system

Abstract

We provide the system. [Solution] Means of obtaining financial information, A means for preprocessing the acquired financial information and organizing it by classification, A means for performing anomaly detection using the aforementioned organized information, A means for visualizing the results of the anomaly detection and presenting them to the user, A means of generating and notifying users of cost reduction proposals, A means to detect unnecessary spending based on users' consumption habits and generate specific reduction suggestions, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern households, there is a problem that it is difficult to perform effective household management among complex and diverse expenditures and incomes. In particular, changes in consumption patterns and unexpected expenses put pressure on the budget, and in many cases, asset formation is hindered by missing opportunities for savings. Also, it is not easy to make a long-term financial plan considering future life events. Therefore, in order to enable users to perform asset formation with confidence, it is necessary to grasp income and expenditure in real time and support appropriate savings proposals and asset management.

Means for Solving the Problems

[0005] This invention solves the aforementioned problems by proposing a system for acquiring and preprocessing financial data and organizing it by category. Furthermore, it provides a means for detecting abnormal spending based on the acquired data, visualizing it, and displaying it to the user. In addition, it analyzes the user's unique consumption patterns, identifies items where savings can be made, and generates and notifies the user of specific and dynamic savings suggestions. As a result, users can grasp their spending status in real time, making asset management easier, and enabling simulations tailored to future life events.

[0006] "Financial data" refers to information about a user's economic activities, such as bank account transaction information and credit card usage history.

[0007] "Preprocessing" refers to the process of removing noise and unnecessary information from raw data and organizing and formatting it into a form that can be analyzed.

[0008] A "category" is a classification of consumption or expenditure based on specific purposes or uses, and includes, for example, food expenses, utility expenses, and entertainment expenses.

[0009] "Anomaly detection" refers to the process of identifying expenditures or income that deviate from normal consumption patterns and recognizing them as unusual activity.

[0010] "Visualization" refers to the technique of representing data and information in visual formats such as graphs and charts to make them easier to understand.

[0011] "Savings suggestions" refer to suggestions that analyze a user's spending patterns and then present specific action plans and methods for reducing expenses.

[0012] "Simulation" refers to a technique for setting up a virtual environment and conditions to predict future events and states, and to consider appropriate countermeasures. [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 the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

[0016] In the following embodiments, the 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, the 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, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[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] To implement this invention, it is first necessary to build a system infrastructure capable of processing financial data. Specifically, it is required to securely acquire transaction information from users' bank accounts and credit cards and prepare the data so that it can be analyzed. This system operates in cooperation with users, servers, and terminals.

[0035] Data acquisition and management

[0036] The server retrieves bank account and credit card transaction data through APIs authorized by the user. This data is encrypted and securely stored in a database on the server.

[0037] Data analysis and notification

[0038] The server analyzes the accumulated data and organizes it by category. Machine learning algorithms are used to detect unusual spending patterns and other abnormalities from the data. These algorithms generate predictive models based on historical data to perform anomaly detection.

[0039] The device displays analysis results to the user in visual formats such as dashboards and graphs. It also notifies the user with savings suggestions and warnings about unusual spending.

[0040] Personalized savings proposals and asset management

[0041] The server identifies potential cost savings based on the user's consumption patterns. For example, it might detect unnecessary subscription services or suggest cheaper utility plans.

[0042] The device displays these savings suggestions to the user, who can then select them to improve their asset management.

[0043] Simulation and long-term financial planning

[0044] The server runs simulations that take future life events into account and generates long-term financial plans. This allows users to predict their future financial situation and take necessary measures.

[0045] The terminal displays the simulation results to the user and provides information to adjust the plan.

[0046] Specific example

[0047] In some households, if monthly electricity consumption exceeds acceptable limits, the server detects and analyzes the anomaly in real time. The terminal notifies the user of this information and suggests energy-saving measures, such as changing plans with a specific electricity provider. By considering these suggestions and taking action as needed, users can reduce their household expenses and achieve efficient asset management.

[0048] In this manner, the present invention provides embodiments for more efficient and dynamic household financial management in individual households.

[0049] The following describes the processing flow.

[0050] Step 1:

[0051] Users register their financial institution account information with the system and authorize the retrieval of their data.

[0052] Step 2:

[0053] The server retrieves transaction data in real time through financial institutions' APIs, based on information authorized by the user. The retrieved data is encrypted and stored in a secure database.

[0054] Step 3:

[0055] The server analyzes the stored data and organizes income and expenses by category. This uses defined categories such as food expenses, transportation expenses, and medical expenses. Data cleaning is also performed at this stage.

[0056] Step 4:

[0057] The server uses machine learning algorithms based on historical data to detect unusual spending patterns. This identifies abnormal spending that deviates from normal trends.

[0058] Step 5:

[0059] The terminal visualizes the results of anomaly detection and the overall household financial situation on a dashboard and displays it to the user. Graphs and pie charts are used to make the information easy to understand.

[0060] Step 6:

[0061] The server analyzes the user's consumption patterns and suggests areas where expenses can be reduced. It generates specific savings suggestions, such as reviewing utility bills or cutting costs on subscription services.

[0062] Step 7:

[0063] The device notifies the user of these savings suggestions and provides options for actually implementing them. The user can review the notification and select a savings plan.

[0064] Step 8:

[0065] The server runs a simulation of long-term financial planning based on future life events (e.g., saving for education or retirement planning).

[0066] Step 9:

[0067] The terminal displays the simulation results to the user and supports them in adjusting their asset management plan as needed.

[0068] (Example 1)

[0069] 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."

[0070] In modern financial management, many users seek ways to efficiently understand their financial activities and reduce waste. However, because a large amount of transaction information is scattered across many different platforms, integrating and analyzing it safely and efficiently is difficult. Furthermore, obtaining the information necessary for long-term asset management and improving consumption patterns is a time-consuming and laborious task using current methods.

[0071] 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.

[0072] In this invention, the server includes means for acquiring user transaction information and securely managing the information, means for encrypting the acquired transaction information and storing it in a storage device, and means for processing the information stored in the storage device and classifying the data. This enables users to securely manage and analyze their financial information on a centralized interface, and to efficiently detect abnormal expenditures and reduce waste.

[0073] A "user" is an individual or legal entity that uses information or services related to financial transactions.

[0074] "Transaction information" refers to data obtained from financial activities such as bank accounts and credit cards, including specific transaction and deposit histories.

[0075] "Encryption" is the process of transforming data using a specific algorithm to prevent it from being misused by third parties.

[0076] A "storage device" is hardware or a medium used to temporarily or permanently store digital data.

[0077] A "machine learning algorithm" is a program that uses past data to recognize patterns and make predictions and classifications about future data.

[0078] "Visual display" refers to using visual formats such as graphs and charts to convey information to users in an easy-to-understand manner.

[0079] A "suggestion" is information that provides specific strategies for saving money and managing assets efficiently, based on the user's financial activities.

[0080] "Simulation" is the process of using a computer to predict the outcome of a real-world situation.

[0081] "Usage patterns" refer to a series of habits and tendencies derived from a user's transaction history and consumption behavior.

[0082] A "strategy" refers to the direction or measures provided to achieve a specific objective.

[0083] In order to implement this invention, it is first necessary to build a foundation for processing financial data. Specifically, a system is installed to securely acquire, store, and analyze user transaction information. The embodiments thereof are described in detail below.

[0084] Data acquisition and management

[0085] The server retrieves financial transaction data through APIs authorized by the user. The technology used includes authentication processes such as OAuth to establish a secure connection. The retrieved data is protected using encryption methods such as AES-256, and the database is stored using a common cloud storage service.

[0086] Data analysis and visualization

[0087] The server performs an ETL process on the acquired data. Specifically, it uses the Python Pandas library to organize the data into categories for data frame analysis. Then, it uses machine learning libraries such as Scikit-learn and TENSORFLOW® to perform anomaly detection. The analysis results are displayed on the user interface via the terminal. D3.js and Chart.js are used for visualization.

[0088] Proposals and notifications

[0089] The device displays data-driven savings suggestions and warnings based on detected anomalies to the user. This includes real-time communication via push notifications using Firebase Cloud Messaging. Users can then take action based on this information.

[0090] Long-term plan simulation

[0091] The server conducts simulations that take into account important future events and uses generative AI models such as Keras to develop long-term asset plans. This allows users to predict future economic conditions and create life plans based on that information. The results are displayed graphically, and users can adjust their plans accordingly.

[0092] As a concrete example, a user monitors their monthly electricity consumption, and an anomaly is detected if it exceeds a certain threshold. In this case, the server analyzes the anomaly in real time, and the terminal presents the user with specific suggestions for saving energy (for example, changing electricity plans), enabling the user to manage their assets efficiently.

[0093] An example of a prompt message is, "Please tell me how to analyze a user's monthly spending patterns and detect unusual spending."

[0094] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0095] Step 1:

[0096] The server retrieves transaction information through an API authorized by the user. The input requires user authentication credentials and API access permission. The server authenticates the user using the OAuth protocol and establishes a secure connection. It then sequentially downloads the transaction information via a RESTful API, encrypts this data, and stores it in temporary storage. The output is the encrypted transaction information.

[0097] Step 2:

[0098] The server stores the acquired transaction information in a database. The input is encrypted transaction information, and the database uses standard cloud storage. The server classifies the information by category while ensuring data security using AES-256 encryption. In this process, the data is organized based on transaction type and date. The output is the database where the classified data is stored.

[0099] Step 3:

[0100] The server analyzes the stored data. It uses categorically organized data stored in a database as input. The server formats the data using the Pandas library and performs anomaly detection using the Scikit-learn machine learning algorithm. Specifically, it splits the data into a training set and a test set and performs pattern matching. The output is a model showing anomaly patterns and its results.

[0101] Step 4:

[0102] The terminal visually displays the analysis results. The input is the analysis results of abnormal patterns sent from the server. The terminal uses D3.js or Chart.js to represent this to the user in graph and chart format. Based on this visual information, the user can evaluate their trading activities. The output is a display of the analysis results in a format that is easy for the user to understand.

[0103] Step 5:

[0104] The device notifies the user of suggestions for saving money and making improvements. The input is the suggestions based on the analysis results. The device uses Firebase Cloud Messaging to send real-time push notifications to the user. In operation, the user is presented with specific suggestions (e.g., canceling a particular subscription or changing a utility plan). The output is specific suggestions to help the user make decisions.

[0105] Step 6:

[0106] The server runs simulations that take future life events into account. The inputs are the user's current asset situation and assumptions about life events. The server uses generative AI models such as Keras to generate predictive scenarios. Specifically, it predicts asset increases and decreases based on conditions set by the user and generates a long-term plan. This result is provided to the terminal as a future asset plan.

[0107] Step 7:

[0108] The user makes decisions based on the information and suggestions received through the device. Inputs are visualized analysis results and notified suggestions. The user evaluates the provided information and takes specific actions as needed (e.g., switching to a suggested plan or developing a new savings plan). Outputs are the user's optimized asset management activities.

[0109] (Application Example 1)

[0110] 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."

[0111] In modern society, personal and household financial management has become increasingly complex, and consumers are often plagued by unnecessary spending. Furthermore, there is a lack of clear guidance for creating long-term financial plans. Therefore, there is a need for a system that allows for efficient management of daily expenses, reduction of potential waste, and easy development of future-oriented plans.

[0112] 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.

[0113] In this invention, the server includes means for acquiring financial information, means for preprocessing the acquired financial information and organizing it by category, and means for detecting unnecessary spending based on the user's consumption habits and generating specific reduction suggestions. This makes it possible for users to efficiently manage their daily expenses, reduce waste, and more easily plan their future assets.

[0114] "Financial information" refers to data that shows a user's asset status and spending habits, such as bank account and credit card transaction history.

[0115] "Preprocessing" refers to classifying and processing acquired financial information and organizing it into an analyzable format.

[0116] "Classification" refers to organizing pre-processed financial information by its nature and purpose.

[0117] Anomaly detection is an analytical technique used to identify spending that deviates from normal patterns or standards.

[0118] "Consumer habits" refer to the tendencies and patterns of consumption behavior that individuals and households engage in on a daily basis.

[0119] A "reduction suggestion" is advice that analyzes a user's past spending patterns and provides specific measures to reduce unnecessary expenses.

[0120] "Visualization" is the process of making analysis results visible in the form of graphs, dashboards, and other formats, making them easy for users to understand.

[0121] A "simulation" is a method for virtually recreating future life events and financial situations in order to formulate plans and countermeasures.

[0122] To implement this invention, it is necessary to build a system in which a server, terminal, and user work together to efficiently acquire, analyze, and display financial information. The server acquires financial information through an API authorized by the user. The acquired information is encrypted and stored in a database, and then preprocessed. Next, the server uses a machine learning algorithm to detect abnormal patterns in the information. This makes unnecessary spending visible. The terminal presents the analysis results to the user in a visual format such as a dashboard or graph, and notifies them of savings suggestions.

[0123] The hardware utilizes a server that performs real-time data acquisition and analysis using AWS® Lambda. Amazon RDS is used to securely store financial information in the database. The user terminal is a smartphone application that runs on Android® or iOS. Python and the pandas library are used for data processing, and the scikit-learn Isolation Forest algorithm is used for anomaly detection. Analysis results are visualized using the Matplotlib library and displayed to the user.

[0124] As a concrete example, consider a scenario where a user uses the app at the end of the month to check "how much they saved this month." This application identifies unnecessary expenses for the user and provides specific reduction suggestions, such as "you should cancel your gym membership if you only use it twice a month." This allows the user to reduce necessary spending and improve their financial management.

[0125] An example of a prompt using a generative AI model would be, "Based on my living expenses over the past three months, please identify areas where I can save money next month and explain why." This prompt allows the AI ​​model to analyze the accumulated data and provide the user with personalized and useful information.

[0126] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0127] Step 1:

[0128] The server retrieves financial information through an API authorized by the user. This step involves inputting the user's bank account information and credit card transaction history, and the retrieved data is securely stored in an encrypted state. The data retrieval process uses OAuth 2.0 for authentication and receives data in JSON format.

[0129] Step 2:

[0130] The server preprocesses the acquired financial information. In this step, it receives the acquired financial information as input and organizes it by category using the pandas library. The output here is a data frame prepared for subsequent analysis. Preprocessing includes removing duplicate data and normalization.

