and improving customer convenience, and its main components are a user, a terminal, and a server. Specific embodiments thereof are described below.

[0229] First, the user uses a terminal to input housing-related information such as annual income, desired loan amount, and repayment period. The terminal converts this data into the appropriate format and sends it to the server. The server receives the data sent from the terminal and verifies its formal accuracy. Subsequently, it provides the correctly received information to an artificial intelligence model for a preliminary assessment.

[0230] The artificial intelligence model analyzes the input information and generates a preliminary screening result based on existing screening criteria. The server interprets the obtained result and sends it to the user's terminal. For users who pass the preliminary screening, the server uses the generated AI model to create and provide an optimal loan plan and repayment simulation.

[0231] In this system, when users want to know more or request additional support, the server provides detailed information on housing market trends and loan-related terminology as a means of providing information. This helps users make more effective decisions regarding repayment plans and loan selection.

[0232] Furthermore, educational content regarding fluctuations in the housing market and new loan plans is selected from the server and delivered to the user's device. This allows users to acquire the necessary knowledge and make more informed decisions.

[0233] Furthermore, feedback from users is collected and used to improve the system. This allows the system of the present invention to flexibly respond to user needs and be continuously optimized. In this way, the system provides users with 24 / 7 customer support, enabling faster and more efficient service.

[0234] As a concrete example, consider a case where a user applies for a loan with an annual income of 6 million yen, a desired loan amount of 25 million yen, and a repayment period of 30 years. This information is entered into a terminal and sent to the server. The server then performs a preliminary assessment using an artificial intelligence model and provides a suitable loan plan along with the results. The user can then make a final decision based on this information.

[0235] The following describes the processing flow.

[0236] Step 1:

[0237] The user uses the terminal to input necessary housing-related information such as annual income, desired loan amount, and repayment period. The terminal then formats this information and makes it ready for transmission.

[0238] Step 2:

[0239] The terminal sends user input information to the server. The server receives the data and checks the format and required fields. If there are any problems, it generates an error message and returns it to the terminal.

[0240] Step 3:

[0241] The server passes correctly formatted information to the generating AI model and requests a preliminary review. The generating AI model analyzes the data and evaluates whether the user's loan application is eligible for pre-approval.

[0242] Step 4:

[0243] The generating AI model returns the preliminary review results to the server. The server interprets the results and sends them to the user's device in a format that is easy for the user to understand.

[0244] Step 5:

[0245] Based on the preliminary screening results, the server requests an AI model to generate the optimal loan plan and repayment simulation for the user.

[0246] Step 6:

[0247] The user receives loan plans and simulations provided by the server. If they want more detailed information or other options, they can submit additional questions from their device.

[0248] Step 7:

[0249] The server receives additional requests from users, prepares appropriate information using an AI model, and sends it back to the terminal. This information includes data on educational content and market trends.

[0250] Step 8:

[0251] Users review the provided information and make their final decisions. They can also send feedback to the server via their device.

[0252] Step 9:

[0253] The server collects user feedback and uses it to improve the system. This allows the system to be continuously optimized to meet user needs.

[0254] (Example 1)

[0255] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0256] Traditional financial procedures, including those for mortgages, have often been inefficient in terms of complex processes and information provision, placing a significant burden on users. In particular, there is a need for rapid and accurate information processing and the presentation of financial plans tailored to individual users. The challenge lies in resolving this issue and improving user convenience and efficiency.

[0257] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0258] In this invention, the server includes a device for receiving financial information input from a user, a device that uses an intelligent model to analyze the received information and perform a preliminary evaluation, and a device that selects and provides educational information on market trends to the user. This enables the user to efficiently receive a preliminary evaluation and be presented with an appropriate financial plan.

[0259] "Financial information" refers to all economic data related to loans and asset management, specifically including annual income, desired loan amount, and repayment period.

[0260] A "data structure" is an organized form used to efficiently manage and manipulate information, and is intended to maintain the consistency and integrity of that information.

[0261] An "intelligent model" refers to an algorithm or program designed to learn from past data and experience, and to analyze and make judgments based on the information it receives.

[0262] A "financial plan" provides optimized loan and investment strategies based on the user's specific financial situation and goals.

[0263] A "computational model" refers to a mathematical framework used to simulate specific repayment plans and risk assessments in various financial scenarios.

[0264] An "information distribution device" is a system or program that provides users with timely and relevant knowledge and data.

[0265] A "feedback collection device" refers to a system used to collect user feedback and opinions and utilize them to improve the system.

[0266] This invention relates to a system that streamlines financial procedures and improves user convenience. It mainly consists of three elements: a server, a terminal, and a user.

[0267] The terminal provides an interface for users to input financial information. On the terminal, users input information such as annual income, desired loan amount, and repayment period, and this information is immediately converted into a data structure. Data processing libraries, such as those using Python, are often used for data formatting.

[0268] The server analyzes the received information using an intelligent model. This intelligent model typically employs machine learning frameworks such as TensorFlow or PyTorch, performing preliminary evaluations based on historical data. The server also has a function to select and provide educational information on market trends to users. This educational information is regularly updated by the server to improve users' knowledge and support more appropriate financial decisions.

[0269] For example, when a user inputs information such as "annual income of 6 million yen, desired loan amount of 25 million yen, repayment period of 30 years" into their device, this data is sent to an intelligent model by the server. The server analyzes this data and sends a preliminary evaluation result, such as "a 35-year repayment plan is optimal," back to the user's device.

[0270] As an example of a prompt, you can instruct the generating AI model in the following format: "User A has an annual income of 6 million yen, desires a loan amount of 25 million yen, and wants a repayment period of 30 years. Please conduct a preliminary assessment based on this information and provide the results."

[0271] These processes allow users to receive appropriate financial plans quickly and make efficient decisions. This system implementation enables 24 / 7 customer support and supports users' future financial activities.

[0272] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0273] Step 1:

[0274] The user enters financial information using a terminal. The terminal receives information such as annual income, desired loan amount, and repayment period, and converts it into a data structure. This conversion formats the input into JSON format, preparing it for the next processing step.

[0275] Step 2:

[0276] The terminal sends the formatted financial-related data to the server. The server analyzes the received data in JSON format and formally checks whether all the necessary items are complete. When the check is completed, the data proceeds to the preliminary evaluation process.

[0277] Step 3:

[0278] The server provides the received data to the intelligent model and performs a preliminary review. The intelligent model uses a machine learning framework such as TensorFlow or PyTorch to analyze past data and generate a risk assessment and loan plan based on the input information. As a result, the preliminary review results are output.

[0279] Step 4:

[0280] The server converts the generated preliminary review results into a form that is easy for the user to understand. The converted data is sent to the user's terminal together with the repayment plan and the applicable conditions. As a result, the user can grasp the most suitable plan for themselves.

[0281] Step 5:

[0282] The user checks the preliminary review results received through the terminal. The terminal provides an interface for the user to send requests to the server when detailed information or additional support is needed. As a result, it becomes possible to obtain further information and send feedback.

[0283] (Application Example 1)

[0284] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0285] Modern financial users are seeking credit offering plans that are fast, transparent, and tailored to their individual needs. However, the procedures in the traditional financial system are complex, making it difficult for users to easily find a plan suitable for themselves. There is also an issue of insufficient support for understanding market trends and formulating repayment plans that can adapt to changes.

[0286] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following means.

[0287] In this invention, the server includes means for using a machine learning model that analyzes the received information and performs a preliminary review, means for generating a credit offering plan and repayment prediction suitable for the user based on the generated preliminary review result, and information providing means for providing information according to the user's request. As a result, the user can quickly access a credit offering plan suitable for themselves and can make a repayment prediction based on the trends in the financial market.

[0288] "Financial-related information" refers to data on economic situations such as annual income, assets, and liabilities that are necessary when a user receives credit.

[0289] "Machine learning model" refers to a collection of algorithms that learn patterns and relationships based on past data and perform predictions and classifications on new data.

[0290] "Credit offering plan" refers to a proposal indicating the conditions and repayment schedule of loans and financing optimized according to the economic situation and needs of the user.

[0291] "Repayment prediction" refers to the result of estimating future repayment amounts and repayment periods based on the user's credit offering plan.

[0292] "Information providing means" refers to a device or program for collecting, analyzing, and presenting appropriate information according to the user's request.

[0293] "Continuous support throughout the day" refers to a service delivery model that provides constant support to users without time constraints.

[0294] An "interface means" is a visual or manipulative component that enables the input and output of information between a user and a system.

[0295] "Financial market trends" refer to the movements in the market that are influenced by changes in the economic environment, policies, interest rates, exchange rates, and other factors.

[0296] A "response collection means" is a method or apparatus for efficiently collecting and analyzing evaluations and opinions from users.

[0297] This embodiment begins with the user inputting financial information. The user uses a smartphone or other device to input information such as annual income and assets into the system. The device then formats this data appropriately and sends it to the server.

[0298] The server uses a machine learning model to perform a preliminary assessment based on the received information. This model is built using TensorFlow and learns assessment criteria based on historical data, allowing it to quickly evaluate the user's credit risk.

[0299] Based on the preliminary assessment results, the server generates the optimal credit plan for the user. Furthermore, it uses a React Native application to calculate a corresponding repayment forecast and visually present it on the user's terminal interface.

