system

Abstract

Provide a system. 【Solution means】 Means for obtaining household financial information, Means for classifying the obtained financial information, Means for analyzing the classified information to identify savings potential, Means for generating advice based on the identified areas where savings are possible, Means for notifying the user of the generated advice, Means for collecting and providing discount information and coupons, Means for analyzing the budget achievement status and providing feedback, A system including the above.

Description

【Technical Field】 【0001】 The technology of the present disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 In the financial situation of a household, due to soaring prices and stagnant wages, it has become difficult to manage the household budget, and there is a problem that efficient and effective savings are required. Also, with current means, detailed expenditure analysis and provision of immediate savings advice are not sufficiently carried out, so users are unable to manage their household budgets appropriately. Furthermore, this makes it difficult to live a secure life. 【Means for Solving the Problems】 【0005】 The present invention solves the aforementioned problems by providing a system that includes means for acquiring household financial information, means for classifying the acquired financial information, means for analyzing the classified information to identify potential savings, means for generating advice based on the identified areas where savings are possible, means for notifying the user of the generated advice, means for collecting and providing discount information and coupons, and means for analyzing budget achievement status and providing feedback. 【0006】 "Means of obtaining household financial information" refers to a function that collects transaction history and balance information from the user's bank accounts and credit cards using APIs, etc. 【0007】 "Means for classifying acquired financial information" refers to algorithms and processes for automatically sorting collected transaction data into categories such as food expenses, transportation expenses, and utility expenses. 【0008】 "Methods for analyzing classified information" refers to the process of using classified spending data to identify spending patterns and abnormal spending, and to find items and trends where savings can be made. 【0009】 "Methods for identifying potential savings" refers to the process of finding out where costs can be reduced by comparing them with the analysis results. 【0010】 "Means of generating advice" refers to functions for formulating specific action advice and suggestions based on identified areas where savings can be made. 【0011】 "Means of notifying users of advice" refers to interfaces and functions that notify users of generated money-saving advice on their devices and encourage them to take action. 【0012】 "Means for collecting and providing discount information and coupons" refers to a system or process for aggregating discount information and coupon data from the market and partners and providing it to users in a format suitable for them. 【0013】 "Means for analyzing budget achievement and providing feedback" refers to a function that monitors actual spending against the budget set by the user and provides feedback on the degree of achievement and areas for improvement. [Brief explanation of the drawing] 【0014】 [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined. 【Embodiments for Carrying Out the Invention】 【0015】 Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings. 【0016】 First, the terms used in the following description will be explained. 【0017】 In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc. 【0018】 In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0019】 In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc. 【0020】 In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark). 【0021】 In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or." 【0022】 [First Embodiment] 【0023】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0024】 As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server. 【0025】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0026】 The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52. 【0027】 The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input. 【0028】 The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor. 【0029】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54. 【0030】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0031】 As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30. 【0032】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0033】 In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0034】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0035】 This invention is an AI system that manages household financial information in real time and provides users with effective saving methods. This system consists of a terminal, a server, and a user working together, with each module performing the following processes. 【0036】 Data collection methods 【0037】 Users link their bank accounts and credit cards to the application via their device. The device periodically retrieves transaction data via APIs of financial institutions authorized by the user and sends that data to the server. 【0038】 Forms of data classification and analysis 【0039】 The server automatically categorizes received transaction data using machine learning algorithms. For example, grocery purchases are categorized as "food expenses," and train fares are categorized as "transportation expenses." After categorization, the server analyzes the data to check for spending trends and any unusual expenditures. 【0040】 Forms of generating and notifying savings advice 【0041】 Based on the analysis results, the server identifies areas where savings can be made and generates advice. For example, "You can save 5,000 yen per month by reducing eating out from three times a week to once a week." The terminal notifies the user of this advice and sets reminders as needed. 【0042】 Discount information and coupon distribution methods 【0043】 The server collects discount information and coupons from partners and stores them in a database. It selects information appropriate to the user's spending patterns and notifies the device. For example, it might provide "This Week's Supermarket Discount Coupons." 【0044】 Budget progress management and feedback methods 【0045】 The server monitors the progress of the user-defined budget in real time and analyzes the degree of achievement. At the end of the month or as needed, the terminal provides the user with feedback on the achievement status and suggestions for improvement. This allows the user to quickly respond to and improve individual budget items. 【0046】 Through these various functions, the present invention provides a useful means for users to efficiently manage their daily expenses and improve their actual household financial situation. 【0047】 The following describes the processing flow. 【0048】 Step 1: 【0049】 The user links their bank account and credit card information to the device. The device periodically retrieves transaction data through APIs of financial institutions authorized by the user. The device temporarily stores the retrieved data and securely sends it to the server. 【0050】 Step 2: 【0051】 The server receives transaction data sent from the terminal. To analyze the received data, the server uses machine learning algorithms to automatically classify the data into categories such as food expenses, transportation expenses, and utility expenses. 【0052】 Step 3: 【0053】 The server analyzes the classified data to identify spending trends and anomalies. Here, the server compares the current data with historical data, paying particular attention to areas of change. If an anomaly is detected, it initiates a process to investigate its cause. 【0054】 Step 4: 【0055】 Based on the analysis results, the server identifies areas where savings can be made. The server generates specific advice, such as "Your food expenses are over budget, so reduce the frequency of eating out." 【0056】 Step 5: 【0057】 The server sends the generated advice to the terminal. The terminal notifies the user of the advice and gives them the option to set a reminder. 【0058】 Step 6: 【0059】 The server collects discount information and coupons from partners and the market, and stores this data in a database. The server then selects relevant discount information based on the user's spending patterns. 【0060】 Step 7: 【0061】 The device notifies the user of discount information and coupons sent from the server. Users can then use this information to make more advantageous purchases. 【0062】 Step 8: 【0063】 The server continuously monitors the user's budget achievement. The server analyzes the progress of spending against the budget and sends feedback to the device. The device notifies the user of the feedback at the end of the month or as needed. 【0064】 (Example 1) 【0065】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0066】 In household financial management, there are challenges such as the difficulty of monitoring individual expenditure items and managing budgets in real time. In particular, reducing unnecessary spending and finding effective saving methods is difficult for many users. Furthermore, efficiently obtaining and utilizing discount and coupon information is also a problem. This invention aims to solve these problems and provide a system to support the sound management of household finances. 【0067】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0068】 In this invention, the server includes means for acquiring information from financial institutions, means for classifying financial data into categories using machine learning techniques, and means for identifying areas where savings can be made and generating advice for saving. This enables real-time spending monitoring and evaluation of budget achievement in household financial management. 【0069】 "Financial institution information" refers to account information and transaction data of users provided by financial institutions such as banks and credit card companies. 【0070】 "Machine learning technology" refers to techniques in which algorithms automatically find patterns based on large amounts of data, and specifically refers to techniques used for data classification and prediction. 【0071】 "Financial data" refers to all information about a user's daily income and expenses, and specifically to data related to financial transactions. 【0072】 "Categorizing" means separating collected data based on specific criteria, such as classifying it as "food expenses" or "transportation expenses." 【0073】 "Areas where savings can be made" refers to the portion of a user's spending where waste can be reduced. 【0074】 "Generating savings advice" refers to the process of creating specific advice for users to reduce their spending. 【0075】 "Real-time spending monitoring" refers to the ability to instantly track and manage a user's current spending status. 【0076】 This invention describes a system for efficiently managing household financial information and providing users with effective saving methods. This system consists of collaboration between a server, terminals, and users. 【0077】 Users link their bank accounts and credit cards to the application using their device. The device is responsible for periodically retrieving transaction data from user-authorized financial institutions via APIs and sending it to the server. This communication is conducted using SSL and TLS protocols to ensure security. 【0078】 The server categorizes received transaction data using machine learning techniques. For this purpose, it can utilize machine learning libraries such as scikit-learn and TENSORFLOW®. The data is automatically sorted into categories such as "food expenses" and "transportation expenses." This allows the server to analyze financial data from multiple perspectives, detecting unnecessary spending and predicting spending trends. Based on this analysis, the server identifies areas where savings can be made and generates specific savings advice. This advice is formulated in a user-friendly format using natural language generation models. 【0079】 The generated advice is notified to the user via their device. Based on this notification, the user can adjust their actions and set reminders if necessary. The server also collects discount information and coupons from partners in real time, providing users with advantageous offers tailored to their spending patterns. Database systems such as PostgreSQL and MongoDB are used for database management. 【0080】 Furthermore, the server monitors the progress of the user's budget in real time and evaluates the degree of achievement. For example, if a user sets a budget of 30,000 yen for food expenses, the system periodically evaluates the progress based on the plan and provides feedback to the user by notifying them via their terminal that "10,000 yen remains to reach the target budget." 【0081】 An example of a prompt for this system would be, "Analyze areas where savings can be made based on next month's spending forecast and generate specific advice." This allows users to achieve cost-effective household financial management. 【0082】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0083】 Step 1: 【0084】 The user links information from a financial institution to the application via their device. The user ID and authentication information are entered as input, and an API connection from the financial institution is established as output. Specifically, the device obtains the user's authentication information and generates an API key, enabling subsequent data retrieval. 【0085】 Step 2: 【0086】 The terminal periodically retrieves transaction data using the financial institution's API and sends it to the server. The input includes the transaction ID, amount, and date obtained from the financial institution, and the output is this transaction data transferred to the server. Specifically, the terminal automatically makes API calls at a fixed time each day and securely transmits the retrieved data to the server using SSL / TLS. 【0087】 Step 3: 【0088】 The server classifies received transaction data into categories using machine learning techniques. The input consists of transaction details and amounts, and the output generates category labels (e.g., "Food Expenses," "Transportation Expenses"). Specifically, the server uses scikit-learn and a Naive Bayes classifier to analyze and classify this data. 【0089】 Step 4: 【0090】 The server analyzes spending trends based on classified data and detects abnormal spending. Transaction history from the past few months is used as input, and a report of abnormal spending is generated as output. Specifically, the server uses TensorFlow to build a predictive model and identify spending that deviates from the normal range. 【0091】 Step 5: 【0092】 Based on the analysis results, the server identifies areas where savings can be made and generates savings advice. The inputs are spending trends and reports on unusual spending, and the output is savings advice. Specifically, the server uses a natural language generation model to put the advice into text and prepares it for delivery to the user. 【0093】 Step 6: 【0094】 The device notifies the user of the generated savings advice and sets reminders as needed. The input is advice from the server, and the output is a notification displayed on the user's device. Specifically, the device sends a push notification to the user and provides a UI for setting reminders. 【0095】 Step 7: 【0096】 The server collects discount information and coupons from partners and provides them to users. The input is an information feed from partners, and the output is the extraction of coupons relevant to the user. Specifically, the server periodically scans the partner database and selects information that matches the user's spending patterns. 【0097】 Step 8: 【0098】 The server monitors the user's budget progress in real time and provides feedback. It takes budget setting data and expenditure data as input and generates achievement reports as output. Specifically, the server evaluates progress and sends weekly review reports to the user's terminal. 【0099】 (Application Example 1) 【0100】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0101】 Modern households are required to efficiently manage financial information and reduce unnecessary spending. However, due to the busyness of daily life, manually collecting and analyzing financial data is burdensome, and it is also difficult to properly identify ways to save money. Furthermore, systems with visual and voice interfaces are limited, resulting in a lack of intuitive and convenient financial management tools for users. 【0102】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0103】 In this invention, the server includes means for acquiring household financial data and analyzing it using a voice input device, means for providing the user with the classified financial data through voice input and visual display, and means for identifying and proposing savings strategies based on the financial data analyzed in real time. This makes it possible for users to intuitively and easily grasp their own financial situation in their daily lives and immediately understand how to save money. 【0104】 "Financial data" refers to data that includes information about household or individual income and expenses. 【0105】 A "voice input device" is a device used to capture and process voice as digital data. 【0106】 "Analysis" is the process of breaking down obtained data in order to understand its content and characteristics. 【0107】 "Visual display" refers to a method of representing information visually on a screen, such as a display. 【0108】 "Classification" is the process of dividing data into different categories based on specific criteria. 【0109】 A "frugality policy" is a specific strategy for reducing unnecessary spending and promoting efficient use of funds. 【0110】 "Real-time" refers to the immediate processing or response that takes place as soon as data is generated. 【0111】 A "suggestion" is specific advice or guidance provided to encourage users to take action. 【0112】 "Users" refer to individuals or households that actually use the system or service. 【0113】 The system used to implement this application is designed to streamline household financial management. Users first access the system using a terminal equipped with a voice input device. The terminal recognizes the user's voice commands and collects household financial data. This includes obtaining bank account transactions and credit card usage data through financial institution APIs. 【0114】 The server analyzes the acquired data using machine learning algorithms to classify income and expenses. Libraries such as TensorFlow and PyTorch can be used for this purpose. Natural language processing APIs are used for speech recognition. The analysis results are displayed to the user visually in real time and also provided via audio. Expenditure trends are visualized in graphs and tables, promoting intuitive understanding for the user. 