System

Abstract

A system is provided.SOLUTION: A system comprising: means for automatically collecting expense information of a user; means for standardizing the collected expense information; means for classifying the standardized expense information into categories; means for generating a household account book based on the classified expense information; and means for displaying the household account book on a terminal of the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Manually keeping a household account book requires a lot of time and effort, making it difficult for many users to use it continuously. Furthermore, since the usage history of various payment services and credit cards is scattered and difficult to manage in a unified manner, it is difficult for users to grasp the overall picture of their spending. As a result, users are unable to properly manage their spending, which can lead to wasteful spending. In addition, security management and privacy protection of collected spending data are also important issues. [Means for solving the problem]

[0005] The present invention includes a means for automatically collecting user expenditure information, and uniformly collects expenditure data from various payment services and credit card companies. Furthermore, a means for standardizing the collected expenditure information enables uniform data management. A means for classifying the standardized expenditure information into categories using an AI model is provided, and automatic classification is performed for categories such as food and transportation expenses. A means for automatically generating a household account book based on the classified expenditure information is provided, and the household account book is displayed in real time on the user's device. The collected expenditure data is also accumulated as big data, and by including a means for analyzing this data, it can be used for marketing initiatives and service improvement. Furthermore, to ensure the security of the collected expenditure data, a means for encrypting the data is included, protecting the user's privacy.

[0006] "User" refers to an individual or organization that uses this system to manage expenses and create a household account book.

[0007] "Expense information" refers to data that records details of expenses incurred by a user using payment services, credit cards, etc.

[0008] "Automatic collection means" refers to technologies and methods for obtaining spending data from payment services and credit card companies without manual user interaction.

[0009] "Standardization measures" refers to technologies and methods for converting different types of expenditure data obtained from each service into a unified format.

[0010] "Categorization means" refers to technology or methods for automatically sorting collected expenditure information into specific categories (e.g., food, transportation, entertainment, etc.).

[0011] "AI model" refers to a model that uses artificial intelligence to analyze spending information and classify it into specific categories.

[0012] "Means for generating a household account book" refers to a technology or method for automatically creating a household account book that organizes a user's monthly or yearly income and expenses based on classified expenditure information.

[0013] "User's terminal" refers to the device (e.g., smartphone, tablet, PC, etc.) used by the user to display information in the household ledger.

[0014] "Big data" refers to a large amount of data, including collected expenditure information, that can be analyzed to extract useful information.

[0015] "Encryption methods" refers to techniques or methods that convert data so that it cannot be read by third parties.

[0016] "Security" refers to the techniques and methods used to ensure the safety of information and protect it from unauthorized access, alteration, or destruction. [Brief explanation of the drawings]

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

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

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

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

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

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

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

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

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

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

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0038] The present invention is a system that automatically collects and standardizes a user's expenditure information, categorizes it using an AI model, and generates and displays a household account book. The following describes in detail the embodiments of the present invention.

[0039] Overall system configuration

[0040] The system consists of the following main components:

[0041] 1. User Device

[0042] A device that allows users to enter registration information and view household accounts.

[0043] Specifically, this includes smartphones, tablets, and PCs.

[0044] 2. Server

[0045] A central processing unit that receives data from users, collects, standardizes, and categorizes expenditure information, and creates a household ledger.

[0046] We accumulate expenditure data, classify it using AI, and analyze big data.

[0047] Program processing overview

[0048] 1. User: Registration

[0049] When a user first uses the system, they create an account and register the payment service and credit card they use, which allows the system to collect the user's spending information appropriately.

[0050] 2. Server: Authentication and Integration

[0051] The server authenticates with the payment service or credit card company entered by the user. If authentication is successful, it securely connects with the service and prepares to periodically collect spending data.

[0052] 3. Server: Data collection

[0053] The server automatically collects spending data from the user's payment services and credit card companies. This is done periodically using APIs. For example, when John buys groceries, his spending information is automatically sent to the server.

[0054] 4. Server: Data Standardization

[0055] The server converts the collected spending data into a unified format, processing payment services and credit card data provided in different formats into a format that can be managed centrally.

[0056] 5. Server: AI-based category determination

[0057] The server uses an AI model to categorize the standardized spending data, such as into categories like "food," "transportation," and "entertainment." The AI ​​model learns from past data and improves its classification accuracy.

[0058] 6. Server: Household accounting

[0059] The server automatically generates a household ledger for the user based on the classified expenditure data. The data is organized by month and category so that expenditures can be seen at a glance, and is saved in a visually easy-to-understand format.

[0060] 7. Terminal: Household account display

[0061] The user's device retrieves the latest household accounting data from the server and displays it. For example, when a user opens the app, the latest expenditure items and their categories, monthly expenditure totals, etc. are displayed.

[0062] 8. Server: Data storage and analysis

[0063] The server stores the collected spending data and analyzes it as big data. This data is used to improve marketing strategies and services. To protect user privacy, all data is encrypted and stored securely.

[0064] Specific examples

[0065] For example, if a user buys groceries online and pays for them with a particular payment service, the following happens:

[0066] 1. User pays

[0067] A user purchases groceries online and completes the payment through a payment service.

[0068] 2. The server collects data

[0069] The payment service sends spending data (e.g., payment amount, purchase store, purchase details, etc.) to the server.

[0070] 3. The server standardizes the data

[0071] The server converts this spending data into a format that can be centrally managed.

[0072] 4. The server uses AI to determine the category

[0073] The server's AI model classifies "groceries" into the "food expenses" category.

[0074] 5. The server creates the household account book

[0075] The server generates and stores an up-to-date household account book that includes this expenditure.

[0076] 6. The device displays the household account book

[0077] When the user opens the household accounting app, this purchase will be reflected in the "This Month's Food Expenses" section.

[0078] In this way, the present invention allows users to manage their spending in real time without having to manually keep a household account book.

[0079] The processing flow will be explained below.

[0080] Step 1:

[0081] The user downloads the application and logs in for the first time.

[0082] The user enters an email address and password to create a new account.

[0083] Step 2:

[0084] The user registers the payment service (e.g., electronic payment service or credit card) they wish to use.

[0085] The user enters the API key and authentication information for each service.

[0086] Step 3:

[0087] The server authenticates the payment service and credit card entered by the user.

[0088] The server obtains a token to establish a secure connection with each payment service using an API.

[0089] Step 4:

[0090] The server automatically collects spending data from each payment service and credit card.

[0091] The server periodically retrieves new spending data via the API and stores it in a database.

[0092] Step 5:

[0093] The server normalizes the collected spending data into a uniform format.

[0094] The server converts the expenditure data provided in different formats into a unified format, enabling centralized management.

[0095] Step 6:

[0096] The server uses AI models to categorize the standardized spending data.

[0097] The server automatically sorts the data into categories such as "food," "transportation," and "entertainment" based on the nature of the expenditure.

[0098] Step 7:

[0099] The server automatically generates a household account book based on the classified expenditure data.

[0100] The server creates monthly and yearly household budgets and simultaneously prepares the data for visualization.

[0101] Step 8:

[0102] The user's terminal obtains the latest household accounting data from the server and displays it.

[0103] When a user opens the application, it sends a request to the server API to retrieve and display the latest household accounting information.

[0104] Step 9:

[0105] The server stores all collected spending data for a long period of time and performs big data analysis.

[0106] The server anonymizes this data and uses it to strengthen security measures and improve marketing strategies and services.

[0107] Example 1

[0108] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0109] Conventional household accounting management systems require users to manually enter expenditure information, which is time-consuming and labor-intensive. Another issue is that data input from different payment services and credit cards is not standardized, making management cumbersome. Furthermore, the accuracy of effectively classifying expenditure information is low, making automated analysis and visual generation of household accounting difficult.

[0110] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0111] In this invention, the server includes means for automatically collecting user expenditure information, means for standardizing the collected expenditure information, and means for categorizing the standardized expenditure information using an artificial intelligence model. This eliminates the need for users to manually input expenditure information and allows data from different payment services and credit cards to be managed in a unified manner. Furthermore, the use of the artificial intelligence model enables accurate classification of expenditure information, enabling automated analysis and the generation of a visual household ledger.

[0112] "Means for automatically collecting user expenditure information" refers to a function that automatically obtains data on a user's expenditures from sources such as payment services and credit cards used by the user.

[0113] "Means for standardizing collected expenditure information" refers to a function that converts expenditure data provided in different formats into a unified format, enabling centralized management.

[0114] "Means for classifying standardized expenditure information into categories using an artificial intelligence model" refers to a function that inputs standardized expenditure data into an AI model and classifies it into specific categories (e.g., food expenses, transportation expenses, entertainment expenses, etc.).

[0115] The "means for generating a household account book based on classified expenditure information" is a function that automatically creates a visually easy-to-understand household account book based on categorized expenditure data.

[0116] "Means for displaying the household account book on the user's device" refers to a function for displaying the generated household account book data on the user's device such as a smartphone or PC.

[0117] "Means of collecting expenditure data using APIs" refers to a function that automatically collects expenditure data using APIs provided by payment services and credit card companies.

[0118] "Means for accumulating and analyzing collected expenditure data as big data" refers to a function that stores large amounts of collected expenditure data in a database and uses analytical technology to analyze patterns and trends.

[0119] "Means for encrypting data to ensure the security of collected expenditure data" refers to a function that encrypts collected expenditure data to protect privacy and protects it from unauthorized access.

[0120] The present invention is a system that automatically collects and standardizes a user's expenditure information, categorizes it using an artificial intelligence model, and generates and displays a household account book. The following describes in detail the embodiments of the present invention.

[0121] Overall system configuration

[0122] The system consists of the following main components:

[0123] 1. User Device

[0124] A device on which a user enters registration information and views the household ledger. Specifically, this applies to smartphones, tablets, PCs, etc.

[0125] 2. Server

[0126] It is the central processing unit that receives data from users, collects, standardizes, and classifies expenditure information, and creates a household ledger. The server accumulates expenditure data, classifies it using artificial intelligence, and performs big data analysis.

[0127] Hardware and software used

[0128] Device: Uses a user device such as a smartphone, tablet, or PC. Users enter information and view their household accounts through these devices.

[0129] Server: Cloud servers and virtual servers are used to collect and process expenditure information, such as Amazon Web Services (AWS) and Google Cloud Platform (GCP).

[0130] Artificial intelligence model: A model for classifying spending information into categories, which is implemented using machine learning libraries such as TensorFlow and PyTorch in Python.

[0131] Basic system operation

[0132] The system works based on the following steps:

[0133] User:Register

[0134] When a user first uses the system, they create an account and register their payment service and credit card information, which allows the system to automatically collect their spending information.

[0135] Server: Data collection and authentication

[0136] The server periodically collects user spending data using the APIs of payment services and credit card companies. First, authentication is performed with the payment service or credit card company to establish a connection. For example, when a user purchases groceries, the spending information is automatically sent from the payment service to the server.

[0137] Server: Data Standardization

[0138] The server converts the collected spending data into a unified format, allowing for the centralized management of the various formats provided by different payment services and credit card companies.

[0139] Server: AI-based category determination

[0140] The server inputs the standardized expenditure data into an AI model and categorizes it into categories, such as "food," "transportation," and "entertainment." The AI ​​model references past data to improve classification accuracy.

[0141] Server: Household accounting and display

[0142] The server generates a household account book based on the categorized expenditure data and organizes it in a visually easy-to-understand format. This household account book is sent from the server to the user's terminal and can be viewed by the user.

[0143] Server: Data storage and analysis

[0144] The server encrypts and securely stores all collected spending data and analyzes it as big data. This data is used to improve marketing strategies and services. All data is also encrypted to protect user privacy.

[0145] Specific examples

[0146] For example, if a user buys groceries online and pays for them with a particular payment service, the following happens:

[0147] 1. User pays

[0148] A user purchases groceries online and completes the payment through a payment service.

[0149] 2. The server collects data

[0150] The payment service sends spending data (e.g., payment amount, purchase store, purchase details, etc.) to the server.

[0151] 3. The server standardizes the data

[0152] The server converts this spending data into a format that can be centrally managed.

[0153] 4. The server uses AI to determine the category

[0154] The server's artificial intelligence model classifies "groceries" into the "food expenses" category.

[0155] 5. The server creates the household account book

[0156] The server generates and stores an up-to-date household account book that includes this expenditure.

[0157] 6. The device displays the household account book

[0158] When the user opens the household accounting app, this purchase will be reflected in the "This Month's Food Expenses" section.

[0159] In this way, the present invention allows users to manage their spending in real time without having to manually keep a household account book.

[0160] Prompt Sentence Examples

[0161] "Describe a system that collects spending information when a user makes a new expense, standardizes it, categorizes it using an AI model, and reflects it in a household ledger. Include a specific scenario, such as a user buying groceries online."

[0162] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0163] Step 1: User Registration

[0164] Users launch a dedicated app on their own device (smartphone, tablet, PC, etc.) and register an account.

[0165] Specifically, the user enters information such as their name, email address, and password, and registers the payment service and credit card information they will use.

[0166] Input: User information (name, email address, password, etc.), payment service information, credit card information

[0167] Output: User registration information stored on the server

[0168] Step 2: Authentication and Integration

[0169] The server receives the payment service and credit card information entered by the user and sends an authentication request using each service's API.

[0170] If authentication is successful, the server establishes a secure data connection with the payment service and credit card company.

[0171] Input: User's payment service information, credit card information

[0172] Output: Authentication success message, data linking token

[0173] Step 3: Data collection

[0174] The server periodically collects spending data from the user's payment service and credit card using the established data federation.

[0175] Specifically, the server obtains expenditure data (e.g., payment amount, store of purchase, purchase details, etc.) through the API.

[0176] Input: Data link token

[0177] Output: Collected spending data

[0178] Step 4: Data Standardization

[0179] The server converts the collected spending data into a unified format.

[0180] Specifically, the system converts expenditure data provided in different formats into a format that can be centrally managed.

[0181] Input: Collected expenditure data

[0182] Output: Normalized spending data

[0183] Step 5: Categorization

[0184] The server inputs the standardized spending data into an artificial intelligence model that categorizes it into specific spending categories.

[0185] Specifically, the artificial intelligence model classifies expenditure data into categories such as "food expenses," "transportation expenses," and "entertainment expenses" based on past data.

[0186] Input: Standardized expenditure data

[0187] Output: Categorized spending data

[0188] Step 6: Create a household budget

[0189] The server generates a household account book based on the categorized expenditure data.

[0190] Specifically, it calculates the total monthly expenditures and total expenditures by category for each category, and organizes them in a visually easy-to-understand format (e.g., graphs or statistical charts).

[0191] Input: Categorized spending data

[0192] Output: Generated household accounting data

[0193] Step 7: View your household budget

[0194] When a user opens the dedicated app, the device requests the latest household accounting data from the server.

[0195] In response to a request, the server transmits the latest household accounting data to the terminal, which then displays it.

[0196] Input: A request to the server

[0197] Output: The latest household accounting data displayed on the device

[0198] Step 8: Data collection and analysis

[0199] The server encrypts and securely stores all collected spending data and analyzes it as big data.

[0200] Specifically, it analyzes data patterns and trends and uses them to improve marketing strategies and services.

[0201] Input: Collected expenditure data

[0202] Output: Analysis results, encrypted database

[0203] (Application example 1)

[0204] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0205] In modern society, many users use multiple electronic payment methods, and their spending information is scattered across multiple platforms, making it difficult to manage spending. Furthermore, it is difficult to centrally manage spending information or visually grasp spending, making it difficult to achieve efficient household management. Ensuring the security of spending data is also an important issue.

[0206] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0207] In this invention, the server includes means for automatically collecting a user's expenditure information, means for standardizing the collected expenditure information, means for categorizing the standardized expenditure information using a generative AI model, means for generating a household account book based on the categorized expenditure information, means for displaying the household account book on the user's terminal, and means for analyzing the user's expenditure information and graphically displaying the expenditure status. This allows for centralized management of expenditure information even if the user uses multiple electronic payment methods, and accurate category classification by the generative AI model enables efficient and visually easy household management. Security is also ensured at the same time.

[0208] "User Spending Information" is data regarding purchases and expenditures made through electronic payment instruments.

[0209] "Automatic collection means" refers to the process of regularly obtaining spending data from electronic payment services using APIs, etc.

[0210] A "standardization measure" is a process for converting expenditure data collected in different formats into a unified format.

[0211] A "generative AI model" is an artificial intelligence algorithm used to learn from past data and classify new data into categories.

[0212] "Categorization method" refers to the process of using a generative AI model to separate standardized expenditure data into categories such as food, transportation, and entertainment.

[0213] A "household account book" is a digital record that organizes a user's spending information by month and category, and shows total amounts, etc.

[0214] "Generation" refers to the process of creating a household ledger based on collected, standardized, and categorized expenditure data.

[0215] "Means for displaying on a terminal" refers to a function for displaying household accounting data on a device such as a smartphone or tablet owned by the user.

[0216] "Means for analyzing spending information" refers to the process of analyzing collected spending data to derive users' spending tendencies and patterns.

[0217] The "means for graphically displaying expenditure status" is a function for visually displaying the user's income and expenditure information in the form of graphs or charts.

[0218] MODE FOR CARRYING OUT THE INVENTION

[0219] The system of the present invention automatically collects user expenditure information, standardizes, categorizes, and generates and displays a household account book. To achieve this, the following main hardware and software components are used:

[0220] Hardware and software used

[0221] User devices: smartphones, tablets, PCs, etc.

[0222] Server: AWS EC2, MySQL database

[0223] Data collection tool: API integration using the requests library

[0224] Data processing library: pandas (for manipulating data frames)

[0225] AI model: TensorFlow, Scikit-learn

[0226] Visualization tool: matplotlib

[0227] Smartphone app: Flutter / Dart

[0228] Program processing

[0229] 1. Automatic collection of user spending information:

[0230] The server periodically collects spending information from the electronic payment service using API integration. It uses the requests library to access the API and retrieve spending data.

[0231] 2. Data Standardization:

[0232] The server uses pandas to convert the collected spending data into a unified format, allowing data provided in different formats to be centrally managed.

[0233] 3. Category Classification:

[0234] The server uses a generative AI model (TensorFlow and Scikit-learn) to categorize the standardized expenditure data, learning from past data and automatically sorting current data into categories such as "food," "transportation," and "entertainment."

[0235] 4. Household account book generation:

[0236] The server generates a household account book based on the classified expenditure data and stores it in a database. The household account book is organized by month and category and kept in a visually easy-to-understand format.

[0237] 5. Visualization and display of household accounts:

[0238] The server uses the matplotlib library to visualize the collected and classified data as bar graphs, pie charts, etc. The user device receives this data and displays the household ledger data through a smartphone app (Flutter / Dart).

[0239] Specific example explanation

[0240] For example, if a user buys groceries for 5000 yen online and pays for them using an electronic payment service, the process would be as follows:

[0241] 1. The user completes the payment.

[0242] 2. The server collects spending data (payment amount, purchase location, purchase details, etc.) from the electronic payment service.

[0243] 3. The server normalizes this spending data into a uniform format.

[0244] 4. The server's generative AI model classifies "groceries" into the "food expenses" category.

[0245] 5. The server generates an updated household account book including this expenditure and stores it in the database.

[0246] 6. When the user opens the household accounting app, this purchase will be reflected in the "This Month's Food Expenses" column.

[0247] Prompt Sentence Examples

[0248] "I bought groceries worth 5,000 yen online and paid for them using an electronic payment service. Please automatically add this expenditure information to my household account book."

[0249] In this way, the present invention saves the user the trouble of manually keeping a household account book, and enables efficient, real-time expenditure management.

[0250] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0251] Step 1:

[0252] Collecting user spending information

[0253] Input: Account information for multiple electronic payment services registered by the user.

[0254] How it works: The server periodically retrieves spending data from the electronic payment service via an API using the requests library.

[0255] Data processing / calculation: Receive the acquired expenditure data in JSON format and extract detailed information such as payment amount, date, and store name.

[0256] Output: Extracted expenditure data.

[0257] Step 2:

[0258] Data Standardization

[0259] Input: The expenditure data collected in Step 1.

