system

Abstract

Provide a system. 【Solution means】 Financial data connection means, Financial information connection means, Information classification means for classifying personal financial behavior information collected using the financial information connection means, Information processing means for storing and analyzing the information obtained by the information classification means, Proposal generation means for generating proposals for improving an individual's financial situation based on the analysis results of the information processing means, Information providing means for providing the proposals obtained by the proposal generation means to an individual, Visual display means for visually displaying an individual's income and expenditure information in real time, Investment proposal means for making specific investment proposals based on an individual's goals, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Many individuals have difficulty accurately understanding and appropriately managing their financial situations, often resulting in wasteful spending and poor investment decisions. In particular, for users with insufficient financial knowledge, it is difficult to identify effective asset management and savings methods, often lacking financial stability. The present invention aims to solve these problems and provide means for users to easily understand their financial status and enable appropriate asset management and savings.

Means for Solving the Problems

[0005] The present invention solves the above problems by providing a means for collecting user financial transaction data using financial data connection means, a means for data classification based on this data, a means for data processing for analysis, a means for generating advice for improving financial status, and an information provision means. Specifically, it has a function to optimize the investment portfolio and select investment products according to the user's financial goals. Furthermore, by classifying financial transaction data by category and identifying unnecessary spending, it provides specific guidelines for users to manage their spending and make effective savings.

[0006] "Financial data connection means" refers to an interface for securely collecting data from financial institutions such as users' bank accounts and credit cards.

[0007] A "data classification system" refers to a system that has the function of organizing collected financial transaction data based on specific criteria or categories (e.g., food expenses, transportation expenses, etc.).

[0008] "Data processing means" refers to a system that has the function of analyzing classified data and evaluating the financial status of users.

[0009] An "advice generation system" refers to a system that has the function of automatically creating specific suggestions and advice for improving a user's financial situation based on the analysis results from data processing.

[0010] "Information provision means" refers to an interface for displaying or delivering generated advice and data in a way that is easy for users to understand.

[0011] An "investment portfolio" refers to a combination of investment products optimized according to the user's investment goals and risk tolerance.

[0012] "Wasteful spending" refers to expenses that are deemed unnecessary or excessive in relation to the user's lifestyle or financial goals. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is a comprehensive system that supports personal financial management and is specifically implemented by the following means. First, the server acquires the user's bank account and credit card transaction data via financial data connection means. This allows financial information to be collected automatically without the user having to manually enter data.

[0035] Subsequently, the server's data classification system categorizes the acquired transaction data into categories such as food expenses, transportation expenses, and entertainment expenses. This process is performed to make it easier to clearly understand the user's spending habits.

[0036] The classified data is analyzed by the server's data processing capabilities. During the analysis, past spending trends and income fluctuations are examined, and the user's financial status is assessed. Furthermore, appropriate investment decisions are made based on the user's risk tolerance and specific goals (e.g., purchasing a home, saving for retirement).

[0037] Based on the analysis results, the server's advice generation system creates specific suggestions for improving the user's finances. These include suggestions for reducing unnecessary spending and selecting investment products that align with the user's goals.

[0038] The generated advice is presented to the user using the terminal's information delivery system. The user interface displays the information clearly and visually, making it easy for the user to understand and implement the advice.

[0039] For example, if user A sets a goal of "buying a home in five years," the server will propose the optimal investment plan to achieve that goal. This plan will include financial products and saving methods to save the target amount while minimizing risk.

[0040] Thus, the present invention supports economic stability and the achievement of future goals by providing a system that allows users to easily manage their own financial situation and select appropriate asset management and saving methods.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server retrieves user bank account and credit card transaction data through financial institutions' APIs. This data is collected securely using the user's authentication information. This data includes transaction details, transaction date, and amount.

[0044] Step 2:

[0045] The server's data classification mechanism categorizes acquired transaction data into categories such as food expenses, transportation expenses, utility expenses, and entertainment expenses. This function analyzes the content of each transaction and automatically organizes it based on a predefined category list.

[0046] Step 3:

[0047] The server's data processing system analyzes classified data to understand the user's income and expenditure balance and spending patterns. It also identifies fluctuations in income and spending trends based on past transaction history to evaluate the user's financial situation.

[0048] Step 4:

[0049] Based on the analysis results, the server uses an advice generation mechanism to generate asset management suggestions tailored to the user. These suggestions include investment products and portfolios that align with the user's set risk tolerance and financial goals.

[0050] Step 5:

[0051] The server's advice generation mechanism analyzes user spending data to identify unnecessary expenses. Based on these identified unnecessary expenses, it provides specific savings suggestions, indicating how much can be saved in each category.

[0052] Step 6:

[0053] The terminal displays advice and suggestions received from the server on the user interface. To ensure user understanding, the information is presented visually using graphs and tables.

[0054] Step 7:

[0055] Users review the advice displayed on their device and adjust their financial goals and risk tolerance as needed. This information is sent from the device to the server and used again for further analysis.

[0056] Step 8:

[0057] The server records new user inputs and settings in a database, which are then used for subsequent suggestions and analyses. This ensures that the system is always operated based on the latest user information.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] In personal financial management, manually collecting and analyzing transaction data from multiple financial institutions is time-consuming and labor-intensive, making it difficult to identify unnecessary spending and make appropriate investment decisions. As a result, users face the challenge of not being able to efficiently manage their assets to achieve their future financial goals.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for acquiring financial data, means for classifying data, means for processing data, means for generating suggestions, and means for presenting information. This enables the automatic collection and organization of an individual's economic transaction data, visualization of their economic situation including unnecessary spending, and the proposal of optimal asset management tailored to the user's goals.

[0063] A "financial data acquisition method" is an interface for automatically collecting users' economic transaction data from external financial institutions.

[0064] A "data classification method" is a function that analyzes acquired economic transaction data and divides each item into predefined categories.

[0065] A "data processing tool" is a function that analyzes the user's spending and income trends based on classified data and evaluates their financial situation.

[0066] A "proposal generation method" is a system that creates specific proposals for optimal asset management and achieving economic goals for the user based on the results of data processing and analysis.

[0067] An "information presentation method" is a function that visually communicates generated suggestions to the user through a user interface.

[0068] This invention is an integrated system for efficiently managing and optimizing a user's personal financial activities. This system functions through the coordinated efforts of a server, a terminal, and the user.

[0069] The server securely retrieves transaction data from multiple financial institutions, such as the user's bank account and credit card company, using financial data acquisition methods. Specifically, it can periodically update data using the APIs of each financial institution. The acquired data is stored in an encrypted format in the server's database, ensuring user privacy.

[0070] Next, the server uses a data classification mechanism to automatically categorize the acquired transaction data. For example, groceries purchased at a supermarket are classified as food expenses, and the use of public transportation is classified as transportation expenses. This automated classification allows users to efficiently track their spending.

[0071] Subsequently, the server analyzes the classified data using data processing tools to understand past spending trends and fluctuations in income. It can also apply machine learning algorithms to predict future income and expenses. This data processing allows for a detailed assessment of the user's financial situation.

[0072] The server uses a proposal generation mechanism to generate specific suggestions for financial improvement for the user based on the analysis results. These suggestions include ideas for reducing wasteful spending and selecting the optimal financial products to help the user achieve their goals.

[0073] The generated suggestions are transmitted to the terminal via an information presentation system and presented to the user visually and intuitively. The user interface is designed to be easily understood, allowing the user to obtain information to take concrete action.

[0074] For example, if a user sets a goal of "buying a house in five years," the system will propose a savings plan and investment strategy necessary to achieve that goal. This selection will include financial products with reduced risk. Advice on everyday saving methods will also be provided.

[0075] An example of a prompt for a generating AI model might be: "Based on User A's current spending habits and financial goals, please suggest the optimal investment and saving strategies for purchasing a home within five years."

[0076] In this way, users can accurately manage their financial situation and take strategic actions to achieve their future goals.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server uses financial data acquisition methods to retrieve user transaction data from each financial institution's API. This input data includes transaction date and time, amount, and trading partner information. The server automatically collects this data daily and stores it in an encrypted state in the database. This process minimizes manual work for the user and ensures accurate data collection.

[0080] Step 2:

[0081] The server classifies the acquired transaction data using data classification methods. This process analyzes the content of each input transaction and categorizes it (e.g., food expenses, transportation expenses, utilities). Specifically, categories are assigned based on the name of the trading partner and the transaction details using natural language processing technology. The output includes category labels for each transaction, allowing the user to understand the breakdown of their expenses.

[0082] Step 3:

[0083] The server analyzes the classified data using various data processing tools. Historical expenditure and income data are used as input. The analysis employs machine learning algorithms to evaluate expenditure and income trends and predict future financial outcomes. The output data includes an assessment of the user's current financial situation, along with future forecasts.

[0084] Step 4:

[0085] The server generates specific financial improvement proposals based on data analysis results using a proposal generation mechanism. Inputs include analysis results and user-defined financial targets. The generated proposals include specific savings advice and recommended investment products. The output is optimized proposals tailored to the user's individual circumstances.

[0086] Step 5:

[0087] The terminal presents generated suggestions to the user through an information display mechanism. It receives suggestion information provided by the server as input. By forming visual dashboards and charts and providing users with easily understandable, visualized information as output, users can easily understand the suggestions and use them to take actual action.

[0088] (Application Example 1)

[0089] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0090] In personal financial management, there is a need for a unified system that automatically collects and classifies financial activity information, provides concrete asset management suggestions based on analysis, and presents spending information in real time. However, conventional systems have not adequately integrated these functions, and have not provided sufficient support for users to effectively improve their financial situation.

[0091] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0092] In this invention, the server includes financial information connection means, information classification means for classifying an individual's financial activity information collected using the financial information connection means, and information processing means for storing and analyzing the information obtained by the information classification means. This makes it possible for individuals to quickly and easily grasp their own financial situation and receive specific asset management suggestions.

[0093] A "financial information connection method" is a means that securely connects financial institution data, such as an individual's bank and credit card information, and has the function of automatically acquiring financial activity information.

[0094] An "information classification tool" is a means that has the function of organizing collected financial activity information into categories and classifying it into a format that can be easily analyzed.

[0095] An "information processing means" is a means that stores classified information and has the function of analyzing income and expenditure trends based on that information.

[0096] A "proposal generation means" is a means that has the function of automatically generating specific proposals for improving an individual's financial situation based on the analysis results of an information processing means.

[0097] An "information provision method" is a means that has the function of visually displaying generated suggestions to an individual and providing them as practical advice.

[0098] A "visual display method" is a means that visualizes an individual's income and expenditure data in an easy-to-understand manner, and has the function of supporting a real-time understanding of their financial situation.

[0099] An "investment proposal tool" is a tool that has the function of selecting and proposing specific steps and financial products for efficient asset management according to an individual's goals.

[0100] This invention is implemented as a system to streamline personal financial management and provide concrete asset management suggestions. The system automatically acquires personal financial information, analyzes and classifies the collected information, and provides advice for financial improvement.

[0101] The server uses "financial information connection means" to securely connect to the user's bank and credit card information and collect financial activity information. This uses highly secure APIs and data security protocols. Next, "information classification means" are used to classify each transaction into categories and clarify the user's spending trends.

[0102] The collected and categorized information is analyzed by an "information processing system" to evaluate the individual's income and expenditure patterns. Here, data analysis is performed using programming languages ​​such as Python and the Pandas library. Based on the analysis results, a "proposal generation system" generates specific and practical suggestions to improve the user's financial situation. These suggestions are generated using an AI module to construct an optimal asset management plan tailored to the user's goals.

[0103] Ultimately, the "information delivery tools" are utilized, and the generated proposals are delivered to the user through a user card widget or mobile application. Here, a visually intuitive interface is designed using React Native. This allows users to easily understand and implement the financial proposals.

[0104] For example, if a user sets a goal of "saving money for a trip in one year," the system will analyze their monthly expenses and provide specific advice such as, "Let's cut back on eating out this month and increase your savings." In this case, an example of a prompt message generated by the AI ​​model would be, "Based on the user's monthly spending data, please generate advice on how to save money for a trip in one year."

[0105] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0106] Step 1:

[0107] The server securely obtains the user's bank and credit card information through financial information connectivity. Inputs include the user's authentication information and transaction data from financial institutions. Output is the secure aggregation of transaction information on the server. Specifically, it uses APIs to access financial institution databases and asynchronously collects the necessary transaction data.

[0108] Step 2:

[0109] The server categorizes the financial transaction information obtained using an information classification system. The input is the transaction data collected in step 1, and the output is transaction information organized by category. Specifically, it creates a data frame using the Pandas library and applies an algorithm to classify the data into existing categories such as "food expenses" and "transportation expenses."

