system

Abstract

Provide a system. A means for inputting basic information of a user; means for receiving the basic information; A means for automatically generating a cash flow table using a generation AI model based on the basic information; A means for constructing a life plan for a user based on the cash flow table; A means of proposing relevant financial products based on the constructed life plan; A means for providing the user with information on the generated cash flow table, life plans, and financial products; A system including:

Description

[Technical Field]

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

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

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

[0004] Concerns about future finances become a major issue at various life stages, such as marriage, childbirth, and home purchases. While it's common to consult with a financial planner (FP) to create a cash flow statement to alleviate these anxieties, this is time-consuming and costly, making it a rather inconvenient option. Furthermore, the accuracy of existing automated cash flow statement generation sites is not sufficient, so a means of easily obtaining highly accurate cash flow statements is needed. [Means for solving the problem]

[0005] The present invention provides a system including: means for inputting basic information about a user; means for receiving the basic information; means for automatically generating a cash flow table using a generative AI model based on the basic information; means for constructing a life plan for the user based on the cash flow table; means for proposing related financial products based on the constructed life plan; and means for providing the user with information about the generated cash flow table, life plan, and financial products. This allows the user to easily and accurately obtain a cash flow table and ideal life plan, thereby effectively reducing financial anxiety about the future.

[0006] "User" refers to a person who uses this system to provide the information necessary to formulate his or her own life plan.

[0007] "Basic information" refers to data necessary for generating a cash flow table, such as the user's age, income, family composition, asset status, and future plans.

[0008] "Input means" refers to the interface or device through which a user provides basic information to the system.

[0009] "Receiving means" refers to the function of the server receiving basic information provided through the input means.

[0010] "Generative AI model" refers to a machine learning model or other artificial intelligence technology that automatically generates a cash flow statement based on basic user information.

[0011] "Cash flow statement" refers to a table showing the fluctuations in a user's income, expenses, and assets by year.

[0012] "Life plan" refers to the user's future life plan estimated based on a cash flow table.

[0013] "Financial products" refers to various financial products related to the user's life plan, such as insurance, mortgages, and investment products.

[0014] "Provision means" refers to a function for displaying or providing the generated cash flow table and life plan, as well as information about related financial products, to the user.

[0015] "System" refers to the entire software and hardware used to create a user's life plan and propose financial products in accordance with that plan through a series of processes including the aforementioned means. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention relates to a system for formulating a life plan for a user and generating a highly accurate cash flow table. Specific embodiments of the system will be described below.

[0038] First, the user accesses the system using a device (PC, smartphone, tablet, etc.) and enters basic information, including age, income, family composition, current asset status, and future plans (e.g., home purchase, planned childbirth, etc.).

[0039] The server receives the input information and stores it in a database. At the same time, the server pre-processes the received data, which includes normalizing numeric data and encoding categorical data.

[0040] The server then feeds the preprocessed data into a generative AI model, which is built using machine learning and deep learning techniques to automatically generate a cash flow statement, detailing yearly income and expenditures and asset fluctuations.

[0041] The server then creates a life plan for the user based on the generated cash flow table. The life plan shows the user's predicted future income and expenses, as well as how their assets will fluctuate. It also takes into account the impact of specific events (e.g., buying a house, paying for their children's education).

[0042] Furthermore, the server will suggest appropriate financial products (e.g., insurance, mortgages, and investment products) based on the user's life plan. This suggestion will select the product that best suits the user's needs and future plans, and explain its benefits in detail.

[0043] The server sends the generated cash flow table, life plan, and information about the proposed financial products to the terminal. The terminal displays this information to the user so that the user can confirm it. The user can adjust their future plans based on the displayed information and enter any unclear points or additional questions into the system again.

[0044] Specific examples

[0045] For example, consider a case where the user is 34 years old, earns 5 million yen a year, has a wife (32 years old) and a child (2 years old), has current savings of 1 million yen, and plans to purchase a home in five years and have a second child in two years.

[0046] Users input this information into the system, and the server receives it. The server preprocesses the information and feeds it to a generative AI model. The model generates a cash flow table, and the server uses that data to create a life plan.

[0047] The life plan includes a loan simulation for purchasing a home and an estimate of the costs of having a second child, showing the impact these expenses will have on future income and expenses.

[0048] Finally, the server proposes appropriate insurance and mortgage loans and sends the results to the user's device, where they can confirm them. This allows users to plan for the future with peace of mind, reducing anxiety about the future.

[0049] Through the above processing, this system enables users to formulate life plans easily and with high accuracy.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] Users access the system using a terminal and enter personal and household information, including age, annual income, family composition, current assets, and future plans (e.g., purchasing a home or paying for children's education).

[0053] Step 2:

[0054] The device collects the input information and sends it to the server, mainly in a standard format such as JSON.

[0055] Step 3:

[0056] The server verifies the received user information and stores it in a database. At the same time, it preprocesses the received information, for example, normalizing numerical data such as age and income, and encoding categorical data.

[0057] Step 4:

[0058] The server feeds the pre-processed data into a generative AI model, which uses existing data and machine learning algorithms to automatically generate cash flow tables.

[0059] Step 5:

[0060] The server uses the generated cash flow table to create a life plan for the user, which takes into account annual income and expenditure, asset fluctuations, and future events such as buying a house or paying for children's education.

[0061] Step 6:

[0062] The server selects relevant financial products (insurance, mortgages, investment products, etc.) based on the life plan and creates proposals.

[0063] Step 7:

[0064] The server transmits the generated cash flow table, life plan, and financial product proposals to the terminal.

[0065] Step 8:

[0066] The terminal displays the information sent from the server, and the user can check details about the cash flow statement, life plan, and proposed financial products.

[0067] Step 9:

[0068] The user can review the plan based on the displayed information, and update or ask additional questions as necessary. The server then performs calculations based on the user's input, and can propose an optimal life plan.

[0069] Example 1

[0070] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0071] In modern society, it is extremely difficult for users to formulate specific and accurate future life plans. In particular, detailed forecasts of income, expenses, and asset increases and decreases require specialized knowledge, which is a burden for many people. It is also not easy to select appropriate financial products and accurately assess the economic impact of future events. For these reasons, there is a demand for a system that allows users to easily create accurate life plans.

[0072] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0073] In this invention, the server includes a means for receiving a user's basic information and storing it in a database, a means for preprocessing the basic information and automatically generating a cash flow table using a generative AI model, and a means for constructing a user's life plan based on the cash flow table, thereby enabling the user to efficiently formulate a future life plan and select appropriate financial products based on it.

[0074] "Basic user information" refers to personal data necessary to formulate a user's life plan, such as age, income, family composition, financial situation, and future plans.

[0075] A "database" is a system for efficiently storing, managing, and retrieving data.

[0076] "Preprocessing" refers to data transformation operations that convert data into a format that is easy for a generative AI model to process, and includes normalizing numerical data and encoding categorical data.

[0077] A "generative AI model" is an algorithm that uses machine learning and deep learning technologies to automatically generate cash flow tables and life plans from input data.

[0078] A cash flow statement is a document that shows in tabular form income and expenses over a certain period of time, as well as the resulting increase or decrease in assets.

[0079] A "life plan" is a long-term plan that predicts a user's future income, expenses, and asset fluctuations and takes into account the financial impact of certain events.

[0080] "Financial products" refer to products used for asset management and risk management, such as insurance, mortgages, and investment products.

[0081] A "means" is a method or device used to achieve a particular purpose.

[0082] The present invention relates to a system for formulating a life plan for a user and generating a highly accurate cash flow table. Specific embodiments of the system will be described below.

[0083] First, users access the system using a device such as a PC, smartphone, or tablet and enter basic information, including age, income, family composition, current asset status, and future plans (e.g., home purchase, planned childbirth, etc.).

[0084] The server receives the input information and stores it in a database system such as MySQL (registered trademark) or PostgreSQL. At the same time, the server preprocesses the received data, which includes normalizing numeric data and encoding categorical data.

[0085] The server then feeds the preprocessed data into a generative AI model, which is built using machine learning and deep learning technologies such as TENSORFLOW® and PyTorch, to automatically generate a cash flow table. The generated cash flow table details yearly income and expenditures, as well as asset fluctuations.

[0086] The server then creates a life plan for the user based on the generated cash flow table. The life plan shows the user's predicted future income and expenses, as well as how their assets will fluctuate. It also takes into account the impact of specific events (e.g., buying a house, paying for their children's education).

[0087] Furthermore, the server will suggest appropriate financial products (e.g., insurance, mortgages, and investment products) based on the user's life plan. This suggestion will select the product that best suits the user's needs and future plans, and explain its benefits in detail.

[0088] The server sends the generated cash flow table, life plan, and information about the proposed financial products to the terminal. The terminal displays this information to the user so that the user can confirm it. The user can adjust their future plans based on the displayed information and enter any unclear points or additional questions into the system again.

[0089] Specific examples

[0090] For example, consider a case where the user is 34 years old, has an annual income of 5 million yen, his family consists of a wife (32 years old) and a child (2 years old), has current savings of 1 million yen, and plans to purchase a home in five years and have a second child in two years.

[0091] The user inputs this information into their device and it is received by the server, which preprocesses it and feeds it to the generative AI model. The model generates a cash flow table, and the server uses that data to create a life plan.

[0092] The life plan includes a loan simulation for purchasing a home and an estimate of the costs of having a second child, showing the impact these expenses will have on future income and expenses.

[0093] Finally, the server will recommend suitable insurance and mortgage loans and send the results to the terminal, where the user can review them and make future plans with peace of mind, reducing future anxiety.

[0094] Prompt Sentence Examples

[0095] "I would like to generate a life plan for the following user: age 34, income 5 million yen, family structure: wife (32 years old) and child (2 years old), current savings of 1 million yen, purchase of a home in 5 years, and plan to have a second child in 2 years."

[0096] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0097] Step 1:

[0098] Users access the system using devices such as PCs, smartphones, and tablets and enter basic information. This basic information includes age, income, family composition, current asset status, and future plans (e.g., home purchase, planned childbirth, etc.). The entered data is sent to the server.

[0099] Input: Basic information entered by the user (age, income, family composition, assets, future plans)

[0100] Output: Basic user information sent to the server

[0101] Step 2:

[0102] The server receives the basic information sent by the user and stores it in a database system such as MySQL or PostgreSQL, while also verifying with a simple query that the data has been stored correctly.

[0103] Input: User basic information

[0104] Output: Basic information stored in the database

[0105] Specific behavior:

[0106] The server receives basic information through an HTTP request.

[0107] Parses the received data and splits it into the appropriate fields.

[0108] The split data is inserted (stored) into the database.

[0109] After storage, queries are run from the database to verify data integrity.

[0110] Step 3:

[0111] The server retrieves the basic information stored in the database and performs preprocessing, which includes normalizing numeric data and encoding categorical data. Normalization aligns the data to a uniform scale, while encoding converts categorical data into numeric values.

[0112] Input: Basic information stored in the database

[0113] Output: Preprocessed data

[0114] Specific behavior:

[0115] Get basic information from the database.

[0116] Standardize numerical data such as income data.

[0117] Encoding categorical data such as family structure (e.g., one-hot encoding).

[0118] Step 4:

[0119] The server feeds the preprocessed data to a generative AI model, which is built using machine learning libraries such as TensorFlow or PyTorch, and sends an API request to pass the data to the model.

[0120] Input: Preprocessed data

[0121] Output: Data passed to the generative AI model

[0122] Specific behavior:

[0123] Convert the preprocessed data into the specified format.

[0124] Send data to the generative AI model endpoint (API).

[0125] Verify that the model was properly fed with data.

[0126] Step 5:

[0127] The generative AI model generates a cash flow table based on the data provided. This cash flow table details annual income and expenditures and asset fluctuations. The generated cash flow table is returned to the server in JSON format.

[0128] Input: The data fed into the generative AI model

[0129] Output: Cash flow table (JSON format)

[0130] Specific behavior:

[0131] The generative AI model uses machine learning algorithms to calculate cash flow tables.

[0132] The calculated result is converted to JSON format and returned to the server.

[0133] Step 6:

[0134] The server then uses the generated cash flow table to construct a life plan for the user, which includes forecasts of future income and expenditure, asset fluctuations, and the financial impact of specific events.

[0135] Input: Generated cash flow table

[0136] Output: User's life plan

[0137] Specific behavior:

[0138] Analyze the generated cash flow table.

[0139] Project long-term income, expense, and asset fluctuations.

[0140] Simulate the impact of a particular event (e.g., buying a home, paying for a child's education).

[0141] Step 7:

[0142] The server proposes appropriate financial products based on the user's life plan, including insurance, mortgages, and investment products. The proposals are optimized to meet the user's needs.

[0143] Input: User's life plan

[0144] Output: Proposed financial instruments

[0145] Specific behavior:

[0146] Analyze life plans to identify user needs.

[0147] Select the most suitable financial product and describe its benefits in detail.

[0148] Step 8:

[0149] The server sends the generated cash flow table, life plan, and information about the proposed financial products to the terminal using the HTTPS protocol to ensure data security.

[0150] Input: Cash flow statement, life plan, proposed financial products

[0151] Output: Information sent to the terminal

[0152] Specific behavior:

[0153] The generated information is then collected and encrypted using the HTTPS protocol.

[0154] The encrypted data is sent to the terminal.

[0155] Step 9:

[0156] The terminal displays the results received from the server to the user via a web browser or dedicated application, allowing the user to visually check cash flow tables, life plans, and proposed financial products.

[0157] Input: Information received from the server

[0158] Output: The results that are displayed to the user

[0159] Specific behavior:

[0160] Parses the received data and displays it in the appropriate format.

[0161] Present information visually in graphs and tables.

[0162] Step 10:

[0163] The user checks the displayed results and uses them as a reference for making future plans. If there are any unclear points or additional questions, they can re-enter basic information into the system and create a new life plan. The system will recalculate to accommodate changes in the scenario (e.g., increased income, new investment plans).

[0164] Input: Basic information re-entered as a result of the display

[0165] Output: New life plan and information

[0166] Specific behavior:

[0167] The user again enters basic information into the system.

[0168] The server receives the input and repeats the same process to generate a new life plan.

[0169] Through the above steps, the system enables users to easily create highly accurate and detailed life plans.

[0170] (Application example 1)

[0171] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0172] With conventional life planning systems, it was difficult to manage and record users' daily income and expenditures, as well as income in real time, making it difficult to provide accurate cash flow tables.In addition, there was a lack of means to visualize this information in an easy-to-understand manner for users, resulting in low user understanding and convenience.

[0173] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0174] In this invention, the server includes means for inputting basic information of a user, means for receiving the basic information, means for automatically generating a cash flow table using a generative AI model based on the basic information, means for constructing a life plan for the user based on the cash flow table, means for proposing related financial products based on the constructed life plan, means for providing the user with information on the generated cash flow table, life plan, and financial products, means for recording and managing the user's daily income and expenditure, expenses, and income in real time, and means for visualizing the information through a user interface. This enables the user to manage and understand their daily income and expenditure and future asset fluctuations in real time based on an accurate cash flow table and life plan.

[0175] "Basic information about the user" refers to information about the user, such as the user's age, income, family structure, financial situation, and future plans.

[0176] A "generative AI model" is a model built using machine learning and deep learning technologies, and is designed to automatically generate cash flow tables and life plans based on input data.

[0177] A "cash flow statement" is a table that details a user's income and expenses and shows the increase or decrease in assets by year.

[0178] A "life plan" is a guideline for predicting and planning a user's future income, expenses, and asset fluctuations.

[0179] "Financial products" are financial products such as insurance, mortgages, and investment products that are provided according to users' needs and future plans.

[0180] "Means for recording and managing in real time" refers to means for recording the user's daily income and expenditure, expenses and income in real time and for managing and understanding them immediately.

[0181] A "user interface" is a display screen or operating means that allows a user to interact with a system and input and confirm information.

[0182] The present invention relates to a system for formulating a user's life plan and generating a highly accurate cash flow table. Specific embodiments of this system will be described below.

[0183] First, the user accesses the system using a device (PC, smartphone, tablet, etc.) and enters basic information, including age, income, family composition, current asset status, and future plans (e.g., home purchase, planned childbirth, etc.).

[0184] The server then receives the basic information and stores it in a database. At the same time, preprocessing involves normalizing numerical data and encoding categorical data. The preprocessed data is then fed into a generative AI model, which automatically generates a cash flow table. The generated cash flow table details annual income and expenditures, as well as asset fluctuations.

[0185] The server then creates a life plan for the user based on the generated cash flow table. The life plan shows the user's predicted future income and expenses, as well as how their assets will fluctuate. It also takes into account the impact of specific events (e.g., buying a home, paying for their children's education). Next, the server recommends appropriate financial products (e.g., insurance, mortgages, investment products) based on the life plan. This recommendation selects the product that best suits the user's needs and future plans, and explains its benefits in detail.

[0186] This system also has the function of recording and managing the user's daily income and expenditure, expenses, and income in real time. The terminal visualizes this information through a user interface, allowing the user to easily check their income and expenditure status. This allows the user to centrally manage their daily income and expenditure and future cash flow.

[0187] Specific examples

[0188] As a concrete example, let's say a 34-year-old user earns 5 million yen a year, his family consists of his wife (32 years old) and a child (2 years old), his current savings are 1 million yen, he plans to buy a house in 5 years and give birth to his second child in 2 years. When this information is entered into the system, the following prompt sentence is generated:

[0189] Example prompt:

[0190] Age: 34

[0191] Income: 5 million yen

[0192] Family: Wife 32, child 2

[0193] Current savings: 1 million yen

[0194] Future plans: Buy a house in 5 years, have a second child in 2 years

[0195] Based on this prompt, the server performs preprocessing and generates a cash flow table and life plan using a generative AI model. The generated cash flow table and life plan are displayed to the user via their device and provided as reference information for the user to make future plans. As a result, the user can feel secure about their life planning.

[0196] As described above, the present invention provides a specific means for assisting users in formulating their life plans, and realizes highly accurate cash flow management.

[0197] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0198] Step 1:

[0199] Users access the system using a terminal and enter basic information, including age, income, family composition, current asset status, and future plans. This basic information becomes the initial input data for the system.

[0200] Step 2:

[0201] The device sends the input basic information to the server, which stores it in a database and initiates the necessary preprocessing, including normalizing numerical data and encoding categorical data to convert it into a format suitable for generative AI models.

[0202] Step 3:

[0203] The server then supplies the preprocessed data to a generative AI model, which then automatically generates a cash flow table based on the input prompts. This cash flow table details annual income and expenditures, as well as asset fluctuations.

[0204] Step 4:

[0205] Based on the generated cash flow table, the server constructs a life plan for the user, which includes predictions of future income and expenditure, asset fluctuations, and the impact of specific events (e.g., home purchase, children's education expenses).

[0206] Step 5:

[0207] The server then recommends suitable financial products based on the user's life plan, including insurance, mortgages, and investment products, and provides a detailed explanation of the benefits of each.

[0208] Step 6:

[0209] The server transmits the generated cash flow table, life plan, and information about the proposed financial products to the terminal, which then visualizes the information through a user interface and displays it for the user to confirm.

[0210] Step 7:

[0211] Users input their daily income and expenditures, expenses, and income, and record and manage them in real time. This information is sent to the server via the terminal, and the server updates the data in real time and reflects it on the user interface.

[0212] Step 8:

[0213] Based on the displayed cash flow table, life plan, and proposed financial products, users can adjust their future plans and take necessary actions, thereby improving the accuracy of their life planning and reducing anxiety.

[0214] Through the above steps, this system can effectively support users in formulating their life plans and achieve highly accurate cash flow management.

[0215] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0216] The present invention relates to a system that formulates a user's life plan, generates a highly accurate cash flow table by combining it with an emotion engine, and proposes financial products that are adapted to the user's psychological state. Specific embodiments of this system are described below.

[0217] First, the user accesses the system using a device (PC, smartphone, tablet, etc.) and enters basic information, including age, income, family composition, current financial situation, and future plans (e.g., home purchase, children's education expenses, etc.). At the same time, the emotion engine recognizes and collects emotional data from the user's facial expressions and tone of voice.

[0218] The device collects the input information and sends it to the server in a standard format such as JSON. Emotion data collected by the emotion engine is also sent at the same time.

[0219] The server verifies the received user information and emotion data and stores them in a database. At the same time, it preprocesses the received information. In addition to normalizing numerical data and encoding categorical data, emotion data is also analyzed.