[0260] How it works: The server uses the pandas library to convert the spending data it receives into a unified format.

[0261] Data manipulation / calculation: Transform all data items into a consistent format, fill in missing data, or change data types.

[0262] Output: Standardized expenditure data.

[0263] Step 3:

[0264] Category Classification

[0265] Input: The standardized expenditure data from step 2.

[0266] How it works: The server uses a generative AI model (TensorFlow or Scikit-learn) to classify standardized spending data into categories.

[0267] Data processing / calculation: The generative AI model analyzes the content of expenditure data and automatically classifies it into categories such as "food," "transportation," and "entertainment."

[0268] Output: Spending data broken down by category.

[0269] Step 4:

[0270] household account book generation

[0271] Input: Expense data categorized in step 3.

[0272] How it works: The server connects to a MySQL database and generates a household ledger based on categorized spending data.

[0273] Data processing / calculation: Data is aggregated by month and category and stored in a database in a visually organized format.

[0274] Output: The latest household accounting data stored in the database.

[0275] Step 5:

[0276] Visualization and display of household finances

[0277] Input: The household budget data generated in step 4.

[0278] How it works: The server uses the matplotlib library to generate image files that display the household accounting data in visual formats such as bar graphs and pie charts.

[0279] Data processing / calculation: Formatting data for graph creation and processing it in a visually understandable format.

[0280] Output: An image file of the visualized household accounting data.

[0281] Step 6:

[0282] Displaying household accounts on user devices

[0283] Input: The household budget data visualized in Step 5.

[0284] Operation: An image file of the latest household accounting data is displayed through a smartphone app (Flutter / Dart) on the user's device.

[0285] Data processing / calculation: None

[0286] Output: Household accounting data displayed on a smartphone screen.

[0287] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0288] The present invention combines a system that automatically collects and standardizes a user's spending information, categorizes it using an AI model, and generates and displays a household account book with an emotion engine that recognizes the user's emotions. The following describes in detail the embodiments of the present invention.

[0289] Overall system configuration

[0290] The system consists of the following main components:

[0291] 1. User Device

[0292] A device that allows users to enter registration information and view household accounts.

[0293] Specifically, this includes smartphones, tablets, and PCs.

[0294] 2. Server

[0295] A central processing unit that receives data from users, collects, standardizes, and categorizes expenditure information, and creates a household ledger.

[0296] It accumulates expenditure data, classifies it using AI, analyzes big data, and recognizes emotions using an emotion engine.

[0297] 3. Emotion Engine

[0298] An engine that recognizes user emotions and reflects that information in the household accounting system.

[0299] Analyzes emotions based on various sensors and user input.

[0300] Program processing overview

[0301] Start:User Registration

[0302] When a user uses the system for the first time, they create an account and register the payment service and credit card they wish to use.

[0303] Server: Authentication and collaboration

[0304] The server authenticates the payment service or credit card entered by the user and cooperates to securely collect spending data.

[0305] Server: Data collection

[0306] The server automatically collects spending data from payment services and credit card companies, which are retrieved periodically using APIs.

[0307] Server: Data Standardization

[0308] The server converts the collected expenditure data into a unified format and organizes it into a form that can be managed centrally.

[0309] Server: AI-based category determination

[0310] The server uses AI models to automatically categorize standardized spending data into categories, such as "food," "transportation," and "entertainment."

[0311] Server: Household accounting

[0312] The server automatically generates a household ledger based on the categorized expenditure data, and the ledger is saved in a format that allows monthly and yearly data to be displayed visually in an easy-to-understand manner.

[0313] User device: Household account display

[0314] The user's terminal obtains the latest household accounting data from the server and displays it in real time.

[0315] Server: Emotion recognition

[0316] The emotion engine recognizes the user's emotions in various ways, such as facial recognition, voice analysis, and text input.

[0317] Server: Emotional reflection

[0318] The server then changes how the financial data is displayed based on the user's perceived emotions, for example, by displaying less warnings and advice about spending if the user is feeling stressed.

[0319] Specific examples

[0320] For example, if a user purchases a high-value item online and pays for it using a particular payment service, the following happens:

[0321] 1. A user purchases a high-value item

[0322] A user purchases an expensive electronic device from an online shop and completes the payment using an electronic payment service.

[0323] 2. The server collects data

[0324] The electronic payment service sends expenditure data for high-value items to the server.

[0325] 3. The server standardizes the data

[0326] The server converts this spending data into a unified format.

[0327] 4. The server uses AI to determine the category

[0328] The AI ​​model classifies this expense into the "high expense" category.

[0329] 5. The server creates the household account book

[0330] The server generates and stores an updated household account book that includes this expenditure.

[0331] 6. Emotion engine recognizes emotions

[0332] When a user opens the household accounting app, the system recognizes the user's emotions through the camera and microphone. For example, if the user is feeling anxious after making a purchase, the system will recognize that emotion.

[0333] 7. The server reflects emotions

[0334] The server can then adjust how the budget is displayed based on the perceived anxiety, for example by providing less warnings about spending and more gentle advice on how to manage spending.

[0335] In this way, the present invention allows the user to save the trouble of manually keeping a household account book, manage expenditures in real time, and receive display of the household account book and advice according to emotions.

[0336] The processing flow will be explained below.

[0337] Step 1:

[0338] The user downloads the application and logs in for the first time.

[0339] The user enters an email address and password to create a new account.

[0340] Step 2:

[0341] The user registers the payment service and credit card they wish to use.

[0342] The user enters the API key and authentication information for each service.

[0343] Step 3:

[0344] The server authenticates the payment service and credit card entered by the user.

[0345] The server uses an API to establish a secure connection with each payment service and obtain an authentication token.

[0346] Step 4:

[0347] The server automatically collects spending data from each payment service and credit card company.

[0348] The server periodically retrieves new spending data via the API and stores it in a database.

[0349] Step 5:

[0350] The server normalizes the collected spending data into a uniform format.

[0351] The server converts the expenditure data provided in different formats into a unified format, enabling centralized management.

[0352] Step 6:

[0353] The server uses AI models to categorize the standardized spending data.

[0354] The server automatically sorts the data into categories such as "food," "transportation," and "entertainment" based on the nature of the expenditure.

[0355] Step 7:

[0356] The server automatically generates a household account book based on the classified expenditure data.

[0357] The server creates monthly and yearly household budgets and simultaneously prepares the data for visualization.

[0358] Step 8:

[0359] The user's terminal obtains the latest household accounting data from the server and displays it.

[0360] When a user opens the application, it sends a request to the server API to retrieve and display the latest household accounting information.

[0361] Step 9:

[0362] The server uses an emotion engine to recognize the user's emotions.

[0363] The server collects and analyzes emotional data through the camera, microphone, and user text input.

[0364] Step 10:

[0365] The server changes the way the household account book data is displayed based on the recognized user emotion.

[0366] For example, the server may tone down spending warnings and display advice in a softer tone if the user is feeling anxious.

[0367] Step 11:

[0368] The server stores all collected spending data and emotion data for a long period of time and performs big data analysis.

[0369] The server anonymizes this data and uses it to strengthen security measures and improve marketing strategies and services.

[0370] Example 2

[0371] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0372] Many modern users find it difficult to manually manage their household accounts given their busy lives. Furthermore, conventional household accounting systems simply record income and expenditures and are unable to provide personalized feedback based on the user's emotions. As a result, users are unable to manage their spending in a way that fully reflects their own spending situation and stress level, making effective use of the system difficult.

[0373] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0374] In this invention, the server includes means for automatically collecting user expenditure information, means for standardizing the collected expenditure information, means for classifying the standardized expenditure information into categories, means for generating a household account book based on the classified expenditure information, means for displaying the household account book on the user's terminal, means for recognizing the user's emotion, and means for adjusting the display method of the household account book based on the recognized emotion. This saves the user the trouble of manually keeping a household account book and enables the user to receive feedback according to their emotion.

[0375] "User expenditure information" is data relating to monetary expenditures made by a user through various payment methods.

[0376] "Standardization means" is a process for converting expenditure information collected in various formats into a unified format.

[0377] A "categorization method" is an algorithm or technique for classifying standardized expenditure information into specific categories, such as "food" or "transportation."

[0378] The "means for generating a household account book" is a process for visually or numerically creating a household account book based on the classified expenditure information.

[0379] "User terminal" refers to the device used by the user to operate the system and view information, including smartphones, tablets, PCs, etc.

[0380] "Means for recognizing emotions" refers to technology for analyzing the emotional state of a user, and includes methods such as facial recognition, voice analysis, and text analysis.

[0381] The "means for adjusting the display method" is a process for changing the display contents of the household account book, warning messages, etc., based on the recognized user's emotions.

[0382] The present invention combines a system that automatically collects and standardizes a user's spending information, categorizes it using a generative AI model, and generates and displays a household account book with an emotion engine that recognizes the user's emotions. The following describes in detail an embodiment of this system.

[0383] Overall system configuration

[0384] The system consists of the following main components:

[0385] 1. User Device

[0386] This is a device that allows users to enter registration information and view their household account book.

[0387] Specifically, this includes devices such as smartphones, tablets, and PCs.

[0388] 2. Server

[0389] It is the central processing unit that receives data from users, collects, standardizes, and classifies expenditure information, and creates a household ledger.

[0390] It accumulates expenditure data and performs big data analysis, categorizes data using a generative AI model, and recognizes emotions using an emotion engine.

[0391] 3. Emotion Engine

[0392] It is an engine that recognizes the user's emotions and reflects that information in the household accounting system.

[0393] Analyzes emotions based on various sensors and user input.

[0394] Program processing overview

[0395] The server connects with payment service and credit card APIs to automatically collect user spending information. The server periodically collects this data and standardizes it into a unified format. It then uses a generative AI model to classify the standardized spending information into categories such as "food," "transportation," and "entertainment." Based on this classified data, the server generates a visually easy-to-understand household ledger. The generated household ledger data is stored on the server and displayed in real time on the user's device.

[0396] The emotion engine also recognizes the user's emotions through the camera and microphone and adjusts the way the household budget is displayed based on this. For example, if the user is feeling stressed, the server will tone down spending warnings and display advice on managing spending in a softer tone.

[0397] Specific examples

[0398] For example, if a user purchases an expensive item online and pays for it using a specific payment service, the following process will occur.

[0399] 1. A user purchases a high-value item

[0400] A user purchases an expensive electronic device from an online shop and completes the payment using an electronic payment service.

[0401] 2. The server collects data

[0402] The electronic payment service sends spending data for high-value items to the server, which collects this data through an API.

[0403] 3. The server standardizes the data

[0404] The server converts the collected expenditure data into a unified format, such as a unified date format and a unified amount format.

[0405] 4. The server uses AI to determine the category

[0406] The generative AI model classifies this expense in the "high expense" category and stores it in a database.

[0407] 5. The server creates the household account book

[0408] The server automatically generates a household account book based on the classified expenditure data, and the household account book sends monthly and yearly expenditure data to the user's device in a format that can be visually displayed.

[0409] 6. Emotion engine recognizes emotions

[0410] When a user opens the household accounting app, the app recognizes the user's emotions through the camera and microphone.

[0411] 7. The server reflects emotions

[0412] The server then adjusts the way the household budget is displayed based on the recognized emotion, for example, if the user is feeling anxious, it will display a message that reflects that emotion.

[0413] Prompt Sentence Examples

[0414] Possible input prompts for a generative AI model include:

[0415] "Describe how you collect spending data from a user's online purchase of expensive electronics and use a generative AI model to categorize it. Also, explain how the display of the household budget changes when the user is feeling anxious."

[0416] By using this method, the present invention can provide an expense management system that takes into consideration the feelings of the user.

[0417] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0418] Step 1:

[0419] Users create an account using their smartphone or PC and register the payment service and credit card information they wish to use. Based on this input information, the system initializes the user data. As an output, the account information is saved in a database.

[0420] Step 2:

[0421] The server performs authentication using the payment service and credit card information registered by the user. This authentication process is performed using the APIs of each payment service and credit card company. It receives the user's authentication information as input and generates an authentication token as output, completing the API integration setup.

[0422] Step 3:

[0423] The server periodically collects user spending data from payment services and credit card companies via configured APIs. The collection process involves periodically sending API requests as input and storing the received spending data on the server. The output is a temporary storage of spending information in its raw form.

[0424] Step 4:

[0425] The server converts the collected expenditure data into a unified format. Specifically, it unifies information such as the date and time of expenditure, amount, and store name provided in different formats. It receives the collected expenditure data as input and generates standardized expenditure data as output.

[0426] Step 5:

[0427] The server uses a generative AI model to classify the standardized expenditure data into categories, such as automatically sorting expenses for food, transportation, entertainment, etc. It receives standardized expenditure data as input and generates categorized expenditure data as output.

[0428] Step 6:

[0429] The server generates a household account book based on the classified expenditure data. The household account book is saved in a format that allows monthly and yearly data to be displayed visually. It receives classified expenditure data as input and generates household account book data as output.

[0430] Step 7:

[0431] The terminal receives the latest household accounting data sent from the server and displays it in real time. Users can view the household accounting data on their smartphones or PCs. The terminal receives household accounting data from the server as input and displays the household accounting data on the screen as output.

[0432] Step 8:

[0433] The server's emotion engine analyzes the user's facial expressions and voice using sensors such as a camera and microphone to recognize the user's emotions. It also extracts emotions from the user's text input. It receives data from the sensors as input and generates recognized emotion data as output.

[0434] Step 9:

[0435] The server adjusts the display of the household account book based on the recognized emotion data. For example, if the user is feeling anxious, it displays a message that takes the user's emotion into consideration or advice on spending management. It receives the recognized emotion data as input and generates an adjusted household account book display as output.

[0436] This process flow allows users to effortlessly manage their spending and receive emotional feedback.

[0437] (Application example 2)

[0438] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0439] While existing household accounting systems have been successful in collecting and classifying users' spending information, they lack appropriate feedback and display adjustments based on the user's emotions, making it difficult to properly manage spending when users feel stressed or anxious. Furthermore, emotion recognition technology needs to be combined to improve the user experience.

[0440] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically collecting user expenditure information, means for standardizing the collected expenditure information, means for classifying the standardized expenditure information into categories, means for generating a household account book based on the classified expenditure information, means for recognizing the user's emotions, means for adjusting the display method of the household account book based on the recognized user emotions, and means for displaying the household account book on the user's terminal. This enables feedback and display adjustment of expenditure management according to the user's emotions, improving the user experience and enabling appropriate expenditure management with reduced stress and anxiety.

[0441] "User expenditure information" refers to data related to the purchasing activities and payments made by the user, specifically the amount used, the date and time, the place of purchase, and other information.

[0442] "Standardization" refers to the process of converting data collected in different forms and formats into a consistent format, arranging it into a unified format for easier analysis and management.

[0443] "Categorizing" means dividing data into groups with similar characteristics based on specific criteria, such as "food expenses," "transportation expenses," and "entertainment expenses."

[0444] A "household account book" refers to a record of income and expenses of an individual or household, and refers to a written or digital record used to visualize the balance of income and expenses.

[0445] "User device" refers to the electronic device used by the user to access the system and view and operate information, specifically a smartphone, tablet, or PC.

[0446] "Means for recognizing emotions" refers to technology for analyzing and determining a user's emotional state, and refers to identifying a user's emotions using methods such as facial recognition technology, voice analysis, and text analysis.

[0447] "Means for adjusting the display method" refers to technology that appropriately changes the display format and content of information depending on the user's emotional state, such as switching to a display that reduces stress or anxiety.

[0448] "Means of accumulating and analyzing big data" refers to the technology of systematically accumulating large amounts of data, analyzing it using advanced analytical techniques, and extracting useful information and patterns.

[0449] "Means of encrypting data" refers to technology that converts collected data using a specific algorithm to protect it from third parties and prevent unauthorized access or leakage.

[0450] The system of the present invention provides a means for automatically collecting, standardizing, and categorizing a user's spending information and generating a household ledger, and also has the function of recognizing the user's emotions and adjusting the display method of the household ledger based on those emotions. The detailed configuration and implementation of each means are described below.

[0451] Overall system overview

[0452] Automatically collect user spending information

[0453] The server automatically collects spending data from the electronic payment services and credit cards registered by the user, including the ability to obtain spending information through a publicly available API.

[0454] Data Standardization

[0455] The server converts the collected spending data into a unified format, allowing for consistent processing of data from different sources.

[0456] Categorized

[0457] The server uses an AI model to categorize the standardized expenditure data, automatically dividing it into categories such as "food expenses," "transportation expenses," and "entertainment expenses."

[0458] Creating and displaying household accounts

[0459] The server automatically generates a household account book based on the classified expenditure data, and the user's device retrieves the household account book in real time and displays it visually in an easy-to-understand manner.

[0460] Emotion recognition

[0461] The user's device recognizes the user's emotions through a camera and microphone, using facial recognition technology and voice analysis. Specifically, OpenCV is used to detect faces and TensorFlow is used to analyze emotions.

[0462] Emotion-based display adjustment

[0463] The server adjusts the display of the household account book and the content of notifications based on the user's recognized emotions. For example, if the user is feeling stressed, spending warnings will be displayed more subtly.

[0464] Hardware and software used

[0465] Smartphones and tablets: These are devices that allow users to view spending information and recognize emotions.

[0466] Server: Performs central processing such as data collection, standardization, classification, emotion recognition, and household accounting generation.

[0467] API: Used to collect data from electronic payment services.

[0468] OpenCV: A library for face recognition.

[0469] TensorFlow: A machine learning library for running emotion recognition models.

[0470] Specific examples

[0471] For example, if a user makes a big purchase and then opens the app feeling anxious, the system might:

[0472] 1. User purchases a high-priced item: A user purchases a high-priced electronic device from an online shop and completes the payment using an electronic payment service.

[0473] 2. Data collection and standardization: The server collects spending data from electronic payment services and converts it into a unified format.

[0474] 3. Data Classification: Using an AI model, classify this spending data into “high-spending” categories.

[0475] 4. Generation of household account book: The server generates an up-to-date household account book based on the classified expenditure data and displays it on the user's terminal.

[0476] 5. Emotion Recognition: When a user opens the household accounting app, the system recognizes the user's emotions through the device's camera and microphone. For example, if the user is feeling anxious after making a purchase, that information will be recognized by the system.

[0477] 6. Display Adjustment: The server adjusts the display of the household budget based on the perceived anxiety, specifically by softening the spending warnings and softening the advice on how to manage spending.

[0478] Example prompts to input to the generative AI model

[0479] "If a user buys a big-ticket item and then opens the app and feels anxious, how should the system display a spending warning?"

[0480] In this way, the present invention allows the user to save time and effort in manually keeping a household account book, and allows the user to manage expenses in real time while receiving optimal display and advice according to emotions.

[0481] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0482] Step 1:

[0483] The user registers their electronic payment service and credit card information to collect expenditure data. The input is the user's credit card information and authentication information for the electronic payment service. This allows the system to perform authentication and prepare to securely collect expenditure data.

[0484] Step 2:

[0485] The server periodically and automatically collects user spending information through the APIs of registered electronic payment services and credit card companies. The input is the user's authentication information and raw spending data obtained from the API. The output is the collected spending data.

[0486] Step 3:

[0487] The server standardizes the collected expenditure data into a unified format. The input is the raw expenditure data obtained in step 2. Data processing involves converting data in different formats into a consistent format. The output is standardized expenditure data.

[0488] Step 4:

[0489] The server classifies the standardized expenditure data into categories using an AI model. The input is the standardized expenditure data. For data calculation, a generative AI model is used to classify each expenditure item into categories such as "food," "transportation," and "entertainment." The output is expenditure data classified by category.

[0490] Step 5:

[0491] The server generates a household ledger based on the classified expenditure data. The input is expenditure data classified by category. The data is processed by calculating the total income and expenditure and summarizing it in household ledger format. The output is household ledger data generated in a visually easy-to-understand format.

[0492] Step 6:

[0493] The user's terminal receives the generated household accounting data and displays it on the user interface. The input is the household accounting data sent from the server. The terminal displays this in real time. The output is visual household accounting information displayed to the user.