[0131] Step 3:

[0132] The server uses a machine learning algorithm to detect anomalies. In this step, the preprocessed dataframe is taken as input, and scikit-learn's Isolation Forest is used to detect transactions with unusual patterns. The output is a list of transactions that were determined to be anomaly. In this process, the data is applied to a trained model to calculate an anomaly score.

[0133] Step 4:

[0134] The terminal visualizes and displays the analysis results to the user. In this step, the results of anomaly detection are used as input, and Matplotlib is used to generate user-friendly dashboards and graphs. The output is a visually organized report. The user can review this on their smartphone to understand their spending habits.

[0135] Step 5:

[0136] The server generates specific reduction suggestions based on the user's consumption habits. This step takes a list of anomaly detections and the user's past consumption data as input to identify expenditure items that can be reduced. The output is a notification of reduction suggestions. The generated suggestions may include, for example, "cancel infrequently used subscriptions."

[0137] Step 6:

[0138] The device notifies the user of the generated reduction suggestions. In this step, the reduction suggestions sent from the server are used as input and displayed to the user as push notifications or in-app messages. The output is suggestions that the user can explicitly see. The user then takes specific actions based on the suggestions.

[0139] Step 7:

[0140] The user can input prompts using a generative AI model and receive suggestions for further savings. In this step, the user's prompt is input, the AI ​​model performs data analysis based on it, and generates and outputs customized suggestions. A prompt such as, "Based on my living expenses over the past three months, please identify expenses I can save on next month and explain why," is used.

[0141] 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.

[0142] This invention describes a system that integrates financial data and emotional data to provide more personalized and emotional support for household financial management. This system combines the processing of financial information with the recognition of the user's emotions to provide personalized recommendations for each user.

[0143] Data acquisition and emotion recognition

[0144] The server continuously retrieves transaction data from the user's bank account and credit card APIs, encrypts it, and stores it. Simultaneously, the device runs an emotion engine that recognizes the user's emotions based on their facial expressions, voice tone, and input. This emotion data is instantly analyzed using edge computing and sent to the server.

[0145] Integrated analysis of data and emotions

[0146] The server organizes and analyzes the acquired financial data by category to detect unusual spending. In parallel with this, it checks the user's current emotional state based on emotional data. For example, if the user is feeling stressed, the system adjusts its processing to offer more cautious suggestions.

[0147] Proactive notifications and optimized suggestions

[0148] The device visualizes and presents analysis results to the user, including displays in graphs and dashboards. It also adapts the content and presentation of savings suggestions based on the user's emotional state. For example, if the user is in a positive mood, it can present more challenging savings goals.

[0149] The server generates multiple cost-saving scenarios and suggests the optimal option based on emotional data. If the emotional engine recognizes the user's worries or anxieties, suggestions are made in a more empathetic approach.

[0150] Simulation and customization

[0151] The server performs simulations based on future life events, but customizes how the results are presented according to the user's emotions. For example, if anxiety about the future is detected, the server will reassure the user by emphasizing the positive aspects of the simulation results.

[0152] Specific example

[0153] If a user is feeling stressed about managing their household finances, the device recognizes this emotion using its emotion engine, and the server, taking that data into consideration, suggests less burdensome ways to save money. Furthermore, the device displays this process visually in a user-friendly way, providing information in an easily acceptable format.

[0154] Thus, the present invention provides a specific embodiment for realizing household budget management support that is tailored to the user's psychological state by incorporating emotion recognition technology.

[0155] The following describes the processing flow.

[0156] Step 1:

[0157] Users register their financial institution account information with the system and set data retrieval permissions. Simultaneously, they configure privacy settings regarding the collection of emotional data.

[0158] Step 2:

[0159] The server retrieves transaction data from financial institutions based on user permission. The retrieved data is securely stored in a database in an encrypted form.

[0160] Step 3:

[0161] The device uses a facial recognition camera and microphone to collect emotional data from the user's facial expressions and voice. An emotion engine analyzes this data to recognize the user's emotional state in real time.

[0162] Step 4:

[0163] The server organizes the acquired financial data by category. Specifically, it classifies it into categories such as food expenses, transportation expenses, and utility expenses to understand spending trends.

[0164] Step 5:

[0165] The server compares organized data with past consumption patterns to detect unusual spending and economic trends. Machine learning algorithms are used for this anomaly detection.

[0166] Step 6:

[0167] The device visualizes the results of anomaly detection. It provides users with an easy-to-understand overview of their spending status through graphs and notification features on the dashboard.

[0168] Step 7:

[0169] The server generates personalized savings suggestions based on emotional data provided by the emotion engine. For example, if a user is feeling anxious, it will offer suggestions to reduce their burden.

[0170] Step 8:

[0171] The device notifies the user of the generated savings suggestions. Based on sentiment data, the suggestions are tailored to the user and presented in an easy-to-implement format.

[0172] Step 9:

[0173] The server performs simulations of future asset planning that take life events into account. It provides a positive perspective by adjusting how the results are displayed based on emotional data.

[0174] Step 10:

[0175] The device presents the simulation results in a way that makes them easy for the user to understand. This allows the user to make better decisions about their future financial planning.

[0176] (Example 2)

[0177] 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".

[0178] Traditional household financial management systems primarily offer fixed advice based on financial information, lacking personalized suggestions that take into account the user's emotions and psychological state. This can lead to users feeling stressed or dissatisfied with the suggestions. Furthermore, there was a need for systems that could respond flexibly to the user's emotional state and alleviate anxiety about future life events.

[0179] 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.

[0180] In this invention, the server includes means for acquiring, preprocessing, and classifying financial information; means for detecting anomalies and visualizing the results; and means for generating and notifying users of savings suggestions. This enables personalized suggestions that take into account the user's emotional information.

[0181] "Financial information" refers to transaction data related to a user's bank accounts, credit cards, and other economic activities.

[0182] "Classification" refers to the process of organizing acquired financial information based on predetermined categories.

[0183] "Anomaly detection" refers to analytical methods used to detect unnatural economic activity that deviates from normal trading patterns.

[0184] "Visualization" refers to techniques for displaying data and analysis results in a format that users can intuitively understand.

[0185] "User" refers to an individual who uses this system to manage their household finances.

[0186] "Emotional information" refers to data indicating the psychological and emotional state of the user, extracted based on their facial expressions, voice, and input data.

[0187] A "savings suggestion" refers to a plan to reduce spending or to use resources more efficiently, based on the user's financial situation and emotional information.

[0188] "Life events" refer to significant events that may affect the user's economic situation in the future, such as marriage, childbirth, entering higher education, or retirement.

[0189] "Personalized" refers to methods and suggestions that are individually tailored to take into account the unique circumstances and characteristics of each user.

[0190] This invention features a system that provides users with personalized household management by integrating financial information and emotional information. This system consists of a backend for managing financial transactions and a frontend engine that recognizes and analyzes the user's emotions.

[0191] Data acquisition and emotion recognition

[0192] The server retrieves transaction data from the user's bank account and credit card via APIs. This process uses the OAuth 2.0 protocol to ensure secure access. The retrieved financial information is securely stored using AES encryption. In parallel, the device collects user emotional information using its camera and microphone. OpenCV is used for image processing, and a speech recognition API is used for voice analysis. The emotional information obtained from the device is transmitted to the server via edge computing.

[0193] Data integration and proposal generation

[0194] The server uses Python to categorize financial information and apply anomaly detection algorithms. It utilizes the Pandas library to organize the information in a dataframe format. Furthermore, it analyzes emotional information to tailor suggestions based on the user's psychological state. For example, it prioritizes presenting low-burden savings options to users experiencing stress.

[0195] Visualization and Feedback

[0196] The device uses visualization libraries such as Matplotlib to display analysis results in graph and dashboard formats. During this process, the difficulty level and presentation of suggestions are adjusted according to the user's emotional state. If positive emotions are detected, challenging options can be presented to increase engagement.

[0197] Specific example

[0198] If a user requests a review of their household budget, the system proposes a concrete action plan based on the user's emotional state. The device analyzes emotions in real time, and the server generates the optimal saving strategy based on that information. By presenting the plan in a visually easy-to-understand format, users can more easily implement the suggestions. As a specific prompt, customized questions such as, "Create saving goals to propose when the user is showing positive emotions," are input into the generating AI model.

[0199] This system provides an implementation that supports effective household financial management while increasing user psychological satisfaction.

[0200] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0201] Step 1:

[0202] Input: Raw data obtained via financial APIs.

[0203] Operation: The server uses OAuth 2.0 to access the financial institution's API and securely retrieve the user's transaction data.

[0204] Data Processing / Calculation: The acquired data is converted into a DataFrame using the Pandas library and organized by category. Unnecessary data is removed at this stage.

[0205] Output: Financial information organized by category.

[0206] Step 2:

[0207] Input: User emotion data obtained from the camera and microphone.

[0208] Operation: The device captures the user's facial expressions and voice through the camera and microphone. OpenCV is used for facial recognition, and the Voice Assistant API is used for speech recognition.

[0209] Data processing / computation: The acquired information is processed in real time using edge computing, and data related to emotional states is extracted.

[0210] Output: User's current emotional state data.

[0211] Step 3:

[0212] Input: Organized financial information and emotional state data.

[0213] Operation: The server integrates this data and runs an anomaly detection algorithm. This algorithm identifies items that deviate from normal spending patterns.

[0214] Data processing / computation: Statistical methods are used for anomaly detection, and both financial data and sentiment information are evaluated.

[0215] Output: A list of unusual spending and its associated sentiment information.

[0216] Step 4:

[0217] Input: List of unusual spending, sentiment information, and other economic analysis information.

[0218] Operation: Based on this data, the server generates savings suggestions tailored to the user's psychological state.

[0219] Data Processing / Calculation: Use a generative AI model to create suggestions and customize them to take sentiment into account. Input is provided to the AI ​​through prompt sentences to obtain the optimal suggestion.

[0220] Output: Personalized savings suggestions and notification messages.

[0221] Step 5:

[0222] Input: Savings suggestions, data for visualization.

[0223] Operation: The terminal generates graphs and charts using visualization tools based on data received from the server.

[0224] Data processing / calculations: Visualization libraries such as Matplotlib are used to visualize data in an intuitively understandable format.

[0225] Output: Information presented to the user in the form of graphs or dashboards.

[0226] This process will provide users with personalized support for managing their household finances.

[0227] (Application Example 2)

[0228] 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".

[0229] In modern households, managing financial information has become increasingly complex, leading to greater stress in individual household budgeting. Therefore, there is a need for personalized and emotionally sensitive financial support that takes into account the user's psychological state. Conventional systems struggle to provide suggestions linked to emotional analysis, resulting in a failure to deliver optimal information to users.

[0230] 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.

[0231] In this invention, the server includes a mechanism for acquiring financial information, a mechanism for preprocessing the acquired financial information and organizing it by classification, and a mechanism for detecting anomalies using the classified information. This makes it possible to recognize the user's emotional state, generate personalized savings suggestions according to that state, and enable optimal household financial management with reduced stress.

[0232] "Financial information" refers to transaction data obtained from bank accounts and credit cards, and is used for household budget management.

[0233] "Preprocessing" refers to the process of organizing and classifying acquired data to prepare it for smooth subsequent anomaly detection and analysis.

[0234] "Classification" is a method of organizing financial information into different categories, making it easier to manage and analyze each category individually.

[0235] Anomaly detection is the process of identifying unusual transactions that deviate from normal spending patterns, based on organized data.

[0236] "Visualization" is the process of displaying data in the form of graphs and dashboards, allowing users to intuitively understand the information.

[0237] "User" refers to an individual who uses this system to manage their household finances.

[0238] An "emotion analysis mechanism" is a system that uses data acquired from cameras and microphones to recognize and determine the user's psychological state based on their facial expressions, voice tone, and other factors.

[0239] "Personalized savings suggestions" are suggestions that present individually optimized savings methods based on the user's financial situation and emotional state.

[0240] The system implementing this invention integrates financial information and sentiment analysis to provide users with personalized household financial management. The server encrypts transaction data obtained from financial institutions' APIs, processes it, and organizes it by category. This systematizes the financial information and streamlines the subsequent analysis process.

[0241] The emotion analysis mechanism uses cameras and microphones mounted on consumer robots and other devices to analyze the user's facial expressions and voice tone in real time. Utilizing edge computing technology, the analyzed emotion data is immediately transmitted to a server to understand the user's current psychological state.

[0242] The server integrates organized financial and emotional data, combining anomaly detection algorithms and emotion recognition to generate optimal savings suggestions for the user. These suggestions are visualized and communicated to the user via consumer robots. In particular, by adjusting the content and presentation of savings suggestions according to the user's emotional state, information can be shared without causing stress to the user.

[0243] For example, if data analysis reveals that the user is experiencing stress, the device will suggest less burdensome saving methods in a gentle tone. Conversely, if the device determines that the user is in a positive state, it can present more challenging saving goals.

[0244] An example of a prompt generated using a generative AI model is: "Please provide five fun money-saving ideas for this weekend. Please use positive language and explain them gently to boost motivation." Based on this prompt, attractive and practical suggestions are generated for the user.

[0245] In this way, a system that integrates sentiment analysis and financial data will provide accurate and effective household financial management support while staying close to the user's needs.

[0246] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0247] Step 1:

[0248] The server retrieves financial information via APIs from financial institutions. It receives user bank account and credit card information as input, encrypts it, and stores it in a database. As output, it generates raw transaction data for organization.

[0249] Step 2:

[0250] The server preprocesses the acquired financial information and organizes it by category. It uses raw transaction data as input and classifies the data into predefined categories within the program. This process results in organized data categorized by expenditure type as output.

[0251] Step 3:

[0252] The server performs anomaly detection using organized financial data. It receives categorized data as input and applies anomaly detection algorithms. It identifies abnormal trading patterns and generates the results as output.

[0253] Step 4:

[0254] The device uses an emotion analysis mechanism to acquire user emotion data. It utilizes visual and audio data obtained from the camera and microphone as input, and performs emotion analysis on edge computing resources. The results of this analysis are then sent to a server as output.

[0255] Step 5:

[0256] The server integrates financial and sentiment data to generate optimal savings suggestions. It uses anomaly detection results and sentiment analysis results as input. A generative AI model is used to create prompt messages, and the output is a savings scenario that takes sentiment into account.