[0220] The server then supplies the preprocessed data and emotion data to a generative AI model, which then uses existing data and machine learning algorithms to automatically generate a cash flow table. The model also adjusts the cash flow table based on the emotion data, taking into account the user's psychological state.

[0221] The server uses the generated cash flow table to create a life plan for the user. The plan takes into account annual income and expenditure, asset fluctuations, and future events such as home purchases and children's education expenses. Furthermore, based on emotional data, the server prioritizes creating a plan that minimizes stress for the user.

[0222] Furthermore, the server proposes appropriate financial products (e.g., insurance, mortgages, and investment products) based on the user's life plan. These proposals take into account emotional data and select products that are suited to the user's psychological state. For example, a user who is prone to anxiety will be proposed a financial product with low risk.

[0223] The server transmits the generated cash flow table, life plan, and information about the proposed financial products to the terminal. The terminal displays this information to the user and provides a user interface that reflects the emotional data. This allows the user to check the information with peace of mind.

[0224] Specific examples

[0225] For example, consider a case where the user is 34 years old, earns 5 million yen a year, has a family consisting of a wife (32 years old) and a child (2 years old), has current savings of 1 million yen, plans to purchase a home in 5 years and have a second child in 2 years. Also, suppose that emotional data reveals that the user has a personality that is prone to anxiety.

[0226] Users input this information into the system, and the emotion engine collects emotional data from the user's facial expressions and tone of voice. The server receives the information and performs preprocessing and emotional data analysis. The generative AI model generates a cash flow table, and the server further builds a life plan based on the emotional data. In this life plan, low-risk financial products are prioritized for users who are prone to anxiety.

[0227] The server selects appropriate insurance and mortgage plans and sends this information to the device, which then displays cash flow tables, life plans, and insurance and loan proposals to the user, using an interface that reflects emotional data so that the user can confirm them with confidence.

[0228] Through the above processing, this system can easily and accurately formulate a life plan for the user, and by taking emotional data into consideration, it can also reduce the psychological burden on the user.

[0229] The processing flow will be explained below.

[0230] Step 1:

[0231] Users access the system using a terminal and enter basic information and emotional data. Basic information includes age, income, family composition, current assets, and future plans (e.g., home purchase and children's education expenses). Emotional data is collected by the emotion engine from the user's facial expressions and tone of voice.

[0232] Step 2:

[0233] The device collects basic information and emotional data provided by the user and sends it to a server in a standard format such as JSON.

[0234] Step 3:

[0235] The server verifies the received user information and emotion data and stores them in a database. At the same time, it performs preprocessing, including normalizing numerical data and encoding categorical data, and also analyzes the emotion data.

[0236] Step 4:

[0237] The server provides the preprocessed basic information and analyzed emotion data to the generative AI model, which then uses a machine learning algorithm to automatically generate a cash flow table. The model then adjusts the cash flow table based on the emotion data, taking into account the user's psychological state.

[0238] Step 5:

[0239] The server uses the generated cash flow table to create a life plan for the user. The life plan takes into account annual income and expenditure, asset fluctuations, and future events (e.g., home purchases, children's education expenses). It also selects a plan that minimizes stress for the user based on emotional data.

[0240] Step 6:

[0241] The server proposes relevant financial products (insurance, mortgages, investment products, etc.) based on the user's life plan. This proposal takes into account emotional data and selects products that are suited to the user's psychological state. For example, a risk-averse user will be proposed low-risk financial products.

[0242] Step 7:

[0243] The server transmits the generated cash flow table, the life plan, and information on the proposed financial products to the terminal.

[0244] Step 8:

[0245] The terminal displays the information sent from the server. The display uses a user interface that reflects the emotional data, allowing the user to check the information with peace of mind.

[0246] Step 9:

[0247] The user can review the plan based on the displayed information and send feedback to the system again if necessary. Based on this feedback, the server can recalculate and adjust the plan to provide the user with the optimal life plan.

[0248] Specific examples

[0249] For example, consider a case where the user is 34 years old, earns 5 million yen a year, has a family consisting of a wife (32 years old) and a child (2 years old), has current savings of 1 million yen, plans to purchase a home in 5 years and have a second child in 2 years. Also, suppose that emotional data reveals that the user has a personality that is prone to anxiety.

[0250] Users input this information into the system, and the device collects emotional data from the user's facial expressions and tone of voice. The server receives the information, performs preprocessing, and analyzes the emotional data. A generative AI model generates a cash flow table and builds an adjusted life plan taking into account the emotional data.

[0251] The server selects appropriate insurance and mortgage plans and sends this information to the device, which then displays cash flow tables, life plans, and insurance and loan proposals to the user, using an interface that reflects emotional data to allow for ease of review.

[0252] The user can check the information and provide feedback as needed, and the server will make adjustments and provide an optimal life plan. This allows users to easily and accurately formulate plans, and also reduces the psychological burden.

[0253] Example 2

[0254] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0255] While conventional financial planning systems are sufficiently accurate in generating cash flow tables and life plans based on a user's basic information, they do not take into account the user's emotional state. This makes it difficult to recommend appropriate financial products while reducing the user's psychological burden. Furthermore, existing systems have difficulty integrating the collection and analysis of emotional data, making it impossible to realize planning that reflects the user's psychological state in real time.

[0256] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0257] In this invention, the server includes a means for receiving a user's basic information and emotional data, a means for automatically generating a cash flow table using a generative AI model based on the basic information and emotional data, and a means for constructing a user's life plan based on the cash flow table and emotional data. This enables the generation of a highly accurate cash flow table and life plan that takes into account not only the user's basic information but also their emotional state. It also enables the proposal of appropriate financial products that reflect the user's psychological state.

[0258] "Basic user information" refers to personal data necessary for generating a user's life plan and cash flow table, such as age, income, family structure, asset status, and future plans.

[0259] "Emotional data" refers to data that indicates the user's emotional state, such as the user's facial expression or tone of voice, and is used to take the user's psychological state into consideration in the planning process.

[0260] A "generative AI model" is a model that uses machine learning algorithms to automatically generate cash flow tables and life plans based on a user's basic information and emotional data.

[0261] A "cash flow table" is a table that shows the flow of a user's income and expenditures over time, and is important data that forms the basis of a life plan.

[0262] A "life plan" is a plan that takes into account the user's future income and expenditure, changes in assets, future events (e.g., home purchase, children's education expenses), etc., and is intended to assist the user in planning their long-term life.

[0263] "Financial products" are products related to economic activities proposed based on the user's life plan, such as insurance, mortgages, and investment products.

[0264] "Preprocessing" refers to the preparation process, such as data normalization, encoding, and analysis, that allows the generative AI model to properly handle basic user information and emotional data.

[0265] "Means for receiving" is a function for incorporating basic information and emotional data of the user into the system.

[0266] "Means for automatic generation" refers to a function that automatically creates a cash flow statement using machine learning algorithms or generative AI models.

[0267] "Means for construction" is a function that creates a life plan based on a cash flow table and emotional data, taking into account the user's individual needs and psychological state.

[0268] The "means for providing" is a function for presenting the generated cash flow table, life plan, and information about financial products to the user.

[0269] A specific embodiment of this system will be described below.

[0270] Users access the system using devices such as PCs, smartphones, and tablets, and enter basic information such as age, income, family composition, current financial situation, and future plans. The emotion engine also analyzes the user's facial expressions and tone of voice to collect emotional data. This allows data on the user's emotional state to be obtained without the user even realizing it.

[0271] The device collects the user's basic information and emotional data and sends it to the server in a standard format such as JSON. At this stage, hardware such as a webcam and microphone are used to collect the emotional data.

[0272] The server verifies the received user basic information and emotion data and stores them in a database. The stored data then undergoes preprocessing steps, where it is normalized and encoded. For example, numerical data such as age and income are scaled, and categorical data such as family structure and financial status are one-hot encoded. Emotion data is also analyzed in detail using facial expression analysis algorithms and voice analysis algorithms.

[0273] The server then feeds the preprocessed data and emotion data to a generative AI model, which uses machine learning frameworks such as TensorFlow or PyTorch. The model automatically generates a cash flow table based on the existing data and algorithms. The emotion data is also incorporated, resulting in a plan that reflects the user's psychological state.

[0274] The server uses the generated cash flow table to create a life plan for the user. This life plan includes annual income and expenditure, asset changes, and future events (such as buying a home or paying for children's education). Based on the user's emotional data, the server prioritizes plans that minimize stress for the user.

[0275] Furthermore, the server recommends appropriate financial products (e.g., insurance, mortgages, and investment products) based on the user's life plan. By utilizing emotional data, products with low risk are prioritized for users who are prone to anxiety.

[0276] Finally, the server sends the generated cash flow table, life plan, and information on proposed financial products to the terminal. The terminal displays the received information to the user and provides an interface that reflects the emotional data, allowing the user to check the information with peace of mind.

[0277] Specific examples

[0278] For example, consider a user who is 34 years old, has an annual income of 5 million yen, a family consisting of a wife (32 years old) and a two-year-old child, has current savings of 1 million yen, plans to buy a house in five years, and is expecting a second child in two years. Furthermore, consider a case where emotional data reveals that the user is prone to anxiety. When the user enters this information into the system, the emotion engine collects emotional data from the user's facial expressions and tone of voice. The server then receives the information and performs preprocessing and emotional data analysis.

[0279] The generative AI model generates a cash flow table, and the server builds an adjusted life plan based on emotional data. This life plan prioritizes low-risk financial products for users who are prone to anxiety. The server selects appropriate insurance and mortgages and sends this information to the device. The device displays the cash flow table, life plan, and insurance / loan proposals to the user, providing an interface that takes the user's emotions into consideration.

[0280] Prompt Sentence Examples

[0281] "A user is 34 years old, earns 5 million yen a year, has a wife (32) and a child (2 years old), currently has 1 million yen in savings, and plans to purchase a home in five years. The user's emotional data reveals that he is prone to anxiety. Please suggest an appropriate cash flow statement, life plan, and financial products for this user."

[0282] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0283] Step 1:

[0284] The user accesses the system using a terminal and inputs basic information (age, income, family composition, financial situation, future plans). In addition, facial expression and voice data are collected via the terminal's camera and microphone. For example, the input information might be "34 years old, annual income of 5 million yen, family composition of wife and child, current savings of 1 million yen, plan to purchase a home in five years, and expect to have a second child in two years." This information is then sent to the system.

[0285] Input: Basic information and emotion data

[0286] Output: Send basic information and emotion data

[0287] Step 2:

[0288] The device organizes the received basic information and emotion data in a standard format such as JSON and sends it to the server. During this process, it checks whether any data is missing and whether the format is correct. For example, data containing collected facial expressions and tone of voice is sent to the server in JSON format.

[0289] Input: Basic information and emotion data

[0290] Output: Send to server as JSON format data

[0291] Step 3:

[0292] The server stores the received basic information and emotion data in a database. When storing the data in the database, it checks for duplicate data and errors. For example, it organizes the data by user ID and stores it in the database.

[0293] Input: Basic information and emotion data in JSON format

[0294] Output: Data stored in the database

[0295] Step 4:

[0296] The server preprocesses the stored data by normalizing the numerical data, encoding the categorical data, and analyzing the emotional data. For example, it normalizes the income data, performs one-hot encoding on the family structure, and analyzes the facial expression data to quantify the user's emotional state.

[0297] Input: Basic information and emotion data stored in the database

[0298] Output: Preprocessed data

[0299] Step 5:

[0300] The server then supplies the preprocessed data and sentiment data to a generative AI model, which then uses the existing data and machine learning algorithms to generate a cash flow statement. For example, the preprocessed income, expenditure, and sentiment data can be used to automatically generate a cash flow statement that predicts future income and expenditures.

[0301] Input: Preprocessed basic information and emotion data

[0302] Output: Generated cash flow table

[0303] Step 6:

[0304] The server then creates a life plan for the user based on the generated cash flow table. This process takes into account annual income and expenditure, asset fluctuations, and future events such as home purchases and children's education expenses. Furthermore, it also generates a plan that minimizes psychological burden by reflecting emotional data. For example, a plan with fewer risks is suggested for a user who is prone to anxiety.

[0305] Input: Generated cash flow tables and sentiment data

[0306] Output: Constructed life plan

[0307] Step 7:

[0308] The server then recommends appropriate financial products (insurance, mortgages, investment products) based on the user's life plan. Emotional data is also taken into consideration, and low-risk financial products are prioritized for users who are prone to anxiety. For example, safe bonds and low-risk investment trusts are recommended.

[0309] Input: Life plan and emotional data

[0310] Output: Proposed financial instruments

[0311] Step 8:

[0312] The server sends the generated cash flow table, life plan, and information about the proposed financial products to the terminal, allowing the user to visually confirm the necessary information.

[0313] Input: Cash flow statement, life plan, information on financial products

[0314] Output: Sending data to the terminal

[0315] Step 9:

[0316] The device displays the received information in a user interface. This interface reflects the emotional data and provides an environment where users can check information with confidence. For example, cash flow tables and life plans are displayed in graphs and tables, accompanied by detailed explanations of financial products.

[0317] Input: Information sent from the server

[0318] Output: Display on the user interface

[0319] (Application example 2)

[0320] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0321] Current life plan formulation and financial product proposal systems only consider basic user information and do not reflect the user's emotions or psychological state. As a result, the proposed life plan or financial product may not match the user's actual psychological state, causing stress or anxiety. In particular, the psychological burden placed on users when using electronic payment services can be a major problem. Therefore, the present invention aims to provide a system that can generate highly accurate cash flow tables that adapt to the user's psychological state based on detailed information, including the user's emotional data, and that can be used with confidence.

[0322] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting basic information about a user, means for receiving the basic information, means for automatically generating a cash flow table using a generative AI model based on the basic information and emotion data, means for constructing a life plan for the user based on the cash flow table and emotion data, means for proposing related financial products based on the constructed life plan, means for providing the user with information about the generated cash flow table, life plan, and financial products, means for collecting emotion data using a camera and microphone of the terminal, and means for analyzing and processing the emotion data. This makes it possible to provide a system that generates a highly accurate cash flow table that is adapted to the user's psychological state and can be used with confidence.

[0323] "Basic user information" refers to data about the individual user, such as age, income, family composition, financial situation, and future plans.

[0324] "Emotional data" refers to data that indicates the emotional state of a user, analyzed from facial expressions and tone of voice collected using a camera or microphone.

[0325] A "generative AI model" is an artificial intelligence algorithm that automatically generates cash flow tables and life plans based on data.

[0326] A cash flow statement is a table that shows the flow of funds over a certain period of time, based on income and expenses.

[0327] A "life plan" is a long-term life planning plan created taking into consideration the user's future events and income and expenditure.

[0328] "Financial products" refers to products aimed at asset management and risk management, such as insurance, mortgages, and investment products.

[0329] A "terminal" is a device used by a user to input information or collect emotional data, and specifically refers to a smartphone, tablet, etc.

[0330] The "server" is a computer system that receives and processes basic information and emotional data of users, and generates and manages cash flow tables and life plans.

[0331] MODE FOR CARRYING OUT THE INVENTION

[0332] The present invention is a system that automatically generates a cash flow table using a user's basic information and emotional data, and proposes life plans and financial products that are adapted to the user's psychological state based on the emotional data. Specific embodiments of this system are described below.

[0333] System configuration

[0334] 1. Input Method

[0335] Device: A device used by a user to input basic information and collect emotional data, such as a smartphone or tablet.

[0336] 2. Data transmission method

[0337] From the device to the server: The user's basic information and emotional data are sent to the server in JSON format or similar.

[0338] 3. Data processing means

[0339] Server: Preprocesses the received data, normalizing numerical data, encoding categorical data, and analyzing sentiment data. Software used includes TensorFlow and Pandas.

[0340] 4. Generation means

[0341] Generative AI model: An algorithm for generating cash flow tables using preprocessed data, specifically GPT-3 (registered trademark) and BERT.

[0342] 5. Life planning tools

[0343] Server: Build a life plan based on the generated cash flow table and emotional data.

[0344] 6. Financial product proposal means

[0345] Server: Based on the constructed life plan, the server proposes financial products (e.g., low-risk investment products or credit cards) that are adapted to the user's psychological state. The software used includes recommendation systems (Scikit-learn, LightFM).

[0346] 7. Display means

[0347] Terminal: Provides users with information such as proposed cash flow tables, life plans, financial products, etc. The software used includes a front-end framework (React Native).

[0348] Processing Details

[0349] Data entry and emotion data collection

[0350] Users use their smartphones to input basic information (age, income, family composition, financial situation, future plans, etc.) At the same time, the smartphone's camera and microphone are used to collect emotional data from facial expressions and tone of voice, which is then analyzed using an emotion recognition library (e.g., Affectiva SDK).

[0351] Data transmission and preprocessing

[0352] Emotion data and basic user information are sent from the device to the server. After receiving the data, the server performs preprocessing. This preprocessing includes normalizing numerical data, encoding categorical data, and analyzing emotional data. Specific preprocessing tools used are TensorFlow and Pandas.

[0353] Applying generative AI models

[0354] The preprocessed data and emotional data are input into a generative AI model (e.g., GPT-3, BERT) to generate a cash flow table. The emotional data is also taken into account, and a cash flow table that takes into account the user's psychological state is output.

[0355] Building life plans and proposing financial products

[0356] The server builds a life plan for the user based on the generated cash flow table. This life plan adapts to the user's psychological state and suggests low-risk investment products and credit cards to reduce anxiety. Scikit-learn and LightFM are used as recommendation systems.

[0357] Displaying Information

[0358] Information such as proposed cash flow tables, life plans, and financial products is displayed on the smartphone screen, and this information is presented to users in a visually easy-to-understand manner using React Native.

[0359] Specific examples

[0360] For example, let's say the user is 40 years old, earns 7 million yen a year, has a wife (38 years old) and two children (ages 10 and 8), has current savings of 3 million yen, and is planning to renovate their home in three years. Emotional data also reveals that the user has a personality that is easily stressed.

[0361] In this case, users enter basic information into their smartphones and collect emotional data. The server receives and preprocesses the data, and the generated cash flow table and life plan are provided to the user. The proposed financial products, including low-risk investment products and home improvement loans, are displayed in an interface that users can easily check.

[0362] Prompt Sentence Examples

[0363] A user is 40 years old, earns 7 million yen a year, has a wife aged 38, two children aged 10 and 8, has current savings of 3 million yen, and plans to renovate their home in three years. Generate a life plan and cash flow table for this user who is prone to stress, and suggest appropriate financial products.

[0364] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0365] Step 1:

[0366] Users use their smartphones to input basic information (age, income, family composition, financial situation, future plans). The smartphone's camera and microphone are also used to collect emotional data from facial expressions and tone of voice. Specifically, analysis is performed using an emotion recognition library (e.g., Affectiva SDK). After the input data is collected, this information is sent from the device to the server. The input is the user's basic information and emotional data, and the output is JSON-formatted data containing this information.

[0367] Step 2:

[0368] The server receives basic information and emotion data sent from the device. It uses JSON format as the reception format and stores the data in an appropriate database. Preprocessing of the received data involves normalizing numerical data (e.g., min-max scaling), encoding categorical data (e.g., one-hot encoding), and analyzing emotion data. Data processing libraries such as TensorFlow and Pandas are used for preprocessing. The input is user data and emotion data in JSON format, and the output is the preprocessed data.

[0369] Step 3:

[0370] Preprocessed basic user information and emotion data are fed into a generative AI model. GPT-3 and BERT are used as generative AI models. This model automatically generates a cash flow table based on the input data. Specifically, the model analyzes the data and performs various calculations to predict the user's income and expenditures. The input is preprocessed data, and the output is the generated cash flow table.

[0371] Step 4:

[0372] The server constructs a life plan for the user based on the generated cash flow table and emotional data. The life plan includes future income and expenditure forecasts and important events (e.g., home purchase, children's education expenses). Based on the emotional data, it prioritizes creating a life plan that will reduce stress and anxiety for the user. This part uses a recommendation system (e.g., Scikit-learn, LightFM). The input is the generated cash flow table and emotional data, and the output is the constructed life plan.

[0373] Step 5:

[0374] The server proposes relevant financial products (e.g., low-risk investment products, insurance) based on the constructed life plan. Based on the emotional data, appropriate products that adapt to the user's psychological state are selected. The input is the constructed life plan and emotional data, and the output is the proposed financial products.

[0375] Step 6:

[0376] The server sends the generated cash flow table, life plan, and information on the proposed financial products to the terminal. The sending method uses a standard format such as JSON. The input is the cash flow table, life plan, and financial product information, and the output is the information sent to the terminal.