[0494] Step 7:

[0495] The user's device uses a camera and microphone to recognize the user's emotions. The input is camera video and audio data. Specifically, the system detects faces using OpenCV and performs emotion analysis using a TensorFlow model. The output is analyzed user emotion data.

[0496] Step 8:

[0497] The server adjusts the display method of the household account book based on the recognized emotion data. The input is the user's emotion data and household account book data. Specifically, if the emotion is "anxiety," the server adjusts the display method, such as displaying spending warnings more subdued. The output is the household account book data in the adjusted display format.

[0498] Step 9:

[0499] The adjusted household accounting data is redisplayed on the user's device. The input is the adjusted household accounting data. The output is the household accounting information redisplayed to the user. The user can confirm that the display content has been adjusted to take their emotions into consideration.

[0500] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0501] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0502] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0503] [Second embodiment]

[0504] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0505] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0506] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0507] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0508] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0509] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0510] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0511] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0512] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0513] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0514] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0515] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0516] The present invention is a system that automatically collects and standardizes a user's expenditure information, categorizes it using an AI model, and generates and displays a household account book. The following describes in detail the embodiments of the present invention.

[0517] Overall system configuration

[0518] The system consists of the following main components:

[0519] 1. User Device

[0520] A device that allows users to enter registration information and view household accounts.

[0521] Specifically, this includes smartphones, tablets, and PCs.

[0522] 2. Server

[0523] A central processing unit that receives data from users, collects, standardizes, and categorizes expenditure information, and creates a household ledger.

[0524] We accumulate expenditure data, classify it using AI, and analyze big data.

[0525] Program processing overview

[0526] 1. User: Registration

[0527] When a user first uses the system, they create an account and register the payment service and credit card they use, which allows the system to collect the user's spending information appropriately.

[0528] 2. Server: Authentication and Integration

[0529] The server authenticates with the payment service or credit card company entered by the user. If authentication is successful, it securely connects with the service and prepares to periodically collect spending data.

[0530] 3. Server: Data collection

[0531] The server automatically collects spending data from the user's payment services and credit card companies. This is done periodically using APIs. For example, when John buys groceries, his spending information is automatically sent to the server.

[0532] 4. Server: Data Standardization

[0533] The server converts the collected spending data into a unified format, processing payment services and credit card data provided in different formats into a format that can be managed centrally.

[0534] 5. Server: AI-based category determination

[0535] The server uses an AI model to categorize the standardized spending data, such as into categories like "food," "transportation," and "entertainment." The AI ​​model learns from past data and improves its classification accuracy.

[0536] 6. Server: Household accounting

[0537] The server automatically generates a household ledger for the user based on the classified expenditure data. The data is organized by month and category so that expenditures can be seen at a glance, and is saved in a visually easy-to-understand format.

[0538] 7. Terminal: Household account display

[0539] The user's device retrieves the latest household accounting data from the server and displays it. For example, when a user opens the app, the latest expenditure items and their categories, monthly expenditure totals, etc. are displayed.

[0540] 8. Server: Data storage and analysis

[0541] The server stores the collected spending data and analyzes it as big data. This data is used to improve marketing strategies and services. To protect user privacy, all data is encrypted and stored securely.

[0542] Specific examples

[0543] For example, if a user buys groceries online and pays for them with a particular payment service, the following happens:

[0544] 1. User pays

[0545] A user purchases groceries online and completes the payment through a payment service.

[0546] 2. The server collects data

[0547] The payment service sends spending data (e.g., payment amount, purchase store, purchase details, etc.) to the server.

[0548] 3. The server standardizes the data

[0549] The server converts this spending data into a format that can be centrally managed.

[0550] 4. The server uses AI to determine the category

[0551] The server's AI model classifies "groceries" into the "food expenses" category.

[0552] 5. The server creates the household account book

[0553] The server generates and stores an up-to-date household account book that includes this expenditure.

[0554] 6. The device displays the household account book

[0555] When the user opens the household accounting app, this purchase will be reflected in the "This Month's Food Expenses" section.

[0556] In this way, the present invention allows users to manage their spending in real time without having to manually keep a household account book.

[0557] The processing flow will be explained below.

[0558] Step 1:

[0559] The user downloads the application and logs in for the first time.

[0560] The user enters an email address and password to create a new account.

[0561] Step 2:

[0562] The user registers the payment service (e.g., electronic payment service or credit card) they wish to use.

[0563] The user enters the API key and authentication information for each service.

[0564] Step 3:

[0565] The server authenticates the payment service and credit card entered by the user.

[0566] The server obtains a token to establish a secure connection with each payment service using an API.

[0567] Step 4:

[0568] The server automatically collects spending data from each payment service and credit card.

[0569] The server periodically retrieves new spending data via the API and stores it in a database.

[0570] Step 5:

[0571] The server normalizes the collected spending data into a uniform format.

[0572] The server converts the expenditure data provided in different formats into a unified format, enabling centralized management.

[0573] Step 6:

[0574] The server uses AI models to categorize the standardized spending data.

[0575] The server automatically sorts the data into categories such as "food," "transportation," and "entertainment" based on the nature of the expenditure.

[0576] Step 7:

[0577] The server automatically generates a household account book based on the classified expenditure data.

[0578] The server creates monthly and yearly household budgets and simultaneously prepares the data for visualization.

[0579] Step 8:

[0580] The user's terminal obtains the latest household accounting data from the server and displays it.

[0581] When a user opens the application, it sends a request to the server API to retrieve and display the latest household accounting information.

[0582] Step 9:

[0583] The server stores all collected spending data for a long period of time and performs big data analysis.

[0584] The server anonymizes this data and uses it to strengthen security measures and improve marketing strategies and services.

[0585] Example 1

[0586] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0587] Conventional household accounting management systems require users to manually enter expenditure information, which is time-consuming and labor-intensive. Another issue is that data input from different payment services and credit cards is not standardized, making management cumbersome. Furthermore, the accuracy of effectively classifying expenditure information is low, making automated analysis and visual generation of household accounting difficult.

[0588] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0589] In this invention, the server includes means for automatically collecting user expenditure information, means for standardizing the collected expenditure information, and means for categorizing the standardized expenditure information using an artificial intelligence model. This eliminates the need for users to manually input expenditure information and allows data from different payment services and credit cards to be managed in a unified manner. Furthermore, the use of the artificial intelligence model enables accurate classification of expenditure information, enabling automated analysis and the generation of a visual household ledger.

[0590] "Means for automatically collecting user expenditure information" refers to a function that automatically obtains data on a user's expenditures from sources such as payment services and credit cards used by the user.

[0591] "Means for standardizing collected expenditure information" refers to a function that converts expenditure data provided in different formats into a unified format, enabling centralized management.

[0592] "Means for classifying standardized expenditure information into categories using an artificial intelligence model" refers to a function that inputs standardized expenditure data into an AI model and classifies it into specific categories (e.g., food expenses, transportation expenses, entertainment expenses, etc.).

[0593] The "means for generating a household account book based on classified expenditure information" is a function that automatically creates a visually easy-to-understand household account book based on categorized expenditure data.

[0594] "Means for displaying the household account book on the user's device" refers to a function for displaying the generated household account book data on the user's device such as a smartphone or PC.

[0595] "Means of collecting expenditure data using APIs" refers to a function that automatically collects expenditure data using APIs provided by payment services and credit card companies.

[0596] "Means for accumulating and analyzing collected expenditure data as big data" refers to a function that stores large amounts of collected expenditure data in a database and uses analytical technology to analyze patterns and trends.

[0597] "Means for encrypting data to ensure the security of collected expenditure data" refers to a function that encrypts collected expenditure data to protect privacy and protects it from unauthorized access.

[0598] The present invention is a system that automatically collects and standardizes a user's expenditure information, categorizes it using an artificial intelligence model, and generates and displays a household account book. The following describes in detail the embodiments of the present invention.

[0599] Overall system configuration

[0600] The system consists of the following main components:

[0601] 1. User Device

[0602] A device on which a user enters registration information and views the household ledger. Specifically, this applies to smartphones, tablets, PCs, etc.

[0603] 2. Server

[0604] It is the central processing unit that receives data from users, collects, standardizes, and classifies expenditure information, and creates a household ledger. The server accumulates expenditure data, classifies it using artificial intelligence, and performs big data analysis.

[0605] Hardware and software used

[0606] Device: Uses a user device such as a smartphone, tablet, or PC. Users enter information and view their household accounts through these devices.

[0607] Server: Cloud servers and virtual servers are used to collect and process expenditure information, such as Amazon Web Services (AWS) and Google Cloud Platform (GCP).

[0608] Artificial intelligence model: A model for classifying spending information into categories, which is implemented using machine learning libraries such as TensorFlow and PyTorch in Python.

[0609] Basic system operation

[0610] The system works based on the following steps:

[0611] User:Register

[0612] When a user first uses the system, they create an account and register their payment service and credit card information, which allows the system to automatically collect their spending information.

[0613] Server: Data collection and authentication

[0614] The server periodically collects user spending data using the APIs of payment services and credit card companies. First, authentication is performed with the payment service or credit card company to establish a connection. For example, when a user purchases groceries, the spending information is automatically sent from the payment service to the server.

[0615] Server: Data Standardization

[0616] The server converts the collected spending data into a unified format, allowing for the centralized management of the various formats provided by different payment services and credit card companies.

[0617] Server: AI-based category determination

[0618] The server inputs the standardized expenditure data into an AI model and categorizes it into categories, such as "food," "transportation," and "entertainment." The AI ​​model references past data to improve classification accuracy.

[0619] Server: Household accounting and display

[0620] The server generates a household account book based on the categorized expenditure data and organizes it in a visually easy-to-understand format. This household account book is sent from the server to the user's terminal and can be viewed by the user.

[0621] Server: Data storage and analysis

[0622] The server encrypts and securely stores all collected spending data and analyzes it as big data. This data is used to improve marketing strategies and services. All data is also encrypted to protect user privacy.

[0623] Specific examples

[0624] For example, if a user buys groceries online and pays for them with a particular payment service, the following happens:

[0625] 1. User pays

[0626] A user purchases groceries online and completes the payment through a payment service.

[0627] 2. The server collects data

[0628] The payment service sends spending data (e.g., payment amount, purchase store, purchase details, etc.) to the server.

[0629] 3. The server standardizes the data

[0630] The server converts this spending data into a format that can be centrally managed.

[0631] 4. The server uses AI to determine the category

[0632] The server's artificial intelligence model classifies "groceries" into the "food expenses" category.

[0633] 5. The server creates the household account book

[0634] The server generates and stores an up-to-date household account book that includes this expenditure.

[0635] 6. The device displays the household account book

[0636] When the user opens the household accounting app, this purchase will be reflected in the "This Month's Food Expenses" section.

[0637] In this way, the present invention allows users to manage their spending in real time without having to manually keep a household account book.

[0638] Prompt Sentence Examples

[0639] "Describe a system that collects spending information when a user makes a new expense, standardizes it, categorizes it using an AI model, and reflects it in a household ledger. Include a specific scenario, such as a user buying groceries online."

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

[0641] Step 1: User Registration

[0642] Users launch a dedicated app on their own device (smartphone, tablet, PC, etc.) and register an account.

[0643] Specifically, the user enters information such as their name, email address, and password, and registers the payment service and credit card information they will use.

[0644] Input: User information (name, email address, password, etc.), payment service information, credit card information

[0645] Output: User registration information stored on the server

[0646] Step 2: Authentication and Integration

[0647] The server receives the payment service and credit card information entered by the user and sends an authentication request using each service's API.

[0648] If authentication is successful, the server establishes a secure data connection with the payment service and credit card company.

[0649] Input: User's payment service information, credit card information

[0650] Output: Authentication success message, data linking token

[0651] Step 3: Data collection

[0652] The server periodically collects spending data from the user's payment service and credit card using the established data federation.

[0653] Specifically, the server obtains expenditure data (e.g., payment amount, store of purchase, purchase details, etc.) through the API.

[0654] Input: Data link token

[0655] Output: Collected spending data

[0656] Step 4: Data Standardization

[0657] The server converts the collected spending data into a unified format.

[0658] Specifically, the system converts expenditure data provided in different formats into a format that can be centrally managed.

[0659] Input: Collected expenditure data

[0660] Output: Normalized spending data

[0661] Step 5: Categorization

[0662] The server inputs the standardized spending data into an artificial intelligence model that categorizes it into specific spending categories.

[0663] Specifically, the artificial intelligence model classifies expenditure data into categories such as "food expenses," "transportation expenses," and "entertainment expenses" based on past data.

[0664] Input: Standardized expenditure data

[0665] Output: Categorized spending data

[0666] Step 6: Create a household budget

[0667] The server generates a household account book based on the categorized expenditure data.

[0668] Specifically, it calculates the total monthly expenditures and total expenditures by category for each category, and organizes them in a visually easy-to-understand format (e.g., graphs or statistical charts).

[0669] Input: Categorized spending data

[0670] Output: Generated household accounting data

[0671] Step 7: View your household budget

[0672] When a user opens the dedicated app, the device requests the latest household accounting data from the server.

[0673] In response to a request, the server transmits the latest household accounting data to the terminal, which then displays it.

[0674] Input: A request to the server

[0675] Output: The latest household accounting data displayed on the device

[0676] Step 8: Data collection and analysis

[0677] The server encrypts and securely stores all collected spending data and analyzes it as big data.

[0678] Specifically, it analyzes data patterns and trends and uses them to improve marketing strategies and services.

[0679] Input: Collected expenditure data

[0680] Output: Analysis results, encrypted database

[0681] (Application example 1)

[0682] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0683] In modern society, many users use multiple electronic payment methods, and their spending information is scattered across multiple platforms, making it difficult to manage spending. Furthermore, it is difficult to centrally manage spending information or visually grasp spending, making it difficult to achieve efficient household management. Ensuring the security of spending data is also an important issue.

[0684] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0685] In this invention, the server includes means for automatically collecting a user's expenditure information, means for standardizing the collected expenditure information, means for categorizing the standardized expenditure information using a generative AI model, means for generating a household account book based on the categorized expenditure information, means for displaying the household account book on the user's terminal, and means for analyzing the user's expenditure information and graphically displaying the expenditure status. This allows for centralized management of expenditure information even if the user uses multiple electronic payment methods, and accurate category classification by the generative AI model enables efficient and visually easy household management. Security is also ensured at the same time.

[0686] "User Spending Information" is data regarding purchases and expenditures made through electronic payment instruments.

[0687] "Automatic collection means" refers to the process of regularly obtaining spending data from electronic payment services using APIs, etc.

[0688] A "standardization measure" is a process for converting expenditure data collected in different formats into a unified format.

[0689] A "generative AI model" is an artificial intelligence algorithm used to learn from past data and classify new data into categories.

[0690] "Categorization method" refers to the process of using a generative AI model to separate standardized expenditure data into categories such as food, transportation, and entertainment.

[0691] A "household account book" is a digital record that organizes a user's spending information by month and category, and shows total amounts, etc.

[0692] "Generation" refers to the process of creating a household ledger based on collected, standardized, and categorized expenditure data.

[0693] "Means for displaying on a terminal" refers to a function for displaying household accounting data on a device such as a smartphone or tablet owned by the user.

[0694] "Means for analyzing spending information" refers to the process of analyzing collected spending data to derive users' spending tendencies and patterns.

[0695] The "means for graphically displaying expenditure status" is a function for visually displaying the user's income and expenditure information in the form of graphs or charts.

[0696] MODE FOR CARRYING OUT THE INVENTION

[0697] The system of the present invention automatically collects user expenditure information, standardizes, categorizes, and generates and displays a household account book. To achieve this, the following main hardware and software components are used:

[0698] Hardware and software used

[0699] User devices: smartphones, tablets, PCs, etc.

[0700] Server: AWS EC2, MySQL database

[0701] Data collection tool: API integration using the requests library

[0702] Data processing library: pandas (for manipulating data frames)

[0703] AI model: TensorFlow, Scikit-learn

[0704] Visualization tool: matplotlib

[0705] Smartphone app: Flutter / Dart

[0706] Program processing

[0707] 1. Automatic collection of user spending information:

[0708] The server periodically collects spending information from the electronic payment service using API integration. It uses the requests library to access the API and retrieve spending data.

[0709] 2. Data Standardization:

[0710] The server uses pandas to convert the collected spending data into a unified format, allowing data provided in different formats to be centrally managed.

[0711] 3. Category Classification:

[0712] The server uses a generative AI model (TensorFlow and Scikit-learn) to categorize the standardized expenditure data, learning from past data and automatically sorting current data into categories such as "food," "transportation," and "entertainment."

[0713] 4. Household account book generation:

[0714] The server generates a household account book based on the classified expenditure data and stores it in a database. The household account book is organized by month and category and kept in a visually easy-to-understand format.

[0715] 5. Visualization and display of household accounts:

[0716] The server uses the matplotlib library to visualize the collected and classified data as bar graphs, pie charts, etc. The user device receives this data and displays the household ledger data through a smartphone app (Flutter / Dart).

[0717] Specific example explanation

[0718] For example, if a user buys groceries for 5000 yen online and pays for them using an electronic payment service, the process would be as follows:

[0719] 1. The user completes the payment.

[0720] 2. The server collects spending data (payment amount, purchase location, purchase details, etc.) from the electronic payment service.

[0721] 3. The server normalizes this spending data into a uniform format.

[0722] 4. The server's generative AI model classifies "groceries" into the "food expenses" category.

[0723] 5. The server generates an updated household account book including this expenditure and stores it in the database.

[0724] 6. When the user opens the household accounting app, this purchase will be reflected in the "This Month's Food Expenses" column.

[0725] Prompt Sentence Examples

[0726] "I bought groceries worth 5,000 yen online and paid for them using an electronic payment service. Please automatically add this expenditure information to my household account book."

[0727] In this way, the present invention saves the user the trouble of manually keeping a household account book, and enables efficient, real-time expenditure management.

[0728] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0729] Step 1:

[0730] Collecting user spending information

[0731] Input: Account information for multiple electronic payment services registered by the user.

[0732] How it works: The server periodically retrieves spending data from the electronic payment service via an API using the requests library.

[0733] Data processing / calculation: Receive the acquired expenditure data in JSON format and extract detailed information such as payment amount, date, and store name.

[0734] Output: Extracted expenditure data.

[0735] Step 2:

[0736] Data Standardization

[0737] Input: The expenditure data collected in Step 1.

[0738] How it works: The server uses the pandas library to convert the spending data it receives into a unified format.

[0739] Data manipulation / calculation: Transform all data items into a consistent format, fill in missing data, or change data types.

[0740] Output: Standardized expenditure data.

[0741] Step 3:

[0742] Category Classification

[0743] Input: The standardized expenditure data from step 2.

[0744] How it works: The server uses a generative AI model (TensorFlow or Scikit-learn) to classify standardized spending data into categories.

[0745] Data processing / calculation: The generative AI model analyzes the content of expenditure data and automatically classifies it into categories such as "food," "transportation," and "entertainment."

[0746] Output: Spending data broken down by category.

[0747] Step 4:

[0748] household account book generation

[0749] Input: Expense data categorized in step 3.

[0750] How it works: The server connects to a MySQL database and generates a household ledger based on categorized spending data.

[0751] Data processing / calculation: Data is aggregated by month and category and stored in a database in a visually organized format.

[0752] Output: The latest household accounting data stored in the database.

[0753] Step 5:

[0754] Visualization and display of household finances

[0755] Input: The household budget data generated in step 4.

[0756] How it works: The server uses the matplotlib library to generate image files that display the household accounting data in visual formats such as bar graphs and pie charts.

[0757] Data processing / calculation: Formatting data for graph creation and processing it in a visually understandable format.

[0758] Output: An image file of the visualized household accounting data.

[0759] Step 6:

[0760] Displaying household accounts on user devices

[0761] Input: The household budget data visualized in Step 5.

[0762] Operation: An image file of the latest household accounting data is displayed through a smartphone app (Flutter / Dart) on the user's device.

[0763] Data processing / calculation: None

[0764] Output: Household accounting data displayed on a smartphone screen.