[0257] Step 6:

[0258] The terminal visualizes the savings suggestions sent from the server and notifies the user. It receives generated savings scenarios as input and displays the information through graphs and icons in the user interface. The output is what the user uses to review the information and understand the suggestions.

[0259] 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.

[0260] 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.

[0261] 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.

[0262] [Second Embodiment]

[0263] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0264] 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.

[0265] 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).

[0266] 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.

[0267] 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.

[0268] 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).

[0269] 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.

[0270] 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.

[0271] 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.

[0272] 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.

[0273] 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.

[0274] 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".

[0275] To implement this invention, it is first necessary to build a system infrastructure capable of processing financial data. Specifically, it is required to securely acquire transaction information from users' bank accounts and credit cards and prepare the data so that it can be analyzed. This system operates in cooperation with users, servers, and terminals.

[0276] Data acquisition and management

[0277] The server retrieves bank account and credit card transaction data through APIs authorized by the user. This data is encrypted and securely stored in a database on the server.

[0278] Data Analysis and Notification

[0279] The server analyzes the accumulated data and organizes it by category. To detect abnormal expenditures and patterns from the data, machine learning algorithms are used. This algorithm generates a prediction model based on past data and performs anomaly detection.

[0280] The terminal displays the analysis results to the user in a visual form such as a dashboard or graph. It also notifies the user of savings proposals and warnings about abnormal expenditures.

[0281] Individual Savings Proposals and Asset Management

[0282] The server identifies cost savings that can be achieved based on the user's consumption patterns. For example, detecting unnecessary subscription services and suggesting cheaper public utility plans.

[0283] The terminal displays these savings proposals to the user, and the user can actually select those proposals to improve asset management.

[0284] Simulation and Long-Term Financial Planning

[0285] The server executes a simulation considering future life events and generates a long-term financial plan. This enables the user to predict their future asset situation and take necessary measures.

[0286] The terminal shows the results of the simulation to the user and provides information for adjusting the plan.

[0287] Specific Examples

[0288] In some households, if monthly electricity consumption exceeds acceptable limits, the server detects and analyzes the anomaly in real time. The terminal notifies the user of this information and suggests energy-saving measures, such as changing plans with a specific electricity provider. By considering these suggestions and taking action as needed, users can reduce their household expenses and achieve efficient asset management.

[0289] In this manner, the present invention provides embodiments for more efficient and dynamic household financial management in individual households.

[0290] The following describes the processing flow.

[0291] Step 1:

[0292] Users register their financial institution account information with the system and authorize the retrieval of their data.

[0293] Step 2:

[0294] The server retrieves transaction data in real time through financial institutions' APIs, based on information authorized by the user. The retrieved data is encrypted and stored in a secure database.

[0295] Step 3:

[0296] The server analyzes the stored data and organizes income and expenses by category. This uses defined categories such as food expenses, transportation expenses, and medical expenses. Data cleaning is also performed at this stage.

[0297] Step 4:

[0298] The server uses machine learning algorithms based on historical data to detect unusual spending patterns. This identifies abnormal spending that deviates from normal trends.

[0299] Step 5:

[0300] The terminal visualizes the results of anomaly detection and the overall household situation on a dashboard or the like and displays it to the user. Utilize graphs and pie charts to make the information easy to understand.

[0301] Step 6:

[0302] The server analyzes the user's consumption patterns and presents the expenses that can be saved. Generate specific savings proposals such as reviewing public charges and reducing the costs of flat-rate services.

[0303] Step 7:

[0304] The terminal notifies the user of these savings proposals and provides options for actually implementing the proposals. The user can check the notification and select a savings plan.

[0305] Step 8:

[0306] The server executes a simulation of a long-term funding plan based on future life events (e.g., savings for educational funds and retirement plans).

[0307] Step 9:

[0308] The terminal displays the results of the simulation to the user and supports the adjustment of the asset management plan as needed.

[0309] (Example 1)

[0310] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0311] In modern financial management, many users seek ways to efficiently understand their financial activities and reduce waste. However, because a large amount of transaction information is scattered across many different platforms, integrating and analyzing it safely and efficiently is difficult. Furthermore, obtaining the information necessary for long-term asset management and improving consumption patterns is a time-consuming and laborious task using current methods.

[0312] 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.

[0313] In this invention, the server includes means for acquiring user transaction information and securely managing the information, means for encrypting the acquired transaction information and storing it in a storage device, and means for processing the information stored in the storage device and classifying the data. This enables users to securely manage and analyze their financial information on a centralized interface, and to efficiently detect abnormal expenditures and reduce waste.

[0314] A "user" is an individual or legal entity that uses information or services related to financial transactions.

[0315] "Transaction information" refers to data obtained from financial activities such as bank accounts and credit cards, including specific transaction and deposit histories.

[0316] "Encryption" is the process of transforming data using a specific algorithm to prevent it from being misused by third parties.

[0317] A "storage device" is hardware or a medium used to temporarily or permanently store digital data.

[0318] A "machine learning algorithm" is a program that uses past data to recognize patterns and make predictions and classifications about future data.

[0319] "Visual display" refers to using visual formats such as graphs and charts to convey information to users in an easy-to-understand manner.

[0320] A "suggestion" is information that provides specific strategies for saving money and managing assets efficiently, based on the user's financial activities.

[0321] "Simulation" is the process of using a computer to predict the outcome of a real-world situation.

[0322] "Usage patterns" refer to a series of habits and tendencies derived from a user's transaction history and consumption behavior.

[0323] A "strategy" refers to the direction or measures provided to achieve a specific objective.

[0324] In order to implement this invention, it is first necessary to build a foundation for processing financial data. Specifically, a system is installed to securely acquire, store, and analyze user transaction information. The embodiments thereof are described in detail below.

[0325] Data acquisition and management

[0326] The server retrieves financial transaction data through APIs authorized by the user. The technology used includes authentication processes such as OAuth to establish a secure connection. The retrieved data is protected using encryption methods such as AES-256, and the database is stored using a common cloud storage service.

[0327] Data analysis and visualization

[0328] The server performs an ETL process on the acquired data. Specifically, it uses the Python Pandas library to analyze the data frame and organize the data into categories. Then, it uses machine learning libraries such as Scikit-learn and TensorFlow to perform anomaly detection. The analysis results are displayed on the user interface via the terminal. D3.js and Chart.js are used for visualization.

[0329] Proposals and notifications

[0330] The device displays data-driven savings suggestions and warnings based on detected anomalies to the user. This includes real-time communication via push notifications using Firebase Cloud Messaging. Users can then take action based on this information.

[0331] Long-term plan simulation

[0332] The server conducts simulations that take into account important future events and uses generative AI models such as Keras to develop long-term asset plans. This allows users to predict future economic conditions and create life plans based on that information. The results are displayed graphically, and users can adjust their plans accordingly.

[0333] As a concrete example, a user monitors their monthly electricity consumption, and an anomaly is detected if it exceeds a certain threshold. In this case, the server analyzes the anomaly in real time, and the terminal presents the user with specific suggestions for saving energy (for example, changing electricity plans), enabling the user to manage their assets efficiently.

[0334] An example of a prompt message is, "Please tell me how to analyze a user's monthly spending patterns and detect unusual spending."

[0335] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0336] Step 1:

[0337] The server retrieves transaction information through an API authorized by the user. The input requires user authentication credentials and API access permission. The server authenticates the user using the OAuth protocol and establishes a secure connection. It then sequentially downloads the transaction information via a RESTful API, encrypts this data, and stores it in temporary storage. The output is the encrypted transaction information.

[0338] Step 2:

[0339] The server stores the acquired transaction information in a database. The input is encrypted transaction information, and the database uses standard cloud storage. The server classifies the information by category while ensuring data security using AES-256 encryption. In this process, the data is organized based on transaction type and date. The output is the database where the classified data is stored.

[0340] Step 3:

[0341] The server analyzes the stored data. It uses categorically organized data stored in a database as input. The server formats the data using the Pandas library and performs anomaly detection using the Scikit-learn machine learning algorithm. Specifically, it splits the data into a training set and a test set and performs pattern matching. The output is a model showing anomaly patterns and its results.

[0342] Step 4:

[0343] The terminal visually displays the analysis results. The input is the analysis results of abnormal patterns sent from the server. The terminal uses D3.js or Chart.js to represent this to the user in graph and chart format. Based on this visual information, the user can evaluate their trading activities. The output is a display of the analysis results in a format that is easy for the user to understand.

[0344] Step 5:

[0345] The device notifies the user of suggestions for saving money and making improvements. The input is the suggestions based on the analysis results. The device uses Firebase Cloud Messaging to send real-time push notifications to the user. In operation, the user is presented with specific suggestions (e.g., canceling a particular subscription or changing a utility plan). The output is specific suggestions to help the user make decisions.

[0346] Step 6:

[0347] The server runs simulations that take future life events into account. The inputs are the user's current asset situation and assumptions about life events. The server uses generative AI models such as Keras to generate predictive scenarios. Specifically, it predicts asset increases and decreases based on conditions set by the user and generates a long-term plan. This result is provided to the terminal as a future asset plan.

[0348] Step 7:

[0349] The user makes decisions based on the information and suggestions received through the device. Inputs are visualized analysis results and notified suggestions. The user evaluates the provided information and takes specific actions as needed (e.g., switching to a suggested plan or developing a new savings plan). Outputs are the user's optimized asset management activities.

[0350] (Application Example 1)

[0351] 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."

[0352] In modern society, personal and household financial management has become increasingly complex, and consumers are often plagued by unnecessary spending. Furthermore, there is a lack of clear guidance for creating long-term financial plans. Therefore, there is a need for a system that allows for efficient management of daily expenses, reduction of potential waste, and easy development of future-oriented plans.

[0353] 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.

[0354] In this invention, the server includes means for acquiring financial information, means for preprocessing the acquired financial information and organizing it by category, and means for detecting unnecessary spending based on the user's consumption habits and generating specific reduction suggestions. This makes it possible for users to efficiently manage their daily expenses, reduce waste, and more easily plan their future assets.

[0355] "Financial information" refers to data that shows a user's asset status and spending habits, such as bank account and credit card transaction history.

[0356] "Preprocessing" refers to classifying and processing acquired financial information and organizing it into an analyzable format.

[0357] "Classification" refers to organizing pre-processed financial information by its nature and purpose.

[0358] Anomaly detection is an analytical technique used to identify spending that deviates from normal patterns or standards.

[0359] "Consumer habits" refer to the tendencies and patterns of consumption behavior that individuals and households engage in on a daily basis.

[0360] A "reduction suggestion" is advice that analyzes a user's past spending patterns and provides specific measures to reduce unnecessary expenses.

[0361] "Visualization" is the process of making analysis results visible in the form of graphs, dashboards, and other formats, making them easy for users to understand.

[0362] A "simulation" is a method for virtually recreating future life events and financial situations in order to formulate plans and countermeasures.

[0363] To implement this invention, it is necessary to build a system in which a server, terminal, and user work together to efficiently acquire, analyze, and display financial information. The server acquires financial information through an API authorized by the user. The acquired information is encrypted and stored in a database, and then preprocessed. Next, the server uses a machine learning algorithm to detect abnormal patterns in the information. This makes unnecessary spending visible. The terminal presents the analysis results to the user in a visual format such as a dashboard or graph, and notifies them of savings suggestions.

[0364] The hardware utilizes a server that performs real-time data acquisition and analysis using AWS Lambda. Amazon RDS is used to securely store financial information in the database. The user terminal is a smartphone application running on Android or iOS. Python and the pandas library are used for data processing, and the scikit-learn Isolation Forest algorithm is used for anomaly detection. The analysis results are visualized using the Matplotlib library and displayed to the user.

[0365] As a concrete example, consider a scenario where a user uses the app at the end of the month to check "how much they saved this month." This application identifies unnecessary expenses for the user and provides specific reduction suggestions, such as "you should cancel your gym membership if you only use it twice a month." This allows the user to reduce necessary spending and improve their financial management.

[0366] An example of a prompt using a generative AI model would be, "Based on my living expenses over the past three months, please identify areas where I can save money next month and explain why." This prompt allows the AI ​​model to analyze the accumulated data and provide the user with personalized and useful information.

[0367] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0368] Step 1:

[0369] The server retrieves financial information through an API authorized by the user. This step involves inputting the user's bank account information and credit card transaction history, and the retrieved data is securely stored in an encrypted state. The data retrieval process uses OAuth 2.0 for authentication and receives data in JSON format.

[0370] Step 2:

[0371] The server preprocesses the acquired financial information. In this step, it receives the acquired financial information as input and organizes it by category using the pandas library. The output here is a data frame prepared for subsequent analysis. Preprocessing includes removing duplicate data and normalization.

[0372] Step 3:

[0373] The server uses a machine learning algorithm to detect anomalies. In this step, the preprocessed dataframe is taken as input, and scikit-learn's Isolation Forest is used to detect transactions with unusual patterns. The output is a list of transactions that were determined to be anomaly. In this process, the data is applied to a trained model to calculate an anomaly score.

[0374] Step 4:

[0375] The terminal visualizes and displays the analysis results to the user. In this step, the results of anomaly detection are used as input, and Matplotlib is used to generate user-friendly dashboards and graphs. The output is a visually organized report. The user can review this on their smartphone to understand their spending habits.

[0376] Step 5:

[0377] The server generates specific reduction suggestions based on the user's consumption habits. This step takes a list of anomaly detections and the user's past consumption data as input to identify expenditure items that can be reduced. The output is a notification of reduction suggestions. The generated suggestions may include, for example, "cancel infrequently used subscriptions."

[0378] Step 6:

[0379] The device notifies the user of the generated reduction suggestions. In this step, the reduction suggestions sent from the server are used as input and displayed to the user as push notifications or in-app messages. The output is suggestions that the user can explicitly see. The user then takes specific actions based on the suggestions.

[0380] Step 7:

[0381] The user can input prompts using a generative AI model and receive suggestions for further savings. In this step, the user's prompt is input, the AI ​​model performs data analysis based on it, and generates and outputs customized suggestions. A prompt such as, "Based on my living expenses over the past three months, please identify expenses I can save on next month and explain why," is used.

[0382] 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.

[0383] This invention describes a system that integrates financial data and emotional data to provide more personalized and emotional support for household financial management. This system combines the processing of financial information with the recognition of the user's emotions to provide personalized recommendations for each user.