[0377] Step 7:

[0378] The device receives the information sent from the server and displays it to the user through a user interface. The software used includes a front-end framework (e.g., React Native). The visually easy-to-understand interface reflects emotional data, allowing the user to check the information with confidence. The input is the information sent from the server, and the output is the information displayed on the user interface.

[0379] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0380] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0381] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0382] [Second embodiment]

[0383] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0384] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0385] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0386] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0387] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0388] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0389] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0390] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0391] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0392] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0393] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0394] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0395] The present invention relates to a system for formulating a life plan for a user and generating a highly accurate cash flow table. Specific embodiments of the system will be described below.

[0396] First, the user accesses the system using a device (PC, smartphone, tablet, etc.) and enters basic information, including age, income, family composition, current asset status, and future plans (e.g., home purchase, planned childbirth, etc.).

[0397] The server receives the input information and stores it in a database. At the same time, the server pre-processes the received data, which includes normalizing numeric data and encoding categorical data.

[0398] The server then feeds the preprocessed data into a generative AI model, which is built using machine learning and deep learning techniques to automatically generate a cash flow statement, detailing yearly income and expenditures and asset fluctuations.

[0399] The server then creates a life plan for the user based on the generated cash flow table. The life plan shows the user's predicted future income and expenses, as well as how their assets will fluctuate. It also takes into account the impact of specific events (e.g., buying a house, paying for their children's education).

[0400] Furthermore, the server will suggest appropriate financial products (e.g., insurance, mortgages, and investment products) based on the user's life plan. This suggestion will select the product that best suits the user's needs and future plans, and explain its benefits in detail.

[0401] The server sends the generated cash flow table, life plan, and information about the proposed financial products to the terminal. The terminal displays this information to the user so that the user can confirm it. The user can adjust their future plans based on the displayed information and enter any unclear points or additional questions into the system again.

[0402] Specific examples

[0403] For example, consider a case where the user is 34 years old, earns 5 million yen a year, has a wife (32 years old) and a child (2 years old), has current savings of 1 million yen, and plans to purchase a home in five years and have a second child in two years.

[0404] Users input this information into the system, and the server receives it. The server preprocesses the information and feeds it to a generative AI model. The model generates a cash flow table, and the server uses that data to create a life plan.

[0405] The life plan includes a loan simulation for purchasing a home and an estimate of the costs of having a second child, showing the impact these expenses will have on future income and expenses.

[0406] Finally, the server proposes appropriate insurance and mortgage loans and sends the results to the user's device, where they can confirm them. This allows users to plan for the future with peace of mind, reducing anxiety about the future.

[0407] Through the above processing, this system enables users to formulate life plans easily and with high accuracy.

[0408] The processing flow will be explained below.

[0409] Step 1:

[0410] Users access the system using a terminal and enter personal and household information, including age, annual income, family composition, current assets, and future plans (e.g., purchasing a home or paying for children's education).

[0411] Step 2:

[0412] The device collects the input information and sends it to the server, mainly in a standard format such as JSON.

[0413] Step 3:

[0414] The server verifies the received user information and stores it in a database. At the same time, it preprocesses the received information, for example, normalizing numerical data such as age and income, and encoding categorical data.

[0415] Step 4:

[0416] The server feeds the pre-processed data into a generative AI model, which uses existing data and machine learning algorithms to automatically generate cash flow tables.

[0417] Step 5:

[0418] The server uses the generated cash flow table to create a life plan for the user, which takes into account annual income and expenditure, asset fluctuations, and future events such as buying a house or paying for children's education.

[0419] Step 6:

[0420] The server selects relevant financial products (insurance, mortgages, investment products, etc.) based on the life plan and creates proposals.

[0421] Step 7:

[0422] The server transmits the generated cash flow table, life plan, and financial product proposals to the terminal.

[0423] Step 8:

[0424] The terminal displays the information sent from the server, and the user can check details about the cash flow statement, life plan, and proposed financial products.

[0425] Step 9:

[0426] The user can review the plan based on the displayed information, and update or ask additional questions as necessary. The server then performs calculations based on the user's input, and can propose an optimal life plan.

[0427] Example 1

[0428] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0429] In modern society, it is extremely difficult for users to formulate specific and accurate future life plans. In particular, detailed forecasts of income, expenses, and asset increases and decreases require specialized knowledge, which is a burden for many people. It is also not easy to select appropriate financial products and accurately assess the economic impact of future events. For these reasons, there is a demand for a system that allows users to easily create accurate life plans.

[0430] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0431] In this invention, the server includes a means for receiving a user's basic information and storing it in a database, a means for preprocessing the basic information and automatically generating a cash flow table using a generative AI model, and a means for constructing a user's life plan based on the cash flow table, thereby enabling the user to efficiently formulate a future life plan and select appropriate financial products based on it.

[0432] "Basic user information" refers to personal data necessary to formulate a user's life plan, such as age, income, family composition, financial situation, and future plans.

[0433] A "database" is a system for efficiently storing, managing, and retrieving data.

[0434] "Preprocessing" refers to data transformation operations that convert data into a format that is easy for a generative AI model to process, and includes normalizing numerical data and encoding categorical data.

[0435] A "generative AI model" is an algorithm that uses machine learning and deep learning technologies to automatically generate cash flow tables and life plans from input data.

[0436] A cash flow statement is a document that shows in tabular form income and expenses over a certain period of time, as well as the resulting increase or decrease in assets.

[0437] A "life plan" is a long-term plan that predicts a user's future income, expenses, and asset fluctuations and takes into account the financial impact of certain events.

[0438] "Financial products" refer to products used for asset management and risk management, such as insurance, mortgages, and investment products.

[0439] A "means" is a method or device used to achieve a particular purpose.

[0440] The present invention relates to a system for formulating a life plan for a user and generating a highly accurate cash flow table. Specific embodiments of the system will be described below.

[0441] First, users access the system using a device such as a PC, smartphone, or tablet and enter basic information, including age, income, family composition, current asset status, and future plans (e.g., home purchase, planned childbirth, etc.).

[0442] The server receives the input information and stores it in a database system such as MySQL or PostgreSQL. At the same time, the server preprocesses the received data, which includes normalizing numeric data and encoding categorical data.

[0443] The server then feeds the preprocessed data into a generative AI model, which is built using machine learning and deep learning techniques such as TensorFlow and PyTorch, to automatically generate a cash flow table, detailing yearly income and expenditures and asset fluctuations.

[0444] The server then creates a life plan for the user based on the generated cash flow table. The life plan shows the user's predicted future income and expenses, as well as how their assets will fluctuate. It also takes into account the impact of specific events (e.g., buying a house, paying for their children's education).

[0445] Furthermore, the server will suggest appropriate financial products (e.g., insurance, mortgages, and investment products) based on the user's life plan. This suggestion will select the product that best suits the user's needs and future plans, and explain its benefits in detail.

[0446] The server sends the generated cash flow table, life plan, and information about the proposed financial products to the terminal. The terminal displays this information to the user so that the user can confirm it. The user can adjust their future plans based on the displayed information and enter any unclear points or additional questions into the system again.

[0447] Specific examples

[0448] For example, consider a case where the user is 34 years old, has an annual income of 5 million yen, his family consists of a wife (32 years old) and a child (2 years old), has current savings of 1 million yen, and plans to purchase a home in five years and have a second child in two years.

[0449] The user inputs this information into their device and it is received by the server, which preprocesses it and feeds it to the generative AI model. The model generates a cash flow table, and the server uses that data to create a life plan.

[0450] The life plan includes a loan simulation for purchasing a home and an estimate of the costs of having a second child, showing the impact these expenses will have on future income and expenses.

[0451] Finally, the server will recommend suitable insurance and mortgage loans and send the results to the terminal, where the user can review them and make future plans with peace of mind, reducing future anxiety.

[0452] Prompt Sentence Examples

[0453] "I would like to generate a life plan for the following user: age 34, income 5 million yen, family structure: wife (32 years old) and child (2 years old), current savings of 1 million yen, purchase of a home in 5 years, and plan to have a second child in 2 years."

[0454] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0455] Step 1:

[0456] Users access the system using devices such as PCs, smartphones, and tablets and enter basic information. This basic information includes age, income, family composition, current asset status, and future plans (e.g., home purchase, planned childbirth, etc.). The entered data is sent to the server.

[0457] Input: Basic information entered by the user (age, income, family composition, assets, future plans)

[0458] Output: Basic user information sent to the server

[0459] Step 2:

[0460] The server receives the basic information sent by the user and stores it in a database system such as MySQL or PostgreSQL, while also verifying with a simple query that the data has been stored correctly.

[0461] Input: User basic information

[0462] Output: Basic information stored in the database

[0463] Specific behavior:

[0464] The server receives basic information through an HTTP request.

[0465] Parses the received data and splits it into the appropriate fields.

[0466] The split data is inserted (stored) into the database.

[0467] After storage, queries are run from the database to verify data integrity.

[0468] Step 3:

[0469] The server retrieves the basic information stored in the database and performs preprocessing, which includes normalizing numeric data and encoding categorical data. Normalization aligns the data to a uniform scale, while encoding converts categorical data into numeric values.

[0470] Input: Basic information stored in the database

[0471] Output: Preprocessed data

[0472] Specific behavior:

[0473] Get basic information from the database.

[0474] Standardize numerical data such as income data.

[0475] Encoding categorical data such as family structure (e.g., one-hot encoding).

[0476] Step 4:

[0477] The server feeds the preprocessed data to a generative AI model, which is built using machine learning libraries such as TensorFlow or PyTorch, and sends an API request to pass the data to the model.

[0478] Input: Preprocessed data

[0479] Output: Data passed to the generative AI model

[0480] Specific behavior:

[0481] Convert the preprocessed data into the specified format.

[0482] Send data to the generative AI model endpoint (API).

[0483] Verify that the model was properly fed with data.

[0484] Step 5:

[0485] The generative AI model generates a cash flow table based on the data provided. This cash flow table details annual income and expenditures and asset fluctuations. The generated cash flow table is returned to the server in JSON format.

[0486] Input: The data fed into the generative AI model

[0487] Output: Cash flow table (JSON format)

[0488] Specific behavior:

[0489] The generative AI model uses machine learning algorithms to calculate cash flow tables.

[0490] The calculated result is converted to JSON format and returned to the server.

[0491] Step 6:

[0492] The server then uses the generated cash flow table to construct a life plan for the user, which includes forecasts of future income and expenditure, asset fluctuations, and the financial impact of specific events.

[0493] Input: Generated cash flow table

[0494] Output: User's life plan

[0495] Specific behavior:

[0496] Analyze the generated cash flow table.

[0497] Project long-term income, expense, and asset fluctuations.

[0498] Simulate the impact of a particular event (e.g., buying a home, paying for a child's education).

[0499] Step 7:

[0500] The server proposes appropriate financial products based on the user's life plan, including insurance, mortgages, and investment products. The proposals are optimized to meet the user's needs.

[0501] Input: User's life plan

[0502] Output: Proposed financial instruments

[0503] Specific behavior:

[0504] Analyze life plans to identify user needs.

[0505] Select the most suitable financial product and describe its benefits in detail.

[0506] Step 8:

[0507] The server sends the generated cash flow table, life plan, and information about the proposed financial products to the terminal using the HTTPS protocol to ensure data security.

[0508] Input: Cash flow statement, life plan, proposed financial products

[0509] Output: Information sent to the terminal

[0510] Specific behavior:

[0511] The generated information is then collected and encrypted using the HTTPS protocol.

[0512] The encrypted data is sent to the terminal.

[0513] Step 9:

[0514] The terminal displays the results received from the server to the user via a web browser or dedicated application, allowing the user to visually check cash flow tables, life plans, and proposed financial products.

[0515] Input: Information received from the server

[0516] Output: The results that are displayed to the user

[0517] Specific behavior:

[0518] Parses the received data and displays it in the appropriate format.

[0519] Present information visually in graphs and tables.

[0520] Step 10:

[0521] The user checks the displayed results and uses them as a reference for making future plans. If there are any unclear points or additional questions, they can re-enter basic information into the system and create a new life plan. The system will recalculate to accommodate changes in the scenario (e.g., increased income, new investment plans).

[0522] Input: Basic information re-entered as a result of the display

[0523] Output: New life plan and information

[0524] Specific behavior:

[0525] The user again enters basic information into the system.

[0526] The server receives the input and repeats the same process to generate a new life plan.

[0527] Through the above steps, the system enables users to easily create highly accurate and detailed life plans.

[0528] (Application example 1)

[0529] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0530] With conventional life planning systems, it was difficult to manage and record users' daily income and expenditures, as well as income in real time, making it difficult to provide accurate cash flow tables.In addition, there was a lack of means to visualize this information in an easy-to-understand manner for users, resulting in low user understanding and convenience.

[0531] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0532] In this invention, the server includes means for inputting basic information of a user, means for receiving the basic information, means for automatically generating a cash flow table using a generative AI model based on the basic information, means for constructing a life plan for the user based on the cash flow table, means for proposing related financial products based on the constructed life plan, means for providing the user with information on the generated cash flow table, life plan, and financial products, means for recording and managing the user's daily income and expenditure, expenses, and income in real time, and means for visualizing the information through a user interface. This enables the user to manage and understand their daily income and expenditure and future asset fluctuations in real time based on an accurate cash flow table and life plan.

[0533] "Basic information about the user" refers to information about the user, such as the user's age, income, family structure, financial situation, and future plans.

[0534] A "generative AI model" is a model built using machine learning and deep learning technologies, and is designed to automatically generate cash flow tables and life plans based on input data.

[0535] A "cash flow statement" is a table that details a user's income and expenses and shows the increase or decrease in assets by year.

[0536] A "life plan" is a guideline for predicting and planning a user's future income, expenses, and asset fluctuations.

[0537] "Financial products" are financial products such as insurance, mortgages, and investment products that are provided according to users' needs and future plans.

[0538] "Means for recording and managing in real time" refers to means for recording the user's daily income and expenditure, expenses and income in real time and for managing and understanding them immediately.

[0539] A "user interface" is a display screen or operating means that allows a user to interact with a system and input and confirm information.

[0540] The present invention relates to a system for formulating a user's life plan and generating a highly accurate cash flow table. Specific embodiments of this system will be described below.

[0541] First, the user accesses the system using a device (PC, smartphone, tablet, etc.) and enters basic information, including age, income, family composition, current asset status, and future plans (e.g., home purchase, planned childbirth, etc.).

[0542] The server then receives the basic information and stores it in a database. At the same time, preprocessing involves normalizing numerical data and encoding categorical data. The preprocessed data is then fed into a generative AI model, which automatically generates a cash flow table. The generated cash flow table details annual income and expenditures, as well as asset fluctuations.

[0543] The server then creates a life plan for the user based on the generated cash flow table. The life plan shows the user's predicted future income and expenses, as well as how their assets will fluctuate. It also takes into account the impact of specific events (e.g., buying a home, paying for their children's education). Next, the server recommends appropriate financial products (e.g., insurance, mortgages, investment products) based on the life plan. This recommendation selects the product that best suits the user's needs and future plans, and explains its benefits in detail.

[0544] This system also has the function of recording and managing the user's daily income and expenditure, expenses, and income in real time. The terminal visualizes this information through a user interface, allowing the user to easily check their income and expenditure status. This allows the user to centrally manage their daily income and expenditure and future cash flow.

[0545] Specific examples

[0546] As a concrete example, let's say a 34-year-old user earns 5 million yen a year, his family consists of his wife (32 years old) and a child (2 years old), his current savings are 1 million yen, he plans to buy a house in 5 years and give birth to his second child in 2 years. When this information is entered into the system, the following prompt sentence is generated:

[0547] Example prompt:

[0548] Age: 34

[0549] Income: 5 million yen

[0550] Family: Wife 32, child 2

[0551] Current savings: 1 million yen

[0552] Future plans: Buy a house in 5 years, have a second child in 2 years

[0553] Based on this prompt, the server performs preprocessing and generates a cash flow table and life plan using a generative AI model. The generated cash flow table and life plan are displayed to the user via their device and provided as reference information for the user to make future plans. As a result, the user can feel secure about their life planning.

[0554] As described above, the present invention provides a specific means for assisting users in formulating their life plans, and realizes highly accurate cash flow management.

[0555] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0556] Step 1:

[0557] Users access the system using a terminal and enter basic information, including age, income, family composition, current asset status, and future plans. This basic information becomes the initial input data for the system.

[0558] Step 2:

[0559] The device sends the input basic information to the server, which stores it in a database and initiates the necessary preprocessing, including normalizing numerical data and encoding categorical data to convert it into a format suitable for generative AI models.

[0560] Step 3:

[0561] The server then supplies the preprocessed data to a generative AI model, which then automatically generates a cash flow table based on the input prompts. This cash flow table details annual income and expenditures, as well as asset fluctuations.

[0562] Step 4:

[0563] Based on the generated cash flow table, the server constructs a life plan for the user, which includes predictions of future income and expenditure, asset fluctuations, and the impact of specific events (e.g., home purchase, children's education expenses).

[0564] Step 5:

[0565] The server then recommends suitable financial products based on the user's life plan, including insurance, mortgages, and investment products, and provides a detailed explanation of the benefits of each.

[0566] Step 6:

[0567] The server transmits the generated cash flow table, life plan, and information about the proposed financial products to the terminal, which then visualizes the information through a user interface and displays it for the user to confirm.

[0568] Step 7:

[0569] Users input their daily income and expenditures, expenses, and income, and record and manage them in real time. This information is sent to the server via the terminal, and the server updates the data in real time and reflects it on the user interface.

[0570] Step 8:

[0571] Based on the displayed cash flow table, life plan, and proposed financial products, users can adjust their future plans and take necessary actions, thereby improving the accuracy of their life planning and reducing anxiety.

[0572] Through the above steps, this system can effectively support users in formulating their life plans and achieve highly accurate cash flow management.

[0573] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0574] The present invention relates to a system that formulates a user's life plan, generates a highly accurate cash flow table by combining it with an emotion engine, and proposes financial products that are adapted to the user's psychological state. Specific embodiments of this system are described below.

[0575] First, the user accesses the system using a device (PC, smartphone, tablet, etc.) and enters basic information, including age, income, family composition, current financial situation, and future plans (e.g., home purchase, children's education expenses, etc.). At the same time, the emotion engine recognizes and collects emotional data from the user's facial expressions and tone of voice.

[0576] The device collects the input information and sends it to the server in a standard format such as JSON. Emotion data collected by the emotion engine is also sent at the same time.

[0577] The server verifies the received user information and emotion data and stores them in a database. At the same time, it preprocesses the received information. In addition to normalizing numerical data and encoding categorical data, emotion data is also analyzed.

[0578] The server then supplies the preprocessed data and emotion data to a generative AI model, which then uses existing data and machine learning algorithms to automatically generate a cash flow table. The model also adjusts the cash flow table based on the emotion data, taking into account the user's psychological state.

[0579] The server uses the generated cash flow table to create a life plan for the user. The plan takes into account annual income and expenditure, asset fluctuations, and future events such as home purchases and children's education expenses. Furthermore, based on emotional data, the server prioritizes creating a plan that minimizes stress for the user.

[0580] Furthermore, the server proposes appropriate financial products (e.g., insurance, mortgages, and investment products) based on the user's life plan. These proposals take into account emotional data and select products that are suited to the user's psychological state. For example, a user who is prone to anxiety will be proposed a financial product with low risk.

[0581] The server transmits the generated cash flow table, life plan, and information about the proposed financial products to the terminal. The terminal displays this information to the user and provides a user interface that reflects the emotional data. This allows the user to check the information with peace of mind.

[0582] Specific examples

[0583] For example, consider a case where the user is 34 years old, earns 5 million yen a year, has a family consisting of a wife (32 years old) and a child (2 years old), has current savings of 1 million yen, plans to purchase a home in 5 years and have a second child in 2 years. Also, suppose that emotional data reveals that the user has a personality that is prone to anxiety.

[0584] Users input this information into the system, and the emotion engine collects emotional data from the user's facial expressions and tone of voice. The server receives the information and performs preprocessing and emotional data analysis. The generative AI model generates a cash flow table, and the server further builds a life plan based on the emotional data. In this life plan, low-risk financial products are prioritized for users who are prone to anxiety.

[0585] The server selects appropriate insurance and mortgage plans and sends this information to the device, which then displays cash flow tables, life plans, and insurance and loan proposals to the user, using an interface that reflects emotional data so that the user can confirm them with confidence.

