system

Abstract

Provide a system. 【Solution means】 Means for collecting financial data from users, Means for automatically classifying the collected financial data by category, Means for analyzing the classified data and identifying opportunities for savings, Means for presenting savings advice to users, Means for tracking users' savings actions and providing feedback, Means for providing users with beneficial information and discount information, Means for a household device to read paper financial data and digitize it, Means for transmitting the digitized data to a remote information processing device, A system including

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 the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, due to rising prices and stagnant wages, the burden on households has been increasing. In many households, it is necessary to manage finances efficiently and save money within limited income, but there is a lack of appropriate expenditure analysis and provision of specific saving advice. Therefore, there is a problem that it is difficult to manage daily expenditures efficiently.

Means for Solving the Problems

[0005] This invention provides a system that automatically collects financial data from users and classifies it by category, enabling a comprehensive understanding of income and expenses. This system includes means for identifying savings opportunities through analysis of the classified data and providing appropriate advice to users. Furthermore, it promotes saving behavior by tracking user actions and providing feedback. It also achieves tangible savings by providing advantageous information and coupons tailored to the user's spending patterns.

[0006] "Financial data" refers to all information related to household income and expenses, specifically including credit card statements and receipts.

[0007] "Means of collection" refers to the processes and technologies used to obtain financial data from users and store it within the system.

[0008] "Methods for automatically classifying by category" refers to algorithms and technologies that divide collected financial data into categories such as food, transportation, housing, and entertainment.

[0009] "Means of analysis and identifying savings opportunities" refers to the processes and techniques used to analyze categorized data and identify which spending items are wasteful.

[0010] "Means of providing advice" refers to methods and tools for communicating appropriate cost-saving measures to users based on analysis results.

[0011] "Means of tracking behavior and providing feedback" refers to processes and technologies that record and analyze users' actual spending behavior and return information to users based on that information.

[0012] "Means of providing advantageous information and coupons" refers to methods and systems for finding and providing discount information and coupons that are suitable for the user's spending habits. [Brief explanation of the drawing]

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

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

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

[0016] In the following embodiments, the 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), and the like.

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

[0018] In the following embodiments, the 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.

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

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

[0021] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0034] This invention is a system that automatically collects, classifies, and analyzes financial data to provide savings advice in order to support users' financial management. Its embodiments will be described in detail below.

[0035] Users access the application using devices such as smartphones or computers and upload images of credit card statements or receipts. The device then uses OCR technology to convert the image data into text data and sends it to the server as financial data. The server stores the received financial data in a database.

[0036] Next, the server analyzes the data and uses natural language processing and machine learning algorithms to categorize the collected data into categories such as food, transportation, housing, and entertainment. Based on this classification, the server analyzes spending patterns and identifies which spending in each category is excessive or can be reduced. Based on these analysis results, the server generates specific advice that shows the user opportunities to save money. For example, if a user's monthly food and beverage expenses are high, the server might suggest "limiting eating out to once a week."

[0037] Subsequently, the device notifies the user of advice generated by the server and provides a reminder function to prompt action as needed. Each time the user takes action, the device sends the spending status to the server, which updates the information in real time to generate even more appropriate feedback.

[0038] Furthermore, the server can utilize discount coupons and special offers obtained from various partner companies to provide users with the most suitable deals based on their preferences and purchasing behavior. This feature allows users to make more efficient purchases and helps them manage their household finances.

[0039] In this way, the entire system works together to promote improvements in users' lives and enhance the efficiency of household budget management.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] Users upload images of credit card statements and receipts via an application using their smartphones or computers. The device then uses OCR technology to extract text information from these images and formats it as financial data.

[0043] Step 2:

[0044] The terminal sends the extracted financial data to the server. The server stores the received data in a database. The data is categorized into information such as date, expenditure amount, and expenditure details.

[0045] Step 3:

[0046] The server analyzes financial data stored in the database and automatically classifies it into categories such as food and beverage, transportation, housing, and entertainment using machine learning algorithms.

[0047] Step 4:

[0048] The server analyzes user spending patterns based on categorized data. By comparing this with past data, it identifies categories of unusual spending or areas where savings can be made.

[0049] Step 5:

[0050] The server identifies opportunities for saving money and generates specific saving advice based on the user's spending habits. This advice includes action plans and specific saving targets to reduce spending.

[0051] Step 6:

[0052] The terminal notifies the user of advice obtained from the server. The notification includes savings suggestions and specific actions to be taken, which the user can review and implement.

[0053] Step 7:

[0054] When a user takes action based on the advice, the device records that action and sends it to the server. The server uses this information to analyze the progress of spending and the achievement of savings goals.

[0055] Step 8:

[0056] Based on the analysis results, the server generates feedback, providing information on achieved savings and further suggestions. It also references coupons and discount information from partner companies and sends advantageous information tailored to the user's spending habits to their device.

[0057] (Example 1)

[0058] 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."

[0059] In modern society, users are required to efficiently manage a wide range of spending information. However, doing so manually is incredibly time-consuming and can make accurate data analysis difficult. Furthermore, providing specific, personalized saving advice to users is challenging, and there is a lack of efficient support based on consumption trends.

[0060] 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.

[0061] In this invention, the server includes means for collecting economic data from users in multiple formats, means for converting the collected data into text using image processing technology, and means for automatically classifying the converted data into hierarchical categories. This makes it possible to efficiently analyze the user's economic data and provide accurate advice and optimal discount information in real time.

[0062] A "user" is an individual or organization that uses this system to manage their own economic data.

[0063] "Economic data" refers to information about a user's daily spending and income, including credit card statements and receipts.

[0064] "Image processing technology" refers to techniques for extracting text data from image data, and includes OCR (Optical Character Recognition).

[0065] "Converting to text" refers to the process of converting image data into text information.

[0066] "Hierarchical categorization" refers to a method of classifying data into several main categories and subdivided subcategories below them.

[0067] "Automatic classification" refers to the process of using machine learning or algorithms to sort data into appropriate categories based on pre-defined rules.

[0068] "Guidelines" refers to specific advice and suggestions for users to make their economic activities more efficient.

[0069] "Discount information" refers to preferential pricing and promotional information provided by affiliated third parties.

[0070] "Real-time delivery" means that whenever user behavior or data is updated, information and feedback corresponding to that change are immediately presented.

[0071] This invention is a system that efficiently handles economic data and provides savings advice through analysis to support users' financial management. Users access a dedicated application using devices such as smartphones or computers. Users collect data by uploading images of credit card statements and receipts to the application.

[0072] The device converts the received image data into text data using image processing technology, specifically OCR technology. Common OCR tools include Tesseract, and cloud-based solutions are available as commercial services. At this stage, the device sends the converted text data to the server.

[0073] The server records the received text-formatted economic data in a database management system. Suitable database systems include scalable open-source systems such as MySQL® and PostgreSQL. The recorded data is then categorized hierarchically using natural language processing and machine learning algorithms, such as food, transportation, housing, entertainment, and others.

[0074] Following data classification, the server analyzes spending patterns in detail and detects unique trends. Based on the analysis results, it uses an AI model to formulate guidelines for optimizing the user's spending. For example, if spending is increasing in a particular category, it generates advice on reducing spending in that category. A specific example of such advice might be, "Since food expenses are high, refrain from eating out once a week."

[0075] The generated guidelines are sent from the server to the terminal, which then notifies the user. Each time the user takes action according to the guidelines, the result is fed back from the terminal to the server, and the server updates the data in real time, enabling further analysis and more efficient advice.

[0076] Furthermore, the server provides users with discount information and coupons obtained from partner third parties. This information is selected based on the user's preferences and purchasing behavior, with the aim of positively influencing the user's purchasing decisions.

[0077] An example of a prompt message might be, "Analyze the user's economic data to identify spending trends and suggest ways to reduce costs." This invention is a comprehensive system for monitoring the user's daily economic activities and supporting efficient financial management.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] Users access the application using devices such as smartphones or computers and upload image data of credit card statements or receipts. The input is image data, and the output is prepared to be converted into text data. The device receives the image and forms the foundation for processing this data in the next step.

[0081] Step 2:

[0082] The terminal applies OCR technology to the received image data, converting the character data within the image into text format. The input is image data, and the output is text data. In this step, OCR software is used to perform character recognition and extract the necessary financial information.

[0083] Step 3:

[0084] The terminal sends the text data extracted by OCR to the server. The input is text data, and the output is data transfer to the server. This makes the financial data available for analysis on the server side.

[0085] Step 4:

[0086] The server records the received text-formatted economic data in a database. The input is text data, and the output is structured data stored in the database. In this step, data persistence takes place and is used in subsequent analysis steps.

[0087] Step 5:

[0088] The server automatically categorizes data using natural language processing and machine learning algorithms. The input is structured data stored in a database, and the output is categorized data. Specifically, expenditures are classified into categories such as food, transportation, housing, and entertainment.

[0089] Step 6:

[0090] The server analyzes the classified data and examines spending patterns in detail. This identifies abnormal spending trends and areas for improvement. The input is classified data, and the output is a report containing the analysis results.

[0091] Step 7:

[0092] The server generates specific savings advice for the user based on the analysis results. The input is the analysis results, and the output is text data providing guidance. Using a generation AI model, it follows the instruction, as an example of a prompt, "Analyze the user's economic data, identify spending trends, and suggest ways to reduce costs."

[0093] Step 8:

[0094] The server sends the generated advice and acquired discount information to the terminal. The input is the advice text and discount information, and the output is a notification signal to the user. This allows the user to receive useful information that is updated regularly.

[0095] Step 9:

[0096] The device notifies the user of the advice it receives and, if necessary, sets a reminder. The input is a notification signal from the server, and the output is information displayed on the user interface. This allows the user to take action according to the advice.

[0097] (Application Example 1)

[0098] 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."

[0099] Modern users receive numerous paper receipts and invoices by mail in their daily lives, making it difficult to efficiently organize this financial data and obtain advice on saving money. Furthermore, the lack of means to digitize and automatically analyze this paper information has made it difficult to grasp more effective saving methods and manage household finances effectively.

[0100] 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.

[0101] In this invention, the server includes means for collecting financial data from users, means for automatically classifying the collected data into categories, means for analyzing the classified data and identifying opportunities for savings, means for a household appliance to read paper financial data and digitize it, and means for transmitting the digitized data to a remote information processing device. This makes it possible to automatically organize all financial data, including paper information, and provide savings advice tailored to the user.

[0102] "Means of collecting financial data from users" refers to technologies that automatically acquire information from financial information owned by users or from paper documents.

[0103] "Methods for automatically classifying data by category" refers to functions that sort collected data into categories such as food, transportation, and housing.

[0104] "Methods for identifying savings opportunities" refer to techniques that use analyzed data to identify unnecessary spending and items that can be reduced.

[0105] "A means of providing users with money-saving advice" refers to a function that notifies users of specific money-saving methods based on the analyzed information.

[0106] "A means of tracking users' saving behavior and providing feedback" refers to technology that tracks users' actions and spending and suggests areas for improvement based on that data.

[0107] "Means of providing users with advantageous information and discount information" refers to technology that delivers promotional information from partner companies to users according to their interests and behavior.

[0108] "A means by which household devices read and digitize paper financial data" refers to technology that reads information printed on paper using a machine and converts it into digital information.

[0109] "Means for transmitting digitized data to a remote information processing device" refers to the technology of transferring locally stored digital data to another device via a network.

[0110] This invention is a financial management support system using consumer electronics, aiming to manage users' lives more efficiently. The server automatically collects and analyzes financial data through the user's terminal and home appliances. Cameras and OCR sensors mounted on the terminal read paper-based receipts and invoices received by the user, digitize them, and transmit the data to a cloud server.

[0111] The cloud server uses natural language processing and machine learning algorithms to categorize this data into categories such as food, transportation, and housing. Furthermore, based on the categorized data, the server analyzes the user's spending patterns and identifies opportunities for saving. Saving advice generated based on the analysis is then communicated visually or audibly through home appliances or the user's device.

[0112] Specifically, the server can issue advice such as "limit eating out to once a week." This allows users to review their spending habits and implement effective saving methods. The server also provides coupons tailored to the user's spending habits based on the latest discount and special offers from partner companies.

[0113] The hardware required to run the program includes camera sensors and OCR sensors built into home appliances, as well as terminals capable of network communication. The software includes OCR libraries (e.g., Tesseract) and cloud services for data analysis (e.g., AWS® Lambda).

[0114] As a concrete example, a user could have a home device scan receipts from restaurants they frequent for dinner, and if the device determines that their spending is excessive, it could provide advice such as "You should reduce the number of times you eat out this month," along with information on coupons that can be used at that restaurant.

[0115] An example of a prompt message for the generated AI model could be: "This home robot is an application that scans paper receipts collected by the user, analyzes them in the cloud, and provides advice on saving money." This allows the entire system to work together and contribute to improving the user's life.

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] Based on user instructions, the terminal uses the camera of a home appliance to scan paper receipts and invoices. In this step, paper financial data is provided as input, and digital image data is generated as output. Through the image capture operation, the information on paper is visually recorded.

[0119] Step 2:

[0120] The terminal scans digital image data, which is then input to an OCR sensor for character recognition. This converts the image data into analyzable digital text data. The input is a scanned image, and the output is text data; this conversion is performed using OCR technology.