[0384] Data acquisition and emotion recognition

[0385] The server continuously retrieves transaction data from the user's bank account and credit card APIs, encrypts it, and stores it. Simultaneously, the device runs an emotion engine that recognizes the user's emotions based on their facial expressions, voice tone, and input. This emotion data is instantly analyzed using edge computing and sent to the server.

[0386] Integrated analysis of data and emotions

[0387] The server organizes and analyzes the acquired financial data by category to detect unusual spending. In parallel with this, it checks the user's current emotional state based on emotional data. For example, if the user is feeling stressed, the system adjusts its processing to offer more cautious suggestions.

[0388] Proactive notifications and optimized suggestions

[0389] The device visualizes and presents analysis results to the user, including displays in graphs and dashboards. It also adapts the content and presentation of savings suggestions based on the user's emotional state. For example, if the user is in a positive mood, it can present more challenging savings goals.

[0390] The server generates multiple cost-saving scenarios and suggests the optimal option based on emotional data. If the emotional engine recognizes the user's worries or anxieties, suggestions are made in a more empathetic approach.

[0391] Simulation and customization

[0392] The server performs simulations based on future life events, but customizes how the results are presented according to the user's emotions. For example, if anxiety about the future is detected, the server will reassure the user by emphasizing the positive aspects of the simulation results.

[0393] Specific example

[0394] If a user is feeling stressed about managing their household finances, the device recognizes this emotion using its emotion engine, and the server, taking that data into consideration, suggests less burdensome ways to save money. Furthermore, the device displays this process visually in a user-friendly way, providing information in an easily acceptable format.

[0395] Thus, the present invention provides a specific embodiment for realizing household budget management support that is tailored to the user's psychological state by incorporating emotion recognition technology.

[0396] The following describes the processing flow.

[0397] Step 1:

[0398] Users register their financial institution account information with the system and set data retrieval permissions. Simultaneously, they configure privacy settings regarding the collection of emotional data.

[0399] Step 2:

[0400] The server retrieves transaction data from financial institutions based on user permission. The retrieved data is securely stored in a database in an encrypted form.

[0401] Step 3:

[0402] The device uses a facial recognition camera and microphone to collect emotional data from the user's facial expressions and voice. An emotion engine analyzes this data to recognize the user's emotional state in real time.

[0403] Step 4:

[0404] The server organizes the acquired financial data by category. Specifically, it classifies it into categories such as food expenses, transportation expenses, and utility expenses to understand spending trends.

[0405] Step 5:

[0406] The server compares organized data with past consumption patterns to detect unusual spending and economic trends. Machine learning algorithms are used for this anomaly detection.

[0407] Step 6:

[0408] The device visualizes the results of anomaly detection. It provides users with an easy-to-understand overview of their spending status through graphs and notification features on the dashboard.

[0409] Step 7:

[0410] The server generates personalized savings suggestions based on emotional data provided by the emotion engine. For example, if a user is feeling anxious, it will offer suggestions to reduce their burden.

[0411] Step 8:

[0412] The device notifies the user of the generated savings suggestions. Based on sentiment data, the suggestions are tailored to the user and presented in an easy-to-implement format.

[0413] Step 9:

[0414] The server performs simulations of future asset planning that take life events into account. It provides a positive perspective by adjusting how the results are displayed based on emotional data.

[0415] Step 10:

[0416] The device presents the simulation results in a way that makes them easy for the user to understand. This allows the user to make better decisions about their future financial planning.

[0417] (Example 2)

[0418] 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".

[0419] Traditional household financial management systems primarily offer fixed advice based on financial information, lacking personalized suggestions that take into account the user's emotions and psychological state. This can lead to users feeling stressed or dissatisfied with the suggestions. Furthermore, there was a need for systems that could respond flexibly to the user's emotional state and alleviate anxiety about future life events.

[0420] 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.

[0421] In this invention, the server includes means for acquiring, preprocessing, and classifying financial information; means for detecting anomalies and visualizing the results; and means for generating and notifying users of savings suggestions. This enables personalized suggestions that take into account the user's emotional information.

[0422] "Financial information" refers to transaction data related to a user's bank accounts, credit cards, and other economic activities.

[0423] "Classification" refers to the process of organizing acquired financial information based on predetermined categories.

[0424] "Anomaly detection" refers to analytical methods used to detect unnatural economic activity that deviates from normal trading patterns.

[0425] "Visualization" refers to techniques for displaying data and analysis results in a format that users can intuitively understand.

[0426] "User" refers to an individual who uses this system to manage their household finances.

[0427] "Emotional information" refers to data indicating the psychological and emotional state of the user, extracted based on their facial expressions, voice, and input data.

[0428] A "savings suggestion" refers to a plan to reduce spending or to use resources more efficiently, based on the user's financial situation and emotional information.

[0429] "Life events" refer to significant events that may affect the user's economic situation in the future, such as marriage, childbirth, entering higher education, or retirement.

[0430] "Personalized" refers to methods and suggestions that are individually tailored to take into account the unique circumstances and characteristics of each user.

[0431] This invention features a system that provides users with personalized household management by integrating financial information and emotional information. This system consists of a backend for managing financial transactions and a frontend engine that recognizes and analyzes the user's emotions.

[0432] Data acquisition and emotion recognition

[0433] The server retrieves transaction data from the user's bank account and credit card via APIs. This process uses the OAuth 2.0 protocol to ensure secure access. The retrieved financial information is securely stored using AES encryption. In parallel, the device collects user emotional information using its camera and microphone. OpenCV is used for image processing, and a speech recognition API is used for voice analysis. The emotional information obtained from the device is transmitted to the server via edge computing.

[0434] Data integration and proposal generation

[0435] The server uses Python to categorize financial information and apply anomaly detection algorithms. It utilizes the Pandas library to organize the information in a dataframe format. Furthermore, it analyzes emotional information to tailor suggestions based on the user's psychological state. For example, it prioritizes presenting low-burden savings options to users experiencing stress.

[0436] Visualization and Feedback

[0437] The device uses visualization libraries such as Matplotlib to display analysis results in graph and dashboard formats. During this process, the difficulty level and presentation of suggestions are adjusted according to the user's emotional state. If positive emotions are detected, challenging options can be presented to increase engagement.

[0438] Specific example

[0439] If a user requests a review of their household budget, the system proposes a concrete action plan based on the user's emotional state. The device analyzes emotions in real time, and the server generates the optimal saving strategy based on that information. By presenting the plan in a visually easy-to-understand format, users can more easily implement the suggestions. As a specific prompt, customized questions such as, "Create saving goals to propose when the user is showing positive emotions," are input into the generating AI model.

[0440] This system provides an implementation that supports effective household financial management while increasing user psychological satisfaction.

[0441] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0442] Step 1:

[0443] Input: Raw data obtained via financial APIs.

[0444] Operation: The server uses OAuth 2.0 to access the financial institution's API and securely retrieve the user's transaction data.

[0445] Data Processing / Calculation: The acquired data is converted into a DataFrame using the Pandas library and organized by category. Unnecessary data is removed at this stage.

[0446] Output: Financial information organized by category.

[0447] Step 2:

[0448] Input: User emotion data obtained from the camera and microphone.

[0449] Operation: The device captures the user's facial expressions and voice through the camera and microphone. OpenCV is used for facial recognition, and the Voice Assistant API is used for speech recognition.

[0450] Data processing / computation: The acquired information is processed in real time using edge computing, and data related to emotional states is extracted.

[0451] Output: User's current emotional state data.

[0452] Step 3:

[0453] Input: Organized financial information and emotional state data.

[0454] Operation: The server integrates this data and runs an anomaly detection algorithm. This algorithm identifies items that deviate from normal spending patterns.

[0455] Data processing / computation: Statistical methods are used for anomaly detection, and both financial data and sentiment information are evaluated.

[0456] Output: A list of unusual spending and its associated sentiment information.

[0457] Step 4:

[0458] Input: List of unusual spending, sentiment information, and other economic analysis information.

[0459] Operation: Based on this data, the server generates savings suggestions tailored to the user's psychological state.

[0460] Data Processing / Calculation: Use a generative AI model to create suggestions and customize them to take sentiment into account. Input is provided to the AI ​​through prompt sentences to obtain the optimal suggestion.

[0461] Output: Personalized savings suggestions and notification messages.

[0462] Step 5:

[0463] Input: Savings suggestions, data for visualization.

[0464] Operation: The terminal generates graphs and charts using visualization tools based on data received from the server.

[0465] Data processing / calculations: Visualization libraries such as Matplotlib are used to visualize data in an intuitively understandable format.

[0466] Output: Information presented to the user in the form of graphs or dashboards.

[0467] This process will provide users with personalized support for managing their household finances.

[0468] (Application Example 2)

[0469] 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."

[0470] In modern households, managing financial information has become increasingly complex, leading to greater stress in individual household budgeting. Therefore, there is a need for personalized and emotionally sensitive financial support that takes into account the user's psychological state. Conventional systems struggle to provide suggestions linked to emotional analysis, resulting in a failure to deliver optimal information to users.

[0471] 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.

[0472] In this invention, the server includes a mechanism for acquiring financial information, a mechanism for preprocessing the acquired financial information and organizing it by classification, and a mechanism for detecting anomalies using the classified information. This makes it possible to recognize the user's emotional state, generate personalized savings suggestions according to that state, and enable optimal household financial management with reduced stress.

[0473] "Financial information" refers to transaction data obtained from bank accounts and credit cards, and is used for household budget management.

[0474] "Preprocessing" refers to the process of organizing and classifying acquired data to prepare it for smooth subsequent anomaly detection and analysis.

[0475] "Classification" is a method of organizing financial information into different categories, making it easier to manage and analyze each category individually.

[0476] Anomaly detection is the process of identifying unusual transactions that deviate from normal spending patterns, based on organized data.

[0477] "Visualization" is the process of displaying data in the form of graphs and dashboards, allowing users to intuitively understand the information.

[0478] "User" refers to an individual who uses this system to manage their household finances.

[0479] An "emotion analysis mechanism" is a system that uses data acquired from cameras and microphones to recognize and determine the user's psychological state based on their facial expressions, voice tone, and other factors.

[0480] "Personalized savings suggestions" are suggestions that present individually optimized savings methods based on the user's financial situation and emotional state.

[0481] The system implementing this invention integrates financial information and sentiment analysis to provide users with personalized household financial management. The server encrypts transaction data obtained from financial institutions' APIs, processes it, and organizes it by category. This systematizes the financial information and streamlines the subsequent analysis process.

[0482] The emotion analysis mechanism uses cameras and microphones mounted on consumer robots and other devices to analyze the user's facial expressions and voice tone in real time. Utilizing edge computing technology, the analyzed emotion data is immediately transmitted to a server to understand the user's current psychological state.

[0483] The server integrates organized financial and emotional data, combining anomaly detection algorithms and emotion recognition to generate optimal savings suggestions for the user. These suggestions are visualized and communicated to the user via consumer robots. In particular, by adjusting the content and presentation of savings suggestions according to the user's emotional state, information can be shared without causing stress to the user.

[0484] For example, if data analysis reveals that the user is experiencing stress, the device will suggest less burdensome saving methods in a gentle tone. Conversely, if the device determines that the user is in a positive state, it can present more challenging saving goals.

[0485] An example of a prompt generated using a generative AI model is: "Please provide five fun money-saving ideas for this weekend. Please use positive language and explain them gently to boost motivation." Based on this prompt, attractive and practical suggestions are generated for the user.

[0486] In this way, a system that integrates sentiment analysis and financial data will provide accurate and effective household financial management support while staying close to the user's needs.

[0487] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0488] Step 1:

[0489] The server retrieves financial information via APIs from financial institutions. It receives user bank account and credit card information as input, encrypts it, and stores it in a database. As output, it generates raw transaction data for organization.

[0490] Step 2:

[0491] The server preprocesses the acquired financial information and organizes it by category. It uses raw transaction data as input and classifies the data into predefined categories within the program. This process results in organized data categorized by expenditure type as output.

[0492] Step 3:

[0493] The server performs anomaly detection using organized financial data. It receives categorized data as input and applies anomaly detection algorithms. It identifies abnormal trading patterns and generates the results as output.

[0494] Step 4:

[0495] The device uses an emotion analysis mechanism to acquire user emotion data. It utilizes visual and audio data obtained from the camera and microphone as input, and performs emotion analysis on edge computing resources. The results of this analysis are then sent to a server as output.

[0496] Step 5:

[0497] The server integrates financial and sentiment data to generate optimal savings suggestions. It uses anomaly detection results and sentiment analysis results as input. A generative AI model is used to create prompt messages, and the output is a savings scenario that takes sentiment into account.

[0498] Step 6:

[0499] The terminal visualizes the savings suggestions sent from the server and notifies the user. It receives generated savings scenarios as input and displays the information through graphs and icons in the user interface. The output is what the user uses to review the information and understand the suggestions.

[0500] 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.

[0501] 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.

[0502] 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.

[0503] [Third Embodiment]

[0504] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0505] 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.

[0506] 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).

[0507] 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.

[0508] 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.

[0509] 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).

[0510] 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.

[0511] 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.

[0512] 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.

[0513] 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.

[0514] 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.

[0515] 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".

[0516] To implement this invention, it is first necessary to build a system infrastructure capable of processing financial data. Specifically, it is required to securely acquire transaction information from users' bank accounts and credit cards and prepare the data so that it can be analyzed. This system operates in cooperation with users, servers, and terminals.

[0517] Data acquisition and management

[0518] The server retrieves bank account and credit card transaction data through APIs authorized by the user. This data is encrypted and securely stored in a database on the server.

[0519] Data analysis and notification

[0520] The server analyzes the accumulated data and organizes it by category. Machine learning algorithms are used to detect unusual spending patterns and other abnormalities from the data. These algorithms generate predictive models based on historical data to perform anomaly detection.

[0521] The device displays analysis results to the user in visual formats such as dashboards and graphs. It also notifies the user with savings suggestions and warnings about unusual spending.

[0522] Personalized savings proposals and asset management

[0523] The server identifies potential cost savings based on the user's consumption patterns. For example, it might detect unnecessary subscription services or suggest cheaper utility plans.

[0524] The device displays these savings suggestions to the user, who can then select them to improve their asset management.