[0586] Through the above processing, this system can easily and accurately formulate a life plan for the user, and by taking emotional data into consideration, it can also reduce the psychological burden on the user.

[0587] The processing flow will be explained below.

[0588] Step 1:

[0589] Users access the system using a terminal and enter basic information and emotional data. Basic information includes age, income, family composition, current assets, and future plans (e.g., home purchase and children's education expenses). Emotional data is collected by the emotion engine from the user's facial expressions and tone of voice.

[0590] Step 2:

[0591] The device collects basic information and emotional data provided by the user and sends it to a server in a standard format such as JSON.

[0592] Step 3:

[0593] The server verifies the received user information and emotion data and stores them in a database. At the same time, it performs preprocessing, including normalizing numerical data and encoding categorical data, and also analyzes the emotion data.

[0594] Step 4:

[0595] The server provides the preprocessed basic information and analyzed emotion data to the generative AI model, which then uses a machine learning algorithm to automatically generate a cash flow table. The model then adjusts the cash flow table based on the emotion data, taking into account the user's psychological state.

[0596] Step 5:

[0597] The server uses the generated cash flow table to create a life plan for the user. The life plan takes into account annual income and expenditure, asset fluctuations, and future events (e.g., home purchases, children's education expenses). It also selects a plan that minimizes stress for the user based on emotional data.

[0598] Step 6:

[0599] The server proposes relevant financial products (insurance, mortgages, investment products, etc.) based on the user's life plan. This proposal takes into account emotional data and selects products that are suited to the user's psychological state. For example, a risk-averse user will be proposed low-risk financial products.

[0600] Step 7:

[0601] The server transmits the generated cash flow table, the life plan, and information on the proposed financial products to the terminal.

[0602] Step 8:

[0603] The terminal displays the information sent from the server. The display uses a user interface that reflects the emotional data, allowing the user to check the information with peace of mind.

[0604] Step 9:

[0605] The user can review the plan based on the displayed information and send feedback to the system again if necessary. Based on this feedback, the server can recalculate and adjust the plan to provide the user with the optimal life plan.

[0606] Specific examples

[0607] For example, consider a case where the user is 34 years old, earns 5 million yen a year, has a family consisting of a wife (32 years old) and a child (2 years old), has current savings of 1 million yen, plans to purchase a home in 5 years and have a second child in 2 years. Also, suppose that emotional data reveals that the user has a personality that is prone to anxiety.

[0608] Users input this information into the system, and the device collects emotional data from the user's facial expressions and tone of voice. The server receives the information, performs preprocessing, and analyzes the emotional data. A generative AI model generates a cash flow table and builds an adjusted life plan taking into account the emotional data.

[0609] The server selects appropriate insurance and mortgage plans and sends this information to the device, which then displays cash flow tables, life plans, and insurance and loan proposals to the user, using an interface that reflects emotional data to allow for ease of review.

[0610] The user can check the information and provide feedback as needed, and the server will make adjustments and provide an optimal life plan. This allows users to easily and accurately formulate plans, and also reduces the psychological burden.

[0611] Example 2

[0612] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0613] While conventional financial planning systems are sufficiently accurate in generating cash flow tables and life plans based on a user's basic information, they do not take into account the user's emotional state. This makes it difficult to recommend appropriate financial products while reducing the user's psychological burden. Furthermore, existing systems have difficulty integrating the collection and analysis of emotional data, making it impossible to realize planning that reflects the user's psychological state in real time.

[0614] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0615] In this invention, the server includes a means for receiving a user's basic information and emotional data, a means for automatically generating a cash flow table using a generative AI model based on the basic information and emotional data, and a means for constructing a user's life plan based on the cash flow table and emotional data. This enables the generation of a highly accurate cash flow table and life plan that takes into account not only the user's basic information but also their emotional state. It also enables the proposal of appropriate financial products that reflect the user's psychological state.

[0616] "Basic user information" refers to personal data necessary for generating a user's life plan and cash flow table, such as age, income, family structure, asset status, and future plans.

[0617] "Emotional data" refers to data that indicates the user's emotional state, such as the user's facial expression or tone of voice, and is used to take the user's psychological state into consideration in the planning process.

[0618] A "generative AI model" is a model that uses machine learning algorithms to automatically generate cash flow tables and life plans based on a user's basic information and emotional data.

[0619] A "cash flow table" is a table that shows the flow of a user's income and expenditures over time, and is important data that forms the basis of a life plan.

[0620] A "life plan" is a plan that takes into account the user's future income and expenditure, changes in assets, future events (e.g., home purchase, children's education expenses), etc., and is intended to assist the user in planning their long-term life.

[0621] "Financial products" are products related to economic activities proposed based on the user's life plan, such as insurance, mortgages, and investment products.

[0622] "Preprocessing" refers to the preparation process, such as data normalization, encoding, and analysis, that allows the generative AI model to properly handle basic user information and emotional data.

[0623] "Means for receiving" is a function for incorporating basic information and emotional data of the user into the system.

[0624] "Means for automatic generation" refers to a function that automatically creates a cash flow statement using machine learning algorithms or generative AI models.

[0625] "Means for construction" is a function that creates a life plan based on a cash flow table and emotional data, taking into account the user's individual needs and psychological state.

[0626] The "means for providing" is a function for presenting the generated cash flow table, life plan, and information about financial products to the user.

[0627] A specific embodiment of this system will be described below.

[0628] Users access the system using devices such as PCs, smartphones, and tablets, and enter basic information such as age, income, family composition, current financial situation, and future plans. The emotion engine also analyzes the user's facial expressions and tone of voice to collect emotional data. This allows data on the user's emotional state to be obtained without the user even realizing it.

[0629] The device collects the user's basic information and emotional data and sends it to the server in a standard format such as JSON. At this stage, hardware such as a webcam and microphone are used to collect the emotional data.

[0630] The server verifies the received user basic information and emotion data and stores them in a database. The stored data then undergoes preprocessing steps, where it is normalized and encoded. For example, numerical data such as age and income are scaled, and categorical data such as family structure and financial status are one-hot encoded. Emotion data is also analyzed in detail using facial expression analysis algorithms and voice analysis algorithms.

[0631] The server then feeds the preprocessed data and emotion data to a generative AI model, which uses machine learning frameworks such as TensorFlow or PyTorch. The model automatically generates a cash flow table based on the existing data and algorithms. The emotion data is also incorporated, resulting in a plan that reflects the user's psychological state.

[0632] The server uses the generated cash flow table to create a life plan for the user. This life plan includes annual income and expenditure, asset changes, and future events (such as buying a home or paying for children's education). Based on the user's emotional data, the server prioritizes plans that minimize stress for the user.

[0633] Furthermore, the server recommends appropriate financial products (e.g., insurance, mortgages, and investment products) based on the user's life plan. By utilizing emotional data, products with low risk are prioritized for users who are prone to anxiety.

[0634] Finally, the server sends the generated cash flow table, life plan, and information on proposed financial products to the terminal. The terminal displays the received information to the user and provides an interface that reflects the emotional data, allowing the user to check the information with peace of mind.

[0635] Specific examples

[0636] For example, consider a user who is 34 years old, has an annual income of 5 million yen, a family consisting of a wife (32 years old) and a two-year-old child, has current savings of 1 million yen, plans to buy a house in five years, and is expecting a second child in two years. Furthermore, consider a case where emotional data reveals that the user is prone to anxiety. When the user enters this information into the system, the emotion engine collects emotional data from the user's facial expressions and tone of voice. The server then receives the information and performs preprocessing and emotional data analysis.

[0637] The generative AI model generates a cash flow table, and the server builds an adjusted life plan based on emotional data. This life plan prioritizes low-risk financial products for users who are prone to anxiety. The server selects appropriate insurance and mortgages and sends this information to the device. The device displays the cash flow table, life plan, and insurance / loan proposals to the user, providing an interface that takes the user's emotions into consideration.

[0638] Prompt Sentence Examples

[0639] "A user is 34 years old, earns 5 million yen a year, has a wife (32) and a child (2 years old), currently has 1 million yen in savings, and plans to purchase a home in five years. The user's emotional data reveals that he is prone to anxiety. Please suggest an appropriate cash flow statement, life plan, and financial products for this user."

[0640] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0641] Step 1:

[0642] The user accesses the system using a terminal and inputs basic information (age, income, family composition, financial situation, future plans). In addition, facial expression and voice data are collected via the terminal's camera and microphone. For example, the input information might be "34 years old, annual income of 5 million yen, family composition of wife and child, current savings of 1 million yen, plan to purchase a home in five years, and expect to have a second child in two years." This information is then sent to the system.

[0643] Input: Basic information and emotion data

[0644] Output: Send basic information and emotion data

[0645] Step 2:

[0646] The device organizes the received basic information and emotion data in a standard format such as JSON and sends it to the server. During this process, it checks whether any data is missing and whether the format is correct. For example, data containing collected facial expressions and tone of voice is sent to the server in JSON format.

[0647] Input: Basic information and emotion data

[0648] Output: Send to server as JSON format data

[0649] Step 3:

[0650] The server stores the received basic information and emotion data in a database. When storing the data in the database, it checks for duplicate data and errors. For example, it organizes the data by user ID and stores it in the database.

[0651] Input: Basic information and emotion data in JSON format

[0652] Output: Data stored in the database

[0653] Step 4:

[0654] The server preprocesses the stored data by normalizing the numerical data, encoding the categorical data, and analyzing the emotional data. For example, it normalizes the income data, performs one-hot encoding on the family structure, and analyzes the facial expression data to quantify the user's emotional state.

[0655] Input: Basic information and emotion data stored in the database

[0656] Output: Preprocessed data

[0657] Step 5:

[0658] The server then supplies the preprocessed data and sentiment data to a generative AI model, which then uses the existing data and machine learning algorithms to generate a cash flow statement. For example, the preprocessed income, expenditure, and sentiment data can be used to automatically generate a cash flow statement that predicts future income and expenditures.

[0659] Input: Preprocessed basic information and emotion data

[0660] Output: Generated cash flow table

[0661] Step 6:

[0662] The server then creates a life plan for the user based on the generated cash flow table. This process takes into account annual income and expenditure, asset fluctuations, and future events such as home purchases and children's education expenses. Furthermore, it also generates a plan that minimizes psychological burden by reflecting emotional data. For example, a plan with fewer risks is suggested for a user who is prone to anxiety.

[0663] Input: Generated cash flow tables and sentiment data

[0664] Output: Constructed life plan

[0665] Step 7:

[0666] The server then recommends appropriate financial products (insurance, mortgages, investment products) based on the user's life plan. Emotional data is also taken into consideration, and low-risk financial products are prioritized for users who are prone to anxiety. For example, safe bonds and low-risk investment trusts are recommended.

[0667] Input: Life plan and emotional data

[0668] Output: Proposed financial instruments

[0669] Step 8:

[0670] The server sends the generated cash flow table, life plan, and information about the proposed financial products to the terminal, allowing the user to visually confirm the necessary information.

[0671] Input: Cash flow statement, life plan, information on financial products

[0672] Output: Sending data to the terminal

[0673] Step 9:

[0674] The device displays the received information in a user interface. This interface reflects the emotional data and provides an environment where users can check information with confidence. For example, cash flow tables and life plans are displayed in graphs and tables, accompanied by detailed explanations of financial products.

[0675] Input: Information sent from the server

[0676] Output: Display on the user interface

[0677] (Application example 2)

[0678] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0679] Current life plan formulation and financial product proposal systems only consider basic user information and do not reflect the user's emotions or psychological state. As a result, the proposed life plan or financial product may not match the user's actual psychological state, causing stress or anxiety. In particular, the psychological burden placed on users when using electronic payment services can be a major problem. Therefore, the present invention aims to provide a system that can generate highly accurate cash flow tables that adapt to the user's psychological state based on detailed information, including the user's emotional data, and that can be used with confidence.

[0680] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting basic information about a user, means for receiving the basic information, means for automatically generating a cash flow table using a generative AI model based on the basic information and emotion data, means for constructing a life plan for the user based on the cash flow table and emotion data, means for proposing related financial products based on the constructed life plan, means for providing the user with information about the generated cash flow table, life plan, and financial products, means for collecting emotion data using a camera and microphone of the terminal, and means for analyzing and processing the emotion data. This makes it possible to provide a system that generates a highly accurate cash flow table that is adapted to the user's psychological state and can be used with confidence.

[0681] "Basic user information" refers to data about the individual user, such as age, income, family composition, financial situation, and future plans.

[0682] "Emotional data" refers to data that indicates the emotional state of a user, analyzed from facial expressions and tone of voice collected using a camera or microphone.

[0683] A "generative AI model" is an artificial intelligence algorithm that automatically generates cash flow tables and life plans based on data.

[0684] A cash flow statement is a table that shows the flow of funds over a certain period of time, based on income and expenses.

[0685] A "life plan" is a long-term life planning plan created taking into consideration the user's future events and income and expenditure.

[0686] "Financial products" refers to products aimed at asset management and risk management, such as insurance, mortgages, and investment products.

[0687] A "terminal" is a device used by a user to input information or collect emotional data, and specifically refers to a smartphone, tablet, etc.

[0688] The "server" is a computer system that receives and processes basic information and emotional data of users, and generates and manages cash flow tables and life plans.

[0689] MODE FOR CARRYING OUT THE INVENTION

[0690] The present invention is a system that automatically generates a cash flow table using a user's basic information and emotional data, and proposes life plans and financial products that are adapted to the user's psychological state based on the emotional data. Specific embodiments of this system are described below.

[0691] System configuration

[0692] 1. Input Method

[0693] Device: A device used by a user to input basic information and collect emotional data, such as a smartphone or tablet.

[0694] 2. Data transmission method

[0695] From the device to the server: The user's basic information and emotional data are sent to the server in JSON format or similar.

[0696] 3. Data processing means

[0697] Server: Preprocesses the received data, normalizing numerical data, encoding categorical data, and analyzing sentiment data. Software used includes TensorFlow and Pandas.

[0698] 4. Generation means

[0699] Generative AI model: An algorithm for generating cash flow tables using preprocessed data, specifically GPT-3 and BERT.

[0700] 5. Life planning tools

[0701] Server: Build a life plan based on the generated cash flow table and emotional data.

[0702] 6. Financial product proposal means

[0703] Server: Based on the constructed life plan, the server proposes financial products (e.g., low-risk investment products or credit cards) that are adapted to the user's psychological state. The software used includes recommendation systems (Scikit-learn, LightFM).

[0704] 7. Display means

[0705] Terminal: Provides users with information such as proposed cash flow tables, life plans, financial products, etc. The software used includes a front-end framework (React Native).

[0706] Processing Details

[0707] Data entry and emotion data collection

[0708] Users use their smartphones to input basic information (age, income, family composition, financial situation, future plans, etc.) At the same time, the smartphone's camera and microphone are used to collect emotional data from facial expressions and tone of voice, which is then analyzed using an emotion recognition library (e.g., Affectiva SDK).

[0709] Data transmission and preprocessing

[0710] Emotion data and basic user information are sent from the device to the server. After receiving the data, the server performs preprocessing. This preprocessing includes normalizing numerical data, encoding categorical data, and analyzing emotional data. Specific preprocessing tools used are TensorFlow and Pandas.

[0711] Applying generative AI models

[0712] The preprocessed data and emotional data are input into a generative AI model (e.g., GPT-3, BERT) to generate a cash flow table. The emotional data is also taken into account, and a cash flow table that takes into account the user's psychological state is output.

[0713] Building life plans and proposing financial products

[0714] The server builds a life plan for the user based on the generated cash flow table. This life plan adapts to the user's psychological state and suggests low-risk investment products and credit cards to reduce anxiety. Scikit-learn and LightFM are used as recommendation systems.

[0715] Displaying Information

[0716] Information such as proposed cash flow tables, life plans, and financial products is displayed on the smartphone screen, and this information is presented to users in a visually easy-to-understand manner using React Native.

[0717] Specific examples

[0718] For example, let's say the user is 40 years old, earns 7 million yen a year, has a wife (38 years old) and two children (ages 10 and 8), has current savings of 3 million yen, and is planning to renovate their home in three years. Emotional data also reveals that the user has a personality that is easily stressed.

[0719] In this case, users enter basic information into their smartphones and collect emotional data. The server receives and preprocesses the data, and the generated cash flow table and life plan are provided to the user. The proposed financial products, including low-risk investment products and home improvement loans, are displayed in an interface that users can easily check.

[0720] Prompt Sentence Examples

[0721] A user is 40 years old, earns 7 million yen a year, has a wife aged 38, two children aged 10 and 8, has current savings of 3 million yen, and plans to renovate their home in three years. Generate a life plan and cash flow table for this user who is prone to stress, and suggest appropriate financial products.

[0722] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0723] Step 1:

[0724] Users use their smartphones to input basic information (age, income, family composition, financial situation, future plans). The smartphone's camera and microphone are also used to collect emotional data from facial expressions and tone of voice. Specifically, analysis is performed using an emotion recognition library (e.g., Affectiva SDK). After the input data is collected, this information is sent from the device to the server. The input is the user's basic information and emotional data, and the output is JSON-formatted data containing this information.

[0725] Step 2:

[0726] The server receives basic information and emotion data sent from the device. It uses JSON format as the reception format and stores the data in an appropriate database. Preprocessing of the received data involves normalizing numerical data (e.g., min-max scaling), encoding categorical data (e.g., one-hot encoding), and analyzing emotion data. Data processing libraries such as TensorFlow and Pandas are used for preprocessing. The input is user data and emotion data in JSON format, and the output is the preprocessed data.

[0727] Step 3:

[0728] Preprocessed basic user information and emotion data are fed into a generative AI model. GPT-3 and BERT are used as generative AI models. This model automatically generates a cash flow table based on the input data. Specifically, the model analyzes the data and performs various calculations to predict the user's income and expenditures. The input is preprocessed data, and the output is the generated cash flow table.

[0729] Step 4:

[0730] The server constructs a life plan for the user based on the generated cash flow table and emotional data. The life plan includes future income and expenditure forecasts and important events (e.g., home purchase, children's education expenses). Based on the emotional data, it prioritizes creating a life plan that will reduce stress and anxiety for the user. This part uses a recommendation system (e.g., Scikit-learn, LightFM). The input is the generated cash flow table and emotional data, and the output is the constructed life plan.

[0731] Step 5:

[0732] The server proposes relevant financial products (e.g., low-risk investment products, insurance) based on the constructed life plan. Based on the emotional data, appropriate products that adapt to the user's psychological state are selected. The input is the constructed life plan and emotional data, and the output is the proposed financial products.

[0733] Step 6:

[0734] The server sends the generated cash flow table, life plan, and information on the proposed financial products to the terminal. The sending method uses a standard format such as JSON. The input is the cash flow table, life plan, and financial product information, and the output is the information sent to the terminal.

[0735] Step 7:

[0736] The device receives the information sent from the server and displays it to the user through a user interface. The software used includes a front-end framework (e.g., React Native). The visually easy-to-understand interface reflects emotional data, allowing the user to check the information with confidence. The input is the information sent from the server, and the output is the information displayed on the user interface.

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

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

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

[0740] [Third embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0753] The present invention relates to a system for formulating a life plan for a user and generating a highly accurate cash flow table. Specific embodiments of the system will be described below.

[0754] First, the user accesses the system using a device (PC, smartphone, tablet, etc.) and enters basic information, including age, income, family composition, current asset status, and future plans (e.g., home purchase, planned childbirth, etc.).

[0755] The server receives the input information and stores it in a database. At the same time, the server pre-processes the received data, which includes normalizing numeric data and encoding categorical data.

[0756] The server then feeds the preprocessed data into a generative AI model, which is built using machine learning and deep learning techniques to automatically generate a cash flow statement, detailing yearly income and expenditures and asset fluctuations.

[0757] The server then creates a life plan for the user based on the generated cash flow table. The life plan shows the user's predicted future income and expenses, as well as how their assets will fluctuate. It also takes into account the impact of specific events (e.g., buying a house, paying for their children's education).

[0758] Furthermore, the server will suggest appropriate financial products (e.g., insurance, mortgages, and investment products) based on the user's life plan. This suggestion will select the product that best suits the user's needs and future plans, and explain its benefits in detail.

[0759] The server sends the generated cash flow table, life plan, and information about the proposed financial products to the terminal. The terminal displays this information to the user so that the user can confirm it. The user can adjust their future plans based on the displayed information and enter any unclear points or additional questions into the system again.