[0121] Step 3:

[0122] The terminal sends the generated digital text to the server. The server stores the received text data in a cloud environment. This ensures that the data is securely stored and used as a basis for subsequent processing.

[0123] Step 4:

[0124] The server analyzes stored text data and classifies it into categories using natural language processing techniques and machine learning algorithms. The input is the stored text data, and the output is the classification results for each category. The analysis process involves pattern recognition using algorithms.

[0125] Step 5:

[0126] The server analyzes users' financial behavior based on categorized data and identifies opportunities for saving. The input is the classification results, and the output is data for saving advice. The analysis process involves comparing spending patterns and generating personalized advice.

[0127] Step 6:

[0128] The server generates money-saving advice and sends it to the terminal, which then notifies the user. The input is the advice data, and the output is the notification information for the user. In this step, specific money-saving suggestions are presented to the user through the mobile terminal's display or audio output device.

[0129] Step 7:

[0130] When a user acts on savings advice, the device reports the results to the server. The input is user behavior data, and the output is updated financial data. This behavior tracking provides continuous feedback, improving the accuracy of the advice.

[0131] Step 8:

[0132] The system integrates behavioral data collected by the server with information from partner companies to provide users with customized discount information. Inputs are user behavioral data and promotional information from companies, and output is customized coupon information. This promotion generation allows users to shop flexibly and save money.

[0133] 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.

[0134] This invention combines a system that manages users' financial data and provides savings support with an emotion engine that recognizes users' emotions, thereby providing more effective savings advice. This system functions when users access the application using a smartphone or computer to manage their finances.

[0135] Users upload images of their credit card statements and receipts to the app. The device uses OCR technology to extract text information from the images and organizes it as financial data. This financial data is sent to a server and stored in a database. The server categorizes the stored data and analyzes the user's spending patterns. Based on the analysis, it generates specific advice highlighting savings opportunities and notifies the user through their device.

[0136] In addition, the system integrates an emotion engine that analyzes the user's emotions. Users input their emotional state into the app or it is detected by biosensors connected to their device. This emotional data is sent to a server and analyzed along with financial data. The emotion engine learns what emotional states a user tends to be in when they increase their spending and identifies emotional patterns that influence spending behavior.

[0137] For example, if it becomes clear that a user's spending on entertainment increases when they are stressed, the server will provide constructive advice to reduce entertainment spending when it detects their stress level. Furthermore, if emotional data predicts that a user is at high risk of unconsciously overspending, the device will send a preventative notification to the user to help them control their spending.

[0138] This combination of emotional engines enables more personalized and specific saving advice for users, significantly improving the efficiency and effectiveness of household budget management.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] Users access the application using their smartphones or computers and upload images of credit card statements or receipts. The device receives these images, extracts text information using OCR technology, and organizes the read data.

[0142] Step 2:

[0143] The terminal sends the extracted financial data to the server. The server stores the received data in a database and organizes it by category for smooth analysis.

[0144] Step 3:

[0145] The server applies machine learning algorithms to analyze the stored data, classifying spending into categories such as food, transportation, housing, and entertainment, and identifying spending trends. From these analysis results, it identifies particularly noteworthy spending trends and areas where savings can be made.

[0146] Step 4:

[0147] Users input their daily emotional states into the application or obtain real-time emotional data using biosensors connected to their device. This emotional data is then transmitted to a server via the device.

[0148] Step 5:

[0149] The server integrates and analyzes financial and emotional data. It learns which spending categories are affected by specific emotional states and adjusts advice based on those results. For example, if spending on entertainment tends to increase when stress levels are high, the server will generate personalized saving advice when it detects that emotional state.

[0150] Step 6:

[0151] Based on the analyzed information, the server generates money-saving advice for the user and presents a concrete action plan. This advice is notified to the user via their device, and reminders and warnings may be issued as needed.

[0152] Step 7:

[0153] The user takes saving actions based on the advice they receive. The device records these actions and sends the action data back to the server. The server takes this data, provides feedback, and improves or updates the advice further.

[0154] Step 8:

[0155] The server optimizes discount coupons and information provided by partner companies based on the user's spending patterns and sentiment data, and delivers them to the user via their device. This allows the user to enjoy substantial savings.

[0156] (Example 2)

[0157] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0158] Modern consumers demand efficient and accurate advice in financial management, but traditional systems have lacked the ability to provide saving advice that adequately considers the impact of users' emotional states on their spending behavior. Furthermore, there was a challenge in identifying emotion-based spending patterns, making personalized advice difficult.

[0159] 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.

[0160] In this invention, the server includes means for extracting text data from the user, means for automatically classifying the stored information by category, and means for generating savings advice based on the analysis results using a generative AI model. This makes it possible to provide more personalized and specific savings advice that takes into account the user's emotional state.

[0161] "Means for extracting text data from users" refers to the process of extracting text information from image data provided by users using optical character recognition technology.

[0162] "Means of formatting and storing financial information" refers to the process of converting extracted text data into a specified format and saving it to a database.

[0163] "Methods for automatically classifying information into categories" refers to the process of automatically categorizing stored information using specific rules or algorithms.

[0164] "A method for generating savings advice based on analysis results using a generative AI model" refers to a process that utilizes artificial intelligence technology to analyze user data and propose the optimal savings method.

[0165] "Means for acquiring users' emotional states and integrating and analyzing them with stored information" refers to the process of analyzing emotional data collected from users in conjunction with existing financial data to gain insights into their spending behavior.

[0166] "Methods for identifying spending patterns based on emotional states" refers to the process of analyzing users' emotional data and using the results to clarify their spending tendencies.

[0167] The "ability to generate personalized savings advice" is the ability to present specific and personalized savings methods based on the user's particular circumstances and information.

[0168] This invention relates to a system that integrates and manages a user's financial data and emotional state to provide individually optimized savings advice. Users access the application using a smartphone or computer to manage their daily finances. This system is implemented in the following way:

[0169] Users upload photos of receipts or credit card statements to the application using their device. The device uses OCR technology to extract text information from the uploaded images. Specific OCR technologies that can be used include Tesseract OCR and Google® Cloud Vision API. This extracted text information is formatted as financial data on the device and prepared for transmission to the server.

[0170] The server receives financial data sent from the terminal and stores it in a database. Common RDBMSs such as MySQL and PostgreSQL can be used as the database management system. The stored data is categorized and analyzed using machine learning algorithms and data mining techniques.

[0171] Furthermore, the user's emotional state is collected through self-input within the application and via biosensors. These biosensors include heart rate monitors and skin electrical activity sensors. The collected emotional data is sent to a server and analyzed in conjunction with financial data. The emotion engine learns the correlation between the user's emotional state and spending behavior.

[0172] For example, if a pattern is identified where a user's spending on fashion increases when they are in a good mood on holidays, the server can send a prompt to the AI ​​model, which can then output specific advice such as, "Please give me advice on how to reduce unnecessary spending on fashion on my next holiday."

[0173] In this way, the server generates personalized saving advice that takes into account the user's emotional state. This system allows users to easily understand their spending patterns and efficiently take actions to reduce unnecessary spending.

[0174] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0175] Step 1:

[0176] Users launch the application using their smartphone or computer and upload images of credit card statements or receipts. The input here is image data. The device uses OCR technology to extract text information from this image data. Specifically, a program called Tesseract OCR is used to convert the text within the image into digital information. The output is text data.

[0177] Step 2:

[0178] The terminal formats the extracted text information into financial data. During this process, the text data is structured according to a specific format. This formatted data is provided in JSON or XML format. Once the data is formatted, it is ready for smooth transmission to the server. The output is the formatted financial data.

[0179] Step 3:

[0180] The terminal sends formatted financial data to the server. Upon receiving this data, the server stores it in a database. The input is the formatted financial data from the terminal, and the output is stored in the database. Generally, database management systems such as MySQL or PostgreSQL are used for this purpose.

[0181] Step 4:

[0182] The server automatically categorizes the stored financial data. This categorization utilizes pre-configured rules and algorithms. The input is financial data from the database, and the output is categorized data. This clearly reveals the user's spending patterns.

[0183] Step 5:

[0184] Users either input their emotional state within the application or collect emotional data using biosensors connected to their device (such as heart rate monitors or skin electrical activity sensors). The input is emotional information from the biosensors, and the output is the collected emotional data. This data is also sent to the server.

[0185] Step 6:

[0186] The server integrates and analyzes emotional and financial data. The emotion engine learns from historical data to identify correlations between emotional states and spending behavior. The inputs are emotional and financial data, and the output is spending patterns associated with emotional states.

[0187] Step 7:

[0188] The server uses a generative AI model to generate savings advice based on the analysis results. Here, prompts are used to gain insights into specific spending patterns. The input is the analyzed data, and the output is specific savings advice for the user.

[0189] Step 8:

[0190] The server sends the generated advice to the terminal, which then notifies the user. The input is the generated savings advice, and the output appears as a real-time notification to the user. This notification allows the user to adjust their actions immediately.

[0191] (Application Example 2)

[0192] 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".

[0193] In today's economic society, individuals engage in numerous economic activities daily, but the associated wastefulness and impulsive spending can negatively impact personal finances. Emotions, in particular, have a significant influence on economic activity, and because self-control is difficult, it is crucial to curb wasteful spending. Furthermore, conventional economic management systems lack the ability to provide personalized suggestions to users, and are especially inadequate in supporting appropriate spending management based on emotional states.

[0194] 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.

[0195] In this invention, the server includes means for collecting economic data from the user, means for analyzing emotional data, and means for generating specific advice to prevent wasteful spending. This enables personalized spending reduction suggestions based on the user's emotional state and economic behavior.

[0196] A "user" refers to an individual or customer who provides economic data and receives assistance with spending management through their emotional state.

[0197] "Economic data" is a general term for information related to an individual's finances, including information on income, expenses, purchase details, and budgets.

[0198] "Emotional data" refers to information that indicates an individual's mental state, and is acquired by the user through physical input or biosensors.

[0199] "Wasteful spending" refers to unplanned or impulsive expenditures that may threaten a user's financial health.

[0200] "Advice" refers to suggestions about economic actions a user should take, and is personalized based on the user's emotional state and economic data.

[0201] A "server" refers to a computer system that receives and processes economic and emotional data and provides users with relevant information.

[0202] "Means" is a concept that includes methods or apparatus provided to achieve a particular function in this invention.

[0203] The system of this invention is designed to enable users to manage their finances and link their personal consumption behavior to their emotional state. The server collects, integrates, and analyzes the user's economic and emotional data, enabling it to provide personalized financial advice.

[0204] First, the device collects economic data from the user using a smartphone or computer. This data includes purchase history and records of financial status. Next, the device sends emotional data collected from the user's biosensors to a server. This data is obtained using facial recognition sensors and heart rate monitors.

[0205] On the server, this data is stored in a database. MySQL is used as the database management system for processing, and Python and the machine learning library TENSORFLOW® are utilized for data analysis. Tesseract is used for OCR to extract necessary text data from statements and receipts.

[0206] Next, the server analyzes the user's economic data to identify patterns in their consumption behavior. Then, the emotion engine analyzes the emotional data and evaluates the impact of that state on their economic activity. Economic advice and warnings generated based on this information are notified to the user in real time using the Twilio API.

[0207] As a concrete example, if a user is experiencing stress while attempting to purchase an expensive item on an e-commerce platform, the server will indicate that the expenditure is unplanned and send a notification suggesting alternatives. This allows users to make rational purchasing decisions rather than reacting emotionally.

[0208] To support this process using a generative AI model, a prompt such as, "Generate effective advice to help users avoid unplanned spending when they are feeling stressed," could be used. This would allow the AI ​​to suggest optimal advice in real time, tailored to the user's situation.

[0209] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0210] Step 1:

[0211] The device retrieves economic data uploaded by the user (such as credit card statements and receipt images). Using this data as input, it extracts text information from the images using OCR technology and organizes it as economic data. The extracted data is stored in temporary data storage.

[0212] Step 2:

[0213] Economic data extracted from the terminal is sent to the server. The server stores this economic data in a database and classifies it by category using a database management system. SQL queries are used to process the data, dividing it into categories such as income and expenses.

[0214] Step 3:

[0215] The user inputs emotional data into the device using biosensors. This emotional data includes heart rate and facial expression information. The device then transmits this emotional data to a server.

[0216] Step 4:

[0217] The server receives emotional data, analyzes it using machine learning libraries (such as TensorFlow), and identifies the user's emotional state. The results of the emotional state identification are stored in a database and linked to the user's economic data.

[0218] Step 5:

[0219] The server integrates user economic and emotional data to analyze user consumption patterns. Python scripts are used for statistical analysis and trend identification. The output is a report on user consumption trends and emotions.

[0220] Step 6:

[0221] The server uses a generative AI model to generate personalized financial advice based on the prompt "Generate effective advice to prevent unplanned spending when the user is feeling stressed." This generated advice is optimized based on the user's past spending habits and emotional patterns.

[0222] Step 7:

[0223] The server uses the Twilio API to notify users of generated financial advice on their devices. These notifications include spending warnings and sentiment-based suggestions for reducing spending, and are provided to users in real time.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] [Second Embodiment]

[0228] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0229] 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.