[0765] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0766] The present invention combines a system that automatically collects and standardizes a user's spending information, categorizes it using an AI model, and generates and displays a household account book with an emotion engine that recognizes the user's emotions. The following describes in detail the embodiments of the present invention.

[0767] Overall system configuration

[0768] The system consists of the following main components:

[0769] 1. User Device

[0770] A device that allows users to enter registration information and view household accounts.

[0771] Specifically, this includes smartphones, tablets, and PCs.

[0772] 2. Server

[0773] A central processing unit that receives data from users, collects, standardizes, and categorizes expenditure information, and creates a household ledger.

[0774] It accumulates expenditure data, classifies it using AI, analyzes big data, and recognizes emotions using an emotion engine.

[0775] 3. Emotion Engine

[0776] An engine that recognizes user emotions and reflects that information in the household accounting system.

[0777] Analyzes emotions based on various sensors and user input.

[0778] Program processing overview

[0779] Start:User Registration

[0780] When a user uses the system for the first time, they create an account and register the payment service and credit card they wish to use.

[0781] Server: Authentication and collaboration

[0782] The server authenticates the payment service or credit card entered by the user and cooperates to securely collect spending data.

[0783] Server: Data collection

[0784] The server automatically collects spending data from payment services and credit card companies, which are retrieved periodically using APIs.

[0785] Server: Data Standardization

[0786] The server converts the collected expenditure data into a unified format and organizes it into a form that can be managed centrally.

[0787] Server: AI-based category determination

[0788] The server uses AI models to automatically categorize standardized spending data into categories, such as "food," "transportation," and "entertainment."

[0789] Server: Household accounting

[0790] The server automatically generates a household ledger based on the categorized expenditure data, and the ledger is saved in a format that allows monthly and yearly data to be displayed visually in an easy-to-understand manner.

[0791] User device: Household account display

[0792] The user's terminal obtains the latest household accounting data from the server and displays it in real time.

[0793] Server: Emotion recognition

[0794] The emotion engine recognizes the user's emotions in various ways, such as facial recognition, voice analysis, and text input.

[0795] Server: Emotional reflection

[0796] The server then changes how the financial data is displayed based on the user's perceived emotions, for example, by displaying less warnings and advice about spending if the user is feeling stressed.

[0797] Specific examples

[0798] For example, if a user purchases a high-value item online and pays for it using a particular payment service, the following happens:

[0799] 1. A user purchases a high-value item

[0800] A user purchases an expensive electronic device from an online shop and completes the payment using an electronic payment service.

[0801] 2. The server collects data

[0802] The electronic payment service sends expenditure data for high-value items to the server.

[0803] 3. The server standardizes the data

[0804] The server converts this spending data into a unified format.

[0805] 4. The server uses AI to determine the category

[0806] The AI ​​model classifies this expense into the "high expense" category.

[0807] 5. The server creates the household account book

[0808] The server generates and stores an updated household account book that includes this expenditure.

[0809] 6. Emotion engine recognizes emotions

[0810] When a user opens the household accounting app, the system recognizes the user's emotions through the camera and microphone. For example, if the user is feeling anxious after making a purchase, the system will recognize that emotion.

[0811] 7. The server reflects emotions

[0812] The server can then adjust how the budget is displayed based on the perceived anxiety, for example by providing less warnings about spending and more gentle advice on how to manage spending.

[0813] In this way, the present invention allows the user to save the trouble of manually keeping a household account book, manage expenditures in real time, and receive display of the household account book and advice according to emotions.

[0814] The processing flow will be explained below.

[0815] Step 1:

[0816] The user downloads the application and logs in for the first time.

[0817] The user enters an email address and password to create a new account.

[0818] Step 2:

[0819] The user registers the payment service and credit card they wish to use.

[0820] The user enters the API key and authentication information for each service.

[0821] Step 3:

[0822] The server authenticates the payment service and credit card entered by the user.

[0823] The server uses an API to establish a secure connection with each payment service and obtain an authentication token.

[0824] Step 4:

[0825] The server automatically collects spending data from each payment service and credit card company.

[0826] The server periodically retrieves new spending data via the API and stores it in a database.

[0827] Step 5:

[0828] The server normalizes the collected spending data into a uniform format.

[0829] The server converts the expenditure data provided in different formats into a unified format, enabling centralized management.

[0830] Step 6:

[0831] The server uses AI models to categorize the standardized spending data.

[0832] The server automatically sorts the data into categories such as "food," "transportation," and "entertainment" based on the nature of the expenditure.

[0833] Step 7:

[0834] The server automatically generates a household account book based on the classified expenditure data.

[0835] The server creates monthly and yearly household budgets and simultaneously prepares the data for visualization.

[0836] Step 8:

[0837] The user's terminal obtains the latest household accounting data from the server and displays it.

[0838] When a user opens the application, it sends a request to the server API to retrieve and display the latest household accounting information.

[0839] Step 9:

[0840] The server uses an emotion engine to recognize the user's emotions.

[0841] The server collects and analyzes emotional data through the camera, microphone, and user text input.

[0842] Step 10:

[0843] The server changes the way the household account book data is displayed based on the recognized user emotion.

[0844] For example, the server may tone down spending warnings and display advice in a softer tone if the user is feeling anxious.

[0845] Step 11:

[0846] The server stores all collected spending data and emotion data for a long period of time and performs big data analysis.

[0847] The server anonymizes this data and uses it to strengthen security measures and improve marketing strategies and services.

[0848] Example 2

[0849] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0850] Many modern users find it difficult to manually manage their household accounts given their busy lives. Furthermore, conventional household accounting systems simply record income and expenditures and are unable to provide personalized feedback based on the user's emotions. As a result, users are unable to manage their spending in a way that fully reflects their own spending situation and stress level, making effective use of the system difficult.

[0851] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0852] In this invention, the server includes means for automatically collecting user expenditure information, means for standardizing the collected expenditure information, means for classifying the standardized expenditure information into categories, means for generating a household account book based on the classified expenditure information, means for displaying the household account book on the user's terminal, means for recognizing the user's emotion, and means for adjusting the display method of the household account book based on the recognized emotion. This saves the user the trouble of manually keeping a household account book and enables the user to receive feedback according to their emotion.

[0853] "User expenditure information" is data relating to monetary expenditures made by a user through various payment methods.

[0854] "Standardization means" is a process for converting expenditure information collected in various formats into a unified format.

[0855] A "categorization method" is an algorithm or technique for classifying standardized expenditure information into specific categories, such as "food" or "transportation."

[0856] The "means for generating a household account book" is a process for visually or numerically creating a household account book based on the classified expenditure information.

[0857] "User terminal" refers to the device used by the user to operate the system and view information, including smartphones, tablets, PCs, etc.

[0858] "Means for recognizing emotions" refers to technology for analyzing the emotional state of a user, and includes methods such as facial recognition, voice analysis, and text analysis.

[0859] The "means for adjusting the display method" is a process for changing the display contents of the household account book, warning messages, etc., based on the recognized user's emotions.

[0860] The present invention combines a system that automatically collects and standardizes a user's spending information, categorizes it using a generative AI model, and generates and displays a household account book with an emotion engine that recognizes the user's emotions. The following describes in detail an embodiment of this system.

[0861] Overall system configuration

[0862] The system consists of the following main components:

[0863] 1. User Device

[0864] This is a device that allows users to enter registration information and view their household account book.

[0865] Specifically, this includes devices such as smartphones, tablets, and PCs.

[0866] 2. Server

[0867] It is the central processing unit that receives data from users, collects, standardizes, and classifies expenditure information, and creates a household ledger.

[0868] It accumulates expenditure data and performs big data analysis, categorizes data using a generative AI model, and recognizes emotions using an emotion engine.

[0869] 3. Emotion Engine

[0870] It is an engine that recognizes the user's emotions and reflects that information in the household accounting system.

[0871] Analyzes emotions based on various sensors and user input.

[0872] Program processing overview

[0873] The server connects with payment service and credit card APIs to automatically collect user spending information. The server periodically collects this data and standardizes it into a unified format. It then uses a generative AI model to classify the standardized spending information into categories such as "food," "transportation," and "entertainment." Based on this classified data, the server generates a visually easy-to-understand household ledger. The generated household ledger data is stored on the server and displayed in real time on the user's device.

[0874] The emotion engine also recognizes the user's emotions through the camera and microphone and adjusts the way the household budget is displayed based on this. For example, if the user is feeling stressed, the server will tone down spending warnings and display advice on managing spending in a softer tone.

[0875] Specific examples

[0876] For example, if a user purchases an expensive item online and pays for it using a specific payment service, the following process will occur.

[0877] 1. A user purchases a high-value item

[0878] A user purchases an expensive electronic device from an online shop and completes the payment using an electronic payment service.

[0879] 2. The server collects data

[0880] The electronic payment service sends spending data for high-value items to the server, which collects this data through an API.

[0881] 3. The server standardizes the data

[0882] The server converts the collected expenditure data into a unified format, such as a unified date format and a unified amount format.

[0883] 4. The server uses AI to determine the category

[0884] The generative AI model classifies this expense in the "high expense" category and stores it in a database.

[0885] 5. The server creates the household account book

[0886] The server automatically generates a household account book based on the classified expenditure data, and the household account book sends monthly and yearly expenditure data to the user's device in a format that can be visually displayed.

[0887] 6. Emotion engine recognizes emotions

[0888] When a user opens the household accounting app, the app recognizes the user's emotions through the camera and microphone.

[0889] 7. The server reflects emotions

[0890] The server then adjusts the way the household budget is displayed based on the recognized emotion, for example, if the user is feeling anxious, it will display a message that reflects that emotion.

[0891] Prompt Sentence Examples

[0892] Possible input prompts for a generative AI model include:

[0893] "Describe how you collect spending data from a user's online purchase of expensive electronics and use a generative AI model to categorize it. Also, explain how the display of the household budget changes when the user is feeling anxious."

[0894] By using this method, the present invention can provide an expense management system that takes into consideration the feelings of the user.

[0895] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0896] Step 1:

[0897] Users create an account using their smartphone or PC and register the payment service and credit card information they wish to use. Based on this input information, the system initializes the user data. As an output, the account information is saved in a database.

[0898] Step 2:

[0899] The server performs authentication using the payment service and credit card information registered by the user. This authentication process is performed using the APIs of each payment service and credit card company. It receives the user's authentication information as input and generates an authentication token as output, completing the API integration setup.

[0900] Step 3:

[0901] The server periodically collects user spending data from payment services and credit card companies via configured APIs. The collection process involves periodically sending API requests as input and storing the received spending data on the server. The output is a temporary storage of spending information in its raw form.

[0902] Step 4:

[0903] The server converts the collected expenditure data into a unified format. Specifically, it unifies information such as the date and time of expenditure, amount, and store name provided in different formats. It receives the collected expenditure data as input and generates standardized expenditure data as output.

[0904] Step 5:

[0905] The server uses a generative AI model to classify the standardized expenditure data into categories, such as automatically sorting expenses for food, transportation, entertainment, etc. It receives standardized expenditure data as input and generates categorized expenditure data as output.

[0906] Step 6:

[0907] The server generates a household account book based on the classified expenditure data. The household account book is saved in a format that allows monthly and yearly data to be displayed visually. It receives classified expenditure data as input and generates household account book data as output.

[0908] Step 7:

[0909] The terminal receives the latest household accounting data sent from the server and displays it in real time. Users can view the household accounting data on their smartphones or PCs. The terminal receives household accounting data from the server as input and displays the household accounting data on the screen as output.

[0910] Step 8:

[0911] The server's emotion engine analyzes the user's facial expressions and voice using sensors such as a camera and microphone to recognize the user's emotions. It also extracts emotions from the user's text input. It receives data from the sensors as input and generates recognized emotion data as output.

[0912] Step 9:

[0913] The server adjusts the display of the household account book based on the recognized emotion data. For example, if the user is feeling anxious, it displays a message that takes the user's emotion into consideration or advice on spending management. It receives the recognized emotion data as input and generates an adjusted household account book display as output.

[0914] This process flow allows users to effortlessly manage their spending and receive emotional feedback.

[0915] (Application example 2)

[0916] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0917] While existing household accounting systems have been successful in collecting and classifying users' spending information, they lack appropriate feedback and display adjustments based on the user's emotions, making it difficult to properly manage spending when users feel stressed or anxious. Furthermore, emotion recognition technology needs to be combined to improve the user experience.

[0918] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically collecting user expenditure information, means for standardizing the collected expenditure information, means for classifying the standardized expenditure information into categories, means for generating a household account book based on the classified expenditure information, means for recognizing the user's emotions, means for adjusting the display method of the household account book based on the recognized user emotions, and means for displaying the household account book on the user's terminal. This enables feedback and display adjustment of expenditure management according to the user's emotions, improving the user experience and enabling appropriate expenditure management with reduced stress and anxiety.

[0919] "User expenditure information" refers to data related to the purchasing activities and payments made by the user, specifically the amount used, the date and time, the place of purchase, and other information.

[0920] "Standardization" refers to the process of converting data collected in different forms and formats into a consistent format, arranging it into a unified format for easier analysis and management.

[0921] "Categorizing" means dividing data into groups with similar characteristics based on specific criteria, such as "food expenses," "transportation expenses," and "entertainment expenses."

[0922] A "household account book" refers to a record of income and expenses of an individual or household, and refers to a written or digital record used to visualize the balance of income and expenses.

[0923] "User device" refers to the electronic device used by the user to access the system and view and operate information, specifically a smartphone, tablet, or PC.

[0924] "Means for recognizing emotions" refers to technology for analyzing and determining a user's emotional state, and refers to identifying a user's emotions using methods such as facial recognition technology, voice analysis, and text analysis.

[0925] "Means for adjusting the display method" refers to technology that appropriately changes the display format and content of information depending on the user's emotional state, such as switching to a display that reduces stress or anxiety.

[0926] "Means of accumulating and analyzing big data" refers to the technology of systematically accumulating large amounts of data, analyzing it using advanced analytical techniques, and extracting useful information and patterns.

[0927] "Means of encrypting data" refers to technology that converts collected data using a specific algorithm to protect it from third parties and prevent unauthorized access or leakage.

[0928] The system of the present invention provides a means for automatically collecting, standardizing, and categorizing a user's spending information and generating a household ledger, and also has the function of recognizing the user's emotions and adjusting the display method of the household ledger based on those emotions. The detailed configuration and implementation of each means are described below.

[0929] Overall system overview

[0930] Automatically collect user spending information

[0931] The server automatically collects spending data from the electronic payment services and credit cards registered by the user, including the ability to obtain spending information through a publicly available API.

[0932] Data Standardization

[0933] The server converts the collected spending data into a unified format, allowing for consistent processing of data from different sources.

[0934] Categorized

[0935] The server uses an AI model to categorize the standardized expenditure data, automatically dividing it into categories such as "food expenses," "transportation expenses," and "entertainment expenses."

[0936] Creating and displaying household accounts

[0937] The server automatically generates a household account book based on the classified expenditure data, and the user's device retrieves the household account book in real time and displays it visually in an easy-to-understand manner.

[0938] Emotion recognition

[0939] The user's device recognizes the user's emotions through a camera and microphone, using facial recognition technology and voice analysis. Specifically, OpenCV is used to detect faces and TensorFlow is used to analyze emotions.

[0940] Emotion-based display adjustment

[0941] The server adjusts the display of the household account book and the content of notifications based on the user's recognized emotions. For example, if the user is feeling stressed, spending warnings will be displayed more subtly.

[0942] Hardware and software used

[0943] Smartphones and tablets: These are devices that allow users to view spending information and recognize emotions.

[0944] Server: Performs central processing such as data collection, standardization, classification, emotion recognition, and household accounting generation.

[0945] API: Used to collect data from electronic payment services.

[0946] OpenCV: A library for face recognition.

[0947] TensorFlow: A machine learning library for running emotion recognition models.

[0948] Specific examples

[0949] For example, if a user makes a big purchase and then opens the app feeling anxious, the system might:

[0950] 1. User purchases a high-priced item: A user purchases a high-priced electronic device from an online shop and completes the payment using an electronic payment service.

[0951] 2. Data collection and standardization: The server collects spending data from electronic payment services and converts it into a unified format.

[0952] 3. Data Classification: Using an AI model, classify this spending data into “high-spending” categories.

[0953] 4. Generation of household account book: The server generates an up-to-date household account book based on the classified expenditure data and displays it on the user's terminal.

[0954] 5. Emotion Recognition: When a user opens the household accounting app, the system recognizes the user's emotions through the device's camera and microphone. For example, if the user is feeling anxious after making a purchase, that information will be recognized by the system.

[0955] 6. Display Adjustment: The server adjusts the display of the household budget based on the perceived anxiety, specifically by softening the spending warnings and softening the advice on how to manage spending.

[0956] Example prompts to input to the generative AI model

[0957] "If a user buys a big-ticket item and then opens the app and feels anxious, how should the system display a spending warning?"

[0958] In this way, the present invention allows the user to save time and effort in manually keeping a household account book, and allows the user to manage expenses in real time while receiving optimal display and advice according to emotions.

[0959] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0960] Step 1:

[0961] The user registers their electronic payment service and credit card information to collect expenditure data. The input is the user's credit card information and authentication information for the electronic payment service. This allows the system to perform authentication and prepare to securely collect expenditure data.

[0962] Step 2:

[0963] The server periodically and automatically collects user spending information through the APIs of registered electronic payment services and credit card companies. The input is the user's authentication information and raw spending data obtained from the API. The output is the collected spending data.

[0964] Step 3:

[0965] The server standardizes the collected expenditure data into a unified format. The input is the raw expenditure data obtained in step 2. Data processing involves converting data in different formats into a consistent format. The output is standardized expenditure data.

[0966] Step 4:

[0967] The server classifies the standardized expenditure data into categories using an AI model. The input is the standardized expenditure data. For data calculation, a generative AI model is used to classify each expenditure item into categories such as "food," "transportation," and "entertainment." The output is expenditure data classified by category.

[0968] Step 5:

[0969] The server generates a household ledger based on the classified expenditure data. The input is expenditure data classified by category. The data is processed by calculating the total income and expenditure and summarizing it in household ledger format. The output is household ledger data generated in a visually easy-to-understand format.

[0970] Step 6:

[0971] The user's terminal receives the generated household accounting data and displays it on the user interface. The input is the household accounting data sent from the server. The terminal displays this in real time. The output is visual household accounting information displayed to the user.

[0972] Step 7:

[0973] The user's device uses a camera and microphone to recognize the user's emotions. The input is camera video and audio data. Specifically, the system detects faces using OpenCV and performs emotion analysis using a TensorFlow model. The output is analyzed user emotion data.

[0974] Step 8:

[0975] The server adjusts the display method of the household account book based on the recognized emotion data. The input is the user's emotion data and household account book data. Specifically, if the emotion is "anxiety," the server adjusts the display method, such as displaying spending warnings more subdued. The output is the household account book data in the adjusted display format.

[0976] Step 9:

[0977] The adjusted household accounting data is redisplayed on the user's device. The input is the adjusted household accounting data. The output is the household accounting information redisplayed to the user. The user can confirm that the display content has been adjusted to take their emotions into consideration.

[0978] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0979] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0980] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0981] [Third embodiment]

[0982] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0983] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0984] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0985] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0986] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0987] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0988] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0989] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0990] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0991] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0992] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0993] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0994] The present invention is a system that automatically collects and standardizes a user's expenditure information, categorizes it using an AI model, and generates and displays a household account book. The following describes in detail the embodiments of the present invention.

[0995] Overall system configuration

[0996] The system consists of the following main components:

[0997] 1. User Device

[0998] A device that allows users to enter registration information and view household accounts.

[0999] Specifically, this includes smartphones, tablets, and PCs.

[1000] 2. Server

[1001] A central processing unit that receives data from users, collects, standardizes, and categorizes expenditure information, and creates a household ledger.

[1002] We accumulate expenditure data, classify it using AI, and analyze big data.

[1003] Program processing overview

[1004] 1. User: Registration

[1005] When a user first uses the system, they create an account and register the payment service and credit card they use, which allows the system to collect the user's spending information appropriately.

[1006] 2. Server: Authentication and Integration

[1007] The server authenticates with the payment service or credit card company entered by the user. If authentication is successful, it securely connects with the service and prepares to periodically collect spending data.

