system

Abstract

We provide the system. [Solution] A means for extracting text information from received image data using image recognition technology, A means of classifying extracted text information and automatically sorting it into pre-defined categories, A means for generating and transmitting financial advice to a user based on classified information using natural language processing technology, A means of automatically generating the data required for the tax return format, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a problem that personal income and expenditure management and tax declaration operations are complicated, and many people cannot perform accurate and efficient management. In addition, due to a lack of financial knowledge and tax system literacy, individuals have the problem of not being able to fully utilize available tax incentives and asset formation opportunities. Solving these problems has become an important need in busy modern society.

Means for Solving the Problems

[0005] This invention provides a system that automatically extracts text information from image data of receipts and invoices received using image recognition technology, and categorizes that information into pre-set categories. This system applies natural language processing technology to provide users with appropriate financial advice based on the categorized data, and also has the function of automatically generating the necessary format for tax filing. This enables individuals to efficiently and accurately manage their income and expenses and file tax returns, thereby improving financial literacy and supporting asset building.

[0006] "Image recognition technology" is a technology that analyzes digital images and videos to extract and process specific information.

[0007] "Text information" refers to information containing characters and sentences extracted from image data, which can be treated as data by analyzing it.

[0008] "Natural language processing technology" is a technology that enables computers to understand, generate, and respond to human language, and is used in interactive systems, information retrieval, and other applications.

[0009] "Financial advice" refers to providing guidance based on income and expenditure data, market information, and other factors to help individuals manage their assets and optimize their investment strategies.

[0010] A "tax return format" refers to the official document format and layout used to submit to the tax authorities, and is designed to accurately record information such as income and deductions.

[0011] "Journal entry" refers to the process of classifying transactions and assigning them to the appropriate accounting items in accounting, and it is a fundamental process for financial reporting. [Brief explanation of the drawing]

[0012] [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]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] The present invention provides an advanced software system for simplifying personal expense management and tax filing. This system is implemented via a computer terminal such as a smartphone or tablet. Users use the terminal to take pictures of everyday receipts and invoices and send them via the internet to a dedicated messaging application. This application works in conjunction with a server to analyze the image data and process the collected information for accounting purposes.

[0034] The server uses image recognition technology to extract text information from received image data. The extracted text is automatically categorized into date, amount, expenditure category, etc. Images sent by users include various categories such as educational institutions, public facilities, food, and dining out, and are sorted appropriately according to each category.

[0035] The terminal is equipped with a front-end interface for managing the user's financial activities, where the user can review and modify their spending. The server also utilizes natural language processing technology to generate financial advice based on the user's financial data. For example, if a user's spending increases in a particular month, it provides advice on the causes and areas for improvement.

[0036] During tax filing season, the server aggregates the user's annual financial data and automatically generates the necessary documents for tax filing. This feature allows users to easily file their taxes without having to perform detailed accounting themselves.

[0037] For example, if a user wants to record a restaurant payment, they simply need to take a picture of the receipt and upload it to the application. The server classifies the image as "dining expenses" and provides the user with advice, including the percentage of that expense within the month's spending and a comparison with past data. In this way, the system of the present invention efficiently manages everyday economic activities and contributes to improving individuals' financial literacy.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] Users take photos of receipts and invoices using their device's camera and upload the image data to a dedicated messaging application.

[0041] Step 2:

[0042] The device sends image data to the LINE server, where it undergoes encoding processing for communication. This process includes checking the image format and, if necessary, compressing it.

[0043] Step 3:

[0044] The server analyzes the received image data. First, it uses optical character recognition (OCR) technology to extract text information from the image.

[0045] Step 4:

[0046] The server analyzes the extracted text information and classifies it into categories such as date, amount, and category (e.g., food and beverage expenses, transportation expenses). Based on this classification, it records the information in an accounting database.

[0047] Step 5:

[0048] The natural language processing AI on the server analyzes recorded data and generates appropriate financial advice for the user. In doing so, it takes into account the user's past data and market trends to provide the most optimal advice.

[0049] Step 6:

[0050] Users receive advice and analysis results from the server via the LINE application. If the user has further questions, they can enter their questions again in natural language, and the server will provide additional information.

[0051] Step 7:

[0052] The server aggregates users' income and expense data at the end of the fiscal year and automatically generates the necessary documents for filing tax returns. This allows users to easily prepare tax return documents and streamline the filing process.

[0053] (Example 1)

[0054] 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."

[0055] Managing personal finances in modern times is a time-consuming and complex task, encompassing a wide range of activities such as organizing receipts and invoices, classifying expenses, and preparing data for tax returns. Furthermore, these tasks require specialized knowledge, and accounting and tax filing, in particular, are difficult for many people. In this context, there is a need for a system that allows individuals to easily manage their finances and access financial advice.

[0056] 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.

[0057] In this invention, the server includes means for acquiring textual information from received digital data using image analysis means, means for classifying the acquired textual information and automatically categorizing it based on pre-set categories, and means for generating and providing financial advice to the user based on the classified information using natural language processing technology. As a result, users can manage their finances without hassle, easily grasp their financial situation without specialized knowledge, and receive advice for improvement.

[0058] "Image analysis means" refers to technologies and methods for obtaining textual information from received digital data.

[0059] "Textual information" refers to text data such as dates, numbers, and item names obtained from images and digital data.

[0060] A "category" refers to a classification item that has been pre-set for classifying the acquired text information.

[0061] "Natural language processing technology" refers to a set of technologies that generate financial advice in a form understandable to the user, based on textual information.

[0062] "Journaling" refers to the process of organizing and classifying acquired textual information based on pre-defined categories.

[0063] "Financial advice" refers to information that analyzes a user's financial situation based on acquired and categorized textual information, and provides suggestions and guidance for improvement.

[0064] This invention is a system for facilitating personal financial management and is primarily implemented through the cooperation of a server and a terminal.

[0065] Users take photos of everyday receipts and invoices using devices such as smartphones and tablets. The captured images are sent to a server via a dedicated application. The application provides a user-friendly interface, making it easy to upload images.

[0066] The server uses general-purpose image analysis techniques for image recognition. For example, it uses OCR technology to extract text information from images. The extracted text information is classified into data such as date, amount, and expenditure category. This allows for efficient organization of received digital data.

[0067] Furthermore, the server utilizes natural language processing technology to generate financial advice for the user. For example, it can provide specific advice such as, "Your food and beverage expenses have increased this month. Please consider ways to save money." The generated information is sent to the terminal application and notified to the user in real time.

[0068] The device features a financial management interface, allowing users to review collected information and make corrections if necessary. It also displays graphs and charts to visualize the user's financial situation, providing an easy-to-use dashboard.

[0069] For example, if a user wants to record a restaurant payment, they take a picture of the receipt with their device and upload the image to the application. The server retrieves the necessary information from the image and automatically categorizes it as "dining." The user then compares this to their past spending data and receives advice on how to manage future spending.

[0070] Examples of prompts include "Please tell me about your spending this month" and "What caused the increase in your food and beverage expenses?", which allow users to receive advanced financial analysis through a generated AI model.

[0071] This system makes it easy for individuals to manage their finances without specialized knowledge, and also simplifies tax filing.

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The user launches the device's camera application and takes a picture of a receipt or invoice. The input is a paper receipt, and the output is a digital image file. The image is saved in JPEG or PNG format and passed on to the next processing step.

[0075] Step 2:

[0076] The device uploads captured image files to the server via a dedicated messaging application. When the user selects an image within the application and presses the send button, the input image data is sent to the server via the internet. The output is the received image data, ready for analysis by the server.

[0077] Step 3:

[0078] The server applies image analysis technology to the received image data. Specifically, it uses an OCR (Optical Character Recognition) engine to extract text information from the image. The input is the received image data, and the output is the extracted text information, which includes information such as the date, amount, and store name.

[0079] Step 4:

[0080] The server automatically categorizes extracted text information into pre-defined categories (e.g., food and drink, transportation, education). The input is extracted text information, and the output is data organized by category. Each item is appropriately categorized using rule-based or machine learning-based classification algorithms.

[0081] Step 5:

[0082] The server uses organized data and natural language processing techniques to generate financial advice for the user. The input is categorized financial data, and the output is advice in a human-readable format. The generated advice includes monthly spending trends and suggestions for future improvements.

[0083] Step 6:

[0084] The terminal displays advice messages and organized financial data sent from the server to the user. Through the terminal's interface, the user can review their spending and compare it to past data. Input is response data from the server, and output is visual data such as graphs and charts presented to the user. The user can also modify the data as needed.

[0085] (Application Example 1)

[0086] 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."

[0087] There is a need to provide a system that reduces the burden of daily expense management and tax filing, and that can automatically classify and analyze expense information, especially in the case of electronic payments. Existing methods have problems such as the effort required for users to manually input and verify information, and insufficient analysis and management of expenses, so improvements are needed.