[0230] 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).

[0231] 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.

[0232] 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.

[0233] 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).

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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".

[0240] This invention is a system that automatically collects, classifies, and analyzes financial data to provide savings advice in order to support users' financial management. Its embodiments will be described in detail below.

[0241] Users access the application using devices such as smartphones or computers and upload images of credit card statements or receipts. The device then uses OCR technology to convert the image data into text data and sends it to the server as financial data. The server stores the received financial data in a database.

[0242] Next, the server analyzes the data and uses natural language processing and machine learning algorithms to categorize the collected data into categories such as food, transportation, housing, and entertainment. Based on this classification, the server analyzes spending patterns and identifies which spending in each category is excessive or can be reduced. Based on these analysis results, the server generates specific advice that shows the user opportunities to save money. For example, if a user's monthly food and beverage expenses are high, the server might suggest "limiting eating out to once a week."

[0243] Subsequently, the device notifies the user of advice generated by the server and provides a reminder function to prompt action as needed. Each time the user takes action, the device sends the spending status to the server, which updates the information in real time to generate even more appropriate feedback.

[0244] Furthermore, the server can utilize discount coupons and special offers obtained from various partner companies to provide users with the most suitable deals based on their preferences and purchasing behavior. This feature allows users to make more efficient purchases and helps them manage their household finances.

[0245] In this way, the entire system works together to promote improvements in users' lives and enhance the efficiency of household budget management.

[0246] The following describes the processing flow.

[0247] Step 1:

[0248] Users upload images of credit card statements and receipts via an application using their smartphones or computers. The device then uses OCR technology to extract text information from these images and formats it as financial data.

[0249] Step 2:

[0250] The terminal sends the extracted financial data to the server. The server stores the received data in a database. The data is categorized into information such as date, expenditure amount, and expenditure details.

[0251] Step 3:

[0252] The server analyzes financial data stored in the database and automatically classifies it into categories such as food and beverage, transportation, housing, and entertainment using machine learning algorithms.

[0253] Step 4:

[0254] The server analyzes user spending patterns based on categorized data. By comparing this with past data, it identifies categories of unusual spending or areas where savings can be made.

[0255] Step 5:

[0256] The server identifies opportunities for saving money and generates specific saving advice based on the user's spending habits. This advice includes action plans and specific saving targets to reduce spending.

[0257] Step 6:

[0258] The terminal notifies the user of advice obtained from the server. The notification includes savings suggestions and specific actions to be taken, which the user can review and implement.

[0259] Step 7:

[0260] When a user takes action based on the advice, the device records that action and sends it to the server. The server uses this information to analyze the progress of spending and the achievement of savings goals.

[0261] Step 8:

[0262] Based on the analysis results, the server generates feedback, providing information on achieved savings and further suggestions. It also references coupons and discount information from partner companies and sends advantageous information tailored to the user's spending habits to their device.

[0263] (Example 1)

[0264] 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."

[0265] In modern society, users are required to efficiently manage a wide range of spending information. However, doing so manually is incredibly time-consuming and can make accurate data analysis difficult. Furthermore, providing specific, personalized saving advice to users is challenging, and there is a lack of efficient support based on consumption trends.

[0266] 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.

[0267] In this invention, the server includes means for collecting economic data from users in multiple formats, means for converting the collected data into text using image processing technology, and means for automatically classifying the converted data into hierarchical categories. This makes it possible to efficiently analyze the user's economic data and provide accurate advice and optimal discount information in real time.

[0268] A "user" is an individual or organization that uses this system to manage their own economic data.

[0269] "Economic data" refers to information about a user's daily spending and income, including credit card statements and receipts.

[0270] "Image processing technology" refers to techniques for extracting text data from image data, and includes OCR (Optical Character Recognition).

[0271] "Converting to text" refers to the process of converting image data into text information.

[0272] "Hierarchical categorization" refers to a method of classifying data into several main categories and subdivided subcategories below them.

[0273] "Automatic classification" refers to the process of using machine learning or algorithms to sort data into appropriate categories based on pre-defined rules.

[0274] "Guidelines" refers to specific advice and suggestions for users to make their economic activities more efficient.

[0275] "Discount information" refers to preferential pricing and promotional information provided by affiliated third parties.

[0276] "Real-time delivery" means that whenever user behavior or data is updated, information and feedback corresponding to that change are immediately presented.

[0277] This invention is a system that efficiently handles economic data and provides savings advice through analysis to support users' financial management. Users access a dedicated application using devices such as smartphones or computers. Users collect data by uploading images of credit card statements and receipts to the application.

[0278] The device converts the received image data into text data using image processing technology, specifically OCR technology. Common OCR tools include Tesseract, and cloud-based solutions are available as commercial services. At this stage, the device sends the converted text data to the server.

[0279] The server records the received text-form economic data in a database management system. MySQL and PostgreSQL, which are scalable open-source systems, are suitable for the database system. The recorded data is classified into hierarchical categories, such as food, transportation expenses, housing expenses, entertainment expenses, and others, using natural language processing and machine learning algorithms.

[0280] Following the classification of the data, the server analyzes the expenditure pattern in detail to detect unusual trends. Based on the analysis results, an AI model is used to formulate guidelines for optimizing the user's expenditure. For example, if the expenditure in a specific category shows an increasing trend, reduction advice for that category is generated. A specific example is advice such as "Since food expenses are high, refrain from eating out once a week."

[0281] The generated guidelines are sent from the server to the terminal, and the terminal notifies the user of them. Each time the user takes an action according to the guidelines, the result is fed back from the terminal to the server, and the server can update the data in real time to perform further analysis and provide more efficient advice.

[0282] Furthermore, the server provides the user with discount information and coupons obtained from third parties in cooperation. This information is selected based on the user's preferences and consumption behavior, aiming to have a positive impact on the user's purchasing behavior.

[0283] As an example of a prompt sentence, an instruction such as "Analyze the user's economic data, identify the expenditure trend, and propose cost reduction suggestions" can be considered. This invention is a comprehensive system for monitoring the user's daily economic activities and supporting efficient financial management.

[0284] The flow of the specific process in Example 1 will be described using FIG. 11.

[0285] Step 1:

[0286] The user accesses the application using a terminal such as a smartphone or a computer and uploads credit card statements and receipt image data. The input is image data, and the output is prepared to be converted into text data. The terminal receives the image and forms the basis for processing this data in the next step.

[0287] Step 2:

[0288] The terminal applies OCR technology to the received image data and converts the character data in the image into text format. The input is image data, and the output is text data. In this step, character recognition is performed using OCR software to extract the necessary financial information.

[0289] Step 3:

[0290] The terminal sends the text data extracted by OCR to the server. The input is text data, and the output is data transfer to the server. As a result, the financial data can be analyzed on the server side.

[0291] Step 4:

[0292] The server records the received text-form economic data in the database. The input is text data, and the output is structured data stored in the database. In this step, data persistence is performed and used in subsequent analysis steps.

[0293] Step 5:

[0294] The server automatically classifies the data into categories using natural language processing and machine learning algorithms. The input is structured data stored in the database, and the output is data classified by category. Specifically, expenditures are classified into food, transportation, housing, entertainment, etc.

[0295] Step 6:

[0296] The server analyzes the classified data and examines spending patterns in detail. This identifies abnormal spending trends and areas for improvement. The input is classified data, and the output is a report containing the analysis results.

[0297] Step 7:

[0298] The server generates specific savings advice for the user based on the analysis results. The input is the analysis results, and the output is text data providing guidance. Using a generation AI model, it follows the instruction, as an example of a prompt, "Analyze the user's economic data, identify spending trends, and suggest ways to reduce costs."

[0299] Step 8:

[0300] The server sends the generated advice and acquired discount information to the terminal. The input is the advice text and discount information, and the output is a notification signal to the user. This allows the user to receive useful information that is updated regularly.

[0301] Step 9:

[0302] The device notifies the user of the advice it receives and, if necessary, sets a reminder. The input is a notification signal from the server, and the output is information displayed on the user interface. This allows the user to take action according to the advice.

[0303] (Application Example 1)

[0304] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0305] Modern users receive a lot of paper receipts and mailed bills in their daily lives, making it difficult to efficiently organize this financial data and obtain savings advice. Additionally, due to the lack of means to digitize and automatically analyze this paper information, it was difficult to grasp more effective savings methods, making household management challenging.

[0306] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following means.

[0307] In this invention, the server includes means for collecting financial data from a user, means for automatically classifying the collected data by category, means for analyzing the classified data to identify savings opportunities, means for a household device to read paper financial data and digitize it, and means for transmitting the digitized data to a remote information processing device. This enables the automatic organization of all financial data including paper information and the provision of savings advice tailored to the user.

[0308] The "means for collecting financial data from a user" is a technology for automatically acquiring information from the financial information and paper media owned by the user.

[0309] The "means for automatically classifying by category" refers to the function of sorting the collected data into categories such as food, transportation, housing, etc.

[0310] The "means for identifying savings opportunities" is a technology for finding wasteful expenditures and items that can be reduced based on the analyzed data.

[0311] The "means for presenting savings advice to the user" is the function of notifying the user of specific savings methods based on the analyzed information.

[0312] The "means for tracking the user's savings actions and providing feedback" is a technology for tracking the user's actions and expenditures and presenting improvement points based on them.

[0313] "Means of providing users with advantageous information and discount information" refers to technology that delivers promotional information from partner companies to users according to their interests and behavior.

[0314] "A means by which household devices read and digitize paper financial data" refers to technology that reads information printed on paper using a machine and converts it into digital information.

[0315] "Means for transmitting digitized data to a remote information processing device" refers to the technology of transferring locally stored digital data to another device via a network.

[0316] This invention is a financial management support system using consumer electronics, aiming to manage users' lives more efficiently. The server automatically collects and analyzes financial data through the user's terminal and home appliances. Cameras and OCR sensors mounted on the terminal read paper-based receipts and invoices received by the user, digitize them, and transmit the data to a cloud server.

[0317] The cloud server uses natural language processing and machine learning algorithms to categorize this data into categories such as food, transportation, and housing. Furthermore, based on the categorized data, the server analyzes the user's spending patterns and identifies opportunities for saving. Saving advice generated based on the analysis is then communicated visually or audibly through home appliances or the user's device.

[0318] Specifically, the server can issue advice such as "limit eating out to once a week." This allows users to review their spending habits and implement effective saving methods. The server also provides coupons tailored to the user's spending habits based on the latest discount and special offers from partner companies.

[0319] The hardware required to run the program includes camera sensors and OCR sensors built into home appliances, as well as terminals capable of network communication. The software includes OCR libraries (e.g., Tesseract) and cloud services for data analysis (e.g., AWS Lambda).

[0320] As a concrete example, a user could have a home device scan receipts from restaurants they frequent for dinner, and if the device determines that their spending is excessive, it could provide advice such as "You should reduce the number of times you eat out this month," along with information on coupons that can be used at that restaurant.

[0321] An example of a prompt message for the generated AI model could be: "This home robot is an application that scans paper receipts collected by the user, analyzes them in the cloud, and provides advice on saving money." This allows the entire system to work together and contribute to improving the user's life.

[0322] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0323] Step 1:

[0324] Based on user instructions, the terminal uses the camera of a home appliance to scan paper receipts and invoices. In this step, paper financial data is provided as input, and digital image data is generated as output. Through the image capture operation, the information on paper is visually recorded.

[0325] Step 2:

[0326] The terminal scans digital image data, which is then input to an OCR sensor for character recognition. This converts the image data into analyzable digital text data. The input is a scanned image, and the output is text data; this conversion is performed using OCR technology.

[0327] Step 3:

[0328] The terminal sends the generated digital text to the server. The server stores the received text data in a cloud environment. This ensures that the data is securely stored and used as a basis for subsequent processing.

[0329] Step 4:

[0330] The server analyzes stored text data and classifies it into categories using natural language processing techniques and machine learning algorithms. The input is the stored text data, and the output is the classification results for each category. The analysis process involves pattern recognition using algorithms.

[0331] Step 5:

[0332] The server analyzes users' financial behavior based on categorized data and identifies opportunities for saving. The input is the classification results, and the output is data for saving advice. The analysis process involves comparing spending patterns and generating personalized advice.

[0333] Step 6:

[0334] The server generates money-saving advice and sends it to the terminal, which then notifies the user. The input is the advice data, and the output is the notification information for the user. In this step, specific money-saving suggestions are presented to the user through the mobile terminal's display or audio output device.

[0335] Step 7:

[0336] When a user acts on savings advice, the device reports the results to the server. The input is user behavior data, and the output is updated financial data. This behavior tracking provides continuous feedback, improving the accuracy of the advice.

[0337] Step 8:

[0338] The system integrates behavioral data collected by the server with information from partner companies to provide users with customized discount information. Inputs are user behavioral data and promotional information from companies, and output is customized coupon information. This promotion generation allows users to shop flexibly and save money.

[0339] 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.

[0340] This invention combines a system that manages users' financial data and provides savings support with an emotion engine that recognizes users' emotions, thereby providing more effective savings advice. This system functions when users access the application using a smartphone or computer to manage their finances.