[1008] 3. Server: Data collection

[1009] The server automatically collects spending data from the user's payment services and credit card companies. This is done periodically using APIs. For example, when John buys groceries, his spending information is automatically sent to the server.

[1010] 4. Server: Data Standardization

[1011] The server converts the collected spending data into a unified format, processing payment services and credit card data provided in different formats into a format that can be managed centrally.

[1012] 5. Server: AI-based category determination

[1013] The server uses an AI model to categorize the standardized spending data, such as into categories like "food," "transportation," and "entertainment." The AI ​​model learns from past data and improves its classification accuracy.

[1014] 6. Server: Household accounting

[1015] The server automatically generates a household ledger for the user based on the classified expenditure data. The data is organized by month and category so that expenditures can be seen at a glance, and is saved in a visually easy-to-understand format.

[1016] 7. Terminal: Household account display

[1017] The user's device retrieves the latest household accounting data from the server and displays it. For example, when a user opens the app, the latest expenditure items and their categories, monthly expenditure totals, etc. are displayed.

[1018] 8. Server: Data storage and analysis

[1019] The server stores the collected spending data and analyzes it as big data. This data is used to improve marketing strategies and services. To protect user privacy, all data is encrypted and stored securely.

[1020] Specific examples

[1021] For example, if a user buys groceries online and pays for them with a particular payment service, the following happens:

[1022] 1. User pays

[1023] A user purchases groceries online and completes the payment through a payment service.

[1024] 2. The server collects data

[1025] The payment service sends spending data (e.g., payment amount, purchase store, purchase details, etc.) to the server.

[1026] 3. The server standardizes the data

[1027] The server converts this spending data into a format that can be centrally managed.

[1028] 4. The server uses AI to determine the category

[1029] The server's AI model classifies "groceries" into the "food expenses" category.

[1030] 5. The server creates the household account book

[1031] The server generates and stores an up-to-date household account book that includes this expenditure.

[1032] 6. The device displays the household account book

[1033] When the user opens the household accounting app, this purchase will be reflected in the "This Month's Food Expenses" section.

[1034] In this way, the present invention allows users to manage their spending in real time without having to manually keep a household account book.

[1035] The processing flow will be explained below.

[1036] Step 1:

[1037] The user downloads the application and logs in for the first time.

[1038] The user enters an email address and password to create a new account.

[1039] Step 2:

[1040] The user registers the payment service (e.g., electronic payment service or credit card) they wish to use.

[1041] The user enters the API key and authentication information for each service.

[1042] Step 3:

[1043] The server authenticates the payment service and credit card entered by the user.

[1044] The server obtains a token to establish a secure connection with each payment service using an API.

[1045] Step 4:

[1046] The server automatically collects spending data from each payment service and credit card.

[1047] The server periodically retrieves new spending data via the API and stores it in a database.

[1048] Step 5:

[1049] The server normalizes the collected spending data into a uniform format.

[1050] The server converts the expenditure data provided in different formats into a unified format, enabling centralized management.

[1051] Step 6:

[1052] The server uses AI models to categorize the standardized spending data.

[1053] The server automatically sorts the data into categories such as "food," "transportation," and "entertainment" based on the nature of the expenditure.

[1054] Step 7:

[1055] The server automatically generates a household account book based on the classified expenditure data.

[1056] The server creates monthly and yearly household budgets and simultaneously prepares the data for visualization.

[1057] Step 8:

[1058] The user's terminal obtains the latest household accounting data from the server and displays it.

[1059] When a user opens the application, it sends a request to the server API to retrieve and display the latest household accounting information.

[1060] Step 9:

[1061] The server stores all collected spending data for a long period of time and performs big data analysis.

[1062] The server anonymizes this data and uses it to strengthen security measures and improve marketing strategies and services.

[1063] Example 1

[1064] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1065] Conventional household accounting management systems require users to manually enter expenditure information, which is time-consuming and labor-intensive. Another issue is that data input from different payment services and credit cards is not standardized, making management cumbersome. Furthermore, the accuracy of effectively classifying expenditure information is low, making automated analysis and visual generation of household accounting difficult.

[1066] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1067] In this invention, the server includes means for automatically collecting user expenditure information, means for standardizing the collected expenditure information, and means for categorizing the standardized expenditure information using an artificial intelligence model. This eliminates the need for users to manually input expenditure information and allows data from different payment services and credit cards to be managed in a unified manner. Furthermore, the use of the artificial intelligence model enables accurate classification of expenditure information, enabling automated analysis and the generation of a visual household ledger.

[1068] "Means for automatically collecting user expenditure information" refers to a function that automatically obtains data on a user's expenditures from sources such as payment services and credit cards used by the user.

[1069] "Means for standardizing collected expenditure information" refers to a function that converts expenditure data provided in different formats into a unified format, enabling centralized management.

[1070] "Means for classifying standardized expenditure information into categories using an artificial intelligence model" refers to a function that inputs standardized expenditure data into an AI model and classifies it into specific categories (e.g., food expenses, transportation expenses, entertainment expenses, etc.).

[1071] The "means for generating a household account book based on classified expenditure information" is a function that automatically creates a visually easy-to-understand household account book based on categorized expenditure data.

[1072] "Means for displaying the household account book on the user's device" refers to a function for displaying the generated household account book data on the user's device such as a smartphone or PC.

[1073] "Means of collecting expenditure data using APIs" refers to a function that automatically collects expenditure data using APIs provided by payment services and credit card companies.

[1074] "Means for accumulating and analyzing collected expenditure data as big data" refers to a function that stores large amounts of collected expenditure data in a database and uses analytical technology to analyze patterns and trends.

[1075] "Means for encrypting data to ensure the security of collected expenditure data" refers to a function that encrypts collected expenditure data to protect privacy and protects it from unauthorized access.

[1076] The present invention is a system that automatically collects and standardizes a user's expenditure information, categorizes it using an artificial intelligence model, and generates and displays a household account book. The following describes in detail the embodiments of the present invention.

[1077] Overall system configuration

[1078] The system consists of the following main components:

[1079] 1. User Device

[1080] A device on which a user enters registration information and views the household ledger. Specifically, this applies to smartphones, tablets, PCs, etc.

[1081] 2. Server

[1082] It is the central processing unit that receives data from users, collects, standardizes, and classifies expenditure information, and creates a household ledger. The server accumulates expenditure data, classifies it using artificial intelligence, and performs big data analysis.

[1083] Hardware and software used

[1084] Device: Uses a user device such as a smartphone, tablet, or PC. Users enter information and view their household accounts through these devices.

[1085] Server: Cloud servers and virtual servers are used to collect and process expenditure information, such as Amazon Web Services (AWS) and Google Cloud Platform (GCP).

[1086] Artificial intelligence model: A model for classifying spending information into categories, which is implemented using machine learning libraries such as TensorFlow and PyTorch in Python.

[1087] Basic system operation

[1088] The system works based on the following steps:

[1089] User:Register

[1090] When a user first uses the system, they create an account and register their payment service and credit card information, which allows the system to automatically collect their spending information.

[1091] Server: Data collection and authentication

[1092] The server periodically collects user spending data using the APIs of payment services and credit card companies. First, authentication is performed with the payment service or credit card company to establish a connection. For example, when a user purchases groceries, the spending information is automatically sent from the payment service to the server.

[1093] Server: Data Standardization

[1094] The server converts the collected spending data into a unified format, allowing for the centralized management of the various formats provided by different payment services and credit card companies.

[1095] Server: AI-based category determination

[1096] The server inputs the standardized expenditure data into an AI model and categorizes it into categories, such as "food," "transportation," and "entertainment." The AI ​​model references past data to improve classification accuracy.

[1097] Server: Household accounting and display

[1098] The server generates a household account book based on the categorized expenditure data and organizes it in a visually easy-to-understand format. This household account book is sent from the server to the user's terminal and can be viewed by the user.

[1099] Server: Data storage and analysis

[1100] The server encrypts and securely stores all collected spending data and analyzes it as big data. This data is used to improve marketing strategies and services. All data is also encrypted to protect user privacy.

[1101] Specific examples

[1102] For example, if a user buys groceries online and pays for them with a particular payment service, the following happens:

[1103] 1. User pays

[1104] A user purchases groceries online and completes the payment through a payment service.

[1105] 2. The server collects data

[1106] The payment service sends spending data (e.g., payment amount, purchase store, purchase details, etc.) to the server.

[1107] 3. The server standardizes the data

[1108] The server converts this spending data into a format that can be centrally managed.

[1109] 4. The server uses AI to determine the category

[1110] The server's artificial intelligence model classifies "groceries" into the "food expenses" category.

[1111] 5. The server creates the household account book

[1112] The server generates and stores an up-to-date household account book that includes this expenditure.

[1113] 6. The device displays the household account book

[1114] When the user opens the household accounting app, this purchase will be reflected in the "This Month's Food Expenses" section.

[1115] In this way, the present invention allows users to manage their spending in real time without having to manually keep a household account book.

[1116] Prompt Sentence Examples

[1117] "Describe a system that collects spending information when a user makes a new expense, standardizes it, categorizes it using an AI model, and reflects it in a household ledger. Include a specific scenario, such as a user buying groceries online."

[1118] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1119] Step 1: User Registration

[1120] Users launch a dedicated app on their own device (smartphone, tablet, PC, etc.) and register an account.

[1121] Specifically, the user enters information such as their name, email address, and password, and registers the payment service and credit card information they will use.

[1122] Input: User information (name, email address, password, etc.), payment service information, credit card information

[1123] Output: User registration information stored on the server

[1124] Step 2: Authentication and Integration

[1125] The server receives the payment service and credit card information entered by the user and sends an authentication request using each service's API.

[1126] If authentication is successful, the server establishes a secure data connection with the payment service and credit card company.

[1127] Input: User's payment service information, credit card information

[1128] Output: Authentication success message, data linking token

[1129] Step 3: Data collection

[1130] The server periodically collects spending data from the user's payment service and credit card using the established data federation.

[1131] Specifically, the server obtains expenditure data (e.g., payment amount, store of purchase, purchase details, etc.) through the API.

[1132] Input: Data link token

[1133] Output: Collected spending data

[1134] Step 4: Data Standardization

[1135] The server converts the collected spending data into a unified format.

[1136] Specifically, the system converts expenditure data provided in different formats into a format that can be centrally managed.

[1137] Input: Collected expenditure data

[1138] Output: Normalized spending data

[1139] Step 5: Categorization

[1140] The server inputs the standardized spending data into an artificial intelligence model that categorizes it into specific spending categories.

[1141] Specifically, the artificial intelligence model classifies expenditure data into categories such as "food expenses," "transportation expenses," and "entertainment expenses" based on past data.

[1142] Input: Standardized expenditure data

[1143] Output: Categorized spending data

[1144] Step 6: Create a household budget

[1145] The server generates a household account book based on the categorized expenditure data.

[1146] Specifically, it calculates the total monthly expenditures and total expenditures by category for each category, and organizes them in a visually easy-to-understand format (e.g., graphs or statistical charts).

[1147] Input: Categorized spending data

[1148] Output: Generated household accounting data

[1149] Step 7: View your household budget

[1150] When a user opens the dedicated app, the device requests the latest household accounting data from the server.

[1151] In response to a request, the server transmits the latest household accounting data to the terminal, which then displays it.

[1152] Input: A request to the server

[1153] Output: The latest household accounting data displayed on the device

[1154] Step 8: Data collection and analysis

[1155] The server encrypts and securely stores all collected spending data and analyzes it as big data.

[1156] Specifically, it analyzes data patterns and trends and uses them to improve marketing strategies and services.

[1157] Input: Collected expenditure data

[1158] Output: Analysis results, encrypted database

[1159] (Application example 1)

[1160] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1161] In modern society, many users use multiple electronic payment methods, and their spending information is scattered across multiple platforms, making it difficult to manage spending. Furthermore, it is difficult to centrally manage spending information or visually grasp spending, making it difficult to achieve efficient household management. Ensuring the security of spending data is also an important issue.

[1162] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1163] In this invention, the server includes means for automatically collecting a user's expenditure information, means for standardizing the collected expenditure information, means for categorizing the standardized expenditure information using a generative AI model, means for generating a household account book based on the categorized expenditure information, means for displaying the household account book on the user's terminal, and means for analyzing the user's expenditure information and graphically displaying the expenditure status. This allows for centralized management of expenditure information even if the user uses multiple electronic payment methods, and accurate category classification by the generative AI model enables efficient and visually easy household management. Security is also ensured at the same time.

[1164] "User Spending Information" is data regarding purchases and expenditures made through electronic payment instruments.

[1165] "Automatic collection means" refers to the process of regularly obtaining spending data from electronic payment services using APIs, etc.

[1166] A "standardization measure" is a process for converting expenditure data collected in different formats into a unified format.

[1167] A "generative AI model" is an artificial intelligence algorithm used to learn from past data and classify new data into categories.

[1168] "Categorization method" refers to the process of using a generative AI model to separate standardized expenditure data into categories such as food, transportation, and entertainment.

[1169] A "household account book" is a digital record that organizes a user's spending information by month and category, and shows total amounts, etc.

[1170] "Generation" refers to the process of creating a household ledger based on collected, standardized, and categorized expenditure data.

[1171] "Means for displaying on a terminal" refers to a function for displaying household accounting data on a device such as a smartphone or tablet owned by the user.

[1172] "Means for analyzing spending information" refers to the process of analyzing collected spending data to derive users' spending tendencies and patterns.

[1173] The "means for graphically displaying expenditure status" is a function for visually displaying the user's income and expenditure information in the form of graphs or charts.

[1174] MODE FOR CARRYING OUT THE INVENTION

[1175] The system of the present invention automatically collects user expenditure information, standardizes, categorizes, and generates and displays a household account book. To achieve this, the following main hardware and software components are used:

[1176] Hardware and software used

[1177] User devices: smartphones, tablets, PCs, etc.

[1178] Server: AWS EC2, MySQL database

[1179] Data collection tool: API integration using the requests library

[1180] Data processing library: pandas (for manipulating data frames)

[1181] AI model: TensorFlow, Scikit-learn

[1182] Visualization tool: matplotlib

[1183] Smartphone app: Flutter / Dart

[1184] Program processing

[1185] 1. Automatic collection of user spending information:

[1186] The server periodically collects spending information from the electronic payment service using API integration. It uses the requests library to access the API and retrieve spending data.

[1187] 2. Data Standardization:

[1188] The server uses pandas to convert the collected spending data into a unified format, allowing data provided in different formats to be centrally managed.

[1189] 3. Category Classification:

[1190] The server uses a generative AI model (TensorFlow and Scikit-learn) to categorize the standardized expenditure data, learning from past data and automatically sorting current data into categories such as "food," "transportation," and "entertainment."

[1191] 4. Household account book generation:

[1192] The server generates a household account book based on the classified expenditure data and stores it in a database. The household account book is organized by month and category and kept in a visually easy-to-understand format.

[1193] 5. Visualization and display of household accounts:

[1194] The server uses the matplotlib library to visualize the collected and classified data as bar graphs, pie charts, etc. The user device receives this data and displays the household ledger data through a smartphone app (Flutter / Dart).

[1195] Specific example explanation

[1196] For example, if a user buys groceries for 5000 yen online and pays for them using an electronic payment service, the process would be as follows:

[1197] 1. The user completes the payment.

[1198] 2. The server collects spending data (payment amount, purchase location, purchase details, etc.) from the electronic payment service.

[1199] 3. The server normalizes this spending data into a uniform format.

[1200] 4. The server's generative AI model classifies "groceries" into the "food expenses" category.

[1201] 5. The server generates an updated household account book including this expenditure and stores it in the database.

[1202] 6. When the user opens the household accounting app, this purchase will be reflected in the "This Month's Food Expenses" column.

[1203] Prompt Sentence Examples

[1204] "I bought groceries worth 5,000 yen online and paid for them using an electronic payment service. Please automatically add this expenditure information to my household account book."

[1205] In this way, the present invention saves the user the trouble of manually keeping a household account book, and enables efficient, real-time expenditure management.

[1206] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1207] Step 1:

[1208] Collecting user spending information

[1209] Input: Account information for multiple electronic payment services registered by the user.

[1210] How it works: The server periodically retrieves spending data from the electronic payment service via an API using the requests library.

[1211] Data processing / calculation: Receive the acquired expenditure data in JSON format and extract detailed information such as payment amount, date, and store name.

[1212] Output: Extracted expenditure data.

[1213] Step 2:

[1214] Data Standardization

[1215] Input: The expenditure data collected in Step 1.

[1216] How it works: The server uses the pandas library to convert the spending data it receives into a unified format.

[1217] Data manipulation / calculation: Transform all data items into a consistent format, fill in missing data, or change data types.

[1218] Output: Standardized expenditure data.

[1219] Step 3:

[1220] Category Classification

[1221] Input: The standardized expenditure data from step 2.

[1222] How it works: The server uses a generative AI model (TensorFlow or Scikit-learn) to classify standardized spending data into categories.

[1223] Data processing / calculation: The generative AI model analyzes the content of expenditure data and automatically classifies it into categories such as "food," "transportation," and "entertainment."

[1224] Output: Spending data broken down by category.

[1225] Step 4:

[1226] household account book generation

[1227] Input: Expense data categorized in step 3.

[1228] How it works: The server connects to a MySQL database and generates a household ledger based on categorized spending data.

[1229] Data processing / calculation: Data is aggregated by month and category and stored in a database in a visually organized format.

[1230] Output: The latest household accounting data stored in the database.

[1231] Step 5:

[1232] Visualization and display of household finances

[1233] Input: The household budget data generated in step 4.

[1234] How it works: The server uses the matplotlib library to generate image files that display the household accounting data in visual formats such as bar graphs and pie charts.

[1235] Data processing / calculation: Formatting data for graph creation and processing it in a visually understandable format.

[1236] Output: An image file of the visualized household accounting data.

[1237] Step 6:

[1238] Displaying household accounts on user devices

[1239] Input: The household budget data visualized in Step 5.

[1240] Operation: An image file of the latest household accounting data is displayed through a smartphone app (Flutter / Dart) on the user's device.

[1241] Data processing / calculation: None

[1242] Output: Household accounting data displayed on a smartphone screen.

[1243] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1244] The present invention combines a system that automatically collects and standardizes a user's spending information, categorizes it using an AI model, and generates and displays a household account book with an emotion engine that recognizes the user's emotions. The following describes in detail the embodiments of the present invention.

[1245] Overall system configuration

[1246] The system consists of the following main components:

[1247] 1. User Device

[1248] A device that allows users to enter registration information and view household accounts.

[1249] Specifically, this includes smartphones, tablets, and PCs.

[1250] 2. Server

[1251] A central processing unit that receives data from users, collects, standardizes, and categorizes expenditure information, and creates a household ledger.

[1252] It accumulates expenditure data, classifies it using AI, analyzes big data, and recognizes emotions using an emotion engine.

[1253] 3. Emotion Engine

[1254] An engine that recognizes user emotions and reflects that information in the household accounting system.

[1255] Analyzes emotions based on various sensors and user input.

[1256] Program processing overview

[1257] Start:User Registration

[1258] When a user uses the system for the first time, they create an account and register the payment service and credit card they wish to use.

[1259] Server: Authentication and collaboration

[1260] The server authenticates the payment service or credit card entered by the user and cooperates to securely collect spending data.

[1261] Server: Data collection

[1262] The server automatically collects spending data from payment services and credit card companies, which are retrieved periodically using APIs.

[1263] Server: Data Standardization

[1264] The server converts the collected expenditure data into a unified format and organizes it into a form that can be managed centrally.

[1265] Server: AI-based category determination

[1266] The server uses AI models to automatically categorize standardized spending data into categories, such as "food," "transportation," and "entertainment."

[1267] Server: Household accounting

[1268] The server automatically generates a household ledger based on the categorized expenditure data, and the ledger is saved in a format that allows monthly and yearly data to be displayed visually in an easy-to-understand manner.

[1269] User device: Household account display

[1270] The user's terminal obtains the latest household accounting data from the server and displays it in real time.