[0088] 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.

[0089] In this invention, the server includes means for extracting textual information from received image data using image recognition technology, means for classifying the extracted textual information and automatically sorting it into pre-set classifications, and means for generating and transmitting financial advice to the user based on the classified information using natural language processing technology. This enables users to automatically manage their spending by using electronic payments and to efficiently perform monthly analysis and budget management.

[0090] "Image recognition technology" is a technology that automatically detects and extracts specific information from image data acquired using cameras and sensors.

[0091] "Textual information" refers to text data extracted from image data, including specific information such as dates, amounts, and names.

[0092] "Classification" is the process of organizing extracted information according to predefined categories or types.

[0093] "Natural language processing technology" is a technology that enables computers to understand and process human language, and it is also applied to the generation of advice.

[0094] "Means for generating and transmitting advice" refers to a method for creating and providing specific financial advice to users.

[0095] "Means of managing expense details" refers to methods for recording information such as the date, amount, and category of a transaction, and allowing users to review and modify it.

[0096] "Expenditure analysis and budget management" is the process of analyzing users' spending data, evaluating consumption trends, suggesting areas for improvement, and planning and managing budgets.

[0097] The system for realizing this invention involves a smartphone or tablet working in conjunction with a server possessing advanced analytical capabilities. The terminal is used by the user for everyday payments, and when electronic payment is made, it has a function to automatically capture an image of the receipt. The server receives this image data, performs image recognition using the Google® Cloud Vision API, and extracts text information. The extracted text information is analyzed by a natural language processing system running in a Node.js environment and classified into expenditure categories. The classified data is stored in MongoDB, and users can easily access and manage it through a frontend developed with React Native.

[0098] The server analyzes monthly spending and generates advice for budget management. This includes comparing past spending patterns with current spending and providing tips for improvement and savings.

[0099] For example, when a user dines at a restaurant, the receipt is automatically photographed at the time of payment and categorized as "food and beverage expenses." At the end of the month, the server uses this data to send a notification asking whether the food expenses are within budget.

[0100] By utilizing a generative AI model, it is possible to receive inquiries from users and generate answers in response to prompts such as "What is the total amount of food expenses for this month?".

[0101] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0102] Step 1:

[0103] The terminal automatically captures an image of the receipt when the user completes an electronic payment. The input is the electronic payment completion signal, and the output is the captured receipt image data. This image data is usually saved to the terminal in JPEG or PNG format.

[0104] Step 2:

[0105] The terminal sends receipt image data to the server via the internet. The input is the image data generated in step 1, and the output is the image data sent to the server. The HTTPS protocol is used for this communication to securely transfer the data.

[0106] Step 3:

[0107] The server uses the Google Cloud Vision API to extract text information from received image data. The input is receipt image data, and the output is extracted text information. This text information includes the date, amount, store name, etc. The API uses OCR technology to detect the text.

[0108] Step 4:

[0109] The server uses a natural language processing system running in a Node.js environment to analyze extracted text information and classify it into the appropriate expenditure category. The input is text information, and the output is category information and text information. For example, if the name of a restaurant is "restaurant", it will be classified as "food expenses".

[0110] Step 5:

[0111] The server stores the analyzed and categorized spending data in MongoDB. This database records the details of each user transaction and is used later for analysis and reference. The input is category information and text information, and the output is the record stored in the database.

[0112] Step 6:

[0113] Users can view their spending data in real time through an app implemented with React Native, and edit or modify it as needed. Input is the user's actions (e.g., changing categories), and output is the updated spending data. This interface features an intuitive and user-friendly design.

[0114] Step 7:

[0115] The server analyzes monthly spending patterns and generates and sends budget management advice to the user. The input is historical spending data stored in a database, and the output is an advice message. The advice message is processed by a generative AI model and expressed in natural language.

[0116] Step 8:

[0117] Users can ask questions within the app using prompts and receive real-time answers based on a generative AI model. The input is the prompt from the user, and the output is the answer from the AI ​​model. For example, in response to a question like "What is the total amount spent on food this month?", the system will provide information on the total amount based on the latest data.

[0118] 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.

[0119] This invention is an advanced system for assisting personal financial management, realized by combining image recognition technology, natural language processing technology, and an emotion engine. The system includes the user's terminal, processing functions on a server, and interaction with the user.

[0120] Users use devices such as smartphones or tablets to take pictures of receipts and invoices, and send the images to a server through a dedicated application. Upon receiving the image data, the server uses optical character recognition (OCR) technology to extract text information, including the date, amount, and item, from the image and automatically categorizes it into pre-configured categories.

[0121] Furthermore, this system incorporates an emotion engine that recognizes the user's emotions from their text input, video calls, and voice. Based on this emotion data, the server adjusts the content and wording of financial advice given to the user. For example, if the user is feeling stressed, the advice can be given using gentle language to help them calm down.

[0122] Using natural language processing technology, the server continuously interacts with the user. When a user asks a question to the system, the server considers the emotional context and dynamically creates a response. This feature helps users feel comfortable receiving advice and having their questions answered.

[0123] For example, if a user asks, "My food expenses have been high lately, how can I save money?", the server can analyze past spending data while also considering the user's current emotional state, and gently suggest recommended ways to save money. In this way, the present invention supports the improvement of personal financial literacy and asset management while being attentive to the user's emotions.

[0124] The following describes the processing flow.

[0125] Step 1:

[0126] Users take photos of receipts and invoices with their devices and send the image data to the server via a dedicated application.

[0127] Step 2:

[0128] To analyze the image data received by the server, optical character recognition (OCR) technology is used to extract text information from the image, including the date, amount, and category.

[0129] Step 3:

[0130] The server analyzes the extracted text information, automatically categorizes it into predefined categories (e.g., food and beverage expenses, transportation expenses), and stores it in a database.

[0131] Step 4:

[0132] The device receives input from the user. For example, the user may ask a question or seek advice via text or voice.

[0133] Step 5:

[0134] The server interprets user input using natural language processing technology to understand the user's inquiry. During this process, an emotion engine identifies emotions from the user's text and voice.

[0135] Step 6:

[0136] The server generates personalized financial advice based on the results of the emotion engine. It adjusts the content and tone of the advice according to the user's emotions, creating a personalized message.

[0137] Step 7:

[0138] The terminal notifies the user of advice provided by the server. The user then considers actions to improve their financial management based on this feedback.

[0139] Step 8:

[0140] The server aggregates user data annually and prepares to automatically generate tax returns. This data is used when users file their tax returns.

[0141] (Example 2)

[0142] 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".

[0143] In personal financial management, efficiently extracting information from paper receipts and invoices and accurately recording and classifying it is a time-consuming and laborious task. Furthermore, providing appropriate financial advice that takes user emotions into account presents a challenge. Additionally, there is a need to simplify the management of daily financial information and the generation of data for tax filing.

[0144] 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.

[0145] In this invention, the server includes means for extracting textual information from received visual information using image recognition technology, means for classifying the extracted textual information and automatically sorting it into pre-set categories, and means for analyzing the user's emotional state using emotion recognition technology and adjusting the content and expression of financial advice. This makes it possible to efficiently manage paper-based information in digital format and provide timely advice that takes the user's emotions into consideration.

[0146] "Image recognition technology" is a technology that processes visual information as digital data and extracts and recognizes specific patterns or character information.

[0147] "Textual information" refers to text data extracted from visual information, including information such as dates, amounts, and item names.

[0148] "Natural language processing technology" is a technology that enables computers to understand and generate human language, and is used for dialogue and information provision.

[0149] "Emotion recognition technology" is a technology that analyzes and determines the emotional state of a user from their voice and visual data.

[0150] A "category" is a pre-defined classification used to organize extracted textual information, and it has a structure that includes various items related to finance.

[0151] "Financial advice" refers to recommendations and guidelines provided based on a user's financial situation, intended to support their economic decisions.

[0152] A "tax return format" is a format that organizes the information required for tax filing and complies with laws and regulations.

[0153] This invention is a system that electronically supports personal financial management. Users take photos of paper receipts and invoices using a device such as a smartphone or tablet. A dedicated application on the device has the function of transmitting the captured image data to a server in the cloud. The transmitted data is protected by a secure communication protocol.

[0154] The server uses Optical Character Recognition (OCR) technology as its image recognition technology. Specifically, a platform specialized in image processing is used as a common software example to extract text information from images. This allows the date, amount, and item name to be entered into the database.

[0155] Furthermore, the server utilizes emotion recognition technology to analyze emotions from the user's input text and voice data. This analysis combines speech processing and natural language processing technologies. Specifically, a general emotion engine is used for emotion analysis to determine whether the user is experiencing stress, among other things.

[0156] Furthermore, the server uses natural language processing technology to interact with the user. Generative AI models are utilized to respond instantly to user questions. For example, if a user asks, "My food expenses have been high lately, how can I save money?", the server will refer to past spending data, take the user's emotional state into consideration, and provide helpful information.