[0525] Simulation and long-term financial planning

[0526] The server runs simulations that take future life events into account and generates long-term financial plans. This allows users to predict their future financial situation and take necessary measures.

[0527] The terminal displays the simulation results to the user and provides information to adjust the plan.

[0528] Specific example

[0529] In some households, if monthly electricity consumption exceeds acceptable limits, the server detects and analyzes the anomaly in real time. The terminal notifies the user of this information and suggests energy-saving measures, such as changing plans with a specific electricity provider. By considering these suggestions and taking action as needed, users can reduce their household expenses and achieve efficient asset management.

[0530] In this manner, the present invention provides embodiments for more efficient and dynamic household financial management in individual households.

[0531] The following describes the processing flow.

[0532] Step 1:

[0533] Users register their financial institution account information with the system and authorize the retrieval of their data.

[0534] Step 2:

[0535] The server retrieves transaction data in real time through financial institutions' APIs, based on information authorized by the user. The retrieved data is encrypted and stored in a secure database.

[0536] Step 3:

[0537] The server analyzes the stored data and organizes income and expenses by category. This uses defined categories such as food expenses, transportation expenses, and medical expenses. Data cleaning is also performed at this stage.

[0538] Step 4:

[0539] The server uses machine learning algorithms based on historical data to detect unusual spending patterns. This identifies abnormal spending that deviates from normal trends.

[0540] Step 5:

[0541] The terminal visualizes the results of anomaly detection and the overall household financial situation on a dashboard and displays it to the user. Graphs and pie charts are used to make the information easy to understand.

[0542] Step 6:

[0543] The server analyzes the user's consumption patterns and suggests areas where expenses can be reduced. It generates specific savings suggestions, such as reviewing utility bills or cutting costs on subscription services.

[0544] Step 7:

[0545] The device notifies the user of these savings suggestions and provides options for actually implementing them. The user can review the notification and select a savings plan.

[0546] Step 8:

[0547] The server runs a simulation of long-term financial planning based on future life events (e.g., saving for education or retirement planning).

[0548] Step 9:

[0549] The terminal displays the simulation results to the user and supports them in adjusting their asset management plan as needed.

[0550] (Example 1)

[0551] 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."

[0552] In modern financial management, many users seek ways to efficiently understand their financial activities and reduce waste. However, because a large amount of transaction information is scattered across many different platforms, integrating and analyzing it safely and efficiently is difficult. Furthermore, obtaining the information necessary for long-term asset management and improving consumption patterns is a time-consuming and laborious task using current methods.

[0553] 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.

[0554] In this invention, the server includes means for acquiring user transaction information and securely managing the information, means for encrypting the acquired transaction information and storing it in a storage device, and means for processing the information stored in the storage device and classifying the data. This enables users to securely manage and analyze their financial information on a centralized interface, and to efficiently detect abnormal expenditures and reduce waste.

[0555] A "user" is an individual or legal entity that uses information or services related to financial transactions.

[0556] "Transaction information" refers to data obtained from financial activities such as bank accounts and credit cards, including specific transaction and deposit histories.

[0557] "Encryption" is the process of transforming data using a specific algorithm to prevent it from being misused by third parties.

[0558] A "storage device" is hardware or a medium used to temporarily or permanently store digital data.

[0559] A "machine learning algorithm" is a program that uses past data to recognize patterns and make predictions and classifications about future data.

[0560] "Visual display" refers to using visual formats such as graphs and charts to convey information to users in an easy-to-understand manner.

[0561] A "suggestion" is information that provides specific strategies for saving money and managing assets efficiently, based on the user's financial activities.

[0562] "Simulation" is the process of using a computer to predict the outcome of a real-world situation.

[0563] "Usage patterns" refer to a series of habits and tendencies derived from a user's transaction history and consumption behavior.

[0564] A "strategy" refers to the direction or measures provided to achieve a specific objective.

[0565] In order to implement this invention, it is first necessary to build a foundation for processing financial data. Specifically, a system is installed to securely acquire, store, and analyze user transaction information. The embodiments thereof are described in detail below.

[0566] Data acquisition and management

[0567] The server retrieves financial transaction data through APIs authorized by the user. The technology used includes authentication processes such as OAuth to establish a secure connection. The retrieved data is protected using encryption methods such as AES-256, and the database is stored using a common cloud storage service.

[0568] Data analysis and visualization

[0569] The server performs an ETL process on the acquired data. Specifically, it uses the Python Pandas library to analyze the data frame and organize the data into categories. Then, it uses machine learning libraries such as Scikit-learn and TensorFlow to perform anomaly detection. The analysis results are displayed on the user interface via the terminal. D3.js and Chart.js are used for visualization.

[0570] Proposals and notifications

[0571] The device displays data-driven savings suggestions and warnings based on detected anomalies to the user. This includes real-time communication via push notifications using Firebase Cloud Messaging. Users can then take action based on this information.

[0572] Long-term plan simulation

[0573] The server conducts simulations that take into account important future events and uses generative AI models such as Keras to develop long-term asset plans. This allows users to predict future economic conditions and create life plans based on that information. The results are displayed graphically, and users can adjust their plans accordingly.

[0574] As a concrete example, a user monitors their monthly electricity consumption, and an anomaly is detected if it exceeds a certain threshold. In this case, the server analyzes the anomaly in real time, and the terminal presents the user with specific suggestions for saving energy (for example, changing electricity plans), enabling the user to manage their assets efficiently.

[0575] An example of a prompt message is, "Please tell me how to analyze a user's monthly spending patterns and detect unusual spending."

[0576] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0577] Step 1:

[0578] The server retrieves transaction information through an API authorized by the user. The input requires user authentication credentials and API access permission. The server authenticates the user using the OAuth protocol and establishes a secure connection. It then sequentially downloads the transaction information via a RESTful API, encrypts this data, and stores it in temporary storage. The output is the encrypted transaction information.

[0579] Step 2:

[0580] The server stores the acquired transaction information in a database. The input is encrypted transaction information, and the database uses standard cloud storage. The server classifies the information by category while ensuring data security using AES-256 encryption. In this process, the data is organized based on transaction type and date. The output is the database where the classified data is stored.

[0581] Step 3:

[0582] The server analyzes the stored data. It uses categorically organized data stored in a database as input. The server formats the data using the Pandas library and performs anomaly detection using the Scikit-learn machine learning algorithm. Specifically, it splits the data into a training set and a test set and performs pattern matching. The output is a model showing anomaly patterns and its results.

[0583] Step 4:

[0584] The terminal visually displays the analysis results. The input is the analysis results of abnormal patterns sent from the server. The terminal uses D3.js or Chart.js to represent this to the user in graph and chart format. Based on this visual information, the user can evaluate their trading activities. The output is a display of the analysis results in a format that is easy for the user to understand.

[0585] Step 5:

[0586] The device notifies the user of suggestions for saving money and making improvements. The input is the suggestions based on the analysis results. The device uses Firebase Cloud Messaging to send real-time push notifications to the user. In operation, the user is presented with specific suggestions (e.g., canceling a particular subscription or changing a utility plan). The output is specific suggestions to help the user make decisions.

[0587] Step 6:

[0588] The server runs simulations that take future life events into account. The inputs are the user's current asset situation and assumptions about life events. The server uses generative AI models such as Keras to generate predictive scenarios. Specifically, it predicts asset increases and decreases based on conditions set by the user and generates a long-term plan. This result is provided to the terminal as a future asset plan.

[0589] Step 7:

[0590] The user makes decisions based on the information and suggestions received through the device. Inputs are visualized analysis results and notified suggestions. The user evaluates the provided information and takes specific actions as needed (e.g., switching to a suggested plan or developing a new savings plan). Outputs are the user's optimized asset management activities.

[0591] (Application Example 1)

[0592] 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."

[0593] In modern society, personal and household financial management has become increasingly complex, and consumers are often plagued by unnecessary spending. Furthermore, there is a lack of clear guidance for creating long-term financial plans. Therefore, there is a need for a system that allows for efficient management of daily expenses, reduction of potential waste, and easy development of future-oriented plans.

[0594] 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.

[0595] In this invention, the server includes means for acquiring financial information, means for preprocessing the acquired financial information and organizing it by category, and means for detecting unnecessary spending based on the user's consumption habits and generating specific reduction suggestions. This makes it possible for users to efficiently manage their daily expenses, reduce waste, and more easily plan their future assets.

[0596] "Financial information" refers to data that shows a user's asset status and spending habits, such as bank account and credit card transaction history.

[0597] "Preprocessing" refers to classifying and processing acquired financial information and organizing it into an analyzable format.

[0598] "Classification" refers to organizing pre-processed financial information by its nature and purpose.

[0599] Anomaly detection is an analytical technique used to identify spending that deviates from normal patterns or standards.

[0600] "Consumer habits" refer to the tendencies and patterns of consumption behavior that individuals and households engage in on a daily basis.

[0601] A "reduction suggestion" is advice that analyzes a user's past spending patterns and provides specific measures to reduce unnecessary expenses.

[0602] "Visualization" is the process of making analysis results visible in the form of graphs, dashboards, and other formats, making them easy for users to understand.

[0603] A "simulation" is a method for virtually recreating future life events and financial situations in order to formulate plans and countermeasures.

[0604] To implement this invention, it is necessary to build a system in which a server, terminal, and user work together to efficiently acquire, analyze, and display financial information. The server acquires financial information through an API authorized by the user. The acquired information is encrypted and stored in a database, and then preprocessed. Next, the server uses a machine learning algorithm to detect abnormal patterns in the information. This makes unnecessary spending visible. The terminal presents the analysis results to the user in a visual format such as a dashboard or graph, and notifies them of savings suggestions.

[0605] The hardware utilizes a server that performs real-time data acquisition and analysis using AWS Lambda. Amazon RDS is used to securely store financial information in the database. The user terminal is a smartphone application running on Android or iOS. Python and the pandas library are used for data processing, and the scikit-learn Isolation Forest algorithm is used for anomaly detection. The analysis results are visualized using the Matplotlib library and displayed to the user.

[0606] As a concrete example, consider a scenario where a user uses the app at the end of the month to check "how much they saved this month." This application identifies unnecessary expenses for the user and provides specific reduction suggestions, such as "you should cancel your gym membership if you only use it twice a month." This allows the user to reduce necessary spending and improve their financial management.

[0607] An example of a prompt using a generative AI model would be, "Based on my living expenses over the past three months, please identify areas where I can save money next month and explain why." This prompt allows the AI ​​model to analyze the accumulated data and provide the user with personalized and useful information.

[0608] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0609] Step 1:

[0610] The server retrieves financial information through an API authorized by the user. This step involves inputting the user's bank account information and credit card transaction history, and the retrieved data is securely stored in an encrypted state. The data retrieval process uses OAuth 2.0 for authentication and receives data in JSON format.

[0611] Step 2:

[0612] The server preprocesses the acquired financial information. In this step, it receives the acquired financial information as input and organizes it by category using the pandas library. The output here is a data frame prepared for subsequent analysis. Preprocessing includes removing duplicate data and normalization.

[0613] Step 3:

[0614] The server uses a machine learning algorithm to detect anomalies. In this step, the preprocessed dataframe is taken as input, and scikit-learn's Isolation Forest is used to detect transactions with unusual patterns. The output is a list of transactions that were determined to be anomaly. In this process, the data is applied to a trained model to calculate an anomaly score.

[0615] Step 4:

[0616] The terminal visualizes and displays the analysis results to the user. In this step, the results of anomaly detection are used as input, and Matplotlib is used to generate user-friendly dashboards and graphs. The output is a visually organized report. The user can review this on their smartphone to understand their spending habits.

[0617] Step 5:

[0618] The server generates specific reduction suggestions based on the user's consumption habits. This step takes a list of anomaly detections and the user's past consumption data as input to identify expenditure items that can be reduced. The output is a notification of reduction suggestions. The generated suggestions may include, for example, "cancel infrequently used subscriptions."

[0619] Step 6:

[0620] The device notifies the user of the generated reduction suggestions. In this step, the reduction suggestions sent from the server are used as input and displayed to the user as push notifications or in-app messages. The output is suggestions that the user can explicitly see. The user then takes specific actions based on the suggestions.

[0621] Step 7:

[0622] The user can input prompts using a generative AI model and receive suggestions for further savings. In this step, the user's prompt is input, the AI ​​model performs data analysis based on it, and generates and outputs customized suggestions. A prompt such as, "Based on my living expenses over the past three months, please identify expenses I can save on next month and explain why," is used.

[0623] 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.

[0624] This invention describes a system that integrates financial data and emotional data to provide more personalized and emotional support for household financial management. This system combines the processing of financial information with the recognition of the user's emotions to provide personalized recommendations for each user.

[0625] Data acquisition and emotion recognition

[0626] The server continuously retrieves transaction data from the user's bank account and credit card APIs, encrypts it, and stores it. Simultaneously, the device runs an emotion engine that recognizes the user's emotions based on their facial expressions, voice tone, and input. This emotion data is instantly analyzed using edge computing and sent to the server.

[0627] Integrated analysis of data and emotions

[0628] The server organizes and analyzes the acquired financial data by category to detect unusual spending. In parallel with this, it checks the user's current emotional state based on emotional data. For example, if the user is feeling stressed, the system adjusts its processing to offer more cautious suggestions.

[0629] Proactive notifications and optimized suggestions

[0630] The device visualizes and presents analysis results to the user, including displays in graphs and dashboards. It also adapts the content and presentation of savings suggestions based on the user's emotional state. For example, if the user is in a positive mood, it can present more challenging savings goals.

[0631] The server generates multiple cost-saving scenarios and suggests the optimal option based on emotional data. If the emotional engine recognizes the user's worries or anxieties, suggestions are made in a more empathetic approach.

[0632] Simulation and customization

[0633] The server performs simulations based on future life events, but customizes how the results are presented according to the user's emotions. For example, if anxiety about the future is detected, the server will reassure the user by emphasizing the positive aspects of the simulation results.

[0634] Specific example

[0635] If a user is feeling stressed about managing their household finances, the device recognizes this emotion using its emotion engine, and the server, taking that data into consideration, suggests less burdensome ways to save money. Furthermore, the device displays this process visually in a user-friendly way, providing information in an easily acceptable format.

[0636] Thus, the present invention provides a specific embodiment for realizing household budget management support that is tailored to the user's psychological state by incorporating emotion recognition technology.

[0637] The following describes the processing flow.