[0110] Step 3:

[0111] The server uses information processing tools to analyze the classified data. The input here is the category-specific transaction data obtained in step 2, and the output is the analysis of individual spending trends based on the classified data. Specifically, statistical methods (e.g., moving average, trend analysis) are applied to aggregate data and analyze past spending trends.

[0112] Step 4:

[0113] The server uses a proposal generation mechanism to generate investment proposals tailored to the user's goals via a generating AI model. The input is the analysis results from step 3 and the user's goal data, and the output is personalized investment advice. Specifically, the AI ​​model is used to generate an optimal savings strategy that takes into account the user's income and expenses and risk tolerance. An example of a prompt to the generating AI model is, "Based on the user's monthly spending data, please generate advice on how to save for a trip in one year."

[0114] Step 5:

[0115] The device utilizes information delivery methods to visually present the generated advice to the user. The input is the advice data from step 4, and the output is an easy-to-understand advice screen provided to the user. Specifically, React Native is used to visually display the information using card widgets and interactive charts.

[0116] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0117] This invention is a system that supports users in managing their finances and provides advice that takes into account the user's emotional state using an emotion engine. In this system, the server first acquires the user's bank account and credit card transaction data via a financial data connection means. The acquired data is organized into categories by a data classification means and forms the basis for understanding the user's income and expenses and asset status.

[0118] Next, the server's data processing system analyzes the obtained data to diagnose the user's financial status. At this stage, the server inputs emotional data into the user's emotion engine to collect the user's emotional state. Emotions are detected, for example, through voice input or text analysis.

[0119] The server's advice generation mechanism combines this financial and emotional data to generate the most appropriate advice for the user. For example, if a user is under stress, it can offer suggestions that provide reassurance by recommending a low-risk investment strategy.

[0120] The advice received is presented to the user through the device's information delivery system. The user can view the information displayed on the device and make appropriate decisions by referring to visually presented indicators and graphs designed for easy understanding.

[0121] For example, if user B sets the goal of "increasing savings" and has been feeling stressed recently, the server will suggest small-scale investments in low-risk products and also provide guidance on saving methods to alleviate anxiety.

[0122] Thus, the present invention provides a means for constructing a system that comprehensively assesses the user's emotions and financial data to provide asset management and saving methods that the user can implement with confidence.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] The server obtains the user's bank account and credit card information through financial data connectivity. Here, APIs are used to securely collect data, obtaining the amount, date, time, and category information for each transaction. This data collection process is performed regularly to ensure that the user's current financial situation is always reflected.

[0126] Step 2:

[0127] The server's data classification system analyzes acquired financial transaction data and automatically categorizes it into predefined categories, such as food expenses, transportation expenses, and utility expenses. This clarifies the user's spending patterns and helps identify unnecessary expenses.

[0128] Step 3:

[0129] The server's emotion engine analyzes user input and dialogue to recognize emotions from speech and text. It identifies emotional states such as optimism, pessimism, and stress, and provides the results to data processing tools. This emotional data is considered as a factor influencing user decision-making.

[0130] Step 4:

[0131] The data processing system integrates and analyzes classified financial and sentiment data. It detects fluctuations in income and expenses and increases / decreases in assets, and evaluates the user's progress toward achieving their goals. Based on this information, it generates more detailed diagnostic results regarding the current financial status.

[0132] Step 5:

[0133] The server's advice generation mechanism constructs user-specific advice based on evaluation results. This advice can focus, for example, on investment strategies to mitigate risk or cost-saving measures to reduce psychological stress, supporting the user in achieving their specific goals.

[0134] Step 6:

[0135] The generated advice is presented to the user through the device's information delivery system. Here, a visually organized dashboard is used to show revenue forecasts, risk assessments, and savings suggestions in a way that is easy for the user to understand intuitively.

[0136] Step 7:

[0137] Users can review the presented information and adjust their financial goals and budgets accordingly. They can also re-evaluate suggestions based on their emotional state and make decisions to select the optimal action. This feedback is then sent back to the server and used for the system's subsequent analysis.

[0138] (Example 2)

[0139] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0140] Modern consumers engage in diverse financial transactions, but lack methods to consider the emotional aspects in managing them. This leads to problems such as inappropriate asset management due to stress and emotional fluctuations, resulting in inefficient asset management. Therefore, there is a need to provide comprehensive asset management support that takes consumers' emotions into account.

[0141] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0142] In this invention, the server includes financial information linking means, data organization means, data analysis means, advice generation means, emotion analysis means, and information transmission means. This makes it possible to comprehensively analyze the user's financial behavior data and emotional state and generate and provide optimal advice tailored to each individual's situation.

[0143] "Financial information sharing means" refers to methods for obtaining information from various financial institutions, such as users' bank accounts and credit cards.

[0144] "Data organization methods" refer to means of organizing acquired financial behavioral data according to specific categories or classifications, and preparing it in a format suitable for analysis and evaluation.

[0145] "Data analysis means" refers to a means of evaluating and diagnosing a user's asset situation using classified financial behavior data and providing basic information for asset management.

[0146] An "advice generation method" is a means of generating specific advice and recommendations based on the results of data analysis methods, with the aim of improving the user's asset management.

[0147] "Emotional analysis methods" are means of collecting and analyzing the emotional state of users through voice input and text analysis, and using that information to generate advice.

[0148] "Information transmission means" refers to means of providing generated advice or recommendations to users visually or aurally, and communicating them in an easily understandable format.

[0149] This invention is a system for streamlining asset management by comprehensively considering a user's financial behavior and emotional state. This system provides an optimal asset management strategy for each individual user by smoothly processing data among the server, terminal, and user.

[0150] The server first uses financial information sharing methods to obtain transaction data from users' bank accounts and credit cards. During this process, technologies such as "financial API systems" are used to securely transfer the latest data in accordance with appropriate security protocols. The acquired data is then categorized using data organization tools, for example, into items such as "fixed costs," "variable costs," and "income." This establishes a foundation for efficiently managing large amounts of transaction data.

[0151] Next, the server's data analysis system uses the acquired data to perform a financial diagnosis of the user. At this stage, "data analysis software" is used to evaluate past spending patterns and asset liquidity. In addition, sentiment analysis tools use voice input and text analysis to understand the user's emotional state. For example, a "sentiment analysis engine" estimates the stress level from tone of voice and word choice.

[0152] By combining generated emotional and financial data, the server's advice generation system creates the most suitable asset management advice for each individual user. For example, if a user has recently been experiencing stress, the system will suggest prioritizing savings plans over high-risk investments. The completed advice is delivered to the user via the terminal's information transmission system and displayed in a visually easy-to-understand format using graphs and charts.

[0153] Users can view visualized information through their devices and use it to manage their own assets. For example, they can see how their monthly expenses fluctuate and implement concrete measures to reduce waste.

[0154] By utilizing a generative AI model, this system can provide optimal advice based on prompts. For example, a possible prompt might be, "Consider the user's financial situation and emotional state, and generate investment and savings advice to reduce stress." This allows for more personalized responses.

[0155] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0156] Step 1:

[0157] The server obtains the latest transaction data from the user's financial institution through financial information sharing mechanisms. This input data includes the user's bank transaction history and credit card statements. The server receives this data and stores it using encryption protocols to ensure the security of the communication. Next, this stored data is prepared to be organized into categories from its raw state.

[0158] Step 2:

[0159] The server classifies the acquired financial data into categories using data organization tools. Input data is divided into categories such as "food expenses," "transportation expenses," and "income" based on specific keywords or transaction details. The server uses natural language processing technology to analyze transaction details and automatically map them to the appropriate categories. The output of this process is an organized transaction list with each transaction assigned a category.

[0160] Step 3:

[0161] The server uses data analysis tools to perform a detailed analysis of the organized transaction list. The input data consists of transaction history from the past few months, categorized for each purpose. The server applies analytical algorithms to analyze the user's spending patterns and assess their asset liquidity. The output of this analysis step is a report that includes the user's financial health and average values ​​for specific spending items.

[0162] Step 4:

[0163] The server uses emotion analysis tools to collect and analyze the user's emotional state. In this process, voice input or text data is used as input to the emotion analysis engine. The server detects emotions from the input data and quantifies stress levels and motivation. The output of this analysis is parameterized emotional state data.

[0164] Step 5:

[0165] The server uses an advice generation mechanism to combine financial and emotional data to generate optimal asset management advice for the user. Financial reports and emotional state data are used as input. The generating AI model uses prompts, such as "I am experiencing high stress, please suggest a conservative investment strategy," to create personalized advice. This advice is output as recommendations, including optimal investment choices and saving methods.

[0166] Step 6:

[0167] The terminal receives advice sent from the server and displays it visually. Based on the advice, the terminal generates graphs and charts and presents them to the user in a visually easy-to-understand format. The user can use this information to review their asset management methods and aid in decision-making. The output of this step is a visualized information dashboard that is easy for the user to understand.

[0168] (Application Example 2)

[0169] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0170] In today's world, consumers engage in a wide variety of financial transactions, but they face the challenge of managing their finances while taking their emotional state into account. Furthermore, emotional decisions can lead to wasteful spending or inappropriate investments. Therefore, there is a growing demand for systems that provide appropriate and personalized financial advice while considering the consumer's emotional state.

[0171] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0172] In this invention, the server includes financial information connection means, information classification means, emotion analysis means, recommendation generation means, and notification means. This enables the integration of the user's financial data and emotional data, allowing for financial management and spending optimization that takes emotional states into account.

[0173] "Financial information connection means" refers to a means of securely and efficiently obtaining a user's account data and transaction information from their financial institution.

[0174] An "information classification method" is a means of classifying acquired user financial transaction information into various categories and organizing it in an easy-to-understand format.

[0175] "Information processing means" refers to a method of analyzing data based on classified financial transaction information to understand the financial situation of users.

[0176] A "recommendation generation method" is a means of generating advice that leads to the improvement of the user's finances, based on analyzed data and the user's emotional state.

[0177] A "notification method" is a means of providing the generated advice to the user and presenting it in a visually or audibly easy-to-understand format.

[0178] "Emotional analysis means" refers to a method of detecting a user's emotional state by analyzing their voice and text information and reflecting that state in the data.

[0179] The server functions as the core of the system, securely acquiring users' financial information using financial information connectivity. This data is exchanged in an encrypted format using APIs. The acquired data is then classified into categories such as transactions, income, and fixed expenses using information classification tools. The information processing tools then use this classified data to perform analysis to understand the user's financial situation.

[0180] Next, the server detects the user's emotional state from their voice input and text data through an emotion analysis tool. This typically involves using machine learning algorithms, such as the Google Cloud Natural Language API.

[0181] Next, the recommendation generation system integrates the analyzed financial and emotional data to generate optimal financial advice for the user. This advice includes specific savings strategies and investment plans. A generation AI model is used to create personalized recommendations tailored to the user's needs. This series of recommendations is delivered to the user's device in real time via a notification system. On the device, the advice is displayed visually, using easy-to-understand graphs and indicators.

[0182] For example, if a user sets their goal to "reduce monthly food expenses" and has recently been experiencing stress, the server will generate a recommendation such as, "Increasing the time you spend enjoying cooking at home will effectively save on food expenses and reduce stress." An example of a prompt used in this case would be, "Consider the user's recent financial data and emotional state to generate recommendations that will lead to effective savings and stress reduction."

[0183] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0184] Step 1:

[0185] The server retrieves users' financial information using financial information connectivity. Inputs include bank account information and transaction history data transmitted via API. The server receives this data in encrypted form and securely stores it in its internal database. Outputs are raw financial transaction data categorized for further processing.

[0186] Step 2:

[0187] The server categorizes the acquired financial transaction data using information classification methods. This process utilizes scripts to analyze input data and assign it to categories such as regular spending, income, savings, and investments. The output is organized, categorized data that helps users understand their financial status.

[0188] Step 3:

[0189] The server uses emotion analysis tools to analyze voice input and text data from users. The input consists of text information extracted from the user's voice and messages. The server analyzes this data using machine learning algorithms to evaluate the user's emotional state. The output is an emotional status such as stress, happiness, or anxiety.

[0190] Step 4:

[0191] The server integrates the analyzed financial and emotional data and uses recommendation generation tools to generate the best recommendations for the user. The input is the data obtained in steps 2 and 3. The server uses a generative AI model to compute the data in order to build recommendations tailored to the user's specific needs. The output is personalized advice presented to the user.

[0192] Step 5:

[0193] The terminal provides the user with recommendations sent from the server via a notification mechanism. The input is the advice generated in step 4. The terminal creates graphs and infographics to visually display the advice and presents them on the user's screen. The output is the recommendation information displayed in a format that is easy for the user to understand.