[0157] A possible example of a specific prompt message from the system would be, "Generate a conversational message that would offer gentle money-saving advice to a user who is feeling stressed." This system configuration would allow users to manage their finances efficiently and with emotional consideration.

[0158] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0159] Step 1:

[0160] Users take photos of receipts and invoices using their smartphones or tablets. The input is image data of the paper documents. The captured image data is set up to be automatically transferred to a cloud server via a dedicated application.

[0161] Step 2:

[0162] The terminal transmits image data to the server using a secure communication protocol. The input is image data on the terminal, and the output is a digital image stored on the cloud server. Through this transmission, the data is stored in a protected format for analysis processing on the server.

[0163] Step 3:

[0164] The server uses optical character recognition (OCR) technology to extract text information from received image data. The input is image data on the server, and the output is text information such as dates, amounts, and item names. OCR technology is used to extract text from images with high accuracy, and this data is stored in a database.

[0165] Step 4:

[0166] The server automatically classifies the extracted textual information. The input is textual information, and the output is the classification result into pre-defined financial categories (e.g., food expenses, transportation expenses, etc.). A rule-based system based on the textual information sorts the information into matching categories.

[0167] Step 5:

[0168] When a user sends text input or a voice message to the server, the server uses sentiment recognition technology to analyze the user's emotional state. The input is text or voice data from the user, and the output is the result of the sentiment analysis. This result is then used to provide subsequent financial advice.

[0169] Step 6:

[0170] The server uses natural language processing technology to generate financial advice for the user. The input consists of classified information and sentiment analysis data, and the output is financial advice expressed in a gentle, emotion-based manner. A generative AI model is used to construct a conversation based on prompt sentences.

[0171] Step 7:

[0172] The server sends the generated financial advice to the user's terminal. The input is the financial advice generated on the server, and the output is the advice message displayed on the user's terminal. This allows the user to manage their finances accurately while being mindful of their own emotions.

[0173] The above is the system's processing flow, and the coordinated interaction of each step enables effective financial management support.

[0174] (Application Example 2)

[0175] 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".

[0176] Personal financial management involves a wide range of tasks, from tracking daily expenses to preparing tax returns, and is often emotionally stressful. This makes it difficult for individuals to grasp and properly manage their overall financial situation. Furthermore, emotions often influence personal financial decisions, and existing systems lack consideration for these emotional factors. Addressing these challenges is crucial.

[0177] 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.

[0178] In this invention, the server includes means for extracting information from received image data, means for classifying the extracted information and automatically categorizing it into pre-set categories, and means for analyzing the user's emotions and adapting the content and expression of advice accordingly. This enables individuals to manage their finances effectively in an intuitive and emotionally responsive manner.

[0179] "Image recognition technology" is a technology that identifies and extracts specific information or features from digital images or videos.

[0180] "Natural language processing technology" is a technology that enables computers to understand, interpret, and generate human language, and is particularly important in human-computer interaction.

[0181] "Emotion recognition technology" is a technology that detects and analyzes a user's emotions from their voice or text, and can adjust responses and advice based on the results.

[0182] "Optical character recognition technology" is a technology that identifies characters within image data and converts them into digital text data.

[0183] A "tax return format" is a document that is automatically generated in a format that includes all necessary information, organized from financial information for tax filing purposes.

[0184] "Financial advice" refers to suggestions for improvement or savings methods provided based on the user's financial and emotional situation.

[0185] The system for implementing this invention uses a terminal such as a smartphone or smart glasses and a server. The terminal is responsible for transmitting image data of receipts and invoices taken by the user to the server. In this process, the smartphone's camera or a dedicated application is used.

[0186] The server performs the following processes: First, it uses optical character recognition (OCR), an image recognition technology, to extract information such as dates, amounts, and items from image data. Software such as Tesseract OCR is used for this process. The extracted information is automatically classified based on pre-configured categories. This makes it possible to efficiently manage the user's financial information.

[0187] Next, the server uses natural language processing technology to analyze user questions and inquiries and generate financial advice. This process utilizes the Google Cloud Natural Language API for user interaction. It also uses IBM Watson® Tone Analyzer to analyze the user's emotions and adjust the content and wording of the advice based on those emotions. For example, if the server determines that the user is stressed, it will provide advice in a gentler, more reassuring tone.

[0188] For example, if a user asks, "I'm going on a trip next month and want to save money on food, do you have any good suggestions?", the system analyzes past spending data to identify the spending categories the user uses most often. Based on this, it then suggests realistic ways to save money based on sentiment analysis. For instance, it might say, "Looking at your recent spending, it seems you eat out a lot. For example, increasing the frequency of cooking at home might help you save money without feeling overwhelmed. Try to save money in a fun and relaxed way."

[0189] In this way, the system provided by the server creates an environment where users can effectively manage their finances without feeling emotionally burdened.

[0190] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0191] Step 1:

[0192] The user takes a picture of the receipt or invoice using their device.

[0193] Input: Paper receipts and invoices

[0194] Specific operation: Take an image with the camera of a smartphone or smart glasses and send the image data to the server via a dedicated application.

[0195] Step 2:

[0196] The server processes the received image data using optical character recognition (OCR) technology.

[0197] Input: Image data submitted by the user

[0198] Data processing: Use Tesseract OCR to extract text information (date, time, amount, item, etc.) from images.

[0199] Output: Extracted text information

[0200] Step 3:

[0201] The server categorizes the extracted text information.

[0202] Input: Extracted text information

[0203] Data processing: Automatically sorts information based on pre-defined categories.

[0204] Output: Categorized financial data

[0205] Step 4:

[0206] The user asks questions using natural language via a device.

[0207] Input: Questions via voice or text

[0208] Specific operation: Questions entered within the smartphone application are sent to the server.

[0209] Step 5:

[0210] The server uses emotion recognition technology to analyze the user's emotions.

[0211] Input: User questions and audio data

[0212] Data processing: Emotions are analyzed using IBM Watson Tone Analyzer to identify their state.

[0213] Output: Analyzed sentiment information

[0214] Step 6:

[0215] The server uses natural language processing technology to generate financial advice.

[0216] Input: Categorized financial data and analyzed sentiment information

[0217] Data processing: Analyze the question content using the Google Cloud Natural Language API and generate advice that takes sentiment into account.

[0218] Output: Financial advice that takes user emotions into consideration.

[0219] Step 7:

[0220] The server sends the generated advice to the user's terminal and displays it to the user.

[0221] Input: Generated financial advice

[0222] Specific action: Display advice to the user via an application on their smartphone.

[0223] Output: Displayed financial advice

[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] The present invention provides an advanced software system for simplifying personal expense management and tax filing. This system is implemented via a computer terminal such as a smartphone or tablet. Users use the terminal to take pictures of everyday receipts and invoices and send them via the internet to a dedicated messaging application. This application works in conjunction with a server to analyze the image data and process the collected information for accounting purposes.

[0241] The server uses image recognition technology to extract text information from received image data. The extracted text is automatically categorized into date, amount, expenditure category, etc. Images sent by users include various categories such as educational institutions, public facilities, food, and dining out, and are sorted appropriately according to each category.

[0242] The terminal is equipped with a front-end interface for managing the user's financial activities, where the user can review and modify their spending. The server also utilizes natural language processing technology to generate financial advice based on the user's financial data. For example, if a user's spending increases in a particular month, it provides advice on the causes and areas for improvement.

[0243] During tax filing season, the server aggregates the user's annual financial data and automatically generates the necessary documents for tax filing. This feature allows users to easily file their taxes without having to perform detailed accounting themselves.

[0244] For example, if a user wants to record a restaurant payment, they simply need to take a picture of the receipt and upload it to the application. The server classifies the image as "dining expenses" and provides the user with advice, including the percentage of that expense within the month's spending and a comparison with past data. In this way, the system of the present invention efficiently manages everyday economic activities and contributes to improving individuals' financial literacy.

[0245] The following describes the processing flow.

[0246] Step 1:

[0247] Users take photos of receipts and invoices using their device's camera and upload the image data to a dedicated messaging application.

[0248] Step 2:

[0249] The device sends image data to the LINE server, where it undergoes encoding processing for communication. This process includes checking the image format and, if necessary, compressing it.

[0250] Step 3:

[0251] The server analyzes the received image data. First, it uses optical character recognition (OCR) technology to extract text information from the image.

[0252] Step 4:

[0253] The server analyzes the extracted text information and classifies it into categories such as date, amount, and category (e.g., food and beverage expenses, transportation expenses). Based on this classification, it records the information in an accounting database.

[0254] Step 5:

[0255] The natural language processing AI on the server analyzes recorded data and generates appropriate financial advice for the user. In doing so, it takes into account the user's past data and market trends to provide the most optimal advice.

[0256] Step 6:

[0257] Users receive advice and analysis results from the server via the LINE application. If the user has further questions, they can enter their questions again in natural language, and the server will provide additional information.