【0115】 The server then generates savings strategies based on the user's spending patterns. These strategies include specific suggestions, such as "You can save 5,000 yen per month by reducing your dining out frequency from twice a week to once a week." These suggestions are communicated to the user via voice notifications. 【0116】 The server also collects discount information and coupons from multiple partner sources and notifies users of information selected to match their interests. For example, it might be provided in the form of "This week's discount coupons for your nearest supermarket." 【0117】 Furthermore, the server monitors the progress of the set budget in real time and provides feedback. By displaying budget achievement status as visual feedback and notifying users of areas for improvement, users can quickly improve their usage. 【0118】 For example, if a user asks, "How much are my food expenses this month?", the system will respond verbally, "Currently, it's 30,000 yen," and visually display a graph showing the monthly food expense trend on the screen. As an example of a prompt to the generating AI model, if you input, "Please explain my transportation expenses for this month," the system will generate a comprehensive analysis of transportation expenses and savings suggestions. 【0119】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0120】 Step 1: 【0121】 The user enters voice commands via a terminal. A voice input device converts these commands into digital data, and a speech recognition API performs natural language processing to interpret the user's questions and instructions. The input is voice command data, and the output is the parsed instructions in text format. 【0122】 Step 2: 【0123】 The device sends requests to financial institutions' APIs with the user's permission to retrieve household financial data. This retrieves bank account and credit card transaction information. The input is user authentication information, and the output is transaction data. 【0124】 Step 3: 【0125】 The server processes the acquired transaction data through a machine learning algorithm. A data classification algorithm is used to categorize each transaction, such as food expenses or transportation costs. The input is raw transaction data, and the output is categorized data. 【0126】 Step 4: 【0127】 The server analyzes the classified data and generates savings strategies. This analysis includes identifying spending patterns and detecting anomalies. The generating AI model suggests necessary savings and outputs specific advice. The input is classified transaction data, and the output is specific savings advice. 【0128】 Step 5: 【0129】 The server collects discount information and coupons from partner sources and selects and presents appropriate options based on the user's spending patterns. The input is discount information from partners, and the output is coupon information tailored to the user's interests. 【0130】 Step 6: 【0131】 The server monitors the progress of the set budget in real time and generates feedback based on the collected data. It notifies the user of achievements and areas for improvement through visual displays and audio. Inputs are the latest expenditure data and budget information, while outputs are visual and audio feedback. 【0132】 Step 7: 【0133】 The user is notified, and suggested savings strategies and coupons are presented visually and audibly through the device. Based on the displayed information, the user can adjust their financial behavior. The input is savings advice and coupon information, and the output is the user's awareness and behavioral changes. 【0134】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0135】 This invention provides more personalized savings advice by combining a system for managing household financial information with an emotion engine that recognizes user emotions. This system effectively manages household spending data and uses that data to provide more accurate advice to the user. 【0136】 The system consists of a terminal, a server, and an emotion engine. The server processes financial data received from the terminal and classifies the data using machine learning algorithms. The classified data is analyzed on the server to detect spending trends and anomalies. Based on the analysis results, the server generates optimal saving advice and notifies the user through the terminal. 【0137】 The emotion engine recognizes the user's emotions in real time. This emotion information is obtained by inferring the emotional state based on data such as the user's actions while operating the device, voice input, and text input. Based on this information, the server adjusts the content and timing of advice and sets reminders that are tailored to the user's emotions. Therefore, it is possible to offer savings suggestions in a way that is easy for the user to accept. 【0138】 For example, suppose users tend to spend more at the end of the month when they are more stressed. In this case, the emotion engine can detect the user's stress, and the server can send budget advice and suggest ways to relax, thereby promoting better spending management. 【0139】 By combining this with an emotional engine, the system can enhance personalized care for users and improve the efficiency of household financial management. This allows users to manage their finances more systematically and with greater peace of mind, taking their own emotional state into consideration. 【0140】 The following describes the processing flow. 【0141】 Step 1: 【0142】 Users link their bank accounts and credit cards to the device. The device periodically retrieves transaction data from the user's financial institutions and sends it to the server. 【0143】 Step 2: 【0144】 The server receives the acquired transaction data. Next, the server uses a machine learning algorithm to automatically classify the data into categories such as food expenses, transportation expenses, and utility expenses. 【0145】 Step 3: 【0146】 The server analyzes the categorized data to identify spending trends and anomaly patterns. Based on the analysis, the server identifies areas where savings can be made. 【0147】 Step 4: 【0148】 The server generates savings advice and sends it to the terminal. The advice includes suggestions for specific behavioral changes. 【0149】 Step 5: 【0150】 The emotion engine uses device data to recognize the user's current emotional state. As the user interacts with the device, emotion data is collected when they use voice input or send text messages, and their emotions are inferred in real time. 【0151】 Step 6: 【0152】 The server receives the output from the emotion engine and adjusts the content of advice and the timing of notifications based on the emotional information. For example, when the user is relaxed, it might send advice about the next month's budget earlier than scheduled. 【0153】 Step 7: 【0154】 The device notifies the user of emotionally tailored advice. The user can review the notified advice and add reminders to make it easier to take action. 【0155】 Step 8: 【0156】 The server evaluates whether the advice and notifications sent were effective for the user, and records and analyzes the data for future improvements. It also evaluates the relationship between the user's emotional state and spending behavior, and uses this information to generate future advice. 【0157】 (Example 2) 【0158】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0159】 Traditional household financial information management systems have struggled to provide personalized saving advice that takes into account the user's emotional state. Because they cannot provide advice at the appropriate time and with the right content based on the user's emotions, effective spending management is hindered. Therefore, there is a need to develop a system that enables financial management that reflects the user's emotions. 【0160】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0161】 In this invention, the server includes means for recognizing the user's emotional state, means for adjusting the results of financial information analysis using the recognized emotional information, and means for generating personalized advice based on the adjusted analysis results. This enables the provision of effective financial management and spending advice tailored to the user's individual emotional state. 【0162】 "Means for recognizing the user's emotional state" refers to a function that analyzes voice input and operation data to identify the user's psychological state and emotions. 【0163】 "Means for adjusting the results of financial information analysis" refers to a function that modifies the evaluation and analysis of existing financial data based on perceived emotional states. 【0164】 "Means of generating personalized advice" refers to a function that creates guidelines for saving and managing spending that are tailored to each user's individual circumstances and feelings, based on the adjusted analysis results. 【0165】 "Means of obtaining household financial information" refers to the function of collecting data such as income and expenses related to household finances. 【0166】 "Means for classifying acquired financial information" refers to the function of organizing collected financial data by category. 【0167】 "Means for identifying potential savings" refers to the function of finding redundancy and waste from analyzed data and determining areas for savings. 【0168】 "Means of notifying users of generated advice" refers to a function that communicates the created guidelines and suggestions to users in an appropriate manner. 【0169】 "Means of collecting and providing discount information and coupons" refers to a function that collects and presents advantageous information obtained from markets and stores to users. 【0170】 "Means of analyzing budget achievement and providing feedback" refers to a function that verifies the actual income and expenditure situation against the budget and provides advice to users based on the results. 【0171】 "Means for detecting abnormal spending" refers to a function that identifies and warns of consumer behavior that deviates from normal patterns. 【0172】 "Methods for automatically classifying financial information using machine learning algorithms" refers to a function that utilizes artificial intelligence technology to automatically organize collected financial data. 【0173】 This invention is designed to effectively support users' financial management in their homes. The system primarily consists of a server, terminals, and an emotion engine. Specific hardware includes smartphones and personal computers that enable user-initiated data entry. Software includes an emotion engine for sentiment analysis, machine learning algorithms, and data analysis tools running on the server. 【0174】 The server manages financial data sent from users in the cloud. Data is sent from the terminal to the server using a secure protocol (e.g., SSL / TLS). The server classifies this data into categories using machine learning algorithms (e.g., scikit-learn) and analyzes user consumption patterns. Database management systems (e.g., PostgreSQL) and data analysis libraries (e.g., Pandas, NumPy) are used for the analysis. 【0175】 The emotion engine utilizes voice input and user actions to recognize the user's emotional state in real time. This data is analyzed using a generative AI model. Based on this input, the emotion engine infers the user's psychological state and sends that information to the server. 【0176】 As a concrete example, consider a case where a user tends to feel stressed at the end of the month and increases their spending. The emotion engine analyzes voice and operation data entered from the device to recognize this stress level. Based on this information, the server generates and notifies the user of advice such as, "It may be difficult to meet this month's budget, but please try some relaxation techniques to alleviate stress." This allows the user to receive appropriate financial management advice based on their emotions. 【0177】 An example of a prompt message is, "Generate the best savings advice for this week based on the user's spending data and emotional state." This allows the system to provide advice tailored to each user's situation. 【0178】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0179】 Step 1: 【0180】 Data collection and input 【0181】 Users input their daily income and expense information into their device. Specifically, they use a smartphone app or web interface to enter the amount, expense category (daily necessities, transportation, etc.), and date. This data is temporarily stored on the device and prepared for later processing. 【0182】 Input: User spending and income information 【0183】 Output: Financial data stored on the device 【0184】 Step 2: 【0185】 Data transmission and classification 【0186】 The terminal transmits financial data collected from the user to the server via the internet. The data is sent securely using a secure communication protocol (SSL / TLS). The server then uses a machine learning algorithm (e.g., scikit-learn) to classify the received data into expenditure categories. During this classification process, the characteristics of the data are extracted and mapped to pre-defined categories. 【0187】 Input: Financial data sent from the terminal 【0188】 Output: Data categorized on the server. 【0189】 Step 3: 【0190】 Data analysis 【0191】 The server uses the classified data to analyze consumption patterns. A database management system (e.g., PostgreSQL) is used to calculate trends and outliers in the collected data, identifying consumption peaks and irregular spending. The data is analyzed using statistical methods with libraries such as Pandas and NumPy. 【0192】 Input: Classified financial data 【0193】 Output: Analysis results of consumption patterns 【0194】 Step 4: 【0195】 Recognition of emotions 【0196】 The emotion engine analyzes the user's emotions in real time based on device operation logs and voice input data. It uses a generative AI model to identify emotional states (e.g., stress, happiness) through text analysis and voice acoustic analysis. The emotional data is sent to a server for use in subsequent processes. 【0197】 Input: Operation data and voice data to the terminal 【0198】 Output: Emotional state data sent to the server 【0199】 Step 5: 【0200】 Generating and notifying advice 【0201】 The server generates personalized savings advice based on the analysis of financial data and the user's emotional state. This advice may include specific suggestions such as, "We recommend relaxing activities at the end of the month." The system also considers the user's emotional state and spending patterns to create an optimal notification schedule. The generated advice is then communicated to the user via their device. 【0202】 Input: Analysis results and emotional state data 【0203】 Output: Advice message notified to the user 【0204】 (Application Example 2) 【0205】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal". 【0206】 Conventional household financial information management systems often fail to provide sufficient savings advice because they do not take into account the emotional state of each user. This can result in insufficient user satisfaction and savings. Furthermore, because they do not utilize emotional information, the timing and content of the advice may not be in line with the user's psychological state, which is a problem. 【0207】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0208】 In this invention, the server includes means for acquiring household financial information, means for classifying the acquired financial information, and means for inferring the user's psychological state and adjusting the timing and content of appropriate advice. This enables personalized saving advice tailored to the user's emotional state to be provided in real time, resulting in more effective spending management. 【0209】 "Economic information" refers to data about a household's financial status, such as income, expenses, assets, and liabilities. 【0210】 "User psychological state" refers to the emotions and moods that users experience in specific situations, and these influence their behavior and reactions when using the system. 【0211】 "Savings advice" refers to specific suggestions and instructions for controlling or optimizing spending, provided based on an individual user's financial information and psychological state. 【0212】 "Real-time" refers to a time standard that involves processing or responding immediately and without delay, based on the current situation and the latest data. 【0213】 A "machine learning algorithm" is a computational method that analyzes large amounts of data to find patterns and uses the learned results to predict and classify new data. 【0214】 "Adjusting the timing and content of appropriate advice" refers to a function that changes the timing and content of notifications according to the user's psychological state, thereby supporting more effective spending management. 【0215】 The system for realizing this invention mainly consists of three elements: a server, a terminal, and a user. The server understands the household's financial information and the user's psychological state, and provides optimal saving advice. The terminal functions as an interface for user operation and transmits and receives data with the server. Through the terminal, the user can check their financial information and advice and use it to manage their daily expenses. 【0216】 The server is primarily built using the Python programming language and utilizes TensorFlow, a machine learning library, for data analysis. On the server, a generative AI model learns based on users' economic information and psychological state, generating personalized advice for each user. A web application using Flask supports communication between the server and the user terminal. 【0217】 Specifically, user psychological data is collected from sensors on the device. This data is sent to a server in real time and processed by machine learning algorithms. Based on the resulting psychological state, the content and timing of advice are adjusted. For example, during periods of high stress, helpful information and money-saving tips that promote relaxation are suggested. 【0218】 This system enables users to manage their household finances in a planned and secure manner, taking their own emotional state into consideration. 【0219】 An example of a prompt message is: "If the user is feeling stressed, please provide relaxing money-saving advice. Sentiment data is updated in real time." 【0220】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0221】 Step 1: 【0222】 The device receives financial information from the user as input. The user records spending and income data through a household budgeting app. This information is immediately sent to the server. 【0223】 Step 2: 【0224】 The server uses the received economic information to classify the data. Machine learning algorithms are used to categorize spending items and trends, and to extract specific patterns. This allows for the automatic detection of spending trends and anomalies. 【0225】 Step 3: 【0226】 The device collects data to understand the user's psychological state. This is primarily done through sensors built into the device, using the smartphone's camera and microphone to analyze the user's facial expressions and tone of voice. The analysis results are sent to a server. 