[0300] Based on the information provided, users can select the loan plan that best suits their needs. Upon user request, the server will immediately provide additional information related to financial market trends and plans, guaranteeing continuous support throughout the day.

[0301] As a specific example, when a user applies under the conditions of an annual income of 6 million yen, a loan amount of 25 million yen, and a repayment period of 30 years, the server can create a repayment simulation assuming interest rate fluctuations and present it to the user based on an interest rate increase scenario. At this time, as an example of a prompt sentence using a generative AI model, there is "Generate the most suitable housing loan plan based on the user's annual income and desired amount, and perform a repayment simulation considering interest rate fluctuations." As a result, the user can obtain sufficient information and judgment materials for selecting an appropriate loan plan.

[0302] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0303] Step 1:

[0304] The terminal receives financial-related information (e.g., annual income, loan amount, repayment period) input by the user. This information is converted into JSON format and prepared for transmission to the server. By this conversion, the data has a consistent structure and becomes easier to analyze on the server.

[0305] Step 2:

[0306] The server receives the JSON-format data transmitted from the terminal. This data is divided into respective fields for verification to confirm if there are any deficiencies or irregularities. The verified data is prepared as input to the machine learning model.

[0307] Step 3:

[0308] The server inputs the information into a machine learning model (using TensorFlow) and performs a preliminary review. The model analyzes the input data, evaluates the user's credit risk, and generates a preliminary review result based on the degree of creditworthiness. The output is the user's credit score and the approval status of the preliminary review.

[0309] Step 4:

[0310] The server creates an optimal credit plan and repayment forecast for the user based on the preliminary assessment results. This generation applies a plan creation algorithm and incorporates various loan conditions and market interest rate information. The output of this process is a loan plan including key conditions and a visualized repayment forecast.

[0311] Step 5:

[0312] The server sends the generated credit plan and repayment forecast to the device. The device then presents the information to the user visually through a React Native application. The user can review the plan details and manipulate the provisional repayment plan through an interactive interface.

[0313] Step 6:

[0314] If the user requests further information after reviewing the details, the server searches for financial market trends and relevant educational content, and sends the necessary information to the user's device. This process allows the user to gain a deeper understanding of the loan plan.

[0315] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0316] This invention provides more personalized support by combining a system that provides mortgage-related information and conducts preliminary screening with an emotion engine that recognizes the user's emotions. A specific embodiment is described below.

[0317] First, the user enters housing-related information through an interface on their device. The device formats this information and sends it to the server. The server receives the input information and performs a preliminary assessment using an artificial intelligence model. The preliminary assessment results are then communicated to the user along with a suitable loan plan and repayment simulation.

[0318] This system incorporates an emotion engine that analyzes user input, feedback, and interaction history to assess their emotional state. Based on the emotion engine's results, the server adjusts the tone of information and notifications to match the user's emotions. For example, if the user is feeling anxious, the system will provide more detailed and easily understandable information and offer additional support.

[0319] Furthermore, housing market trends and educational content are individually customized according to the user's interests and preferences and delivered to the user through their device. If the emotion engine detects signs of stress or questions from the user's responses and behavior, the server will provide the user with additional support in real time.

[0320] For example, if a user expresses anxiety about a mortgage, the emotion engine detects that emotion, and the server delivers additional explanatory videos or FAQ sessions to the device. It also highlights a chat link to support staff, allowing users to easily obtain additional information.

[0321] This system operates 24 / 7, continuously collecting user feedback to improve the system. This ensures users always receive appropriate and timely support and enjoy a highly customized mortgage experience.

[0322] The following describes the processing flow.

[0323] Step 1:

[0324] The user uses the terminal to input housing-related information such as their annual income, desired loan amount, and repayment period. The terminal receives this information, formats it, and prepares it for transmission to the server.

[0325] Step 2:

[0326] The server receives the information sent from the terminal and verifies the integrity and completeness of the input data. If the data is appropriate, the server proceeds with further processing and performs a preliminary review using an artificial intelligence model.

[0327] Step 3:

[0328] The server performs a preliminary review using an artificial intelligence model and generates results. These results include a preliminary assessment of the likelihood of loan approval and related risk assessments.

[0329] Step 4:

[0330] Based on the generated preliminary screening results, the server creates an optimal loan plan and repayment simulation for the user. This includes options for fixed and variable interest rates, as well as simulations for different repayment periods.

[0331] Step 5:

[0332] The server uses an emotion engine to analyze the user's emotional state from past inputs and feedback. The emotion engine evaluates the user's stress level, anxiety, level of interest, etc., and instructs the server on the most appropriate response.

[0333] Step 6:

[0334] Based on the analysis results of the emotion engine, the server adjusts the tone and content of the information presented on the device. For example, if anxiety is detected, the server provides the device with additional information, including explanations that emphasize the details and benefits of the loan, as well as FAQ links.

[0335] Step 7:

[0336] Users receive preliminary screening results, loan plans, and supplementary information from the server via their device. Emotionally responsive communication allows users to confidently make decisions about proceeding to the next step.

[0337] Step 8:

[0338] Users can input feedback into their devices as needed and send it to the server via their devices. The server collects this feedback and uses it to further improve the system.

[0339] Step 9:

[0340] Based on the collected feedback and sentiment data, the server optimizes overall system service and individual customizations. The system is then prepared to provide more precise support the next time the user accesses it.

[0341] (Example 2)

[0342] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0343] Traditional information systems for mortgages and other financial products often provide a uniform response without considering the individual emotional state of each user. As a result, users often fail to receive the optimal information and support tailored to their specific circumstances and needs. Furthermore, systems that do not properly utilize feedback can lead to delays in service improvement and decreased user satisfaction.

[0344] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0345] In this invention, the server includes means for receiving financial data input from the user, means for using a machine learning model to analyze the received data and perform a preliminary review, and means for analyzing the user's emotional state and adjusting the tone of information provided. This enables personalized information provision tailored to each user's emotional state and needs, and continuous improvement of the service through the use of appropriate feedback.

[0346] A "user" refers to a person who uses the system to input financial data and receives information and support.

[0347] "Financial data" refers to information related to mortgages and financial services, such as property prices, down payments, and income information entered by the user.

[0348] "Means of receiving" refers to the devices and processes used to send data entered by the user from the terminal to the server, and for the server to receive that data.

[0349] A "machine learning model that analyzes and performs preliminary screening" refers to a learning program that runs on a server, analyzes received data, and provisionally evaluates a financial plan suitable for the user.

[0350] "Emotional analysis means" refers to algorithms and devices that analyze the emotional state based on user input and feedback, and adjust the method of information provision accordingly.

[0351] "Information distribution means" refers to communication methods used to provide users with appropriate information based on sentiment analysis results and preliminary screening results.

[0352] "Feedback collection methods" refer to the methods and processes used to obtain opinions and evaluations from users and utilize them for system improvement.

[0353] A "server" refers to a central computer system that processes data from users and generates and distributes information.

[0354] This invention provides a system that allows users to access mortgages and other financial services more intuitively and individually. The system aims to provide personalized information by taking into account the user's emotional state.

[0355] Users enter detailed mortgage-related data through their devices. This includes property price, down payment, annual income, and other financial conditions, entered via the system interface. The device formats this data and sends it to the server. The protocol used by the device is typically secure HTTPS communication.

[0356] The server utilizes generative AI models to analyze the received data. Machine learning platforms such as TensorFlow and PyTorch are used for this analysis. The model presents the user with a preliminary loan plan and provides a repayment simulation tailored to the user's financial situation.

[0357] Furthermore, the system integrates an emotion analysis engine that evaluates the user's emotional state based on their input and feedback. Natural language processing libraries such as NLTK and DeepMoji are used for this purpose. The analysis results are then used to adjust the tone of information and notifications provided to the user.

[0358] For example, if a user types "I'm worried about rising interest rates," the emotion engine detects the anxiety, and the server provides additional easy-to-understand explanatory videos and FAQs. At this point, the user can easily access additional support through a chat link highlighted on their device.

[0359] Examples of prompts for a generative AI model include concise and specific requests such as, "Please provide additional information about concerns regarding mortgages."

[0360] This system operates 24 hours a day, systematically collecting user feedback, which is then analyzed and stored on the server. This feedback is used to improve the system, enabling us to provide optimal support to users over the long term.

[0361] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0362] Step 1:

[0363] The user enters information about their mortgage into the terminal's input interface. This information includes financial details such as the property price, down payment, and annual income. The terminal receives this information and converts it into a data format, such as JSON. The converted data is then sent to the server.

[0364] Step 2:

[0365] The server receives data sent from the terminal. The received data is analyzed using a machine learning model. Frameworks such as TensorFlow and PyTorch are used for this analysis. The purpose of the analysis is to pre-screen a loan plan suitable for the user based on the input data and generate a repayment simulation based on that plan. The analysis results are output as a loan plan and simulation data.

[0366] Step 3:

[0367] The server provides feedback to the user based on the generated loan plan and simulation data. During this process, it monitors the user's emotional state using sentiment analysis tools. Specifically, sentiment analysis is performed using tools such as NLTK and DeepMoji, based on the user's input and additional feedback received previously. The analysis results are used as input to adjust the tone and content of the information provided.