[0258] Step 7:

[0259] The server aggregates users' income and expense data at the end of the fiscal year and automatically generates the necessary documents for filing tax returns. This allows users to easily prepare tax return documents and streamline the filing process.

[0260] (Example 1)

[0261] 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."

[0262] Managing personal finances in modern times is a time-consuming and complex task, encompassing a wide range of activities such as organizing receipts and invoices, classifying expenses, and preparing data for tax returns. Furthermore, these tasks require specialized knowledge, and accounting and tax filing, in particular, are difficult for many people. In this context, there is a need for a system that allows individuals to easily manage their finances and access financial advice.

[0263] 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.

[0264] In this invention, the server includes means for acquiring textual information from received digital data using image analysis means, means for classifying the acquired textual information and automatically categorizing it based on pre-set categories, and means for generating and providing financial advice to the user based on the classified information using natural language processing technology. As a result, users can manage their finances without hassle, easily grasp their financial situation without specialized knowledge, and receive advice for improvement.

[0265] "Image analysis means" refers to technologies and methods for obtaining textual information from received digital data.

[0266] "Textual information" refers to text data such as dates, numbers, and item names obtained from images and digital data.

[0267] A "category" refers to a classification item that has been pre-set for classifying the acquired text information.

[0268] "Natural language processing technology" refers to a set of technologies that generate financial advice in a form understandable to the user, based on textual information.

[0269] "Journaling" refers to the process of organizing and classifying acquired textual information based on pre-defined categories.

[0270] "Financial advice" refers to information that analyzes a user's financial situation based on acquired and categorized textual information, and provides suggestions and guidance for improvement.

[0271] This invention is a system for facilitating personal financial management and is primarily implemented through the cooperation of a server and a terminal.

[0272] Users take photos of everyday receipts and invoices using devices such as smartphones and tablets. The captured images are sent to a server via a dedicated application. The application provides a user-friendly interface, making it easy to upload images.

[0273] The server uses general-purpose image analysis techniques for image recognition. For example, it uses OCR technology to extract text information from images. The extracted text information is classified into data such as date, amount, and expenditure category. This allows for efficient organization of received digital data.

[0274] Furthermore, the server utilizes natural language processing technology to generate financial advice for the user. For example, it can provide specific advice such as, "Your food and beverage expenses have increased this month. Please consider ways to save money." The generated information is sent to the terminal application and notified to the user in real time.

[0275] The device features a financial management interface, allowing users to review collected information and make corrections if necessary. It also displays graphs and charts to visualize the user's financial situation, providing an easy-to-use dashboard.

[0276] For example, if a user wants to record a restaurant payment, they take a picture of the receipt with their device and upload the image to the application. The server retrieves the necessary information from the image and automatically categorizes it as "dining." The user then compares this to their past spending data and receives advice on how to manage future spending.

[0277] Examples of prompts include "Please tell me about your spending this month" and "What caused the increase in your food and beverage expenses?", which allow users to receive advanced financial analysis through a generated AI model.

[0278] This system makes it easy for individuals to manage their finances without specialized knowledge, and also simplifies tax filing.

[0279] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0280] Step 1:

[0281] The user launches the device's camera application and takes a picture of a receipt or invoice. The input is a paper receipt, and the output is a digital image file. The image is saved in JPEG or PNG format and passed on to the next processing step.

[0282] Step 2:

[0283] The terminal uploads the captured image file to the server through a dedicated messaging application. When the user selects an image within the application and presses the send button, the input image data is transmitted to the server via the Internet. The output is the received image data that is ready for the server to analyze.

[0284] Step 3:

[0285] The server applies image analysis technology to the received image data. Specifically, it uses an OCR (Optical Character Recognition) engine to perform the operation of extracting character information from the image. The input is the received image data, and the output is the extracted text information, which includes information such as date, amount, store name, etc.

[0286] Step 4:

[0287] Based on the extracted text information, the server automatically posts to pre-set categories (e.g., dining, transportation, education). The input is the extracted character information, and the output is the data organized by category. Each item is appropriately categorized by a rule-based or machine learning-based classification algorithm.

[0288] Step 5:

[0289] The server uses the organized data to employ natural language processing technology to generate financial advice for the user. The input is the financial data organized by category, and the output is advice sentences in a format that is easy for humans to understand. The generated advice includes monthly spending trends and suggestions for future improvement, etc.

[0290] Step 6:

[0291] The terminal displays advice messages and organized financial data sent from the server to the user. Through the terminal's interface, the user can review their spending and compare it to past data. Input is response data from the server, and output is visual data such as graphs and charts presented to the user. The user can also modify the data as needed.

[0292] (Application Example 1)

[0293] 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."

[0294] There is a need to provide a system that reduces the burden of daily expense management and tax filing, and that can automatically classify and analyze expense information, especially in the case of electronic payments. Existing methods have problems such as the effort required for users to manually input and verify information, and insufficient analysis and management of expenses, so improvements are needed.

[0295] 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.

[0296] In this invention, the server includes means for extracting textual information from received image data using image recognition technology, means for classifying the extracted textual information and automatically sorting it into pre-set classifications, and means for generating and transmitting financial advice to the user based on the classified information using natural language processing technology. This enables users to automatically manage their spending by using electronic payments and to efficiently perform monthly analysis and budget management.

[0297] "Image recognition technology" is a technology that automatically detects and extracts specific information from image data acquired using cameras and sensors.

[0298] "Textual information" refers to text data extracted from image data, including specific information such as dates, amounts, and names.

[0299] "Classification" is the process of organizing extracted information according to predefined categories or types.

[0300] "Natural language processing technology" is a technology that enables computers to understand and process human language, and it is also applied to the generation of advice.

[0301] "Means for generating and transmitting advice" refers to a method for creating and providing specific financial advice to users.

[0302] "Means of managing expense details" refers to methods for recording information such as the date, amount, and category of a transaction, and allowing users to review and modify it.

[0303] "Expenditure analysis and budget management" is the process of analyzing users' spending data, evaluating consumption trends, suggesting areas for improvement, and planning and managing budgets.

[0304] The system for realizing this invention involves a smartphone or tablet working in conjunction with a server possessing advanced analytical capabilities. The terminal is used by the user for everyday payments, and when electronic payment is made, it has a function to automatically capture an image of the receipt. The server receives this image data, performs image recognition using the Google Cloud Vision API, and extracts text information. The extracted text information is analyzed by a natural language processing system running in a Node.js environment and classified into expenditure categories. The classified data is stored in MongoDB, and users can easily access and manage it through a frontend developed with React Native.

[0305] The server analyzes monthly expenditures and generates advice for budget management. This includes comparing past expenditure patterns with current expenditures and providing hints for improvement and savings.

[0306] As a specific example, when a user dines at a restaurant, a receipt is automatically photographed at the time of payment and classified as "food and beverage expenses". At the end of the month, the server uses this data to send a notification on whether the food expenses are within the budget.

[0307] By leveraging the generated AI model, it is possible to receive inquiries from users and generate responses according to prompt texts such as "What is the total food expense this month?".

[0308] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0309] Step 1:

[0310] When the user makes a payment, the terminal automatically photographs the receipt image triggered by the completion of the electronic payment. The input is the completion signal of the electronic payment, and the output is the photographed receipt image data. This image data is usually saved on the terminal in JPEG or PNG format.

[0311] Step 2:

[0312] The terminal sends the receipt image data to the server via the Internet. The input is the image data generated in Step 1, and the output is the image data passed to the server. The HTTPS protocol is used for this communication to transfer data securely.

[0313] Step 3:

[0314] The server uses the Google Cloud Vision API to extract text information from received image data. The input is receipt image data, and the output is extracted text information. This text information includes the date, amount, store name, etc. The API uses OCR technology to detect the text.

[0315] Step 4:

[0316] The server uses a natural language processing system running in a Node.js environment to analyze extracted text information and classify it into the appropriate expenditure category. The input is text information, and the output is category information and text information. For example, if the name of a restaurant is "restaurant", it will be classified as "food expenses".

[0317] Step 5:

[0318] The server stores the analyzed and categorized spending data in MongoDB. This database records the details of each user transaction and is used later for analysis and reference. The input is category information and text information, and the output is the record stored in the database.

[0319] Step 6:

[0320] Users can view their spending data in real time through an app implemented with React Native, and edit or modify it as needed. Input is the user's actions (e.g., changing categories), and output is the updated spending data. This interface features an intuitive and user-friendly design.

[0321] Step 7:

[0322] The server analyzes monthly spending patterns and generates and sends budget management advice to the user. The input is historical spending data stored in a database, and the output is an advice message. The advice message is processed by a generative AI model and expressed in natural language.