[0638] Step 1:

[0639] Users register their financial institution account information with the system and set data retrieval permissions. Simultaneously, they configure privacy settings regarding the collection of emotional data.

[0640] Step 2:

[0641] The server retrieves transaction data from financial institutions based on user permission. The retrieved data is securely stored in a database in an encrypted form.

[0642] Step 3:

[0643] The device uses a facial recognition camera and microphone to collect emotional data from the user's facial expressions and voice. An emotion engine analyzes this data to recognize the user's emotional state in real time.

[0644] Step 4:

[0645] The server organizes the acquired financial data by category. Specifically, it classifies it into categories such as food expenses, transportation expenses, and utility expenses to understand spending trends.

[0646] Step 5:

[0647] The server compares organized data with past consumption patterns to detect unusual spending and economic trends. Machine learning algorithms are used for this anomaly detection.

[0648] Step 6:

[0649] The device visualizes the results of anomaly detection. It provides users with an easy-to-understand overview of their spending status through graphs and notification features on the dashboard.

[0650] Step 7:

[0651] The server generates personalized savings suggestions based on emotional data provided by the emotion engine. For example, if a user is feeling anxious, it will offer suggestions to reduce their burden.

[0652] Step 8:

[0653] The device notifies the user of the generated savings suggestions. Based on sentiment data, the suggestions are tailored to the user and presented in an easy-to-implement format.

[0654] Step 9:

[0655] The server performs simulations of future asset planning that take life events into account. It provides a positive perspective by adjusting how the results are displayed based on emotional data.

[0656] Step 10:

[0657] The device presents the simulation results in a way that makes them easy for the user to understand. This allows the user to make better decisions about their future financial planning.

[0658] (Example 2)

[0659] 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."

[0660] Traditional household financial management systems primarily offer fixed advice based on financial information, lacking personalized suggestions that take into account the user's emotions and psychological state. This can lead to users feeling stressed or dissatisfied with the suggestions. Furthermore, there was a need for systems that could respond flexibly to the user's emotional state and alleviate anxiety about future life events.

[0661] 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.

[0662] In this invention, the server includes means for acquiring, preprocessing, and classifying financial information; means for detecting anomalies and visualizing the results; and means for generating and notifying users of savings suggestions. This enables personalized suggestions that take into account the user's emotional information.

[0663] "Financial information" refers to transaction data related to a user's bank accounts, credit cards, and other economic activities.

[0664] "Classification" refers to the process of organizing acquired financial information based on predetermined categories.

[0665] "Anomaly detection" refers to analytical methods used to detect unnatural economic activity that deviates from normal trading patterns.

[0666] "Visualization" refers to techniques for displaying data and analysis results in a format that users can intuitively understand.

[0667] "User" refers to an individual who uses this system to manage their household finances.

[0668] "Emotional information" refers to data indicating the psychological and emotional state of the user, extracted based on their facial expressions, voice, and input data.

[0669] A "savings suggestion" refers to a plan to reduce spending or to use resources more efficiently, based on the user's financial situation and emotional information.

[0670] "Life events" refer to significant events that may affect the user's economic situation in the future, such as marriage, childbirth, entering higher education, or retirement.

[0671] "Personalized" refers to methods and suggestions that are individually tailored to take into account the unique circumstances and characteristics of each user.

[0672] This invention features a system that provides users with personalized household management by integrating financial information and emotional information. This system consists of a backend for managing financial transactions and a frontend engine that recognizes and analyzes the user's emotions.

[0673] Data acquisition and emotion recognition

[0674] The server retrieves transaction data from the user's bank account and credit card via APIs. This process uses the OAuth 2.0 protocol to ensure secure access. The retrieved financial information is securely stored using AES encryption. In parallel, the device collects user emotional information using its camera and microphone. OpenCV is used for image processing, and a speech recognition API is used for voice analysis. The emotional information obtained from the device is transmitted to the server via edge computing.

[0675] Data integration and proposal generation

[0676] The server uses Python to categorize financial information and apply anomaly detection algorithms. It utilizes the Pandas library to organize the information in a dataframe format. Furthermore, it analyzes emotional information to tailor suggestions based on the user's psychological state. For example, it prioritizes presenting low-burden savings options to users experiencing stress.

[0677] Visualization and Feedback

[0678] The device uses visualization libraries such as Matplotlib to display analysis results in graph and dashboard formats. During this process, the difficulty level and presentation of suggestions are adjusted according to the user's emotional state. If positive emotions are detected, challenging options can be presented to increase engagement.

[0679] Specific example

[0680] If a user requests a review of their household budget, the system proposes a concrete action plan based on the user's emotional state. The device analyzes emotions in real time, and the server generates the optimal saving strategy based on that information. By presenting the plan in a visually easy-to-understand format, users can more easily implement the suggestions. As a specific prompt, customized questions such as, "Create saving goals to propose when the user is showing positive emotions," are input into the generating AI model.

[0681] This system provides an implementation that supports effective household financial management while increasing user psychological satisfaction.

[0682] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0683] Step 1:

[0684] Input: Raw data obtained via financial APIs.

[0685] Operation: The server uses OAuth 2.0 to access the financial institution's API and securely retrieve the user's transaction data.

[0686] Data Processing / Calculation: The acquired data is converted into a DataFrame using the Pandas library and organized by category. Unnecessary data is removed at this stage.

[0687] Output: Financial information organized by category.

[0688] Step 2:

[0689] Input: User emotion data obtained from the camera and microphone.

[0690] Operation: The device captures the user's facial expressions and voice through the camera and microphone. OpenCV is used for facial recognition, and the Voice Assistant API is used for speech recognition.

[0691] Data processing / computation: The acquired information is processed in real time using edge computing, and data related to emotional states is extracted.

[0692] Output: User's current emotional state data.

[0693] Step 3:

[0694] Input: Organized financial information and emotional state data.

[0695] Operation: The server integrates this data and runs an anomaly detection algorithm. This algorithm identifies items that deviate from normal spending patterns.

[0696] Data processing / computation: Statistical methods are used for anomaly detection, and both financial data and sentiment information are evaluated.

[0697] Output: A list of unusual spending and its associated sentiment information.

[0698] Step 4:

[0699] Input: List of unusual spending, sentiment information, and other economic analysis information.

[0700] Operation: Based on this data, the server generates savings suggestions tailored to the user's psychological state.

[0701] Data Processing / Calculation: Use a generative AI model to create suggestions and customize them to take sentiment into account. Input is provided to the AI ​​through prompt sentences to obtain the optimal suggestion.

[0702] Output: Personalized savings suggestions and notification messages.

[0703] Step 5:

[0704] Input: Savings suggestions, data for visualization.

[0705] Operation: The terminal generates graphs and charts using visualization tools based on data received from the server.

[0706] Data processing / calculations: Visualization libraries such as Matplotlib are used to visualize data in an intuitively understandable format.

[0707] Output: Information presented to the user in the form of graphs or dashboards.

[0708] This process will provide users with personalized support for managing their household finances.

[0709] (Application Example 2)

[0710] 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."

[0711] In modern households, managing financial information has become increasingly complex, leading to greater stress in individual household budgeting. Therefore, there is a need for personalized and emotionally sensitive financial support that takes into account the user's psychological state. Conventional systems struggle to provide suggestions linked to emotional analysis, resulting in a failure to deliver optimal information to users.

[0712] 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.

[0713] In this invention, the server includes a mechanism for acquiring financial information, a mechanism for preprocessing the acquired financial information and organizing it by classification, and a mechanism for detecting anomalies using the classified information. This makes it possible to recognize the user's emotional state, generate personalized savings suggestions according to that state, and enable optimal household financial management with reduced stress.

[0714] "Financial information" refers to transaction data obtained from bank accounts and credit cards, and is used for household budget management.

[0715] "Preprocessing" refers to the process of organizing and classifying acquired data to prepare it for smooth subsequent anomaly detection and analysis.

[0716] "Classification" is a method of organizing financial information into different categories, making it easier to manage and analyze each category individually.

[0717] Anomaly detection is the process of identifying unusual transactions that deviate from normal spending patterns, based on organized data.

[0718] "Visualization" is the process of displaying data in the form of graphs and dashboards, allowing users to intuitively understand the information.

[0719] "User" refers to an individual who uses this system to manage their household finances.

[0720] An "emotion analysis mechanism" is a system that uses data acquired from cameras and microphones to recognize and determine the user's psychological state based on their facial expressions, voice tone, and other factors.

[0721] "Personalized savings suggestions" are suggestions that present individually optimized savings methods based on the user's financial situation and emotional state.

[0722] The system implementing this invention integrates financial information and sentiment analysis to provide users with personalized household financial management. The server encrypts transaction data obtained from financial institutions' APIs, processes it, and organizes it by category. This systematizes the financial information and streamlines the subsequent analysis process.

[0723] The emotion analysis mechanism uses cameras and microphones mounted on consumer robots and other devices to analyze the user's facial expressions and voice tone in real time. Utilizing edge computing technology, the analyzed emotion data is immediately transmitted to a server to understand the user's current psychological state.

[0724] The server integrates organized financial and emotional data, combining anomaly detection algorithms and emotion recognition to generate optimal savings suggestions for the user. These suggestions are visualized and communicated to the user via consumer robots. In particular, by adjusting the content and presentation of savings suggestions according to the user's emotional state, information can be shared without causing stress to the user.

[0725] For example, if data analysis reveals that the user is experiencing stress, the device will suggest less burdensome saving methods in a gentle tone. Conversely, if the device determines that the user is in a positive state, it can present more challenging saving goals.

[0726] An example of a prompt generated using a generative AI model is: "Please provide five fun money-saving ideas for this weekend. Please use positive language and explain them gently to boost motivation." Based on this prompt, attractive and practical suggestions are generated for the user.

[0727] In this way, a system that integrates sentiment analysis and financial data will provide accurate and effective household financial management support while staying close to the user's needs.

[0728] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0729] Step 1:

[0730] The server retrieves financial information via APIs from financial institutions. It receives user bank account and credit card information as input, encrypts it, and stores it in a database. As output, it generates raw transaction data for organization.

[0731] Step 2:

[0732] The server preprocesses the acquired financial information and organizes it by category. It uses raw transaction data as input and classifies the data into predefined categories within the program. This process results in organized data categorized by expenditure type as output.

[0733] Step 3:

[0734] The server performs anomaly detection using organized financial data. It receives categorized data as input and applies anomaly detection algorithms. It identifies abnormal trading patterns and generates the results as output.

[0735] Step 4:

[0736] The device uses an emotion analysis mechanism to acquire user emotion data. It utilizes visual and audio data obtained from the camera and microphone as input, and performs emotion analysis on edge computing resources. The results of this analysis are then sent to a server as output.

[0737] Step 5:

[0738] The server integrates financial and sentiment data to generate optimal savings suggestions. It uses anomaly detection results and sentiment analysis results as input. A generative AI model is used to create prompt messages, and the output is a savings scenario that takes sentiment into account.

[0739] Step 6:

[0740] The terminal visualizes the savings suggestions sent from the server and notifies the user. It receives generated savings scenarios as input and displays the information through graphs and icons in the user interface. The output is what the user uses to review the information and understand the suggestions.

[0741] 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.

[0742] 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.

[0743] 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.

[0744] [Fourth Embodiment]

[0745] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0746] 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.

[0747] 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).

[0748] 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.

[0749] 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.

[0750] 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).

[0751] 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.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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".

[0758] To implement this invention, it is first necessary to build a system infrastructure capable of processing financial data. Specifically, it is required to securely acquire transaction information from users' bank accounts and credit cards and prepare the data so that it can be analyzed. This system operates in cooperation with users, servers, and terminals.

[0759] Data acquisition and management

[0760] The server retrieves bank account and credit card transaction data through APIs authorized by the user. This data is encrypted and securely stored in a database on the server.

[0761] Data analysis and notification

[0762] The server analyzes the accumulated data and organizes it by category. Machine learning algorithms are used to detect unusual spending patterns and other abnormalities from the data. These algorithms generate predictive models based on historical data to perform anomaly detection.

[0763] The device displays analysis results to the user in visual formats such as dashboards and graphs. It also notifies the user with savings suggestions and warnings about unusual spending.

[0764] Personalized savings proposals and asset management

[0765] The server identifies potential cost savings based on the user's consumption patterns. For example, it might detect unnecessary subscription services or suggest cheaper utility plans.

[0766] The device displays these savings suggestions to the user, who can then select them to improve their asset management.

[0767] Simulation and long-term financial planning

[0768] The server runs simulations that take future life events into account and generates long-term financial plans. This allows users to predict their future financial situation and take necessary measures.

[0769] The terminal displays the simulation results to the user and provides information to adjust the plan.

[0770] Specific example

[0771] In some households, if monthly electricity consumption exceeds acceptable limits, the server detects and analyzes the anomaly in real time. The terminal notifies the user of this information and suggests energy-saving measures, such as changing plans with a specific electricity provider. By considering these suggestions and taking action as needed, users can reduce their household expenses and achieve efficient asset management.

[0772] In this manner, the present invention provides embodiments for more efficient and dynamic household financial management in individual households.

[0773] The following describes the processing flow.

[0774] Step 1:

[0775] Users register their financial institution account information with the system and authorize the retrieval of their data.

[0776] Step 2:

[0777] The server retrieves transaction data in real time through financial institutions' APIs, based on information authorized by the user. The retrieved data is encrypted and stored in a secure database.

[0778] Step 3:

[0779] The server analyzes the stored data and organizes income and expenses by category. This uses defined categories such as food expenses, transportation expenses, and medical expenses. Data cleaning is also performed at this stage.

[0780] Step 4:

[0781] The server uses machine learning algorithms based on historical data to detect unusual spending patterns. This identifies abnormal spending that deviates from normal trends.

[0782] Step 5:

[0783] The terminal visualizes the results of anomaly detection and the overall household financial situation on a dashboard and displays it to the user. Graphs and pie charts are used to make the information easy to understand.

[0784] Step 6:

[0785] The server analyzes the user's consumption patterns and suggests areas where expenses can be reduced. It generates specific savings suggestions, such as reviewing utility bills or cutting costs on subscription services.

[0786] Step 7:

[0787] The device notifies the user of these savings suggestions and provides options for actually implementing them. The user can review the notification and select a savings plan.