[0368] Step 4:

[0369] The device receives feedback and analysis results sent from the server. After making adjustments based on the user's emotional state, it displays details of the loan plan and the results of the repayment simulation. The user can then decide on further actions based on this information. Links to additional materials and FAQs are displayed as needed to aid the user's understanding.

[0370] Step 5:

[0371] When a user enters feedback or asks additional questions, the device sends it to the server. The server collects this feedback and stores it in a database for future system improvements. The feedback helps improve the user experience and the accuracy of the generated AI model.

[0372] (Application Example 2)

[0373] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0374] There is a need to alleviate the anxiety and stress experienced by mortgage borrowers and to provide more personalized loan information and support. However, conventional systems struggle to provide flexible support that responds to users' emotional states. Therefore, the challenge is to provide an environment where users can manage their mortgages with peace of mind.

[0375] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0376] In this invention, the server includes means for receiving housing-related information input by the user, means for using a machine learning model that analyzes the received information and performs a preliminary review, and means for using an emotion analysis function that analyzes the user's input data and dialogue history and evaluates their emotional state. This makes it possible to provide information and support that is tailored to the user's emotions.

[0377] A "user" is someone who uses the system to receive housing-related information and loan support.

[0378] "Means for receiving housing-related information" refers to a function that incorporates information related to home purchases and loans entered by users into the system.

[0379] A "machine learning model" is a model based on artificial intelligence technology that is used to analyze user input information and perform preliminary screening.

[0380] The "emotion analysis function" is a feature that analyzes user input data and conversation history to evaluate the user's emotional state.

[0381] "Means for evaluating emotional state" refers to methods used by a system to determine a user's emotions and adjust the level of support provided.

[0382] "Means of adjusting the tone of information provision and notifications" refers to a function that changes the way information is presented and the content of notifications based on the user's emotional state.

[0383] "Means of providing 24-hour customer support" refers to means of responding to user inquiries at any time and providing necessary information and support.

[0384] "Means of providing support information" refers to means of presenting appropriate support information in response to the anxieties and questions that users may have.

[0385] This invention develops a system that incorporates sentiment analysis capabilities to provide personalized support to mortgage borrowers. The system has a server-terminal and user-centric structure.

[0386] The server includes the following steps: First, the user inputs information about their home via a terminal. The terminal converts the input information into a digital format and sends it to the server. Next, the server uses a machine learning model to analyze the input information and conduct a preliminary assessment of the mortgage. At this time, the system also implements a function that uses Google Cloud AI's natural language API to perform sentiment analysis on the user's text data and evaluate their emotional state. Based on the emotional state, the tone of information provided and notifications is adjusted, and the user is provided with customized loan plans and support information.

[0387] The application is designed for smartphones, with the frontend developed using React Native and the backend using Ruby on Rails. This structure allows users to manage their mortgage information intuitively and efficiently.

[0388] Through the process described above, the sentiment analysis function detects the user's level of anxiety based on text entered by the user, such as "I'm worried because I've been behind on payments lately." In this case, the server provides specific advice and additional support information to alleviate the anxiety. Additionally, a contact link to support staff is put into standby mode, allowing the user to contact them immediately.

[0389] Examples of prompt statements used for generative AI models are as follows:

[0390] "Analyze the user's sentiment from the following text and determine if they need support: 'I'm worried because I've been behind on payments lately.'"

[0391] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0392] Step 1:

[0393] The terminal provides a user interface for entering mortgage information. The user enters information such as the desired purchase price, annual income, and desired loan term. This information is converted into a digital format and sent to the server.

[0394] Step 2:

[0395] The server receives housing-related information from the terminal. Based on the received information, it performs a preliminary assessment using a machine learning model. This generates a preliminary loan assessment based on the user's eligibility and conditions.

[0396] Step 3:

[0397] The server uses sentiment analysis functionality to evaluate the user's emotional state. It utilizes additional data and text input provided by the user, leveraging Google Cloud AI's natural language API to perform sentiment analysis. This process extracts emotional information such as the user's anxiety and worries.

[0398] Step 4:

[0399] The server integrates the preliminary assessment results and sentiment analysis results, and adjusts the tone of information and notifications accordingly. For example, if the user is feeling anxious, detailed and concise support information and video guides are provided. This information is sent to the device and displayed to the user.

[0400] Step 5:

[0401] The terminal displays information and support details sent from the server to the user. If necessary, a contact link to support staff is highlighted, allowing the user to easily request additional support.

[0402] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0403] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0404] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0405] [Third Embodiment]

[0406] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0407] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0408] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0409] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0410] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0411] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0412] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0413] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0414] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0415] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0416] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0417] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0418] This invention is a system for streamlining mortgage-related procedures and improving customer convenience, and its main components are a user, a terminal, and a server. Specific embodiments thereof are described below.

[0419] First, the user uses a terminal to input housing-related information such as annual income, desired loan amount, and repayment period. The terminal converts this data into the appropriate format and sends it to the server. The server receives the data sent from the terminal and verifies its formal accuracy. Subsequently, it provides the correctly received information to an artificial intelligence model for a preliminary assessment.

[0420] The artificial intelligence model analyzes the input information and generates a preliminary screening result based on existing screening criteria. The server interprets the obtained result and sends it to the user's terminal. For users who pass the preliminary screening, the server uses the generated AI model to create and provide an optimal loan plan and repayment simulation.

[0421] In this system, when users want to know more or request additional support, the server provides detailed information on housing market trends and loan-related terminology as a means of providing information. This helps users make more effective decisions regarding repayment plans and loan selection.

[0422] Furthermore, educational content regarding fluctuations in the housing market and new loan plans is selected from the server and delivered to the user's device. This allows users to acquire the necessary knowledge and make more informed decisions.

[0423] Furthermore, feedback from users is collected and used to improve the system. This allows the system of the present invention to flexibly respond to user needs and be continuously optimized. In this way, the system provides users with 24 / 7 customer support, enabling faster and more efficient service.

[0424] As a concrete example, consider a case where a user applies for a loan with an annual income of 6 million yen, a desired loan amount of 25 million yen, and a repayment period of 30 years. This information is entered into a terminal and sent to the server. The server then performs a preliminary assessment using an artificial intelligence model and provides a suitable loan plan along with the results. The user can then make a final decision based on this information.

[0425] The following describes the processing flow.

[0426] Step 1:

[0427] The user uses the terminal to input necessary housing-related information such as annual income, desired loan amount, and repayment period. The terminal then formats this information and makes it ready for transmission.

[0428] Step 2:

[0429] The terminal sends user input information to the server. The server receives the data and checks the format and required fields. If there are any problems, it generates an error message and returns it to the terminal.

[0430] Step 3:

[0431] The server passes correctly formatted information to the generating AI model and requests a preliminary review. The generating AI model analyzes the data and evaluates whether the user's loan application is eligible for pre-approval.

[0432] Step 4:

[0433] The generating AI model returns the preliminary review results to the server. The server interprets the results and sends them to the user's device in a format that is easy for the user to understand.

[0434] Step 5:

[0435] Based on the preliminary screening results, the server requests an AI model to generate the optimal loan plan and repayment simulation for the user.

[0436] Step 6:

[0437] The user receives loan plans and simulations provided by the server. If they want more detailed information or other options, they can submit additional questions from their device.

[0438] Step 7:

[0439] The server receives additional requests from users, prepares appropriate information using an AI model, and sends it back to the terminal. This information includes data on educational content and market trends.

[0440] Step 8:

[0441] Users review the provided information and make their final decisions. They can also send feedback to the server via their device.

[0442] Step 9:

[0443] The server collects user feedback and uses it to improve the system. This allows the system to be continuously optimized to meet user needs.

[0444] (Example 1)

[0445] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0446] Traditional financial procedures, including those for mortgages, have often been inefficient in terms of complex processes and information provision, placing a significant burden on users. In particular, there is a need for rapid and accurate information processing and the presentation of financial plans tailored to individual users. The challenge lies in resolving this issue and improving user convenience and efficiency.

[0447] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0448] In this invention, the server includes a device for receiving financial information input from a user, a device that uses an intelligent model to analyze the received information and perform a preliminary evaluation, and a device that selects and provides educational information on market trends to the user. This enables the user to efficiently receive a preliminary evaluation and be presented with an appropriate financial plan.

[0449] "Financial information" refers to all economic data related to loans and asset management, specifically including annual income, desired loan amount, and repayment period.

[0450] A "data structure" is an organized form used to efficiently manage and manipulate information, and is intended to maintain the consistency and integrity of that information.

[0451] An "intelligent model" refers to an algorithm or program designed to learn from past data and experience, and to analyze and make judgments based on the information it receives.

[0452] A "financial plan" provides optimized loan and investment strategies based on the user's specific financial situation and goals.

[0453] A "computational model" refers to a mathematical framework used to simulate specific repayment plans and risk assessments in various financial scenarios.

[0454] An "information distribution device" is a system or program that provides users with timely and relevant knowledge and data.

[0455] A "feedback collection device" refers to a system used to collect user feedback and opinions and utilize them to improve the system.

[0456] This invention relates to a system that streamlines financial procedures and improves user convenience. It mainly consists of three elements: a server, a terminal, and a user.