[0323] Step 8:

[0324] Users can ask questions within the app using prompts and receive real-time answers based on a generative AI model. The input is the prompt from the user, and the output is the answer from the AI ​​model. For example, in response to a question like "What is the total amount spent on food this month?", the system will provide information on the total amount based on the latest data.

[0325] 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.

[0326] This invention is an advanced system for assisting personal financial management, realized by combining image recognition technology, natural language processing technology, and an emotion engine. The system includes the user's terminal, processing functions on a server, and interaction with the user.

[0327] Users use devices such as smartphones or tablets to take pictures of receipts and invoices, and send the images to a server through a dedicated application. Upon receiving the image data, the server uses optical character recognition (OCR) technology to extract text information, including the date, amount, and item, from the image and automatically categorizes it into pre-configured categories.

[0328] Furthermore, this system incorporates an emotion engine that recognizes the user's emotions from their text input, video calls, and voice. Based on this emotion data, the server adjusts the content and wording of financial advice given to the user. For example, if the user is feeling stressed, the advice can be given using gentle language to help them calm down.

[0329] Using natural language processing technology, the server continuously interacts with the user. When a user asks a question to the system, the server considers the emotional context and dynamically creates a response. This feature helps users feel comfortable receiving advice and having their questions answered.

[0330] For example, if a user asks, "My food expenses have been high lately, how can I save money?", the server can analyze past spending data while also considering the user's current emotional state, and gently suggest recommended ways to save money. In this way, the present invention supports the improvement of personal financial literacy and asset management while being attentive to the user's emotions.

[0331] The following describes the processing flow.

[0332] Step 1:

[0333] Users take photos of receipts and invoices with their devices and send the image data to the server via a dedicated application.

[0334] Step 2:

[0335] To analyze the image data received by the server, optical character recognition (OCR) technology is used to extract text information from the image, including the date, amount, and category.

[0336] Step 3:

[0337] The server analyzes the extracted text information, automatically categorizes it into predefined categories (e.g., food and beverage expenses, transportation expenses), and stores it in a database.

[0338] Step 4:

[0339] The device receives input from the user. For example, the user may ask a question or seek advice via text or voice.

[0340] Step 5:

[0341] The server interprets user input using natural language processing technology to understand the user's inquiry. During this process, an emotion engine identifies emotions from the user's text and voice.

[0342] Step 6:

[0343] The server generates personalized financial advice based on the results of the emotion engine. It adjusts the content and tone of the advice according to the user's emotions, creating a personalized message.

[0344] Step 7:

[0345] The terminal notifies the user of advice provided by the server. The user then considers actions to improve their financial management based on this feedback.

[0346] Step 8:

[0347] The server aggregates user data annually and prepares to automatically generate tax returns. This data is used when users file their tax returns.

[0348] (Example 2)

[0349] 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".

[0350] In personal financial management, efficiently extracting information from paper receipts and invoices and accurately recording and classifying it is a time-consuming and laborious task. Furthermore, providing appropriate financial advice that takes user emotions into account presents a challenge. Additionally, there is a need to simplify the management of daily financial information and the generation of data for tax filing.

[0351] 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.

[0352] In this invention, the server includes means for extracting textual information from received visual information using image recognition technology, means for classifying the extracted textual information and automatically sorting it into pre-set categories, and means for analyzing the user's emotional state using emotion recognition technology and adjusting the content and expression of financial advice. This makes it possible to efficiently manage paper-based information in digital format and provide timely advice that takes the user's emotions into consideration.

[0353] "Image recognition technology" is a technology that processes visual information as digital data and extracts and recognizes specific patterns or character information.

[0354] "Textual information" refers to text data extracted from visual information, including information such as dates, amounts, and item names.

[0355] "Natural language processing technology" is a technology that enables computers to understand and generate human language, and is used for dialogue and information provision.

[0356] "Emotion recognition technology" is a technology that analyzes and determines the emotional state of a user from their voice and visual data.

[0357] A "category" is a pre-defined classification used to organize extracted textual information, and it has a structure that includes various items related to finance.

[0358] "Financial advice" refers to recommendations and guidelines provided based on a user's financial situation, intended to support their economic decisions.

[0359] A "tax return format" is a format that organizes the information required for tax filing and complies with laws and regulations.

[0360] This invention is a system that electronically supports personal financial management. Users take photos of paper receipts and invoices using a device such as a smartphone or tablet. A dedicated application on the device has the function of transmitting the captured image data to a server in the cloud. The transmitted data is protected by a secure communication protocol.

[0361] The server uses Optical Character Recognition (OCR) technology as its image recognition technology. Specifically, a platform specialized in image processing is used as a common software example to extract text information from images. This allows the date, amount, and item name to be entered into the database.

[0362] Furthermore, the server utilizes emotion recognition technology to analyze emotions from the user's input text and voice data. This analysis combines speech processing and natural language processing technologies. Specifically, a general emotion engine is used for emotion analysis to determine whether the user is experiencing stress, among other things.

[0363] Furthermore, the server uses natural language processing technology to interact with the user. Generative AI models are utilized to respond instantly to user questions. For example, if a user asks, "My food expenses have been high lately, how can I save money?", the server will refer to past spending data, take the user's emotional state into consideration, and provide helpful information.

[0364] A possible example of a specific prompt message from the system would be, "Generate a conversational message that would offer gentle money-saving advice to a user who is feeling stressed." This system configuration would allow users to manage their finances efficiently and with emotional consideration.

[0365] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0366] Step 1:

[0367] Users take photos of receipts and invoices using their smartphones or tablets. The input is image data of the paper documents. The captured image data is set up to be automatically transferred to a cloud server via a dedicated application.

[0368] Step 2:

[0369] The terminal transmits image data to the server using a secure communication protocol. The input is image data on the terminal, and the output is a digital image stored on the cloud server. Through this transmission, the data is stored in a protected format for analysis processing on the server.

[0370] Step 3:

[0371] The server uses optical character recognition (OCR) technology to extract text information from received image data. The input is image data on the server, and the output is text information such as dates, amounts, and item names. OCR technology is used to extract text from images with high accuracy, and this data is stored in a database.

[0372] Step 4:

[0373] The server automatically classifies the extracted textual information. The input is textual information, and the output is the classification result into pre-defined financial categories (e.g., food expenses, transportation expenses, etc.). A rule-based system based on the textual information sorts the information into matching categories.

[0374] Step 5:

[0375] When a user sends text input or a voice message to the server, the server uses sentiment recognition technology to analyze the user's emotional state. The input is text or voice data from the user, and the output is the result of the sentiment analysis. This result is then used to provide subsequent financial advice.

[0376] Step 6:

[0377] The server uses natural language processing technology to generate financial advice for the user. The input consists of classified information and sentiment analysis data, and the output is financial advice expressed in a gentle, emotion-based manner. A generative AI model is used to construct a conversation based on prompt sentences.

[0378] Step 7:

[0379] The server sends the generated financial advice to the user's terminal. The input is the financial advice generated on the server, and the output is the advice message displayed on the user's terminal. This allows the user to manage their finances accurately while being mindful of their own emotions.

[0380] The above is the system's processing flow, and the coordinated interaction of each step enables effective financial management support.

[0381] (Application Example 2)

[0382] 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."

[0383] Personal financial management involves a wide range of tasks, from tracking daily expenses to preparing tax returns, and is often emotionally stressful. This makes it difficult for individuals to grasp and properly manage their overall financial situation. Furthermore, emotions often influence personal financial decisions, and existing systems lack consideration for these emotional factors. Addressing these challenges is crucial.

[0384] 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.

[0385] In this invention, the server includes means for extracting information from received image data, means for classifying the extracted information and automatically categorizing it into pre-set categories, and means for analyzing the user's emotions and adapting the content and expression of advice accordingly. This enables individuals to manage their finances effectively in an intuitive and emotionally responsive manner.

[0386] "Image recognition technology" is a technology that identifies and extracts specific information or features from digital images or videos.

[0387] "Natural language processing technology" is a technology that enables computers to understand, interpret, and generate human language, and is particularly important in human-computer interaction.

[0388] "Emotion recognition technology" is a technology that detects and analyzes a user's emotions from their voice or text, and can adjust responses and advice based on the results.

[0389] "Optical character recognition technology" is a technology that identifies characters within image data and converts them into digital text data.

[0390] A "tax return format" is a document that is automatically generated in a format that includes all necessary information, organized from financial information for tax filing purposes.

[0391] "Financial advice" refers to suggestions for improvement or savings methods provided based on the user's financial and emotional situation.

[0392] The system for implementing this invention uses a terminal such as a smartphone or smart glasses and a server. The terminal is responsible for transmitting image data of receipts and invoices taken by the user to the server. In this process, the smartphone's camera or a dedicated application is used.

[0393] The server performs the following processes: First, it uses optical character recognition (OCR), an image recognition technology, to extract information such as dates, amounts, and items from image data. Software such as Tesseract OCR is used for this process. The extracted information is automatically classified based on pre-configured categories. This makes it possible to efficiently manage the user's financial information.