[0194] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0195] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0196] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0197] [Second Embodiment]

[0198] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0199] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0200] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0201] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0202] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0203] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0204] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0205] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0206] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0207] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0208] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0209] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0210] This invention is a comprehensive system that supports personal financial management and is specifically implemented by the following means. First, the server acquires the user's bank account and credit card transaction data via financial data connection means. This allows financial information to be collected automatically without the user having to manually enter data.

[0211] Subsequently, the server's data classification system categorizes the acquired transaction data into categories such as food expenses, transportation expenses, and entertainment expenses. This process is performed to make it easier to clearly understand the user's spending habits.

[0212] The classified data is analyzed by the server's data processing capabilities. During the analysis, past spending trends and income fluctuations are examined, and the user's financial status is assessed. Furthermore, appropriate investment decisions are made based on the user's risk tolerance and specific goals (e.g., purchasing a home, saving for retirement).

[0213] Based on the analysis results, the server's advice generation system creates specific suggestions for improving the user's finances. These include suggestions for reducing unnecessary spending and selecting investment products that align with the user's goals.

[0214] The generated advice is presented to the user using the terminal's information delivery system. The user interface displays the information clearly and visually, making it easy for the user to understand and implement the advice.

[0215] For example, if user A sets a goal of "buying a home in five years," the server will propose the optimal investment plan to achieve that goal. This plan will include financial products and saving methods to save the target amount while minimizing risk.

[0216] Thus, the present invention supports economic stability and the achievement of future goals by providing a system that allows users to easily manage their own financial situation and select appropriate asset management and saving methods.

[0217] The following describes the processing flow.

[0218] Step 1:

[0219] The server retrieves user bank account and credit card transaction data through financial institutions' APIs. This data is collected securely using the user's authentication information. This data includes transaction details, transaction date, and amount.

[0220] Step 2:

[0221] The server's data classification mechanism categorizes acquired transaction data into categories such as food expenses, transportation expenses, utility expenses, and entertainment expenses. This function analyzes the content of each transaction and automatically organizes it based on a predefined category list.

[0222] Step 3:

[0223] The server's data processing system analyzes classified data to understand the user's income and expenditure balance and spending patterns. It also identifies fluctuations in income and spending trends based on past transaction history to evaluate the user's financial situation.

[0224] Step 4:

[0225] Based on the analysis results, the server uses an advice generation mechanism to generate asset management suggestions tailored to the user. These suggestions include investment products and portfolios that align with the user's set risk tolerance and financial goals.

[0226] Step 5:

[0227] The server's advice generation mechanism analyzes user spending data to identify unnecessary expenses. Based on these identified unnecessary expenses, it provides specific savings suggestions, indicating how much can be saved in each category.

[0228] Step 6:

[0229] The terminal displays advice and suggestions received from the server on the user interface. To ensure user understanding, the information is presented visually using graphs and tables.

[0230] Step 7:

[0231] Users review the advice displayed on their device and adjust their financial goals and risk tolerance as needed. This information is sent from the device to the server and used again for further analysis.

[0232] Step 8:

[0233] The server records new user inputs and settings in a database, which are then used for subsequent suggestions and analyses. This ensures that the system is always operated based on the latest user information.

[0234] (Example 1)

[0235] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0236] In personal financial management, manually collecting and analyzing transaction data from multiple financial institutions is time-consuming and labor-intensive, making it difficult to identify unnecessary spending and make appropriate investment decisions. As a result, users face the challenge of not being able to efficiently manage their assets to achieve their future financial goals.

[0237] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0238] In this invention, the server includes means for acquiring financial data, means for classifying data, means for processing data, means for generating suggestions, and means for presenting information. This enables the automatic collection and organization of an individual's economic transaction data, visualization of their economic situation including unnecessary spending, and the proposal of optimal asset management tailored to the user's goals.

[0239] A "financial data acquisition method" is an interface for automatically collecting users' economic transaction data from external financial institutions.

[0240] A "data classification method" is a function that analyzes acquired economic transaction data and divides each item into predefined categories.

[0241] A "data processing tool" is a function that analyzes the user's spending and income trends based on classified data and evaluates their financial situation.

[0242] A "proposal generation method" is a system that creates specific proposals for optimal asset management and achieving economic goals for the user based on the results of data processing and analysis.

[0243] An "information presentation method" is a function that visually communicates generated suggestions to the user through a user interface.

[0244] This invention is an integrated system for efficiently managing and optimizing a user's personal financial activities. This system functions through the coordinated efforts of a server, a terminal, and the user.

[0245] The server securely retrieves transaction data from multiple financial institutions, such as the user's bank account and credit card company, using financial data acquisition methods. Specifically, it can periodically update data using the APIs of each financial institution. The acquired data is stored in an encrypted format in the server's database, ensuring user privacy.

[0246] Next, the server uses a data classification mechanism to automatically categorize the acquired transaction data. For example, groceries purchased at a supermarket are classified as food expenses, and the use of public transportation is classified as transportation expenses. This automated classification allows users to efficiently track their spending.

[0247] Subsequently, the server analyzes the classified data using data processing tools to understand past spending trends and fluctuations in income. It can also apply machine learning algorithms to predict future income and expenses. This data processing allows for a detailed assessment of the user's financial situation.

[0248] The server uses a proposal generation mechanism to generate specific suggestions for financial improvement for the user based on the analysis results. These suggestions include ideas for reducing wasteful spending and selecting the optimal financial products to help the user achieve their goals.

[0249] The generated suggestions are transmitted to the terminal via an information presentation system and presented to the user visually and intuitively. The user interface is designed to be easily understood, allowing the user to obtain information to take concrete action.

[0250] For example, if a user sets a goal of "buying a house in five years," the system will propose a savings plan and investment strategy necessary to achieve that goal. This selection will include financial products with reduced risk. Advice on everyday saving methods will also be provided.

[0251] An example of a prompt for a generating AI model might be: "Based on User A's current spending habits and financial goals, please suggest the optimal investment and saving strategies for purchasing a home within five years."

[0252] In this way, users can accurately manage their financial situation and take strategic actions to achieve their future goals.

[0253] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0254] Step 1:

[0255] The server uses financial data acquisition methods to retrieve user transaction data from each financial institution's API. This input data includes transaction date and time, amount, and trading partner information. The server automatically collects this data daily and stores it in an encrypted state in the database. This process minimizes manual work for the user and ensures accurate data collection.

[0256] Step 2:

[0257] The server classifies the acquired transaction data using data classification methods. This process analyzes the content of each input transaction and categorizes it (e.g., food expenses, transportation expenses, utilities). Specifically, categories are assigned based on the name of the trading partner and the transaction details using natural language processing technology. The output includes category labels for each transaction, allowing the user to understand the breakdown of their expenses.

[0258] Step 3:

[0259] The server analyzes the classified data using various data processing tools. Historical expenditure and income data are used as input. The analysis employs machine learning algorithms to evaluate expenditure and income trends and predict future financial outcomes. The output data includes an assessment of the user's current financial situation, along with future forecasts.

[0260] Step 4:

[0261] The server generates specific financial improvement proposals based on data analysis results using a proposal generation mechanism. Inputs include analysis results and user-defined financial targets. The generated proposals include specific savings advice and recommended investment products. The output is optimized proposals tailored to the user's individual circumstances.

[0262] Step 5:

[0263] The terminal presents generated suggestions to the user through an information display mechanism. It receives suggestion information provided by the server as input. By forming visual dashboards and charts and providing users with easily understandable, visualized information as output, users can easily understand the suggestions and use them to take actual action.

[0264] (Application Example 1)

[0265] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0266] In personal financial management, there is a need for a unified system that automatically collects and classifies financial activity information, provides concrete asset management suggestions based on analysis, and presents spending information in real time. However, conventional systems have not adequately integrated these functions, and have not provided sufficient support for users to effectively improve their financial situation.

[0267] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0268] In this invention, the server includes financial information connection means, information classification means for classifying an individual's financial activity information collected using the financial information connection means, and information processing means for storing and analyzing the information obtained by the information classification means. This makes it possible for individuals to quickly and easily grasp their own financial situation and receive specific asset management suggestions.

[0269] A "financial information connection method" is a means that securely connects financial institution data, such as an individual's bank and credit card information, and has the function of automatically acquiring financial activity information.

[0270] An "information classification tool" is a means that has the function of organizing collected financial activity information into categories and classifying it into a format that can be easily analyzed.

[0271] An "information processing means" is a means that stores classified information and has the function of analyzing income and expenditure trends based on that information.

[0272] A "proposal generation means" is a means that has the function of automatically generating specific proposals for improving an individual's financial situation based on the analysis results of an information processing means.

[0273] An "information provision method" is a means that has the function of visually displaying generated suggestions to an individual and providing them as practical advice.

[0274] A "visual display method" is a means that visualizes an individual's income and expenditure data in an easy-to-understand manner, and has the function of supporting a real-time understanding of their financial situation.

[0275] An "investment proposal tool" is a tool that has the function of selecting and proposing specific steps and financial products for efficient asset management according to an individual's goals.

[0276] This invention is implemented as a system to streamline personal financial management and provide concrete asset management suggestions. The system automatically acquires personal financial information, analyzes and classifies the collected information, and provides advice for financial improvement.

[0277] The server uses "financial information connection means" to securely connect to the user's bank and credit card information and collect financial activity information. This uses highly secure APIs and data security protocols. Next, "information classification means" are used to classify each transaction into categories and clarify the user's spending trends.

[0278] The collected and categorized information is analyzed by an "information processing system" to evaluate the individual's income and expenditure patterns. Here, data analysis is performed using programming languages ​​such as Python and the Pandas library. Based on the analysis results, a "proposal generation system" generates specific and practical suggestions to improve the user's financial situation. These suggestions are generated using an AI module to construct an optimal asset management plan tailored to the user's goals.

[0279] Finally, the "information provision means" is utilized, and the generated proposals are provided to the user through the user card widget or the mobile application. Here, a visually understandable interface is designed using React Native. As a result, the user can easily understand and execute the content of the financial proposal.

[0280] As a specific example, when the user sets a goal of "saving travel funds in one year", the system analyzes the monthly expenses and provides specific advice such as "reduce dining expenses a bit this month and increase savings". At this time, an example of the prompt sentence by the generative AI model is "Based on the user's monthly expense data, please generate advice on saving travel funds in one year".

[0281] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0282] Step 1:

[0283] The server securely obtains the user's bank and credit card information through the financial information connection means. The input is the user's authentication information and transaction data from the financial institution. As the output, the transaction information is securely aggregated on the server. As a specific operation, an API is used to access the financial institution database and asynchronously collect the necessary transaction data.

[0284] Step 2:

[0285] The server classifies the obtained financial behavior information into categories using the information classification means. The input is the transaction data collected in Step 1, and the output is the transaction information organized by category. As a specific operation, a data frame is created using the Pandas library, and an algorithm for classifying into existing categories such as "food expenses" and "transportation expenses" is applied.

[0286] Step 3:

[0287] The server uses information processing tools to analyze the classified data. The input here is the category-specific transaction data obtained in step 2, and the output is the analysis of individual spending trends based on the classified data. Specifically, statistical methods (e.g., moving average, trend analysis) are applied to aggregate data and analyze past spending trends.

[0288] Step 4:

[0289] The server uses a proposal generation mechanism to generate investment proposals tailored to the user's goals via a generating AI model. The input is the analysis results from step 3 and the user's goal data, and the output is personalized investment advice. Specifically, the AI ​​model is used to generate an optimal savings strategy that takes into account the user's income and expenses and risk tolerance. An example of a prompt to the generating AI model is, "Based on the user's monthly spending data, please generate advice on how to save for a trip in one year."

[0290] Step 5:

[0291] The device utilizes information delivery methods to visually present the generated advice to the user. The input is the advice data from step 4, and the output is an easy-to-understand advice screen provided to the user. Specifically, React Native is used to visually display the information using card widgets and interactive charts.

[0292] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0293] This invention is a system that supports users in managing their finances and provides advice that takes into account the user's emotional state using an emotion engine. In this system, the server first acquires the user's bank account and credit card transaction data via a financial data connection means. The acquired data is organized into categories by a data classification means and forms the basis for understanding the user's income and expenses and asset status.

[0294] Next, the server's data processing system analyzes the obtained data to diagnose the user's financial status. At this stage, the server inputs emotional data into the user's emotion engine to collect the user's emotional state. Emotions are detected, for example, through voice input or text analysis.

[0295] The server's advice generation mechanism combines this financial and emotional data to generate the most appropriate advice for the user. For example, if a user is under stress, it can offer suggestions that provide reassurance by recommending a low-risk investment strategy.

[0296] The advice received is presented to the user through the device's information delivery system. The user can view the information displayed on the device and make appropriate decisions by referring to visually presented indicators and graphs designed for easy understanding.