【0227】 Step 4: 【0228】 The server uses a generative AI model to analyze data based on the user's psychological state. It integrates and analyzes psychological data and economic information to generate personalized savings advice. In this process, appropriate advice is designed based on prompt statements. 【0229】 Step 5: 【0230】 The server sends the generated advice to the terminal. The terminal notifies the user of the advice. Through the notification, the user can check specific saving methods tailored to their situation and the coupon information offered. 【0231】 Step 6: 【0232】 Users adjust their daily financial activities based on the advice they receive. They periodically send feedback from their device to the server to reflect their income, expenses, and satisfaction levels. This feedback is used to improve future advice. 【0233】 The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data. 【0234】 Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0235】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14. 【0236】 [Second Embodiment] 【0237】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0238】 As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server. 【0239】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0240】 The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52. 【0241】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0242】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0243】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0244】 Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0245】 The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30. 【0246】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0247】 In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0248】 Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal". 【0249】 This invention is an AI system that manages household financial information in real time and provides users with effective saving methods. This system consists of a terminal, a server, and a user working together, with each module performing the following processes. 【0250】 Data collection methods 【0251】 Users link their bank accounts and credit cards to the application via their device. The device periodically retrieves transaction data via APIs of financial institutions authorized by the user and sends that data to the server. 【0252】 Forms of data classification and analysis 【0253】 The server automatically categorizes received transaction data using machine learning algorithms. For example, grocery purchases are categorized as "food expenses," and train fares are categorized as "transportation expenses." After categorization, the server analyzes the data to check for spending trends and any unusual expenditures. 【0254】 Forms of generating and notifying savings advice 【0255】 Based on the analysis results, the server identifies areas where savings can be made and generates advice. For example, "You can save 5,000 yen per month by reducing eating out from three times a week to once a week." The terminal notifies the user of this advice and sets reminders as needed. 【0256】 Discount information and coupon distribution methods 【0257】 The server collects discount information and coupons from partners and stores them in a database. It selects information appropriate to the user's spending patterns and notifies the device. For example, it might provide "This Week's Supermarket Discount Coupons." 【0258】 Budget progress management and feedback methods 【0259】 The server monitors the progress of the user-defined budget in real time and analyzes the degree of achievement. At the end of the month or as needed, the terminal provides the user with feedback on the achievement status and suggestions for improvement. This allows the user to quickly respond to and improve individual budget items. 【0260】 Through these various functions, the present invention provides a useful means for users to efficiently manage their daily expenses and improve their actual household financial situation. 【0261】 The following describes the processing flow. 【0262】 Step 1: 【0263】 The user links their bank account and credit card information to the device. The device periodically retrieves transaction data through APIs of financial institutions authorized by the user. The device temporarily stores the retrieved data and securely sends it to the server. 【0264】 Step 2: 【0265】 The server receives transaction data sent from the terminal. To analyze the received data, the server uses machine learning algorithms to automatically classify the data into categories such as food expenses, transportation expenses, and utility expenses. 【0266】 Step 3: 【0267】 The server analyzes the classified data to identify spending trends and anomalies. Here, the server compares the current data with historical data, paying particular attention to areas of change. If an anomaly is detected, it initiates a process to investigate its cause. 【0268】 Step 4: 【0269】 Based on the analysis results, the server identifies areas where savings can be made. The server generates specific advice, such as "Your food expenses are over budget, so reduce the frequency of eating out." 【0270】 Step 5: 【0271】 The server sends the generated advice to the terminal. The terminal notifies the user of the advice and gives them the option to set a reminder. 【0272】 Step 6: 【0273】 The server collects discount information and coupons from partners and the market, and stores this data in a database. The server then selects relevant discount information based on the user's spending patterns. 【0274】 Step 7: 【0275】 The device notifies the user of discount information and coupons sent from the server. Users can then use this information to make more advantageous purchases. 【0276】 Step 8: 【0277】 The server continuously monitors the user's budget achievement. The server analyzes the progress of spending against the budget and sends feedback to the device. The device notifies the user of the feedback at the end of the month or as needed. 【0278】 (Example 1) 【0279】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0280】 In household financial management, there are challenges such as the difficulty of monitoring individual expenditure items and managing budgets in real time. In particular, reducing unnecessary spending and finding effective saving methods is difficult for many users. Furthermore, efficiently obtaining and utilizing discount and coupon information is also a problem. This invention aims to solve these problems and provide a system to support the sound management of household finances. 【0281】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0282】 In this invention, the server includes means for acquiring financial institution information, means for classifying financial data into categories using machine learning technology, and means for identifying areas where savings can be made and generating advice for savings. As a result, it becomes possible to monitor expenditures in real time and evaluate the degree of budget achievement in household fund management. 【0283】 "Financial institution information" refers to account information and transaction data of users provided by financial institutions such as banks and credit card companies. 【0284】 "Machine learning technology" refers to a technology in which an algorithm automatically discovers patterns based on a large amount of data, and particularly refers to a technology used for data classification and prediction. 【0285】 "Financial data" refers to all information related to users' daily income and expenditures, and particularly means data related to financial transactions. 【0286】 "Classifying into categories" means dividing the collected data based on specific criteria, for example, classifying it as "food expenses", "transportation expenses", etc. 【0287】 "Areas where savings can be made" refers to the scope of identifying parts in the user's expenditures that can reduce waste. 【0288】 "Generating advice for savings" refers to the process of creating specific advice for the user to suppress expenditures. 【0289】 "Real-time expenditure monitoring" refers to immediately tracking and managing the user's current expenditure situation. 【0290】 This invention describes a system for efficiently managing household financial information and providing an effective savings method for users. This system is composed of the cooperation of a server, a terminal, and a user. 【0291】 Users link their bank accounts and credit cards to the application using their device. The device is responsible for periodically retrieving transaction data from user-authorized financial institutions via APIs and sending it to the server. This communication is conducted using SSL and TLS protocols to ensure security. 【0292】 The server categorizes received transaction data using machine learning techniques. For this purpose, it can utilize machine learning libraries such as scikit-learn and TensorFlow. The data is automatically sorted into categories such as "food expenses" and "transportation expenses." This allows the server to analyze financial data from multiple perspectives, detecting unnecessary spending and predicting spending trends. Based on this analysis, the server identifies areas where savings can be made and generates specific savings advice. This advice is formulated in a user-friendly format using natural language generation models. 【0293】 The generated advice is notified to the user via their device. Based on this notification, the user can adjust their actions and set reminders if necessary. The server also collects discount information and coupons from partners in real time, providing users with advantageous offers tailored to their spending patterns. Database systems such as PostgreSQL and MongoDB are used for database management. 【0294】 Furthermore, the server monitors the progress of the user's budget in real time and evaluates the degree of achievement. For example, if a user sets a budget of 30,000 yen for food expenses, the system periodically evaluates the progress based on the plan and provides feedback to the user by notifying them via their terminal that "10,000 yen remains to reach the target budget." 【0295】 An example of a prompt for this system would be, "Analyze areas where savings can be made based on next month's spending forecast and generate specific advice." This allows users to achieve cost-effective household financial management. 【0296】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0297】 Step 1: 【0298】 The user links information from a financial institution to the application via their device. The user ID and authentication information are entered as input, and an API connection from the financial institution is established as output. Specifically, the device obtains the user's authentication information and generates an API key, enabling subsequent data retrieval. 【0299】 Step 2: 【0300】 The terminal periodically retrieves transaction data using the financial institution's API and sends it to the server. The input includes the transaction ID, amount, and date obtained from the financial institution, and the output is this transaction data transferred to the server. Specifically, the terminal automatically makes API calls at a fixed time each day and securely transmits the retrieved data to the server using SSL / TLS. 【0301】 Step 3: 【0302】 The server classifies received transaction data into categories using machine learning techniques. The input consists of transaction details and amounts, and the output generates category labels (e.g., "Food Expenses," "Transportation Expenses"). Specifically, the server uses scikit-learn and a Naive Bayes classifier to analyze and classify this data. 【0303】 Step 4: 【0304】 The server analyzes spending trends based on classified data and detects abnormal spending. Transaction history from the past few months is used as input, and a report of abnormal spending is generated as output. Specifically, the server uses TensorFlow to build a predictive model and identify spending that deviates from the normal range. 【0305】 Step 5: 【0306】 Based on the analysis results, the server identifies the areas where savings can be made and generates savings advice. The input includes spending trends and abnormal spending reports, and the output is the generated savings advice. As a specific operation, the server uses a natural language generation model to formulate the advice into text and prepares to provide it to the user. 【0307】 Step 6: 【0308】 The terminal notifies the user of the generated savings advice and sets a reminder if necessary. The input is the advice from the server, and the output is the notification displayed on the user terminal. As a specific operation, the terminal sends a push notification to the user and provides a UI for setting reminders. 【0309】 Step 7: 【0310】 The server collects discount information and coupons from partners and provides them to the user. The input is the information feed from partners, and the output is the coupons relevant to the user being extracted. As a specific operation, the server scans the partner database at regular intervals and selects information that matches the user's spending patterns. 【0311】 Step 8: 【0312】 The server monitors the user's budget progress in real-time and provides feedback. The input is the budget setting data and spending data, and the output is a report on the achievement status being generated. As a specific operation, the server evaluates the progress and sends a weekly review report to the user terminal. 【0313】 (Application Example 1) 【0314】 Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal". 【0315】 Modern households are required to efficiently manage financial information and reduce unnecessary spending. However, due to the busyness of daily life, manually collecting and analyzing financial data is burdensome, and it is also difficult to properly identify ways to save money. Furthermore, systems with visual and voice interfaces are limited, resulting in a lack of intuitive and convenient financial management tools for users. 【0316】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0317】 In this invention, the server includes means for acquiring household financial data and analyzing it using a voice input device, means for providing the user with the classified financial data through voice input and visual display, and means for identifying and proposing savings strategies based on the financial data analyzed in real time. This makes it possible for users to intuitively and easily grasp their own financial situation in their daily lives and immediately understand how to save money. 【0318】 "Financial data" refers to data that includes information about household or individual income and expenses. 【0319】 A "voice input device" is a device used to capture and process voice as digital data. 【0320】 "Analysis" is the process of breaking down obtained data in order to understand its content and characteristics. 【0321】 "Visual display" refers to a method of representing information visually on a screen, such as a display. 【0322】 "Classification" is the process of dividing data into different categories based on specific criteria. 【0323】 A "frugality policy" is a specific strategy for reducing unnecessary spending and promoting efficient use of funds. 【0324】 "Real-time" refers to the immediate processing or response that takes place as soon as data is generated. 【0325】 A "suggestion" is specific advice or guidance provided to encourage users to take action. 【0326】 "Users" refer to individuals or households that actually use the system or service. 【0327】 The system used to implement this application is designed to streamline household financial management. Users first access the system using a terminal equipped with a voice input device. The terminal recognizes the user's voice commands and collects household financial data. This includes obtaining bank account transactions and credit card usage data through financial institution APIs. 【0328】 The server analyzes the acquired data using machine learning algorithms to classify income and expenses. Libraries such as TensorFlow and PyTorch can be used for this purpose. Natural language processing APIs are used for speech recognition. The analysis results are displayed to the user visually in real time and also provided via audio. Expenditure trends are visualized in graphs and tables, promoting intuitive understanding for the user. 【0329】 The server then generates savings strategies based on the user's spending patterns. These strategies include specific suggestions, such as "You can save 5,000 yen per month by reducing your dining out frequency from twice a week to once a week." These suggestions are communicated to the user via voice notifications. 【0330】 The server also collects discount information and coupons from multiple partner sources and notifies users of information selected to match their interests. For example, it might be provided in the form of "This week's discount coupons for your nearest supermarket." 【0331】 Furthermore, the server monitors the progress of the set budget in real time and provides feedback. By displaying budget achievement status as visual feedback and notifying users of areas for improvement, users can quickly improve their usage. 【0332】 For example, if a user asks, "How much are my food expenses this month?", the system will respond verbally, "Currently, it's 30,000 yen," and visually display a graph showing the monthly food expense trend on the screen. As an example of a prompt to the generating AI model, if you input, "Please explain my transportation expenses for this month," the system will generate a comprehensive analysis of transportation expenses and savings suggestions. 【0333】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0334】 Step 1: 【0335】 The user enters voice commands via a terminal. A voice input device converts these commands into digital data, and a speech recognition API performs natural language processing to interpret the user's questions and instructions. The input is voice command data, and the output is the parsed instructions in text format. 【0336】 Step 2: 【0337】 The device sends requests to financial institutions' APIs with the user's permission to retrieve household financial data. This retrieves bank account and credit card transaction information. The input is user authentication information, and the output is transaction data. 【0338】 Step 3: 【0339】 The server processes the acquired transaction data through a machine learning algorithm. A data classification algorithm is used to categorize each transaction, such as food expenses or transportation costs. The input is raw transaction data, and the output is categorized data. 【0340】 Step 4: 【0341】 The server analyzes the classified data and generates savings strategies. This analysis includes identifying spending patterns and detecting anomalies. The generating AI model suggests necessary savings and outputs specific advice. The input is classified transaction data, and the output is specific savings advice. 【0342】 Step 5: 【0343】 The server collects discount information and coupons from partner sources and selects and presents appropriate options based on the user's spending patterns. The input is discount information from partners, and the output is coupon information tailored to the user's interests. 