[1271] Server: Emotion recognition

[1272] The emotion engine recognizes the user's emotions in various ways, such as facial recognition, voice analysis, and text input.

[1273] Server: Emotional reflection

[1274] The server then changes how the financial data is displayed based on the user's perceived emotions, for example, by displaying less warnings and advice about spending if the user is feeling stressed.

[1275] Specific examples

[1276] For example, if a user purchases a high-value item online and pays for it using a particular payment service, the following happens:

[1277] 1. A user purchases a high-value item

[1278] A user purchases an expensive electronic device from an online shop and completes the payment using an electronic payment service.

[1279] 2. The server collects data

[1280] The electronic payment service sends expenditure data for high-value items to the server.

[1281] 3. The server standardizes the data

[1282] The server converts this spending data into a unified format.

[1283] 4. The server uses AI to determine the category

[1284] The AI ​​model classifies this expense into the "high expense" category.

[1285] 5. The server creates the household account book

[1286] The server generates and stores an updated household account book that includes this expenditure.

[1287] 6. Emotion engine recognizes emotions

[1288] When a user opens the household accounting app, the system recognizes the user's emotions through the camera and microphone. For example, if the user is feeling anxious after making a purchase, the system will recognize that emotion.

[1289] 7. The server reflects emotions

[1290] The server can then adjust how the budget is displayed based on the perceived anxiety, for example by providing less warnings about spending and more gentle advice on how to manage spending.

[1291] In this way, the present invention allows the user to save the trouble of manually keeping a household account book, manage expenditures in real time, and receive display of the household account book and advice according to emotions.

[1292] The processing flow will be explained below.

[1293] Step 1:

[1294] The user downloads the application and logs in for the first time.

[1295] The user enters an email address and password to create a new account.

[1296] Step 2:

[1297] The user registers the payment service and credit card they wish to use.

[1298] The user enters the API key and authentication information for each service.

[1299] Step 3:

[1300] The server authenticates the payment service and credit card entered by the user.

[1301] The server uses an API to establish a secure connection with each payment service and obtain an authentication token.

[1302] Step 4:

[1303] The server automatically collects spending data from each payment service and credit card company.

[1304] The server periodically retrieves new spending data via the API and stores it in a database.

[1305] Step 5:

[1306] The server normalizes the collected spending data into a uniform format.

[1307] The server converts the expenditure data provided in different formats into a unified format, enabling centralized management.

[1308] Step 6:

[1309] The server uses AI models to categorize the standardized spending data.

[1310] The server automatically sorts the data into categories such as "food," "transportation," and "entertainment" based on the nature of the expenditure.

[1311] Step 7:

[1312] The server automatically generates a household account book based on the classified expenditure data.

[1313] The server creates monthly and yearly household budgets and simultaneously prepares the data for visualization.

[1314] Step 8:

[1315] The user's terminal obtains the latest household accounting data from the server and displays it.

[1316] When a user opens the application, it sends a request to the server API to retrieve and display the latest household accounting information.

[1317] Step 9:

[1318] The server uses an emotion engine to recognize the user's emotions.

[1319] The server collects and analyzes emotional data through the camera, microphone, and user text input.

[1320] Step 10:

[1321] The server changes the way the household account book data is displayed based on the recognized user emotion.

[1322] For example, the server may tone down spending warnings and display advice in a softer tone if the user is feeling anxious.

[1323] Step 11:

[1324] The server stores all collected spending data and emotion data for a long period of time and performs big data analysis.

[1325] The server anonymizes this data and uses it to strengthen security measures and improve marketing strategies and services.

[1326] Example 2

[1327] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1328] Many modern users find it difficult to manually manage their household accounts given their busy lives. Furthermore, conventional household accounting systems simply record income and expenditures and are unable to provide personalized feedback based on the user's emotions. As a result, users are unable to manage their spending in a way that fully reflects their own spending situation and stress level, making effective use of the system difficult.

[1329] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1330] In this invention, the server includes means for automatically collecting user expenditure information, means for standardizing the collected expenditure information, means for classifying the standardized expenditure information into categories, means for generating a household account book based on the classified expenditure information, means for displaying the household account book on the user's terminal, means for recognizing the user's emotion, and means for adjusting the display method of the household account book based on the recognized emotion. This saves the user the trouble of manually keeping a household account book and enables the user to receive feedback according to their emotion.

[1331] "User expenditure information" is data relating to monetary expenditures made by a user through various payment methods.

[1332] "Standardization means" is a process for converting expenditure information collected in various formats into a unified format.

[1333] A "categorization method" is an algorithm or technique for classifying standardized expenditure information into specific categories, such as "food" or "transportation."

[1334] The "means for generating a household account book" is a process for visually or numerically creating a household account book based on the classified expenditure information.

[1335] "User terminal" refers to the device used by the user to operate the system and view information, including smartphones, tablets, PCs, etc.

[1336] "Means for recognizing emotions" refers to technology for analyzing the emotional state of a user, and includes methods such as facial recognition, voice analysis, and text analysis.

[1337] The "means for adjusting the display method" is a process for changing the display contents of the household account book, warning messages, etc., based on the recognized user's emotions.

[1338] The present invention combines a system that automatically collects and standardizes a user's spending information, categorizes it using a generative AI model, and generates and displays a household account book with an emotion engine that recognizes the user's emotions. The following describes in detail an embodiment of this system.

[1339] Overall system configuration

[1340] The system consists of the following main components:

[1341] 1. User Device

[1342] This is a device that allows users to enter registration information and view their household account book.

[1343] Specifically, this includes devices such as smartphones, tablets, and PCs.

[1344] 2. Server

[1345] It is the central processing unit that receives data from users, collects, standardizes, and classifies expenditure information, and creates a household ledger.

[1346] It accumulates expenditure data and performs big data analysis, categorizes data using a generative AI model, and recognizes emotions using an emotion engine.

[1347] 3. Emotion Engine

[1348] It is an engine that recognizes the user's emotions and reflects that information in the household accounting system.

[1349] Analyzes emotions based on various sensors and user input.

[1350] Program processing overview

[1351] The server connects with payment service and credit card APIs to automatically collect user spending information. The server periodically collects this data and standardizes it into a unified format. It then uses a generative AI model to classify the standardized spending information into categories such as "food," "transportation," and "entertainment." Based on this classified data, the server generates a visually easy-to-understand household ledger. The generated household ledger data is stored on the server and displayed in real time on the user's device.

[1352] The emotion engine also recognizes the user's emotions through the camera and microphone and adjusts the way the household budget is displayed based on this. For example, if the user is feeling stressed, the server will tone down spending warnings and display advice on managing spending in a softer tone.

[1353] Specific examples

[1354] For example, if a user purchases an expensive item online and pays for it using a specific payment service, the following process will occur.

[1355] 1. A user purchases a high-value item

[1356] A user purchases an expensive electronic device from an online shop and completes the payment using an electronic payment service.

[1357] 2. The server collects data

[1358] The electronic payment service sends spending data for high-value items to the server, which collects this data through an API.

[1359] 3. The server standardizes the data

[1360] The server converts the collected expenditure data into a unified format, such as a unified date format and a unified amount format.

[1361] 4. The server uses AI to determine the category

[1362] The generative AI model classifies this expense in the "high expense" category and stores it in a database.

[1363] 5. The server creates the household account book

[1364] The server automatically generates a household account book based on the classified expenditure data, and the household account book sends monthly and yearly expenditure data to the user's device in a format that can be visually displayed.

[1365] 6. Emotion engine recognizes emotions

[1366] When a user opens the household accounting app, the app recognizes the user's emotions through the camera and microphone.

[1367] 7. The server reflects emotions

[1368] The server then adjusts the way the household budget is displayed based on the recognized emotion, for example, if the user is feeling anxious, it will display a message that reflects that emotion.

[1369] Prompt Sentence Examples

[1370] Possible input prompts for a generative AI model include:

[1371] "Describe how you collect spending data from a user's online purchase of expensive electronics and use a generative AI model to categorize it. Also, explain how the display of the household budget changes when the user is feeling anxious."

[1372] By using this method, the present invention can provide an expense management system that takes into consideration the feelings of the user.

[1373] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1374] Step 1:

[1375] Users create an account using their smartphone or PC and register the payment service and credit card information they wish to use. Based on this input information, the system initializes the user data. As an output, the account information is saved in a database.

[1376] Step 2:

[1377] The server performs authentication using the payment service and credit card information registered by the user. This authentication process is performed using the APIs of each payment service and credit card company. It receives the user's authentication information as input and generates an authentication token as output, completing the API integration setup.

[1378] Step 3:

[1379] The server periodically collects user spending data from payment services and credit card companies via configured APIs. The collection process involves periodically sending API requests as input and storing the received spending data on the server. The output is a temporary storage of spending information in its raw form.

[1380] Step 4:

[1381] The server converts the collected expenditure data into a unified format. Specifically, it unifies information such as the date and time of expenditure, amount, and store name provided in different formats. It receives the collected expenditure data as input and generates standardized expenditure data as output.

[1382] Step 5:

[1383] The server uses a generative AI model to classify the standardized expenditure data into categories, such as automatically sorting expenses for food, transportation, entertainment, etc. It receives standardized expenditure data as input and generates categorized expenditure data as output.

[1384] Step 6:

[1385] The server generates a household account book based on the classified expenditure data. The household account book is saved in a format that allows monthly and yearly data to be displayed visually. It receives classified expenditure data as input and generates household account book data as output.

[1386] Step 7:

[1387] The terminal receives the latest household accounting data sent from the server and displays it in real time. Users can view the household accounting data on their smartphones or PCs. The terminal receives household accounting data from the server as input and displays the household accounting data on the screen as output.

[1388] Step 8:

[1389] The server's emotion engine analyzes the user's facial expressions and voice using sensors such as a camera and microphone to recognize the user's emotions. It also extracts emotions from the user's text input. It receives data from the sensors as input and generates recognized emotion data as output.

[1390] Step 9:

[1391] The server adjusts the display of the household account book based on the recognized emotion data. For example, if the user is feeling anxious, it displays a message that takes the user's emotion into consideration or advice on spending management. It receives the recognized emotion data as input and generates an adjusted household account book display as output.

[1392] This process flow allows users to effortlessly manage their spending and receive emotional feedback.

[1393] (Application example 2)

[1394] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1395] While existing household accounting systems have been successful in collecting and classifying users' spending information, they lack appropriate feedback and display adjustments based on the user's emotions, making it difficult to properly manage spending when users feel stressed or anxious. Furthermore, emotion recognition technology needs to be combined to improve the user experience.

[1396] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically collecting user expenditure information, means for standardizing the collected expenditure information, means for classifying the standardized expenditure information into categories, means for generating a household account book based on the classified expenditure information, means for recognizing the user's emotions, means for adjusting the display method of the household account book based on the recognized user emotions, and means for displaying the household account book on the user's terminal. This enables feedback and display adjustment of expenditure management according to the user's emotions, improving the user experience and enabling appropriate expenditure management with reduced stress and anxiety.

[1397] "User expenditure information" refers to data related to the purchasing activities and payments made by the user, specifically the amount used, the date and time, the place of purchase, and other information.

[1398] "Standardization" refers to the process of converting data collected in different forms and formats into a consistent format, arranging it into a unified format for easier analysis and management.

[1399] "Categorizing" means dividing data into groups with similar characteristics based on specific criteria, such as "food expenses," "transportation expenses," and "entertainment expenses."

[1400] A "household account book" refers to a record of income and expenses of an individual or household, and refers to a written or digital record used to visualize the balance of income and expenses.

[1401] "User device" refers to the electronic device used by the user to access the system and view and operate information, specifically a smartphone, tablet, or PC.

[1402] "Means for recognizing emotions" refers to technology for analyzing and determining a user's emotional state, and refers to identifying a user's emotions using methods such as facial recognition technology, voice analysis, and text analysis.

[1403] "Means for adjusting the display method" refers to technology that appropriately changes the display format and content of information depending on the user's emotional state, such as switching to a display that reduces stress or anxiety.

[1404] "Means of accumulating and analyzing big data" refers to the technology of systematically accumulating large amounts of data, analyzing it using advanced analytical techniques, and extracting useful information and patterns.

[1405] "Means of encrypting data" refers to technology that converts collected data using a specific algorithm to protect it from third parties and prevent unauthorized access or leakage.

[1406] The system of the present invention provides a means for automatically collecting, standardizing, and categorizing a user's spending information and generating a household ledger, and also has the function of recognizing the user's emotions and adjusting the display method of the household ledger based on those emotions. The detailed configuration and implementation of each means are described below.

[1407] Overall system overview

[1408] Automatically collect user spending information

[1409] The server automatically collects spending data from the electronic payment services and credit cards registered by the user, including the ability to obtain spending information through a publicly available API.

[1410] Data Standardization

[1411] The server converts the collected spending data into a unified format, allowing for consistent processing of data from different sources.

[1412] Categorized

[1413] The server uses an AI model to categorize the standardized expenditure data, automatically dividing it into categories such as "food expenses," "transportation expenses," and "entertainment expenses."

[1414] Creating and displaying household accounts

[1415] The server automatically generates a household account book based on the classified expenditure data, and the user's device retrieves the household account book in real time and displays it visually in an easy-to-understand manner.

[1416] Emotion recognition

[1417] The user's device recognizes the user's emotions through a camera and microphone, using facial recognition technology and voice analysis. Specifically, OpenCV is used to detect faces and TensorFlow is used to analyze emotions.

[1418] Emotion-based display adjustment

[1419] The server adjusts the display of the household account book and the content of notifications based on the user's recognized emotions. For example, if the user is feeling stressed, spending warnings will be displayed more subtly.

[1420] Hardware and software used

[1421] Smartphones and tablets: These are devices that allow users to view spending information and recognize emotions.

[1422] Server: Performs central processing such as data collection, standardization, classification, emotion recognition, and household accounting generation.

[1423] API: Used to collect data from electronic payment services.

[1424] OpenCV: A library for face recognition.

[1425] TensorFlow: A machine learning library for running emotion recognition models.

[1426] Specific examples

[1427] For example, if a user makes a big purchase and then opens the app feeling anxious, the system might:

[1428] 1. User purchases a high-priced item: A user purchases a high-priced electronic device from an online shop and completes the payment using an electronic payment service.

[1429] 2. Data collection and standardization: The server collects spending data from electronic payment services and converts it into a unified format.

[1430] 3. Data Classification: Using an AI model, classify this spending data into “high-spending” categories.

[1431] 4. Generation of household account book: The server generates an up-to-date household account book based on the classified expenditure data and displays it on the user's terminal.

[1432] 5. Emotion Recognition: When a user opens the household accounting app, the system recognizes the user's emotions through the device's camera and microphone. For example, if the user is feeling anxious after making a purchase, that information will be recognized by the system.

[1433] 6. Display Adjustment: The server adjusts the display of the household budget based on the perceived anxiety, specifically by softening the spending warnings and softening the advice on how to manage spending.

[1434] Example prompts to input to the generative AI model

[1435] "If a user buys a big-ticket item and then opens the app and feels anxious, how should the system display a spending warning?"

[1436] In this way, the present invention allows the user to save time and effort in manually keeping a household account book, and allows the user to manage expenses in real time while receiving optimal display and advice according to emotions.

[1437] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1438] Step 1:

[1439] The user registers their electronic payment service and credit card information to collect expenditure data. The input is the user's credit card information and authentication information for the electronic payment service. This allows the system to perform authentication and prepare to securely collect expenditure data.

[1440] Step 2:

[1441] The server periodically and automatically collects user spending information through the APIs of registered electronic payment services and credit card companies. The input is the user's authentication information and raw spending data obtained from the API. The output is the collected spending data.

[1442] Step 3:

[1443] The server standardizes the collected expenditure data into a unified format. The input is the raw expenditure data obtained in step 2. Data processing involves converting data in different formats into a consistent format. The output is standardized expenditure data.

[1444] Step 4:

[1445] The server classifies the standardized expenditure data into categories using an AI model. The input is the standardized expenditure data. For data calculation, a generative AI model is used to classify each expenditure item into categories such as "food," "transportation," and "entertainment." The output is expenditure data classified by category.

[1446] Step 5:

[1447] The server generates a household ledger based on the classified expenditure data. The input is expenditure data classified by category. The data is processed by calculating the total income and expenditure and summarizing it in household ledger format. The output is household ledger data generated in a visually easy-to-understand format.

[1448] Step 6:

[1449] The user's terminal receives the generated household accounting data and displays it on the user interface. The input is the household accounting data sent from the server. The terminal displays this in real time. The output is visual household accounting information displayed to the user.

[1450] Step 7:

[1451] The user's device uses a camera and microphone to recognize the user's emotions. The input is camera video and audio data. Specifically, the system detects faces using OpenCV and performs emotion analysis using a TensorFlow model. The output is the analyzed user's emotion data.

[1452] Step 8:

[1453] The server adjusts the display method of the household account book based on the recognized emotion data. The input is the user's emotion data and household account book data. Specifically, if the emotion is "anxiety," the server adjusts the display method, such as displaying spending warnings less. The output is the household account book data in the adjusted display format.

[1454] Step 9:

[1455] The adjusted household accounting data is redisplayed on the user's device. The input is the adjusted household accounting data. The output is the household accounting information redisplayed to the user. The user can confirm that the display content has been adjusted to take their emotions into consideration.

[1456] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1457] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1458] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1459] [Fourth embodiment]

[1460] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1461] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1462] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1463] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1464] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1465] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1466] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1467] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1468] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1469] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1470] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1471] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1472] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1473] The present invention is a system that automatically collects and standardizes a user's expenditure information, categorizes it using an AI model, and generates and displays a household account book. The following describes in detail the embodiments of the present invention.

[1474] Overall system configuration

[1475] The system consists of the following main components:

[1476] 1. User Device

[1477] A device that allows users to enter registration information and view household accounts.

[1478] Specifically, this includes smartphones, tablets, and PCs.

[1479] 2. Server

[1480] A central processing unit that receives data from users, collects, standardizes, and categorizes expenditure information, and creates a household ledger.

[1481] We accumulate expenditure data, classify it using AI, and analyze big data.

[1482] Program processing overview

[1483] 1. User: Registration

[1484] When a user first uses the system, they create an account and register the payment service and credit card they use, which allows the system to collect the user's spending information appropriately.

[1485] 2. Server: Authentication and Integration

[1486] The server authenticates with the payment service or credit card company entered by the user. If authentication is successful, it securely connects with the service and prepares to periodically collect spending data.

[1487] 3. Server: Data collection

[1488] The server automatically collects spending data from the user's payment services and credit card companies. This is done periodically using APIs. For example, when John buys groceries, his spending information is automatically sent to the server.

[1489] 4. Server: Data Standardization

[1490] The server converts the collected spending data into a unified format, processing payment services and credit card data provided in different formats into a format that can be managed centrally.

[1491] 5. Server: AI-based category determination

[1492] The server uses an AI model to categorize the standardized spending data, such as into categories like "food," "transportation," and "entertainment." The AI ​​model learns from past data and improves its classification accuracy.

[1493] 6. Server: Household accounting

[1494] The server automatically generates a household ledger for the user based on the classified expenditure data. The data is organized by month and category so that expenditures can be seen at a glance, and is saved in a visually easy-to-understand format.

[1495] 7. Terminal: Household account display

[1496] The user's device retrieves the latest household accounting data from the server and displays it. For example, when a user opens the app, the latest expenditure items and their categories, monthly expenditure totals, etc. are displayed.

[1497] 8. Server: Data storage and analysis

[1498] The server stores the collected spending data and analyzes it as big data. This data is used to improve marketing strategies and services. To protect user privacy, all data is encrypted and stored securely.

[1499] Specific examples

[1500] For example, if a user buys groceries online and pays for them with a particular payment service, the following happens:

[1501] 1. User pays

[1502] A user purchases groceries online and completes the payment through a payment service.

[1503] 2. The server collects data

[1504] The payment service sends spending data (e.g., payment amount, purchase store, purchase details, etc.) to the server.

[1505] 3. The server standardizes the data

[1506] The server converts this spending data into a format that can be centrally managed.