[0297] For example, if user B sets the goal of "increasing savings" and has been feeling stressed recently, the server will suggest small-scale investments in low-risk products and also provide guidance on saving methods to alleviate anxiety.

[0298] Thus, the present invention provides a means for constructing a system that comprehensively assesses the user's emotions and financial data to provide asset management and saving methods that the user can implement with confidence.

[0299] The following describes the processing flow.

[0300] Step 1:

[0301] The server obtains the user's bank account and credit card information through financial data connection means. Here, the API is used to safely collect data, and the amount, date and time, and category information of each transaction are obtained. This data collection process is performed regularly to ensure that the user's latest financial situation is always reflected.

[0302] Step 2:

[0303] The server's data classification means analyzes the acquired financial transaction data and automatically classifies it into set categories, such as food expenses, transportation expenses, utility bills, etc. This clarifies the user's spending patterns and helps identify wasteful spending.

[0304] Step 3:

[0305] The server's emotion engine analyzes the user's input and conversation content and recognizes emotions from voice and text. At this time, emotional states such as optimism, pessimism, and stress are discriminated, and the results are provided to the data processing means. This emotional data is considered as a factor influencing the user's decision-making.

[0306] Step 4:

[0307] The data processing means integrates and analyzes the classified financial data and emotional data. Here, fluctuations in the income and expenditure situation and increases and decreases in assets are detected, and the progress towards the user's goals is evaluated. Based on this information, a more detailed diagnosis result regarding the current financial state is generated.

[0308] Step 5:

[0309] The server's advice generation means constructs advice suitable for the user based on the evaluation results. This advice can focus on, for example, investment strategies to reduce risks or savings means to relieve psychological stress, and supports the user's specific goal achievement.

[0310] Step 6:

[0311] The generated advice is presented to the user through the device's information delivery system. Here, a visually organized dashboard is used to show revenue forecasts, risk assessments, and savings suggestions in a way that is easy for the user to understand intuitively.

[0312] Step 7:

[0313] Users can review the presented information and adjust their financial goals and budgets accordingly. They can also re-evaluate suggestions based on their emotional state and make decisions to select the optimal action. This feedback is then sent back to the server and used for the system's subsequent analysis.

[0314] (Example 2)

[0315] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0316] Modern consumers engage in diverse financial transactions, but lack methods to consider the emotional aspects in managing them. This leads to problems such as inappropriate asset management due to stress and emotional fluctuations, resulting in inefficient asset management. Therefore, there is a need to provide comprehensive asset management support that takes consumers' emotions into account.

[0317] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0318] In this invention, the server includes financial information linking means, data organization means, data analysis means, advice generation means, emotion analysis means, and information transmission means. This makes it possible to comprehensively analyze the user's financial behavior data and emotional state and generate and provide optimal advice tailored to each individual's situation.

[0319] "Financial information sharing means" refers to methods for obtaining information from various financial institutions, such as users' bank accounts and credit cards.

[0320] "Data organization methods" refer to means of organizing acquired financial behavioral data according to specific categories or classifications, and preparing it in a format suitable for analysis and evaluation.

[0321] "Data analysis means" refers to a means of evaluating and diagnosing a user's asset situation using classified financial behavior data and providing basic information for asset management.

[0322] An "advice generation method" is a means of generating specific advice and recommendations based on the results of data analysis methods, with the aim of improving the user's asset management.

[0323] "Emotional analysis methods" are means of collecting and analyzing the emotional state of users through voice input and text analysis, and using that information to generate advice.

[0324] "Information transmission means" refers to means of providing generated advice or recommendations to users visually or aurally, and communicating them in an easily understandable format.

[0325] This invention is a system for streamlining asset management by comprehensively considering a user's financial behavior and emotional state. This system provides an optimal asset management strategy for each individual user by smoothly processing data among the server, terminal, and user.

[0326] The server first uses financial information sharing methods to obtain transaction data from users' bank accounts and credit cards. During this process, technologies such as "financial API systems" are used to securely transfer the latest data in accordance with appropriate security protocols. The acquired data is then categorized using data organization tools, for example, into items such as "fixed costs," "variable costs," and "income." This establishes a foundation for efficiently managing large amounts of transaction data.

[0327] Next, the server's data analysis system uses the acquired data to perform a financial diagnosis of the user. At this stage, "data analysis software" is used to evaluate past spending patterns and asset liquidity. In addition, sentiment analysis tools use voice input and text analysis to understand the user's emotional state. For example, a "sentiment analysis engine" estimates the stress level from tone of voice and word choice.

[0328] By combining generated emotional and financial data, the server's advice generation system creates the most suitable asset management advice for each individual user. For example, if a user has recently been experiencing stress, the system will suggest prioritizing savings plans over high-risk investments. The completed advice is delivered to the user via the terminal's information transmission system and displayed in a visually easy-to-understand format using graphs and charts.

[0329] Users can view visualized information through their devices and use it to manage their own assets. For example, they can see how their monthly expenses fluctuate and implement concrete measures to reduce waste.

[0330] By utilizing a generative AI model, this system can provide optimal advice based on prompts. For example, a possible prompt might be, "Consider the user's financial situation and emotional state, and generate investment and savings advice to reduce stress." This allows for more personalized responses.

[0331] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0332] Step 1:

[0333] The server obtains the latest transaction data from the user's financial institution through financial information sharing mechanisms. This input data includes the user's bank transaction history and credit card statements. The server receives this data and stores it using encryption protocols to ensure the security of the communication. Next, this stored data is prepared to be organized into categories from its raw state.

[0334] Step 2:

[0335] The server classifies the acquired financial data into categories using data organization tools. Input data is divided into categories such as "food expenses," "transportation expenses," and "income" based on specific keywords or transaction details. The server uses natural language processing technology to analyze transaction details and automatically map them to the appropriate categories. The output of this process is an organized transaction list with each transaction assigned a category.

[0336] Step 3:

[0337] The server uses data analysis tools to perform a detailed analysis of the organized transaction list. The input data consists of transaction history from the past few months, categorized for each purpose. The server applies analytical algorithms to analyze the user's spending patterns and assess their asset liquidity. The output of this analysis step is a report that includes the user's financial health and average values ​​for specific spending items.

[0338] Step 4:

[0339] The server uses emotion analysis tools to collect and analyze the user's emotional state. In this process, voice input or text data is used as input to the emotion analysis engine. The server detects emotions from the input data and quantifies stress levels and motivation. The output of this analysis is parameterized emotional state data.

[0340] Step 5:

[0341] The server uses an advice generation mechanism to combine financial and emotional data to generate optimal asset management advice for the user. Financial reports and emotional state data are used as input. The generating AI model uses prompts, such as "I am experiencing high stress, please suggest a conservative investment strategy," to create personalized advice. This advice is output as recommendations, including optimal investment choices and saving methods.

[0342] Step 6:

[0343] The terminal receives advice sent from the server and displays it visually. Based on the advice, the terminal generates graphs and charts and presents them to the user in a visually easy-to-understand format. The user can use this information to review their asset management methods and aid in decision-making. The output of this step is a visualized information dashboard that is easy for the user to understand.

[0344] (Application Example 2)

[0345] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0346] In today's world, consumers engage in a wide variety of financial transactions, but they face the challenge of managing their finances while taking their emotional state into account. Furthermore, emotional decisions can lead to wasteful spending or inappropriate investments. Therefore, there is a growing demand for systems that provide appropriate and personalized financial advice while considering the consumer's emotional state.

[0347] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0348] In this invention, the server includes financial information connection means, information classification means, emotion analysis means, recommendation generation means, and notification means. This enables the integration of the user's financial data and emotional data, allowing for financial management and spending optimization that takes emotional states into account.

[0349] "Financial information connection means" refers to a means of securely and efficiently obtaining a user's account data and transaction information from their financial institution.

[0350] An "information classification method" is a means of classifying acquired user financial transaction information into various categories and organizing it in an easy-to-understand format.

[0351] "Information processing means" refers to a method of analyzing data based on classified financial transaction information to understand the financial situation of users.

[0352] A "recommendation generation method" is a means of generating advice that leads to the improvement of the user's finances, based on analyzed data and the user's emotional state.

[0353] A "notification method" is a means of providing the generated advice to the user and presenting it in a visually or audibly easy-to-understand format.

[0354] "Emotional analysis means" refers to a method of detecting a user's emotional state by analyzing their voice and text information and reflecting that state in the data.

[0355] The server functions as the core of the system, securely acquiring users' financial information using financial information connectivity. This data is exchanged in an encrypted format using APIs. The acquired data is then classified into categories such as transactions, income, and fixed expenses using information classification tools. The information processing tools then use this classified data to perform analysis to understand the user's financial situation.

[0356] Next, the server detects the user's emotional state from their voice input and text data through an emotion analysis tool. This typically involves using machine learning algorithms, such as the Google Cloud Natural Language API.

[0357] Next, the recommendation generation system integrates the analyzed financial and emotional data to generate optimal financial advice for the user. This advice includes specific savings strategies and investment plans. A generation AI model is used to create personalized recommendations tailored to the user's needs. This series of recommendations is delivered to the user's device in real time via a notification system. On the device, the advice is displayed visually, using easy-to-understand graphs and indicators.

[0358] For example, if a user sets their goal to "reduce monthly food expenses" and has recently been experiencing stress, the server will generate a recommendation such as, "Increasing the time you spend enjoying cooking at home will effectively save on food expenses and reduce stress." An example of a prompt used in this case would be, "Consider the user's recent financial data and emotional state to generate recommendations that will lead to effective savings and stress reduction."

[0359] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0360] Step 1:

[0361] The server retrieves users' financial information using financial information connectivity. Inputs include bank account information and transaction history data transmitted via API. The server receives this data in encrypted form and securely stores it in its internal database. Outputs are raw financial transaction data categorized for further processing.

[0362] Step 2:

[0363] The server categorizes the acquired financial transaction data using information classification methods. This process utilizes scripts to analyze input data and assign it to categories such as regular spending, income, savings, and investments. The output is organized, categorized data that helps users understand their financial status.

[0364] Step 3:

[0365] The server uses emotion analysis tools to analyze voice input and text data from users. The input consists of text information extracted from the user's voice and messages. The server analyzes this data using machine learning algorithms to evaluate the user's emotional state. The output is an emotional status such as stress, happiness, or anxiety.

[0366] Step 4:

[0367] The server integrates the analyzed financial and emotional data and uses recommendation generation tools to generate the best recommendations for the user. The input is the data obtained in steps 2 and 3. The server uses a generative AI model to compute the data in order to build recommendations tailored to the user's specific needs. The output is personalized advice presented to the user.

[0368] Step 5:

[0369] The terminal provides the user with recommendations sent from the server via a notification mechanism. The input is the advice generated in step 4. The terminal creates graphs and infographics to visually display the advice and presents them on the user's screen. The output is the recommendation information displayed in a format that is easy for the user to understand.

[0370] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0371] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0372] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0373] [Third Embodiment]

[0374] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0375] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0376] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0377] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0378] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0379] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0380] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0381] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0382] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0383] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0384] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0385] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0386] This invention is a comprehensive system that supports personal financial management and is specifically implemented by the following means. First, the server acquires the user's bank account and credit card transaction data via financial data connection means. This allows financial information to be collected automatically without the user having to manually enter data.

[0387] Subsequently, the server's data classification system categorizes the acquired transaction data into categories such as food expenses, transportation expenses, and entertainment expenses. This process is performed to make it easier to clearly understand the user's spending habits.

[0388] The classified data is analyzed by the server's data processing capabilities. During the analysis, past spending trends and income fluctuations are examined, and the user's financial status is assessed. Furthermore, appropriate investment decisions are made based on the user's risk tolerance and specific goals (e.g., purchasing a home, saving for retirement).

[0389] Based on the analysis results, the server's advice generation system creates specific suggestions for improving the user's finances. These include suggestions for reducing unnecessary spending and selecting investment products that align with the user's goals.

[0390] The generated advice is presented to the user using the terminal's information delivery system. The user interface displays the information clearly and visually, making it easy for the user to understand and implement the advice.

[0391] For example, if user A sets a goal of "buying a home in five years," the server will propose the optimal investment plan to achieve that goal. This plan will include financial products and saving methods to save the target amount while minimizing risk.

[0392] Thus, the present invention supports economic stability and the achievement of future goals by providing a system that allows users to easily manage their own financial situation and select appropriate asset management and saving methods.

[0393] The following describes the processing flow.

[0394] Step 1:

[0395] The server retrieves user bank account and credit card transaction data through financial institutions' APIs. This data is collected securely using the user's authentication information. This data includes transaction details, transaction date, and amount.

[0396] Step 2:

[0397] The server's data classification mechanism categorizes acquired transaction data into categories such as food expenses, transportation expenses, utility expenses, and entertainment expenses. This function analyzes the content of each transaction and automatically organizes it based on a predefined category list.