[0760] Specific examples

[0761] For example, consider a case where the user is 34 years old, earns 5 million yen a year, has a wife (32 years old) and a child (2 years old), has current savings of 1 million yen, and plans to purchase a home in five years and have a second child in two years.

[0762] Users input this information into the system, and the server receives it. The server preprocesses the information and feeds it to a generative AI model. The model generates a cash flow table, and the server uses that data to create a life plan.

[0763] The life plan includes a loan simulation for purchasing a home and an estimate of the costs of having a second child, showing the impact these expenses will have on future income and expenses.

[0764] Finally, the server proposes appropriate insurance and mortgage loans and sends the results to the user's device, where they can confirm them. This allows users to plan for the future with peace of mind, reducing anxiety about the future.

[0765] Through the above processing, this system enables users to formulate life plans easily and with high accuracy.

[0766] The processing flow will be explained below.

[0767] Step 1:

[0768] Users access the system using a terminal and enter personal and household information, including age, annual income, family composition, current assets, and future plans (e.g., purchasing a home or paying for children's education).

[0769] Step 2:

[0770] The device collects the input information and sends it to the server, mainly in a standard format such as JSON.

[0771] Step 3:

[0772] The server verifies the received user information and stores it in a database. At the same time, it preprocesses the received information, for example, normalizing numerical data such as age and income, and encoding categorical data.

[0773] Step 4:

[0774] The server feeds the pre-processed data into a generative AI model, which uses existing data and machine learning algorithms to automatically generate cash flow tables.

[0775] Step 5:

[0776] The server uses the generated cash flow table to create a life plan for the user, which takes into account annual income and expenditure, asset fluctuations, and future events such as buying a house or paying for children's education.

[0777] Step 6:

[0778] The server selects relevant financial products (insurance, mortgages, investment products, etc.) based on the life plan and creates proposals.

[0779] Step 7:

[0780] The server transmits the generated cash flow table, life plan, and financial product proposals to the terminal.

[0781] Step 8:

[0782] The terminal displays the information sent from the server, and the user can check details about the cash flow statement, life plan, and proposed financial products.

[0783] Step 9:

[0784] The user can review the plan based on the displayed information, and update or ask additional questions as necessary. The server then performs calculations based on the user's input, and can propose an optimal life plan.

[0785] Example 1

[0786] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0787] In modern society, it is extremely difficult for users to formulate specific and accurate future life plans. In particular, detailed forecasts of income, expenses, and asset increases and decreases require specialized knowledge, which is a burden for many people. It is also not easy to select appropriate financial products and accurately assess the economic impact of future events. For these reasons, there is a demand for a system that allows users to easily create accurate life plans.

[0788] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0789] In this invention, the server includes a means for receiving a user's basic information and storing it in a database, a means for preprocessing the basic information and automatically generating a cash flow table using a generative AI model, and a means for constructing a user's life plan based on the cash flow table, thereby enabling the user to efficiently formulate a future life plan and select appropriate financial products based on it.

[0790] "Basic user information" refers to personal data necessary to formulate a user's life plan, such as age, income, family composition, financial situation, and future plans.

[0791] A "database" is a system for efficiently storing, managing, and retrieving data.

[0792] "Preprocessing" refers to data transformation operations that convert data into a format that is easy for a generative AI model to process, and includes normalizing numerical data and encoding categorical data.

[0793] A "generative AI model" is an algorithm that uses machine learning and deep learning technologies to automatically generate cash flow tables and life plans from input data.

[0794] A cash flow statement is a document that shows in tabular form income and expenses over a certain period of time, as well as the resulting increase or decrease in assets.

[0795] A "life plan" is a long-term plan that predicts a user's future income, expenses, and asset fluctuations and takes into account the financial impact of certain events.

[0796] "Financial products" refer to products used for asset management and risk management, such as insurance, mortgages, and investment products.

[0797] A "means" is a method or device used to achieve a particular purpose.

[0798] The present invention relates to a system for formulating a life plan for a user and generating a highly accurate cash flow table. Specific embodiments of the system will be described below.

[0799] First, users access the system using a device such as a PC, smartphone, or tablet and enter basic information, including age, income, family composition, current asset status, and future plans (e.g., home purchase, planned childbirth, etc.).

[0800] The server receives the input information and stores it in a database system such as MySQL or PostgreSQL. At the same time, the server preprocesses the received data, which includes normalizing numeric data and encoding categorical data.

[0801] The server then feeds the preprocessed data into a generative AI model, which is built using machine learning and deep learning techniques such as TensorFlow and PyTorch, to automatically generate a cash flow table, detailing yearly income and expenditures and asset fluctuations.

[0802] The server then creates a life plan for the user based on the generated cash flow table. The life plan shows the user's predicted future income and expenses, as well as how their assets will fluctuate. It also takes into account the impact of specific events (e.g., buying a house, paying for their children's education).

[0803] Furthermore, the server will suggest appropriate financial products (e.g., insurance, mortgages, and investment products) based on the user's life plan. This suggestion will select the product that best suits the user's needs and future plans, and explain its benefits in detail.

[0804] The server sends the generated cash flow table, life plan, and information about the proposed financial products to the terminal. The terminal displays this information to the user so that the user can confirm it. The user can adjust their future plans based on the displayed information and enter any unclear points or additional questions into the system again.

[0805] Specific examples

[0806] For example, consider a case where the user is 34 years old, has an annual income of 5 million yen, his family consists of a wife (32 years old) and a child (2 years old), has current savings of 1 million yen, and plans to purchase a home in five years and have a second child in two years.

[0807] The user inputs this information into their device and it is received by the server, which preprocesses it and feeds it to the generative AI model. The model generates a cash flow table, and the server uses that data to create a life plan.

[0808] The life plan includes a loan simulation for purchasing a home and an estimate of the costs of having a second child, showing the impact these expenses will have on future income and expenses.

[0809] Finally, the server will recommend suitable insurance and mortgage loans and send the results to the terminal, where the user can review them and make future plans with peace of mind, reducing future anxiety.

[0810] Prompt Sentence Examples

[0811] "I would like to generate a life plan for the following user: age 34, income 5 million yen, family structure: wife (32 years old) and child (2 years old), current savings of 1 million yen, purchase of a home in 5 years, and plan to have a second child in 2 years."

[0812] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0813] Step 1:

[0814] Users access the system using devices such as PCs, smartphones, and tablets and enter basic information. This basic information includes age, income, family composition, current asset status, and future plans (e.g., home purchase, planned childbirth, etc.). The entered data is sent to the server.

[0815] Input: Basic information entered by the user (age, income, family composition, assets, future plans)

[0816] Output: Basic user information sent to the server

[0817] Step 2:

[0818] The server receives the basic information sent by the user and stores it in a database system such as MySQL or PostgreSQL, while also verifying with a simple query that the data has been stored correctly.

[0819] Input: User basic information

[0820] Output: Basic information stored in the database

[0821] Specific behavior:

[0822] The server receives basic information through an HTTP request.

[0823] Parses the received data and splits it into the appropriate fields.

[0824] The split data is inserted (stored) into the database.

[0825] After storage, queries are run from the database to verify data integrity.

[0826] Step 3:

[0827] The server retrieves the basic information stored in the database and performs preprocessing, which includes normalizing numeric data and encoding categorical data. Normalization aligns the data to a uniform scale, while encoding converts categorical data into numeric values.

[0828] Input: Basic information stored in the database

[0829] Output: Preprocessed data

[0830] Specific behavior:

[0831] Get basic information from the database.

[0832] Standardize numerical data such as income data.

[0833] Encoding categorical data such as family structure (e.g., one-hot encoding).

[0834] Step 4:

[0835] The server feeds the preprocessed data to a generative AI model, which is built using machine learning libraries such as TensorFlow or PyTorch, and sends an API request to pass the data to the model.

[0836] Input: Preprocessed data

[0837] Output: Data passed to the generative AI model

[0838] Specific behavior:

[0839] Convert the preprocessed data into the specified format.

[0840] Send data to the generative AI model endpoint (API).

[0841] Verify that the model was properly fed with data.

[0842] Step 5:

[0843] The generative AI model generates a cash flow table based on the data provided. This cash flow table details annual income and expenditures and asset fluctuations. The generated cash flow table is returned to the server in JSON format.

[0844] Input: The data fed into the generative AI model

[0845] Output: Cash flow table (JSON format)

[0846] Specific behavior:

[0847] The generative AI model uses machine learning algorithms to calculate cash flow tables.

[0848] The calculated result is converted to JSON format and returned to the server.

[0849] Step 6:

[0850] The server then uses the generated cash flow table to construct a life plan for the user, which includes forecasts of future income and expenditure, asset fluctuations, and the financial impact of specific events.

[0851] Input: Generated cash flow table

[0852] Output: User's life plan

[0853] Specific behavior:

[0854] Analyze the generated cash flow table.

[0855] Project long-term income, expense, and asset fluctuations.

[0856] Simulate the impact of a particular event (e.g., buying a home, paying for a child's education).

[0857] Step 7:

[0858] The server proposes appropriate financial products based on the user's life plan, including insurance, mortgages, and investment products. The proposals are optimized to meet the user's needs.

[0859] Input: User's life plan

[0860] Output: Proposed financial instruments

[0861] Specific behavior:

[0862] Analyze life plans to identify user needs.

[0863] Select the most suitable financial product and describe its benefits in detail.

[0864] Step 8:

[0865] The server sends the generated cash flow table, life plan, and information about the proposed financial products to the terminal using the HTTPS protocol to ensure data security.

[0866] Input: Cash flow statement, life plan, proposed financial products

[0867] Output: Information sent to the terminal

[0868] Specific behavior:

[0869] The generated information is then collected and encrypted using the HTTPS protocol.

[0870] The encrypted data is sent to the terminal.

[0871] Step 9:

[0872] The terminal displays the results received from the server to the user via a web browser or dedicated application, allowing the user to visually check cash flow tables, life plans, and proposed financial products.

[0873] Input: Information received from the server

[0874] Output: The results that are displayed to the user

[0875] Specific behavior:

[0876] Parses the received data and displays it in the appropriate format.

[0877] Present information visually in graphs and tables.

[0878] Step 10:

[0879] The user checks the displayed results and uses them as a reference for making future plans. If there are any unclear points or additional questions, they can re-enter basic information into the system and create a new life plan. The system will recalculate to accommodate changes in the scenario (e.g., increased income, new investment plans).

[0880] Input: Basic information re-entered as a result of the display

[0881] Output: New life plan and information

[0882] Specific behavior:

[0883] The user again enters basic information into the system.

[0884] The server receives the input and repeats the same process to generate a new life plan.

[0885] Through the above steps, the system enables users to easily create highly accurate and detailed life plans.

[0886] (Application example 1)

[0887] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0888] With conventional life planning systems, it was difficult to manage and record users' daily income and expenditures, as well as income in real time, making it difficult to provide accurate cash flow tables.In addition, there was a lack of means to visualize this information in an easy-to-understand manner for users, resulting in low user understanding and convenience.

[0889] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0890] In this invention, the server includes means for inputting basic information of a user, means for receiving the basic information, means for automatically generating a cash flow table using a generative AI model based on the basic information, means for constructing a life plan for the user based on the cash flow table, means for proposing related financial products based on the constructed life plan, means for providing the user with information on the generated cash flow table, life plan, and financial products, means for recording and managing the user's daily income and expenditure, expenses, and income in real time, and means for visualizing the information through a user interface. This enables the user to manage and understand their daily income and expenditure and future asset fluctuations in real time based on an accurate cash flow table and life plan.

[0891] "Basic information about the user" refers to information about the user, such as the user's age, income, family structure, financial situation, and future plans.

[0892] A "generative AI model" is a model built using machine learning and deep learning technologies, and is designed to automatically generate cash flow tables and life plans based on input data.

[0893] A "cash flow statement" is a table that details a user's income and expenses and shows the increase or decrease in assets by year.

[0894] A "life plan" is a guideline for predicting and planning a user's future income, expenses, and asset fluctuations.

[0895] "Financial products" are financial products such as insurance, mortgages, and investment products that are provided according to users' needs and future plans.

[0896] "Means for recording and managing in real time" refers to means for recording the user's daily income and expenditure, expenses and income in real time and for managing and understanding them immediately.

[0897] A "user interface" is a display screen or operating means that allows a user to interact with a system and input and confirm information.

[0898] The present invention relates to a system for formulating a user's life plan and generating a highly accurate cash flow table. Specific embodiments of this system will be described below.

[0899] First, the user accesses the system using a device (PC, smartphone, tablet, etc.) and enters basic information, including age, income, family composition, current asset status, and future plans (e.g., home purchase, planned childbirth, etc.).

[0900] The server then receives the basic information and stores it in a database. At the same time, preprocessing involves normalizing numerical data and encoding categorical data. The preprocessed data is then fed into a generative AI model, which automatically generates a cash flow table. The generated cash flow table details annual income and expenditures, as well as asset fluctuations.

[0901] The server then creates a life plan for the user based on the generated cash flow table. The life plan shows the user's predicted future income and expenses, as well as how their assets will fluctuate. It also takes into account the impact of specific events (e.g., buying a home, paying for their children's education). Next, the server recommends appropriate financial products (e.g., insurance, mortgages, investment products) based on the life plan. This recommendation selects the product that best suits the user's needs and future plans, and explains its benefits in detail.

[0902] This system also has the function of recording and managing the user's daily income and expenditure, expenses, and income in real time. The terminal visualizes this information through a user interface, allowing the user to easily check their income and expenditure status. This allows the user to centrally manage their daily income and expenditure and future cash flow.

[0903] Specific examples

[0904] As a concrete example, let's say a 34-year-old user earns 5 million yen a year, his family consists of his wife (32 years old) and a child (2 years old), his current savings are 1 million yen, he plans to buy a house in 5 years and give birth to his second child in 2 years. When this information is entered into the system, the following prompt sentence is generated:

[0905] Example prompt:

[0906] Age: 34

[0907] Income: 5 million yen

[0908] Family: Wife 32, child 2

[0909] Current savings: 1 million yen

[0910] Future plans: Buy a house in 5 years, have a second child in 2 years

[0911] Based on this prompt, the server performs preprocessing and generates a cash flow table and life plan using a generative AI model. The generated cash flow table and life plan are displayed to the user via their device and provided as reference information for the user to make future plans. As a result, the user can feel secure about their life planning.

[0912] As described above, the present invention provides a specific means for assisting users in formulating their life plans, and realizes highly accurate cash flow management.

[0913] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0914] Step 1:

[0915] Users access the system using a terminal and enter basic information, including age, income, family composition, current asset status, and future plans. This basic information becomes the initial input data for the system.

[0916] Step 2:

[0917] The device sends the input basic information to the server, which stores it in a database and initiates the necessary preprocessing, including normalizing numerical data and encoding categorical data to convert it into a format suitable for generative AI models.

[0918] Step 3:

[0919] The server then supplies the preprocessed data to a generative AI model, which then automatically generates a cash flow table based on the input prompts. This cash flow table details annual income and expenditures, as well as asset fluctuations.

[0920] Step 4:

[0921] Based on the generated cash flow table, the server constructs a life plan for the user, which includes predictions of future income and expenditure, asset fluctuations, and the impact of specific events (e.g., home purchase, children's education expenses).

[0922] Step 5:

[0923] The server then recommends suitable financial products based on the user's life plan, including insurance, mortgages, and investment products, and provides a detailed explanation of the benefits of each.

[0924] Step 6:

[0925] The server transmits the generated cash flow table, life plan, and information about the proposed financial products to the terminal, which then visualizes the information through a user interface and displays it for the user to confirm.

[0926] Step 7:

[0927] Users input their daily income and expenditures, expenses, and income, and record and manage them in real time. This information is sent to the server via the terminal, and the server updates the data in real time and reflects it on the user interface.

[0928] Step 8:

[0929] Based on the displayed cash flow table, life plan, and proposed financial products, users can adjust their future plans and take necessary actions, thereby improving the accuracy of their life planning and reducing anxiety.

[0930] Through the above steps, this system can effectively support users in formulating their life plans and achieve highly accurate cash flow management.

[0931] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0932] The present invention relates to a system that formulates a user's life plan, generates a highly accurate cash flow table by combining it with an emotion engine, and proposes financial products that are adapted to the user's psychological state. Specific embodiments of this system are described below.

[0933] First, the user accesses the system using a device (PC, smartphone, tablet, etc.) and enters basic information, including age, income, family composition, current financial situation, and future plans (e.g., home purchase, children's education expenses, etc.). At the same time, the emotion engine recognizes and collects emotional data from the user's facial expressions and tone of voice.

[0934] The device collects the input information and sends it to the server in a standard format such as JSON. Emotion data collected by the emotion engine is also sent at the same time.

[0935] The server verifies the received user information and emotion data and stores them in a database. At the same time, it preprocesses the received information. In addition to normalizing numerical data and encoding categorical data, emotion data is also analyzed.

[0936] The server then supplies the preprocessed data and emotion data to a generative AI model, which then uses existing data and machine learning algorithms to automatically generate a cash flow table. The model also adjusts the cash flow table based on the emotion data, taking into account the user's psychological state.

[0937] The server uses the generated cash flow table to create a life plan for the user. The plan takes into account annual income and expenditure, asset fluctuations, and future events such as home purchases and children's education expenses. Furthermore, based on emotional data, the server prioritizes creating a plan that minimizes stress for the user.

[0938] Furthermore, the server proposes appropriate financial products (e.g., insurance, mortgages, and investment products) based on the user's life plan. These proposals take into account emotional data and select products that are suited to the user's psychological state. For example, a user who is prone to anxiety will be proposed a financial product with low risk.

[0939] The server transmits the generated cash flow table, life plan, and information about the proposed financial products to the terminal. The terminal displays this information to the user and provides a user interface that reflects the emotional data. This allows the user to check the information with peace of mind.

[0940] Specific examples

[0941] For example, consider a case where the user is 34 years old, earns 5 million yen a year, has a family consisting of a wife (32 years old) and a child (2 years old), has current savings of 1 million yen, plans to purchase a home in 5 years and have a second child in 2 years. Also, suppose that emotional data reveals that the user has a personality that is prone to anxiety.

[0942] Users input this information into the system, and the emotion engine collects emotional data from the user's facial expressions and tone of voice. The server receives the information and performs preprocessing and emotional data analysis. The generative AI model generates a cash flow table, and the server further builds a life plan based on the emotional data. In this life plan, low-risk financial products are prioritized for users who are prone to anxiety.

[0943] The server selects appropriate insurance and mortgage plans and sends this information to the device, which then displays cash flow tables, life plans, and insurance and loan proposals to the user, using an interface that reflects emotional data so that the user can confirm them with confidence.

[0944] Through the above processing, this system can easily and accurately formulate a life plan for the user, and by taking emotional data into consideration, it can also reduce the psychological burden on the user.

[0945] The processing flow will be explained below.

[0946] Step 1:

[0947] Users access the system using a terminal and enter basic information and emotional data. Basic information includes age, income, family composition, current assets, and future plans (e.g., home purchase and children's education expenses). Emotional data is collected by the emotion engine from the user's facial expressions and tone of voice.

[0948] Step 2:

[0949] The device collects basic information and emotional data provided by the user and sends it to a server in a standard format such as JSON.

[0950] Step 3:

[0951] The server verifies the received user information and emotion data and stores them in a database. At the same time, it performs preprocessing, including normalizing numerical data and encoding categorical data, and also analyzes the emotion data.

[0952] Step 4:

[0953] The server provides the preprocessed basic information and analyzed emotion data to the generative AI model, which then uses a machine learning algorithm to automatically generate a cash flow table. The model then adjusts the cash flow table based on the emotion data, taking into account the user's psychological state.

[0954] Step 5:

[0955] The server uses the generated cash flow table to create a life plan for the user. The life plan takes into account annual income and expenditure, asset fluctuations, and future events (e.g., home purchases, children's education expenses). It also selects a plan that minimizes stress for the user based on emotional data.

[0956] Step 6:

[0957] The server proposes relevant financial products (insurance, mortgages, investment products, etc.) based on the user's life plan. This proposal takes into account emotional data and selects products that are suited to the user's psychological state. For example, a risk-averse user will be proposed low-risk financial products.

[0958] Step 7:

[0959] The server transmits the generated cash flow table, the life plan, and information on the proposed financial products to the terminal.

[0960] Step 8:

[0961] The terminal displays the information sent from the server. The display uses a user interface that reflects the emotional data, allowing the user to check the information with peace of mind.

[0962] Step 9:

[0963] The user can review the plan based on the displayed information and send feedback to the system again if necessary. Based on this feedback, the server can recalculate and adjust the plan to provide the user with the optimal life plan.