[0341] Users upload images of their credit card statements and receipts to the app. The device uses OCR technology to extract text information from the images and organizes it as financial data. This financial data is sent to a server and stored in a database. The server categorizes the stored data and analyzes the user's spending patterns. Based on the analysis, it generates specific advice highlighting savings opportunities and notifies the user through their device.

[0342] In addition, the system integrates an emotion engine that analyzes the user's emotions. Users input their emotional state into the app or it is detected by biosensors connected to their device. This emotional data is sent to a server and analyzed along with financial data. The emotion engine learns what emotional states a user tends to be in when they increase their spending and identifies emotional patterns that influence spending behavior.

[0343] For example, if it becomes clear that a user's spending on entertainment increases when they are stressed, the server will provide constructive advice to reduce entertainment spending when it detects their stress level. Furthermore, if emotional data predicts that a user is at high risk of unconsciously overspending, the device will send a preventative notification to the user to help them control their spending.

[0344] This combination of emotional engines enables more personalized and specific saving advice for users, significantly improving the efficiency and effectiveness of household budget management.

[0345] The following describes the processing flow.

[0346] Step 1:

[0347] Users access the application using their smartphones or computers and upload images of credit card statements or receipts. The device receives these images, extracts text information using OCR technology, and organizes the read data.

[0348] Step 2:

[0349] The terminal sends the extracted financial data to the server. The server stores the received data in a database and organizes it by category for smooth analysis.

[0350] Step 3:

[0351] The server applies machine learning algorithms to analyze the stored data, classifying spending into categories such as food, transportation, housing, and entertainment, and identifying spending trends. From these analysis results, it identifies particularly noteworthy spending trends and areas where savings can be made.

[0352] Step 4:

[0353] Users input their daily emotional states into the application or obtain real-time emotional data using biosensors connected to their device. This emotional data is then transmitted to a server via the device.

[0354] Step 5:

[0355] The server integrates and analyzes financial and emotional data. It learns which spending categories are affected by specific emotional states and adjusts advice based on those results. For example, if spending on entertainment tends to increase when stress levels are high, the server will generate personalized saving advice when it detects that emotional state.

[0356] Step 6:

[0357] Based on the analyzed information, the server generates money-saving advice for the user and presents a concrete action plan. This advice is notified to the user via their device, and reminders and warnings may be issued as needed.

[0358] Step 7:

[0359] The user takes saving actions based on the advice they receive. The device records these actions and sends the action data back to the server. The server takes this data, provides feedback, and improves or updates the advice further.

[0360] Step 8:

[0361] The server optimizes discount coupons and information provided by partner companies based on the user's spending patterns and sentiment data, and delivers them to the user via their device. This allows the user to enjoy substantial savings.

[0362] (Example 2)

[0363] 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".

[0364] Modern consumers demand efficient and accurate advice in financial management, but traditional systems have lacked the ability to provide saving advice that adequately considers the impact of users' emotional states on their spending behavior. Furthermore, there was a challenge in identifying emotion-based spending patterns, making personalized advice difficult.

[0365] 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.

[0366] In this invention, the server includes means for extracting text data from the user, means for automatically classifying the stored information by category, and means for generating savings advice based on the analysis results using a generative AI model. This makes it possible to provide more personalized and specific savings advice that takes into account the user's emotional state.

[0367] "Means for extracting text data from users" refers to the process of extracting text information from image data provided by users using optical character recognition technology.

[0368] "Means of formatting and storing financial information" refers to the process of converting extracted text data into a specified format and saving it to a database.

[0369] "Methods for automatically classifying information into categories" refers to the process of automatically categorizing stored information using specific rules or algorithms.

[0370] "A method for generating savings advice based on analysis results using a generative AI model" refers to a process that utilizes artificial intelligence technology to analyze user data and propose the optimal savings method.

[0371] "Means for acquiring users' emotional states and integrating and analyzing them with stored information" refers to the process of analyzing emotional data collected from users in conjunction with existing financial data to gain insights into their spending behavior.

[0372] "Methods for identifying spending patterns based on emotional states" refers to the process of analyzing users' emotional data and using the results to clarify their spending tendencies.

[0373] The "ability to generate personalized savings advice" is the ability to present specific and personalized savings methods based on the user's particular circumstances and information.

[0374] This invention relates to a system that integrates and manages a user's financial data and emotional state to provide individually optimized savings advice. Users access the application using a smartphone or computer to manage their daily finances. This system is implemented in the following way:

[0375] Users upload photos of receipts or credit card statements to the application using their device. The device uses OCR technology to extract text information from the uploaded images. Specific OCR technologies that can be used include Tesseract OCR and Google Cloud Vision API. This extracted text information is formatted as financial data on the device and prepared for transmission to the server.

[0376] The server receives financial data sent from the terminal and stores it in a database. Common RDBMSs such as MySQL and PostgreSQL can be used as the database management system. The stored data is categorized and analyzed using machine learning algorithms and data mining techniques.

[0377] Furthermore, the user's emotional state is collected through self-input within the application and via biosensors. These biosensors include heart rate monitors and skin electrical activity sensors. The collected emotional data is sent to a server and analyzed in conjunction with financial data. The emotion engine learns the correlation between the user's emotional state and spending behavior.

[0378] For example, if a pattern is identified where a user's spending on fashion increases when they are in a good mood on holidays, the server can send a prompt to the AI ​​model, which can then output specific advice such as, "Please give me advice on how to reduce unnecessary spending on fashion on my next holiday."

[0379] In this way, the server generates personalized saving advice that takes into account the user's emotional state. This system allows users to easily understand their spending patterns and efficiently take actions to reduce unnecessary spending.

[0380] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0381] Step 1:

[0382] Users launch the application using their smartphone or computer and upload images of credit card statements or receipts. The input here is image data. The device uses OCR technology to extract text information from this image data. Specifically, a program called Tesseract OCR is used to convert the text within the image into digital information. The output is text data.

[0383] Step 2:

[0384] The terminal formats the extracted text information into financial data. During this process, the text data is structured according to a specific format. This formatted data is provided in JSON or XML format. Once the data is formatted, it is ready for smooth transmission to the server. The output is the formatted financial data.

[0385] Step 3:

[0386] The terminal sends formatted financial data to the server. Upon receiving this data, the server stores it in a database. The input is the formatted financial data from the terminal, and the output is stored in the database. Generally, database management systems such as MySQL or PostgreSQL are used for this purpose.

[0387] Step 4:

[0388] The server automatically categorizes the stored financial data. This categorization utilizes pre-configured rules and algorithms. The input is financial data from the database, and the output is categorized data. This clearly reveals the user's spending patterns.

[0389] Step 5:

[0390] Users either input their emotional state within the application or collect emotional data using biosensors connected to their device (such as heart rate monitors or skin electrical activity sensors). The input is emotional information from the biosensors, and the output is the collected emotional data. This data is also sent to the server.

[0391] Step 6:

[0392] The server integrates and analyzes emotional and financial data. The emotion engine learns from historical data to identify correlations between emotional states and spending behavior. The inputs are emotional and financial data, and the output is spending patterns associated with emotional states.

[0393] Step 7:

[0394] The server uses a generative AI model to generate savings advice based on the analysis results. Here, prompts are used to gain insights into specific spending patterns. The input is the analyzed data, and the output is specific savings advice for the user.

[0395] Step 8:

[0396] The server sends the generated advice to the terminal, which then notifies the user. The input is the generated savings advice, and the output appears as a real-time notification to the user. This notification allows the user to adjust their actions immediately.

[0397] (Application Example 2)

[0398] 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."

[0399] In today's economic society, individuals engage in numerous economic activities daily, but the associated wastefulness and impulsive spending can negatively impact personal finances. Emotions, in particular, have a significant influence on economic activity, and because self-control is difficult, it is crucial to curb wasteful spending. Furthermore, conventional economic management systems lack the ability to provide personalized suggestions to users, and are especially inadequate in supporting appropriate spending management based on emotional states.

[0400] 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.

[0401] In this invention, the server includes means for collecting economic data from the user, means for analyzing emotional data, and means for generating specific advice to prevent wasteful spending. This enables personalized spending reduction suggestions based on the user's emotional state and economic behavior.

[0402] A "user" refers to an individual or customer who provides economic data and receives assistance with spending management through their emotional state.

[0403] "Economic data" is a general term for information related to an individual's finances, including information on income, expenses, purchase details, and budgets.

[0404] "Emotional data" refers to information that indicates an individual's mental state, and is acquired by the user through physical input or biosensors.

[0405] "Wasteful spending" refers to unplanned or impulsive expenditures that may threaten a user's financial health.

[0406] "Advice" refers to suggestions about economic actions a user should take, and is personalized based on the user's emotional state and economic data.

[0407] A "server" refers to a computer system that receives and processes economic and emotional data and provides users with relevant information.

[0408] "Means" is a concept that includes methods or apparatus provided to achieve a particular function in this invention.

[0409] The system of this invention is designed to enable users to manage their finances and link their personal consumption behavior to their emotional state. The server collects, integrates, and analyzes the user's economic and emotional data, enabling it to provide personalized financial advice.

[0410] First, the device collects economic data from the user using a smartphone or computer. This data includes purchase history and records of financial status. Next, the device sends emotional data collected from the user's biosensors to a server. This data is obtained using facial recognition sensors and heart rate monitors.

[0411] On the server, this data is stored in a database. MySQL is used as the database management system for processing, and Python and the machine learning library TensorFlow are utilized for data analysis. Tesseract is used for OCR to extract necessary text data from statements and receipts.

[0412] Next, the server analyzes the user's economic data to identify patterns in their consumption behavior. Then, the emotion engine analyzes the emotional data and evaluates the impact of that state on their economic activity. Economic advice and warnings generated based on this information are notified to the user in real time using the Twilio API.

[0413] As a concrete example, if a user is experiencing stress while attempting to purchase an expensive item on an e-commerce platform, the server will indicate that the expenditure is unplanned and send a notification suggesting alternatives. This allows users to make rational purchasing decisions rather than reacting emotionally.

[0414] To support this process using a generative AI model, a prompt such as, "Generate effective advice to help users avoid unplanned spending when they are feeling stressed," could be used. This would allow the AI ​​to suggest optimal advice in real time, tailored to the user's situation.

[0415] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0416] Step 1:

[0417] The device retrieves economic data uploaded by the user (such as credit card statements and receipt images). Using this data as input, it extracts text information from the images using OCR technology and organizes it as economic data. The extracted data is stored in temporary data storage.

[0418] Step 2:

[0419] Economic data extracted from the terminal is sent to the server. The server stores this economic data in a database and classifies it by category using a database management system. SQL queries are used to process the data, dividing it into categories such as income and expenses.

[0420] Step 3:

[0421] The user inputs emotional data into the device using biosensors. This emotional data includes heart rate and facial expression information. The device then transmits this emotional data to a server.

[0422] Step 4:

[0423] The server receives emotional data, analyzes it using machine learning libraries (such as TensorFlow), and identifies the user's emotional state. The results of the emotional state identification are stored in a database and linked to the user's economic data.

[0424] Step 5:

[0425] The server integrates user economic and emotional data to analyze user consumption patterns. Python scripts are used for statistical analysis and trend identification. The output is a report on user consumption trends and emotions.

[0426] Step 6:

[0427] The server uses a generative AI model to generate personalized financial advice based on the prompt "Generate effective advice to prevent unplanned spending when the user is feeling stressed." This generated advice is optimized based on the user's past spending habits and emotional patterns.

[0428] Step 7:

[0429] The server uses the Twilio API to notify users of generated financial advice on their devices. These notifications include spending warnings and sentiment-based suggestions for reducing spending, and are provided to users in real time.

[0430] 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.

[0431] 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.

[0432] 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.

[0433] [Third Embodiment]

[0434] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0435] 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.

[0436] 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).

[0437] 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.

[0438] 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.

[0439] 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).

[0440] 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.

[0441] 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.

[0442] 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.

[0443] 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.

[0444] 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.

[0445] 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".

[0446] This invention is a system that automatically collects, classifies, and analyzes financial data to provide savings advice in order to support users' financial management. Its embodiments will be described in detail below.

[0447] Users access the application using devices such as smartphones or computers and upload images of credit card statements or receipts. The device then uses OCR technology to convert the image data into text data and sends it to the server as financial data. The server stores the received financial data in a database.

[0448] Next, the server analyzes the data and uses natural language processing and machine learning algorithms to categorize the collected data into categories such as food, transportation, housing, and entertainment. Based on this classification, the server analyzes spending patterns and identifies which spending in each category is excessive or can be reduced. Based on these analysis results, the server generates specific advice that shows the user opportunities to save money. For example, if a user's monthly food and beverage expenses are high, the server might suggest "limiting eating out to once a week."

[0449] Subsequently, the device notifies the user of advice generated by the server and provides a reminder function to prompt action as needed. Each time the user takes action, the device sends the spending status to the server, which updates the information in real time to generate even more appropriate feedback.

[0450] Furthermore, the server can utilize discount coupons and special offers obtained from various partner companies to provide users with the most suitable deals based on their preferences and purchasing behavior. This feature allows users to make more efficient purchases and helps them manage their household finances.

[0451] In this way, the entire system works together to promote improvements in users' lives and enhance the efficiency of household budget management.