[0457] The terminal provides an interface for users to input financial information. On the terminal, users input information such as annual income, desired loan amount, and repayment period, and this information is immediately converted into a data structure. Data processing libraries, such as those using Python, are often used for data formatting.

[0458] The server analyzes the received information using an intelligent model. This intelligent model typically employs machine learning frameworks such as TensorFlow or PyTorch, performing preliminary evaluations based on historical data. The server also has a function to select and provide educational information on market trends to users. This educational information is regularly updated by the server to improve users' knowledge and support more appropriate financial decisions.

[0459] For example, when a user inputs information such as "annual income of 6 million yen, desired loan amount of 25 million yen, repayment period of 30 years" into their device, this data is sent to an intelligent model by the server. The server analyzes this data and sends a preliminary evaluation result, such as "a 35-year repayment plan is optimal," back to the user's device.

[0460] As an example of a prompt, you can instruct the generating AI model in the following format: "User A has an annual income of 6 million yen, desires a loan amount of 25 million yen, and wants a repayment period of 30 years. Please conduct a preliminary assessment based on this information and provide the results."

[0461] These processes allow users to receive appropriate financial plans quickly and make efficient decisions. This system implementation enables 24 / 7 customer support and supports users' future financial activities.

[0462] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0463] Step 1:

[0464] The user enters financial information using a terminal. The terminal receives information such as annual income, desired loan amount, and repayment period, and converts it into a data structure. This conversion formats the input into JSON format, preparing it for the next processing step.

[0465] Step 2:

[0466] The terminal sends formatted financial data to the server. The server parses the received JSON data and formally verifies that all necessary items are present. Once verification is complete, the data proceeds to the preliminary evaluation process.

[0467] Step 3:

[0468] The server provides the received data to an intelligent model and performs a preliminary review. The intelligent model uses machine learning frameworks such as TensorFlow or PyTorch to analyze historical data and generate a risk assessment and loan plan based on the input information. This then outputs the preliminary review results.

[0469] Step 4:

[0470] The server converts the generated preliminary assessment results into a format that is easy for the user to understand. The converted data is then sent to the user's device along with the repayment plan and applicable conditions. This allows the user to understand the plan that is best suited to them.

[0471] Step 5:

[0472] The user reviews the preliminary review results received through the device. The device provides an interface for the user to send requests to the server if they require more detailed information or additional support. This allows for further information retrieval and feedback submission.

[0473] (Application Example 1)

[0474] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0475] Modern borrowers demand fast, transparent, and personalized credit plans. However, the procedures in the traditional financial system are cumbersome, making it difficult for users to easily find a plan that suits them. Furthermore, there is a lack of support for understanding market trends and developing repayment plans that adapt to changes.

[0476] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0477] In this invention, the server includes means for using a machine learning model to analyze received information and perform a preliminary assessment, means for generating a credit provision plan and repayment forecast suitable for the user based on the generated preliminary assessment results, and means for providing information in response to the user's requests. This allows the user to quickly access a credit provision plan suitable for them and to receive repayment forecasts based on financial market trends.

[0478] "Financial information" refers to data about a user's economic situation, such as annual income, assets, and liabilities, which is necessary when a user applies for credit.

[0479] A "machine learning model" is a collection of algorithms that learn patterns and relationships based on past data and use them to make predictions and classifications on new data.

[0480] A "credit provision plan" is a proposal outlining loan or financing terms and repayment schedules optimized according to the user's financial situation and needs.

[0481] "Repayment forecast" is an estimate of future repayment amounts and repayment periods based on the user's credit provision plan.

[0482] "Information provision means" refers to a device or program for collecting, analyzing, and presenting appropriate information in response to a user's request.

[0483] "Continuous support throughout the day" refers to a service delivery model that provides constant support to users without time constraints.

[0484] An "interface means" is a visual or manipulative component that enables the input and output of information between a user and a system.

[0485] "Financial market trends" refer to the movements in the market that are influenced by changes in the economic environment, policies, interest rates, exchange rates, and other factors.

[0486] A "response collection means" is a method or apparatus for efficiently collecting and analyzing evaluations and opinions from users.

[0487] This embodiment begins with the user inputting financial information. The user uses a smartphone or other device to input information such as annual income and assets into the system. The device then formats this data appropriately and sends it to the server.

[0488] The server uses a machine learning model to perform a preliminary assessment based on the received information. This model is built using TensorFlow and learns assessment criteria based on historical data, allowing it to quickly evaluate the user's credit risk.

[0489] Based on the preliminary assessment results, the server generates the optimal credit plan for the user. Furthermore, it uses a React Native application to calculate a corresponding repayment forecast and visually present it on the user's terminal interface.

[0490] Based on the information provided, users can select the loan plan that best suits their needs. Upon user request, the server will immediately provide additional information related to financial market trends and plans, guaranteeing continuous support throughout the day.

[0491] For example, if a user applies with an annual income of 6 million yen, a desired loan amount of 25 million yen, and a repayment period of 30 years, the server can create a repayment simulation that takes interest rate fluctuations into account and present it to the user based on an interest rate increase scenario. In this case, an example of a prompt message using the generated AI model would be, "Please generate the most suitable mortgage plan based on the user's annual income and desired amount, and perform a repayment simulation that takes interest rate fluctuations into account." This allows the user to obtain sufficient information and criteria to make an informed decision about selecting an appropriate loan plan.

[0492] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0493] Step 1:

[0494] The terminal receives financial information entered by the user (e.g., annual income, desired loan amount, repayment period). This information is converted to JSON format and prepared for transmission to the server. This conversion ensures a consistent data structure, making it easier to analyze on the server.

[0495] Step 2:

[0496] The server receives data in JSON format sent from the terminal. This data is then validated, field by field, to check for missing or invalid data. Once validated, the data is prepared as input for a machine learning model.

[0497] Step 3:

[0498] The server inputs information into a machine learning model (using TensorFlow) and performs a preliminary screening. The model analyzes the input data, assesses the user's credit risk, and generates a preliminary screening result based on their creditworthiness. The output is the user's credit score and whether or not they passed the preliminary screening.

[0499] Step 4:

[0500] The server creates an optimal credit plan and repayment forecast for the user based on the preliminary assessment results. This generation applies a plan creation algorithm and incorporates various loan conditions and market interest rate information. The output of this process is a loan plan including key conditions and a visualized repayment forecast.

[0501] Step 5:

[0502] The server sends the generated credit plan and repayment forecast to the device. The device then presents the information to the user visually through a React Native application. The user can review the plan details and manipulate the provisional repayment plan through an interactive interface.

[0503] Step 6:

[0504] If the user requests further information after reviewing the details, the server searches for financial market trends and relevant educational content, and sends the necessary information to the user's device. This process allows the user to gain a deeper understanding of the loan plan.

[0505] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0506] This invention provides more personalized support by combining a system that provides mortgage-related information and conducts preliminary screening with an emotion engine that recognizes the user's emotions. A specific embodiment is described below.

[0507] First, the user enters housing-related information through an interface on their device. The device formats this information and sends it to the server. The server receives the input information and performs a preliminary assessment using an artificial intelligence model. The preliminary assessment results are then communicated to the user along with a suitable loan plan and repayment simulation.

[0508] This system incorporates an emotion engine that analyzes user input, feedback, and interaction history to assess their emotional state. Based on the emotion engine's results, the server adjusts the tone of information and notifications to match the user's emotions. For example, if the user is feeling anxious, the system will provide more detailed and easily understandable information and offer additional support.

[0509] Furthermore, housing market trends and educational content are individually customized according to the user's interests and preferences and delivered to the user through their device. If the emotion engine detects signs of stress or questions from the user's responses and behavior, the server will provide the user with additional support in real time.

[0510] For example, if a user expresses anxiety about a mortgage, the emotion engine detects that emotion, and the server delivers additional explanatory videos or FAQ sessions to the device. It also highlights a chat link to support staff, allowing users to easily obtain additional information.

[0511] This system operates 24 / 7, continuously collecting user feedback to improve the system. This ensures users always receive appropriate and timely support and enjoy a highly customized mortgage experience.

[0512] The following describes the processing flow.

[0513] Step 1:

[0514] The user uses the terminal to input housing-related information such as their annual income, desired loan amount, and repayment period. The terminal receives this information, formats it, and prepares it for transmission to the server.

[0515] Step 2:

[0516] The server receives the information sent from the terminal and verifies the integrity and completeness of the input data. If the data is appropriate, the server proceeds with further processing and performs a preliminary review using an artificial intelligence model.

[0517] Step 3:

[0518] The server performs a preliminary review using an artificial intelligence model and generates results. These results include a preliminary assessment of the likelihood of loan approval and related risk assessments.

[0519] Step 4:

[0520] Based on the generated preliminary screening results, the server creates an optimal loan plan and repayment simulation for the user. This includes options for fixed and variable interest rates, as well as simulations for different repayment periods.

[0521] Step 5:

[0522] The server uses an emotion engine to analyze the user's emotional state from past inputs and feedback. The emotion engine evaluates the user's stress level, anxiety, level of interest, etc., and instructs the server on the most appropriate response.