[0964] Specific examples

[0965] For example, consider a case where the user is 34 years old, earns 5 million yen a year, has a family consisting of a wife (32 years old) and a child (2 years old), has current savings of 1 million yen, plans to purchase a home in 5 years and have a second child in 2 years. Also, suppose that emotional data reveals that the user has a personality that is prone to anxiety.

[0966] Users input this information into the system, and the device collects emotional data from the user's facial expressions and tone of voice. The server receives the information, performs preprocessing, and analyzes the emotional data. A generative AI model generates a cash flow table and builds an adjusted life plan taking into account the emotional data.

[0967] The server selects appropriate insurance and mortgage plans and sends this information to the device, which then displays cash flow tables, life plans, and insurance and loan proposals to the user, using an interface that reflects emotional data to allow for ease of review.

[0968] The user can check the information and provide feedback as needed, and the server will make adjustments and provide an optimal life plan. This allows users to easily and accurately formulate plans, and also reduces the psychological burden.

[0969] Example 2

[0970] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0971] While conventional financial planning systems are sufficiently accurate in generating cash flow tables and life plans based on a user's basic information, they do not take into account the user's emotional state. This makes it difficult to recommend appropriate financial products while reducing the user's psychological burden. Furthermore, existing systems have difficulty integrating the collection and analysis of emotional data, making it impossible to realize planning that reflects the user's psychological state in real time.

[0972] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0973] In this invention, the server includes a means for receiving a user's basic information and emotional data, a means for automatically generating a cash flow table using a generative AI model based on the basic information and emotional data, and a means for constructing a user's life plan based on the cash flow table and emotional data. This enables the generation of a highly accurate cash flow table and life plan that takes into account not only the user's basic information but also their emotional state. It also enables the proposal of appropriate financial products that reflect the user's psychological state.

[0974] "Basic user information" refers to personal data necessary for generating a user's life plan and cash flow table, such as age, income, family structure, asset status, and future plans.

[0975] "Emotional data" refers to data that indicates the user's emotional state, such as the user's facial expression or tone of voice, and is used to take the user's psychological state into consideration in the planning process.

[0976] A "generative AI model" is a model that uses machine learning algorithms to automatically generate cash flow tables and life plans based on a user's basic information and emotional data.

[0977] A "cash flow table" is a table that shows the flow of a user's income and expenditures over time, and is important data that forms the basis of a life plan.

[0978] A "life plan" is a plan that takes into account the user's future income and expenditure, changes in assets, future events (e.g., home purchase, children's education expenses), etc., and is intended to assist the user in planning their long-term life.

[0979] "Financial products" are products related to economic activities proposed based on the user's life plan, such as insurance, mortgages, and investment products.

[0980] "Preprocessing" refers to the preparation process, such as data normalization, encoding, and analysis, that allows the generative AI model to properly handle basic user information and emotional data.

[0981] "Means for receiving" is a function for incorporating basic information and emotional data of the user into the system.

[0982] "Means for automatic generation" refers to a function that automatically creates a cash flow statement using machine learning algorithms or generative AI models.

[0983] "Means for construction" is a function that creates a life plan based on a cash flow table and emotional data, taking into account the user's individual needs and psychological state.

[0984] The "means for providing" is a function for presenting the generated cash flow table, life plan, and information about financial products to the user.

[0985] A specific embodiment of this system will be described below.

[0986] Users access the system using devices such as PCs, smartphones, and tablets, and enter basic information such as age, income, family composition, current financial situation, and future plans. The emotion engine also analyzes the user's facial expressions and tone of voice to collect emotional data. This allows data on the user's emotional state to be obtained without the user even realizing it.

[0987] The device collects the user's basic information and emotional data and sends it to the server in a standard format such as JSON. At this stage, hardware such as a webcam and microphone are used to collect the emotional data.

[0988] The server verifies the received user basic information and emotion data and stores them in a database. The stored data then undergoes preprocessing steps, where it is normalized and encoded. For example, numerical data such as age and income are scaled, and categorical data such as family structure and financial status are one-hot encoded. Emotion data is also analyzed in detail using facial expression analysis algorithms and voice analysis algorithms.

[0989] The server then feeds the preprocessed data and emotion data to a generative AI model, which uses machine learning frameworks such as TensorFlow or PyTorch. The model automatically generates a cash flow table based on the existing data and algorithms. The emotion data is also incorporated, resulting in a plan that reflects the user's psychological state.

[0990] The server uses the generated cash flow table to create a life plan for the user. This life plan includes annual income and expenditure, asset changes, and future events (such as buying a home or paying for children's education). Based on the user's emotional data, the server prioritizes plans that minimize stress for the user.

[0991] Furthermore, the server recommends appropriate financial products (e.g., insurance, mortgages, and investment products) based on the user's life plan. By utilizing emotional data, products with low risk are prioritized for users who are prone to anxiety.

[0992] Finally, the server sends the generated cash flow table, life plan, and information on proposed financial products to the terminal. The terminal displays the received information to the user and provides an interface that reflects the emotional data, allowing the user to check the information with peace of mind.

[0993] Specific examples

[0994] For example, consider a user who is 34 years old, has an annual income of 5 million yen, a family consisting of a wife (32 years old) and a two-year-old child, has current savings of 1 million yen, plans to buy a house in five years, and is expecting a second child in two years. Furthermore, consider a case where emotional data reveals that the user is prone to anxiety. When the user enters this information into the system, the emotion engine collects emotional data from the user's facial expressions and tone of voice. The server then receives the information and performs preprocessing and emotional data analysis.

[0995] The generative AI model generates a cash flow table, and the server builds an adjusted life plan based on emotional data. This life plan prioritizes low-risk financial products for users who are prone to anxiety. The server selects appropriate insurance and mortgages and sends this information to the device. The device displays the cash flow table, life plan, and insurance / loan proposals to the user, providing an interface that takes the user's emotions into consideration.

[0996] Prompt Sentence Examples

[0997] "A user is 34 years old, earns 5 million yen a year, has a wife (32) and a child (2 years old), currently has 1 million yen in savings, and plans to purchase a home in five years. The user's emotional data reveals that he is prone to anxiety. Please suggest an appropriate cash flow statement, life plan, and financial products for this user."

[0998] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0999] Step 1:

[1000] The user accesses the system using a terminal and inputs basic information (age, income, family composition, financial situation, future plans). In addition, facial expression and voice data are collected via the terminal's camera and microphone. For example, the input information might be "34 years old, annual income of 5 million yen, family composition of wife and child, current savings of 1 million yen, plan to purchase a home in five years, and expect to have a second child in two years." This information is then sent to the system.

[1001] Input: Basic information and emotion data

[1002] Output: Send basic information and emotion data

[1003] Step 2:

[1004] The device organizes the received basic information and emotion data in a standard format such as JSON and sends it to the server. During this process, it checks whether any data is missing and whether the format is correct. For example, data containing collected facial expressions and tone of voice is sent to the server in JSON format.

[1005] Input: Basic information and emotion data

[1006] Output: Send to server as JSON format data

[1007] Step 3:

[1008] The server stores the received basic information and emotion data in a database. When storing the data in the database, it checks for duplicate data and errors. For example, it organizes the data by user ID and stores it in the database.

[1009] Input: Basic information and emotion data in JSON format

[1010] Output: Data stored in the database

[1011] Step 4:

[1012] The server preprocesses the stored data by normalizing the numerical data, encoding the categorical data, and analyzing the emotional data. For example, it normalizes the income data, performs one-hot encoding on the family structure, and analyzes the facial expression data to quantify the user's emotional state.

[1013] Input: Basic information and emotion data stored in the database

[1014] Output: Preprocessed data

[1015] Step 5:

[1016] The server then supplies the preprocessed data and sentiment data to a generative AI model, which then uses the existing data and machine learning algorithms to generate a cash flow statement. For example, the preprocessed income, expenditure, and sentiment data can be used to automatically generate a cash flow statement that predicts future income and expenditures.

[1017] Input: Preprocessed basic information and emotion data

[1018] Output: Generated cash flow table

[1019] Step 6:

[1020] The server then creates a life plan for the user based on the generated cash flow table. This process takes into account annual income and expenditure, asset fluctuations, and future events such as home purchases and children's education expenses. Furthermore, it also generates a plan that minimizes psychological burden by reflecting emotional data. For example, a plan with fewer risks is suggested for a user who is prone to anxiety.

[1021] Input: Generated cash flow tables and sentiment data

[1022] Output: Constructed life plan

[1023] Step 7:

[1024] The server then recommends appropriate financial products (insurance, mortgages, investment products) based on the user's life plan. Emotional data is also taken into consideration, and low-risk financial products are prioritized for users who are prone to anxiety. For example, safe bonds and low-risk investment trusts are recommended.

[1025] Input: Life plan and emotional data

[1026] Output: Proposed financial instruments

[1027] Step 8:

[1028] The server sends the generated cash flow table, life plan, and information about the proposed financial products to the terminal, allowing the user to visually confirm the necessary information.

[1029] Input: Cash flow statement, life plan, information on financial products

[1030] Output: Sending data to the terminal

[1031] Step 9:

[1032] The device displays the received information in a user interface. This interface reflects the emotional data and provides an environment where users can check information with confidence. For example, cash flow tables and life plans are displayed in graphs and tables, accompanied by detailed explanations of financial products.

[1033] Input: Information sent from the server

[1034] Output: Display on the user interface

[1035] (Application example 2)

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

[1037] Current life plan formulation and financial product proposal systems only consider basic user information and do not reflect the user's emotions or psychological state. As a result, the proposed life plan or financial product may not match the user's actual psychological state, causing stress or anxiety. In particular, the psychological burden placed on users when using electronic payment services can be a major problem. Therefore, the present invention aims to provide a system that can generate highly accurate cash flow tables that adapt to the user's psychological state based on detailed information, including the user's emotional data, and that can be used with confidence.

[1038] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting basic information about a user, means for receiving the basic information, means for automatically generating a cash flow table using a generative AI model based on the basic information and emotion data, means for constructing a life plan for the user based on the cash flow table and emotion data, means for proposing related financial products based on the constructed life plan, means for providing the user with information about the generated cash flow table, life plan, and financial products, means for collecting emotion data using a camera and microphone of the terminal, and means for analyzing and processing the emotion data. This makes it possible to provide a system that generates a highly accurate cash flow table that is adapted to the user's psychological state and can be used with confidence.

[1039] "Basic user information" refers to data about the individual user, such as age, income, family composition, financial situation, and future plans.

[1040] "Emotional data" refers to data that indicates the emotional state of a user, analyzed from facial expressions and tone of voice collected using a camera or microphone.

[1041] A "generative AI model" is an artificial intelligence algorithm that automatically generates cash flow tables and life plans based on data.

[1042] A cash flow statement is a table that shows the flow of funds over a certain period of time, based on income and expenses.

[1043] A "life plan" is a long-term life planning plan created taking into consideration the user's future events and income and expenditure.

[1044] "Financial products" refers to products aimed at asset management and risk management, such as insurance, mortgages, and investment products.

[1045] A "terminal" is a device used by a user to input information or collect emotional data, and specifically refers to a smartphone, tablet, etc.

[1046] The "server" is a computer system that receives and processes basic information and emotional data of users, and generates and manages cash flow tables and life plans.

[1047] MODE FOR CARRYING OUT THE INVENTION

[1048] The present invention is a system that automatically generates a cash flow table using a user's basic information and emotional data, and proposes life plans and financial products that are adapted to the user's psychological state based on the emotional data. Specific embodiments of this system are described below.

[1049] System configuration

[1050] 1. Input Method

[1051] Device: A device used by a user to input basic information and collect emotional data, such as a smartphone or tablet.

[1052] 2. Data transmission method

[1053] From the device to the server: The user's basic information and emotional data are sent to the server in JSON format or similar.

[1054] 3. Data processing means

[1055] Server: Preprocesses the received data, normalizing numerical data, encoding categorical data, and analyzing sentiment data. Software used includes TensorFlow and Pandas.

[1056] 4. Generation means

[1057] Generative AI model: An algorithm for generating cash flow tables using preprocessed data, specifically GPT-3 and BERT.

[1058] 5. Life planning tools

[1059] Server: Build a life plan based on the generated cash flow table and emotional data.

[1060] 6. Financial product proposal means

[1061] Server: Based on the constructed life plan, the server proposes financial products (e.g., low-risk investment products or credit cards) that are adapted to the user's psychological state. The software used includes recommendation systems (Scikit-learn, LightFM).

[1062] 7. Display means

[1063] Terminal: Provides users with information such as proposed cash flow tables, life plans, financial products, etc. The software used includes a front-end framework (React Native).

[1064] Processing Details

[1065] Data entry and emotion data collection

[1066] Users use their smartphones to input basic information (age, income, family composition, financial situation, future plans, etc.) At the same time, the smartphone's camera and microphone are used to collect emotional data from facial expressions and tone of voice, which is then analyzed using an emotion recognition library (e.g., Affectiva SDK).

[1067] Data transmission and preprocessing

[1068] Emotion data and basic user information are sent from the device to the server. After receiving the data, the server performs preprocessing. This preprocessing includes normalizing numerical data, encoding categorical data, and analyzing emotional data. Specific preprocessing tools used are TensorFlow and Pandas.

[1069] Applying generative AI models

[1070] The preprocessed data and emotional data are input into a generative AI model (e.g., GPT-3, BERT) to generate a cash flow table. The emotional data is also taken into account, and a cash flow table that takes into account the user's psychological state is output.

[1071] Building life plans and proposing financial products

[1072] The server builds a life plan for the user based on the generated cash flow table. This life plan adapts to the user's psychological state and suggests low-risk investment products and credit cards to reduce anxiety. Scikit-learn and LightFM are used as recommendation systems.

[1073] Displaying Information

[1074] Information such as proposed cash flow tables, life plans, and financial products is displayed on the smartphone screen, and this information is presented to users in a visually easy-to-understand manner using React Native.

[1075] Specific examples

[1076] For example, let's say the user is 40 years old, earns 7 million yen a year, has a wife (38 years old) and two children (ages 10 and 8), has current savings of 3 million yen, and is planning to renovate their home in three years. Emotional data also reveals that the user has a personality that is easily stressed.

[1077] In this case, users enter basic information into their smartphones and collect emotional data. The server receives and preprocesses the data, and the generated cash flow table and life plan are provided to the user. The proposed financial products, including low-risk investment products and home improvement loans, are displayed in an interface that users can easily check.

[1078] Prompt Sentence Examples

[1079] A user is 40 years old, earns 7 million yen a year, has a wife aged 38, two children aged 10 and 8, has current savings of 3 million yen, and plans to renovate their home in three years. Generate a life plan and cash flow table for this user who is prone to stress, and suggest appropriate financial products.

[1080] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1081] Step 1:

[1082] Users use their smartphones to input basic information (age, income, family composition, financial situation, future plans). The smartphone's camera and microphone are also used to collect emotional data from facial expressions and tone of voice. Specifically, analysis is performed using an emotion recognition library (e.g., Affectiva SDK). After the input data is collected, this information is sent from the device to the server. The input is the user's basic information and emotional data, and the output is JSON-formatted data containing this information.

[1083] Step 2:

[1084] The server receives basic information and emotion data sent from the device. It uses JSON format as the reception format and stores the data in an appropriate database. Preprocessing of the received data involves normalizing numerical data (e.g., min-max scaling), encoding categorical data (e.g., one-hot encoding), and analyzing emotion data. Data processing libraries such as TensorFlow and Pandas are used for preprocessing. The input is user data and emotion data in JSON format, and the output is the preprocessed data.

[1085] Step 3:

[1086] Preprocessed basic user information and emotion data are fed into a generative AI model. GPT-3 and BERT are used as generative AI models. This model automatically generates a cash flow table based on the input data. Specifically, the model analyzes the data and performs various calculations to predict the user's income and expenditures. The input is preprocessed data, and the output is the generated cash flow table.

[1087] Step 4:

[1088] The server constructs a life plan for the user based on the generated cash flow table and emotional data. The life plan includes future income and expenditure forecasts and important events (e.g., home purchase, children's education expenses). Based on the emotional data, it prioritizes creating a life plan that will reduce stress and anxiety for the user. This part uses a recommendation system (e.g., Scikit-learn, LightFM). The input is the generated cash flow table and emotional data, and the output is the constructed life plan.

[1089] Step 5:

[1090] The server proposes relevant financial products (e.g., low-risk investment products, insurance) based on the constructed life plan. Based on the emotional data, appropriate products that adapt to the user's psychological state are selected. The input is the constructed life plan and emotional data, and the output is the proposed financial products.

[1091] Step 6:

[1092] The server sends the generated cash flow table, life plan, and information on the proposed financial products to the terminal. The sending method uses a standard format such as JSON. The input is the cash flow table, life plan, and financial product information, and the output is the information sent to the terminal.

[1093] Step 7:

[1094] The device receives the information sent from the server and displays it to the user through a user interface. The software used includes a front-end framework (e.g., React Native). The visually easy-to-understand interface reflects emotional data, allowing the user to check the information with confidence. The input is the information sent from the server, and the output is the information displayed on the user interface.

[1095] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1096] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1097] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1098] [Fourth embodiment]

[1099] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1100] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1101] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1102] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1103] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1104] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1105] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1106] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1107] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1108] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1109] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1110] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1111] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1112] The present invention relates to a system for formulating a life plan for a user and generating a highly accurate cash flow table. Specific embodiments of the system will be described below.

[1113] First, the user accesses the system using a device (PC, smartphone, tablet, etc.) and enters basic information, including age, income, family composition, current asset status, and future plans (e.g., home purchase, planned childbirth, etc.).

[1114] The server receives the input information and stores it in a database. At the same time, the server pre-processes the received data, which includes normalizing numeric data and encoding categorical data.

[1115] The server then feeds the preprocessed data into a generative AI model, which is built using machine learning and deep learning techniques to automatically generate a cash flow statement, detailing yearly income and expenditures and asset fluctuations.

[1116] The server then creates a life plan for the user based on the generated cash flow table. The life plan shows the user's predicted future income and expenses, as well as how their assets will fluctuate. It also takes into account the impact of specific events (e.g., buying a house, paying for their children's education).

[1117] Furthermore, the server will suggest appropriate financial products (e.g., insurance, mortgages, and investment products) based on the user's life plan. This suggestion will select the product that best suits the user's needs and future plans, and explain its benefits in detail.

[1118] The server sends the generated cash flow table, life plan, and information about the proposed financial products to the terminal. The terminal displays this information to the user so that the user can confirm it. The user can adjust their future plans based on the displayed information and enter any unclear points or additional questions into the system again.

[1119] Specific examples

[1120] For example, consider a case where the user is 34 years old, earns 5 million yen a year, has a wife (32 years old) and a child (2 years old), has current savings of 1 million yen, and plans to purchase a home in five years and have a second child in two years.

[1121] Users input this information into the system, and the server receives it. The server preprocesses the information and feeds it to a generative AI model. The model generates a cash flow table, and the server uses that data to create a life plan.

[1122] The life plan includes a loan simulation for purchasing a home and an estimate of the costs of having a second child, showing the impact these expenses will have on future income and expenses.

[1123] Finally, the server proposes appropriate insurance and mortgage loans and sends the results to the user's device, where they can confirm them. This allows users to plan for the future with peace of mind, reducing anxiety about the future.

[1124] Through the above processing, this system enables users to formulate life plans easily and with high accuracy.

[1125] The processing flow will be explained below.

[1126] Step 1:

[1127] Users access the system using a terminal and enter personal and household information, including age, annual income, family composition, current assets, and future plans (e.g., purchasing a home or paying for children's education).

[1128] Step 2:

[1129] The device collects the input information and sends it to the server, mainly in a standard format such as JSON.

[1130] Step 3:

[1131] The server verifies the received user information and stores it in a database. At the same time, it preprocesses the received information, for example, normalizing numerical data such as age and income, and encoding categorical data.

[1132] Step 4:

[1133] The server feeds the pre-processed data into a generative AI model, which uses existing data and machine learning algorithms to automatically generate cash flow tables.

[1134] Step 5:

[1135] The server uses the generated cash flow table to create a life plan for the user, which takes into account annual income and expenditure, asset fluctuations, and future events such as buying a house or paying for children's education.

[1136] Step 6:

[1137] The server selects relevant financial products (insurance, mortgages, investment products, etc.) based on the life plan and creates proposals.

[1138] Step 7:

[1139] The server transmits the generated cash flow table, life plan, and financial product proposals to the terminal.