[0452] The following describes the processing flow.

[0453] Step 1:

[0454] Users upload images of credit card statements and receipts via an application using their smartphones or computers. The device then uses OCR technology to extract text information from these images and formats it as financial data.

[0455] Step 2:

[0456] The terminal sends the extracted financial data to the server. The server stores the received data in a database. The data is categorized into information such as date, expenditure amount, and expenditure details.

[0457] Step 3:

[0458] The server analyzes financial data stored in the database and automatically classifies it into categories such as food and beverage, transportation, housing, and entertainment using machine learning algorithms.

[0459] Step 4:

[0460] The server analyzes user spending patterns based on categorized data. By comparing this with past data, it identifies categories of unusual spending or areas where savings can be made.

[0461] Step 5:

[0462] The server identifies opportunities for saving money and generates specific saving advice based on the user's spending habits. This advice includes action plans and specific saving targets to reduce spending.

[0463] Step 6:

[0464] The terminal notifies the user of advice obtained from the server. The notification includes savings suggestions and specific actions to be taken, which the user can review and implement.

[0465] Step 7:

[0466] When a user takes action based on the advice, the device records that action and sends it to the server. The server uses this information to analyze the progress of spending and the achievement of savings goals.

[0467] Step 8:

[0468] Based on the analysis results, the server generates feedback, providing information on achieved savings and further suggestions. It also references coupons and discount information from partner companies and sends advantageous information tailored to the user's spending habits to their device.

[0469] (Example 1)

[0470] 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."

[0471] In modern society, users are required to efficiently manage a wide range of spending information. However, doing so manually is incredibly time-consuming and can make accurate data analysis difficult. Furthermore, providing specific, personalized saving advice to users is challenging, and there is a lack of efficient support based on consumption trends.

[0472] 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.

[0473] In this invention, the server includes means for collecting economic data from users in multiple formats, means for converting the collected data into text using image processing technology, and means for automatically classifying the converted data into hierarchical categories. This makes it possible to efficiently analyze the user's economic data and provide accurate advice and optimal discount information in real time.

[0474] A "user" is an individual or organization that uses this system to manage their own economic data.

[0475] "Economic data" refers to information about a user's daily spending and income, including credit card statements and receipts.

[0476] "Image processing technology" refers to techniques for extracting text data from image data, and includes OCR (Optical Character Recognition).

[0477] "Converting to text" refers to the process of converting image data into text information.

[0478] "Hierarchical categorization" refers to a method of classifying data into several main categories and subdivided subcategories below them.

[0479] "Automatic classification" refers to the process of using machine learning or algorithms to sort data into appropriate categories based on pre-defined rules.

[0480] "Guidelines" refers to specific advice and suggestions for users to make their economic activities more efficient.

[0481] "Discount information" refers to preferential pricing and promotional information provided by affiliated third parties.

[0482] "Real-time delivery" means that whenever user behavior or data is updated, information and feedback corresponding to that change are immediately presented.

[0483] This invention is a system that efficiently handles economic data and provides savings advice through analysis to support users' financial management. Users access a dedicated application using devices such as smartphones or computers. Users collect data by uploading images of credit card statements and receipts to the application.

[0484] The device converts the received image data into text data using image processing technology, specifically OCR technology. Common OCR tools include Tesseract, and cloud-based solutions are available as commercial services. At this stage, the device sends the converted text data to the server.

[0485] The server records the received text-based economic data in a database management system. Suitable database systems include scalable open-source systems such as MySQL and PostgreSQL. The recorded data is then categorized hierarchically using natural language processing and machine learning algorithms, such as food, transportation, housing, entertainment, and others.

[0486] Following data classification, the server analyzes spending patterns in detail and detects unique trends. Based on the analysis results, it uses an AI model to formulate guidelines for optimizing the user's spending. For example, if spending is increasing in a particular category, it generates advice on reducing spending in that category. A specific example of such advice might be, "Since food expenses are high, refrain from eating out once a week."

[0487] The generated guidelines are sent from the server to the terminal, which then notifies the user. Each time the user takes action according to the guidelines, the result is fed back from the terminal to the server, and the server updates the data in real time, enabling further analysis and more efficient advice.

[0488] Furthermore, the server provides users with discount information and coupons obtained from partner third parties. This information is selected based on the user's preferences and purchasing behavior, with the aim of positively influencing the user's purchasing decisions.

[0489] An example of a prompt message might be, "Analyze the user's economic data to identify spending trends and suggest ways to reduce costs." This invention is a comprehensive system for monitoring the user's daily economic activities and supporting efficient financial management.

[0490] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0491] Step 1:

[0492] Users access the application using devices such as smartphones or computers and upload image data of credit card statements or receipts. The input is image data, and the output is prepared to be converted into text data. The device receives the image and forms the foundation for processing this data in the next step.

[0493] Step 2:

[0494] The terminal applies OCR technology to the received image data, converting the character data within the image into text format. The input is image data, and the output is text data. In this step, OCR software is used to perform character recognition and extract the necessary financial information.

[0495] Step 3:

[0496] The terminal sends the text data extracted by OCR to the server. The input is text data, and the output is data transfer to the server. This makes the financial data available for analysis on the server side.

[0497] Step 4:

[0498] The server records the received text-formatted economic data in a database. The input is text data, and the output is structured data stored in the database. In this step, data persistence takes place and is used in subsequent analysis steps.

[0499] Step 5:

[0500] The server automatically categorizes data using natural language processing and machine learning algorithms. The input is structured data stored in a database, and the output is categorized data. Specifically, expenditures are classified into categories such as food, transportation, housing, and entertainment.

[0501] Step 6:

[0502] The server analyzes the classified data and examines spending patterns in detail. This identifies abnormal spending trends and areas for improvement. The input is classified data, and the output is a report containing the analysis results.

[0503] Step 7:

[0504] The server generates specific savings advice for the user based on the analysis results. The input is the analysis results, and the output is text data providing guidance. Using a generation AI model, it follows the instruction, as an example of a prompt, "Analyze the user's economic data, identify spending trends, and suggest ways to reduce costs."

[0505] Step 8:

[0506] The server sends the generated advice and acquired discount information to the terminal. The input is the advice text and discount information, and the output is a notification signal to the user. This allows the user to receive useful information that is updated regularly.

[0507] Step 9:

[0508] The device notifies the user of the advice it receives and, if necessary, sets a reminder. The input is a notification signal from the server, and the output is information displayed on the user interface. This allows the user to take action according to the advice.

[0509] (Application Example 1)

[0510] 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."

[0511] Modern users receive numerous paper receipts and invoices by mail in their daily lives, making it difficult to efficiently organize this financial data and obtain advice on saving money. Furthermore, the lack of means to digitize and automatically analyze this paper information has made it difficult to grasp more effective saving methods and manage household finances effectively.

[0512] 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.

[0513] In this invention, the server includes means for collecting financial data from users, means for automatically classifying the collected data into categories, means for analyzing the classified data and identifying opportunities for savings, means for a household appliance to read paper financial data and digitize it, and means for transmitting the digitized data to a remote information processing device. This makes it possible to automatically organize all financial data, including paper information, and provide savings advice tailored to the user.

[0514] "Means of collecting financial data from users" refers to technologies that automatically acquire information from financial information owned by users or from paper documents.

[0515] "Methods for automatically classifying data by category" refers to functions that sort collected data into categories such as food, transportation, and housing.

[0516] "Methods for identifying savings opportunities" refer to techniques that use analyzed data to identify unnecessary spending and items that can be reduced.

[0517] "A means of providing users with money-saving advice" refers to a function that notifies users of specific money-saving methods based on the analyzed information.

[0518] "A means of tracking users' saving behavior and providing feedback" refers to technology that tracks users' actions and spending and suggests areas for improvement based on that data.

[0519] "Means of providing users with advantageous information and discount information" refers to technology that delivers promotional information from partner companies to users according to their interests and behavior.

[0520] "A means by which household devices read and digitize paper financial data" refers to technology that reads information printed on paper using a machine and converts it into digital information.

[0521] "Means for transmitting digitized data to a remote information processing device" refers to the technology of transferring locally stored digital data to another device via a network.

[0522] This invention is a financial management support system using consumer electronics, aiming to manage users' lives more efficiently. The server automatically collects and analyzes financial data through the user's terminal and home appliances. Cameras and OCR sensors mounted on the terminal read paper-based receipts and invoices received by the user, digitize them, and transmit the data to a cloud server.

[0523] The cloud server uses natural language processing and machine learning algorithms to categorize this data into categories such as food, transportation, and housing. Furthermore, based on the categorized data, the server analyzes the user's spending patterns and identifies opportunities for saving. Saving advice generated based on the analysis is then communicated visually or audibly through home appliances or the user's device.

[0524] Specifically, the server can issue advice such as "limit eating out to once a week." This allows users to review their spending habits and implement effective saving methods. The server also provides coupons tailored to the user's spending habits based on the latest discount and special offers from partner companies.

[0525] The hardware required to run the program includes camera sensors and OCR sensors built into home appliances, as well as terminals capable of network communication. The software includes OCR libraries (e.g., Tesseract) and cloud services for data analysis (e.g., AWS Lambda).

[0526] As a concrete example, a user could have a home device scan receipts from restaurants they frequent for dinner, and if the device determines that their spending is excessive, it could provide advice such as "You should reduce the number of times you eat out this month," along with information on coupons that can be used at that restaurant.

[0527] An example of a prompt message for the generated AI model could be: "This home robot is an application that scans paper receipts collected by the user, analyzes them in the cloud, and provides advice on saving money." This allows the entire system to work together and contribute to improving the user's life.

[0528] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0529] Step 1:

[0530] Based on user instructions, the terminal uses the camera of a home appliance to scan paper receipts and invoices. In this step, paper financial data is provided as input, and digital image data is generated as output. Through the image capture operation, the information on paper is visually recorded.

[0531] Step 2:

[0532] The terminal scans digital image data, which is then input to an OCR sensor for character recognition. This converts the image data into analyzable digital text data. The input is a scanned image, and the output is text data; this conversion is performed using OCR technology.

[0533] Step 3:

[0534] The terminal sends the generated digital text to the server. The server stores the received text data in a cloud environment. This ensures that the data is securely stored and used as a basis for subsequent processing.

[0535] Step 4:

[0536] The server analyzes stored text data and classifies it into categories using natural language processing techniques and machine learning algorithms. The input is the stored text data, and the output is the classification results for each category. The analysis process involves pattern recognition using algorithms.

[0537] Step 5:

[0538] The server analyzes users' financial behavior based on categorized data and identifies opportunities for saving. The input is the classification results, and the output is data for saving advice. The analysis process involves comparing spending patterns and generating personalized advice.

[0539] Step 6:

[0540] The server generates money-saving advice and sends it to the terminal, which then notifies the user. The input is the advice data, and the output is the notification information for the user. In this step, specific money-saving suggestions are presented to the user through the mobile terminal's display or audio output device.

[0541] Step 7:

[0542] When a user acts on savings advice, the device reports the results to the server. The input is user behavior data, and the output is updated financial data. This behavior tracking provides continuous feedback, improving the accuracy of the advice.

[0543] Step 8:

[0544] The system integrates behavioral data collected by the server with information from partner companies to provide users with customized discount information. Inputs are user behavioral data and promotional information from companies, and output is customized coupon information. This promotion generation allows users to shop flexibly and save money.

[0545] 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.

[0546] This invention combines a system that manages users' financial data and provides savings support with an emotion engine that recognizes users' emotions, thereby providing more effective savings advice. This system functions when users access the application using a smartphone or computer to manage their finances.

[0547] Users upload images of their credit card statements and receipts to the app. The device uses OCR technology to extract text information from the images and organizes it as financial data. This financial data is sent to a server and stored in a database. The server categorizes the stored data and analyzes the user's spending patterns. Based on the analysis, it generates specific advice highlighting savings opportunities and notifies the user through their device.

[0548] In addition, the system integrates an emotion engine that analyzes the user's emotions. Users input their emotional state into the app or it is detected by biosensors connected to their device. This emotional data is sent to a server and analyzed along with financial data. The emotion engine learns what emotional states a user tends to be in when they increase their spending and identifies emotional patterns that influence spending behavior.

[0549] For example, if it becomes clear that a user's spending on entertainment increases when they are stressed, the server will provide constructive advice to reduce entertainment spending when it detects their stress level. Furthermore, if emotional data predicts that a user is at high risk of unconsciously overspending, the device will send a preventative notification to the user to help them control their spending.

[0550] This combination of emotional engines enables more personalized and specific saving advice for users, significantly improving the efficiency and effectiveness of household budget management.

[0551] The following describes the processing flow.

[0552] Step 1:

[0553] Users access the application using their smartphones or computers and upload images of credit card statements or receipts. The device receives these images, extracts text information using OCR technology, and organizes the read data.

[0554] Step 2:

[0555] The terminal sends the extracted financial data to the server. The server stores the received data in a database and organizes it by category for smooth analysis.

[0556] Step 3:

[0557] The server applies machine learning algorithms to analyze the stored data, classifying spending into categories such as food, transportation, housing, and entertainment, and identifying spending trends. From these analysis results, it identifies particularly noteworthy spending trends and areas where savings can be made.