[0394] Next, the server uses natural language processing technology to analyze user questions and inquiries and generate financial advice. This process utilizes the Google Cloud Natural Language API for user interaction. It also uses IBM Watson Tone Analyzer to analyze the user's emotions and adjust the content and wording of the advice accordingly. For example, if the system determines that the user is stressed, it will provide advice in a gentler, more reassuring tone.

[0395] For example, if a user asks, "I'm going on a trip next month and want to save money on food, do you have any good suggestions?", the system analyzes past spending data to identify the spending categories the user uses most often. Based on this, it then suggests realistic ways to save money based on sentiment analysis. For instance, it might say, "Looking at your recent spending, it seems you eat out a lot. For example, increasing the frequency of cooking at home might help you save money without feeling overwhelmed. Try to save money in a fun and relaxed way."

[0396] In this way, the system provided by the server creates an environment where users can effectively manage their finances without feeling emotionally burdened.

[0397] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0398] Step 1:

[0399] The user takes a picture of the receipt or invoice using their device.

[0400] Input: Paper receipts and invoices

[0401] Specific operation: Take an image with the camera of a smartphone or smart glasses and send the image data to the server via a dedicated application.

[0402] Step 2:

[0403] The server processes the received image data using optical character recognition (OCR) technology.

[0404] Input: Image data submitted by the user

[0405] Data processing: Use Tesseract OCR to extract text information (date, time, amount, item, etc.) from images.

[0406] Output: Extracted text information

[0407] Step 3:

[0408] The server categorizes the extracted text information.

[0409] Input: Extracted text information

[0410] Data processing: Automatically sorts information based on pre-defined categories.

[0411] Output: Categorized financial data

[0412] Step 4:

[0413] The user asks questions using natural language via a device.

[0414] Input: Questions via voice or text

[0415] Specific operation: Questions entered within the smartphone application are sent to the server.

[0416] Step 5:

[0417] The server uses emotion recognition technology to analyze the user's emotions.

[0418] Input: User questions and audio data

[0419] Data processing: Emotions are analyzed using IBM Watson Tone Analyzer to identify their state.

[0420] Output: Analyzed sentiment information

[0421] Step 6:

[0422] The server uses natural language processing technology to generate financial advice.

[0423] Input: Categorized financial data and analyzed sentiment information

[0424] Data processing: Analyze the question content using the Google Cloud Natural Language API and generate advice that takes sentiment into account.

[0425] Output: Financial advice that takes user emotions into consideration.

[0426] Step 7:

[0427] The server sends the generated advice to the user's terminal and displays it to the user.

[0428] Input: Generated financial advice

[0429] Specific action: Display advice to the user via an application on their smartphone.

[0430] Output: Displayed financial advice

[0431] 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.

[0432] 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.

[0433] 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.

[0434] [Third Embodiment]

[0435] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0436] 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.

[0437] 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).

[0438] 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.

[0439] 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.

[0440] 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).

[0441] 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.

[0442] 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.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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".

[0447] The present invention provides an advanced software system for simplifying personal expense management and tax filing. This system is implemented via a computer terminal such as a smartphone or tablet. Users use the terminal to take pictures of everyday receipts and invoices and send them via the internet to a dedicated messaging application. This application works in conjunction with a server to analyze the image data and process the collected information for accounting purposes.

[0448] The server uses image recognition technology to extract text information from received image data. The extracted text is automatically categorized into date, amount, expenditure category, etc. Images sent by users include various categories such as educational institutions, public facilities, food, and dining out, and are sorted appropriately according to each category.

[0449] The terminal is equipped with a front-end interface for managing the user's financial activities, where the user can review and modify their spending. The server also utilizes natural language processing technology to generate financial advice based on the user's financial data. For example, if a user's spending increases in a particular month, it provides advice on the causes and areas for improvement.

[0450] During tax filing season, the server aggregates the user's annual financial data and automatically generates the necessary documents for tax filing. This feature allows users to easily file their taxes without having to perform detailed accounting themselves.

[0451] For example, if a user wants to record a restaurant payment, they simply need to take a picture of the receipt and upload it to the application. The server classifies the image as "dining expenses" and provides the user with advice, including the percentage of that expense within the month's spending and a comparison with past data. In this way, the system of the present invention efficiently manages everyday economic activities and contributes to improving individuals' financial literacy.

[0452] The following describes the processing flow.

[0453] Step 1:

[0454] Users take photos of receipts and invoices using their device's camera and upload the image data to a dedicated messaging application.

[0455] Step 2:

[0456] The device sends image data to the LINE server, where it undergoes encoding processing for communication. This process includes checking the image format and, if necessary, compressing it.

[0457] Step 3:

[0458] The server analyzes the received image data. First, it uses optical character recognition (OCR) technology to extract text information from the image.

[0459] Step 4:

[0460] The server analyzes the extracted text information and classifies it into categories such as date, amount, and category (e.g., food and beverage expenses, transportation expenses). Based on this classification, it records the information in an accounting database.

[0461] Step 5:

[0462] The natural language processing AI on the server analyzes recorded data and generates appropriate financial advice for the user. In doing so, it takes into account the user's past data and market trends to provide the most optimal advice.

[0463] Step 6:

[0464] Users receive advice and analysis results from the server via the LINE application. If the user has further questions, they can enter their questions again in natural language, and the server will provide additional information.

[0465] Step 7:

[0466] The server aggregates users' income and expense data at the end of the fiscal year and automatically generates the necessary documents for filing tax returns. This allows users to easily prepare tax return documents and streamline the filing process.

[0467] (Example 1)

[0468] 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."

[0469] Managing personal finances in modern times is a time-consuming and complex task, encompassing a wide range of activities such as organizing receipts and invoices, classifying expenses, and preparing data for tax returns. Furthermore, these tasks require specialized knowledge, and accounting and tax filing, in particular, are difficult for many people. In this context, there is a need for a system that allows individuals to easily manage their finances and access financial advice.

[0470] 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.

[0471] In this invention, the server includes means for acquiring textual information from received digital data using image analysis means, means for classifying the acquired textual information and automatically categorizing it based on pre-set categories, and means for generating and providing financial advice to the user based on the classified information using natural language processing technology. As a result, users can manage their finances without hassle, easily grasp their financial situation without specialized knowledge, and receive advice for improvement.

[0472] "Image analysis means" refers to technologies and methods for obtaining textual information from received digital data.

[0473] "Textual information" refers to text data such as dates, numbers, and item names obtained from images and digital data.

[0474] A "category" refers to a classification item that has been pre-set for classifying the acquired text information.

[0475] "Natural language processing technology" refers to a set of technologies that generate financial advice in a form understandable to the user, based on textual information.

[0476] "Journaling" refers to the process of organizing and classifying acquired textual information based on pre-defined categories.

[0477] "Financial advice" refers to information that analyzes a user's financial situation based on acquired and categorized textual information, and provides suggestions and guidance for improvement.

[0478] This invention is a system for facilitating personal financial management and is primarily implemented through the cooperation of a server and a terminal.

[0479] Users take photos of everyday receipts and invoices using devices such as smartphones and tablets. The captured images are sent to a server via a dedicated application. The application provides a user-friendly interface, making it easy to upload images.

[0480] The server uses general-purpose image analysis techniques for image recognition. For example, it uses OCR technology to extract text information from images. The extracted text information is classified into data such as date, amount, and expenditure category. This allows for efficient organization of received digital data.

[0481] Furthermore, the server utilizes natural language processing technology to generate financial advice for the user. For example, it can provide specific advice such as, "Your food and beverage expenses have increased this month. Please consider ways to save money." The generated information is sent to the terminal application and notified to the user in real time.

[0482] The device features a financial management interface, allowing users to review collected information and make corrections if necessary. It also displays graphs and charts to visualize the user's financial situation, providing an easy-to-use dashboard.

[0483] For example, if a user wants to record a restaurant payment, they take a picture of the receipt with their device and upload the image to the application. The server retrieves the necessary information from the image and automatically categorizes it as "dining." The user then compares this to their past spending data and receives advice on how to manage future spending.

[0484] Examples of prompts include "Please tell me about your spending this month" and "What caused the increase in your food and beverage expenses?", which allow users to receive advanced financial analysis through a generated AI model.

[0485] This system makes it easy for individuals to manage their finances without specialized knowledge, and also simplifies tax filing.

[0486] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0487] Step 1:

[0488] The user launches the device's camera application and takes a picture of a receipt or invoice. The input is a paper receipt, and the output is a digital image file. The image is saved in JPEG or PNG format and passed on to the next processing step.

[0489] Step 2:

[0490] The device uploads captured image files to the server via a dedicated messaging application. When the user selects an image within the application and presses the send button, the input image data is sent to the server via the internet. The output is the received image data, ready for analysis by the server.