[0788] Step 8:

[0789] The server runs a simulation of long-term financial planning based on future life events (e.g., saving for education or retirement planning).

[0790] Step 9:

[0791] The terminal displays the simulation results to the user and supports them in adjusting their asset management plan as needed.

[0792] (Example 1)

[0793] 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".

[0794] In modern financial management, many users seek ways to efficiently understand their financial activities and reduce waste. However, because a large amount of transaction information is scattered across many different platforms, integrating and analyzing it safely and efficiently is difficult. Furthermore, obtaining the information necessary for long-term asset management and improving consumption patterns is a time-consuming and laborious task using current methods.

[0795] 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.

[0796] In this invention, the server includes means for acquiring user transaction information and securely managing the information, means for encrypting the acquired transaction information and storing it in a storage device, and means for processing the information stored in the storage device and classifying the data. This enables users to securely manage and analyze their financial information on a centralized interface, and to efficiently detect abnormal expenditures and reduce waste.

[0797] A "user" is an individual or legal entity that uses information or services related to financial transactions.

[0798] "Transaction information" refers to data obtained from financial activities such as bank accounts and credit cards, including specific transaction and deposit histories.

[0799] "Encryption" is the process of transforming data using a specific algorithm to prevent it from being misused by third parties.

[0800] A "storage device" is hardware or a medium used to temporarily or permanently store digital data.

[0801] A "machine learning algorithm" is a program that uses past data to recognize patterns and make predictions and classifications about future data.

[0802] "Visual display" refers to using visual formats such as graphs and charts to convey information to users in an easy-to-understand manner.

[0803] A "suggestion" is information that provides specific strategies for saving money and managing assets efficiently, based on the user's financial activities.

[0804] "Simulation" is the process of using a computer to predict the outcome of a real-world situation.

[0805] "Usage patterns" refer to a series of habits and tendencies derived from a user's transaction history and consumption behavior.

[0806] A "strategy" refers to the direction or measures provided to achieve a specific objective.

[0807] In order to implement this invention, it is first necessary to build a foundation for processing financial data. Specifically, a system is installed to securely acquire, store, and analyze user transaction information. The embodiments thereof are described in detail below.

[0808] Data acquisition and management

[0809] The server retrieves financial transaction data through APIs authorized by the user. The technology used includes authentication processes such as OAuth to establish a secure connection. The retrieved data is protected using encryption methods such as AES-256, and the database is stored using a common cloud storage service.

[0810] Data analysis and visualization

[0811] The server performs an ETL process on the acquired data. Specifically, it uses the Python Pandas library to analyze the data frame and organize the data into categories. Then, it uses machine learning libraries such as Scikit-learn and TensorFlow to perform anomaly detection. The analysis results are displayed on the user interface via the terminal. D3.js and Chart.js are used for visualization.

[0812] Proposals and notifications

[0813] The device displays data-driven savings suggestions and warnings based on detected anomalies to the user. This includes real-time communication via push notifications using Firebase Cloud Messaging. Users can then take action based on this information.

[0814] Long-term plan simulation

[0815] The server conducts simulations that take into account important future events and uses generative AI models such as Keras to develop long-term asset plans. This allows users to predict future economic conditions and create life plans based on that information. The results are displayed graphically, and users can adjust their plans accordingly.

[0816] As a concrete example, a user monitors their monthly electricity consumption, and an anomaly is detected if it exceeds a certain threshold. In this case, the server analyzes the anomaly in real time, and the terminal presents the user with specific suggestions for saving energy (for example, changing electricity plans), enabling the user to manage their assets efficiently.

[0817] An example of a prompt message is, "Please tell me how to analyze a user's monthly spending patterns and detect unusual spending."

[0818] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0819] Step 1:

[0820] The server retrieves transaction information through an API authorized by the user. The input requires user authentication credentials and API access permission. The server authenticates the user using the OAuth protocol and establishes a secure connection. It then sequentially downloads the transaction information via a RESTful API, encrypts this data, and stores it in temporary storage. The output is the encrypted transaction information.

[0821] Step 2:

[0822] The server stores the acquired transaction information in a database. The input is encrypted transaction information, and the database uses standard cloud storage. The server classifies the information by category while ensuring data security using AES-256 encryption. In this process, the data is organized based on transaction type and date. The output is the database where the classified data is stored.

[0823] Step 3:

[0824] The server analyzes the stored data. It uses categorically organized data stored in a database as input. The server formats the data using the Pandas library and performs anomaly detection using the Scikit-learn machine learning algorithm. Specifically, it splits the data into a training set and a test set and performs pattern matching. The output is a model showing anomaly patterns and its results.

[0825] Step 4:

[0826] The terminal visually displays the analysis results. The input is the analysis results of abnormal patterns sent from the server. The terminal uses D3.js or Chart.js to represent this to the user in graph and chart format. Based on this visual information, the user can evaluate their trading activities. The output is a display of the analysis results in a format that is easy for the user to understand.

[0827] Step 5:

[0828] The device notifies the user of suggestions for saving money and making improvements. The input is the suggestions based on the analysis results. The device uses Firebase Cloud Messaging to send real-time push notifications to the user. In operation, the user is presented with specific suggestions (e.g., canceling a particular subscription or changing a utility plan). The output is specific suggestions to help the user make decisions.

[0829] Step 6:

[0830] The server runs simulations that take future life events into account. The inputs are the user's current asset situation and assumptions about life events. The server uses generative AI models such as Keras to generate predictive scenarios. Specifically, it predicts asset increases and decreases based on conditions set by the user and generates a long-term plan. This result is provided to the terminal as a future asset plan.

[0831] Step 7:

[0832] The user makes decisions based on the information and suggestions received through the device. Inputs are visualized analysis results and notified suggestions. The user evaluates the provided information and takes specific actions as needed (e.g., switching to a suggested plan or developing a new savings plan). Outputs are the user's optimized asset management activities.

[0833] (Application Example 1)

[0834] 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".

[0835] In modern society, personal and household financial management has become increasingly complex, and consumers are often plagued by unnecessary spending. Furthermore, there is a lack of clear guidance for creating long-term financial plans. Therefore, there is a need for a system that allows for efficient management of daily expenses, reduction of potential waste, and easy development of future-oriented plans.

[0836] 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.

[0837] In this invention, the server includes means for acquiring financial information, means for preprocessing the acquired financial information and organizing it by category, and means for detecting unnecessary spending based on the user's consumption habits and generating specific reduction suggestions. This makes it possible for users to efficiently manage their daily expenses, reduce waste, and more easily plan their future assets.

[0838] "Financial information" refers to data that shows a user's asset status and spending habits, such as bank account and credit card transaction history.

[0839] "Preprocessing" refers to classifying and processing acquired financial information and organizing it into an analyzable format.

[0840] "Classification" refers to organizing pre-processed financial information by its nature and purpose.

[0841] Anomaly detection is an analytical technique used to identify spending that deviates from normal patterns or standards.

[0842] "Consumer habits" refer to the tendencies and patterns of consumption behavior that individuals and households engage in on a daily basis.

[0843] A "reduction suggestion" is advice that analyzes a user's past spending patterns and provides specific measures to reduce unnecessary expenses.

[0844] "Visualization" is the process of making analysis results visible in the form of graphs, dashboards, and other formats, making them easy for users to understand.

[0845] A "simulation" is a method for virtually recreating future life events and financial situations in order to formulate plans and countermeasures.

[0846] To implement this invention, it is necessary to build a system in which a server, terminal, and user work together to efficiently acquire, analyze, and display financial information. The server acquires financial information through an API authorized by the user. The acquired information is encrypted and stored in a database, and then preprocessed. Next, the server uses a machine learning algorithm to detect abnormal patterns in the information. This makes unnecessary spending visible. The terminal presents the analysis results to the user in a visual format such as a dashboard or graph, and notifies them of savings suggestions.

[0847] The hardware utilizes a server that performs real-time data acquisition and analysis using AWS Lambda. Amazon RDS is used to securely store financial information in the database. The user terminal is a smartphone application running on Android or iOS. Python and the pandas library are used for data processing, and the scikit-learn Isolation Forest algorithm is used for anomaly detection. The analysis results are visualized using the Matplotlib library and displayed to the user.

[0848] As a concrete example, consider a scenario where a user uses the app at the end of the month to check "how much they saved this month." This application identifies unnecessary expenses for the user and provides specific reduction suggestions, such as "you should cancel your gym membership if you only use it twice a month." This allows the user to reduce necessary spending and improve their financial management.

[0849] An example of a prompt using a generative AI model would be, "Based on my living expenses over the past three months, please identify areas where I can save money next month and explain why." This prompt allows the AI ​​model to analyze the accumulated data and provide the user with personalized and useful information.

[0850] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0851] Step 1:

[0852] The server retrieves financial information through an API authorized by the user. This step involves inputting the user's bank account information and credit card transaction history, and the retrieved data is securely stored in an encrypted state. The data retrieval process uses OAuth 2.0 for authentication and receives data in JSON format.

[0853] Step 2:

[0854] The server preprocesses the acquired financial information. In this step, it receives the acquired financial information as input and organizes it by category using the pandas library. The output here is a data frame prepared for subsequent analysis. Preprocessing includes removing duplicate data and normalization.

[0855] Step 3:

[0856] The server uses a machine learning algorithm to detect anomalies. In this step, the preprocessed dataframe is taken as input, and scikit-learn's Isolation Forest is used to detect transactions with unusual patterns. The output is a list of transactions that were determined to be anomaly. In this process, the data is applied to a trained model to calculate an anomaly score.

[0857] Step 4:

[0858] The terminal visualizes and displays the analysis results to the user. In this step, the results of anomaly detection are used as input, and Matplotlib is used to generate user-friendly dashboards and graphs. The output is a visually organized report. The user can review this on their smartphone to understand their spending habits.

[0859] Step 5:

[0860] The server generates specific reduction suggestions based on the user's consumption habits. This step takes a list of anomaly detections and the user's past consumption data as input to identify expenditure items that can be reduced. The output is a notification of reduction suggestions. The generated suggestions may include, for example, "cancel infrequently used subscriptions."

[0861] Step 6:

[0862] The device notifies the user of the generated reduction suggestions. In this step, the reduction suggestions sent from the server are used as input and displayed to the user as push notifications or in-app messages. The output is suggestions that the user can explicitly see. The user then takes specific actions based on the suggestions.

[0863] Step 7:

[0864] The user can input prompts using a generative AI model and receive suggestions for further savings. In this step, the user's prompt is input, the AI ​​model performs data analysis based on it, and generates and outputs customized suggestions. A prompt such as, "Based on my living expenses over the past three months, please identify expenses I can save on next month and explain why," is used.

[0865] 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.

[0866] This invention describes a system that integrates financial data and emotional data to provide more personalized and emotional support for household financial management. This system combines the processing of financial information with the recognition of the user's emotions to provide personalized recommendations for each user.

[0867] Data acquisition and emotion recognition

[0868] The server continuously retrieves transaction data from the user's bank account and credit card APIs, encrypts it, and stores it. Simultaneously, the device runs an emotion engine that recognizes the user's emotions based on their facial expressions, voice tone, and input. This emotion data is instantly analyzed using edge computing and sent to the server.

[0869] Integrated analysis of data and emotions

[0870] The server organizes and analyzes the acquired financial data by category to detect unusual spending. In parallel with this, it checks the user's current emotional state based on emotional data. For example, if the user is feeling stressed, the system adjusts its processing to offer more cautious suggestions.

[0871] Proactive notifications and optimized suggestions

[0872] The device visualizes and presents analysis results to the user, including displays in graphs and dashboards. It also adapts the content and presentation of savings suggestions based on the user's emotional state. For example, if the user is in a positive mood, it can present more challenging savings goals.

[0873] The server generates multiple cost-saving scenarios and suggests the optimal option based on emotional data. If the emotional engine recognizes the user's worries or anxieties, suggestions are made in a more empathetic approach.

[0874] Simulation and customization

[0875] The server performs simulations based on future life events, but customizes how the results are presented according to the user's emotions. For example, if anxiety about the future is detected, the server will reassure the user by emphasizing the positive aspects of the simulation results.

[0876] Specific example

[0877] If a user is feeling stressed about managing their household finances, the device recognizes this emotion using its emotion engine, and the server, taking that data into consideration, suggests less burdensome ways to save money. Furthermore, the device displays this process visually in a user-friendly way, providing information in an easily acceptable format.

[0878] Thus, the present invention provides a specific embodiment for realizing household budget management support that is tailored to the user's psychological state by incorporating emotion recognition technology.

[0879] The following describes the processing flow.

[0880] Step 1:

[0881] Users register their financial institution account information with the system and set data retrieval permissions. Simultaneously, they configure privacy settings regarding the collection of emotional data.

[0882] Step 2:

[0883] The server retrieves transaction data from financial institutions based on user permission. The retrieved data is securely stored in a database in an encrypted form.

[0884] Step 3:

[0885] The device uses a facial recognition camera and microphone to collect emotional data from the user's facial expressions and voice. An emotion engine analyzes this data to recognize the user's emotional state in real time.

[0886] Step 4:

[0887] The server organizes the acquired financial data by category. Specifically, it classifies it into categories such as food expenses, transportation expenses, and utility expenses to understand spending trends.

[0888] Step 5:

[0889] The server compares organized data with past consumption patterns to detect unusual spending and economic trends. Machine learning algorithms are used for this anomaly detection.

[0890] Step 6:

[0891] The device visualizes the results of anomaly detection. It provides users with an easy-to-understand overview of their spending status through graphs and notification features on the dashboard.

[0892] Step 7:

[0893] The server generates personalized savings suggestions based on emotional data provided by the emotion engine. For example, if a user is feeling anxious, it will offer suggestions to reduce their burden.

[0894] Step 8:

[0895] The device notifies the user of the generated savings suggestions. Based on sentiment data, the suggestions are tailored to the user and presented in an easy-to-implement format.

[0896] Step 9:

[0897] The server performs simulations of future asset planning that take life events into account. It provides a positive perspective by adjusting how the results are displayed based on emotional data.

[0898] Step 10:

[0899] The device presents the simulation results in a way that makes them easy for the user to understand. This allows the user to make better decisions about their future financial planning.

[0900] (Example 2)

[0901] 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".