[0558] Step 4:

[0559] Users input their daily emotional states into the application or obtain real-time emotional data using biosensors connected to their device. This emotional data is then transmitted to a server via the device.

[0560] Step 5:

[0561] The server integrates and analyzes financial and emotional data. It learns which spending categories are affected by specific emotional states and adjusts advice based on those results. For example, if spending on entertainment tends to increase when stress levels are high, the server will generate personalized saving advice when it detects that emotional state.

[0562] Step 6:

[0563] Based on the analyzed information, the server generates money-saving advice for the user and presents a concrete action plan. This advice is notified to the user via their device, and reminders and warnings may be issued as needed.

[0564] Step 7:

[0565] The user takes saving actions based on the advice they receive. The device records these actions and sends the action data back to the server. The server takes this data, provides feedback, and improves or updates the advice further.

[0566] Step 8:

[0567] The server optimizes discount coupons and information provided by partner companies based on the user's spending patterns and sentiment data, and delivers them to the user via their device. This allows the user to enjoy substantial savings.

[0568] (Example 2)

[0569] 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."

[0570] Modern consumers demand efficient and accurate advice in financial management, but traditional systems have lacked the ability to provide saving advice that adequately considers the impact of users' emotional states on their spending behavior. Furthermore, there was a challenge in identifying emotion-based spending patterns, making personalized advice difficult.

[0571] 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.

[0572] In this invention, the server includes means for extracting text data from the user, means for automatically classifying the stored information by category, and means for generating savings advice based on the analysis results using a generative AI model. This makes it possible to provide more personalized and specific savings advice that takes into account the user's emotional state.

[0573] "Means for extracting text data from users" refers to the process of extracting text information from image data provided by users using optical character recognition technology.

[0574] "Means of formatting and storing financial information" refers to the process of converting extracted text data into a specified format and saving it to a database.

[0575] "Methods for automatically classifying information into categories" refers to the process of automatically categorizing stored information using specific rules or algorithms.

[0576] "A method for generating savings advice based on analysis results using a generative AI model" refers to a process that utilizes artificial intelligence technology to analyze user data and propose the optimal savings method.

[0577] "Means for acquiring users' emotional states and integrating and analyzing them with stored information" refers to the process of analyzing emotional data collected from users in conjunction with existing financial data to gain insights into their spending behavior.

[0578] "Methods for identifying spending patterns based on emotional states" refers to the process of analyzing users' emotional data and using the results to clarify their spending tendencies.

[0579] The "ability to generate personalized savings advice" is the ability to present specific and personalized savings methods based on the user's particular circumstances and information.

[0580] This invention relates to a system that integrates and manages a user's financial data and emotional state to provide individually optimized savings advice. Users access the application using a smartphone or computer to manage their daily finances. This system is implemented in the following way:

[0581] Users upload photos of receipts or credit card statements to the application using their device. The device uses OCR technology to extract text information from the uploaded images. Specific OCR technologies that can be used include Tesseract OCR and Google Cloud Vision API. This extracted text information is formatted as financial data on the device and prepared for transmission to the server.

[0582] The server receives financial data sent from the terminal and stores it in a database. Common RDBMSs such as MySQL and PostgreSQL can be used as the database management system. The stored data is categorized and analyzed using machine learning algorithms and data mining techniques.

[0583] Furthermore, the user's emotional state is collected through self-input within the application and via biosensors. These biosensors include heart rate monitors and skin electrical activity sensors. The collected emotional data is sent to a server and analyzed in conjunction with financial data. The emotion engine learns the correlation between the user's emotional state and spending behavior.

[0584] For example, if a pattern is identified where a user's spending on fashion increases when they are in a good mood on holidays, the server can send a prompt to the AI ​​model, which can then output specific advice such as, "Please give me advice on how to reduce unnecessary spending on fashion on my next holiday."

[0585] In this way, the server generates personalized saving advice that takes into account the user's emotional state. This system allows users to easily understand their spending patterns and efficiently take actions to reduce unnecessary spending.

[0586] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0587] Step 1:

[0588] Users launch the application using their smartphone or computer and upload images of credit card statements or receipts. The input here is image data. The device uses OCR technology to extract text information from this image data. Specifically, a program called Tesseract OCR is used to convert the text within the image into digital information. The output is text data.

[0589] Step 2:

[0590] The terminal formats the extracted text information into financial data. During this process, the text data is structured according to a specific format. This formatted data is provided in JSON or XML format. Once the data is formatted, it is ready for smooth transmission to the server. The output is the formatted financial data.

[0591] Step 3:

[0592] The terminal sends formatted financial data to the server. Upon receiving this data, the server stores it in a database. The input is the formatted financial data from the terminal, and the output is stored in the database. Generally, database management systems such as MySQL or PostgreSQL are used for this purpose.

[0593] Step 4:

[0594] The server automatically categorizes the stored financial data. This categorization utilizes pre-configured rules and algorithms. The input is financial data from the database, and the output is categorized data. This clearly reveals the user's spending patterns.

[0595] Step 5:

[0596] Users either input their emotional state within the application or collect emotional data using biosensors connected to their device (such as heart rate monitors or skin electrical activity sensors). The input is emotional information from the biosensors, and the output is the collected emotional data. This data is also sent to the server.

[0597] Step 6:

[0598] The server integrates and analyzes emotional and financial data. The emotion engine learns from historical data to identify correlations between emotional states and spending behavior. The inputs are emotional and financial data, and the output is spending patterns associated with emotional states.

[0599] Step 7:

[0600] The server uses a generative AI model to generate savings advice based on the analysis results. Here, prompts are used to gain insights into specific spending patterns. The input is the analyzed data, and the output is specific savings advice for the user.

[0601] Step 8:

[0602] The server sends the generated advice to the terminal, which then notifies the user. The input is the generated savings advice, and the output appears as a real-time notification to the user. This notification allows the user to adjust their actions immediately.

[0603] (Application Example 2)

[0604] 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."

[0605] In today's economic society, individuals engage in numerous economic activities daily, but the associated wastefulness and impulsive spending can negatively impact personal finances. Emotions, in particular, have a significant influence on economic activity, and because self-control is difficult, it is crucial to curb wasteful spending. Furthermore, conventional economic management systems lack the ability to provide personalized suggestions to users, and are especially inadequate in supporting appropriate spending management based on emotional states.

[0606] 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.

[0607] In this invention, the server includes means for collecting economic data from the user, means for analyzing emotional data, and means for generating specific advice to prevent wasteful spending. This enables personalized spending reduction suggestions based on the user's emotional state and economic behavior.

[0608] A "user" refers to an individual or customer who provides economic data and receives assistance with spending management through their emotional state.

[0609] "Economic data" is a general term for information related to an individual's finances, including information on income, expenses, purchase details, and budgets.

[0610] "Emotional data" refers to information that indicates an individual's mental state, and is acquired by the user through physical input or biosensors.

[0611] "Wasteful spending" refers to unplanned or impulsive expenditures that may threaten a user's financial health.

[0612] "Advice" refers to suggestions about economic actions a user should take, and is personalized based on the user's emotional state and economic data.

[0613] A "server" refers to a computer system that receives and processes economic and emotional data and provides users with relevant information.

[0614] "Means" is a concept that includes methods or apparatus provided to achieve a particular function in this invention.

[0615] The system of this invention is designed to enable users to manage their finances and link their personal consumption behavior to their emotional state. The server collects, integrates, and analyzes the user's economic and emotional data, enabling it to provide personalized financial advice.

[0616] First, the device collects economic data from the user using a smartphone or computer. This data includes purchase history and records of financial status. Next, the device sends emotional data collected from the user's biosensors to a server. This data is obtained using facial recognition sensors and heart rate monitors.

[0617] On the server, this data is stored in a database. MySQL is used as the database management system for processing, and Python and the machine learning library TensorFlow are utilized for data analysis. Tesseract is used for OCR to extract necessary text data from statements and receipts.

[0618] Next, the server analyzes the user's economic data to identify patterns in their consumption behavior. Then, the emotion engine analyzes the emotional data and evaluates the impact of that state on their economic activity. Economic advice and warnings generated based on this information are notified to the user in real time using the Twilio API.

[0619] As a concrete example, if a user is experiencing stress while attempting to purchase an expensive item on an e-commerce platform, the server will indicate that the expenditure is unplanned and send a notification suggesting alternatives. This allows users to make rational purchasing decisions rather than reacting emotionally.

[0620] To support this process using a generative AI model, a prompt such as, "Generate effective advice to help users avoid unplanned spending when they are feeling stressed," could be used. This would allow the AI ​​to suggest optimal advice in real time, tailored to the user's situation.

[0621] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0622] Step 1:

[0623] The device retrieves economic data uploaded by the user (such as credit card statements and receipt images). Using this data as input, it extracts text information from the images using OCR technology and organizes it as economic data. The extracted data is stored in temporary data storage.

[0624] Step 2:

[0625] Economic data extracted from the terminal is sent to the server. The server stores this economic data in a database and classifies it by category using a database management system. SQL queries are used to process the data, dividing it into categories such as income and expenses.

[0626] Step 3:

[0627] The user inputs emotional data into the device using biosensors. This emotional data includes heart rate and facial expression information. The device then transmits this emotional data to a server.

[0628] Step 4:

[0629] The server receives emotional data, analyzes it using machine learning libraries (such as TensorFlow), and identifies the user's emotional state. The results of the emotional state identification are stored in a database and linked to the user's economic data.

[0630] Step 5:

[0631] The server integrates user economic and emotional data to analyze user consumption patterns. Python scripts are used for statistical analysis and trend identification. The output is a report on user consumption trends and emotions.

[0632] Step 6:

[0633] The server uses a generative AI model to generate personalized financial advice based on the prompt "Generate effective advice to prevent unplanned spending when the user is feeling stressed." This generated advice is optimized based on the user's past spending habits and emotional patterns.

[0634] Step 7:

[0635] The server uses the Twilio API to notify users of generated financial advice on their devices. These notifications include spending warnings and sentiment-based suggestions for reducing spending, and are provided to users in real time.

[0636] 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.

[0637] 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.

[0638] 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.

[0639] [Fourth Embodiment]

[0640] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0641] 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.

[0642] 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).

[0643] 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.

[0644] 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.

[0645] 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).

[0646] 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.

[0647] 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.

[0648] 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.

[0649] 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.

[0650] 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.

[0651] 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.

[0652] 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".

[0653] This invention is a system that automatically collects, classifies, and analyzes financial data to provide savings advice in order to support users' financial management. Its embodiments will be described in detail below.

[0654] Users access the application using devices such as smartphones or computers and upload images of credit card statements or receipts. The device then uses OCR technology to convert the image data into text data and sends it to the server as financial data. The server stores the received financial data in a database.

[0655] Next, the server analyzes the data and uses natural language processing and machine learning algorithms to categorize the collected data into categories such as food, transportation, housing, and entertainment. Based on this classification, the server analyzes spending patterns and identifies which spending in each category is excessive or can be reduced. Based on these analysis results, the server generates specific advice that shows the user opportunities to save money. For example, if a user's monthly food and beverage expenses are high, the server might suggest "limiting eating out to once a week."

[0656] Subsequently, the device notifies the user of advice generated by the server and provides a reminder function to prompt action as needed. Each time the user takes action, the device sends the spending status to the server, which updates the information in real time to generate even more appropriate feedback.

[0657] Furthermore, the server can utilize discount coupons and special offers obtained from various partner companies to provide users with the most suitable deals based on their preferences and purchasing behavior. This feature allows users to make more efficient purchases and helps them manage their household finances.

[0658] In this way, the entire system works together to promote improvements in users' lives and enhance the efficiency of household budget management.

[0659] The following describes the processing flow.

[0660] Step 1:

[0661] Users upload images of credit card statements and receipts via an application using their smartphones or computers. The device then uses OCR technology to extract text information from these images and formats it as financial data.

[0662] Step 2:

[0663] The terminal sends the extracted financial data to the server. The server stores the received data in a database. The data is categorized into information such as date, expenditure amount, and expenditure details.

[0664] Step 3:

[0665] The server analyzes financial data stored in the database and automatically classifies it into categories such as food and beverage, transportation, housing, and entertainment using machine learning algorithms.

[0666] Step 4:

[0667] The server analyzes user spending patterns based on categorized data. By comparing this with past data, it identifies categories of unusual spending or areas where savings can be made.

[0668] Step 5:

[0669] The server identifies opportunities for saving money and generates specific saving advice based on the user's spending habits. This advice includes action plans and specific saving targets to reduce spending.

[0670] Step 6:

[0671] The terminal notifies the user of advice obtained from the server. The notification includes savings suggestions and specific actions to be taken, which the user can review and implement.

[0672] Step 7:

[0673] When a user takes action based on the advice, the device records that action and sends it to the server. The server uses this information to analyze the progress of spending and the achievement of savings goals.

[0674] Step 8:

[0675] Based on the analysis results, the server generates feedback, providing information on achieved savings and further suggestions. It also references coupons and discount information from partner companies and sends advantageous information tailored to the user's spending habits to their device.

[0676] (Example 1)

[0677] 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".