[0398] Step 3:

[0399] The server's data processing system analyzes classified data to understand the user's income and expenditure balance and spending patterns. It also identifies fluctuations in income and spending trends based on past transaction history to evaluate the user's financial situation.

[0400] Step 4:

[0401] Based on the analysis results, the server uses an advice generation mechanism to generate asset management suggestions tailored to the user. These suggestions include investment products and portfolios that align with the user's set risk tolerance and financial goals.

[0402] Step 5:

[0403] The server's advice generation mechanism analyzes user spending data to identify unnecessary expenses. Based on these identified unnecessary expenses, it provides specific savings suggestions, indicating how much can be saved in each category.

[0404] Step 6:

[0405] The terminal displays advice and suggestions received from the server on the user interface. To ensure user understanding, the information is presented visually using graphs and tables.

[0406] Step 7:

[0407] Users review the advice displayed on their device and adjust their financial goals and risk tolerance as needed. This information is sent from the device to the server and used again for further analysis.

[0408] Step 8:

[0409] The server records new user inputs and settings in a database, which are then used for subsequent suggestions and analyses. This ensures that the system is always operated based on the latest user information.

[0410] (Example 1)

[0411] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0412] In personal financial management, manually collecting and analyzing transaction data from multiple financial institutions is time-consuming and labor-intensive, making it difficult to identify unnecessary spending and make appropriate investment decisions. As a result, users face the challenge of not being able to efficiently manage their assets to achieve their future financial goals.

[0413] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0414] In this invention, the server includes means for acquiring financial data, means for classifying data, means for processing data, means for generating suggestions, and means for presenting information. This enables the automatic collection and organization of an individual's economic transaction data, visualization of their economic situation including unnecessary spending, and the proposal of optimal asset management tailored to the user's goals.

[0415] A "financial data acquisition method" is an interface for automatically collecting users' economic transaction data from external financial institutions.

[0416] A "data classification method" is a function that analyzes acquired economic transaction data and divides each item into predefined categories.

[0417] A "data processing tool" is a function that analyzes the user's spending and income trends based on classified data and evaluates their financial situation.

[0418] A "proposal generation method" is a system that creates specific proposals for optimal asset management and achieving economic goals for the user based on the results of data processing and analysis.

[0419] An "information presentation method" is a function that visually communicates generated suggestions to the user through a user interface.

[0420] This invention is an integrated system for efficiently managing and optimizing a user's personal financial activities. This system functions through the coordinated efforts of a server, a terminal, and the user.

[0421] The server securely retrieves transaction data from multiple financial institutions, such as the user's bank account and credit card company, using financial data acquisition methods. Specifically, it can periodically update data using the APIs of each financial institution. The acquired data is stored in an encrypted format in the server's database, ensuring user privacy.

[0422] Next, the server uses a data classification mechanism to automatically categorize the acquired transaction data. For example, groceries purchased at a supermarket are classified as food expenses, and the use of public transportation is classified as transportation expenses. This automated classification allows users to efficiently track their spending.

[0423] Subsequently, the server analyzes the classified data using data processing tools to understand past spending trends and fluctuations in income. It can also apply machine learning algorithms to predict future income and expenses. This data processing allows for a detailed assessment of the user's financial situation.

[0424] The server uses a proposal generation mechanism to generate specific suggestions for financial improvement for the user based on the analysis results. These suggestions include ideas for reducing wasteful spending and selecting the optimal financial products to help the user achieve their goals.

[0425] The generated suggestions are transmitted to the terminal via an information presentation system and presented to the user visually and intuitively. The user interface is designed to be easily understood, allowing the user to obtain information to take concrete action.

[0426] For example, if a user sets a goal of "buying a house in five years," the system will propose a savings plan and investment strategy necessary to achieve that goal. This selection will include financial products with reduced risk. Advice on everyday saving methods will also be provided.

[0427] An example of a prompt for a generating AI model might be: "Based on User A's current spending habits and financial goals, please suggest the optimal investment and saving strategies for purchasing a home within five years."

[0428] In this way, users can accurately manage their financial situation and take strategic actions to achieve their future goals.

[0429] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0430] Step 1:

[0431] The server uses financial data acquisition methods to retrieve user transaction data from each financial institution's API. This input data includes transaction date and time, amount, and trading partner information. The server automatically collects this data daily and stores it in an encrypted state in the database. This process minimizes manual work for the user and ensures accurate data collection.

[0432] Step 2:

[0433] The server classifies the acquired transaction data using data classification methods. This process analyzes the content of each input transaction and categorizes it (e.g., food expenses, transportation expenses, utilities). Specifically, categories are assigned based on the name of the trading partner and the transaction details using natural language processing technology. The output includes category labels for each transaction, allowing the user to understand the breakdown of their expenses.

[0434] Step 3:

[0435] The server analyzes the classified data using various data processing tools. Historical expenditure and income data are used as input. The analysis employs machine learning algorithms to evaluate expenditure and income trends and predict future financial outcomes. The output data includes an assessment of the user's current financial situation, along with future forecasts.

[0436] Step 4:

[0437] The server generates specific financial improvement proposals based on data analysis results using a proposal generation mechanism. Inputs include analysis results and user-defined financial targets. The generated proposals include specific savings advice and recommended investment products. The output is optimized proposals tailored to the user's individual circumstances.

[0438] Step 5:

[0439] The terminal presents generated suggestions to the user through an information display mechanism. It receives suggestion information provided by the server as input. By forming visual dashboards and charts and providing users with easily understandable, visualized information as output, users can easily understand the suggestions and use them to take actual action.

[0440] (Application Example 1)

[0441] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0442] In personal financial management, there is a need for a unified system that automatically collects and classifies financial activity information, provides concrete asset management suggestions based on analysis, and presents spending information in real time. However, conventional systems have not adequately integrated these functions, and have not provided sufficient support for users to effectively improve their financial situation.

[0443] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0444] In this invention, the server includes financial information connection means, information classification means for classifying an individual's financial activity information collected using the financial information connection means, and information processing means for storing and analyzing the information obtained by the information classification means. This makes it possible for individuals to quickly and easily grasp their own financial situation and receive specific asset management suggestions.

[0445] A "financial information connection method" is a means that securely connects financial institution data, such as an individual's bank and credit card information, and has the function of automatically acquiring financial activity information.

[0446] An "information classification tool" is a means that has the function of organizing collected financial activity information into categories and classifying it into a format that can be easily analyzed.

[0447] An "information processing means" is a means that stores classified information and has the function of analyzing income and expenditure trends based on that information.

[0448] A "proposal generation means" is a means that has the function of automatically generating specific proposals for improving an individual's financial situation based on the analysis results of an information processing means.

[0449] An "information provision method" is a means that has the function of visually displaying generated suggestions to an individual and providing them as practical advice.

[0450] A "visual display method" is a means that visualizes an individual's income and expenditure data in an easy-to-understand manner, and has the function of supporting a real-time understanding of their financial situation.

[0451] An "investment proposal tool" is a tool that has the function of selecting and proposing specific steps and financial products for efficient asset management according to an individual's goals.

[0452] This invention is implemented as a system to streamline personal financial management and provide concrete asset management suggestions. The system automatically acquires personal financial information, analyzes and classifies the collected information, and provides advice for financial improvement.

[0453] The server uses "financial information connection means" to securely connect to the user's bank and credit card information and collect financial activity information. This uses highly secure APIs and data security protocols. Next, "information classification means" are used to classify each transaction into categories and clarify the user's spending trends.

[0454] The collected and categorized information is analyzed by an "information processing system" to evaluate the individual's income and expenditure patterns. Here, data analysis is performed using programming languages ​​such as Python and the Pandas library. Based on the analysis results, a "proposal generation system" generates specific and practical suggestions to improve the user's financial situation. These suggestions are generated using an AI module to construct an optimal asset management plan tailored to the user's goals.

[0455] Ultimately, the "information delivery tools" are utilized, and the generated proposals are delivered to the user through a user card widget or mobile application. Here, a visually intuitive interface is designed using React Native. This allows users to easily understand and implement the financial proposals.

[0456] For example, if a user sets a goal of "saving money for a trip in one year," the system will analyze their monthly expenses and provide specific advice such as, "Let's cut back on eating out this month and increase your savings." In this case, an example of a prompt message generated by the AI ​​model would be, "Based on the user's monthly spending data, please generate advice on how to save money for a trip in one year."

[0457] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0458] Step 1:

[0459] The server securely obtains the user's bank and credit card information through financial information connectivity. Inputs include the user's authentication information and transaction data from financial institutions. Output is the secure aggregation of transaction information on the server. Specifically, it uses APIs to access financial institution databases and asynchronously collects the necessary transaction data.

[0460] Step 2:

[0461] The server categorizes the financial transaction information obtained using an information classification system. The input is the transaction data collected in step 1, and the output is transaction information organized by category. Specifically, it creates a data frame using the Pandas library and applies an algorithm to classify the data into existing categories such as "food expenses" and "transportation expenses."

[0462] Step 3:

[0463] The server uses information processing tools to analyze the classified data. The input here is the category-specific transaction data obtained in step 2, and the output is the analysis of individual spending trends based on the classified data. Specifically, statistical methods (e.g., moving average, trend analysis) are applied to aggregate data and analyze past spending trends.

[0464] Step 4:

[0465] The server uses a proposal generation mechanism to generate investment proposals tailored to the user's goals via a generating AI model. The input is the analysis results from step 3 and the user's goal data, and the output is personalized investment advice. Specifically, the AI ​​model is used to generate an optimal savings strategy that takes into account the user's income and expenses and risk tolerance. An example of a prompt to the generating AI model is, "Based on the user's monthly spending data, please generate advice on how to save for a trip in one year."

[0466] Step 5:

[0467] The device utilizes information delivery methods to visually present the generated advice to the user. The input is the advice data from step 4, and the output is an easy-to-understand advice screen provided to the user. Specifically, React Native is used to visually display the information using card widgets and interactive charts.

[0468] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0469] This invention is a system that supports users in managing their finances and provides advice that takes into account the user's emotional state using an emotion engine. In this system, the server first acquires the user's bank account and credit card transaction data via a financial data connection means. The acquired data is organized into categories by a data classification means and forms the basis for understanding the user's income and expenses and asset status.

[0470] Next, the server's data processing system analyzes the obtained data to diagnose the user's financial status. At this stage, the server inputs emotional data into the user's emotion engine to collect the user's emotional state. Emotions are detected, for example, through voice input or text analysis.

[0471] The server's advice generation mechanism combines this financial and emotional data to generate the most appropriate advice for the user. For example, if a user is under stress, it can offer suggestions that provide reassurance by recommending a low-risk investment strategy.

[0472] The advice received is presented to the user through the device's information delivery system. The user can view the information displayed on the device and make appropriate decisions by referring to visually presented indicators and graphs designed for easy understanding.

[0473] For example, if user B sets the goal of "increasing savings" and has been feeling stressed recently, the server will suggest small-scale investments in low-risk products and also provide guidance on saving methods to alleviate anxiety.

[0474] Thus, the present invention provides a means for constructing a system that comprehensively assesses the user's emotions and financial data to provide asset management and saving methods that the user can implement with confidence.

[0475] The following describes the processing flow.

[0476] Step 1:

[0477] The server obtains the user's bank account and credit card information through financial data connectivity. Here, APIs are used to securely collect data, obtaining the amount, date, time, and category information for each transaction. This data collection process is performed regularly to ensure that the user's current financial situation is always reflected.

[0478] Step 2:

[0479] The server's data classification system analyzes acquired financial transaction data and automatically categorizes it into predefined categories, such as food expenses, transportation expenses, and utility expenses. This clarifies the user's spending patterns and helps identify unnecessary expenses.

[0480] Step 3:

[0481] The server's emotion engine analyzes user input and dialogue to recognize emotions from speech and text. It identifies emotional states such as optimism, pessimism, and stress, and provides the results to data processing tools. This emotional data is considered as a factor influencing user decision-making.

[0482] Step 4:

[0483] The data processing system integrates and analyzes classified financial and sentiment data. It detects fluctuations in income and expenses and increases / decreases in assets, and evaluates the user's progress toward achieving their goals. Based on this information, it generates more detailed diagnostic results regarding the current financial status.

[0484] Step 5:

[0485] The server's advice generation mechanism constructs user-specific advice based on evaluation results. This advice can focus, for example, on investment strategies to mitigate risk or cost-saving measures to reduce psychological stress, supporting the user in achieving their specific goals.

[0486] Step 6:

[0487] The generated advice is presented to the user through the device's information delivery system. Here, a visually organized dashboard is used to show revenue forecasts, risk assessments, and savings suggestions in a way that is easy for the user to understand intuitively.