[0491] Step 3:

[0492] The server applies image analysis technology to the received image data. Specifically, it uses an OCR (Optical Character Recognition) engine to extract text information from the image. The input is the received image data, and the output is the extracted text information, which includes information such as the date, amount, and store name.

[0493] Step 4:

[0494] The server automatically categorizes extracted text information into pre-defined categories (e.g., food and drink, transportation, education). The input is extracted text information, and the output is data organized by category. Each item is appropriately categorized using rule-based or machine learning-based classification algorithms.

[0495] Step 5:

[0496] The server uses organized data and natural language processing techniques to generate financial advice for the user. The input is categorized financial data, and the output is advice in a human-readable format. The generated advice includes monthly spending trends and suggestions for future improvements.

[0497] Step 6:

[0498] The terminal displays advice messages and organized financial data sent from the server to the user. Through the terminal's interface, the user can review their spending and compare it to past data. Input is response data from the server, and output is visual data such as graphs and charts presented to the user. The user can also modify the data as needed.

[0499] (Application Example 1)

[0500] 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."

[0501] There is a need to provide a system that reduces the burden of daily expense management and tax filing, and that can automatically classify and analyze expense information, especially in the case of electronic payments. Existing methods have problems such as the effort required for users to manually input and verify information, and insufficient analysis and management of expenses, so improvements are needed.

[0502] 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.

[0503] In this invention, the server includes means for extracting textual information from received image data using image recognition technology, means for classifying the extracted textual information and automatically sorting it into pre-set classifications, and means for generating and transmitting financial advice to the user based on the classified information using natural language processing technology. This enables users to automatically manage their spending by using electronic payments and to efficiently perform monthly analysis and budget management.

[0504] "Image recognition technology" is a technology that automatically detects and extracts specific information from image data acquired using cameras and sensors.

[0505] "Textual information" refers to text data extracted from image data, including specific information such as dates, amounts, and names.

[0506] "Classification" is the process of organizing extracted information according to predefined categories or types.

[0507] "Natural language processing technology" is a technology that enables computers to understand and process human language, and it is also applied to the generation of advice.

[0508] "Means for generating and transmitting advice" refers to a method for creating and providing specific financial advice to users.

[0509] "Means of managing expense details" refers to methods for recording information such as the date, amount, and category of a transaction, and allowing users to review and modify it.

[0510] "Expenditure analysis and budget management" is the process of analyzing users' spending data, evaluating consumption trends, suggesting areas for improvement, and planning and managing budgets.

[0511] The system for realizing this invention involves a smartphone or tablet working in conjunction with a server possessing advanced analytical capabilities. The terminal is used by the user for everyday payments, and when electronic payment is made, it has a function to automatically capture an image of the receipt. The server receives this image data, performs image recognition using the Google Cloud Vision API, and extracts text information. The extracted text information is analyzed by a natural language processing system running in a Node.js environment and classified into expenditure categories. The classified data is stored in MongoDB, and users can easily access and manage it through a frontend developed with React Native.

[0512] The server analyzes monthly spending and generates advice for budget management. This includes comparing past spending patterns with current spending and providing tips for improvement and savings.

[0513] For example, when a user dines at a restaurant, the receipt is automatically photographed at the time of payment and categorized as "food and beverage expenses." At the end of the month, the server uses this data to send a notification asking whether the food expenses are within budget.

[0514] By utilizing a generative AI model, it is possible to receive inquiries from users and generate answers in response to prompts such as "What is the total amount of food expenses for this month?".

[0515] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0516] Step 1:

[0517] The terminal automatically captures an image of the receipt when the user completes an electronic payment. The input is the electronic payment completion signal, and the output is the captured receipt image data. This image data is usually saved to the terminal in JPEG or PNG format.

[0518] Step 2:

[0519] The terminal sends receipt image data to the server via the internet. The input is the image data generated in step 1, and the output is the image data sent to the server. The HTTPS protocol is used for this communication to securely transfer the data.

[0520] Step 3:

[0521] The server uses the Google Cloud Vision API to extract text information from received image data. The input is receipt image data, and the output is extracted text information. This text information includes the date, amount, store name, etc. The API uses OCR technology to detect the text.

[0522] Step 4:

[0523] The server uses a natural language processing system running in a Node.js environment to analyze extracted text information and classify it into the appropriate expenditure category. The input is text information, and the output is category information and text information. For example, if the name of a restaurant is "restaurant", it will be classified as "food expenses".

[0524] Step 5:

[0525] The server stores the analyzed and categorized spending data in MongoDB. This database records the details of each user transaction and is used later for analysis and reference. The input is category information and text information, and the output is the record stored in the database.

[0526] Step 6:

[0527] Users can view their spending data in real time through an app implemented with React Native, and edit or modify it as needed. Input is the user's actions (e.g., changing categories), and output is the updated spending data. This interface features an intuitive and user-friendly design.

[0528] Step 7:

[0529] The server analyzes monthly spending patterns and generates and sends budget management advice to the user. The input is historical spending data stored in a database, and the output is an advice message. The advice message is processed by a generative AI model and expressed in natural language.

[0530] Step 8:

[0531] Users can ask questions within the app using prompts and receive real-time answers based on a generative AI model. The input is the prompt from the user, and the output is the answer from the AI ​​model. For example, in response to a question like "What is the total amount spent on food this month?", the system will provide information on the total amount based on the latest data.

[0532] 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.

[0533] This invention is an advanced system for assisting personal financial management, realized by combining image recognition technology, natural language processing technology, and an emotion engine. The system includes the user's terminal, processing functions on a server, and interaction with the user.

[0534] Users use devices such as smartphones or tablets to take pictures of receipts and invoices, and send the images to a server through a dedicated application. Upon receiving the image data, the server uses optical character recognition (OCR) technology to extract text information, including the date, amount, and item, from the image and automatically categorizes it into pre-configured categories.

[0535] Furthermore, this system incorporates an emotion engine that recognizes the user's emotions from their text input, video calls, and voice. Based on this emotion data, the server adjusts the content and wording of financial advice given to the user. For example, if the user is feeling stressed, the advice can be given using gentle language to help them calm down.

[0536] Using natural language processing technology, the server continuously interacts with the user. When a user asks a question to the system, the server considers the emotional context and dynamically creates a response. This feature helps users feel comfortable receiving advice and having their questions answered.

[0537] For example, if a user asks, "My food expenses have been high lately, how can I save money?", the server can analyze past spending data while also considering the user's current emotional state, and gently suggest recommended ways to save money. In this way, the present invention supports the improvement of personal financial literacy and asset management while being attentive to the user's emotions.

[0538] The following describes the processing flow.

[0539] Step 1:

[0540] Users take photos of receipts and invoices with their devices and send the image data to the server via a dedicated application.

[0541] Step 2:

[0542] To analyze the image data received by the server, optical character recognition (OCR) technology is used to extract text information from the image, including the date, amount, and category.

[0543] Step 3:

[0544] The server analyzes the extracted text information, automatically categorizes it into predefined categories (e.g., food and beverage expenses, transportation expenses), and stores it in a database.

[0545] Step 4:

[0546] The device receives input from the user. For example, the user may ask a question or seek advice via text or voice.

[0547] Step 5:

[0548] The server interprets user input using natural language processing technology to understand the user's inquiry. During this process, an emotion engine identifies emotions from the user's text and voice.

[0549] Step 6:

[0550] The server generates personalized financial advice based on the results of the emotion engine. It adjusts the content and tone of the advice according to the user's emotions, creating a personalized message.

[0551] Step 7:

[0552] The terminal notifies the user of advice provided by the server. The user then considers actions to improve their financial management based on this feedback.

[0553] Step 8:

[0554] The server aggregates user data annually and prepares to automatically generate tax returns. This data is used when users file their tax returns.

[0555] (Example 2)

[0556] 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."

[0557] In personal financial management, efficiently extracting information from paper receipts and invoices and accurately recording and classifying it is a time-consuming and laborious task. Furthermore, providing appropriate financial advice that takes user emotions into account presents a challenge. Additionally, there is a need to simplify the management of daily financial information and the generation of data for tax filing.

[0558] 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.

[0559] In this invention, the server includes means for extracting textual information from received visual information using image recognition technology, means for classifying the extracted textual information and automatically sorting it into pre-set categories, and means for analyzing the user's emotional state using emotion recognition technology and adjusting the content and expression of financial advice. This makes it possible to efficiently manage paper-based information in digital format and provide timely advice that takes the user's emotions into consideration.

[0560] "Image recognition technology" is a technology that processes visual information as digital data and extracts and recognizes specific patterns or character information.

[0561] "Textual information" refers to text data extracted from visual information, including information such as dates, amounts, and item names.

[0562] "Natural language processing technology" is a technology that enables computers to understand and generate human language, and is used for dialogue and information provision.

[0563] "Emotion recognition technology" is a technology that analyzes and determines the emotional state of a user from their voice and visual data.