[0678] In modern society, users are required to efficiently manage a wide range of spending information. However, doing so manually is incredibly time-consuming and can make accurate data analysis difficult. Furthermore, providing specific, personalized saving advice to users is challenging, and there is a lack of efficient support based on consumption trends.

[0679] 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.

[0680] In this invention, the server includes means for collecting economic data from users in multiple formats, means for converting the collected data into text using image processing technology, and means for automatically classifying the converted data into hierarchical categories. This makes it possible to efficiently analyze the user's economic data and provide accurate advice and optimal discount information in real time.

[0681] A "user" is an individual or organization that uses this system to manage their own economic data.

[0682] "Economic data" refers to information about a user's daily spending and income, including credit card statements and receipts.

[0683] "Image processing technology" refers to techniques for extracting text data from image data, and includes OCR (Optical Character Recognition).

[0684] "Converting to text" refers to the process of converting image data into text information.

[0685] "Hierarchical categorization" refers to a method of classifying data into several main categories and subdivided subcategories below them.

[0686] "Automatic classification" refers to the process of using machine learning or algorithms to sort data into appropriate categories based on pre-defined rules.

[0687] "Guidelines" refers to specific advice and suggestions for users to make their economic activities more efficient.

[0688] "Discount information" refers to preferential pricing and promotional information provided by affiliated third parties.

[0689] "Real-time delivery" means that whenever user behavior or data is updated, information and feedback corresponding to that change are immediately presented.

[0690] This invention is a system that efficiently handles economic data and provides savings advice through analysis to support users' financial management. Users access a dedicated application using devices such as smartphones or computers. Users collect data by uploading images of credit card statements and receipts to the application.

[0691] The device converts the received image data into text data using image processing technology, specifically OCR technology. Common OCR tools include Tesseract, and cloud-based solutions are available as commercial services. At this stage, the device sends the converted text data to the server.

[0692] The server records the received text-based economic data in a database management system. Suitable database systems include scalable open-source systems such as MySQL and PostgreSQL. The recorded data is then categorized hierarchically using natural language processing and machine learning algorithms, such as food, transportation, housing, entertainment, and others.

[0693] Following data classification, the server analyzes spending patterns in detail and detects unique trends. Based on the analysis results, it uses an AI model to formulate guidelines for optimizing the user's spending. For example, if spending is increasing in a particular category, it generates advice on reducing spending in that category. A specific example of such advice might be, "Since food expenses are high, refrain from eating out once a week."

[0694] The generated guidelines are sent from the server to the terminal, which then notifies the user. Each time the user takes action according to the guidelines, the result is fed back from the terminal to the server, and the server updates the data in real time, enabling further analysis and more efficient advice.

[0695] Furthermore, the server provides users with discount information and coupons obtained from partner third parties. This information is selected based on the user's preferences and purchasing behavior, with the aim of positively influencing the user's purchasing decisions.

[0696] An example of a prompt message might be, "Analyze the user's economic data to identify spending trends and suggest ways to reduce costs." This invention is a comprehensive system for monitoring the user's daily economic activities and supporting efficient financial management.

[0697] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0698] Step 1:

[0699] Users access the application using devices such as smartphones or computers and upload image data of credit card statements or receipts. The input is image data, and the output is prepared to be converted into text data. The device receives the image and forms the foundation for processing this data in the next step.

[0700] Step 2:

[0701] The terminal applies OCR technology to the received image data, converting the character data within the image into text format. The input is image data, and the output is text data. In this step, OCR software is used to perform character recognition and extract the necessary financial information.

[0702] Step 3:

[0703] The terminal sends the text data extracted by OCR to the server. The input is text data, and the output is data transfer to the server. This makes the financial data available for analysis on the server side.

[0704] Step 4:

[0705] The server records the received text-formatted economic data in a database. The input is text data, and the output is structured data stored in the database. In this step, data persistence takes place and is used in subsequent analysis steps.

[0706] Step 5:

[0707] The server automatically categorizes data using natural language processing and machine learning algorithms. The input is structured data stored in a database, and the output is categorized data. Specifically, expenditures are classified into categories such as food, transportation, housing, and entertainment.

[0708] Step 6:

[0709] The server analyzes the classified data and examines spending patterns in detail. This identifies abnormal spending trends and areas for improvement. The input is classified data, and the output is a report containing the analysis results.

[0710] Step 7:

[0711] The server generates specific savings advice for the user based on the analysis results. The input is the analysis results, and the output is text data providing guidance. Using a generation AI model, it follows the instruction, as an example of a prompt, "Analyze the user's economic data, identify spending trends, and suggest ways to reduce costs."

[0712] Step 8:

[0713] The server sends the generated advice and acquired discount information to the terminal. The input is the advice text and discount information, and the output is a notification signal to the user. This allows the user to receive useful information that is updated regularly.

[0714] Step 9:

[0715] The device notifies the user of the advice it receives and, if necessary, sets a reminder. The input is a notification signal from the server, and the output is information displayed on the user interface. This allows the user to take action according to the advice.

[0716] (Application Example 1)

[0717] 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".

[0718] Modern users receive numerous paper receipts and invoices by mail in their daily lives, making it difficult to efficiently organize this financial data and obtain advice on saving money. Furthermore, the lack of means to digitize and automatically analyze this paper information has made it difficult to grasp more effective saving methods and manage household finances effectively.

[0719] 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.

[0720] In this invention, the server includes means for collecting financial data from users, means for automatically classifying the collected data into categories, means for analyzing the classified data and identifying opportunities for savings, means for a household appliance to read paper financial data and digitize it, and means for transmitting the digitized data to a remote information processing device. This makes it possible to automatically organize all financial data, including paper information, and provide savings advice tailored to the user.

[0721] "Means of collecting financial data from users" refers to technologies that automatically acquire information from financial information owned by users or from paper documents.

[0722] "Methods for automatically classifying data by category" refers to functions that sort collected data into categories such as food, transportation, and housing.

[0723] "Methods for identifying savings opportunities" refer to techniques that use analyzed data to identify unnecessary spending and items that can be reduced.

[0724] "A means of providing users with money-saving advice" refers to a function that notifies users of specific money-saving methods based on the analyzed information.

[0725] "A means of tracking users' saving behavior and providing feedback" refers to technology that tracks users' actions and spending and suggests areas for improvement based on that data.

[0726] "Means of providing users with advantageous information and discount information" refers to technology that delivers promotional information from partner companies to users according to their interests and behavior.

[0727] "A means by which household devices read and digitize paper financial data" refers to technology that reads information printed on paper using a machine and converts it into digital information.

[0728] "Means for transmitting digitized data to a remote information processing device" refers to the technology of transferring locally stored digital data to another device via a network.

[0729] This invention is a financial management support system using consumer electronics, aiming to manage users' lives more efficiently. The server automatically collects and analyzes financial data through the user's terminal and home appliances. Cameras and OCR sensors mounted on the terminal read paper-based receipts and invoices received by the user, digitize them, and transmit the data to a cloud server.

[0730] The cloud server uses natural language processing and machine learning algorithms to categorize this data into categories such as food, transportation, and housing. Furthermore, based on the categorized data, the server analyzes the user's spending patterns and identifies opportunities for saving. Saving advice generated based on the analysis is then communicated visually or audibly through home appliances or the user's device.

[0731] Specifically, the server can issue advice such as "limit eating out to once a week." This allows users to review their spending habits and implement effective saving methods. The server also provides coupons tailored to the user's spending habits based on the latest discount and special offers from partner companies.

[0732] The hardware required to run the program includes camera sensors and OCR sensors built into home appliances, as well as terminals capable of network communication. The software includes OCR libraries (e.g., Tesseract) and cloud services for data analysis (e.g., AWS Lambda).

[0733] As a concrete example, a user could have a home device scan receipts from restaurants they frequent for dinner, and if the device determines that their spending is excessive, it could provide advice such as "You should reduce the number of times you eat out this month," along with information on coupons that can be used at that restaurant.

[0734] An example of a prompt message for the generated AI model could be: "This home robot is an application that scans paper receipts collected by the user, analyzes them in the cloud, and provides advice on saving money." This allows the entire system to work together and contribute to improving the user's life.

[0735] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0736] Step 1:

[0737] Based on user instructions, the terminal uses the camera of a home appliance to scan paper receipts and invoices. In this step, paper financial data is provided as input, and digital image data is generated as output. Through the image capture operation, the information on paper is visually recorded.

[0738] Step 2:

[0739] The terminal scans digital image data, which is then input to an OCR sensor for character recognition. This converts the image data into analyzable digital text data. The input is a scanned image, and the output is text data; this conversion is performed using OCR technology.

[0740] Step 3:

[0741] The terminal sends the generated digital text to the server. The server stores the received text data in a cloud environment. This ensures that the data is securely stored and used as a basis for subsequent processing.

[0742] Step 4:

[0743] The server analyzes stored text data and classifies it into categories using natural language processing techniques and machine learning algorithms. The input is the stored text data, and the output is the classification results for each category. The analysis process involves pattern recognition using algorithms.

[0744] Step 5:

[0745] The server analyzes users' financial behavior based on categorized data and identifies opportunities for saving. The input is the classification results, and the output is data for saving advice. The analysis process involves comparing spending patterns and generating personalized advice.

[0746] Step 6:

[0747] The server generates money-saving advice and sends it to the terminal, which then notifies the user. The input is the advice data, and the output is the notification information for the user. In this step, specific money-saving suggestions are presented to the user through the mobile terminal's display or audio output device.

[0748] Step 7:

[0749] When a user acts on savings advice, the device reports the results to the server. The input is user behavior data, and the output is updated financial data. This behavior tracking provides continuous feedback, improving the accuracy of the advice.

[0750] Step 8:

[0751] The system integrates behavioral data collected by the server with information from partner companies to provide users with customized discount information. Inputs are user behavioral data and promotional information from companies, and output is customized coupon information. This promotion generation allows users to shop flexibly and save money.

[0752] 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.

[0753] This invention combines a system that manages users' financial data and provides savings support with an emotion engine that recognizes users' emotions, thereby providing more effective savings advice. This system functions when users access the application using a smartphone or computer to manage their finances.

[0754] Users upload images of their credit card statements and receipts to the app. The device uses OCR technology to extract text information from the images and organizes it as financial data. This financial data is sent to a server and stored in a database. The server categorizes the stored data and analyzes the user's spending patterns. Based on the analysis, it generates specific advice highlighting savings opportunities and notifies the user through their device.

[0755] In addition, the system integrates an emotion engine that analyzes the user's emotions. Users input their emotional state into the app or it is detected by biosensors connected to their device. This emotional data is sent to a server and analyzed along with financial data. The emotion engine learns what emotional states a user tends to be in when they increase their spending and identifies emotional patterns that influence spending behavior.

[0756] For example, if it becomes clear that a user's spending on entertainment increases when they are stressed, the server will provide constructive advice to reduce entertainment spending when it detects their stress level. Furthermore, if emotional data predicts that a user is at high risk of unconsciously overspending, the device will send a preventative notification to the user to help them control their spending.

[0757] This combination of emotional engines enables more personalized and specific saving advice for users, significantly improving the efficiency and effectiveness of household budget management.

[0758] The following describes the processing flow.

[0759] Step 1:

[0760] Users access the application using their smartphones or computers and upload images of credit card statements or receipts. The device receives these images, extracts text information using OCR technology, and organizes the read data.

[0761] Step 2:

[0762] The terminal sends the extracted financial data to the server. The server stores the received data in a database and organizes it by category for smooth analysis.

[0763] Step 3:

[0764] The server applies machine learning algorithms to analyze the stored data, classifying spending into categories such as food, transportation, housing, and entertainment, and identifying spending trends. From these analysis results, it identifies particularly noteworthy spending trends and areas where savings can be made.

[0765] Step 4:

[0766] Users input their daily emotional states into the application or obtain real-time emotional data using biosensors connected to their device. This emotional data is then transmitted to a server via the device.

[0767] Step 5:

[0768] The server integrates and analyzes financial and emotional data. It learns which spending categories are affected by specific emotional states and adjusts advice based on those results. For example, if spending on entertainment tends to increase when stress levels are high, the server will generate personalized saving advice when it detects that emotional state.

[0769] Step 6:

[0770] Based on the analyzed information, the server generates money-saving advice for the user and presents a concrete action plan. This advice is notified to the user via their device, and reminders and warnings may be issued as needed.

[0771] Step 7:

[0772] The user takes saving actions based on the advice they receive. The device records these actions and sends the action data back to the server. The server takes this data, provides feedback, and improves or updates the advice further.

[0773] Step 8:

[0774] The server optimizes discount coupons and information provided by partner companies based on the user's spending patterns and sentiment data, and delivers them to the user via their device. This allows the user to enjoy substantial savings.

[0775] (Example 2)

[0776] 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".

[0777] Modern consumers demand efficient and accurate advice in financial management, but traditional systems have lacked the ability to provide saving advice that adequately considers the impact of users' emotional states on their spending behavior. Furthermore, there was a challenge in identifying emotion-based spending patterns, making personalized advice difficult.

[0778] 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.

[0779] In this invention, the server includes means for extracting text data from the user, means for automatically classifying the stored information by category, and means for generating savings advice based on the analysis results using a generative AI model. This makes it possible to provide more personalized and specific savings advice that takes into account the user's emotional state.