【0344】 Step 6: 【0345】 The server monitors the progress of the set budget in real time and generates feedback based on the collected data. It notifies the user of achievements and areas for improvement through visual displays and audio. Inputs are the latest expenditure data and budget information, while outputs are visual and audio feedback. 【0346】 Step 7: 【0347】 The user is notified, and suggested savings strategies and coupons are presented visually and audibly through the device. Based on the displayed information, the user can adjust their financial behavior. The input is savings advice and coupon information, and the output is the user's awareness and behavioral changes. 【0348】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0349】 This invention provides more personalized savings advice by combining a system for managing household financial information with an emotion engine that recognizes user emotions. This system effectively manages household spending data and uses that data to provide more accurate advice to the user. 【0350】 The system consists of a terminal, a server, and an emotion engine. The server processes financial data received from the terminal and classifies the data using machine learning algorithms. The classified data is analyzed on the server to detect spending trends and anomalies. Based on the analysis results, the server generates optimal saving advice and notifies the user through the terminal. 【0351】 The emotion engine recognizes the user's emotions in real time. This emotion information is obtained by inferring the emotional state based on data such as the user's actions while operating the device, voice input, and text input. Based on this information, the server adjusts the content and timing of advice and sets reminders that are tailored to the user's emotions. Therefore, it is possible to offer savings suggestions in a way that is easy for the user to accept. 【0352】 For example, suppose users tend to spend more at the end of the month when they are more stressed. In this case, the emotion engine can detect the user's stress, and the server can send budget advice and suggest ways to relax, thereby promoting better spending management. 【0353】 By combining this with an emotional engine, the system can enhance personalized care for users and improve the efficiency of household financial management. This allows users to manage their finances more systematically and with greater peace of mind, taking their own emotional state into consideration. 【0354】 The following describes the processing flow. 【0355】 Step 1: 【0356】 Users link their bank accounts and credit cards to the device. The device periodically retrieves transaction data from the user's financial institutions and sends it to the server. 【0357】 Step 2: 【0358】 The server receives the acquired transaction data. Next, the server uses a machine learning algorithm to automatically classify the data into categories such as food expenses, transportation expenses, and utility expenses. 【0359】 Step 3: 【0360】 The server analyzes the categorized data to identify spending trends and anomaly patterns. Based on the analysis, the server identifies areas where savings can be made. 【0361】 Step 4: 【0362】 The server generates savings advice and sends it to the terminal. The advice includes suggestions for specific behavioral changes. 【0363】 Step 5: 【0364】 The emotion engine uses device data to recognize the user's current emotional state. As the user interacts with the device, emotion data is collected when they use voice input or send text messages, and their emotions are inferred in real time. 【0365】 Step 6: 【0366】 The server receives the output from the emotion engine and adjusts the content of advice and the timing of notifications based on the emotional information. For example, when the user is relaxed, it might send advice about the next month's budget earlier than scheduled. 【0367】 Step 7: 【0368】 The device notifies the user of emotionally tailored advice. The user can review the notified advice and add reminders to make it easier to take action. 【0369】 Step 8: 【0370】 The server evaluates whether the advice and notifications sent were effective for the user, and records and analyzes the data for future improvements. It also evaluates the relationship between the user's emotional state and spending behavior, and uses this information to generate future advice. 【0371】 (Example 2) 【0372】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal". 【0373】 Traditional household financial information management systems have struggled to provide personalized saving advice that takes into account the user's emotional state. Because they cannot provide advice at the appropriate time and with the right content based on the user's emotions, effective spending management is hindered. Therefore, there is a need to develop a system that enables financial management that reflects the user's emotions. 【0374】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0375】 In this invention, the server includes means for recognizing the user's emotional state, means for adjusting the results of financial information analysis using the recognized emotional information, and means for generating personalized advice based on the adjusted analysis results. This enables the provision of effective financial management and spending advice tailored to the user's individual emotional state. 【0376】 "Means for recognizing the user's emotional state" refers to a function that analyzes voice input and operation data to identify the user's psychological state and emotions. 【0377】 "Means for adjusting the results of financial information analysis" refers to a function that modifies the evaluation and analysis of existing financial data based on perceived emotional states. 【0378】 "Means of generating personalized advice" refers to a function that creates guidelines for saving and managing spending that are tailored to each user's individual circumstances and feelings, based on the adjusted analysis results. 【0379】 "Means of obtaining household financial information" refers to the function of collecting data such as income and expenses related to household finances. 【0380】 "Means for classifying acquired financial information" refers to the function of organizing collected financial data by category. 【0381】 "Means for identifying potential savings" refers to the function of finding redundancy and waste from analyzed data and determining areas for savings. 【0382】 "Means of notifying users of generated advice" refers to a function that communicates the created guidelines and suggestions to users in an appropriate manner. 【0383】 "Means of collecting and providing discount information and coupons" refers to a function that collects and presents advantageous information obtained from markets and stores to users. 【0384】 "Means of analyzing budget achievement and providing feedback" refers to a function that verifies the actual income and expenditure situation against the budget and provides advice to users based on the results. 【0385】 "Means for detecting abnormal spending" refers to a function that identifies and warns of consumer behavior that deviates from normal patterns. 【0386】 "Methods for automatically classifying financial information using machine learning algorithms" refers to a function that utilizes artificial intelligence technology to automatically organize collected financial data. 【0387】 This invention is designed to effectively support users' financial management in their homes. The system primarily consists of a server, terminals, and an emotion engine. Specific hardware includes smartphones and personal computers that enable user-initiated data entry. Software includes an emotion engine for sentiment analysis, machine learning algorithms, and data analysis tools running on the server. 【0388】 The server manages financial data sent from users in the cloud. Data is sent from the terminal to the server using a secure protocol (e.g., SSL / TLS). The server classifies this data into categories using machine learning algorithms (e.g., scikit-learn) and analyzes user consumption patterns. Database management systems (e.g., PostgreSQL) and data analysis libraries (e.g., Pandas, NumPy) are used for the analysis. 【0389】 The emotion engine utilizes voice input and user actions to recognize the user's emotional state in real time. This data is analyzed using a generative AI model. Based on this input, the emotion engine infers the user's psychological state and sends that information to the server. 【0390】 As a concrete example, consider a case where a user tends to feel stressed at the end of the month and increases their spending. The emotion engine analyzes voice and operation data entered from the device to recognize this stress level. Based on this information, the server generates and notifies the user of advice such as, "It may be difficult to meet this month's budget, but please try some relaxation techniques to alleviate stress." This allows the user to receive appropriate financial management advice based on their emotions. 【0391】 An example of a prompt message is, "Generate the best savings advice for this week based on the user's spending data and emotional state." This allows the system to provide advice tailored to each user's situation. 【0392】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0393】 Step 1: 【0394】 Data collection and input 【0395】 Users input their daily income and expense information into their device. Specifically, they use a smartphone app or web interface to enter the amount, expense category (daily necessities, transportation, etc.), and date. This data is temporarily stored on the device and prepared for later processing. 【0396】 Input: User spending and income information 【0397】 Output: Financial data stored on the device 【0398】 Step 2: 【0399】 Data transmission and classification 【0400】 The terminal transmits financial data collected from the user to the server via the internet. The data is sent securely using a secure communication protocol (SSL / TLS). The server then uses a machine learning algorithm (e.g., scikit-learn) to classify the received data into expenditure categories. During this classification process, the characteristics of the data are extracted and mapped to pre-defined categories. 【0401】 Input: Financial data sent from the terminal 【0402】 Output: Data categorized on the server. 【0403】 Step 3: 【0404】 Data analysis 【0405】 The server uses the classified data to analyze consumption patterns. A database management system (e.g., PostgreSQL) is used to calculate trends and outliers in the collected data, identifying consumption peaks and irregular spending. The data is analyzed using statistical methods with libraries such as Pandas and NumPy. 【0406】 Input: Classified financial data 【0407】 Output: Analysis results of consumption patterns 【0408】 Step 4: 【0409】 Recognition of emotions 【0410】 The emotion engine analyzes the user's emotions in real time based on device operation logs and voice input data. It uses a generative AI model to identify emotional states (e.g., stress, happiness) through text analysis and voice acoustic analysis. The emotional data is sent to a server for use in subsequent processes. 【0411】 Input: Operation data and voice data to the terminal 【0412】 Output: Emotional state data sent to the server 【0413】 Step 5: 【0414】 Generating and notifying advice 【0415】 The server generates personalized savings advice based on the analysis of financial data and the user's emotional state. This advice may include specific suggestions such as, "We recommend relaxing activities at the end of the month." The system also considers the user's emotional state and spending patterns to create an optimal notification schedule. The generated advice is then communicated to the user via their device. 【0416】 Input: Analysis results and emotional state data 【0417】 Output: Advice message notified to the user 【0418】 (Application Example 2) 【0419】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0420】 Conventional household financial information management systems often fail to provide sufficient savings advice because they do not take into account the emotional state of each user. This can result in insufficient user satisfaction and savings. Furthermore, because they do not utilize emotional information, the timing and content of the advice may not be in line with the user's psychological state, which is a problem. 【0421】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0422】 In this invention, the server includes means for acquiring household financial information, means for classifying the acquired financial information, and means for inferring the user's psychological state and adjusting the timing and content of appropriate advice. This enables personalized saving advice tailored to the user's emotional state to be provided in real time, resulting in more effective spending management. 【0423】 "Economic information" refers to data about a household's financial status, such as income, expenses, assets, and liabilities. 【0424】 "User psychological state" refers to the emotions and moods that users experience in specific situations, and these influence their behavior and reactions when using the system. 【0425】 "Savings advice" refers to specific suggestions and instructions for controlling or optimizing spending, provided based on an individual user's financial information and psychological state. 【0426】 "Real-time" refers to a time standard that involves processing or responding immediately and without delay, based on the current situation and the latest data. 【0427】 A "machine learning algorithm" is a computational method that analyzes large amounts of data to find patterns and uses the learned results to predict and classify new data. 【0428】 "Adjusting the timing and content of appropriate advice" refers to a function that changes the timing and content of notifications according to the user's psychological state, thereby supporting more effective spending management. 【0429】 The system for realizing this invention mainly consists of three elements: a server, a terminal, and a user. The server understands the household's financial information and the user's psychological state, and provides optimal saving advice. The terminal functions as an interface for user operation and transmits and receives data with the server. Through the terminal, the user can check their financial information and advice and use it to manage their daily expenses. 【0430】 The server is primarily built using the Python programming language and utilizes TensorFlow, a machine learning library, for data analysis. On the server, a generative AI model learns based on users' economic information and psychological state, generating personalized advice for each user. A web application using Flask supports communication between the server and the user terminal. 【0431】 Specifically, user psychological data is collected from sensors on the device. This data is sent to a server in real time and processed by machine learning algorithms. Based on the resulting psychological state, the content and timing of advice are adjusted. For example, during periods of high stress, helpful information and money-saving tips that promote relaxation are suggested. 【0432】 This system enables users to manage their household finances in a planned and secure manner, taking their own emotional state into consideration. 【0433】 An example of a prompt message is: "If the user is feeling stressed, please provide relaxing money-saving advice. Sentiment data is updated in real time." 【0434】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0435】 Step 1: 【0436】 The device receives financial information from the user as input. The user records spending and income data through a household budgeting app. This information is immediately sent to the server. 【0437】 Step 2: 【0438】 The server uses the received economic information to classify the data. Machine learning algorithms are used to categorize spending items and trends, and to extract specific patterns. This allows for the automatic detection of spending trends and anomalies. 【0439】 Step 3: 【0440】 The device collects data to understand the user's psychological state. This is primarily done through sensors built into the device, using the smartphone's camera and microphone to analyze the user's facial expressions and tone of voice. The analysis results are sent to a server. 【0441】 Step 4: 【0442】 The server uses a generative AI model to analyze data based on the user's psychological state. It integrates and analyzes psychological data and economic information to generate personalized savings advice. In this process, appropriate advice is designed based on prompt statements. 【0443】 Step 5: 【0444】 The server sends the generated advice to the terminal. The terminal notifies the user of the advice. Through the notification, the user can check specific saving methods tailored to their situation and the coupon information offered. 【0445】 Step 6: 【0446】 Users adjust their daily financial activities based on the advice they receive. They periodically send feedback from their device to the server to reflect their income, expenses, and satisfaction levels. This feedback is used to improve future advice. 【0447】 The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0448】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0449】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214. 【0450】 [Third Embodiment] 【0451】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0452】 As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server. 【0453】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0454】 The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52. 【0455】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0456】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0457】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0458】 Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0459】 The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30. 【0460】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0461】 In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0462】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal". 【0463】 This invention is an AI system that manages household financial information in real time and provides users with effective saving methods. This system consists of a terminal, a server, and a user working together, with each module performing the following processes. 【0464】 Data collection methods 【0465】 Users link their bank accounts and credit cards to the application via their device. The device periodically retrieves transaction data via APIs of financial institutions authorized by the user and sends that data to the server. 【0466】 Forms of data classification and analysis 【0467】 The server automatically categorizes received transaction data using machine learning algorithms. For example, grocery purchases are categorized as "food expenses," and train fares are categorized as "transportation expenses." After categorization, the server analyzes the data to check for spending trends and any unusual expenditures. 