[0523] Step 6:

[0524] Based on the analysis results of the emotion engine, the server adjusts the tone and content of the information presented on the device. For example, if anxiety is detected, the server provides the device with additional information, including explanations that emphasize the details and benefits of the loan, as well as FAQ links.

[0525] Step 7:

[0526] Users receive preliminary screening results, loan plans, and supplementary information from the server via their device. Emotionally responsive communication allows users to confidently make decisions about proceeding to the next step.

[0527] Step 8:

[0528] Users can input feedback into their devices as needed and send it to the server via their devices. The server collects this feedback and uses it to further improve the system.

[0529] Step 9:

[0530] Based on the collected feedback and sentiment data, the server optimizes overall system service and individual customizations. The system is then prepared to provide more precise support the next time the user accesses it.

[0531] (Example 2)

[0532] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0533] Traditional information systems for mortgages and other financial products often provide a uniform response without considering the individual emotional state of each user. As a result, users often fail to receive the optimal information and support tailored to their specific circumstances and needs. Furthermore, systems that do not properly utilize feedback can lead to delays in service improvement and decreased user satisfaction.

[0534] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0535] In this invention, the server includes means for receiving financial data input from the user, means for using a machine learning model to analyze the received data and perform a preliminary review, and means for analyzing the user's emotional state and adjusting the tone of information provided. This enables personalized information provision tailored to each user's emotional state and needs, and continuous improvement of the service through the use of appropriate feedback.

[0536] A "user" refers to a person who uses the system to input financial data and receives information and support.

[0537] "Financial data" refers to information related to mortgages and financial services, such as property prices, down payments, and income information entered by the user.

[0538] "Means of receiving" refers to the devices and processes used to send data entered by the user from the terminal to the server, and for the server to receive that data.

[0539] A "machine learning model that analyzes and performs preliminary screening" refers to a learning program that runs on a server, analyzes received data, and provisionally evaluates a financial plan suitable for the user.

[0540] "Emotional analysis means" refers to algorithms and devices that analyze the emotional state based on user input and feedback, and adjust the method of information provision accordingly.

[0541] "Information distribution means" refers to communication methods used to provide users with appropriate information based on sentiment analysis results and preliminary screening results.

[0542] "Feedback collection methods" refer to the methods and processes used to obtain opinions and evaluations from users and utilize them for system improvement.

[0543] A "server" refers to a central computer system that processes data from users and generates and distributes information.

[0544] This invention provides a system that allows users to access mortgages and other financial services more intuitively and individually. The system aims to provide personalized information by taking into account the user's emotional state.

[0545] Users enter detailed mortgage-related data through their devices. This includes property price, down payment, annual income, and other financial conditions, entered via the system interface. The device formats this data and sends it to the server. The protocol used by the device is typically secure HTTPS communication.

[0546] The server utilizes generative AI models to analyze the received data. Machine learning platforms such as TensorFlow and PyTorch are used for this analysis. The model presents the user with a preliminary loan plan and provides a repayment simulation tailored to the user's financial situation.

[0547] Furthermore, the system integrates an emotion analysis engine that evaluates the user's emotional state based on their input and feedback. Natural language processing libraries such as NLTK and DeepMoji are used for this purpose. The analysis results are then used to adjust the tone of information and notifications provided to the user.

[0548] For example, if a user types "I'm worried about rising interest rates," the emotion engine detects the anxiety, and the server provides additional easy-to-understand explanatory videos and FAQs. At this point, the user can easily access additional support through a chat link highlighted on their device.

[0549] Examples of prompts for a generative AI model include concise and specific requests such as, "Please provide additional information about concerns regarding mortgages."

[0550] This system operates 24 hours a day, systematically collecting user feedback, which is then analyzed and stored on the server. This feedback is used to improve the system, enabling us to provide optimal support to users over the long term.

[0551] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0552] Step 1:

[0553] The user enters information about their mortgage into the terminal's input interface. This information includes financial details such as the property price, down payment, and annual income. The terminal receives this information and converts it into a data format, such as JSON. The converted data is then sent to the server.

[0554] Step 2:

[0555] The server receives data sent from the terminal. The received data is analyzed using a machine learning model. Frameworks such as TensorFlow and PyTorch are used for this analysis. The purpose of the analysis is to pre-screen a loan plan suitable for the user based on the input data and generate a repayment simulation based on that plan. The analysis results are output as a loan plan and simulation data.

[0556] Step 3:

[0557] The server provides feedback to the user based on the generated loan plan and simulation data. During this process, it monitors the user's emotional state using sentiment analysis tools. Specifically, sentiment analysis is performed using tools such as NLTK and DeepMoji, based on the user's input and additional feedback received previously. The analysis results are used as input to adjust the tone and content of the information provided.

[0558] Step 4:

[0559] The device receives feedback and analysis results sent from the server. After making adjustments based on the user's emotional state, it displays details of the loan plan and the results of the repayment simulation. The user can then decide on further actions based on this information. Links to additional materials and FAQs are displayed as needed to aid the user's understanding.

[0560] Step 5:

[0561] When a user enters feedback or asks additional questions, the device sends it to the server. The server collects this feedback and stores it in a database for future system improvements. The feedback helps improve the user experience and the accuracy of the generated AI model.

[0562] (Application Example 2)

[0563] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0564] There is a need to alleviate the anxiety and stress experienced by mortgage borrowers and to provide more personalized loan information and support. However, conventional systems struggle to provide flexible support that responds to users' emotional states. Therefore, the challenge is to provide an environment where users can manage their mortgages with peace of mind.

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

[0566] In this invention, the server includes means for receiving housing-related information input by the user, means for using a machine learning model that analyzes the received information and performs a preliminary review, and means for using an emotion analysis function that analyzes the user's input data and dialogue history and evaluates their emotional state. This makes it possible to provide information and support that is tailored to the user's emotions.

[0567] A "user" is someone who uses the system to receive housing-related information and loan support.

[0568] "Means for receiving housing-related information" refers to a function that incorporates information related to home purchases and loans entered by users into the system.

[0569] A "machine learning model" is a model based on artificial intelligence technology that is used to analyze user input information and perform preliminary screening.

[0570] The "emotion analysis function" is a feature that analyzes user input data and conversation history to evaluate the user's emotional state.

[0571] "Means for evaluating emotional state" refers to methods used by a system to determine a user's emotions and adjust the level of support provided.

[0572] "Means of adjusting the tone of information provision and notifications" refers to a function that changes the way information is presented and the content of notifications based on the user's emotional state.

[0573] "Means of providing 24-hour customer support" refers to means of responding to user inquiries at any time and providing necessary information and support.

[0574] "Means of providing support information" refers to means of presenting appropriate support information in response to the anxieties and questions that users may have.

[0575] This invention develops a system that incorporates sentiment analysis capabilities to provide personalized support to mortgage borrowers. The system has a server-terminal and user-centric structure.

[0576] The server includes the following steps: First, the user inputs information about their home via a terminal. The terminal converts the input information into a digital format and sends it to the server. Next, the server uses a machine learning model to analyze the input information and conduct a preliminary assessment of the mortgage. At this time, the system also implements a function that uses Google Cloud AI's natural language API to perform sentiment analysis on the user's text data and evaluate their emotional state. Based on the emotional state, the tone of information provided and notifications is adjusted, and the user is provided with customized loan plans and support information.

[0577] The application is designed for smartphones, with the frontend developed using React Native and the backend using Ruby on Rails. This structure allows users to manage their mortgage information intuitively and efficiently.

[0578] Through the process described above, the sentiment analysis function detects the user's level of anxiety based on text entered by the user, such as "I'm worried because I've been behind on payments lately." In this case, the server provides specific advice and additional support information to alleviate the anxiety. Additionally, a contact link to support staff is put into standby mode, allowing the user to contact them immediately.

[0579] Examples of prompt statements used for generative AI models are as follows:

[0580] "Analyze the user's sentiment from the following text and determine if they need support: 'I'm worried because I've been behind on payments lately.'"

[0581] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0582] Step 1:

[0583] The terminal provides a user interface for entering mortgage information. The user enters information such as the desired purchase price, annual income, and desired loan term. This information is converted into a digital format and sent to the server.

[0584] Step 2:

[0585] The server receives housing-related information from the terminal. Based on the received information, it performs a preliminary assessment using a machine learning model. This generates a preliminary loan assessment based on the user's eligibility and conditions.

[0586] Step 3:

[0587] The server uses sentiment analysis functionality to evaluate the user's emotional state. It utilizes additional data and text input provided by the user, leveraging Google Cloud AI's natural language API to perform sentiment analysis. This process extracts emotional information such as the user's anxiety and worries.

[0588] Step 4:

[0589] The server integrates the preliminary assessment results and sentiment analysis results, and adjusts the tone of information and notifications accordingly. For example, if the user is feeling anxious, detailed and concise support information and video guides are provided. This information is sent to the device and displayed to the user.

[0590] Step 5:

[0591] The terminal displays information and support details sent from the server to the user. If necessary, a contact link to support staff is highlighted, allowing the user to easily request additional support.

[0592] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0593] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0594] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0595] [Fourth Embodiment]

[0596] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0597] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0598] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0599] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0600] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0601] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0602] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0603] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0604] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0605] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0606] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0607] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0608] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0609] This invention is a system for streamlining mortgage-related procedures and improving customer convenience, and its main components are a user, a terminal, and a server. Specific embodiments thereof are described below.