[1507] 4. The server uses AI to determine the category

[1508] The server's AI model classifies "groceries" into the "food expenses" category.

[1509] 5. The server creates the household account book

[1510] The server generates and stores an up-to-date household account book that includes this expenditure.

[1511] 6. The device displays the household account book

[1512] When the user opens the household accounting app, this purchase will be reflected in the "This Month's Food Expenses" section.

[1513] In this way, the present invention allows users to manage their spending in real time without having to manually keep a household account book.

[1514] The processing flow will be explained below.

[1515] Step 1:

[1516] The user downloads the application and logs in for the first time.

[1517] The user enters an email address and password to create a new account.

[1518] Step 2:

[1519] The user registers the payment service (e.g., electronic payment service or credit card) they wish to use.

[1520] The user enters the API key and authentication information for each service.

[1521] Step 3:

[1522] The server authenticates the payment service and credit card entered by the user.

[1523] The server obtains a token to establish a secure connection with each payment service using an API.

[1524] Step 4:

[1525] The server automatically collects spending data from each payment service and credit card.

[1526] The server periodically retrieves new spending data via the API and stores it in a database.

[1527] Step 5:

[1528] The server normalizes the collected spending data into a uniform format.

[1529] The server converts the expenditure data provided in different formats into a unified format, enabling centralized management.

[1530] Step 6:

[1531] The server uses AI models to categorize the standardized spending data.

[1532] The server automatically sorts the data into categories such as "food," "transportation," and "entertainment" based on the nature of the expenditure.

[1533] Step 7:

[1534] The server automatically generates a household account book based on the classified expenditure data.

[1535] The server creates monthly and yearly household budgets and simultaneously prepares the data for visualization.

[1536] Step 8:

[1537] The user's terminal obtains the latest household accounting data from the server and displays it.

[1538] When a user opens the application, it sends a request to the server API to retrieve and display the latest household accounting information.

[1539] Step 9:

[1540] The server stores all collected spending data for a long period of time and performs big data analysis.

[1541] The server anonymizes this data and uses it to strengthen security measures and improve marketing strategies and services.

[1542] Example 1

[1543] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1544] Conventional household accounting management systems require users to manually enter expenditure information, which is time-consuming and labor-intensive. Another issue is that data input from different payment services and credit cards is not standardized, making management cumbersome. Furthermore, the accuracy of effectively classifying expenditure information is low, making automated analysis and visual generation of household accounting difficult.

[1545] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1546] In this invention, the server includes means for automatically collecting user expenditure information, means for standardizing the collected expenditure information, and means for categorizing the standardized expenditure information using an artificial intelligence model. This eliminates the need for users to manually input expenditure information and allows data from different payment services and credit cards to be managed in a unified manner. Furthermore, the use of the artificial intelligence model enables accurate classification of expenditure information, enabling automated analysis and the generation of a visual household ledger.

[1547] "Means for automatically collecting user expenditure information" refers to a function that automatically obtains data on a user's expenditures from sources such as payment services and credit cards used by the user.

[1548] "Means for standardizing collected expenditure information" refers to a function that converts expenditure data provided in different formats into a unified format, enabling centralized management.

[1549] "Means for classifying standardized expenditure information into categories using an artificial intelligence model" refers to a function that inputs standardized expenditure data into an AI model and classifies it into specific categories (e.g., food expenses, transportation expenses, entertainment expenses, etc.).

[1550] The "means for generating a household account book based on classified expenditure information" is a function that automatically creates a visually easy-to-understand household account book based on categorized expenditure data.

[1551] "Means for displaying the household account book on the user's device" refers to a function for displaying the generated household account book data on the user's device such as a smartphone or PC.

[1552] "Means of collecting expenditure data using APIs" refers to a function that automatically collects expenditure data using APIs provided by payment services and credit card companies.

[1553] "Means for accumulating and analyzing collected expenditure data as big data" refers to a function that stores large amounts of collected expenditure data in a database and uses analytical technology to analyze patterns and trends.

[1554] "Means for encrypting data to ensure the security of collected expenditure data" refers to a function that encrypts collected expenditure data to protect privacy and protects it from unauthorized access.

[1555] The present invention is a system that automatically collects and standardizes a user's expenditure information, categorizes it using an artificial intelligence model, and generates and displays a household account book. The following describes in detail the embodiments of the present invention.

[1556] Overall system configuration

[1557] The system consists of the following main components:

[1558] 1. User Device

[1559] A device on which a user enters registration information and views the household ledger. Specifically, this applies to smartphones, tablets, PCs, etc.

[1560] 2. Server

[1561] It is the central processing unit that receives data from users, collects, standardizes, and classifies expenditure information, and creates a household ledger. The server accumulates expenditure data, classifies it using artificial intelligence, and performs big data analysis.

[1562] Hardware and software used

[1563] Device: Uses a user device such as a smartphone, tablet, or PC. Users enter information and view their household accounts through these devices.

[1564] Server: Cloud servers and virtual servers are used to collect and process expenditure information, such as Amazon Web Services (AWS) and Google Cloud Platform (GCP).

[1565] Artificial intelligence model: A model for classifying spending information into categories, which is implemented using machine learning libraries such as TensorFlow and PyTorch in Python.

[1566] Basic system operation

[1567] The system works based on the following steps:

[1568] User:Register

[1569] When a user first uses the system, they create an account and register their payment service and credit card information, which allows the system to automatically collect their spending information.

[1570] Server: Data collection and authentication

[1571] The server periodically collects user spending data using the APIs of payment services and credit card companies. First, authentication is performed with the payment service or credit card company to establish a connection. For example, when a user purchases groceries, the spending information is automatically sent from the payment service to the server.

[1572] Server: Data Standardization

[1573] The server converts the collected spending data into a unified format, allowing for the centralized management of the various formats provided by different payment services and credit card companies.

[1574] Server: AI-based category determination

[1575] The server inputs the standardized expenditure data into an AI model and categorizes it into categories, such as "food," "transportation," and "entertainment." The AI ​​model references past data to improve classification accuracy.

[1576] Server: Household accounting and display

[1577] The server generates a household account book based on the categorized expenditure data and organizes it in a visually easy-to-understand format. This household account book is sent from the server to the user's terminal and can be viewed by the user.

[1578] Server: Data storage and analysis

[1579] The server encrypts and securely stores all collected spending data and analyzes it as big data. This data is used to improve marketing strategies and services. All data is also encrypted to protect user privacy.

[1580] Specific examples

[1581] For example, if a user buys groceries online and pays for them with a particular payment service, the following happens:

[1582] 1. User pays

[1583] A user purchases groceries online and completes the payment through a payment service.

[1584] 2. The server collects data

[1585] The payment service sends spending data (e.g., payment amount, purchase store, purchase details, etc.) to the server.

[1586] 3. The server standardizes the data

[1587] The server converts this spending data into a format that can be centrally managed.

[1588] 4. The server uses AI to determine the category

[1589] The server's artificial intelligence model classifies "groceries" into the "food expenses" category.

[1590] 5. The server creates the household account book

[1591] The server generates and stores an up-to-date household account book that includes this expenditure.

[1592] 6. The device displays the household account book

[1593] When the user opens the household accounting app, this purchase will be reflected in the "This Month's Food Expenses" section.

[1594] In this way, the present invention allows users to manage their spending in real time without having to manually keep a household account book.

[1595] Prompt Sentence Examples

[1596] "Describe a system that collects spending information when a user makes a new expense, standardizes it, categorizes it using an AI model, and reflects it in a household ledger. Include a specific scenario, such as a user buying groceries online."

[1597] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1598] Step 1: User Registration

[1599] Users launch a dedicated app on their own device (smartphone, tablet, PC, etc.) and register an account.

[1600] Specifically, the user enters information such as their name, email address, and password, and registers the payment service and credit card information they will use.

[1601] Input: User information (name, email address, password, etc.), payment service information, credit card information

[1602] Output: User registration information stored on the server

[1603] Step 2: Authentication and Integration

[1604] The server receives the payment service and credit card information entered by the user and sends an authentication request using each service's API.

[1605] If authentication is successful, the server establishes a secure data connection with the payment service and credit card company.

[1606] Input: User's payment service information, credit card information

[1607] Output: Authentication success message, data linking token

[1608] Step 3: Data collection

[1609] The server periodically collects spending data from the user's payment service and credit card using the established data federation.

[1610] Specifically, the server obtains expenditure data (e.g., payment amount, store of purchase, purchase details, etc.) through the API.

[1611] Input: Data link token

[1612] Output: Collected spending data

[1613] Step 4: Data Standardization

[1614] The server converts the collected spending data into a unified format.

[1615] Specifically, the system converts expenditure data provided in different formats into a format that can be centrally managed.

[1616] Input: Collected expenditure data

[1617] Output: Normalized spending data

[1618] Step 5: Categorization

[1619] The server inputs the standardized spending data into an artificial intelligence model that categorizes it into specific spending categories.

[1620] Specifically, the artificial intelligence model classifies expenditure data into categories such as "food expenses," "transportation expenses," and "entertainment expenses" based on past data.

[1621] Input: Standardized expenditure data

[1622] Output: Categorized spending data

[1623] Step 6: Create a household budget

[1624] The server generates a household account book based on the categorized expenditure data.

[1625] Specifically, it calculates the total monthly expenditures and total expenditures by category for each category, and organizes them in a visually easy-to-understand format (e.g., graphs or statistical charts).

[1626] Input: Categorized spending data

[1627] Output: Generated household accounting data

[1628] Step 7: View your household budget

[1629] When a user opens the dedicated app, the device requests the latest household accounting data from the server.

[1630] In response to a request, the server transmits the latest household accounting data to the terminal, which then displays it.

[1631] Input: A request to the server

[1632] Output: The latest household accounting data displayed on the device

[1633] Step 8: Data collection and analysis

[1634] The server encrypts and securely stores all collected spending data and analyzes it as big data.

[1635] Specifically, it analyzes data patterns and trends and uses them to improve marketing strategies and services.

[1636] Input: Collected expenditure data

[1637] Output: Analysis results, encrypted database

[1638] (Application example 1)

[1639] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1640] In modern society, many users use multiple electronic payment methods, and their spending information is scattered across multiple platforms, making it difficult to manage spending. Furthermore, it is difficult to centrally manage spending information or visually grasp spending, making it difficult to achieve efficient household management. Ensuring the security of spending data is also an important issue.

[1641] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1642] In this invention, the server includes means for automatically collecting a user's expenditure information, means for standardizing the collected expenditure information, means for categorizing the standardized expenditure information using a generative AI model, means for generating a household account book based on the categorized expenditure information, means for displaying the household account book on the user's terminal, and means for analyzing the user's expenditure information and graphically displaying the expenditure status. This allows for centralized management of expenditure information even if the user uses multiple electronic payment methods, and accurate category classification by the generative AI model enables efficient and visually easy household management. Security is also ensured at the same time.

[1643] "User Spending Information" is data regarding purchases and expenditures made through electronic payment instruments.

[1644] "Automatic collection means" refers to the process of regularly obtaining spending data from electronic payment services using APIs, etc.

[1645] A "standardization measure" is a process for converting expenditure data collected in different formats into a unified format.

[1646] A "generative AI model" is an artificial intelligence algorithm used to learn from past data and classify new data into categories.

[1647] "Categorization method" refers to the process of using a generative AI model to separate standardized expenditure data into categories such as food, transportation, and entertainment.

[1648] A "household account book" is a digital record that organizes a user's spending information by month and category, and shows total amounts, etc.

[1649] "Generation" refers to the process of creating a household ledger based on collected, standardized, and categorized expenditure data.

[1650] "Means for displaying on a terminal" refers to a function for displaying household accounting data on a device such as a smartphone or tablet owned by the user.

[1651] "Means for analyzing spending information" refers to the process of analyzing collected spending data to derive users' spending tendencies and patterns.

[1652] The "means for graphically displaying expenditure status" is a function for visually displaying the user's income and expenditure information in the form of graphs or charts.

[1653] MODE FOR CARRYING OUT THE INVENTION

[1654] The system of the present invention automatically collects user expenditure information, standardizes, categorizes, and generates and displays a household account book. To achieve this, the following main hardware and software components are used:

[1655] Hardware and software used

[1656] User devices: smartphones, tablets, PCs, etc.

[1657] Server: AWS EC2, MySQL database

[1658] Data collection tool: API integration using the requests library

[1659] Data processing library: pandas (for manipulating data frames)

[1660] AI model: TensorFlow, Scikit-learn

[1661] Visualization tool: matplotlib

[1662] Smartphone app: Flutter / Dart

[1663] Program processing

[1664] 1. Automatic collection of user spending information:

[1665] The server periodically collects spending information from the electronic payment service using API integration. It uses the requests library to access the API and retrieve spending data.

[1666] 2. Data Standardization:

[1667] The server uses pandas to convert the collected spending data into a unified format, allowing data provided in different formats to be centrally managed.

[1668] 3. Category Classification:

[1669] The server uses a generative AI model (TensorFlow and Scikit-learn) to categorize the standardized expenditure data, learning from past data and automatically sorting current data into categories such as "food," "transportation," and "entertainment."

[1670] 4. Household account book generation:

[1671] The server generates a household account book based on the classified expenditure data and stores it in a database. The household account book is organized by month and category and kept in a visually easy-to-understand format.

[1672] 5. Visualization and display of household accounts:

[1673] The server uses the matplotlib library to visualize the collected and classified data as bar graphs, pie charts, etc. The user device receives this data and displays the household ledger data through a smartphone app (Flutter / Dart).

[1674] Specific example explanation

[1675] For example, if a user buys groceries for 5000 yen online and pays for them using an electronic payment service, the process would be as follows:

[1676] 1. The user completes the payment.

[1677] 2. The server collects spending data (payment amount, purchase location, purchase details, etc.) from the electronic payment service.

[1678] 3. The server normalizes this spending data into a uniform format.

[1679] 4. The server's generative AI model classifies "groceries" into the "food expenses" category.

[1680] 5. The server generates an updated household account book including this expenditure and stores it in the database.

[1681] 6. When the user opens the household accounting app, this purchase will be reflected in the "This Month's Food Expenses" column.

[1682] Prompt Sentence Examples

[1683] "I bought groceries worth 5,000 yen online and paid for them using an electronic payment service. Please automatically add this expenditure information to my household account book."

[1684] In this way, the present invention saves the user the trouble of manually keeping a household account book, and enables efficient, real-time expenditure management.

[1685] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1686] Step 1:

[1687] Collecting user spending information

[1688] Input: Account information for multiple electronic payment services registered by the user.

[1689] How it works: The server periodically retrieves spending data from the electronic payment service via an API using the requests library.

[1690] Data processing / calculation: Receive the acquired expenditure data in JSON format and extract detailed information such as payment amount, date, and store name.

[1691] Output: Extracted expenditure data.

[1692] Step 2:

[1693] Data Standardization

[1694] Input: The expenditure data collected in Step 1.

[1695] How it works: The server uses the pandas library to convert the spending data it receives into a unified format.

[1696] Data manipulation / calculation: Transform all data items into a consistent format, fill in missing data, or change data types.

[1697] Output: Standardized expenditure data.

[1698] Step 3:

[1699] Category Classification

[1700] Input: The standardized expenditure data from step 2.

[1701] How it works: The server uses a generative AI model (TensorFlow or Scikit-learn) to classify standardized spending data into categories.

[1702] Data processing / calculation: The generative AI model analyzes the content of expenditure data and automatically classifies it into categories such as "food," "transportation," and "entertainment."

[1703] Output: Spending data broken down by category.

[1704] Step 4:

[1705] household account book generation

[1706] Input: Expense data categorized in step 3.

[1707] How it works: The server connects to a MySQL database and generates a household ledger based on categorized spending data.

[1708] Data processing / calculation: Data is aggregated by month and category and stored in a database in a visually organized format.

[1709] Output: The latest household accounting data stored in the database.

[1710] Step 5:

[1711] Visualization and display of household finances

[1712] Input: The household budget data generated in step 4.

[1713] How it works: The server uses the matplotlib library to generate image files that display the household accounting data in visual formats such as bar graphs and pie charts.

[1714] Data processing / calculation: Formatting data for graph creation and processing it in a visually understandable format.

[1715] Output: An image file of the visualized household accounting data.

[1716] Step 6:

[1717] Displaying household accounts on user devices

[1718] Input: The household budget data visualized in Step 5.

[1719] Operation: An image file of the latest household accounting data is displayed through a smartphone app (Flutter / Dart) on the user's device.

[1720] Data processing / calculation: None

[1721] Output: Household accounting data displayed on a smartphone screen.

[1722] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1723] The present invention combines a system that automatically collects and standardizes a user's spending information, categorizes it using an AI model, and generates and displays a household account book with an emotion engine that recognizes the user's emotions. The following describes in detail the embodiments of the present invention.

[1724] Overall system configuration

[1725] The system consists of the following main components:

[1726] 1. User Device

[1727] A device that allows users to enter registration information and view household accounts.

[1728] Specifically, this includes smartphones, tablets, and PCs.

[1729] 2. Server

[1730] A central processing unit that receives data from users, collects, standardizes, and categorizes expenditure information, and creates a household ledger.

[1731] It accumulates expenditure data, classifies it using AI, analyzes big data, and recognizes emotions using an emotion engine.

[1732] 3. Emotion Engine

[1733] An engine that recognizes user emotions and reflects that information in the household accounting system.

[1734] Analyzes emotions based on various sensors and user input.

[1735] Program processing overview

[1736] Start:User Registration

[1737] When a user uses the system for the first time, they create an account and register the payment service and credit card they wish to use.

[1738] Server: Authentication and collaboration

[1739] The server authenticates the payment service or credit card entered by the user and cooperates to securely collect spending data.

[1740] Server: Data collection

[1741] The server automatically collects spending data from payment services and credit card companies, which are retrieved periodically using APIs.

[1742] Server: Data Standardization

[1743] The server converts the collected expenditure data into a unified format and organizes it into a form that can be managed centrally.

[1744] Server: AI-based category determination

[1745] The server uses AI models to automatically categorize standardized spending data into categories, such as "food," "transportation," and "entertainment."

[1746] Server: Household accounting

[1747] The server automatically generates a household ledger based on the categorized expenditure data, and the ledger is saved in a format that allows monthly and yearly data to be displayed visually in an easy-to-understand manner.

[1748] User device: Household account display

[1749] The user's terminal obtains the latest household accounting data from the server and displays it in real time.

[1750] Server: Emotion recognition

[1751] The emotion engine recognizes the user's emotions in various ways, such as facial recognition, voice analysis, and text input.

[1752] Server: Emotional reflection

[1753] The server then changes how the financial data is displayed based on the user's perceived emotions, for example, by displaying less warnings and advice about spending if the user is feeling stressed.

[1754] Specific examples

[1755] For example, if a user purchases a high-value item online and pays for it using a particular payment service, the following happens:

[1756] 1. A user purchases a high-value item

[1757] A user purchases an expensive electronic device from an online shop and completes the payment using an electronic payment service.

[1758] 2. The server collects data

[1759] The electronic payment service sends expenditure data for high-value items to the server.

[1760] 3. The server standardizes the data

[1761] The server converts this spending data into a unified format.

[1762] 4. The server uses AI to determine the category

[1763] The AI ​​model classifies this expense into the "high expense" category.

[1764] 5. The server creates the household account book

[1765] The server generates and stores an updated household account book that includes this expenditure.

[1766] 6. Emotion engine recognizes emotions

[1767] When a user opens the household accounting app, the system recognizes the user's emotions through the camera and microphone. For example, if the user is feeling anxious after making a purchase, the system will recognize that emotion.

[1768] 7. The server reflects emotions

[1769] The server can then adjust how the budget is displayed based on the perceived anxiety, for example by providing less warnings about spending and more gentle advice on how to manage spending.

[1770] In this way, the present invention allows the user to save the trouble of manually keeping a household account book, manage expenditures in real time, and receive display of the household account book and advice according to emotions.

[1771] The processing flow will be explained below.

[1772] Step 1:

[1773] The user downloads the application and logs in for the first time.

[1774] The user enters an email address and password to create a new account.

[1775] Step 2:

[1776] The user registers the payment service and credit card they wish to use.