【0468】 Forms of generating and notifying savings advice 【0469】 Based on the analysis results, the server identifies areas where savings can be made and generates advice. For example, "You can save 5,000 yen per month by reducing eating out from three times a week to once a week." The terminal notifies the user of this advice and sets reminders as needed. 【0470】 Discount information and coupon distribution methods 【0471】 The server collects discount information and coupons from partners and stores them in a database. It selects information appropriate to the user's spending patterns and notifies the device. For example, it might provide "This Week's Supermarket Discount Coupons." 【0472】 Budget progress management and feedback methods 【0473】 The server monitors the progress of the user-defined budget in real time and analyzes the degree of achievement. At the end of the month or as needed, the terminal provides the user with feedback on the achievement status and suggestions for improvement. This allows the user to quickly respond to and improve individual budget items. 【0474】 Through these various functions, the present invention provides a useful means for users to efficiently manage their daily expenses and improve their actual household financial situation. 【0475】 The following describes the processing flow. 【0476】 Step 1: 【0477】 The user links their bank account and credit card information to the device. The device periodically retrieves transaction data through APIs of financial institutions authorized by the user. The device temporarily stores the retrieved data and securely sends it to the server. 【0478】 Step 2: 【0479】 The server receives transaction data sent from the terminal. To analyze the received data, the server uses machine learning algorithms to automatically classify the data into categories such as food expenses, transportation expenses, and utility expenses. 【0480】 Step 3: 【0481】 The server analyzes the classified data to identify spending trends and anomalies. Here, the server compares the current data with historical data, paying particular attention to areas of change. If an anomaly is detected, it initiates a process to investigate its cause. 【0482】 Step 4: 【0483】 Based on the analysis results, the server identifies areas where savings can be made. The server generates specific advice, such as "Your food expenses are over budget, so reduce the frequency of eating out." 【0484】 Step 5: 【0485】 The server sends the generated advice to the terminal. The terminal notifies the user of the advice and gives them the option to set a reminder. 【0486】 Step 6: 【0487】 The server collects discount information and coupons from partners and the market, and stores this data in a database. The server then selects relevant discount information based on the user's spending patterns. 【0488】 Step 7: 【0489】 The device notifies the user of discount information and coupons sent from the server. Users can then use this information to make more advantageous purchases. 【0490】 Step 8: 【0491】 The server continuously monitors the user's budget achievement. The server analyzes the progress of spending against the budget and sends feedback to the device. The device notifies the user of the feedback at the end of the month or as needed. 【0492】 (Example 1) 【0493】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0494】 In household financial management, there are challenges such as the difficulty of monitoring individual expenditure items and managing budgets in real time. In particular, reducing unnecessary spending and finding effective saving methods is difficult for many users. Furthermore, efficiently obtaining and utilizing discount and coupon information is also a problem. This invention aims to solve these problems and provide a system to support the sound management of household finances. 【0495】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0496】 In this invention, the server includes means for acquiring information from financial institutions, means for classifying financial data into categories using machine learning techniques, and means for identifying areas where savings can be made and generating advice for saving. This enables real-time spending monitoring and evaluation of budget achievement in household financial management. 【0497】 "Financial institution information" refers to account information and transaction data of users provided by financial institutions such as banks and credit card companies. 【0498】 "Machine learning technology" refers to techniques in which algorithms automatically find patterns based on large amounts of data, and specifically refers to techniques used for data classification and prediction. 【0499】 "Financial data" refers to all information about a user's daily income and expenses, and specifically to data related to financial transactions. 【0500】 "Categorizing" means separating collected data based on specific criteria, such as classifying it as "food expenses" or "transportation expenses." 【0501】 "Areas where savings can be made" refers to the portion of a user's spending where waste can be reduced. 【0502】 "Generating savings advice" refers to the process of creating specific advice for users to reduce their spending. 【0503】 "Real-time spending monitoring" refers to the ability to instantly track and manage a user's current spending status. 【0504】 This invention describes a system for efficiently managing household financial information and providing users with effective saving methods. This system consists of collaboration between a server, terminals, and users. 【0505】 Users link their bank accounts and credit cards to the application using their device. The device is responsible for periodically retrieving transaction data from user-authorized financial institutions via APIs and sending it to the server. This communication is conducted using SSL and TLS protocols to ensure security. 【0506】 The server categorizes received transaction data using machine learning techniques. For this purpose, it can utilize machine learning libraries such as scikit-learn and TensorFlow. The data is automatically sorted into categories such as "food expenses" and "transportation expenses." This allows the server to analyze financial data from multiple perspectives, detecting unnecessary spending and predicting spending trends. Based on this analysis, the server identifies areas where savings can be made and generates specific savings advice. This advice is formulated in a user-friendly format using natural language generation models. 【0507】 The generated advice is notified to the user via their device. Based on this notification, the user can adjust their actions and set reminders if necessary. The server also collects discount information and coupons from partners in real time, providing users with advantageous offers tailored to their spending patterns. Database systems such as PostgreSQL and MongoDB are used for database management. 【0508】 Furthermore, the server monitors the progress of the user's budget in real time and evaluates the degree of achievement. For example, if a user sets a budget of 30,000 yen for food expenses, the system periodically evaluates the progress based on the plan and provides feedback to the user by notifying them via their terminal that "10,000 yen remains to reach the target budget." 【0509】 An example of a prompt for this system would be, "Analyze areas where savings can be made based on next month's spending forecast and generate specific advice." This allows users to achieve cost-effective household financial management. 【0510】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0511】 Step 1: 【0512】 The user links information from a financial institution to the application via their device. The user ID and authentication information are entered as input, and an API connection from the financial institution is established as output. Specifically, the device obtains the user's authentication information and generates an API key, enabling subsequent data retrieval. 【0513】 Step 2: 【0514】 The terminal periodically retrieves transaction data using the financial institution's API and sends it to the server. The input includes the transaction ID, amount, and date obtained from the financial institution, and the output is this transaction data transferred to the server. Specifically, the terminal automatically makes API calls at a fixed time each day and securely transmits the retrieved data to the server using SSL / TLS. 【0515】 Step 3: 【0516】 The server classifies received transaction data into categories using machine learning techniques. The input consists of transaction details and amounts, and the output generates category labels (e.g., "Food Expenses," "Transportation Expenses"). Specifically, the server uses scikit-learn and a Naive Bayes classifier to analyze and classify this data. 【0517】 Step 4: 【0518】 The server analyzes spending trends based on classified data and detects abnormal spending. Transaction history from the past few months is used as input, and a report of abnormal spending is generated as output. Specifically, the server uses TensorFlow to build a predictive model and identify spending that deviates from the normal range. 【0519】 Step 5: 【0520】 Based on the analysis results, the server identifies areas where savings can be made and generates savings advice. The inputs are spending trends and reports on unusual spending, and the output is savings advice. Specifically, the server uses a natural language generation model to put the advice into text and prepares it for delivery to the user. 【0521】 Step 6: 【0522】 The device notifies the user of the generated savings advice and sets reminders as needed. The input is advice from the server, and the output is a notification displayed on the user's device. Specifically, the device sends a push notification to the user and provides a UI for setting reminders. 【0523】 Step 7: 【0524】 The server collects discount information and coupons from partners and provides them to users. The input is an information feed from partners, and the output is the extraction of coupons relevant to the user. Specifically, the server periodically scans the partner database and selects information that matches the user's spending patterns. 【0525】 Step 8: 【0526】 The server monitors the user's budget progress in real time and provides feedback. It takes budget setting data and expenditure data as input and generates achievement reports as output. Specifically, the server evaluates progress and sends weekly review reports to the user's terminal. 【0527】 (Application Example 1) 【0528】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0529】 Modern households are required to efficiently manage financial information and reduce unnecessary spending. However, due to the busyness of daily life, manually collecting and analyzing financial data is burdensome, and it is also difficult to properly identify ways to save money. Furthermore, systems with visual and voice interfaces are limited, resulting in a lack of intuitive and convenient financial management tools for users. 【0530】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0531】 In this invention, the server includes means for acquiring household financial data and analyzing it using a voice input device, means for providing the user with the classified financial data through voice input and visual display, and means for identifying and proposing savings strategies based on the financial data analyzed in real time. This makes it possible for users to intuitively and easily grasp their own financial situation in their daily lives and immediately understand how to save money. 【0532】 "Financial data" refers to data that includes information about household or individual income and expenses. 【0533】 A "voice input device" is a device used to capture and process voice as digital data. 【0534】 "Analysis" is the process of breaking down obtained data in order to understand its content and characteristics. 【0535】 "Visual display" refers to a method of representing information visually on a screen, such as a display. 【0536】 "Classification" is the process of dividing data into different categories based on specific criteria. 【0537】 A "frugality policy" is a specific strategy for reducing unnecessary spending and promoting efficient use of funds. 【0538】 "Real-time" refers to the immediate processing or response that takes place as soon as data is generated. 【0539】 A "suggestion" is specific advice or guidance provided to encourage users to take action. 【0540】 "Users" refer to individuals or households that actually use the system or service. 【0541】 The system used to implement this application is designed to streamline household financial management. Users first access the system using a terminal equipped with a voice input device. The terminal recognizes the user's voice commands and collects household financial data. This includes obtaining bank account transactions and credit card usage data through financial institution APIs. 【0542】 The server analyzes the acquired data using machine learning algorithms to classify income and expenses. Libraries such as TensorFlow and PyTorch can be used for this purpose. Natural language processing APIs are used for speech recognition. The analysis results are displayed to the user visually in real time and also provided via audio. Expenditure trends are visualized in graphs and tables, promoting intuitive understanding for the user. 【0543】 The server then generates savings strategies based on the user's spending patterns. These strategies include specific suggestions, such as "You can save 5,000 yen per month by reducing your dining out frequency from twice a week to once a week." These suggestions are communicated to the user via voice notifications. 【0544】 The server also collects discount information and coupons from multiple partner sources and notifies users of information selected to match their interests. For example, it might be provided in the form of "This week's discount coupons for your nearest supermarket." 【0545】 Furthermore, the server monitors the progress of the set budget in real time and provides feedback. By displaying budget achievement status as visual feedback and notifying users of areas for improvement, users can quickly improve their usage. 【0546】 For example, if a user asks, "How much are my food expenses this month?", the system will respond verbally, "Currently, it's 30,000 yen," and visually display a graph showing the monthly food expense trend on the screen. As an example of a prompt to the generating AI model, if you input, "Please explain my transportation expenses for this month," the system will generate a comprehensive analysis of transportation expenses and savings suggestions. 【0547】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0548】 Step 1: 【0549】 The user enters voice commands via a terminal. A voice input device converts these commands into digital data, and a speech recognition API performs natural language processing to interpret the user's questions and instructions. The input is voice command data, and the output is the parsed instructions in text format. 【0550】 Step 2: 【0551】 The device sends requests to financial institutions' APIs with the user's permission to retrieve household financial data. This retrieves bank account and credit card transaction information. The input is user authentication information, and the output is transaction data. 【0552】 Step 3: 【0553】 The server processes the acquired transaction data through a machine learning algorithm. A data classification algorithm is used to categorize each transaction, such as food expenses or transportation costs. The input is raw transaction data, and the output is categorized data. 【0554】 Step 4: 【0555】 The server analyzes the classified data and generates savings strategies. This analysis includes identifying spending patterns and detecting anomalies. The generating AI model suggests necessary savings and outputs specific advice. The input is classified transaction data, and the output is specific savings advice. 【0556】 Step 5: 【0557】 The server collects discount information and coupons from partner sources and selects and presents appropriate options based on the user's spending patterns. The input is discount information from partners, and the output is coupon information tailored to the user's interests. 【0558】 Step 6: 【0559】 The server monitors the progress of the set budget in real time and generates feedback based on the collected data. It notifies the user of achievements and areas for improvement through visual displays and audio. Inputs are the latest expenditure data and budget information, while outputs are visual and audio feedback. 【0560】 Step 7: 【0561】 The user is notified, and suggested savings strategies and coupons are presented visually and audibly through the device. Based on the displayed information, the user can adjust their financial behavior. The input is savings advice and coupon information, and the output is the user's awareness and behavioral changes. 【0562】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0563】 This invention provides more personalized savings advice by combining a system for managing household financial information with an emotion engine that recognizes user emotions. This system effectively manages household spending data and uses that data to provide more accurate advice to the user. 【0564】 The system consists of a terminal, a server, and an emotion engine. The server processes financial data received from the terminal and classifies the data using machine learning algorithms. The classified data is analyzed on the server to detect spending trends and anomalies. Based on the analysis results, the server generates optimal saving advice and notifies the user through the terminal. 【0565】 The emotion engine recognizes the user's emotions in real time. This emotion information is obtained by inferring the emotional state based on data such as the user's actions while operating the device, voice input, and text input. Based on this information, the server adjusts the content and timing of advice and sets reminders that are tailored to the user's emotions. Therefore, it is possible to offer savings suggestions in a way that is easy for the user to accept. 【0566】 For example, suppose users tend to spend more at the end of the month when they are more stressed. In this case, the emotion engine can detect the user's stress, and the server can send budget advice and suggest ways to relax, thereby promoting better spending management. 【0567】 By combining this with an emotional engine, the system can enhance personalized care for users and improve the efficiency of household financial management. This allows users to manage their finances more systematically and with greater peace of mind, taking their own emotional state into consideration. 【0568】 The following describes the processing flow. 【0569】 Step 1: 【0570】 Users link their bank accounts and credit cards to the device. The device periodically retrieves transaction data from the user's financial institutions and sends it to the server. 【0571】 Step 2: 【0572】 The server receives the acquired transaction data. Next, the server uses a machine learning algorithm to automatically classify the data into categories such as food expenses, transportation expenses, and utility expenses. 