[1140] Step 8:

[1141] The terminal displays the information sent from the server, and the user can check details about the cash flow statement, life plan, and proposed financial products.

[1142] Step 9:

[1143] The user can review the plan based on the displayed information, and update or ask additional questions as necessary. The server then performs calculations based on the user's input, and can propose an optimal life plan.

[1144] Example 1

[1145] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1146] In modern society, it is extremely difficult for users to formulate specific and accurate future life plans. In particular, detailed forecasts of income, expenses, and asset increases and decreases require specialized knowledge, which is a burden for many people. It is also not easy to select appropriate financial products and accurately assess the economic impact of future events. For these reasons, there is a demand for a system that allows users to easily create accurate life plans.

[1147] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1148] In this invention, the server includes a means for receiving a user's basic information and storing it in a database, a means for preprocessing the basic information and automatically generating a cash flow table using a generative AI model, and a means for constructing a user's life plan based on the cash flow table, thereby enabling the user to efficiently formulate a future life plan and select appropriate financial products based on it.

[1149] "Basic user information" refers to personal data necessary to formulate a user's life plan, such as age, income, family composition, financial situation, and future plans.

[1150] A "database" is a system for efficiently storing, managing, and retrieving data.

[1151] "Preprocessing" refers to data transformation operations that convert data into a format that is easy for a generative AI model to process, and includes normalizing numerical data and encoding categorical data.

[1152] A "generative AI model" is an algorithm that uses machine learning and deep learning technologies to automatically generate cash flow tables and life plans from input data.

[1153] A cash flow statement is a document that shows in tabular form income and expenses over a certain period of time, as well as the resulting increase or decrease in assets.

[1154] A "life plan" is a long-term plan that predicts a user's future income, expenses, and asset fluctuations and takes into account the financial impact of certain events.

[1155] "Financial products" refer to products used for asset management and risk management, such as insurance, mortgages, and investment products.

[1156] A "means" is a method or device used to achieve a particular purpose.

[1157] The present invention relates to a system for formulating a life plan for a user and generating a highly accurate cash flow table. Specific embodiments of the system will be described below.

[1158] First, users access the system using a device such as a PC, smartphone, or tablet and enter basic information, including age, income, family composition, current asset status, and future plans (e.g., home purchase, planned childbirth, etc.).

[1159] The server receives the input information and stores it in a database system such as MySQL or PostgreSQL. At the same time, the server preprocesses the received data, which includes normalizing numeric data and encoding categorical data.

[1160] The server then feeds the preprocessed data into a generative AI model, which is built using machine learning and deep learning techniques such as TensorFlow and PyTorch, to automatically generate a cash flow table, detailing yearly income and expenditures and asset fluctuations.

[1161] The server then creates a life plan for the user based on the generated cash flow table. The life plan shows the user's predicted future income and expenses, as well as how their assets will fluctuate. It also takes into account the impact of specific events (e.g., buying a house, paying for their children's education).

[1162] Furthermore, the server will suggest appropriate financial products (e.g., insurance, mortgages, and investment products) based on the user's life plan. This suggestion will select the product that best suits the user's needs and future plans, and explain its benefits in detail.

[1163] The server sends the generated cash flow table, life plan, and information about the proposed financial products to the terminal. The terminal displays this information to the user so that the user can confirm it. The user can adjust their future plans based on the displayed information and enter any unclear points or additional questions into the system again.

[1164] Specific examples

[1165] For example, consider a case where the user is 34 years old, has an annual income of 5 million yen, his family consists of a wife (32 years old) and a child (2 years old), has current savings of 1 million yen, and plans to purchase a home in five years and have a second child in two years.

[1166] The user inputs this information into their device and it is received by the server, which preprocesses it and feeds it to the generative AI model. The model generates a cash flow table, and the server uses that data to create a life plan.

[1167] The life plan includes a loan simulation for purchasing a home and an estimate of the costs of having a second child, showing the impact these expenses will have on future income and expenses.

[1168] Finally, the server will recommend suitable insurance and mortgage loans and send the results to the terminal, where the user can review them and make future plans with peace of mind, reducing future anxiety.

[1169] Prompt Sentence Examples

[1170] "I would like to generate a life plan for the following user: age 34, income 5 million yen, family structure: wife (32 years old) and child (2 years old), current savings of 1 million yen, purchase of a home in 5 years, and plan to have a second child in 2 years."

[1171] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1172] Step 1:

[1173] Users access the system using devices such as PCs, smartphones, and tablets and enter basic information. This basic information includes age, income, family composition, current asset status, and future plans (e.g., home purchase, planned childbirth, etc.). The entered data is sent to the server.

[1174] Input: Basic information entered by the user (age, income, family composition, assets, future plans)

[1175] Output: Basic user information sent to the server

[1176] Step 2:

[1177] The server receives the basic information sent by the user and stores it in a database system such as MySQL or PostgreSQL, while also verifying with a simple query that the data has been stored correctly.

[1178] Input: User basic information

[1179] Output: Basic information stored in the database

[1180] Specific behavior:

[1181] The server receives basic information through an HTTP request.

[1182] Parses the received data and splits it into the appropriate fields.

[1183] The split data is inserted (stored) into the database.

[1184] After storage, queries are run from the database to verify data integrity.

[1185] Step 3:

[1186] The server retrieves the basic information stored in the database and performs preprocessing, which includes normalizing numeric data and encoding categorical data. Normalization aligns the data to a uniform scale, while encoding converts categorical data into numeric values.

[1187] Input: Basic information stored in the database

[1188] Output: Preprocessed data

[1189] Specific behavior:

[1190] Get basic information from the database.

[1191] Standardize numerical data such as income data.

[1192] Encoding categorical data such as family structure (e.g., one-hot encoding).

[1193] Step 4:

[1194] The server feeds the preprocessed data to a generative AI model, which is built using machine learning libraries such as TensorFlow or PyTorch, and sends an API request to pass the data to the model.

[1195] Input: Preprocessed data

[1196] Output: Data passed to the generative AI model

[1197] Specific behavior:

[1198] Convert the preprocessed data into the specified format.

[1199] Send data to the generative AI model endpoint (API).

[1200] Verify that the model was properly fed with data.

[1201] Step 5:

[1202] The generative AI model generates a cash flow table based on the data provided. This cash flow table details annual income and expenditures and asset fluctuations. The generated cash flow table is returned to the server in JSON format.

[1203] Input: The data fed into the generative AI model

[1204] Output: Cash flow table (JSON format)

[1205] Specific behavior:

[1206] The generative AI model uses machine learning algorithms to calculate cash flow tables.

[1207] The calculated result is converted to JSON format and returned to the server.

[1208] Step 6:

[1209] The server then uses the generated cash flow table to construct a life plan for the user, which includes forecasts of future income and expenditure, asset fluctuations, and the financial impact of specific events.

[1210] Input: Generated cash flow table

[1211] Output: User's life plan

[1212] Specific behavior:

[1213] Analyze the generated cash flow table.

[1214] Project long-term income, expense, and asset fluctuations.

[1215] Simulate the impact of a particular event (e.g., buying a home, paying for a child's education).

[1216] Step 7:

[1217] The server proposes appropriate financial products based on the user's life plan, including insurance, mortgages, and investment products. The proposals are optimized to meet the user's needs.

[1218] Input: User's life plan

[1219] Output: Proposed financial instruments

[1220] Specific behavior:

[1221] Analyze life plans to identify user needs.

[1222] Select the most suitable financial product and describe its benefits in detail.

[1223] Step 8:

[1224] The server sends the generated cash flow table, life plan, and information about the proposed financial products to the terminal using the HTTPS protocol to ensure data security.

[1225] Input: Cash flow statement, life plan, proposed financial products

[1226] Output: Information sent to the terminal

[1227] Specific behavior:

[1228] The generated information is then collected and encrypted using the HTTPS protocol.

[1229] The encrypted data is sent to the terminal.

[1230] Step 9:

[1231] The terminal displays the results received from the server to the user via a web browser or dedicated application, allowing the user to visually check cash flow tables, life plans, and proposed financial products.

[1232] Input: Information received from the server

[1233] Output: The results that are displayed to the user

[1234] Specific behavior:

[1235] Parses the received data and displays it in the appropriate format.

[1236] Present information visually in graphs and tables.

[1237] Step 10:

[1238] The user checks the displayed results and uses them as a reference for making future plans. If there are any unclear points or additional questions, they can re-enter basic information into the system and create a new life plan. The system will recalculate to accommodate changes in the scenario (e.g., increased income, new investment plans).

[1239] Input: Basic information re-entered as a result of the display

[1240] Output: New life plan and information

[1241] Specific behavior:

[1242] The user again enters basic information into the system.

[1243] The server receives the input and repeats the same process to generate a new life plan.

[1244] Through the above steps, the system enables users to easily create highly accurate and detailed life plans.

[1245] (Application example 1)

[1246] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1247] With conventional life planning systems, it was difficult to manage and record users' daily income and expenditures, as well as income in real time, making it difficult to provide accurate cash flow tables.In addition, there was a lack of means to visualize this information in an easy-to-understand manner for users, resulting in low user understanding and convenience.

[1248] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1249] In this invention, the server includes means for inputting basic information of a user, means for receiving the basic information, means for automatically generating a cash flow table using a generative AI model based on the basic information, means for constructing a life plan for the user based on the cash flow table, means for proposing related financial products based on the constructed life plan, means for providing the user with information on the generated cash flow table, life plan, and financial products, means for recording and managing the user's daily income and expenditure, expenses, and income in real time, and means for visualizing the information through a user interface. This enables the user to manage and understand their daily income and expenditure and future asset fluctuations in real time based on an accurate cash flow table and life plan.

[1250] "Basic information about the user" refers to information about the user, such as the user's age, income, family structure, financial situation, and future plans.

[1251] A "generative AI model" is a model built using machine learning and deep learning technologies, and is designed to automatically generate cash flow tables and life plans based on input data.

[1252] A "cash flow statement" is a table that details a user's income and expenses and shows the increase or decrease in assets by year.

[1253] A "life plan" is a guideline for predicting and planning a user's future income, expenses, and asset fluctuations.

[1254] "Financial products" are financial products such as insurance, mortgages, and investment products that are provided according to users' needs and future plans.

[1255] "Means for recording and managing in real time" refers to means for recording the user's daily income and expenditure, expenses and income in real time and for managing and understanding them immediately.

[1256] A "user interface" is a display screen or operating means that allows a user to interact with a system and input and confirm information.

[1257] The present invention relates to a system for formulating a user's life plan and generating a highly accurate cash flow table. Specific embodiments of this system will be described below.

[1258] First, the user accesses the system using a device (PC, smartphone, tablet, etc.) and enters basic information, including age, income, family composition, current asset status, and future plans (e.g., home purchase, planned childbirth, etc.).

[1259] The server then receives the basic information and stores it in a database. At the same time, preprocessing involves normalizing numerical data and encoding categorical data. The preprocessed data is then fed into a generative AI model, which automatically generates a cash flow table. The generated cash flow table details annual income and expenditures, as well as asset fluctuations.

[1260] The server then creates a life plan for the user based on the generated cash flow table. The life plan shows the user's predicted future income and expenses, as well as how their assets will fluctuate. It also takes into account the impact of specific events (e.g., buying a home, paying for their children's education). Next, the server recommends appropriate financial products (e.g., insurance, mortgages, investment products) based on the life plan. This recommendation selects the product that best suits the user's needs and future plans, and explains its benefits in detail.

[1261] This system also has the function of recording and managing the user's daily income and expenditure, expenses, and income in real time. The terminal visualizes this information through a user interface, allowing the user to easily check their income and expenditure status. This allows the user to centrally manage their daily income and expenditure and future cash flow.

[1262] Specific examples

[1263] As a concrete example, let's say a 34-year-old user earns 5 million yen a year, his family consists of his wife (32 years old) and a child (2 years old), his current savings are 1 million yen, he plans to buy a house in 5 years and give birth to his second child in 2 years. When this information is entered into the system, the following prompt sentence is generated:

[1264] Example prompt:

[1265] Age: 34

[1266] Income: 5 million yen

[1267] Family: Wife 32, child 2

[1268] Current savings: 1 million yen

[1269] Future plans: Buy a house in 5 years, have a second child in 2 years

[1270] Based on this prompt, the server performs preprocessing and generates a cash flow table and life plan using a generative AI model. The generated cash flow table and life plan are displayed to the user via their device and provided as reference information for the user to make future plans. As a result, the user can feel secure about their life planning.

[1271] As described above, the present invention provides a specific means for assisting users in formulating their life plans, and realizes highly accurate cash flow management.

[1272] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1273] Step 1:

[1274] Users access the system using a terminal and enter basic information, including age, income, family composition, current asset status, and future plans. This basic information becomes the initial input data for the system.

[1275] Step 2:

[1276] The device sends the input basic information to the server, which stores it in a database and initiates the necessary preprocessing, including normalizing numerical data and encoding categorical data to convert it into a format suitable for generative AI models.

[1277] Step 3:

[1278] The server then supplies the preprocessed data to a generative AI model, which then automatically generates a cash flow table based on the input prompts. This cash flow table details annual income and expenditures, as well as asset fluctuations.

[1279] Step 4:

[1280] Based on the generated cash flow table, the server constructs a life plan for the user, which includes predictions of future income and expenditure, asset fluctuations, and the impact of specific events (e.g., home purchase, children's education expenses).

[1281] Step 5:

[1282] The server then recommends suitable financial products based on the user's life plan, including insurance, mortgages, and investment products, and provides a detailed explanation of the benefits of each.

[1283] Step 6:

[1284] The server transmits the generated cash flow table, life plan, and information about the proposed financial products to the terminal, which then visualizes the information through a user interface and displays it for the user to confirm.

[1285] Step 7:

[1286] Users input their daily income and expenditures, expenses, and income, and record and manage them in real time. This information is sent to the server via the terminal, and the server updates the data in real time and reflects it on the user interface.

[1287] Step 8:

[1288] Based on the displayed cash flow table, life plan, and proposed financial products, users can adjust their future plans and take necessary actions, thereby improving the accuracy of their life planning and reducing anxiety.

[1289] Through the above steps, this system can effectively support users in formulating their life plans and achieve highly accurate cash flow management.

[1290] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1291] The present invention relates to a system that formulates a user's life plan, generates a highly accurate cash flow table by combining it with an emotion engine, and proposes financial products that are adapted to the user's psychological state. Specific embodiments of this system are described below.

[1292] First, the user accesses the system using a device (PC, smartphone, tablet, etc.) and enters basic information, including age, income, family composition, current financial situation, and future plans (e.g., home purchase, children's education expenses, etc.). At the same time, the emotion engine recognizes and collects emotional data from the user's facial expressions and tone of voice.

[1293] The device collects the input information and sends it to the server in a standard format such as JSON. Emotion data collected by the emotion engine is also sent at the same time.

[1294] The server verifies the received user information and emotion data and stores them in a database. At the same time, it preprocesses the received information. In addition to normalizing numerical data and encoding categorical data, emotion data is also analyzed.

[1295] The server then supplies the preprocessed data and emotion data to a generative AI model, which then uses existing data and machine learning algorithms to automatically generate a cash flow table. The model also adjusts the cash flow table based on the emotion data, taking into account the user's psychological state.

[1296] The server uses the generated cash flow table to create a life plan for the user. The plan takes into account annual income and expenditure, asset fluctuations, and future events such as home purchases and children's education expenses. Furthermore, based on emotional data, the server prioritizes creating a plan that minimizes stress for the user.

[1297] Furthermore, the server proposes appropriate financial products (e.g., insurance, mortgages, and investment products) based on the user's life plan. These proposals take into account emotional data and select products that are suited to the user's psychological state. For example, a user who is prone to anxiety will be proposed a financial product with low risk.

[1298] The server transmits the generated cash flow table, life plan, and information about the proposed financial products to the terminal. The terminal displays this information to the user and provides a user interface that reflects the emotional data. This allows the user to check the information with peace of mind.

[1299] Specific examples

[1300] For example, consider a case where the user is 34 years old, earns 5 million yen a year, has a family consisting of a wife (32 years old) and a child (2 years old), has current savings of 1 million yen, plans to purchase a home in 5 years and have a second child in 2 years. Also, suppose that emotional data reveals that the user has a personality that is prone to anxiety.

[1301] Users input this information into the system, and the emotion engine collects emotional data from the user's facial expressions and tone of voice. The server receives the information and performs preprocessing and emotional data analysis. The generative AI model generates a cash flow table, and the server further builds a life plan based on the emotional data. In this life plan, low-risk financial products are prioritized for users who are prone to anxiety.

[1302] The server selects appropriate insurance and mortgage plans and sends this information to the device, which then displays cash flow tables, life plans, and insurance and loan proposals to the user, using an interface that reflects emotional data so that the user can confirm them with confidence.

[1303] Through the above processing, this system can easily and accurately formulate a life plan for the user, and by taking emotional data into consideration, it can also reduce the psychological burden on the user.

[1304] The processing flow will be explained below.

[1305] Step 1:

[1306] Users access the system using a terminal and enter basic information and emotional data. Basic information includes age, income, family composition, current assets, and future plans (e.g., home purchase and children's education expenses). Emotional data is collected by the emotion engine from the user's facial expressions and tone of voice.

[1307] Step 2:

[1308] The device collects basic information and emotional data provided by the user and sends it to a server in a standard format such as JSON.

[1309] Step 3:

[1310] The server verifies the received user information and emotion data and stores them in a database. At the same time, it performs preprocessing, including normalizing numerical data and encoding categorical data, and also analyzes the emotion data.

[1311] Step 4:

[1312] The server provides the preprocessed basic information and analyzed emotion data to the generative AI model, which then uses a machine learning algorithm to automatically generate a cash flow table. The model then adjusts the cash flow table based on the emotion data, taking into account the user's psychological state.

[1313] Step 5:

[1314] The server uses the generated cash flow table to create a life plan for the user. The life plan takes into account annual income and expenditure, asset fluctuations, and future events (e.g., home purchases, children's education expenses). It also selects a plan that minimizes stress for the user based on emotional data.

[1315] Step 6:

[1316] The server proposes relevant financial products (insurance, mortgages, investment products, etc.) based on the user's life plan. This proposal takes into account emotional data and selects products that are suited to the user's psychological state. For example, a risk-averse user will be proposed low-risk financial products.

[1317] Step 7:

[1318] The server transmits the generated cash flow table, the life plan, and information on the proposed financial products to the terminal.

[1319] Step 8:

[1320] The terminal displays the information sent from the server. The display uses a user interface that reflects the emotional data, allowing the user to check the information with peace of mind.

[1321] Step 9:

[1322] The user can review the plan based on the displayed information and send feedback to the system again if necessary. Based on this feedback, the server can recalculate and adjust the plan to provide the user with the optimal life plan.

[1323] Specific examples

[1324] For example, consider a case where the user is 34 years old, earns 5 million yen a year, has a family consisting of a wife (32 years old) and a child (2 years old), has current savings of 1 million yen, plans to purchase a home in 5 years and have a second child in 2 years. Also, suppose that emotional data reveals that the user has a personality that is prone to anxiety.

[1325] Users input this information into the system, and the device collects emotional data from the user's facial expressions and tone of voice. The server receives the information, performs preprocessing, and analyzes the emotional data. A generative AI model generates a cash flow table and builds an adjusted life plan taking into account the emotional data.

[1326] The server selects appropriate insurance and mortgage plans and sends this information to the device, which then displays cash flow tables, life plans, and insurance and loan proposals to the user, using an interface that reflects emotional data to allow for ease of review.

[1327] The user can check the information and provide feedback as needed, and the server will make adjustments and provide an optimal life plan. This allows users to easily and accurately formulate plans, and also reduces the psychological burden.

[1328] Example 2

[1329] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1330] While conventional financial planning systems are sufficiently accurate in generating cash flow tables and life plans based on a user's basic information, they do not take into account the user's emotional state. This makes it difficult to recommend appropriate financial products while reducing the user's psychological burden. Furthermore, existing systems have difficulty integrating the collection and analysis of emotional data, making it impossible to realize planning that reflects the user's psychological state in real time.

[1331] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1332] In this invention, the server includes a means for receiving a user's basic information and emotional data, a means for automatically generating a cash flow table using a generative AI model based on the basic information and emotional data, and a means for constructing a user's life plan based on the cash flow table and emotional data. This enables the generation of a highly accurate cash flow table and life plan that takes into account not only the user's basic information but also their emotional state. It also enables the proposal of appropriate financial products that reflect the user's psychological state.