[1777] The user enters the API key and authentication information for each service.

[1778] Step 3:

[1779] The server authenticates the payment service and credit card entered by the user.

[1780] The server uses an API to establish a secure connection with each payment service and obtain an authentication token.

[1781] Step 4:

[1782] The server automatically collects spending data from each payment service and credit card company.

[1783] The server periodically retrieves new spending data via the API and stores it in a database.

[1784] Step 5:

[1785] The server normalizes the collected spending data into a uniform format.

[1786] The server converts the expenditure data provided in different formats into a unified format, enabling centralized management.

[1787] Step 6:

[1788] The server uses AI models to categorize the standardized spending data.

[1789] The server automatically sorts the data into categories such as "food," "transportation," and "entertainment" based on the nature of the expenditure.

[1790] Step 7:

[1791] The server automatically generates a household account book based on the classified expenditure data.

[1792] The server creates monthly and yearly household budgets and simultaneously prepares the data for visualization.

[1793] Step 8:

[1794] The user's terminal obtains the latest household accounting data from the server and displays it.

[1795] When a user opens the application, it sends a request to the server API to retrieve and display the latest household accounting information.

[1796] Step 9:

[1797] The server uses an emotion engine to recognize the user's emotions.

[1798] The server collects and analyzes emotional data through the camera, microphone, and user text input.

[1799] Step 10:

[1800] The server changes the way the household account book data is displayed based on the recognized user emotion.

[1801] For example, the server may tone down spending warnings and display advice in a softer tone if the user is feeling anxious.

[1802] Step 11:

[1803] The server stores all collected spending data and emotion data for a long period of time and performs big data analysis.

[1804] The server anonymizes this data and uses it to strengthen security measures and improve marketing strategies and services.

[1805] Example 2

[1806] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1807] Many modern users find it difficult to manually manage their household accounts given their busy lives. Furthermore, conventional household accounting systems simply record income and expenditures and are unable to provide personalized feedback based on the user's emotions. As a result, users are unable to manage their spending in a way that fully reflects their own spending situation and stress level, making effective use of the system difficult.

[1808] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1809] In this invention, the server includes means for automatically collecting user expenditure information, means for standardizing the collected expenditure information, means for classifying the standardized expenditure information into categories, means for generating a household account book based on the classified expenditure information, means for displaying the household account book on the user's terminal, means for recognizing the user's emotion, and means for adjusting the display method of the household account book based on the recognized emotion. This saves the user the trouble of manually keeping a household account book and enables the user to receive feedback according to their emotion.

[1810] "User expenditure information" is data relating to monetary expenditures made by a user through various payment methods.

[1811] "Standardization means" is a process for converting expenditure information collected in various formats into a unified format.

[1812] A "categorization method" is an algorithm or technique for classifying standardized expenditure information into specific categories, such as "food" or "transportation."

[1813] The "means for generating a household account book" is a process for visually or numerically creating a household account book based on the classified expenditure information.

[1814] "User terminal" refers to the device used by the user to operate the system and view information, including smartphones, tablets, PCs, etc.

[1815] "Means for recognizing emotions" refers to technology for analyzing the emotional state of a user, and includes methods such as facial recognition, voice analysis, and text analysis.

[1816] The "means for adjusting the display method" is a process for changing the display contents of the household account book, warning messages, etc., based on the recognized user's emotions.

[1817] The present invention combines a system that automatically collects and standardizes a user's spending information, categorizes it using a generative AI model, and generates and displays a household account book with an emotion engine that recognizes the user's emotions. The following describes in detail an embodiment of this system.

[1818] Overall system configuration

[1819] The system consists of the following main components:

[1820] 1. User Device

[1821] This is a device that allows users to enter registration information and view their household account book.

[1822] Specifically, this includes devices such as smartphones, tablets, and PCs.

[1823] 2. Server

[1824] It is the central processing unit that receives data from users, collects, standardizes, and classifies expenditure information, and creates a household ledger.

[1825] It accumulates expenditure data and performs big data analysis, categorizes data using a generative AI model, and recognizes emotions using an emotion engine.

[1826] 3. Emotion Engine

[1827] It is an engine that recognizes the user's emotions and reflects that information in the household accounting system.

[1828] Analyzes emotions based on various sensors and user input.

[1829] Program processing overview

[1830] The server connects with payment service and credit card APIs to automatically collect user spending information. The server periodically collects this data and standardizes it into a unified format. It then uses a generative AI model to classify the standardized spending information into categories such as "food," "transportation," and "entertainment." Based on this classified data, the server generates a visually easy-to-understand household ledger. The generated household ledger data is stored on the server and displayed in real time on the user's device.

[1831] The emotion engine also recognizes the user's emotions through the camera and microphone and adjusts the way the household budget is displayed based on this. For example, if the user is feeling stressed, the server will tone down spending warnings and display advice on managing spending in a softer tone.

[1832] Specific examples

[1833] For example, if a user purchases an expensive item online and pays for it using a specific payment service, the following process will occur.

[1834] 1. A user purchases a high-value item

[1835] A user purchases an expensive electronic device from an online shop and completes the payment using an electronic payment service.

[1836] 2. The server collects data

[1837] The electronic payment service sends spending data for high-value items to the server, which collects this data through an API.

[1838] 3. The server standardizes the data

[1839] The server converts the collected expenditure data into a unified format, such as a unified date format and a unified amount format.

[1840] 4. The server uses AI to determine the category

[1841] The generative AI model classifies this expense in the "high expense" category and stores it in a database.

[1842] 5. The server creates the household account book

[1843] The server automatically generates a household account book based on the classified expenditure data, and the household account book sends monthly and yearly expenditure data to the user's device in a format that can be visually displayed.

[1844] 6. Emotion engine recognizes emotions

[1845] When a user opens the household accounting app, the app recognizes the user's emotions through the camera and microphone.

[1846] 7. The server reflects emotions

[1847] The server then adjusts the way the household budget is displayed based on the recognized emotion, for example, if the user is feeling anxious, it will display a message that reflects that emotion.

[1848] Prompt Sentence Examples

[1849] Possible input prompts for a generative AI model include:

[1850] "Describe how you collect spending data from a user's online purchase of expensive electronics and use a generative AI model to categorize it. Also, explain how the display of the household budget changes when the user is feeling anxious."

[1851] By using this method, the present invention can provide an expense management system that takes into consideration the feelings of the user.

[1852] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1853] Step 1:

[1854] Users create an account using their smartphone or PC and register the payment service and credit card information they wish to use. Based on this input information, the system initializes the user data. As an output, the account information is saved in a database.

[1855] Step 2:

[1856] The server performs authentication using the payment service and credit card information registered by the user. This authentication process is performed using the APIs of each payment service and credit card company. It receives the user's authentication information as input and generates an authentication token as output, completing the API integration setup.

[1857] Step 3:

[1858] The server periodically collects user spending data from payment services and credit card companies via configured APIs. The collection process involves periodically sending API requests as input and storing the received spending data on the server. The output is a temporary storage of spending information in its raw form.

[1859] Step 4:

[1860] The server converts the collected expenditure data into a unified format. Specifically, it unifies information such as the date and time of expenditure, amount, and store name provided in different formats. It receives the collected expenditure data as input and generates standardized expenditure data as output.

[1861] Step 5:

[1862] The server uses a generative AI model to classify the standardized expenditure data into categories, such as automatically sorting expenses for food, transportation, entertainment, etc. It receives standardized expenditure data as input and generates categorized expenditure data as output.

[1863] Step 6:

[1864] The server generates a household account book based on the classified expenditure data. The household account book is saved in a format that allows monthly and yearly data to be displayed visually. It receives classified expenditure data as input and generates household account book data as output.

[1865] Step 7:

[1866] The terminal receives the latest household accounting data sent from the server and displays it in real time. Users can view the household accounting data on their smartphones or PCs. The terminal receives household accounting data from the server as input and displays the household accounting data on the screen as output.

[1867] Step 8:

[1868] The server's emotion engine analyzes the user's facial expressions and voice using sensors such as a camera and microphone to recognize the user's emotions. It also extracts emotions from the user's text input. It receives data from the sensors as input and generates recognized emotion data as output.

[1869] Step 9:

[1870] The server adjusts the display of the household account book based on the recognized emotion data. For example, if the user is feeling anxious, it displays a message that takes the user's emotion into consideration or advice on spending management. It receives the recognized emotion data as input and generates an adjusted household account book display as output.

[1871] This process flow allows users to effortlessly manage their spending and receive emotional feedback.

[1872] (Application example 2)

[1873] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1874] While existing household accounting systems have been successful in collecting and classifying users' spending information, they lack appropriate feedback and display adjustments based on the user's emotions, making it difficult to properly manage spending when users feel stressed or anxious. Furthermore, emotion recognition technology needs to be combined to improve the user experience.

[1875] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically collecting user expenditure information, means for standardizing the collected expenditure information, means for classifying the standardized expenditure information into categories, means for generating a household account book based on the classified expenditure information, means for recognizing the user's emotions, means for adjusting the display method of the household account book based on the recognized user emotions, and means for displaying the household account book on the user's terminal. This enables feedback and display adjustment of expenditure management according to the user's emotions, improving the user experience and enabling appropriate expenditure management with reduced stress and anxiety.

[1876] "User expenditure information" refers to data related to the purchasing activities and payments made by the user, specifically the amount used, the date and time, the place of purchase, and other information.

[1877] "Standardization" refers to the process of converting data collected in different forms and formats into a consistent format, arranging it into a unified format for easier analysis and management.

[1878] "Categorizing" means dividing data into groups with similar characteristics based on specific criteria, such as "food expenses," "transportation expenses," and "entertainment expenses."

[1879] A "household account book" refers to a record of income and expenses of an individual or household, and refers to a written or digital record used to visualize the balance of income and expenses.

[1880] "User device" refers to the electronic device used by the user to access the system and view and operate information, specifically a smartphone, tablet, or PC.

[1881] "Means for recognizing emotions" refers to technology for analyzing and determining a user's emotional state, and refers to identifying a user's emotions using methods such as facial recognition technology, voice analysis, and text analysis.

[1882] "Means for adjusting the display method" refers to technology that appropriately changes the display format and content of information depending on the user's emotional state, such as switching to a display that reduces stress or anxiety.

[1883] "Means of accumulating and analyzing big data" refers to the technology of systematically accumulating large amounts of data, analyzing it using advanced analytical techniques, and extracting useful information and patterns.

[1884] "Means of encrypting data" refers to technology that converts collected data using a specific algorithm to protect it from third parties and prevent unauthorized access or leakage.

[1885] The system of the present invention provides a means for automatically collecting, standardizing, and categorizing a user's spending information and generating a household ledger, and also has the function of recognizing the user's emotions and adjusting the display method of the household ledger based on those emotions. The detailed configuration and implementation of each means are described below.

[1886] Overall system overview

[1887] Automatically collect user spending information

[1888] The server automatically collects spending data from the electronic payment services and credit cards registered by the user, including the ability to obtain spending information through a publicly available API.

[1889] Data Standardization

[1890] The server converts the collected spending data into a unified format, allowing for consistent processing of data from different sources.

[1891] Categorized

[1892] The server uses an AI model to categorize the standardized expenditure data, automatically dividing it into categories such as "food expenses," "transportation expenses," and "entertainment expenses."

[1893] Creating and displaying household accounts

[1894] The server automatically generates a household account book based on the classified expenditure data, and the user's device retrieves the household account book in real time and displays it visually in an easy-to-understand manner.

[1895] Emotion recognition

[1896] The user's device recognizes the user's emotions through a camera and microphone, using facial recognition technology and voice analysis. Specifically, OpenCV is used to detect faces and TensorFlow is used to analyze emotions.

[1897] Emotion-based display adjustment

[1898] The server adjusts the display of the household account book and the content of notifications based on the user's recognized emotions. For example, if the user is feeling stressed, spending warnings will be displayed more subtly.

[1899] Hardware and software used

[1900] Smartphones and tablets: These are devices that allow users to view spending information and recognize emotions.

[1901] Server: Performs central processing such as data collection, standardization, classification, emotion recognition, and household accounting generation.

[1902] API: Used to collect data from electronic payment services.

[1903] OpenCV: A library for face recognition.

[1904] TensorFlow: A machine learning library for running emotion recognition models.

[1905] Specific examples

[1906] For example, if a user makes a big purchase and then opens the app feeling anxious, the system might:

[1907] 1. User purchases a high-priced item: A user purchases a high-priced electronic device from an online shop and completes the payment using an electronic payment service.

[1908] 2. Data collection and standardization: The server collects spending data from electronic payment services and converts it into a unified format.

[1909] 3. Data Classification: Using an AI model, classify this spending data into “high-spending” categories.

[1910] 4. Generation of household account book: The server generates an up-to-date household account book based on the classified expenditure data and displays it on the user's terminal.

[1911] 5. Emotion Recognition: When a user opens the household accounting app, the system recognizes the user's emotions through the device's camera and microphone. For example, if the user is feeling anxious after making a purchase, that information will be recognized by the system.

[1912] 6. Display Adjustment: The server adjusts the display of the household budget based on the perceived anxiety, specifically by softening the spending warnings and softening the advice on how to manage spending.

[1913] Example prompts to input to the generative AI model

[1914] "If a user buys a big-ticket item and then opens the app and feels anxious, how should the system display a spending warning?"

[1915] In this way, the present invention allows the user to save time and effort in manually keeping a household account book, and allows the user to manage expenses in real time while receiving optimal display and advice according to emotions.

[1916] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1917] Step 1:

[1918] The user registers their electronic payment service and credit card information to collect expenditure data. The input is the user's credit card information and authentication information for the electronic payment service. This allows the system to perform authentication and prepare to securely collect expenditure data.

[1919] Step 2:

[1920] The server periodically and automatically collects user spending information through the APIs of registered electronic payment services and credit card companies. The input is the user's authentication information and raw spending data obtained from the API. The output is the collected spending data.

[1921] Step 3:

[1922] The server standardizes the collected expenditure data into a unified format. The input is the raw expenditure data obtained in step 2. Data processing involves converting data in different formats into a consistent format. The output is standardized expenditure data.

[1923] Step 4:

[1924] The server classifies the standardized expenditure data into categories using an AI model. The input is the standardized expenditure data. For data calculation, a generative AI model is used to classify each expenditure item into categories such as "food," "transportation," and "entertainment." The output is expenditure data classified by category.

[1925] Step 5:

[1926] The server generates a household ledger based on the classified expenditure data. The input is expenditure data classified by category. The data is processed by calculating the total income and expenditure and summarizing it in household ledger format. The output is household ledger data generated in a visually easy-to-understand format.

[1927] Step 6:

[1928] The user's terminal receives the generated household accounting data and displays it on the user interface. The input is the household accounting data sent from the server. The terminal displays this in real time. The output is visual household accounting information displayed to the user.

[1929] Step 7:

[1930] The user's device uses a camera and microphone to recognize the user's emotions. The input is camera video and audio data. Specifically, the system detects faces using OpenCV and performs emotion analysis using a TensorFlow model. The output is analyzed user emotion data.

[1931] Step 8:

[1932] The server adjusts the display method of the household account book based on the recognized emotion data. The input is the user's emotion data and household account book data. Specifically, if the emotion is "anxiety," the server adjusts the display method, such as displaying spending warnings more subdued. The output is the household account book data in the adjusted display format.

[1933] Step 9:

[1934] The adjusted household accounting data is redisplayed on the user's device. The input is the adjusted household accounting data. The output is the household accounting information redisplayed to the user. The user can confirm that the display content has been adjusted to take their emotions into consideration.

[1935] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1936] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1937] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1938] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1939] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1940] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1941] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1942] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1943] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1944] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1945] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1946] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1947] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1948] 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.

[1949] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1950] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1951] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1952] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1953] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1954] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1955] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1956] The following is further disclosed regarding the above embodiment.

[1957] (Claim 1)

[1958] means for automatically collecting user spending information;

[1959] a means of standardizing the expenditure information collected;

[1960] a means of categorizing standardized expenditure information;

[1961] a means for generating a household account book based on the classified expenditure information;

[1962] A means for displaying the household account book on a user's terminal;

[1963] A system including:

[1964] (Claim 2)

[1965] 2. The system according to claim 1, further comprising means for accumulating and analyzing the collected expenditure data as big data.

[1966] (Claim 3)

[1967] 10. The system of claim 1, further comprising means for encrypting the collected spending data to ensure its security.

[1968] (Claim 4)

[1969] 10. The system of claim 1, further comprising means for converting the collected spend data into a standard format.

[1970] (Claim 5)

[1971] 10. The system of claim 1, further comprising means for using an AI model to classify spending information into categories.

[1972] "Example 1"

[1973] (Claim 1)

[1974] means for automatically collecting user spending information;

[1975] a means of standardizing the expenditure information collected;

[1976] a means for categorizing the standardized expenditure information into categories using an artificial intelligence model;

[1977] a means for generating a household account book based on the classified expenditure information;

[1978] A means for displaying the household account book on a user's terminal;

[1979] A means of collecting spending data using APIs;

[1980] A system including:

[1981] (Claim 2)

[1982] 2. The system according to claim 1, further comprising means for accumulating and analyzing the collected expenditure data as big data.

[1983] (Claim 3)

[1984] 10. The system of claim 1, further comprising means for encrypting the collected spending data to ensure its security.

[1985] "Application Example 1"

[1986] (Claim 1)

[1987] means for automatically collecting user spending information;

[1988] a means of standardizing the expenditure information collected;

[1989] A means of categorizing standardized spending information using a generative AI model; and

[1990] a means for generating a household account book based on the classified expenditure information;

[1991] A means for displaying the household account book on a user's terminal;

[1992] means for analyzing the user's expenditure information and graphically displaying the expenditure status;

[1993] A system including:

[1994] (Claim 2)

[1995] 2. The system according to claim 1, further comprising means for accumulating and analyzing the collected expenditure data as big data.

[1996] (Claim 3)

[1997] 10. The system of claim 1, further comprising means for encrypting the collected spending data to ensure its security.

[1998] "Example 2: Combining Emotion Engines"

[1999] (Claim 1)

[2000] means for automatically collecting user spending information;

[2001] a means of standardizing the expenditure information collected;

[2002] a means of categorizing standardized expenditure information;

[2003] a means for generating a household account book based on the classified expenditure information;

[2004] A means for displaying the household account book on a user's terminal;

[2005] means for recognizing a user's emotion;

[2006] a means for adjusting the display of the household account book based on the recognized emotion;

[2007] A system including:

[2008] (Claim 2)

[2009] 2. The system according to claim 1, further comprising means for accumulating and analyzing the collected expenditure data as big data.

[2010] (Claim 3)

[2011] 10. The system of claim 1, further comprising means for encrypting the collected spending data to ensure its security.

[2012] "Application example 2 when combining emotion engines"

[2013] (Claim 1)

[2014] means for automatically collecting user spending information;

[2015] a means of standardizing the expenditure information collected;

[2016] a means of categorizing standardized expenditure information;

[2017] a means for generating a household account book based on the classified expenditure information;

[2018] means for recognizing a user's emotion;

[2019] a means for adjusting the display method of the household account book based on the recognized user's emotion;

[2020] A means for displaying the household account book on a user's terminal;

[2021] A system including:

[2022] (Claim 2)

[2023] 2. The system according to claim 1, further comprising means for accumulating and analyzing the collected expenditure data as big data.

[2024] (Claim 3)

[2025] 10. The system of claim 1, further comprising means for encrypting the collected spending data to ensure its security. [Explanation of symbols]

[2026] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for automatically collecting user spending information; a means of standardizing the expenditure information collected; a means of categorizing standardized expenditure information; a means for generating a household account book based on the classified expenditure information; A means for displaying the household account book on a user's terminal; A system including:

2. The system according to claim 1 , further comprising means for accumulating and analyzing the collected expenditure data as big data.

3. 10. The system of claim 1, further comprising means for encrypting the collected spending data to ensure its security.

4. 10. The system of claim 1, further comprising means for converting the collected spend data into a standard format.

5. 10. The system of claim 1, further comprising means for using an AI model to classify spending information into categories.

Images