【0573】 Step 3: 【0574】 The server analyzes the categorized data to identify spending trends and anomaly patterns. Based on the analysis, the server identifies areas where savings can be made. 【0575】 Step 4: 【0576】 The server generates savings advice and sends it to the terminal. The advice includes suggestions for specific behavioral changes. 【0577】 Step 5: 【0578】 The emotion engine uses device data to recognize the user's current emotional state. As the user interacts with the device, emotion data is collected when they use voice input or send text messages, and their emotions are inferred in real time. 【0579】 Step 6: 【0580】 The server receives the output from the emotion engine and adjusts the content of advice and the timing of notifications based on the emotional information. For example, when the user is relaxed, it might send advice about the next month's budget earlier than scheduled. 【0581】 Step 7: 【0582】 The device notifies the user of emotionally tailored advice. The user can review the notified advice and add reminders to make it easier to take action. 【0583】 Step 8: 【0584】 The server evaluates whether the advice and notifications sent were effective for the user, and records and analyzes the data for future improvements. It also evaluates the relationship between the user's emotional state and spending behavior, and uses this information to generate future advice. 【0585】 (Example 2) 【0586】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0587】 Traditional household financial information management systems have struggled to provide personalized saving advice that takes into account the user's emotional state. Because they cannot provide advice at the appropriate time and with the right content based on the user's emotions, effective spending management is hindered. Therefore, there is a need to develop a system that enables financial management that reflects the user's emotions. 【0588】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0589】 In this invention, the server includes means for recognizing the user's emotional state, means for adjusting the results of financial information analysis using the recognized emotional information, and means for generating personalized advice based on the adjusted analysis results. This enables the provision of effective financial management and spending advice tailored to the user's individual emotional state. 【0590】 "Means for recognizing the user's emotional state" refers to a function that analyzes voice input and operation data to identify the user's psychological state and emotions. 【0591】 "Means for adjusting the results of financial information analysis" refers to a function that modifies the evaluation and analysis of existing financial data based on perceived emotional states. 【0592】 "Means of generating personalized advice" refers to a function that creates guidelines for saving and managing spending that are tailored to each user's individual circumstances and feelings, based on the adjusted analysis results. 【0593】 "Means of obtaining household financial information" refers to the function of collecting data such as income and expenses related to household finances. 【0594】 "Means for classifying acquired financial information" refers to the function of organizing collected financial data by category. 【0595】 "Means for identifying potential savings" refers to the function of finding redundancy and waste from analyzed data and determining areas for savings. 【0596】 "Means of notifying users of generated advice" refers to a function that communicates the created guidelines and suggestions to users in an appropriate manner. 【0597】 "Means of collecting and providing discount information and coupons" refers to a function that collects and presents advantageous information obtained from markets and stores to users. 【0598】 "Means of analyzing budget achievement and providing feedback" refers to a function that verifies the actual income and expenditure situation against the budget and provides advice to users based on the results. 【0599】 "Means for detecting abnormal spending" refers to a function that identifies and warns of consumer behavior that deviates from normal patterns. 【0600】 "Methods for automatically classifying financial information using machine learning algorithms" refers to a function that utilizes artificial intelligence technology to automatically organize collected financial data. 【0601】 This invention is designed to effectively support users' financial management in their homes. The system primarily consists of a server, terminals, and an emotion engine. Specific hardware includes smartphones and personal computers that enable user-initiated data entry. Software includes an emotion engine for sentiment analysis, machine learning algorithms, and data analysis tools running on the server. 【0602】 The server manages financial data sent from users in the cloud. Data is sent from the terminal to the server using a secure protocol (e.g., SSL / TLS). The server classifies this data into categories using machine learning algorithms (e.g., scikit-learn) and analyzes user consumption patterns. Database management systems (e.g., PostgreSQL) and data analysis libraries (e.g., Pandas, NumPy) are used for the analysis. 【0603】 The emotion engine utilizes voice input and user actions to recognize the user's emotional state in real time. This data is analyzed using a generative AI model. Based on this input, the emotion engine infers the user's psychological state and sends that information to the server. 【0604】 As a concrete example, consider a case where a user tends to feel stressed at the end of the month and increases their spending. The emotion engine analyzes voice and operation data entered from the device to recognize this stress level. Based on this information, the server generates and notifies the user of advice such as, "It may be difficult to meet this month's budget, but please try some relaxation techniques to alleviate stress." This allows the user to receive appropriate financial management advice based on their emotions. 【0605】 An example of a prompt message is, "Generate the best savings advice for this week based on the user's spending data and emotional state." This allows the system to provide advice tailored to each user's situation. 【0606】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0607】 Step 1: 【0608】 Data collection and input 【0609】 Users input their daily income and expense information into their device. Specifically, they use a smartphone app or web interface to enter the amount, expense category (daily necessities, transportation, etc.), and date. This data is temporarily stored on the device and prepared for later processing. 【0610】 Input: User spending and income information 【0611】 Output: Financial data stored on the device 【0612】 Step 2: 【0613】 Data transmission and classification 【0614】 The terminal transmits financial data collected from the user to the server via the internet. The data is sent securely using a secure communication protocol (SSL / TLS). The server then uses a machine learning algorithm (e.g., scikit-learn) to classify the received data into expenditure categories. During this classification process, the characteristics of the data are extracted and mapped to pre-defined categories. 【0615】 Input: Financial data sent from the terminal 【0616】 Output: Data categorized on the server. 【0617】 Step 3: 【0618】 Data analysis 【0619】 The server uses the classified data to analyze consumption patterns. A database management system (e.g., PostgreSQL) is used to calculate trends and outliers in the collected data, identifying consumption peaks and irregular spending. The data is analyzed using statistical methods with libraries such as Pandas and NumPy. 【0620】 Input: Classified financial data 【0621】 Output: Analysis results of consumption patterns 【0622】 Step 4: 【0623】 Recognition of emotions 【0624】 The emotion engine analyzes the user's emotions in real time based on device operation logs and voice input data. It uses a generative AI model to identify emotional states (e.g., stress, happiness) through text analysis and voice acoustic analysis. The emotional data is sent to a server for use in subsequent processes. 【0625】 Input: Operation data and voice data to the terminal 【0626】 Output: Emotional state data sent to the server 【0627】 Step 5: 【0628】 Generating and notifying advice 【0629】 The server generates personalized savings advice based on the analysis of financial data and the user's emotional state. This advice may include specific suggestions such as, "We recommend relaxing activities at the end of the month." The system also considers the user's emotional state and spending patterns to create an optimal notification schedule. The generated advice is then communicated to the user via their device. 【0630】 Input: Analysis results and emotional state data 【0631】 Output: Advice message notified to the user 【0632】 (Application Example 2) 【0633】 Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0634】 Conventional household financial information management systems often fail to provide sufficient savings advice because they do not take into account the emotional state of each user. This can result in insufficient user satisfaction and savings. Furthermore, because they do not utilize emotional information, the timing and content of the advice may not be in line with the user's psychological state, which is a problem. 【0635】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0636】 In this invention, the server includes means for acquiring household financial information, means for classifying the acquired financial information, and means for inferring the user's psychological state and adjusting the timing and content of appropriate advice. This enables personalized saving advice tailored to the user's emotional state to be provided in real time, resulting in more effective spending management. 【0637】 "Economic information" refers to data about a household's financial status, such as income, expenses, assets, and liabilities. 【0638】 "User psychological state" refers to the emotions and moods that users experience in specific situations, and these influence their behavior and reactions when using the system. 【0639】 "Savings advice" refers to specific suggestions and instructions for controlling or optimizing spending, provided based on an individual user's financial information and psychological state. 【0640】 "Real-time" refers to a time standard that involves processing or responding immediately and without delay, based on the current situation and the latest data. 【0641】 A "machine learning algorithm" is a computational method that analyzes large amounts of data to find patterns and uses the learned results to predict and classify new data. 【0642】 "Adjusting the timing and content of appropriate advice" refers to a function that changes the timing and content of notifications according to the user's psychological state, thereby supporting more effective spending management. 【0643】 The system for realizing this invention mainly consists of three elements: a server, a terminal, and a user. The server understands the household's financial information and the user's psychological state, and provides optimal saving advice. The terminal functions as an interface for user operation and transmits and receives data with the server. Through the terminal, the user can check their financial information and advice and use it to manage their daily expenses. 【0644】 The server is primarily built using the Python programming language and utilizes TensorFlow, a machine learning library, for data analysis. On the server, a generative AI model learns based on users' economic information and psychological state, generating personalized advice for each user. A web application using Flask supports communication between the server and the user terminal. 【0645】 Specifically, user psychological data is collected from sensors on the device. This data is sent to a server in real time and processed by machine learning algorithms. Based on the resulting psychological state, the content and timing of advice are adjusted. For example, during periods of high stress, helpful information and money-saving tips that promote relaxation are suggested. 【0646】 This system enables users to manage their household finances in a planned and secure manner, taking their own emotional state into consideration. 【0647】 An example of a prompt message is: "If the user is feeling stressed, please provide relaxing money-saving advice. Sentiment data is updated in real time." 【0648】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0649】 Step 1: 【0650】 The device receives financial information from the user as input. The user records spending and income data through a household budgeting app. This information is immediately sent to the server. 【0651】 Step 2: 【0652】 The server uses the received economic information to classify the data. Machine learning algorithms are used to categorize spending items and trends, and to extract specific patterns. This allows for the automatic detection of spending trends and anomalies. 【0653】 Step 3: 【0654】 The device collects data to understand the user's psychological state. This is primarily done through sensors built into the device, using the smartphone's camera and microphone to analyze the user's facial expressions and tone of voice. The analysis results are sent to a server. 【0655】 Step 4: 【0656】 The server uses a generative AI model to analyze data based on the user's psychological state. It integrates and analyzes psychological data and economic information to generate personalized savings advice. In this process, appropriate advice is designed based on prompt statements. 【0657】 Step 5: 【0658】 The server sends the generated advice to the terminal. The terminal notifies the user of the advice. Through the notification, the user can check specific saving methods tailored to their situation and the coupon information offered. 【0659】 Step 6: 【0660】 Users adjust their daily financial activities based on the advice they receive. They periodically send feedback from their device to the server to reflect their income, expenses, and satisfaction levels. This feedback is used to improve future advice. 【0661】 The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0662】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0663】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314. 【0664】 [Fourth Embodiment] 【0665】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0666】 As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server. 【0667】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0668】 The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52. 【0669】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0670】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0671】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0672】 The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes. 【0673】 Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0674】 The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30. 【0675】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0676】 In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0677】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0678】 This invention is an AI system that manages household financial information in real time and provides users with effective saving methods. This system consists of a terminal, a server, and a user working together, with each module performing the following processes. 【0679】 Data collection methods 【0680】 Users link their bank accounts and credit cards to the application via their device. The device periodically retrieves transaction data via APIs of financial institutions authorized by the user and sends that data to the server. 【0681】 Forms of data classification and analysis 【0682】 The server automatically categorizes received transaction data using machine learning algorithms. For example, grocery purchases are categorized as "food expenses," and train fares are categorized as "transportation expenses." After categorization, the server analyzes the data to check for spending trends and any unusual expenditures. 【0683】 Forms of generating and notifying savings advice 【0684】 Based on the analysis results, the server identifies areas where savings can be made and generates advice. For example, "You can save 5,000 yen per month by reducing eating out from three times a week to once a week." The terminal notifies the user of this advice and sets reminders as needed. 【0685】 Discount information and coupon distribution methods 【0686】 The server collects discount information and coupons from partners and stores them in a database. It selects information appropriate to the user's spending patterns and notifies the device. For example, it might provide "This Week's Supermarket Discount Coupons." 【0687】 Budget progress management and feedback methods 【0688】 The server monitors the progress of the user-defined budget in real time and analyzes the degree of achievement. At the end of the month or as needed, the terminal provides the user with feedback on the achievement status and suggestions for improvement. This allows the user to quickly respond to and improve individual budget items. 【0689】 Through these various functions, the present invention provides a useful means for users to efficiently manage their daily expenses and improve their actual household financial situation. 【0690】 The following describes the processing flow. 【0691】 Step 1: 【0692】 The user links their bank account and credit card information to the device. The device periodically retrieves transaction data through APIs of financial institutions authorized by the user. The device temporarily stores the retrieved data and securely sends it to the server. 【0693】 Step 2: 【0694】 The server receives transaction data sent from the terminal. To analyze the received data, the server uses machine learning algorithms to automatically classify the data into categories such as food expenses, transportation expenses, and utility expenses. 【0695】 Step 3: 【0696】 The server analyzes the classified data to identify spending trends and anomalies. Here, the server compares the current data with historical data, paying particular attention to areas of change. If an anomaly is detected, it initiates a process to investigate its cause. 【0697】 Step 4: 【0698】 Based on the analysis results, the server identifies areas where savings can be made. The server generates specific advice, such as "Your food expenses are over budget, so reduce the frequency of eating out." 【0699】 Step 5: 【0700】 The server sends the generated advice to the terminal. The terminal notifies the user of the advice and gives them the option to set a reminder. 【0701】 Step 6: 【0702】 The server collects discount information and coupons from partners and the market, and stores this data in a database. The server then selects relevant discount information based on the user's spending patterns. 【0703】 Step 7: 【0704】 The device notifies the user of discount information and coupons sent from the server. Users can then use this information to make more advantageous purchases. 【0705】 Step 8: 【0706】 The server continuously monitors the user's budget achievement. The server analyzes the progress of spending against the budget and sends feedback to the device. The device notifies the user of the feedback at the end of the month or as needed. 