[0488] Step 7:

[0489] Users can review the presented information and adjust their financial goals and budgets accordingly. They can also re-evaluate suggestions based on their emotional state and make decisions to select the optimal action. This feedback is then sent back to the server and used for the system's subsequent analysis.

[0490] (Example 2)

[0491] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0492] Modern consumers engage in diverse financial transactions, but lack methods to consider the emotional aspects in managing them. This leads to problems such as inappropriate asset management due to stress and emotional fluctuations, resulting in inefficient asset management. Therefore, there is a need to provide comprehensive asset management support that takes consumers' emotions into account.

[0493] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0494] In this invention, the server includes financial information linking means, data organization means, data analysis means, advice generation means, emotion analysis means, and information transmission means. This makes it possible to comprehensively analyze the user's financial behavior data and emotional state and generate and provide optimal advice tailored to each individual's situation.

[0495] "Financial information sharing means" refers to methods for obtaining information from various financial institutions, such as users' bank accounts and credit cards.

[0496] "Data organization methods" refer to means of organizing acquired financial behavioral data according to specific categories or classifications, and preparing it in a format suitable for analysis and evaluation.

[0497] "Data analysis means" refers to a means of evaluating and diagnosing a user's asset situation using classified financial behavior data and providing basic information for asset management.

[0498] An "advice generation method" is a means of generating specific advice and recommendations based on the results of data analysis methods, with the aim of improving the user's asset management.

[0499] "Emotional analysis methods" are means of collecting and analyzing the emotional state of users through voice input and text analysis, and using that information to generate advice.

[0500] "Information transmission means" refers to means of providing generated advice or recommendations to users visually or aurally, and communicating them in an easily understandable format.

[0501] This invention is a system for streamlining asset management by comprehensively considering a user's financial behavior and emotional state. This system provides an optimal asset management strategy for each individual user by smoothly processing data among the server, terminal, and user.

[0502] The server first uses financial information sharing methods to obtain transaction data from users' bank accounts and credit cards. During this process, technologies such as "financial API systems" are used to securely transfer the latest data in accordance with appropriate security protocols. The acquired data is then categorized using data organization tools, for example, into items such as "fixed costs," "variable costs," and "income." This establishes a foundation for efficiently managing large amounts of transaction data.

[0503] Next, the server's data analysis system uses the acquired data to perform a financial diagnosis of the user. At this stage, "data analysis software" is used to evaluate past spending patterns and asset liquidity. In addition, sentiment analysis tools use voice input and text analysis to understand the user's emotional state. For example, a "sentiment analysis engine" estimates the stress level from tone of voice and word choice.

[0504] By combining generated emotional and financial data, the server's advice generation system creates the most suitable asset management advice for each individual user. For example, if a user has recently been experiencing stress, the system will suggest prioritizing savings plans over high-risk investments. The completed advice is delivered to the user via the terminal's information transmission system and displayed in a visually easy-to-understand format using graphs and charts.

[0505] Users can view visualized information through their devices and use it to manage their own assets. For example, they can see how their monthly expenses fluctuate and implement concrete measures to reduce waste.

[0506] By utilizing a generative AI model, this system can provide optimal advice based on prompts. For example, a possible prompt might be, "Consider the user's financial situation and emotional state, and generate investment and savings advice to reduce stress." This allows for more personalized responses.

[0507] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0508] Step 1:

[0509] The server obtains the latest transaction data from the user's financial institution through financial information sharing mechanisms. This input data includes the user's bank transaction history and credit card statements. The server receives this data and stores it using encryption protocols to ensure the security of the communication. Next, this stored data is prepared to be organized into categories from its raw state.

[0510] Step 2:

[0511] The server classifies the acquired financial data into categories using data organization tools. Input data is divided into categories such as "food expenses," "transportation expenses," and "income" based on specific keywords or transaction details. The server uses natural language processing technology to analyze transaction details and automatically map them to the appropriate categories. The output of this process is an organized transaction list with each transaction assigned a category.

[0512] Step 3:

[0513] The server uses data analysis tools to perform a detailed analysis of the organized transaction list. The input data consists of transaction history from the past few months, categorized for each purpose. The server applies analytical algorithms to analyze the user's spending patterns and assess their asset liquidity. The output of this analysis step is a report that includes the user's financial health and average values ​​for specific spending items.

[0514] Step 4:

[0515] The server uses emotion analysis tools to collect and analyze the user's emotional state. In this process, voice input or text data is used as input to the emotion analysis engine. The server detects emotions from the input data and quantifies stress levels and motivation. The output of this analysis is parameterized emotional state data.

[0516] Step 5:

[0517] The server uses an advice generation mechanism to combine financial and emotional data to generate optimal asset management advice for the user. Financial reports and emotional state data are used as input. The generating AI model uses prompts, such as "I am experiencing high stress, please suggest a conservative investment strategy," to create personalized advice. This advice is output as recommendations, including optimal investment choices and saving methods.

[0518] Step 6:

[0519] The terminal receives advice sent from the server and displays it visually. Based on the advice, the terminal generates graphs and charts and presents them to the user in a visually easy-to-understand format. The user can use this information to review their asset management methods and aid in decision-making. The output of this step is a visualized information dashboard that is easy for the user to understand.

[0520] (Application Example 2)

[0521] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0522] In today's world, consumers engage in a wide variety of financial transactions, but they face the challenge of managing their finances while taking their emotional state into account. Furthermore, emotional decisions can lead to wasteful spending or inappropriate investments. Therefore, there is a growing demand for systems that provide appropriate and personalized financial advice while considering the consumer's emotional state.

[0523] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0524] In this invention, the server includes financial information connection means, information classification means, emotion analysis means, recommendation generation means, and notification means. This enables the integration of the user's financial data and emotional data, allowing for financial management and spending optimization that takes emotional states into account.

[0525] "Financial information connection means" refers to a means of securely and efficiently obtaining a user's account data and transaction information from their financial institution.

[0526] An "information classification method" is a means of classifying acquired user financial transaction information into various categories and organizing it in an easy-to-understand format.

[0527] "Information processing means" refers to a method of analyzing data based on classified financial transaction information to understand the financial situation of users.

[0528] A "recommendation generation method" is a means of generating advice that leads to the improvement of the user's finances, based on analyzed data and the user's emotional state.

[0529] A "notification method" is a means of providing the generated advice to the user and presenting it in a visually or audibly easy-to-understand format.

[0530] "Emotional analysis means" refers to a method of detecting a user's emotional state by analyzing their voice and text information and reflecting that state in the data.

[0531] The server functions as the core of the system, securely acquiring users' financial information using financial information connectivity. This data is exchanged in an encrypted format using APIs. The acquired data is then classified into categories such as transactions, income, and fixed expenses using information classification tools. The information processing tools then use this classified data to perform analysis to understand the user's financial situation.

[0532] Next, the server detects the user's emotional state from their voice input and text data through an emotion analysis tool. This typically involves using machine learning algorithms, such as the Google Cloud Natural Language API.

[0533] Next, the recommendation generation system integrates the analyzed financial and emotional data to generate optimal financial advice for the user. This advice includes specific savings strategies and investment plans. A generation AI model is used to create personalized recommendations tailored to the user's needs. This series of recommendations is delivered to the user's device in real time via a notification system. On the device, the advice is displayed visually, using easy-to-understand graphs and indicators.

[0534] For example, if a user sets their goal to "reduce monthly food expenses" and has recently been experiencing stress, the server will generate a recommendation such as, "Increasing the time you spend enjoying cooking at home will effectively save on food expenses and reduce stress." An example of a prompt used in this case would be, "Consider the user's recent financial data and emotional state to generate recommendations that will lead to effective savings and stress reduction."

[0535] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0536] Step 1:

[0537] The server retrieves users' financial information using financial information connectivity. Inputs include bank account information and transaction history data transmitted via API. The server receives this data in encrypted form and securely stores it in its internal database. Outputs are raw financial transaction data categorized for further processing.

[0538] Step 2:

[0539] The server categorizes the acquired financial transaction data using information classification methods. This process utilizes scripts to analyze input data and assign it to categories such as regular spending, income, savings, and investments. The output is organized, categorized data that helps users understand their financial status.

[0540] Step 3:

[0541] The server uses emotion analysis tools to analyze voice input and text data from users. The input consists of text information extracted from the user's voice and messages. The server analyzes this data using machine learning algorithms to evaluate the user's emotional state. The output is an emotional status such as stress, happiness, or anxiety.

[0542] Step 4:

[0543] The server integrates the analyzed financial and emotional data and uses recommendation generation tools to generate the best recommendations for the user. The input is the data obtained in steps 2 and 3. The server uses a generative AI model to compute the data in order to build recommendations tailored to the user's specific needs. The output is personalized advice presented to the user.

[0544] Step 5:

[0545] The terminal provides the user with recommendations sent from the server via a notification mechanism. The input is the advice generated in step 4. The terminal creates graphs and infographics to visually display the advice and presents them on the user's screen. The output is the recommendation information displayed in a format that is easy for the user to understand.

[0546] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0547] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0548] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0549] [Fourth Embodiment]

[0550] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0551] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0552] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0553] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0554] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0555] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0556] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0557] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0558] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0559] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0560] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0561] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0562] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0563] This invention is a comprehensive system that supports personal financial management and is specifically implemented by the following means. First, the server acquires the user's bank account and credit card transaction data via financial data connection means. This allows financial information to be collected automatically without the user having to manually enter data.

[0564] Subsequently, the server's data classification system categorizes the acquired transaction data into categories such as food expenses, transportation expenses, and entertainment expenses. This process is performed to make it easier to clearly understand the user's spending habits.

[0565] The classified data is analyzed by the server's data processing capabilities. During the analysis, past spending trends and income fluctuations are examined, and the user's financial status is assessed. Furthermore, appropriate investment decisions are made based on the user's risk tolerance and specific goals (e.g., purchasing a home, saving for retirement).

[0566] Based on the analysis results, the server's advice generation system creates specific suggestions for improving the user's finances. These include suggestions for reducing unnecessary spending and selecting investment products that align with the user's goals.

[0567] The generated advice is presented to the user using the terminal's information delivery system. The user interface displays the information clearly and visually, making it easy for the user to understand and implement the advice.

[0568] For example, if user A sets a goal of "buying a home in five years," the server will propose the optimal investment plan to achieve that goal. This plan will include financial products and saving methods to save the target amount while minimizing risk.

[0569] Thus, the present invention supports economic stability and the achievement of future goals by providing a system that allows users to easily manage their own financial situation and select appropriate asset management and saving methods.

[0570] The following describes the processing flow.

[0571] Step 1:

[0572] The server retrieves user bank account and credit card transaction data through financial institutions' APIs. This data is collected securely using the user's authentication information. This data includes transaction details, transaction date, and amount.

[0573] Step 2:

[0574] The server's data classification mechanism categorizes acquired transaction data into categories such as food expenses, transportation expenses, utility expenses, and entertainment expenses. This function analyzes the content of each transaction and automatically organizes it based on a predefined category list.

[0575] Step 3:

[0576] The server's data processing system analyzes classified data to understand the user's income and expenditure balance and spending patterns. It also identifies fluctuations in income and spending trends based on past transaction history to evaluate the user's financial situation.

[0577] Step 4:

[0578] Based on the analysis results, the server uses an advice generation mechanism to generate asset management suggestions tailored to the user. These suggestions include investment products and portfolios that align with the user's set risk tolerance and financial goals.

[0579] Step 5:

[0580] The server's advice generation mechanism analyzes user spending data to identify unnecessary expenses. Based on these identified unnecessary expenses, it provides specific savings suggestions, indicating how much can be saved in each category.

[0581] Step 6:

[0582] The terminal displays advice and suggestions received from the server on the user interface. To ensure user understanding, the information is presented visually using graphs and tables.

[0583] Step 7:

[0584] Users review the advice displayed on their device and adjust their financial goals and risk tolerance as needed. This information is sent from the device to the server and used again for further analysis.

[0585] Step 8:

[0586] The server records new user inputs and settings in a database, which are then used for subsequent suggestions and analyses. This ensures that the system is always operated based on the latest user information.

[0587] (Example 1)

[0588] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0589] In personal financial management, manually collecting and analyzing transaction data from multiple financial institutions is time-consuming and labor-intensive, making it difficult to identify unnecessary spending and make appropriate investment decisions. As a result, users face the challenge of not being able to efficiently manage their assets to achieve their future financial goals.

[0590] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0591] In this invention, the server includes means for acquiring financial data, means for classifying data, means for processing data, means for generating suggestions, and means for presenting information. This enables the automatic collection and organization of an individual's economic transaction data, visualization of their economic situation including unnecessary spending, and the proposal of optimal asset management tailored to the user's goals.