[0610] First, the user uses a terminal to input housing-related information such as annual income, desired loan amount, and repayment period. The terminal converts this data into the appropriate format and sends it to the server. The server receives the data sent from the terminal and verifies its formal accuracy. Subsequently, it provides the correctly received information to an artificial intelligence model for a preliminary assessment.

[0611] The artificial intelligence model analyzes the input information and generates a preliminary screening result based on existing screening criteria. The server interprets the obtained result and sends it to the user's terminal. For users who pass the preliminary screening, the server uses the generated AI model to create and provide an optimal loan plan and repayment simulation.

[0612] In this system, when users want to know more or request additional support, the server provides detailed information on housing market trends and loan-related terminology as a means of providing information. This helps users make more effective decisions regarding repayment plans and loan selection.

[0613] Furthermore, educational content regarding fluctuations in the housing market and new loan plans is selected from the server and delivered to the user's device. This allows users to acquire the necessary knowledge and make more informed decisions.

[0614] Furthermore, feedback from users is collected and used to improve the system. This allows the system of the present invention to flexibly respond to user needs and be continuously optimized. In this way, the system provides users with 24 / 7 customer support, enabling faster and more efficient service.

[0615] As a concrete example, consider a case where a user applies for a loan with an annual income of 6 million yen, a desired loan amount of 25 million yen, and a repayment period of 30 years. This information is entered into a terminal and sent to the server. The server then performs a preliminary assessment using an artificial intelligence model and provides a suitable loan plan along with the results. The user can then make a final decision based on this information.

[0616] The following describes the processing flow.

[0617] Step 1:

[0618] The user uses the terminal to input necessary housing-related information such as annual income, desired loan amount, and repayment period. The terminal then formats this information and makes it ready for transmission.

[0619] Step 2:

[0620] The terminal sends user input information to the server. The server receives the data and checks the format and required fields. If there are any problems, it generates an error message and returns it to the terminal.

[0621] Step 3:

[0622] The server passes correctly formatted information to the generating AI model and requests a preliminary review. The generating AI model analyzes the data and evaluates whether the user's loan application is eligible for pre-approval.

[0623] Step 4:

[0624] The generating AI model returns the preliminary review results to the server. The server interprets the results and sends them to the user's device in a format that is easy for the user to understand.

[0625] Step 5:

[0626] Based on the preliminary screening results, the server requests an AI model to generate the optimal loan plan and repayment simulation for the user.

[0627] Step 6:

[0628] The user receives loan plans and simulations provided by the server. If they want more detailed information or other options, they can submit additional questions from their device.

[0629] Step 7:

[0630] The server receives additional requests from users, prepares appropriate information using an AI model, and sends it back to the terminal. This information includes data on educational content and market trends.

[0631] Step 8:

[0632] Users review the provided information and make their final decisions. They can also send feedback to the server via their device.

[0633] Step 9:

[0634] The server collects user feedback and uses it to improve the system. This allows the system to be continuously optimized to meet user needs.

[0635] (Example 1)

[0636] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0637] Traditional financial procedures, including those for mortgages, have often been inefficient in terms of complex processes and information provision, placing a significant burden on users. In particular, there is a need for rapid and accurate information processing and the presentation of financial plans tailored to individual users. The challenge lies in resolving this issue and improving user convenience and efficiency.

[0638] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0639] In this invention, the server includes a device for receiving financial information input from a user, a device that uses an intelligent model to analyze the received information and perform a preliminary evaluation, and a device that selects and provides educational information on market trends to the user. This enables the user to efficiently receive a preliminary evaluation and be presented with an appropriate financial plan.

[0640] "Financial information" refers to all economic data related to loans and asset management, specifically including annual income, desired loan amount, and repayment period.

[0641] A "data structure" is an organized form used to efficiently manage and manipulate information, and is intended to maintain the consistency and integrity of that information.

[0642] An "intelligent model" refers to an algorithm or program designed to learn from past data and experience, and to analyze and make judgments based on the information it receives.

[0643] A "financial plan" provides optimized loan and investment strategies based on the user's specific financial situation and goals.

[0644] A "computational model" refers to a mathematical framework used to simulate specific repayment plans and risk assessments in various financial scenarios.

[0645] An "information distribution device" is a system or program that provides users with timely and relevant knowledge and data.

[0646] A "feedback collection device" refers to a system used to collect user feedback and opinions and utilize them to improve the system.

[0647] This invention relates to a system that streamlines financial procedures and improves user convenience. It mainly consists of three elements: a server, a terminal, and a user.

[0648] The terminal provides an interface for users to input financial information. On the terminal, users input information such as annual income, desired loan amount, and repayment period, and this information is immediately converted into a data structure. Data processing libraries, such as those using Python, are often used for data formatting.

[0649] The server analyzes the received information using an intelligent model. This intelligent model typically employs machine learning frameworks such as TensorFlow or PyTorch, performing preliminary evaluations based on historical data. The server also has a function to select and provide educational information on market trends to users. This educational information is regularly updated by the server to improve users' knowledge and support more appropriate financial decisions.

[0650] For example, when a user inputs information such as "annual income of 6 million yen, desired loan amount of 25 million yen, repayment period of 30 years" into their device, this data is sent to an intelligent model by the server. The server analyzes this data and sends a preliminary evaluation result, such as "a 35-year repayment plan is optimal," back to the user's device.

[0651] As an example of a prompt, you can instruct the generating AI model in the following format: "User A has an annual income of 6 million yen, desires a loan amount of 25 million yen, and wants a repayment period of 30 years. Please conduct a preliminary assessment based on this information and provide the results."

[0652] These processes allow users to receive appropriate financial plans quickly and make efficient decisions. This system implementation enables 24 / 7 customer support and supports users' future financial activities.

[0653] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0654] Step 1:

[0655] The user enters financial information using a terminal. The terminal receives information such as annual income, desired loan amount, and repayment period, and converts it into a data structure. This conversion formats the input into JSON format, preparing it for the next processing step.

[0656] Step 2:

[0657] The terminal sends formatted financial data to the server. The server parses the received JSON data and formally verifies that all necessary items are present. Once verification is complete, the data proceeds to the preliminary evaluation process.

[0658] Step 3:

[0659] The server provides the received data to an intelligent model and performs a preliminary review. The intelligent model uses machine learning frameworks such as TensorFlow or PyTorch to analyze historical data and generate a risk assessment and loan plan based on the input information. This then outputs the preliminary review results.

[0660] Step 4:

[0661] The server converts the generated preliminary assessment results into a format that is easy for the user to understand. The converted data is then sent to the user's device along with the repayment plan and applicable conditions. This allows the user to understand the plan that is best suited to them.

[0662] Step 5:

[0663] The user reviews the preliminary review results received through the device. The device provides an interface for the user to send requests to the server if they require more detailed information or additional support. This allows for further information retrieval and feedback submission.

[0664] (Application Example 1)

[0665] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0666] Modern borrowers demand fast, transparent, and personalized credit plans. However, the procedures in the traditional financial system are cumbersome, making it difficult for users to easily find a plan that suits them. Furthermore, there is a lack of support for understanding market trends and developing repayment plans that adapt to changes.

[0667] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0668] In this invention, the server includes means for using a machine learning model to analyze received information and perform a preliminary assessment, means for generating a credit provision plan and repayment forecast suitable for the user based on the generated preliminary assessment results, and means for providing information in response to the user's requests. This allows the user to quickly access a credit provision plan suitable for them and to receive repayment forecasts based on financial market trends.

[0669] "Financial information" refers to data about a user's economic situation, such as annual income, assets, and liabilities, which is necessary when a user applies for credit.

[0670] A "machine learning model" is a collection of algorithms that learn patterns and relationships based on past data and use them to make predictions and classifications on new data.

[0671] A "credit provision plan" is a proposal outlining loan or financing terms and repayment schedules optimized according to the user's financial situation and needs.

[0672] "Repayment forecast" is an estimate of future repayment amounts and repayment periods based on the user's credit provision plan.

[0673] "Information provision means" refers to a device or program for collecting, analyzing, and presenting appropriate information in response to a user's request.

[0674] "Continuous support throughout the day" refers to a service delivery model that provides constant support to users without time constraints.

[0675] An "interface means" is a visual or manipulative component that enables the input and output of information between a user and a system.

[0676] "Financial market trends" refer to the movements in the market that are influenced by changes in the economic environment, policies, interest rates, exchange rates, and other factors.

[0677] A "response collection means" is a method or apparatus for efficiently collecting and analyzing evaluations and opinions from users.

[0678] This embodiment begins with the user inputting financial information. The user uses a smartphone or other device to input information such as annual income and assets into the system. The device then formats this data appropriately and sends it to the server.

[0679] The server uses a machine learning model to perform a preliminary assessment based on the received information. This model is built using TensorFlow and learns assessment criteria based on historical data, allowing it to quickly evaluate the user's credit risk.

[0680] Based on the preliminary assessment results, the server generates the optimal credit plan for the user. Furthermore, it uses a React Native application to calculate a corresponding repayment forecast and visually present it on the user's terminal interface.

[0681] Based on the information provided, users can select the loan plan that best suits their needs. Upon user request, the server will immediately provide additional information related to financial market trends and plans, guaranteeing continuous support throughout the day.