[0902] Traditional household financial management systems primarily offer fixed advice based on financial information, lacking personalized suggestions that take into account the user's emotions and psychological state. This can lead to users feeling stressed or dissatisfied with the suggestions. Furthermore, there was a need for systems that could respond flexibly to the user's emotional state and alleviate anxiety about future life events.

[0903] 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.

[0904] In this invention, the server includes means for acquiring, preprocessing, and classifying financial information; means for detecting anomalies and visualizing the results; and means for generating and notifying users of savings suggestions. This enables personalized suggestions that take into account the user's emotional information.

[0905] "Financial information" refers to transaction data related to a user's bank accounts, credit cards, and other economic activities.

[0906] "Classification" refers to the process of organizing acquired financial information based on predetermined categories.

[0907] "Anomaly detection" refers to analytical methods used to detect unnatural economic activity that deviates from normal trading patterns.

[0908] "Visualization" refers to techniques for displaying data and analysis results in a format that users can intuitively understand.

[0909] "User" refers to an individual who uses this system to manage their household finances.

[0910] "Emotional information" refers to data indicating the psychological and emotional state of the user, extracted based on their facial expressions, voice, and input data.

[0911] A "savings suggestion" refers to a plan to reduce spending or to use resources more efficiently, based on the user's financial situation and emotional information.

[0912] "Life events" refer to significant events that may affect the user's economic situation in the future, such as marriage, childbirth, entering higher education, or retirement.

[0913] "Personalized" refers to methods and suggestions that are individually tailored to take into account the unique circumstances and characteristics of each user.

[0914] This invention features a system that provides users with personalized household management by integrating financial information and emotional information. This system consists of a backend for managing financial transactions and a frontend engine that recognizes and analyzes the user's emotions.

[0915] Data acquisition and emotion recognition

[0916] The server retrieves transaction data from the user's bank account and credit card via APIs. This process uses the OAuth 2.0 protocol to ensure secure access. The retrieved financial information is securely stored using AES encryption. In parallel, the device collects user emotional information using its camera and microphone. OpenCV is used for image processing, and a speech recognition API is used for voice analysis. The emotional information obtained from the device is transmitted to the server via edge computing.

[0917] Data integration and proposal generation

[0918] The server uses Python to categorize financial information and apply anomaly detection algorithms. It utilizes the Pandas library to organize the information in a dataframe format. Furthermore, it analyzes emotional information to tailor suggestions based on the user's psychological state. For example, it prioritizes presenting low-burden savings options to users experiencing stress.

[0919] Visualization and Feedback

[0920] The device uses visualization libraries such as Matplotlib to display analysis results in graph and dashboard formats. During this process, the difficulty level and presentation of suggestions are adjusted according to the user's emotional state. If positive emotions are detected, challenging options can be presented to increase engagement.

[0921] Specific example

[0922] If a user requests a review of their household budget, the system proposes a concrete action plan based on the user's emotional state. The device analyzes emotions in real time, and the server generates the optimal saving strategy based on that information. By presenting the plan in a visually easy-to-understand format, users can more easily implement the suggestions. As a specific prompt, customized questions such as, "Create saving goals to propose when the user is showing positive emotions," are input into the generating AI model.

[0923] This system provides an implementation that supports effective household financial management while increasing user psychological satisfaction.

[0924] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0925] Step 1:

[0926] Input: Raw data obtained via financial APIs.

[0927] Operation: The server uses OAuth 2.0 to access the financial institution's API and securely retrieve the user's transaction data.

[0928] Data Processing / Calculation: The acquired data is converted into a DataFrame using the Pandas library and organized by category. Unnecessary data is removed at this stage.

[0929] Output: Financial information organized by category.

[0930] Step 2:

[0931] Input: User emotion data obtained from the camera and microphone.

[0932] Operation: The device captures the user's facial expressions and voice through the camera and microphone. OpenCV is used for facial recognition, and the Voice Assistant API is used for speech recognition.

[0933] Data processing / computation: The acquired information is processed in real time using edge computing, and data related to emotional states is extracted.

[0934] Output: User's current emotional state data.

[0935] Step 3:

[0936] Input: Organized financial information and emotional state data.

[0937] Operation: The server integrates this data and runs an anomaly detection algorithm. This algorithm identifies items that deviate from normal spending patterns.

[0938] Data processing / computation: Statistical methods are used for anomaly detection, and both financial data and sentiment information are evaluated.

[0939] Output: A list of unusual spending and its associated sentiment information.

[0940] Step 4:

[0941] Input: List of unusual spending, sentiment information, and other economic analysis information.

[0942] Operation: Based on this data, the server generates savings suggestions tailored to the user's psychological state.

[0943] Data Processing / Calculation: Use a generative AI model to create suggestions and customize them to take sentiment into account. Input is provided to the AI ​​through prompt sentences to obtain the optimal suggestion.

[0944] Output: Personalized savings suggestions and notification messages.

[0945] Step 5:

[0946] Input: Savings suggestions, data for visualization.

[0947] Operation: The terminal generates graphs and charts using visualization tools based on data received from the server.

[0948] Data processing / calculations: Visualization libraries such as Matplotlib are used to visualize data in an intuitively understandable format.

[0949] Output: Information presented to the user in the form of graphs or dashboards.

[0950] This process will provide users with personalized support for managing their household finances.

[0951] (Application Example 2)

[0952] 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".

[0953] In modern households, managing financial information has become increasingly complex, leading to greater stress in individual household budgeting. Therefore, there is a need for personalized and emotionally sensitive financial support that takes into account the user's psychological state. Conventional systems struggle to provide suggestions linked to emotional analysis, resulting in a failure to deliver optimal information to users.

[0954] 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.

[0955] In this invention, the server includes a mechanism for acquiring financial information, a mechanism for preprocessing the acquired financial information and organizing it by classification, and a mechanism for detecting anomalies using the classified information. This makes it possible to recognize the user's emotional state, generate personalized savings suggestions according to that state, and enable optimal household financial management with reduced stress.

[0956] "Financial information" refers to transaction data obtained from bank accounts and credit cards, and is used for household budget management.

[0957] "Preprocessing" refers to the process of organizing and classifying acquired data to prepare it for smooth subsequent anomaly detection and analysis.

[0958] "Classification" is a method of organizing financial information into different categories, making it easier to manage and analyze each category individually.

[0959] Anomaly detection is the process of identifying unusual transactions that deviate from normal spending patterns, based on organized data.

[0960] "Visualization" is the process of displaying data in the form of graphs and dashboards, allowing users to intuitively understand the information.

[0961] "User" refers to an individual who uses this system to manage their household finances.

[0962] An "emotion analysis mechanism" is a system that uses data acquired from cameras and microphones to recognize and determine the user's psychological state based on their facial expressions, voice tone, and other factors.

[0963] "Personalized savings suggestions" are suggestions that present individually optimized savings methods based on the user's financial situation and emotional state.

[0964] The system implementing this invention integrates financial information and sentiment analysis to provide users with personalized household financial management. The server encrypts transaction data obtained from financial institutions' APIs, processes it, and organizes it by category. This systematizes the financial information and streamlines the subsequent analysis process.

[0965] The emotion analysis mechanism uses cameras and microphones mounted on consumer robots and other devices to analyze the user's facial expressions and voice tone in real time. Utilizing edge computing technology, the analyzed emotion data is immediately transmitted to a server to understand the user's current psychological state.

[0966] The server integrates organized financial and emotional data, combining anomaly detection algorithms and emotion recognition to generate optimal savings suggestions for the user. These suggestions are visualized and communicated to the user via consumer robots. In particular, by adjusting the content and presentation of savings suggestions according to the user's emotional state, information can be shared without causing stress to the user.

[0967] For example, if data analysis reveals that the user is experiencing stress, the device will suggest less burdensome saving methods in a gentle tone. Conversely, if the device determines that the user is in a positive state, it can present more challenging saving goals.

[0968] An example of a prompt generated using a generative AI model is: "Please provide five fun money-saving ideas for this weekend. Please use positive language and explain them gently to boost motivation." Based on this prompt, attractive and practical suggestions are generated for the user.

[0969] In this way, a system that integrates sentiment analysis and financial data will provide accurate and effective household financial management support while staying close to the user's needs.

[0970] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0971] Step 1:

[0972] The server retrieves financial information via APIs from financial institutions. It receives user bank account and credit card information as input, encrypts it, and stores it in a database. As output, it generates raw transaction data for organization.

[0973] Step 2:

[0974] The server preprocesses the acquired financial information and organizes it by category. It uses raw transaction data as input and classifies the data into predefined categories within the program. This process results in organized data categorized by expenditure type as output.

[0975] Step 3:

[0976] The server performs anomaly detection using organized financial data. It receives categorized data as input and applies anomaly detection algorithms. It identifies abnormal trading patterns and generates the results as output.

[0977] Step 4:

[0978] The device uses an emotion analysis mechanism to acquire user emotion data. It utilizes visual and audio data obtained from the camera and microphone as input, and performs emotion analysis on edge computing resources. The results of this analysis are then sent to a server as output.

[0979] Step 5:

[0980] The server integrates financial and sentiment data to generate optimal savings suggestions. It uses anomaly detection results and sentiment analysis results as input. A generative AI model is used to create prompt messages, and the output is a savings scenario that takes sentiment into account.

[0981] Step 6:

[0982] The terminal visualizes the savings suggestions sent from the server and notifies the user. It receives generated savings scenarios as input and displays the information through graphs and icons in the user interface. The output is what the user uses to review the information and understand the suggestions.

[0983] 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.

[0984] 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.

[0985] 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.

[0986] 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.

[0987] 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.

[0988] 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.

[0989] 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.

[0990] 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.

[0991] 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."

[0992] 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.

[0993] 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.

[0994] 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.

[0995] 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.

[0996] 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.

[0997] 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.

[0998] 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.

[0999] 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.

[1000] 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.

[1001] 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.

[1002] 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.

[1003] 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.

[1004] The following is further disclosed regarding the embodiments described above.

[1005] (Claim 1)

[1006] Means of obtaining financial data,

[1007] A means for preprocessing the acquired financial data and organizing it by category,

[1008] A means for performing anomaly detection using the aforementioned organized data,

[1009] A means for visualizing the results of the anomaly detection and displaying them to the user,

[1010] A means of generating and notifying users of savings suggestions,

[1011] A system that includes this.

[1012] (Claim 2)

[1013] The system according to claim 1, comprising means for simulating and displaying an asset plan based on future life events.

[1014] (Claim 3)

[1015] The system according to claim 1, comprising means for identifying expenses that can be saved from a user's consumption patterns and generating specific actions.

[1016] "Example 1"

[1017] (Claim 1)

[1018] A means of acquiring user transaction information and securely managing that information,

[1019] Means for encrypting the acquired transaction information and storing it in a storage device,

[1020] means for processing information stored in the aforementioned storage device and classifying the data,

[1021] A means for detecting anomalies using a machine learning algorithm with the classified data,

[1022] A means for analyzing the results of the anomaly detection and displaying them visually,

[1023] A means for generating and notifying the user of a proposal based on the aforementioned analysis results,

[1024] A system that includes this.

[1025] (Claim 2)

[1026] The system according to claim 1, comprising means for simulating a long-term plan and providing information, taking into account important future events.

[1027] (Claim 3)

[1028] The system according to claim 1, comprising means for analyzing user usage patterns and proposing specific measures to reduce waste.

[1029] "Application Example 1"

[1030] (Claim 1)

[1031] Means of obtaining financial information,

[1032] A means for preprocessing the acquired financial information and organizing it by classification,

[1033] A means for performing anomaly detection using the aforementioned organized information,

[1034] A means for visualizing the results of the anomaly detection and presenting them to the user,

[1035] A means of generating and notifying users of cost reduction proposals,

[1036] A means to detect unnecessary spending based on users' consumption habits and generate specific reduction suggestions,

[1037] A system that includes this.

[1038] (Claim 2)

[1039] The system according to claim 1, comprising means for simulating and displaying an asset plan based on future life events.

[1040] (Claim 3)

[1041] The system according to claim 1, comprising means for identifying cost reductions based on users' consumption habits and generating specific actions.

[1042] "Example 2 of combining an emotion engine"

[1043] (Claim 1)

[1044] A device for acquiring financial information,

[1045] A device for preprocessing the acquired financial information and organizing it by classification,

[1046] A device that performs anomaly detection using the aforementioned organized information,

[1047] A device that visualizes the results of the anomaly detection and displays them to the user,

[1048] A device that generates and notifies users of savings suggestions,

[1049] A device that collects emotional information using the user's facial expressions, voice, and input,

[1050] A device for analyzing the collected emotional information and adjusting the content and display method of the savings proposal based on the emotional information,

[1051] A system that includes this.

[1052] (Claim 2)

[1053] The system according to claim 1, which simulates resource planning based on future life events and adjusts and displays the results based on emotional information.

[1054] (Claim 3)

[1055] The system according to claim 1, which identifies expenses that can be saved from the user's consumption patterns and generates specific actions that depend on emotional information.

[1056] "Application example 2 when combining with an emotional engine"

[1057] (Claim 1)

[1058] Organizations that acquire financial information,

[1059] A mechanism for preprocessing the acquired financial information and organizing it by classification,

[1060] A mechanism for detecting anomalies using the classified information,

[1061] A mechanism for visualizing the results of the aforementioned anomaly detection and presenting them to the user,

[1062] A mechanism for recognizing the user's emotional state and analyzing emotions,

[1063] A mechanism that generates and notifies users of savings suggestions based on the results of the aforementioned sentiment analysis,

[1064] A system that includes this.

[1065] (Claim 2)

[1066] The system according to claim 1, comprising a mechanism for simulating and displaying an asset plan based on future life events.

[1067] (Claim 3)

[1068] The system according to claim 1, comprising a mechanism for identifying resalable expenses based on the user's consumption behavior patterns and generating specific action suggestions. [Explanation of symbols]

[1069] 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. Means of obtaining financial information, A means for preprocessing the acquired financial information and organizing it by classification, A means for performing anomaly detection using the aforementioned organized information, A means for visualizing the results of the anomaly detection and presenting them to the user, A means of generating and notifying users of cost reduction proposals, A means to detect unnecessary spending based on users' consumption habits and generate specific reduction suggestions, A system that includes this.

2. The system according to claim 1, comprising means for simulating and displaying an asset plan based on future life events.

3. The system according to claim 1, comprising means for identifying cost reductions based on users' consumption habits and generating specific actions.

Images