[0592] A "financial data acquisition method" is an interface for automatically collecting users' economic transaction data from external financial institutions.

[0593] A "data classification method" is a function that analyzes acquired economic transaction data and divides each item into predefined categories.

[0594] A "data processing tool" is a function that analyzes the user's spending and income trends based on classified data and evaluates their financial situation.

[0595] A "proposal generation method" is a system that creates specific proposals for optimal asset management and achieving economic goals for the user based on the results of data processing and analysis.

[0596] An "information presentation method" is a function that visually communicates generated suggestions to the user through a user interface.

[0597] This invention is an integrated system for efficiently managing and optimizing a user's personal financial activities. This system functions through the coordinated efforts of a server, a terminal, and the user.

[0598] The server securely retrieves transaction data from multiple financial institutions, such as the user's bank account and credit card company, using financial data acquisition methods. Specifically, it can periodically update data using the APIs of each financial institution. The acquired data is stored in an encrypted format in the server's database, ensuring user privacy.

[0599] Next, the server uses a data classification mechanism to automatically categorize the acquired transaction data. For example, groceries purchased at a supermarket are classified as food expenses, and the use of public transportation is classified as transportation expenses. This automated classification allows users to efficiently track their spending.

[0600] Subsequently, the server analyzes the classified data using data processing tools to understand past spending trends and fluctuations in income. It can also apply machine learning algorithms to predict future income and expenses. This data processing allows for a detailed assessment of the user's financial situation.

[0601] The server uses a proposal generation mechanism to generate specific suggestions for financial improvement for the user based on the analysis results. These suggestions include ideas for reducing wasteful spending and selecting the optimal financial products to help the user achieve their goals.

[0602] The generated suggestions are transmitted to the terminal via an information presentation system and presented to the user visually and intuitively. The user interface is designed to be easily understood, allowing the user to obtain information to take concrete action.

[0603] For example, if a user sets a goal of "buying a house in five years," the system will propose a savings plan and investment strategy necessary to achieve that goal. This selection will include financial products with reduced risk. Advice on everyday saving methods will also be provided.

[0604] An example of a prompt for a generating AI model might be: "Based on User A's current spending habits and financial goals, please suggest the optimal investment and saving strategies for purchasing a home within five years."

[0605] In this way, users can accurately manage their financial situation and take strategic actions to achieve their future goals.

[0606] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0607] Step 1:

[0608] The server uses financial data acquisition methods to retrieve user transaction data from each financial institution's API. This input data includes transaction date and time, amount, and trading partner information. The server automatically collects this data daily and stores it in an encrypted state in the database. This process minimizes manual work for the user and ensures accurate data collection.

[0609] Step 2:

[0610] The server classifies the acquired transaction data using data classification methods. This process analyzes the content of each input transaction and categorizes it (e.g., food expenses, transportation expenses, utilities). Specifically, categories are assigned based on the name of the trading partner and the transaction details using natural language processing technology. The output includes category labels for each transaction, allowing the user to understand the breakdown of their expenses.

[0611] Step 3:

[0612] The server analyzes the classified data using various data processing tools. Historical expenditure and income data are used as input. The analysis employs machine learning algorithms to evaluate expenditure and income trends and predict future financial outcomes. The output data includes an assessment of the user's current financial situation, along with future forecasts.

[0613] Step 4:

[0614] The server generates specific financial improvement proposals based on data analysis results using a proposal generation mechanism. Inputs include analysis results and user-defined financial targets. The generated proposals include specific savings advice and recommended investment products. The output is optimized proposals tailored to the user's individual circumstances.

[0615] Step 5:

[0616] The terminal presents generated suggestions to the user through an information display mechanism. It receives suggestion information provided by the server as input. By forming visual dashboards and charts and providing users with easily understandable, visualized information as output, users can easily understand the suggestions and use them to take actual action.

[0617] (Application Example 1)

[0618] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0619] In personal financial management, there is a need for a unified system that automatically collects and classifies financial activity information, provides concrete asset management suggestions based on analysis, and presents spending information in real time. However, conventional systems have not adequately integrated these functions, and have not provided sufficient support for users to effectively improve their financial situation.

[0620] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0621] In this invention, the server includes financial information connection means, information classification means for classifying an individual's financial activity information collected using the financial information connection means, and information processing means for storing and analyzing the information obtained by the information classification means. This makes it possible for individuals to quickly and easily grasp their own financial situation and receive specific asset management suggestions.

[0622] A "financial information connection method" is a means that securely connects financial institution data, such as an individual's bank and credit card information, and has the function of automatically acquiring financial activity information.

[0623] An "information classification tool" is a means that has the function of organizing collected financial activity information into categories and classifying it into a format that can be easily analyzed.

[0624] An "information processing means" is a means that stores classified information and has the function of analyzing income and expenditure trends based on that information.

[0625] A "proposal generation means" is a means that has the function of automatically generating specific proposals for improving an individual's financial situation based on the analysis results of an information processing means.

[0626] An "information provision method" is a means that has the function of visually displaying generated suggestions to an individual and providing them as practical advice.

[0627] A "visual display method" is a means that visualizes an individual's income and expenditure data in an easy-to-understand manner, and has the function of supporting a real-time understanding of their financial situation.

[0628] An "investment proposal tool" is a tool that has the function of selecting and proposing specific steps and financial products for efficient asset management according to an individual's goals.

[0629] This invention is implemented as a system to streamline personal financial management and provide concrete asset management suggestions. The system automatically acquires personal financial information, analyzes and classifies the collected information, and provides advice for financial improvement.

[0630] The server uses "financial information connection means" to securely connect to the user's bank and credit card information and collect financial activity information. This uses highly secure APIs and data security protocols. Next, "information classification means" are used to classify each transaction into categories and clarify the user's spending trends.

[0631] The collected and categorized information is analyzed by an "information processing system" to evaluate the individual's income and expenditure patterns. Here, data analysis is performed using programming languages ​​such as Python and the Pandas library. Based on the analysis results, a "proposal generation system" generates specific and practical suggestions to improve the user's financial situation. These suggestions are generated using an AI module to construct an optimal asset management plan tailored to the user's goals.

[0632] Ultimately, the "information delivery tools" are utilized, and the generated proposals are delivered to the user through a user card widget or mobile application. Here, a visually intuitive interface is designed using React Native. This allows users to easily understand and implement the financial proposals.

[0633] For example, if a user sets a goal of "saving money for a trip in one year," the system will analyze their monthly expenses and provide specific advice such as, "Let's cut back on eating out this month and increase your savings." In this case, an example of a prompt message generated by the AI ​​model would be, "Based on the user's monthly spending data, please generate advice on how to save money for a trip in one year."

[0634] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0635] Step 1:

[0636] The server securely obtains the user's bank and credit card information through financial information connectivity. Inputs include the user's authentication information and transaction data from financial institutions. Output is the secure aggregation of transaction information on the server. Specifically, it uses APIs to access financial institution databases and asynchronously collects the necessary transaction data.

[0637] Step 2:

[0638] The server categorizes the financial transaction information obtained using an information classification system. The input is the transaction data collected in step 1, and the output is transaction information organized by category. Specifically, it creates a data frame using the Pandas library and applies an algorithm to classify the data into existing categories such as "food expenses" and "transportation expenses."

[0639] Step 3:

[0640] The server uses information processing tools to analyze the classified data. The input here is the category-specific transaction data obtained in step 2, and the output is the analysis of individual spending trends based on the classified data. Specifically, statistical methods (e.g., moving average, trend analysis) are applied to aggregate data and analyze past spending trends.

[0641] Step 4:

[0642] The server uses a proposal generation mechanism to generate investment proposals tailored to the user's goals via a generating AI model. The input is the analysis results from step 3 and the user's goal data, and the output is personalized investment advice. Specifically, the AI ​​model is used to generate an optimal savings strategy that takes into account the user's income and expenses and risk tolerance. An example of a prompt to the generating AI model is, "Based on the user's monthly spending data, please generate advice on how to save for a trip in one year."

[0643] Step 5:

[0644] The device utilizes information delivery methods to visually present the generated advice to the user. The input is the advice data from step 4, and the output is an easy-to-understand advice screen provided to the user. Specifically, React Native is used to visually display the information using card widgets and interactive charts.

[0645] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0646] This invention is a system that supports users in managing their finances and provides advice that takes into account the user's emotional state using an emotion engine. In this system, the server first acquires the user's bank account and credit card transaction data via a financial data connection means. The acquired data is organized into categories by a data classification means and forms the basis for understanding the user's income and expenses and asset status.

[0647] Next, the server's data processing system analyzes the obtained data to diagnose the user's financial status. At this stage, the server inputs emotional data into the user's emotion engine to collect the user's emotional state. Emotions are detected, for example, through voice input or text analysis.

[0648] The server's advice generation mechanism combines this financial and emotional data to generate the most appropriate advice for the user. For example, if a user is under stress, it can offer suggestions that provide reassurance by recommending a low-risk investment strategy.

[0649] The advice received is presented to the user through the device's information delivery system. The user can view the information displayed on the device and make appropriate decisions by referring to visually presented indicators and graphs designed for easy understanding.

[0650] For example, if user B sets the goal of "increasing savings" and has been feeling stressed recently, the server will suggest small-scale investments in low-risk products and also provide guidance on saving methods to alleviate anxiety.

[0651] Thus, the present invention provides a means for constructing a system that comprehensively assesses the user's emotions and financial data to provide asset management and saving methods that the user can implement with confidence.

[0652] The following describes the processing flow.

[0653] Step 1:

[0654] The server obtains the user's bank account and credit card information through financial data connectivity. Here, APIs are used to securely collect data, obtaining the amount, date, time, and category information for each transaction. This data collection process is performed regularly to ensure that the user's current financial situation is always reflected.

[0655] Step 2:

[0656] The server's data classification system analyzes acquired financial transaction data and automatically categorizes it into predefined categories, such as food expenses, transportation expenses, and utility expenses. This clarifies the user's spending patterns and helps identify unnecessary expenses.

[0657] Step 3:

[0658] The server's emotion engine analyzes user input and dialogue to recognize emotions from speech and text. It identifies emotional states such as optimism, pessimism, and stress, and provides the results to data processing tools. This emotional data is considered as a factor influencing user decision-making.

[0659] Step 4:

[0660] The data processing system integrates and analyzes classified financial and sentiment data. It detects fluctuations in income and expenses and increases / decreases in assets, and evaluates the user's progress toward achieving their goals. Based on this information, it generates more detailed diagnostic results regarding the current financial status.

[0661] Step 5:

[0662] The server's advice generation mechanism constructs user-specific advice based on evaluation results. This advice can focus, for example, on investment strategies to mitigate risk or cost-saving measures to reduce psychological stress, supporting the user in achieving their specific goals.

[0663] Step 6:

[0664] The generated advice is presented to the user through the device's information delivery system. Here, a visually organized dashboard is used to show revenue forecasts, risk assessments, and savings suggestions in a way that is easy for the user to understand intuitively.

[0665] Step 7:

[0666] Users can review the presented information and adjust their financial goals and budgets accordingly. They can also re-evaluate suggestions based on their emotional state and make decisions to select the optimal action. This feedback is then sent back to the server and used for the system's subsequent analysis.

[0667] (Example 2)

[0668] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0669] Modern consumers engage in diverse financial transactions, but lack methods to consider the emotional aspects in managing them. This leads to problems such as inappropriate asset management due to stress and emotional fluctuations, resulting in inefficient asset management. Therefore, there is a need to provide comprehensive asset management support that takes consumers' emotions into account.

[0670] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0671] In this invention, the server includes financial information linking means, data organization means, data analysis means, advice generation means, emotion analysis means, and information transmission means. This makes it possible to comprehensively analyze the user's financial behavior data and emotional state and generate and provide optimal advice tailored to each individual's situation.

[0672] "Financial information sharing means" refers to methods for obtaining information from various financial institutions, such as users' bank accounts and credit cards.

[0673] "Data organization methods" refer to means of organizing acquired financial behavioral data according to specific categories or classifications, and preparing it in a format suitable for analysis and evaluation.

[0674] "Data analysis means" refers to a means of evaluating and diagnosing a user's asset situation using classified financial behavior data and providing basic information for asset management.

[0675] An "advice generation method" is a means of generating specific advice and recommendations based on the results of data analysis methods, with the aim of improving the user's asset management.

[0676] "Emotional analysis methods" are means of collecting and analyzing the emotional state of users through voice input and text analysis, and using that information to generate advice.

[0677] "Information transmission means" refers to means of providing generated advice or recommendations to users visually or aurally, and communicating them in an easily understandable format.

[0678] This invention is a system for streamlining asset management by comprehensively considering a user's financial behavior and emotional state. This system provides an optimal asset management strategy for each individual user by smoothly processing data among the server, terminal, and user.