[1333] "Basic user information" refers to personal data necessary for generating a user's life plan and cash flow table, such as age, income, family structure, asset status, and future plans.

[1334] "Emotional data" refers to data that indicates the user's emotional state, such as the user's facial expression or tone of voice, and is used to take the user's psychological state into consideration in the planning process.

[1335] A "generative AI model" is a model that uses machine learning algorithms to automatically generate cash flow tables and life plans based on a user's basic information and emotional data.

[1336] A "cash flow table" is a table that shows the flow of a user's income and expenditures over time, and is important data that forms the basis of a life plan.

[1337] A "life plan" is a plan that takes into account the user's future income and expenditure, changes in assets, future events (e.g., home purchase, children's education expenses), etc., and is intended to assist the user in planning their long-term life.

[1338] "Financial products" are products related to economic activities proposed based on the user's life plan, such as insurance, mortgages, and investment products.

[1339] "Preprocessing" refers to the preparation process, such as data normalization, encoding, and analysis, that allows the generative AI model to properly handle basic user information and emotional data.

[1340] "Means for receiving" is a function for incorporating basic information and emotional data of the user into the system.

[1341] "Means for automatic generation" refers to a function that automatically creates a cash flow statement using machine learning algorithms or generative AI models.

[1342] "Means for construction" is a function that creates a life plan based on a cash flow table and emotional data, taking into account the user's individual needs and psychological state.

[1343] The "means for providing" is a function for presenting the generated cash flow table, life plan, and information about financial products to the user.

[1344] A specific embodiment of this system will be described below.

[1345] Users access the system using devices such as PCs, smartphones, and tablets, and enter basic information such as age, income, family composition, current financial situation, and future plans. The emotion engine also analyzes the user's facial expressions and tone of voice to collect emotional data. This allows data on the user's emotional state to be obtained without the user even realizing it.

[1346] The device collects the user's basic information and emotional data and sends it to the server in a standard format such as JSON. At this stage, hardware such as a webcam and microphone are used to collect the emotional data.

[1347] The server verifies the received user basic information and emotion data and stores them in a database. The stored data then undergoes preprocessing steps, where it is normalized and encoded. For example, numerical data such as age and income are scaled, and categorical data such as family structure and financial status are one-hot encoded. Emotion data is also analyzed in detail using facial expression analysis algorithms and voice analysis algorithms.

[1348] The server then feeds the preprocessed data and emotion data to a generative AI model, which uses machine learning frameworks such as TensorFlow or PyTorch. The model automatically generates a cash flow table based on the existing data and algorithms. The emotion data is also incorporated, resulting in a plan that reflects the user's psychological state.

[1349] The server uses the generated cash flow table to create a life plan for the user. This life plan includes annual income and expenditure, asset changes, and future events (such as buying a home or paying for children's education). Based on the user's emotional data, the server prioritizes plans that minimize stress for the user.

[1350] Furthermore, the server recommends appropriate financial products (e.g., insurance, mortgages, and investment products) based on the user's life plan. By utilizing emotional data, products with low risk are prioritized for users who are prone to anxiety.

[1351] Finally, the server sends the generated cash flow table, life plan, and information on proposed financial products to the terminal. The terminal displays the received information to the user and provides an interface that reflects the emotional data, allowing the user to check the information with peace of mind.

[1352] Specific examples

[1353] For example, consider a user who is 34 years old, has an annual income of 5 million yen, a family consisting of a wife (32 years old) and a two-year-old child, has current savings of 1 million yen, plans to buy a house in five years, and is expecting a second child in two years. Furthermore, consider a case where emotional data reveals that the user is prone to anxiety. When the user enters this information into the system, the emotion engine collects emotional data from the user's facial expressions and tone of voice. The server then receives the information and performs preprocessing and emotional data analysis.

[1354] The generative AI model generates a cash flow table, and the server builds an adjusted life plan based on emotional data. This life plan prioritizes low-risk financial products for users who are prone to anxiety. The server selects appropriate insurance and mortgages and sends this information to the device. The device displays the cash flow table, life plan, and insurance / loan proposals to the user, providing an interface that takes the user's emotions into consideration.

[1355] Prompt Sentence Examples

[1356] "A user is 34 years old, earns 5 million yen a year, has a wife (32) and a child (2 years old), currently has 1 million yen in savings, and plans to purchase a home in five years. The user's emotional data reveals that he is prone to anxiety. Please suggest an appropriate cash flow statement, life plan, and financial products for this user."

[1357] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1358] Step 1:

[1359] The user accesses the system using a terminal and inputs basic information (age, income, family composition, financial situation, future plans). In addition, facial expression and voice data are collected via the terminal's camera and microphone. For example, the input information might be "34 years old, annual income of 5 million yen, family composition of wife and child, current savings of 1 million yen, plan to purchase a home in five years, and expect to have a second child in two years." This information is then sent to the system.

[1360] Input: Basic information and emotion data

[1361] Output: Send basic information and emotion data

[1362] Step 2:

[1363] The device organizes the received basic information and emotion data in a standard format such as JSON and sends it to the server. During this process, it checks whether any data is missing and whether the format is correct. For example, data containing collected facial expressions and tone of voice is sent to the server in JSON format.

[1364] Input: Basic information and emotion data

[1365] Output: Send to server as JSON format data

[1366] Step 3:

[1367] The server stores the received basic information and emotion data in a database. When storing the data in the database, it checks for duplicate data and errors. For example, it organizes the data by user ID and stores it in the database.

[1368] Input: Basic information and emotion data in JSON format

[1369] Output: Data stored in the database

[1370] Step 4:

[1371] The server preprocesses the stored data by normalizing the numerical data, encoding the categorical data, and analyzing the emotional data. For example, it normalizes the income data, performs one-hot encoding on the family structure, and analyzes the facial expression data to quantify the user's emotional state.

[1372] Input: Basic information and emotion data stored in the database

[1373] Output: Preprocessed data

[1374] Step 5:

[1375] The server then supplies the preprocessed data and sentiment data to a generative AI model, which then uses the existing data and machine learning algorithms to generate a cash flow statement. For example, the preprocessed income, expenditure, and sentiment data can be used to automatically generate a cash flow statement that predicts future income and expenditures.

[1376] Input: Preprocessed basic information and emotion data

[1377] Output: Generated cash flow table

[1378] Step 6:

[1379] The server then creates a life plan for the user based on the generated cash flow table. This process takes into account annual income and expenditure, asset fluctuations, and future events such as home purchases and children's education expenses. Furthermore, it also generates a plan that minimizes psychological burden by reflecting emotional data. For example, a plan with fewer risks is suggested for a user who is prone to anxiety.

[1380] Input: Generated cash flow tables and sentiment data

[1381] Output: Constructed life plan

[1382] Step 7:

[1383] The server then recommends appropriate financial products (insurance, mortgages, investment products) based on the user's life plan. Emotional data is also taken into consideration, and low-risk financial products are prioritized for users who are prone to anxiety. For example, safe bonds and low-risk investment trusts are recommended.

[1384] Input: Life plan and emotional data

[1385] Output: Proposed financial instruments

[1386] Step 8:

[1387] The server sends the generated cash flow table, life plan, and information about the proposed financial products to the terminal, allowing the user to visually confirm the necessary information.

[1388] Input: Cash flow statement, life plan, information on financial products

[1389] Output: Sending data to the terminal

[1390] Step 9:

[1391] The device displays the received information in a user interface. This interface reflects the emotional data and provides an environment where users can check information with confidence. For example, cash flow tables and life plans are displayed in graphs and tables, accompanied by detailed explanations of financial products.

[1392] Input: Information sent from the server

[1393] Output: Display on the user interface

[1394] (Application example 2)

[1395] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1396] Current life plan formulation and financial product proposal systems only consider basic user information and do not reflect the user's emotions or psychological state. As a result, the proposed life plan or financial product may not match the user's actual psychological state, causing stress or anxiety. In particular, the psychological burden placed on users when using electronic payment services can be a major problem. Therefore, the present invention aims to provide a system that can generate highly accurate cash flow tables that adapt to the user's psychological state based on detailed information, including the user's emotional data, and that can be used with confidence.

[1397] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting basic information about a user, means for receiving the basic information, means for automatically generating a cash flow table using a generative AI model based on the basic information and emotion data, means for constructing a life plan for the user based on the cash flow table and emotion data, means for proposing related financial products based on the constructed life plan, means for providing the user with information about the generated cash flow table, life plan, and financial products, means for collecting emotion data using a camera and microphone of the terminal, and means for analyzing and processing the emotion data. This makes it possible to provide a system that generates a highly accurate cash flow table that is adapted to the user's psychological state and can be used with confidence.

[1398] "Basic user information" refers to data about the individual user, such as age, income, family composition, financial situation, and future plans.

[1399] "Emotional data" refers to data that indicates the emotional state of a user, analyzed from facial expressions and tone of voice collected using a camera or microphone.

[1400] A "generative AI model" is an artificial intelligence algorithm that automatically generates cash flow tables and life plans based on data.

[1401] A cash flow statement is a table that shows the flow of funds over a certain period of time, based on income and expenses.

[1402] A "life plan" is a long-term life planning plan created taking into consideration the user's future events and income and expenditure.

[1403] "Financial products" refers to products aimed at asset management and risk management, such as insurance, mortgages, and investment products.

[1404] A "terminal" is a device used by a user to input information or collect emotional data, and specifically refers to a smartphone, tablet, etc.

[1405] The "server" is a computer system that receives and processes basic information and emotional data of users, and generates and manages cash flow tables and life plans.

[1406] MODE FOR CARRYING OUT THE INVENTION

[1407] The present invention is a system that automatically generates a cash flow table using a user's basic information and emotional data, and proposes life plans and financial products that are adapted to the user's psychological state based on the emotional data. Specific embodiments of this system are described below.

[1408] System configuration

[1409] 1. Input Method

[1410] Device: A device used by a user to input basic information and collect emotional data, such as a smartphone or tablet.

[1411] 2. Data transmission method

[1412] From the device to the server: The user's basic information and emotional data are sent to the server in JSON format or similar.

[1413] 3. Data processing means

[1414] Server: Preprocesses the received data, normalizing numerical data, encoding categorical data, and analyzing sentiment data. Software used includes TensorFlow and Pandas.

[1415] 4. Generation means

[1416] Generative AI model: An algorithm for generating cash flow tables using preprocessed data, specifically GPT-3 and BERT.

[1417] 5. Life planning tools

[1418] Server: Build a life plan based on the generated cash flow table and emotional data.

[1419] 6. Financial product proposal means

[1420] Server: Based on the constructed life plan, the server proposes financial products (e.g., low-risk investment products or credit cards) that are adapted to the user's psychological state. The software used includes recommendation systems (Scikit-learn, LightFM).

[1421] 7. Display means

[1422] Terminal: Provides users with information such as proposed cash flow tables, life plans, financial products, etc. The software used includes a front-end framework (React Native).

[1423] Processing Details

[1424] Data entry and emotion data collection

[1425] Users use their smartphones to input basic information (age, income, family composition, financial situation, future plans, etc.) At the same time, the smartphone's camera and microphone are used to collect emotional data from facial expressions and tone of voice, which is then analyzed using an emotion recognition library (e.g., Affectiva SDK).

[1426] Data transmission and preprocessing

[1427] Emotion data and basic user information are sent from the device to the server. After receiving the data, the server performs preprocessing. This preprocessing includes normalizing numerical data, encoding categorical data, and analyzing emotional data. Specific preprocessing tools used are TensorFlow and Pandas.

[1428] Applying generative AI models

[1429] The preprocessed data and emotional data are input into a generative AI model (e.g., GPT-3, BERT) to generate a cash flow table. The emotional data is also taken into account, and a cash flow table that takes into account the user's psychological state is output.

[1430] Building life plans and proposing financial products

[1431] The server builds a life plan for the user based on the generated cash flow table. This life plan adapts to the user's psychological state and suggests low-risk investment products and credit cards to reduce anxiety. Scikit-learn and LightFM are used as recommendation systems.

[1432] Displaying Information

[1433] Information such as proposed cash flow tables, life plans, and financial products is displayed on the smartphone screen, and this information is presented to users in a visually easy-to-understand manner using React Native.

[1434] Specific examples

[1435] For example, let's say the user is 40 years old, earns 7 million yen a year, has a wife (38 years old) and two children (ages 10 and 8), has current savings of 3 million yen, and is planning to renovate their home in three years. Emotional data also reveals that the user has a personality that is easily stressed.

[1436] In this case, users enter basic information into their smartphones and collect emotional data. The server receives and preprocesses the data, and the generated cash flow table and life plan are provided to the user. The proposed financial products, including low-risk investment products and home improvement loans, are displayed in an interface that users can easily check.

[1437] Prompt Sentence Examples

[1438] A user is 40 years old, earns 7 million yen a year, has a wife aged 38, two children aged 10 and 8, has current savings of 3 million yen, and plans to renovate their home in three years. Generate a life plan and cash flow table for this user who is prone to stress, and suggest appropriate financial products.

[1439] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1440] Step 1:

[1441] Users use their smartphones to input basic information (age, income, family composition, financial situation, future plans). The smartphone's camera and microphone are also used to collect emotional data from facial expressions and tone of voice. Specifically, analysis is performed using an emotion recognition library (e.g., Affectiva SDK). After the input data is collected, this information is sent from the device to the server. The input is the user's basic information and emotional data, and the output is JSON-formatted data containing this information.

[1442] Step 2:

[1443] The server receives basic information and emotion data sent from the device. It uses JSON format as the reception format and stores the data in an appropriate database. Preprocessing of the received data involves normalizing numerical data (e.g., min-max scaling), encoding categorical data (e.g., one-hot encoding), and analyzing emotion data. Data processing libraries such as TensorFlow and Pandas are used for preprocessing. The input is user data and emotion data in JSON format, and the output is the preprocessed data.

[1444] Step 3:

[1445] Preprocessed basic user information and emotion data are fed into a generative AI model. GPT-3 and BERT are used as generative AI models. This model automatically generates a cash flow table based on the input data. Specifically, the model analyzes the data and performs various calculations to predict the user's income and expenditures. The input is preprocessed data, and the output is the generated cash flow table.

[1446] Step 4:

[1447] The server constructs a life plan for the user based on the generated cash flow table and emotional data. The life plan includes future income and expenditure forecasts and important events (e.g., home purchase, children's education expenses). Based on the emotional data, it prioritizes creating a life plan that will reduce stress and anxiety for the user. This part uses a recommendation system (e.g., Scikit-learn, LightFM). The input is the generated cash flow table and emotional data, and the output is the constructed life plan.

[1448] Step 5:

[1449] The server proposes relevant financial products (e.g., low-risk investment products, insurance) based on the constructed life plan. Based on the emotional data, appropriate products that adapt to the user's psychological state are selected. The input is the constructed life plan and emotional data, and the output is the proposed financial products.

[1450] Step 6:

[1451] The server sends the generated cash flow table, life plan, and information on the proposed financial products to the terminal. The sending method uses a standard format such as JSON. The input is the cash flow table, life plan, and financial product information, and the output is the information sent to the terminal.

[1452] Step 7:

[1453] The device receives the information sent from the server and displays it to the user through a user interface. The software used includes a front-end framework (e.g., React Native). The visually easy-to-understand interface reflects emotional data, allowing the user to check the information with confidence. The input is the information sent from the server, and the output is the information displayed on the user interface.

[1454] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1455] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1456] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1457] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1458] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1459] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1460] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1461] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1462] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1463] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1464] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1465] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1466] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1467] 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.

[1468] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1469] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1470] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1471] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1472] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1473] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1474] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1475] The following is further disclosed regarding the above embodiment.

[1476] (Claim 1)

[1477] a means for inputting basic information about a user;

[1478] means for receiving the basic information;

[1479] A means for automatically generating a cash flow table using a generation AI model based on the basic information;

[1480] A means for constructing a life plan for a user based on the cash flow table;

[1481] A means of proposing relevant financial products based on the constructed life plan;

[1482] A means for providing the user with information on the generated cash flow table, life plans, and financial products;

[1483] A system including:

[1484] (Claim 2)

[1485] 2. The system according to claim 1, wherein the basic information of the user includes age, income, family structure, asset status, and future plans.

[1486] (Claim 3)

[1487] 2. The system of claim 1, wherein the generative AI model comprises means for normalizing numerical data and encoding categorical data during a preprocessing stage.

[1488] "Example 1"

[1489] (Claim 1)

[1490] a means for inputting basic information about a user;

[1491] means for receiving the basic information and storing it in a database;

[1492] A means for preprocessing the basic information and automatically generating a cash flow table using a generation AI model;

[1493] A means for constructing a life plan for a user based on the cash flow table;

[1494] A means of proposing relevant financial products based on the constructed life plan;

[1495] A means for providing the user with information on the generated cash flow table, life plans, and financial products;

[1496] A system including:

[1497] (Claim 2)

[1498] 2. The system according to claim 1, wherein the basic information of the user includes age, income, family structure, asset status, and future plans.

[1499] (Claim 3)

[1500] 2. The system of claim 1, wherein the generative AI model comprises means for normalizing numerical data and encoding categorical data during a preprocessing stage.

[1501] "Application Example 1"

[1502] (Claim 1)

[1503] a means for inputting basic information about a user;

[1504] means for receiving the basic information;

[1505] A means for automatically generating a cash flow table using a generation AI model based on the basic information;

[1506] A means for constructing a life plan for a user based on the cash flow table;

[1507] A means of proposing relevant financial products based on the constructed life plan;

[1508] A means for providing the user with information on the generated cash flow table, life plans, and financial products;

[1509] A means for recording and managing the user's daily income, expenditures, and income in real time;

[1510] A means for visualizing the information through a user interface.

[1511] Including system.

[1512] (Claim 2)

[1513] 2. The system according to claim 1, wherein the basic information of the user includes age, income, family structure, asset status, and future plans.

[1514] (Claim 3)

[1515] 2. The system of claim 1, wherein the generative AI model comprises means for normalizing numerical data and encoding categorical data during a preprocessing stage.

[1516] "Example 2: Combining Emotion Engines"

[1517] (Claim 1)

[1518] A means for inputting basic information and emotion data of a user;

[1519] means for receiving the basic information and emotion data;

[1520] means for automatically generating a cash flow table using a generation AI model based on the basic information and emotion data;

[1521] means for constructing a life plan for a user based on the cash flow table and emotion data;

[1522] A means of proposing relevant financial products based on the constructed life plan;

[1523] A means for providing the user with information on the generated cash flow table, life plans, and financial products;

[1524] A system including:

[1525] (Claim 2)

[1526] 2. The system according to claim 1, wherein the basic information of the user includes age, income, family structure, financial situation, and future plans, and further includes the user's facial expression and tone of voice as emotional data.

[1527] (Claim 3)

[1528] The system of claim 1, characterized in that the generative AI model comprises means for normalizing numerical data and encoding categorical data in the preprocessing stage, as well as analyzing emotional data.

[1529] "Application example 2 when combining emotion engines"

[1530] (Claim 1)

[1531] a means for inputting basic information about a user;

[1532] means for receiving the basic information;

[1533] means for automatically generating a cash flow table using a generation AI model based on the basic information and emotion data;

[1534] means for constructing a life plan for a user based on the cash flow table and emotion data;

[1535] A means of proposing relevant financial products based on the constructed life plan;

[1536] A means for providing the user with information on the generated cash flow table, life plans, and financial products;

[1537] a means for collecting emotion data using a camera and microphone of the device;

[1538] means for analyzing and processing said emotion data;

[1539] A system including:

[1540] (Claim 2)

[1541] 2. The system according to claim 1, wherein the basic information of the user includes age, income, family structure, financial situation, future plans, and collected emotional data.

[1542] (Claim 3)

[1543] 2. The system of claim 1, wherein the generative AI model comprises means for normalizing numerical data and encoding categorical data, as well as analyzing emotional data, in a preprocessing stage. [Explanation of symbols]

[1544] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for inputting basic information about a user; means for receiving the basic information; A means for automatically generating a cash flow table using a generation AI model based on the basic information; A means for constructing a life plan for a user based on the cash flow table; A means of proposing relevant financial products based on the constructed life plan; A means for providing the user with information on the generated cash flow table, life plans, and financial products; A system including:

2. 2. The system according to claim 1, wherein the basic information of the user includes age, income, family structure, asset status, and future plans.

3. 10. The system of claim 1, wherein the generative AI model comprises means for normalizing numerical data and encoding categorical data in a preprocessing stage.

Images