[0682] For example, if a user applies with an annual income of 6 million yen, a desired loan amount of 25 million yen, and a repayment period of 30 years, the server can create a repayment simulation that takes interest rate fluctuations into account and present it to the user based on an interest rate increase scenario. In this case, an example of a prompt message using the generated AI model would be, "Please generate the most suitable mortgage plan based on the user's annual income and desired amount, and perform a repayment simulation that takes interest rate fluctuations into account." This allows the user to obtain sufficient information and criteria to make an informed decision about selecting an appropriate loan plan.

[0683] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0684] Step 1:

[0685] The terminal receives financial information entered by the user (e.g., annual income, desired loan amount, repayment period). This information is converted to JSON format and prepared for transmission to the server. This conversion ensures a consistent data structure, making it easier to analyze on the server.

[0686] Step 2:

[0687] The server receives data in JSON format sent from the terminal. This data is then validated, field by field, to check for missing or invalid data. Once validated, the data is prepared as input for a machine learning model.

[0688] Step 3:

[0689] The server inputs information into a machine learning model (using TensorFlow) and performs a preliminary screening. The model analyzes the input data, assesses the user's credit risk, and generates a preliminary screening result based on their creditworthiness. The output is the user's credit score and whether or not they passed the preliminary screening.

[0690] Step 4:

[0691] The server creates an optimal credit plan and repayment forecast for the user based on the preliminary assessment results. This generation applies a plan creation algorithm and incorporates various loan conditions and market interest rate information. The output of this process is a loan plan including key conditions and a visualized repayment forecast.

[0692] Step 5:

[0693] The server sends the generated credit plan and repayment forecast to the device. The device then presents the information to the user visually through a React Native application. The user can review the plan details and manipulate the provisional repayment plan through an interactive interface.

[0694] Step 6:

[0695] If the user requests further information after reviewing the details, the server searches for financial market trends and relevant educational content, and sends the necessary information to the user's device. This process allows the user to gain a deeper understanding of the loan plan.

[0696] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0697] This invention provides more personalized support by combining a system that provides mortgage-related information and conducts preliminary screening with an emotion engine that recognizes the user's emotions. A specific embodiment is described below.

[0698] First, the user enters housing-related information through an interface on their device. The device formats this information and sends it to the server. The server receives the input information and performs a preliminary assessment using an artificial intelligence model. The preliminary assessment results are then communicated to the user along with a suitable loan plan and repayment simulation.

[0699] This system incorporates an emotion engine that analyzes user input, feedback, and interaction history to assess their emotional state. Based on the emotion engine's results, the server adjusts the tone of information and notifications to match the user's emotions. For example, if the user is feeling anxious, the system will provide more detailed and easily understandable information and offer additional support.

[0700] Furthermore, housing market trends and educational content are individually customized according to the user's interests and preferences and delivered to the user through their device. If the emotion engine detects signs of stress or questions from the user's responses and behavior, the server will provide the user with additional support in real time.

[0701] For example, if a user expresses anxiety about a mortgage, the emotion engine detects that emotion, and the server delivers additional explanatory videos or FAQ sessions to the device. It also highlights a chat link to support staff, allowing users to easily obtain additional information.

[0702] This system operates 24 / 7, continuously collecting user feedback to improve the system. This ensures users always receive appropriate and timely support and enjoy a highly customized mortgage experience.

[0703] The following describes the processing flow.

[0704] Step 1:

[0705] The user uses the terminal to input housing-related information such as their annual income, desired loan amount, and repayment period. The terminal receives this information, formats it, and prepares it for transmission to the server.

[0706] Step 2:

[0707] The server receives the information sent from the terminal and verifies the integrity and completeness of the input data. If the data is appropriate, the server proceeds with further processing and performs a preliminary review using an artificial intelligence model.

[0708] Step 3:

[0709] The server performs a preliminary review using an artificial intelligence model and generates results. These results include a preliminary assessment of the likelihood of loan approval and related risk assessments.

[0710] Step 4:

[0711] Based on the generated preliminary screening results, the server creates an optimal loan plan and repayment simulation for the user. This includes options for fixed and variable interest rates, as well as simulations for different repayment periods.

[0712] Step 5:

[0713] The server uses an emotion engine to analyze the user's emotional state from past inputs and feedback. The emotion engine evaluates the user's stress level, anxiety, level of interest, etc., and instructs the server on the most appropriate response.

[0714] Step 6:

[0715] Based on the analysis results of the emotion engine, the server adjusts the tone and content of the information presented on the device. For example, if anxiety is detected, the server provides the device with additional information, including explanations that emphasize the details and benefits of the loan, as well as FAQ links.

[0716] Step 7:

[0717] Users receive preliminary screening results, loan plans, and supplementary information from the server via their device. Emotionally responsive communication allows users to confidently make decisions about proceeding to the next step.

[0718] Step 8:

[0719] Users can input feedback into their devices as needed and send it to the server via their devices. The server collects this feedback and uses it to further improve the system.

[0720] Step 9:

[0721] Based on the collected feedback and sentiment data, the server optimizes overall system service and individual customizations. The system is then prepared to provide more precise support the next time the user accesses it.

[0722] (Example 2)

[0723] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0724] Traditional information systems for mortgages and other financial products often provide a uniform response without considering the individual emotional state of each user. As a result, users often fail to receive the optimal information and support tailored to their specific circumstances and needs. Furthermore, systems that do not properly utilize feedback can lead to delays in service improvement and decreased user satisfaction.

[0725] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0726] In this invention, the server includes means for receiving financial data input from the user, means for using a machine learning model to analyze the received data and perform a preliminary review, and means for analyzing the user's emotional state and adjusting the tone of information provided. This enables personalized information provision tailored to each user's emotional state and needs, and continuous improvement of the service through the use of appropriate feedback.

[0727] A "user" refers to a person who uses the system to input financial data and receives information and support.

[0728] "Financial data" refers to information related to mortgages and financial services, such as property prices, down payments, and income information entered by the user.

[0729] "Means of receiving" refers to the devices and processes used to send data entered by the user from the terminal to the server, and for the server to receive that data.

[0730] A "machine learning model that analyzes and performs preliminary screening" refers to a learning program that runs on a server, analyzes received data, and provisionally evaluates a financial plan suitable for the user.

[0731] "Emotional analysis means" refers to algorithms and devices that analyze the emotional state based on user input and feedback, and adjust the method of information provision accordingly.

[0732] "Information distribution means" refers to communication methods used to provide users with appropriate information based on sentiment analysis results and preliminary screening results.

[0733] "Feedback collection methods" refer to the methods and processes used to obtain opinions and evaluations from users and utilize them for system improvement.

[0734] A "server" refers to a central computer system that processes data from users and generates and distributes information.

[0735] This invention provides a system that allows users to access mortgages and other financial services more intuitively and individually. The system aims to provide personalized information by taking into account the user's emotional state.

[0736] Users enter detailed mortgage-related data through their devices. This includes property price, down payment, annual income, and other financial conditions, entered via the system interface. The device formats this data and sends it to the server. The protocol used by the device is typically secure HTTPS communication.

[0737] The server utilizes generative AI models to analyze the received data. Machine learning platforms such as TensorFlow and PyTorch are used for this analysis. The model presents the user with a preliminary loan plan and provides a repayment simulation tailored to the user's financial situation.

[0738] Furthermore, the system integrates an emotion analysis engine that evaluates the user's emotional state based on their input and feedback. Natural language processing libraries such as NLTK and DeepMoji are used for this purpose. The analysis results are then used to adjust the tone of information and notifications provided to the user.

[0739] For example, if a user types "I'm worried about rising interest rates," the emotion engine detects the anxiety, and the server provides additional easy-to-understand explanatory videos and FAQs. At this point, the user can easily access additional support through a chat link highlighted on their device.

[0740] Examples of prompts for a generative AI model include concise and specific requests such as, "Please provide additional information about concerns regarding mortgages."

[0741] This system operates 24 hours a day, systematically collecting user feedback, which is then analyzed and stored on the server. This feedback is used to improve the system, enabling us to provide optimal support to users over the long term.

[0742] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0743] Step 1:

[0744] The user enters information about their mortgage into the terminal's input interface. This information includes financial details such as the property price, down payment, and annual income. The terminal receives this information and converts it into a data format, such as JSON. The converted data is then sent to the server.

[0745] Step 2:

[0746] The server receives data sent from the terminal. The received data is analyzed using a machine learning model. Frameworks such as TensorFlow and PyTorch are used for this analysis. The purpose of the analysis is to pre-screen a loan plan suitable for the user based on the input data and generate a repayment simulation based on that plan. The analysis results are output as a loan plan and simulation data.

[0747] Step 3:

[0748] The server provides feedback to the user based on the generated loan plan and simulation data. During this process, it monitors the user's emotional state using sentiment analysis tools. Specifically, sentiment analysis is performed using tools such as NLTK and DeepMoji, based on the user's input and additional feedback received previously. The analysis results are used as input to adjust the tone and content of the information provided.