【0707】 (Example 1) 【0708】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0709】 In household financial management, there are challenges such as the difficulty of monitoring individual expenditure items and managing budgets in real time. In particular, reducing unnecessary spending and finding effective saving methods is difficult for many users. Furthermore, efficiently obtaining and utilizing discount and coupon information is also a problem. This invention aims to solve these problems and provide a system to support the sound management of household finances. 【0710】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0711】 In this invention, the server includes means for acquiring information from financial institutions, means for classifying financial data into categories using machine learning techniques, and means for identifying areas where savings can be made and generating advice for saving. This enables real-time spending monitoring and evaluation of budget achievement in household financial management. 【0712】 "Financial institution information" refers to account information and transaction data of users provided by financial institutions such as banks and credit card companies. 【0713】 "Machine learning technology" refers to techniques in which algorithms automatically find patterns based on large amounts of data, and specifically refers to techniques used for data classification and prediction. 【0714】 "Financial data" refers to all information about a user's daily income and expenses, and specifically to data related to financial transactions. 【0715】 "Categorizing" means separating collected data based on specific criteria, such as classifying it as "food expenses" or "transportation expenses." 【0716】 "Areas where savings can be made" refers to the portion of a user's spending where waste can be reduced. 【0717】 "Generating savings advice" refers to the process of creating specific advice for users to reduce their spending. 【0718】 "Real-time spending monitoring" refers to the ability to instantly track and manage a user's current spending status. 【0719】 This invention describes a system for efficiently managing household financial information and providing users with effective saving methods. This system consists of collaboration between a server, terminals, and users. 【0720】 Users link their bank accounts and credit cards to the application using their device. The device is responsible for periodically retrieving transaction data from user-authorized financial institutions via APIs and sending it to the server. This communication is conducted using SSL and TLS protocols to ensure security. 【0721】 The server categorizes received transaction data using machine learning techniques. For this purpose, it can utilize machine learning libraries such as scikit-learn and TensorFlow. The data is automatically sorted into categories such as "food expenses" and "transportation expenses." This allows the server to analyze financial data from multiple perspectives, detecting unnecessary spending and predicting spending trends. Based on this analysis, the server identifies areas where savings can be made and generates specific savings advice. This advice is formulated in a user-friendly format using natural language generation models. 【0722】 The generated advice is notified to the user via their device. Based on this notification, the user can adjust their actions and set reminders if necessary. The server also collects discount information and coupons from partners in real time, providing users with advantageous offers tailored to their spending patterns. Database systems such as PostgreSQL and MongoDB are used for database management. 【0723】 Furthermore, the server monitors the progress of the user's budget in real time and evaluates the degree of achievement. For example, if a user sets a budget of 30,000 yen for food expenses, the system periodically evaluates the progress based on the plan and provides feedback to the user by notifying them via their terminal that "10,000 yen remains to reach the target budget." 【0724】 An example of a prompt for this system would be, "Analyze areas where savings can be made based on next month's spending forecast and generate specific advice." This allows users to achieve cost-effective household financial management. 【0725】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0726】 Step 1: 【0727】 The user links information from a financial institution to the application via their device. The user ID and authentication information are entered as input, and an API connection from the financial institution is established as output. Specifically, the device obtains the user's authentication information and generates an API key, enabling subsequent data retrieval. 【0728】 Step 2: 【0729】 The terminal periodically retrieves transaction data using the financial institution's API and sends it to the server. The input includes the transaction ID, amount, and date obtained from the financial institution, and the output is this transaction data transferred to the server. Specifically, the terminal automatically makes API calls at a fixed time each day and securely transmits the retrieved data to the server using SSL / TLS. 【0730】 Step 3: 【0731】 The server classifies received transaction data into categories using machine learning techniques. The input consists of transaction details and amounts, and the output generates category labels (e.g., "Food Expenses," "Transportation Expenses"). Specifically, the server uses scikit-learn and a Naive Bayes classifier to analyze and classify this data. 【0732】 Step 4: 【0733】 The server analyzes spending trends based on classified data and detects abnormal spending. Transaction history from the past few months is used as input, and a report of abnormal spending is generated as output. Specifically, the server uses TensorFlow to build a predictive model and identify spending that deviates from the normal range. 【0734】 Step 5: 【0735】 Based on the analysis results, the server identifies areas where savings can be made and generates savings advice. The inputs are spending trends and reports on unusual spending, and the output is savings advice. Specifically, the server uses a natural language generation model to put the advice into text and prepares it for delivery to the user. 【0736】 Step 6: 【0737】 The device notifies the user of the generated savings advice and sets reminders as needed. The input is advice from the server, and the output is a notification displayed on the user's device. Specifically, the device sends a push notification to the user and provides a UI for setting reminders. 【0738】 Step 7: 【0739】 The server collects discount information and coupons from partners and provides them to users. The input is an information feed from partners, and the output is the extraction of coupons relevant to the user. Specifically, the server periodically scans the partner database and selects information that matches the user's spending patterns. 【0740】 Step 8: 【0741】 The server monitors the user's budget progress in real time and provides feedback. It takes budget setting data and expenditure data as input and generates achievement reports as output. Specifically, the server evaluates progress and sends weekly review reports to the user's terminal. 【0742】 (Application Example 1) 【0743】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0744】 Modern households are required to efficiently manage financial information and reduce unnecessary spending. However, due to the busyness of daily life, manually collecting and analyzing financial data is burdensome, and it is also difficult to properly identify ways to save money. Furthermore, systems with visual and voice interfaces are limited, resulting in a lack of intuitive and convenient financial management tools for users. 【0745】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0746】 In this invention, the server includes means for acquiring household financial data and analyzing it using a voice input device, means for providing the user with the classified financial data through voice input and visual display, and means for identifying and proposing savings strategies based on the financial data analyzed in real time. This makes it possible for users to intuitively and easily grasp their own financial situation in their daily lives and immediately understand how to save money. 【0747】 "Financial data" refers to data that includes information about household or individual income and expenses. 【0748】 A "voice input device" is a device used to capture and process voice as digital data. 【0749】 "Analysis" is the process of breaking down obtained data in order to understand its content and characteristics. 【0750】 "Visual display" refers to a method of representing information visually on a screen, such as a display. 【0751】 "Classification" is the process of dividing data into different categories based on specific criteria. 【0752】 A "frugality policy" is a specific strategy for reducing unnecessary spending and promoting efficient use of funds. 【0753】 "Real-time" refers to the immediate processing or response that takes place as soon as data is generated. 【0754】 A "suggestion" is specific advice or guidance provided to encourage users to take action. 【0755】 "Users" refer to individuals or households that actually use the system or service. 【0756】 The system used to implement this application is designed to streamline household financial management. Users first access the system using a terminal equipped with a voice input device. The terminal recognizes the user's voice commands and collects household financial data. This includes obtaining bank account transactions and credit card usage data through financial institution APIs. 【0757】 The server analyzes the acquired data using machine learning algorithms to classify income and expenses. Libraries such as TensorFlow and PyTorch can be used for this purpose. Natural language processing APIs are used for speech recognition. The analysis results are displayed to the user visually in real time and also provided via audio. Expenditure trends are visualized in graphs and tables, promoting intuitive understanding for the user. 【0758】 The server then generates savings strategies based on the user's spending patterns. These strategies include specific suggestions, such as "You can save 5,000 yen per month by reducing your dining out frequency from twice a week to once a week." These suggestions are communicated to the user via voice notifications. 【0759】 The server also collects discount information and coupons from multiple partner sources and notifies users of information selected to match their interests. For example, it might be provided in the form of "This week's discount coupons for your nearest supermarket." 【0760】 Furthermore, the server monitors the progress of the set budget in real time and provides feedback. By displaying budget achievement status as visual feedback and notifying users of areas for improvement, users can quickly improve their usage. 【0761】 For example, if a user asks, "How much are my food expenses this month?", the system will respond verbally, "Currently, it's 30,000 yen," and visually display a graph showing the monthly food expense trend on the screen. As an example of a prompt to the generating AI model, if you input, "Please explain my transportation expenses for this month," the system will generate a comprehensive analysis of transportation expenses and savings suggestions. 【0762】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0763】 Step 1: 【0764】 The user enters voice commands via a terminal. A voice input device converts these commands into digital data, and a speech recognition API performs natural language processing to interpret the user's questions and instructions. The input is voice command data, and the output is the parsed instructions in text format. 【0765】 Step 2: 【0766】 The device sends requests to financial institutions' APIs with the user's permission to retrieve household financial data. This retrieves bank account and credit card transaction information. The input is user authentication information, and the output is transaction data. 【0767】 Step 3: 【0768】 The server processes the acquired transaction data through a machine learning algorithm. A data classification algorithm is used to categorize each transaction, such as food expenses or transportation costs. The input is raw transaction data, and the output is categorized data. 【0769】 Step 4: 【0770】 The server analyzes the classified data and generates savings strategies. This analysis includes identifying spending patterns and detecting anomalies. The generating AI model suggests necessary savings and outputs specific advice. The input is classified transaction data, and the output is specific savings advice. 【0771】 Step 5: 【0772】 The server collects discount information and coupons from partner sources and selects and presents appropriate options based on the user's spending patterns. The input is discount information from partners, and the output is coupon information tailored to the user's interests. 【0773】 Step 6: 【0774】 The server monitors the progress of the set budget in real time and generates feedback based on the collected data. It notifies the user of achievements and areas for improvement through visual displays and audio. Inputs are the latest expenditure data and budget information, while outputs are visual and audio feedback. 【0775】 Step 7: 【0776】 The user is notified, and suggested savings strategies and coupons are presented visually and audibly through the device. Based on the displayed information, the user can adjust their financial behavior. The input is savings advice and coupon information, and the output is the user's awareness and behavioral changes. 【0777】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0778】 This invention provides more personalized savings advice by combining a system for managing household financial information with an emotion engine that recognizes user emotions. This system effectively manages household spending data and uses that data to provide more accurate advice to the user. 【0779】 The system consists of a terminal, a server, and an emotion engine. The server processes financial data received from the terminal and classifies the data using machine learning algorithms. The classified data is analyzed on the server to detect spending trends and anomalies. Based on the analysis results, the server generates optimal saving advice and notifies the user through the terminal. 【0780】 The emotion engine recognizes the user's emotions in real time. This emotion information is obtained by inferring the emotional state based on data such as the user's actions while operating the device, voice input, and text input. Based on this information, the server adjusts the content and timing of advice and sets reminders that are tailored to the user's emotions. Therefore, it is possible to offer savings suggestions in a way that is easy for the user to accept. 【0781】 For example, suppose users tend to spend more at the end of the month when they are more stressed. In this case, the emotion engine can detect the user's stress, and the server can send budget advice and suggest ways to relax, thereby promoting better spending management. 【0782】 By combining this with an emotional engine, the system can enhance personalized care for users and improve the efficiency of household financial management. This allows users to manage their finances more systematically and with greater peace of mind, taking their own emotional state into consideration. 【0783】 The following describes the processing flow. 【0784】 Step 1: 【0785】 Users link their bank accounts and credit cards to the device. The device periodically retrieves transaction data from the user's financial institutions and sends it to the server. 【0786】 Step 2: 【0787】 The server receives the acquired transaction data. Next, the server uses a machine learning algorithm to automatically classify the data into categories such as food expenses, transportation expenses, and utility expenses. 【0788】 Step 3: 【0789】 The server analyzes the categorized data to identify spending trends and anomaly patterns. Based on the analysis, the server identifies areas where savings can be made. 【0790】 Step 4: 【0791】 The server generates savings advice and sends it to the terminal. The advice includes suggestions for specific behavioral changes. 【0792】 Step 5: 【0793】 The emotion engine uses device data to recognize the user's current emotional state. As the user interacts with the device, emotion data is collected when they use voice input or send text messages, and their emotions are inferred in real time. 【0794】 Step 6: 【0795】 The server receives the output from the emotion engine and adjusts the content of advice and the timing of notifications based on the emotional information. For example, when the user is relaxed, it might send advice about the next month's budget earlier than scheduled. 【0796】 Step 7: 【0797】 The device notifies the user of emotionally tailored advice. The user can review the notified advice and add reminders to make it easier to take action. 【0798】 Step 8: 【0799】 The server evaluates whether the advice and notifications sent were effective for the user, and records and analyzes the data for future improvements. It also evaluates the relationship between the user's emotional state and spending behavior, and uses this information to generate future advice. 【0800】 (Example 2) 【0801】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0802】 Traditional household financial information management systems have struggled to provide personalized saving advice that takes into account the user's emotional state. Because they cannot provide advice at the appropriate time and with the right content based on the user's emotions, effective spending management is hindered. Therefore, there is a need to develop a system that enables financial management that reflects the user's emotions. 【0803】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0804】 In this invention, the server includes means for recognizing the user's emotional state, means for adjusting the results of financial information analysis using the recognized emotional information, and means for generating personalized advice based on the adjusted analysis results. This enables the provision of effective financial management and spending advice tailored to the user's individual emotional state. 【0805】 "Means for recognizing the user's emotional state" refers to a function that analyzes voice input and operation data to identify the user's psychological state and emotions. 【0806】 "Means for adjusting the results of financial information analysis" refers to a function that modifies the evaluation and analysis of existing financial data based on perceived emotional states. 【0807】 "Means of generating personalized advice" refers to a function that creates guidelines for saving and managing spending that are tailored to each user's individual circumstances and feelings, based on the adjusted analysis results. 