[0780] "Means for extracting text data from users" refers to the process of extracting text information from image data provided by users using optical character recognition technology.

[0781] "Means of formatting and storing financial information" refers to the process of converting extracted text data into a specified format and saving it to a database.

[0782] "Methods for automatically classifying information into categories" refers to the process of automatically categorizing stored information using specific rules or algorithms.

[0783] "A method for generating savings advice based on analysis results using a generative AI model" refers to a process that utilizes artificial intelligence technology to analyze user data and propose the optimal savings method.

[0784] "Means for acquiring users' emotional states and integrating and analyzing them with stored information" refers to the process of analyzing emotional data collected from users in conjunction with existing financial data to gain insights into their spending behavior.

[0785] "Methods for identifying spending patterns based on emotional states" refers to the process of analyzing users' emotional data and using the results to clarify their spending tendencies.

[0786] The "ability to generate personalized savings advice" is the ability to present specific and personalized savings methods based on the user's particular circumstances and information.

[0787] This invention relates to a system that integrates and manages a user's financial data and emotional state to provide individually optimized savings advice. Users access the application using a smartphone or computer to manage their daily finances. This system is implemented in the following way:

[0788] Users upload photos of receipts or credit card statements to the application using their device. The device uses OCR technology to extract text information from the uploaded images. Specific OCR technologies that can be used include Tesseract OCR and Google Cloud Vision API. This extracted text information is formatted as financial data on the device and prepared for transmission to the server.

[0789] The server receives financial data sent from the terminal and stores it in a database. Common RDBMSs such as MySQL and PostgreSQL can be used as the database management system. The stored data is categorized and analyzed using machine learning algorithms and data mining techniques.

[0790] Furthermore, the user's emotional state is collected through self-input within the application and via biosensors. These biosensors include heart rate monitors and skin electrical activity sensors. The collected emotional data is sent to a server and analyzed in conjunction with financial data. The emotion engine learns the correlation between the user's emotional state and spending behavior.

[0791] For example, if a pattern is identified where a user's spending on fashion increases when they are in a good mood on holidays, the server can send a prompt to the AI ​​model, which can then output specific advice such as, "Please give me advice on how to reduce unnecessary spending on fashion on my next holiday."

[0792] In this way, the server generates personalized saving advice that takes into account the user's emotional state. This system allows users to easily understand their spending patterns and efficiently take actions to reduce unnecessary spending.

[0793] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0794] Step 1:

[0795] Users launch the application using their smartphone or computer and upload images of credit card statements or receipts. The input here is image data. The device uses OCR technology to extract text information from this image data. Specifically, a program called Tesseract OCR is used to convert the text within the image into digital information. The output is text data.

[0796] Step 2:

[0797] The terminal formats the extracted text information into financial data. During this process, the text data is structured according to a specific format. This formatted data is provided in JSON or XML format. Once the data is formatted, it is ready for smooth transmission to the server. The output is the formatted financial data.

[0798] Step 3:

[0799] The terminal sends formatted financial data to the server. Upon receiving this data, the server stores it in a database. The input is the formatted financial data from the terminal, and the output is stored in the database. Generally, database management systems such as MySQL or PostgreSQL are used for this purpose.

[0800] Step 4:

[0801] The server automatically categorizes the stored financial data. This categorization utilizes pre-configured rules and algorithms. The input is financial data from the database, and the output is categorized data. This clearly reveals the user's spending patterns.

[0802] Step 5:

[0803] Users either input their emotional state within the application or collect emotional data using biosensors connected to their device (such as heart rate monitors or skin electrical activity sensors). The input is emotional information from the biosensors, and the output is the collected emotional data. This data is also sent to the server.

[0804] Step 6:

[0805] The server integrates and analyzes emotional and financial data. The emotion engine learns from historical data to identify correlations between emotional states and spending behavior. The inputs are emotional and financial data, and the output is spending patterns associated with emotional states.

[0806] Step 7:

[0807] The server uses a generative AI model to generate savings advice based on the analysis results. Here, prompts are used to gain insights into specific spending patterns. The input is the analyzed data, and the output is specific savings advice for the user.

[0808] Step 8:

[0809] The server sends the generated advice to the terminal, which then notifies the user. The input is the generated savings advice, and the output appears as a real-time notification to the user. This notification allows the user to adjust their actions immediately.

[0810] (Application Example 2)

[0811] 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".

[0812] In today's economic society, individuals engage in numerous economic activities daily, but the associated wastefulness and impulsive spending can negatively impact personal finances. Emotions, in particular, have a significant influence on economic activity, and because self-control is difficult, it is crucial to curb wasteful spending. Furthermore, conventional economic management systems lack the ability to provide personalized suggestions to users, and are especially inadequate in supporting appropriate spending management based on emotional states.

[0813] 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.

[0814] In this invention, the server includes means for collecting economic data from the user, means for analyzing emotional data, and means for generating specific advice to prevent wasteful spending. This enables personalized spending reduction suggestions based on the user's emotional state and economic behavior.

[0815] A "user" refers to an individual or customer who provides economic data and receives assistance with spending management through their emotional state.

[0816] "Economic data" is a general term for information related to an individual's finances, including information on income, expenses, purchase details, and budgets.

[0817] "Emotional data" refers to information that indicates an individual's mental state, and is acquired by the user through physical input or biosensors.

[0818] "Wasteful spending" refers to unplanned or impulsive expenditures that may threaten a user's financial health.

[0819] "Advice" refers to suggestions about economic actions a user should take, and is personalized based on the user's emotional state and economic data.

[0820] A "server" refers to a computer system that receives and processes economic and emotional data and provides users with relevant information.

[0821] "Means" is a concept that includes methods or apparatus provided to achieve a particular function in this invention.

[0822] The system of this invention is designed to enable users to manage their finances and link their personal consumption behavior to their emotional state. The server collects, integrates, and analyzes the user's economic and emotional data, enabling it to provide personalized financial advice.

[0823] First, the device collects economic data from the user using a smartphone or computer. This data includes purchase history and records of financial status. Next, the device sends emotional data collected from the user's biosensors to a server. This data is obtained using facial recognition sensors and heart rate monitors.

[0824] On the server, this data is stored in a database. MySQL is used as the database management system for processing, and Python and the machine learning library TensorFlow are utilized for data analysis. Tesseract is used for OCR to extract necessary text data from statements and receipts.

[0825] Next, the server analyzes the user's economic data to identify patterns in their consumption behavior. Then, the emotion engine analyzes the emotional data and evaluates the impact of that state on their economic activity. Economic advice and warnings generated based on this information are notified to the user in real time using the Twilio API.

[0826] As a concrete example, if a user is experiencing stress while attempting to purchase an expensive item on an e-commerce platform, the server will indicate that the expenditure is unplanned and send a notification suggesting alternatives. This allows users to make rational purchasing decisions rather than reacting emotionally.

[0827] To support this process using a generative AI model, a prompt such as, "Generate effective advice to help users avoid unplanned spending when they are feeling stressed," could be used. This would allow the AI ​​to suggest optimal advice in real time, tailored to the user's situation.

[0828] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0829] Step 1:

[0830] The device retrieves economic data uploaded by the user (such as credit card statements and receipt images). Using this data as input, it extracts text information from the images using OCR technology and organizes it as economic data. The extracted data is stored in temporary data storage.

[0831] Step 2:

[0832] Economic data extracted from the terminal is sent to the server. The server stores this economic data in a database and classifies it by category using a database management system. SQL queries are used to process the data, dividing it into categories such as income and expenses.

[0833] Step 3:

[0834] The user inputs emotional data into the device using biosensors. This emotional data includes heart rate and facial expression information. The device then transmits this emotional data to a server.

[0835] Step 4:

[0836] The server receives emotional data, analyzes it using machine learning libraries (such as TensorFlow), and identifies the user's emotional state. The results of the emotional state identification are stored in a database and linked to the user's economic data.

[0837] Step 5:

[0838] The server integrates user economic and emotional data to analyze user consumption patterns. Python scripts are used for statistical analysis and trend identification. The output is a report on user consumption trends and emotions.

[0839] Step 6:

[0840] The server uses a generative AI model to generate personalized financial advice based on the prompt "Generate effective advice to prevent unplanned spending when the user is feeling stressed." This generated advice is optimized based on the user's past spending habits and emotional patterns.

[0841] Step 7:

[0842] The server uses the Twilio API to notify users of generated financial advice on their devices. These notifications include spending warnings and sentiment-based suggestions for reducing spending, and are provided to users in real time.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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."

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0864] The following is further disclosed regarding the embodiments described above.

[0865] (Claim 1)

[0866] Means of collecting financial data from users,

[0867] A method for automatically classifying collected financial data by category,

[0868] A means of analyzing classified data and identifying opportunities for savings,

[0869] A means of providing users with money-saving advice,

[0870] A means to track users' saving behavior and provide feedback,

[0871] A system that includes means of providing users with special offers and coupons.

[0872] (Claim 2)

[0873] The system according to claim 1, which has a function to detect abnormal spending patterns from the user's financial data.

[0874] (Claim 3)

[0875] The system according to claim 1, which has a function to generate savings advice for a specific category according to the user's spending pattern.

[0876] "Example 1"

[0877] (Claim 1)

[0878] A means of collecting economic data from users in multiple formats,

[0879] A means of converting collected economic data into text using image processing technology,

[0880] A means of automatically classifying the converted data into hierarchical categories,

[0881] A means of analyzing classified data to identify opportunities for efficiency improvements,

[0882] A means of providing users with guidelines for efficiency,

[0883] A means of tracking user behavior and providing dynamic feedback,

[0884] A system that includes means of presenting users with discount information provided by a third party.

[0885] (Claim 2)

[0886] The system according to claim 1, which has a function to detect unusual spending trends from the user's economic data.

[0887] (Claim 3)

[0888] The system according to claim 1, which has a function to generate efficiency guidelines for a specified category according to the user's spending tendencies.

[0889] "Application Example 1"

[0890] (Claim 1)

[0891] Means of collecting financial data from users,

[0892] A method for automatically classifying collected financial data by category,

[0893] A means of analyzing classified data and identifying opportunities for savings,

[0894] A means of providing users with money-saving advice,

[0895] A means to track users' saving behavior and provide feedback,

[0896] A means of providing users with advantageous information and discount information,

[0897] A means for home appliances to read paper financial data and digitize it,

[0898] A means for transmitting digitized data to a remote information processing device,

[0899] A system that includes this.

[0900] (Claim 2)

[0901] The system according to claim 1, wherein a household appliance has a function to analyze financial data and detect abnormal spending patterns.

[0902] (Claim 3)

[0903] The system according to claim 1, which has a function to generate savings advice for a specific category according to the user's spending pattern, and presents the generated advice via a home appliance.

[0904] "Example 2 of combining an emotion engine"

[0905] (Claim 1)

[0906] A means of extracting text data from users,

[0907] A means of formatting and storing extracted text data as financial information,

[0908] A means of automatically classifying stored information into categories,

[0909] A means of analyzing classified information and identifying opportunities for saving,

[0910] A means for generating savings advice based on analysis results using a generative AI model,

[0911] A means for acquiring the user's emotional state, integrating it with stored information, and analyzing it,

[0912] A means of identifying spending patterns based on emotional states,

[0913] A system that includes means for providing money-saving advice based on the user's emotional state.

[0914] (Claim 2)

[0915] The system according to claim 1, which has a function to detect an abnormal spending pattern of a user based on emotional data.

[0916] (Claim 3)

[0917] The system according to claim 1, which has the function of learning the relationship between user emotional data and spending patterns and generating personalized saving advice.

[0918] "Application example 2 when combining with an emotional engine"

[0919] (Claim 1)

[0920] Means of collecting economic data from users,

[0921] A method for automatically classifying collected economic data by category,

[0922] A means of analyzing segmented data and identifying opportunities for savings,

[0923] A means of providing users with money-saving advice,

[0924] A means to track users' saving behavior and provide feedback,

[0925] Means of providing users with useful information and discount coupons,

[0926] A means of analyzing user sentiment data and sending warnings based on consumer behavior,

[0927] This is a format that combines economic information and emotional states to generate specific advice to prevent wasteful spending.

[0928] A system that includes means of providing users with immediate notifications to curb spending.

[0929] (Claim 2)

[0930] The system according to claim 1, which has the function of detecting abnormal spending trends from the user's economic data and making corresponding suggestions based on emotional data.

[0931] (Claim 3)

[0932] The system according to claim 1, which has a function to generate savings advice of a specific category that takes into account the user's emotional state according to their consumption trends. [Explanation of Symbols]

[0933] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting financial data from users, A method for automatically classifying collected financial data by category, A means of analyzing classified data and identifying opportunities for savings, A means of providing users with money-saving advice, A means to track users' saving behavior and provide feedback, A means of providing users with advantageous information and discount information, A means for home appliances to read paper financial data and digitize it, A means for transmitting digitized data to a remote information processing device, A system that includes this.

2. The system according to claim 1, wherein a household appliance has a function to analyze financial data and detect abnormal spending patterns.

3. The system according to claim 1, which has a function to generate savings advice for a specific category according to the user's spending pattern, and presents the generated advice via a home appliance.

Images