[0749] Step 4:

[0750] The device receives feedback and analysis results sent from the server. After making adjustments based on the user's emotional state, it displays details of the loan plan and the results of the repayment simulation. The user can then decide on further actions based on this information. Links to additional materials and FAQs are displayed as needed to aid the user's understanding.

[0751] Step 5:

[0752] When a user enters feedback or asks additional questions, the device sends it to the server. The server collects this feedback and stores it in a database for future system improvements. The feedback helps improve the user experience and the accuracy of the generated AI model.

[0753] (Application Example 2)

[0754] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0755] There is a need to alleviate the anxiety and stress experienced by mortgage borrowers and to provide more personalized loan information and support. However, conventional systems struggle to provide flexible support that responds to users' emotional states. Therefore, the challenge is to provide an environment where users can manage their mortgages with peace of mind.

[0756] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0757] In this invention, the server includes means for receiving housing-related information input by the user, means for using a machine learning model that analyzes the received information and performs a preliminary review, and means for using an emotion analysis function that analyzes the user's input data and dialogue history and evaluates their emotional state. This makes it possible to provide information and support that is tailored to the user's emotions.

[0758] A "user" is someone who uses the system to receive housing-related information and loan support.

[0759] "Means for receiving housing-related information" refers to a function that incorporates information related to home purchases and loans entered by users into the system.

[0760] A "machine learning model" is a model based on artificial intelligence technology that is used to analyze user input information and perform preliminary screening.

[0761] The "emotion analysis function" is a feature that analyzes user input data and conversation history to evaluate the user's emotional state.

[0762] "Means for evaluating emotional state" refers to methods used by a system to determine a user's emotions and adjust the level of support provided.

[0763] "Means of adjusting the tone of information provision and notifications" refers to a function that changes the way information is presented and the content of notifications based on the user's emotional state.

[0764] "Means of providing 24-hour customer support" refers to means of responding to user inquiries at any time and providing necessary information and support.

[0765] "Means of providing support information" refers to means of presenting appropriate support information in response to the anxieties and questions that users may have.

[0766] This invention develops a system that incorporates sentiment analysis capabilities to provide personalized support to mortgage borrowers. The system has a server-terminal and user-centric structure.

[0767] The server includes the following steps: First, the user inputs information about their home via a terminal. The terminal converts the input information into a digital format and sends it to the server. Next, the server uses a machine learning model to analyze the input information and conduct a preliminary assessment of the mortgage. At this time, the system also implements a function that uses Google Cloud AI's natural language API to perform sentiment analysis on the user's text data and evaluate their emotional state. Based on the emotional state, the tone of information provided and notifications is adjusted, and the user is provided with customized loan plans and support information.

[0768] The application is designed for smartphones, with the frontend developed using React Native and the backend using Ruby on Rails. This structure allows users to manage their mortgage information intuitively and efficiently.

[0769] Through the process described above, the sentiment analysis function detects the user's level of anxiety based on text entered by the user, such as "I'm worried because I've been behind on payments lately." In this case, the server provides specific advice and additional support information to alleviate the anxiety. Additionally, a contact link to support staff is put into standby mode, allowing the user to contact them immediately.

[0770] Examples of prompt statements used for generative AI models are as follows:

[0771] "Analyze the user's sentiment from the following text and determine if they need support: 'I'm worried because I've been behind on payments lately.'"

[0772] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0773] Step 1:

[0774] The terminal provides a user interface for entering mortgage information. The user enters information such as the desired purchase price, annual income, and desired loan term. This information is converted into a digital format and sent to the server.

[0775] Step 2:

[0776] The server receives housing-related information from the terminal. Based on the received information, it performs a preliminary assessment using a machine learning model. This generates a preliminary loan assessment based on the user's eligibility and conditions.

[0777] Step 3:

[0778] The server uses sentiment analysis functionality to evaluate the user's emotional state. It utilizes additional data and text input provided by the user, leveraging Google Cloud AI's natural language API to perform sentiment analysis. This process extracts emotional information such as the user's anxiety and worries.

[0779] Step 4:

[0780] The server integrates the preliminary assessment results and sentiment analysis results, and adjusts the tone of information and notifications accordingly. For example, if the user is feeling anxious, detailed and concise support information and video guides are provided. This information is sent to the device and displayed to the user.

[0781] Step 5:

[0782] The terminal displays information and support details sent from the server to the user. If necessary, a contact link to support staff is highlighted, allowing the user to easily request additional support.

[0783] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0784] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0785] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0786] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0787] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0788] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0789] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0790] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0791] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0792] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0793] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0794] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0795] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0796] 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.

[0797] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0798] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0799] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0800] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0801] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0802] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0803] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0804] The following is further disclosed regarding the embodiments described above.

[0805] (Claim 1)

[0806] A means of receiving housing-related information entered by the user,

[0807] A method using an artificial intelligence model that analyzes received information and performs a preliminary review,

[0808] A means for generating a loan plan and repayment simulation suitable for the user based on the generated preliminary screening results,

[0809] Information provision means for providing information in response to user requests,

[0810] A means of managing the above means in conjunction and providing 24-hour customer support to users,

[0811] A system that includes this.

[0812] (Claim 2)

[0813] The system according to claim 1, further comprising means for selecting and providing to users educational content related to fluctuations in the housing market.

[0814] (Claim 3)

[0815] The system according to claim 1, further comprising a feedback collection means for collecting user feedback and utilizing it to improve the system.

[0816] "Example 1"

[0817] (Claim 1)

[0818] A device that receives financial information entered by a user,

[0819] A device that converts received information into a data structure and manages it,

[0820] A device that uses an intelligent model to analyze received information and perform a preliminary evaluation,

[0821] A device that generates a financial plan and calculation model suitable for the user based on preliminary evaluation results,

[0822] An information distribution device for providing information in response to user requests,

[0823] A device that manages the above devices in coordination and provides continuous support to users,

[0824] A system that includes this.

[0825] (Claim 2)

[0826] The system according to claim 1, further comprising a device for selecting and providing educational information regarding market trends to users.

[0827] (Claim 3)

[0828] The system according to claim 1, further comprising a feedback collection device for collecting user opinions and utilizing them to improve the system.

[0829] "Application Example 1"

[0830] (Claim 1)

[0831] A means of receiving financial information entered by the user,

[0832] A method using a machine learning model that analyzes received information and performs a preliminary review,

[0833] A means for generating a credit provision plan and repayment forecast suitable for the user based on the generated preliminary screening results,

[0834] Information provision means for providing information in response to user requests,

[0835] A means of managing the above means in conjunction and providing continuous support to users throughout the day,

[0836] An interface means that allows repayment predictions to be intuitively visualized on the user's terminal,

[0837] A system that includes this.

[0838] (Claim 2)

[0839] The system according to claim 1, further comprising means for selecting and providing to users educational content concerning trends in financial markets.

[0840] (Claim 3)

[0841] The system according to claim 1, further comprising a response collection means for collecting user responses and utilizing them to improve the system.

[0842] "Example 2 of combining an emotion engine"

[0843] (Claim 1)

[0844] A means of receiving financial data entered by the user,

[0845] One method involves using a machine learning model that analyzes received data and performs a preliminary review.

[0846] A means for generating a financial plan and repayment simulation suitable for the user based on the generated preliminary screening results,

[0847] A sentiment analysis tool that analyzes the user's emotional state and adjusts the tone of information provided,

[0848] Information distribution means for providing information that responds to user requests or emotions,

[0849] A means of managing the above means in coordination and providing constant support to users,

[0850] A system that includes this.

[0851] (Claim 2)

[0852] The system according to claim 1, further comprising means for selecting and providing to users educational content relating to market fluctuations.

[0853] (Claim 3)

[0854] The system according to claim 1, further comprising a data collection means for collecting user feedback and utilizing it to improve the system.

[0855] "Application example 2 when combining with an emotional engine"

[0856] (Claim 1)

[0857] A means of receiving housing-related information entered by the user,

[0858] A method using a machine learning model that analyzes received information and performs a preliminary review,

[0859] A means for generating a loan plan and repayment simulation suitable for the user based on the generated preliminary screening results,

[0860] A method that uses a sentiment analysis function to analyze user input data and dialogue history and evaluate emotional state,

[0861] A means of adjusting the tone of information provision and notifications based on the results of sentiment analysis,

[0862] A means of managing the above means in conjunction and providing 24-hour customer support to users,

[0863] A means of providing additional support information when emotions such as anxiety are detected,

[0864] A system that includes this.

[0865] (Claim 2)

[0866] The system according to claim 1, further comprising means for selecting and providing to users educational content related to fluctuations in the housing market.

[0867] (Claim 3)

[0868] The system according to claim 1, further comprising means for collecting user feedback and using it to improve the system. [Explanation of Symbols]

[0869] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving financial information entered by the user, A method using a machine learning model that analyzes received information and performs a preliminary review, A means for generating a credit provision plan and repayment forecast suitable for the user based on the generated preliminary screening results, Information provision means for providing information in response to user requests, A means of managing the above means in conjunction and providing continuous support to users throughout the day, An interface means that allows repayment predictions to be intuitively visualized on the user's terminal, A system that includes this.

2. The system according to claim 1, further comprising means for selecting and providing to users educational content concerning trends in financial markets.

3. The system according to claim 1, further comprising a response collection means for collecting user responses and utilizing them to improve the system.

Images