【0808】 "Means of obtaining household financial information" refers to the function of collecting data such as income and expenses related to household finances. 【0809】 "Means for classifying acquired financial information" refers to the function of organizing collected financial data by category. 【0810】 "Means for identifying potential savings" refers to the function of finding redundancy and waste from analyzed data and determining areas for savings. 【0811】 "Means of notifying users of generated advice" refers to a function that communicates the created guidelines and suggestions to users in an appropriate manner. 【0812】 "Means of collecting and providing discount information and coupons" refers to a function that collects and presents advantageous information obtained from markets and stores to users. 【0813】 "Means of analyzing budget achievement and providing feedback" refers to a function that verifies the actual income and expenditure situation against the budget and provides advice to users based on the results. 【0814】 "Means for detecting abnormal spending" refers to a function that identifies and warns of consumer behavior that deviates from normal patterns. 【0815】 "Methods for automatically classifying financial information using machine learning algorithms" refers to a function that utilizes artificial intelligence technology to automatically organize collected financial data. 【0816】 This invention is designed to effectively support users' financial management in their homes. The system primarily consists of a server, terminals, and an emotion engine. Specific hardware includes smartphones and personal computers that enable user-initiated data entry. Software includes an emotion engine for sentiment analysis, machine learning algorithms, and data analysis tools running on the server. 【0817】 The server manages financial data sent from users in the cloud. Data is sent from the terminal to the server using a secure protocol (e.g., SSL / TLS). The server classifies this data into categories using machine learning algorithms (e.g., scikit-learn) and analyzes user consumption patterns. Database management systems (e.g., PostgreSQL) and data analysis libraries (e.g., Pandas, NumPy) are used for the analysis. 【0818】 The emotion engine utilizes voice input and user actions to recognize the user's emotional state in real time. This data is analyzed using a generative AI model. Based on this input, the emotion engine infers the user's psychological state and sends that information to the server. 【0819】 As a concrete example, consider a case where a user tends to feel stressed at the end of the month and increases their spending. The emotion engine analyzes voice and operation data entered from the device to recognize this stress level. Based on this information, the server generates and notifies the user of advice such as, "It may be difficult to meet this month's budget, but please try some relaxation techniques to alleviate stress." This allows the user to receive appropriate financial management advice based on their emotions. 【0820】 An example of a prompt message is, "Generate the best savings advice for this week based on the user's spending data and emotional state." This allows the system to provide advice tailored to each user's situation. 【0821】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0822】 Step 1: 【0823】 Data collection and input 【0824】 Users input their daily income and expense information into their device. Specifically, they use a smartphone app or web interface to enter the amount, expense category (daily necessities, transportation, etc.), and date. This data is temporarily stored on the device and prepared for later processing. 【0825】 Input: User spending and income information 【0826】 Output: Financial data stored on the device 【0827】 Step 2: 【0828】 Data transmission and classification 【0829】 The terminal transmits financial data collected from the user to the server via the internet. The data is sent securely using a secure communication protocol (SSL / TLS). The server then uses a machine learning algorithm (e.g., scikit-learn) to classify the received data into expenditure categories. During this classification process, the characteristics of the data are extracted and mapped to pre-defined categories. 【0830】 Input: Financial data sent from the terminal 【0831】 Output: Data categorized on the server. 【0832】 Step 3: 【0833】 Data analysis 【0834】 The server uses the classified data to analyze consumption patterns. A database management system (e.g., PostgreSQL) is used to calculate trends and outliers in the collected data, identifying consumption peaks and irregular spending. The data is analyzed using statistical methods with libraries such as Pandas and NumPy. 【0835】 Input: Classified financial data 【0836】 Output: Analysis results of consumption patterns 【0837】 Step 4: 【0838】 Recognition of emotions 【0839】 The emotion engine analyzes the user's emotions in real time based on device operation logs and voice input data. It uses a generative AI model to identify emotional states (e.g., stress, happiness) through text analysis and voice acoustic analysis. The emotional data is sent to a server for use in subsequent processes. 【0840】 Input: Operation data and voice data to the terminal 【0841】 Output: Emotional state data sent to the server 【0842】 Step 5: 【0843】 Generating and notifying advice 【0844】 The server generates personalized savings advice based on the analysis of financial data and the user's emotional state. This advice may include specific suggestions such as, "We recommend relaxing activities at the end of the month." The system also considers the user's emotional state and spending patterns to create an optimal notification schedule. The generated advice is then communicated to the user via their device. 【0845】 Input: Analysis results and emotional state data 【0846】 Output: Advice message notified to the user 【0847】 (Application Example 2) 【0848】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0849】 Conventional household financial information management systems often fail to provide sufficient savings advice because they do not take into account the emotional state of each user. This can result in insufficient user satisfaction and savings. Furthermore, because they do not utilize emotional information, the timing and content of the advice may not be in line with the user's psychological state, which is a problem. 【0850】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0851】 In this invention, the server includes means for acquiring household financial information, means for classifying the acquired financial information, and means for inferring the user's psychological state and adjusting the timing and content of appropriate advice. This enables personalized saving advice tailored to the user's emotional state to be provided in real time, resulting in more effective spending management. 【0852】 "Economic information" refers to data about a household's financial status, such as income, expenses, assets, and liabilities. 【0853】 "User psychological state" refers to the emotions and moods that users experience in specific situations, and these influence their behavior and reactions when using the system. 【0854】 "Savings advice" refers to specific suggestions and instructions for controlling or optimizing spending, provided based on an individual user's financial information and psychological state. 【0855】 "Real-time" refers to a time standard that involves processing or responding immediately and without delay, based on the current situation and the latest data. 【0856】 A "machine learning algorithm" is a computational method that analyzes large amounts of data to find patterns and uses the learned results to predict and classify new data. 【0857】 "Adjusting the timing and content of appropriate advice" refers to a function that changes the timing and content of notifications according to the user's psychological state, thereby supporting more effective spending management. 【0858】 The system for realizing this invention mainly consists of three elements: a server, a terminal, and a user. The server understands the household's financial information and the user's psychological state, and provides optimal saving advice. The terminal functions as an interface for user operation and transmits and receives data with the server. Through the terminal, the user can check their financial information and advice and use it to manage their daily expenses. 【0859】 The server is primarily built using the Python programming language and utilizes TensorFlow, a machine learning library, for data analysis. On the server, a generative AI model learns based on users' economic information and psychological state, generating personalized advice for each user. A web application using Flask supports communication between the server and the user terminal. 【0860】 Specifically, user psychological data is collected from sensors on the device. This data is sent to a server in real time and processed by machine learning algorithms. Based on the resulting psychological state, the content and timing of advice are adjusted. For example, during periods of high stress, helpful information and money-saving tips that promote relaxation are suggested. 【0861】 This system enables users to manage their household finances in a planned and secure manner, taking their own emotional state into consideration. 【0862】 An example of a prompt message is: "If the user is feeling stressed, please provide relaxing money-saving advice. Sentiment data is updated in real time." 【0863】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0864】 Step 1: 【0865】 The device receives financial information from the user as input. The user records spending and income data through a household budgeting app. This information is immediately sent to the server. 【0866】 Step 2: 【0867】 The server uses the received economic information to classify the data. Machine learning algorithms are used to categorize spending items and trends, and to extract specific patterns. This allows for the automatic detection of spending trends and anomalies. 【0868】 Step 3: 【0869】 The device collects data to understand the user's psychological state. This is primarily done through sensors built into the device, using the smartphone's camera and microphone to analyze the user's facial expressions and tone of voice. The analysis results are sent to a server. 【0870】 Step 4: 【0871】 The server uses a generative AI model to analyze data based on the user's psychological state. It integrates and analyzes psychological data and economic information to generate personalized savings advice. In this process, appropriate advice is designed based on prompt statements. 【0872】 Step 5: 【0873】 The server sends the generated advice to the terminal. The terminal notifies the user of the advice. Through the notification, the user can check specific saving methods tailored to their situation and the coupon information offered. 【0874】 Step 6: 【0875】 Users adjust their daily financial activities based on the advice they receive. They periodically send feedback from their device to the server to reflect their income, expenses, and satisfaction levels. This feedback is used to improve future advice. 【0876】 The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0877】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0878】 In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414. 【0879】 Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion. 【0880】 Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together. 【0881】 These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression. 【0882】 The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become. 【0883】 Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant. 【0884】 The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more." 【0885】 The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values. 【0886】 The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format. 【0887】 In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data. 【0888】 In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56. 【0889】 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. 【0890】 Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56. 【0891】 The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory. 【0892】 The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor. 【0893】 Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources. 【0894】 Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose. 【0895】 The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above. 【0896】 All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference. 【0897】 The following is further disclosed regarding the embodiments described above. 【0898】 (Claim 1) 【0899】 Means of obtaining household financial information, 【0900】 A means of classifying acquired financial information, 【0901】 A means of analyzing classified information and identifying potential savings, 【0902】 Means for generating advice based on identified areas where savings can be made, 【0903】 A means of notifying the user of the generated advice, 【0904】 Means for collecting and providing discount information and coupons, 【0905】 A means of analyzing budget achievement status and providing feedback, 【0906】 A system that includes this. 【0907】 (Claim 2) 【0908】 The system according to claim 1, comprising means for monitoring household financial information in real time and detecting abnormal expenditures. 【0909】 (Claim 3) 【0910】 The system according to claim 1, comprising means for automatically classifying financial information using a machine learning algorithm. 【0911】 "Example 1" 【0912】 (Claim 1) 【0913】 Means of obtaining information from financial institutions, 【0914】 A means of periodically collecting transaction data using the acquired information, 【0915】 A method for classifying financial data into categories using machine learning technology, 【0916】 A means of analyzing spending trends using classified information and detecting abnormal spending, 【0917】 A means for identifying areas where savings can be made based on the analysis results and generating advice for saving, 【0918】 A means of notifying the device of the generated advice and setting reminders as needed, 【0919】 A means of collecting discount information and coupons from partners and providing them to users, 【0920】 A means to monitor the progress of the budget set by the user and evaluate the degree of achievement in real time, 【0921】 A system that includes this. 【0922】 (Claim 2) 【0923】 The system according to claim 1, comprising means for monitoring household financial management in real time and identifying anomalies in spending. 【0924】 (Claim 3) 【0925】 The system according to claim 1, comprising means for automatically classifying financial data using a machine learning model. 【0926】 "Application Example 1" 【0927】 (Claim 1) 【0928】 Means of obtaining household financial data, 【0929】 A means of analyzing acquired financial data using a voice input device, 【0930】 A means of providing users with classified financial data through voice input and visual display, 【0931】 A means of identifying and proposing savings strategies based on financial data analyzed in real time, 【0932】 Means for notifying users of suggestions generated based on identified conservation policies via audio and visual means, 【0933】 A means of collecting discount information and coupons from various sources and presenting them to users, 【0934】 A means of analyzing the achievement status of the set budget in audio and visual formats and providing feedback, 【0935】 A system that includes this. 【0936】 (Claim 2) 【0937】 The system according to claim 1, comprising means for monitoring household financial data in real time using a voice input device and detecting abnormal expenditures. 【0938】 (Claim 3) 【0939】 The system according to claim 1, comprising means for automatically classifying financial data using a machine learning algorithm and providing audio and visual feedback. 【0940】 "Example 2 of combining an emotion engine" 【0941】 (Claim 1) 【0942】 Means for recognizing the emotional state of the user, 【0943】 A means of adjusting the results of financial information analysis using recognized sentiment information, 【0944】 A means of generating personalized advice based on adjusted analysis results, 【0945】 A means of notifying the user of the generated advice at the optimal time, 【0946】 Means of obtaining household financial information, 【0947】 A means of classifying acquired financial information, 【0948】 A means of analyzing classified information and identifying potential savings, 【0949】 Means for generating advice based on identified areas where savings can be made, 【0950】 A means of notifying the user of the generated advice, 【0951】 Means for collecting and providing discount information and coupons, 【0952】 A means of analyzing budget achievement status and providing feedback, 【0953】 A system that includes this. 【0954】 (Claim 2) 【0955】 The system according to claim 1, comprising means for monitoring household financial information in real time and detecting abnormal expenditures. 【0956】 (Claim 3) 【0957】 The system according to claim 1, comprising means for automatically classifying financial information using a machine learning algorithm. 【0958】 "Application example 2 when combining with an emotional engine" 【0959】 (Claim 1) 【0960】 Means of obtaining household financial information, 【0961】 A means of classifying acquired economic information, 【0962】 A means of analyzing classified information and identifying potential savings, 【0963】 Means for generating advice based on identified areas where savings are possible, 【0964】 A means of notifying the user of the generated advice, 【0965】 A means of inferring the user's psychological state and adjusting the timing and content of appropriate advice, 【0966】 Means for collecting and providing discount information and coupons, 【0967】 A means of analyzing budget achievement status and providing feedback, 【0968】 A system that includes this. 【0969】 (Claim 2) 【0970】 The system according to claim 1, comprising means for monitoring household financial information in real time and detecting abnormal spending, and means for monitoring payment status based on user psychological data. 【0971】 (Claim 3) 【0972】 The system according to claim 1, comprising means for automatically classifying economic information and psychological data using machine learning algorithms. [Explanation of Symbols] 【0973】 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

[Claim 1] Means of obtaining household financial information, A means of classifying acquired financial information, A means of analyzing classified information and identifying potential savings, Means for generating advice based on identified areas where savings can be made, A means of notifying the user of the generated advice, Means for collecting and providing discount information and coupons, A means of analyzing budget achievement status and providing feedback, A system that includes this. [Claim 2] The system according to claim 1, comprising means for monitoring household financial information in real time and detecting abnormal expenditures. [Claim 3] The system according to claim 1, comprising means for automatically classifying financial information using a machine learning algorithm.

Images