[0679] The server first uses financial information sharing methods to obtain transaction data from users' bank accounts and credit cards. During this process, technologies such as "financial API systems" are used to securely transfer the latest data in accordance with appropriate security protocols. The acquired data is then categorized using data organization tools, for example, into items such as "fixed costs," "variable costs," and "income." This establishes a foundation for efficiently managing large amounts of transaction data.

[0680] Next, the server's data analysis system uses the acquired data to perform a financial diagnosis of the user. At this stage, "data analysis software" is used to evaluate past spending patterns and asset liquidity. In addition, sentiment analysis tools use voice input and text analysis to understand the user's emotional state. For example, a "sentiment analysis engine" estimates the stress level from tone of voice and word choice.

[0681] By combining generated emotional and financial data, the server's advice generation system creates the most suitable asset management advice for each individual user. For example, if a user has recently been experiencing stress, the system will suggest prioritizing savings plans over high-risk investments. The completed advice is delivered to the user via the terminal's information transmission system and displayed in a visually easy-to-understand format using graphs and charts.

[0682] Users can view visualized information through their devices and use it to manage their own assets. For example, they can see how their monthly expenses fluctuate and implement concrete measures to reduce waste.

[0683] By utilizing a generative AI model, this system can provide optimal advice based on prompts. For example, a possible prompt might be, "Consider the user's financial situation and emotional state, and generate investment and savings advice to reduce stress." This allows for more personalized responses.

[0684] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0685] Step 1:

[0686] The server obtains the latest transaction data from the user's financial institution through financial information sharing mechanisms. This input data includes the user's bank transaction history and credit card statements. The server receives this data and stores it using encryption protocols to ensure the security of the communication. Next, this stored data is prepared to be organized into categories from its raw state.

[0687] Step 2:

[0688] The server classifies the acquired financial data into categories using data organization tools. Input data is divided into categories such as "food expenses," "transportation expenses," and "income" based on specific keywords or transaction details. The server uses natural language processing technology to analyze transaction details and automatically map them to the appropriate categories. The output of this process is an organized transaction list with each transaction assigned a category.

[0689] Step 3:

[0690] The server uses data analysis tools to perform a detailed analysis of the organized transaction list. The input data consists of transaction history from the past few months, categorized for each purpose. The server applies analytical algorithms to analyze the user's spending patterns and assess their asset liquidity. The output of this analysis step is a report that includes the user's financial health and average values ​​for specific spending items.

[0691] Step 4:

[0692] The server uses emotion analysis tools to collect and analyze the user's emotional state. In this process, voice input or text data is used as input to the emotion analysis engine. The server detects emotions from the input data and quantifies stress levels and motivation. The output of this analysis is parameterized emotional state data.

[0693] Step 5:

[0694] The server uses an advice generation mechanism to combine financial and emotional data to generate optimal asset management advice for the user. Financial reports and emotional state data are used as input. The generating AI model uses prompts, such as "I am experiencing high stress, please suggest a conservative investment strategy," to create personalized advice. This advice is output as recommendations, including optimal investment choices and saving methods.

[0695] Step 6:

[0696] The terminal receives advice sent from the server and displays it visually. Based on the advice, the terminal generates graphs and charts and presents them to the user in a visually easy-to-understand format. The user can use this information to review their asset management methods and aid in decision-making. The output of this step is a visualized information dashboard that is easy for the user to understand.

[0697] (Application Example 2)

[0698] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0699] In today's world, consumers engage in a wide variety of financial transactions, but they face the challenge of managing their finances while taking their emotional state into account. Furthermore, emotional decisions can lead to wasteful spending or inappropriate investments. Therefore, there is a growing demand for systems that provide appropriate and personalized financial advice while considering the consumer's emotional state.

[0700] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0701] In this invention, the server includes financial information connection means, information classification means, emotion analysis means, recommendation generation means, and notification means. This enables the integration of the user's financial data and emotional data, allowing for financial management and spending optimization that takes emotional states into account.

[0702] "Financial information connection means" refers to a means of securely and efficiently obtaining a user's account data and transaction information from their financial institution.

[0703] An "information classification method" is a means of classifying acquired user financial transaction information into various categories and organizing it in an easy-to-understand format.

[0704] "Information processing means" refers to a method of analyzing data based on classified financial transaction information to understand the financial situation of users.

[0705] A "recommendation generation method" is a means of generating advice that leads to the improvement of the user's finances, based on analyzed data and the user's emotional state.

[0706] A "notification method" is a means of providing the generated advice to the user and presenting it in a visually or audibly easy-to-understand format.

[0707] "Emotional analysis means" refers to a method of detecting a user's emotional state by analyzing their voice and text information and reflecting that state in the data.

[0708] The server functions as the core of the system, securely acquiring users' financial information using financial information connectivity. This data is exchanged in an encrypted format using APIs. The acquired data is then classified into categories such as transactions, income, and fixed expenses using information classification tools. The information processing tools then use this classified data to perform analysis to understand the user's financial situation.

[0709] Next, the server detects the user's emotional state from their voice input and text data through an emotion analysis tool. This typically involves using machine learning algorithms, such as the Google Cloud Natural Language API.

[0710] Next, the recommendation generation system integrates the analyzed financial and emotional data to generate optimal financial advice for the user. This advice includes specific savings strategies and investment plans. A generation AI model is used to create personalized recommendations tailored to the user's needs. This series of recommendations is delivered to the user's device in real time via a notification system. On the device, the advice is displayed visually, using easy-to-understand graphs and indicators.

[0711] For example, if a user sets their goal to "reduce monthly food expenses" and has recently been experiencing stress, the server will generate a recommendation such as, "Increasing the time you spend enjoying cooking at home will effectively save on food expenses and reduce stress." An example of a prompt used in this case would be, "Consider the user's recent financial data and emotional state to generate recommendations that will lead to effective savings and stress reduction."

[0712] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0713] Step 1:

[0714] The server retrieves users' financial information using financial information connectivity. Inputs include bank account information and transaction history data transmitted via API. The server receives this data in encrypted form and securely stores it in its internal database. Outputs are raw financial transaction data categorized for further processing.

[0715] Step 2:

[0716] The server categorizes the acquired financial transaction data using information classification methods. This process utilizes scripts to analyze input data and assign it to categories such as regular spending, income, savings, and investments. The output is organized, categorized data that helps users understand their financial status.

[0717] Step 3:

[0718] The server uses emotion analysis tools to analyze voice input and text data from users. The input consists of text information extracted from the user's voice and messages. The server analyzes this data using machine learning algorithms to evaluate the user's emotional state. The output is an emotional status such as stress, happiness, or anxiety.

[0719] Step 4:

[0720] The server integrates the analyzed financial and emotional data and uses recommendation generation tools to generate the best recommendations for the user. The input is the data obtained in steps 2 and 3. The server uses a generative AI model to compute the data in order to build recommendations tailored to the user's specific needs. The output is personalized advice presented to the user.

[0721] Step 5:

[0722] The terminal provides the user with recommendations sent from the server via a notification mechanism. The input is the advice generated in step 4. The terminal creates graphs and infographics to visually display the advice and presents them on the user's screen. The output is the recommendation information displayed in a format that is easy for the user to understand.

[0723] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0724] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0725] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0726] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0727] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0728] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0729] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0730] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0731] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0732] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0733] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0734] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0735] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0736] 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.

[0737] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0738] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0739] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0740] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0741] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0742] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0743] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0744] The following is further disclosed regarding the embodiments described above.

[0745] (Claim 1)

[0746] Financial data connection means,

[0747] A data classification means for classifying user financial transaction data collected using the aforementioned financial data connection means,

[0748] A data processing means for storing and analyzing data obtained by the data classification means,

[0749] An advice generation means that generates advice for improving the user's financial condition based on the analysis results of the data processing means,

[0750] Information provision means for providing advice obtained by the advice generation means to the user,

[0751] A system that includes this.

[0752] (Claim 2)

[0753] The system according to claim 1, wherein the advice generation means includes a function to optimize the investment portfolio and select investment products according to the user's financial goals.

[0754] (Claim 3)

[0755] The system according to claim 1, wherein the data classification means includes a function to classify the user's financial transaction data by category and identify unnecessary spending.

[0756] "Example 1"

[0757] (Claim 1)

[0758] means of acquiring financial data,

[0759] A data classification means for classifying the user's economic transaction data obtained using the aforementioned financial data acquisition means,

[0760] A data processing means for recording and analyzing the data obtained by the data classification means,

[0761] A proposal generation means that creates proposals for improving the user's financial situation based on the analysis results from the aforementioned data processing means,

[0762] Information presentation means for presenting proposals obtained by the proposal generation means to the user,

[0763] An integrated system that includes this.

[0764] (Claim 2)

[0765] The integrated system according to claim 1, wherein the proposal generation means includes a function to optimize an investment portfolio and select financial products based on the user's economic goals.

[0766] (Claim 3)

[0767] The integrated system according to claim 1, wherein the data classification means includes a function to classify the user's economic transaction data by category and identify unnecessary spending.

[0768] "Application Example 1"

[0769] (Claim 1)

[0770] Financial information connectivity structure,

[0771] An information classification structure for classifying an individual's financial activity information collected using the aforementioned financial information connection structure,

[0772] An information processing structure that stores and analyzes the information obtained by the aforementioned information classification structure,

[0773] Based on the analysis results of the aforementioned information processing structure, a proposal generation structure is provided to generate suggestions for improving an individual's financial situation.

[0774] An information provision structure that provides proposals obtained through the aforementioned proposal generation structure to individuals,

[0775] A visual display structure that visually displays individual income and expense information in real time,

[0776] An investment proposal structure that provides specific asset management suggestions based on individual goals,

[0777] A system that includes this.

[0778] (Claim 2)

[0779] The system according to claim 1, wherein the proposal generation structure has a function of optimizing investment allocation, selecting financial products, and presenting a specific savings strategy according to an individual's financial goals.

[0780] (Claim 3)

[0781] The system according to claim 1, wherein the information classification structure includes a function to classify an individual's financial activity information by category and identify unnecessary spending.

[0782] "Example 2 of combining an emotion engine"

[0783] (Claim 1)

[0784] Financial information sharing methods,

[0785] A data organization means for classifying user financial behavior data collected using the aforementioned financial information sharing means,

[0786] A data analysis means that records and processes the information obtained by the aforementioned data organization means,

[0787] An advice generation means that generates advice for improving the user's asset management based on the analysis results of the data analysis means,

[0788] Information transmission means for providing advice obtained by the advice generation means to the user,

[0789] An emotion analysis means that collects the emotional state of the user and generates advice considering the emotional state of the user in the advice generation means,

[0790] A system that includes this.

[0791] (Claim 2)

[0792] The system according to claim 1, wherein the advice generation means includes a function to optimize the investment composition and select investment products according to the user's asset goals.

[0793] (Claim 3)

[0794] The system according to claim 1, wherein the data organization means includes a function to classify the user's financial behavior data by category and identify unnecessary expenses.

[0795] "Application example 2 when combining with an emotional engine"

[0796] (Claim 1)

[0797] Financial information connection means,

[0798] Information classification means for classifying user financial transaction information collected using the aforementioned financial information connection means,

[0799] Information processing means for storing and analyzing information obtained by the information classification means,

[0800] A recommendation generation means that generates recommendations for improving the user's financial situation based on the analysis results of the aforementioned information processing means,

[0801] A notification means for providing recommendations obtained by the recommendation generation means to the user,

[0802] An emotional analysis means for detecting the user's emotional state and reflecting it in the recommendation,

[0803] A system that includes this.

[0804] (Claim 2)

[0805] The system according to claim 1, wherein the recommendation generation means includes a function to optimize an investment plan and select investment targets according to the user's financial goals.

[0806] (Claim 3)

[0807] The system according to claim 1, wherein the information classification means includes a function to classify the user's financial transaction information by category and identify unnecessary expenditures. [Explanation of symbols]

[0808] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Financial information connection means, Information classification means for classifying an individual's financial activity information collected using the aforementioned financial information connection means, Information processing means for storing and analyzing information obtained by the information classification means, A proposal generation means that generates proposals for improving an individual's financial situation based on the analysis results of the aforementioned information processing means, Information provision means for providing proposals obtained by the proposal generation means to an individual, A visual display means for visually displaying individual income and expense information in real time, An investment proposal tool that provides specific asset management suggestions based on individual goals, A system that includes this.

2. The system according to claim 1, comprising a function in which the proposal generation means optimizes investment allocation, selects financial products, and presents a specific savings strategy according to an individual's financial goals.

3. The system according to claim 1, wherein the information classification means includes a function to classify an individual's financial activity information by category and identify unnecessary spending.

Images