[0564] A "category" is a pre-defined classification used to organize extracted textual information, and it has a structure that includes various items related to finance.

[0565] "Financial advice" refers to recommendations and guidelines provided based on a user's financial situation, intended to support their economic decisions.

[0566] A "tax return format" is a format that organizes the information required for tax filing and complies with laws and regulations.

[0567] This invention is a system that electronically supports personal financial management. Users take photos of paper receipts and invoices using a device such as a smartphone or tablet. A dedicated application on the device has the function of transmitting the captured image data to a server in the cloud. The transmitted data is protected by a secure communication protocol.

[0568] The server uses Optical Character Recognition (OCR) technology as its image recognition technology. Specifically, a platform specialized in image processing is used as a common software example to extract text information from images. This allows the date, amount, and item name to be entered into the database.

[0569] Furthermore, the server utilizes emotion recognition technology to analyze emotions from the user's input text and voice data. This analysis combines speech processing and natural language processing technologies. Specifically, a general emotion engine is used for emotion analysis to determine whether the user is experiencing stress, among other things.

[0570] Furthermore, the server uses natural language processing technology to interact with the user. Generative AI models are utilized to respond instantly to user questions. For example, if a user asks, "My food expenses have been high lately, how can I save money?", the server will refer to past spending data, take the user's emotional state into consideration, and provide helpful information.

[0571] A possible example of a specific prompt message from the system would be, "Generate a conversational message that would offer gentle money-saving advice to a user who is feeling stressed." This system configuration would allow users to manage their finances efficiently and with emotional consideration.

[0572] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0573] Step 1:

[0574] Users take photos of receipts and invoices using their smartphones or tablets. The input is image data of the paper documents. The captured image data is set up to be automatically transferred to a cloud server via a dedicated application.

[0575] Step 2:

[0576] The terminal transmits image data to the server using a secure communication protocol. The input is image data on the terminal, and the output is a digital image stored on the cloud server. Through this transmission, the data is stored in a protected format for analysis processing on the server.

[0577] Step 3:

[0578] The server uses optical character recognition (OCR) technology to extract text information from received image data. The input is image data on the server, and the output is text information such as dates, amounts, and item names. OCR technology is used to extract text from images with high accuracy, and this data is stored in a database.

[0579] Step 4:

[0580] The server automatically classifies the extracted textual information. The input is textual information, and the output is the classification result into pre-defined financial categories (e.g., food expenses, transportation expenses, etc.). A rule-based system based on the textual information sorts the information into matching categories.

[0581] Step 5:

[0582] When a user sends text input or a voice message to the server, the server uses sentiment recognition technology to analyze the user's emotional state. The input is text or voice data from the user, and the output is the result of the sentiment analysis. This result is then used to provide subsequent financial advice.

[0583] Step 6:

[0584] The server uses natural language processing technology to generate financial advice for the user. The input consists of classified information and sentiment analysis data, and the output is financial advice expressed in a gentle, emotion-based manner. A generative AI model is used to construct a conversation based on prompt sentences.

[0585] Step 7:

[0586] The server sends the generated financial advice to the user's terminal. The input is the financial advice generated on the server, and the output is the advice message displayed on the user's terminal. This allows the user to manage their finances accurately while being mindful of their own emotions.

[0587] The above is the system's processing flow, and the coordinated interaction of each step enables effective financial management support.

[0588] (Application Example 2)

[0589] 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."

[0590] Personal financial management involves a wide range of tasks, from tracking daily expenses to preparing tax returns, and is often emotionally stressful. This makes it difficult for individuals to grasp and properly manage their overall financial situation. Furthermore, emotions often influence personal financial decisions, and existing systems lack consideration for these emotional factors. Addressing these challenges is crucial.

[0591] 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.

[0592] In this invention, the server includes means for extracting information from received image data, means for classifying the extracted information and automatically categorizing it into pre-set categories, and means for analyzing the user's emotions and adapting the content and expression of advice accordingly. This enables individuals to manage their finances effectively in an intuitive and emotionally responsive manner.

[0593] "Image recognition technology" is a technology that identifies and extracts specific information or features from digital images or videos.

[0594] "Natural language processing technology" is a technology that enables computers to understand, interpret, and generate human language, and is particularly important in human-computer interaction.

[0595] "Emotion recognition technology" is a technology that detects and analyzes a user's emotions from their voice or text, and can adjust responses and advice based on the results.

[0596] "Optical character recognition technology" is a technology that identifies characters within image data and converts them into digital text data.

[0597] A "tax return format" is a document that is automatically generated in a format that includes all necessary information, organized from financial information for tax filing purposes.

[0598] "Financial advice" refers to suggestions for improvement or savings methods provided based on the user's financial and emotional situation.

[0599] The system for implementing this invention uses a terminal such as a smartphone or smart glasses and a server. The terminal is responsible for transmitting image data of receipts and invoices taken by the user to the server. In this process, the smartphone's camera or a dedicated application is used.

[0600] The server performs the following processes: First, it uses optical character recognition (OCR), an image recognition technology, to extract information such as dates, amounts, and items from image data. Software such as Tesseract OCR is used for this process. The extracted information is automatically classified based on pre-configured categories. This makes it possible to efficiently manage the user's financial information.

[0601] Next, the server uses natural language processing technology to analyze user questions and inquiries and generate financial advice. This process utilizes the Google Cloud Natural Language API for user interaction. It also uses IBM Watson Tone Analyzer to analyze the user's emotions and adjust the content and wording of the advice accordingly. For example, if the system determines that the user is stressed, it will provide advice in a gentler, more reassuring tone.

[0602] For example, if a user asks, "I'm going on a trip next month and want to save money on food, do you have any good suggestions?", the system analyzes past spending data to identify the spending categories the user uses most often. Based on this, it then suggests realistic ways to save money based on sentiment analysis. For instance, it might say, "Looking at your recent spending, it seems you eat out a lot. For example, increasing the frequency of cooking at home might help you save money without feeling overwhelmed. Try to save money in a fun and relaxed way."

[0603] In this way, the system provided by the server creates an environment where users can effectively manage their finances without feeling emotionally burdened.

[0604] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0605] Step 1:

[0606] The user takes a picture of the receipt or invoice using their device.

[0607] Input: Paper receipts and invoices

[0608] Specific operation: Take an image with the camera of a smartphone or smart glasses and send the image data to the server via a dedicated application.

[0609] Step 2:

[0610] The server processes the received image data using optical character recognition (OCR) technology.

[0611] Input: Image data submitted by the user

[0612] Data processing: Use Tesseract OCR to extract text information (date, time, amount, item, etc.) from images.

[0613] Output: Extracted text information

[0614] Step 3:

[0615] The server categorizes the extracted text information.

[0616] Input: Extracted text information

[0617] Data processing: Automatically sorts information based on pre-defined categories.

[0618] Output: Categorized financial data

[0619] Step 4:

[0620] The user asks questions using natural language via a device.

[0621] Input: Questions via voice or text

[0622] Specific operation: Questions entered within the smartphone application are sent to the server.

[0623] Step 5:

[0624] The server uses emotion recognition technology to analyze the user's emotions.

[0625] Input: User questions and audio data

[0626] Data processing: Emotions are analyzed using IBM Watson Tone Analyzer to identify their state.

[0627] Output: Analyzed sentiment information

[0628] Step 6:

[0629] The server uses natural language processing technology to generate financial advice.

[0630] Input: Categorized financial data and analyzed sentiment information

[0631] Data processing: Analyze the question content using the Google Cloud Natural Language API and generate advice that takes sentiment into account.

[0632] Output: Financial advice that takes user emotions into consideration.

[0633] Step 7:

[0634] The server sends the generated advice to the user's terminal and displays it to the user.

[0635] Input: Generated financial advice

[0636] Specific action: Display advice to the user via an application on their smartphone.

[0637] Output: Displayed financial advice

[0638] 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.

[0639] 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.

[0640] 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.

[0641] [Fourth Embodiment]

[0642] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0643] 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.

[0644] 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).

[0645] 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.

[0646] 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.

[0647] 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).

[0648] 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.

[0649] 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 in 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.

[0650] 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.

[0651] 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.

[0652] 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.

[0653] 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.

[0654] 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".

[0655] The present invention provides an advanced software system for simplifying personal expense management and tax filing. This system is implemented via a computer terminal such as a smartphone or tablet. Users use the terminal to take pictures of everyday receipts and invoices and send them via the internet to a dedicated messaging application. This application works in conjunction with a server to analyze the image data and process the collected information for accounting purposes.

[0656] The server uses image recognition technology to extract text information from received image data. The extracted text is automatically categorized into date, amount, expenditure category, etc. Images sent by users include various categories such as educational institutions, public facilities, food, and dining out, and are sorted appropriately according to each category.

[0657] The terminal is equipped with a front-end interface for managing the user's financial activities, where the user can review and modify their spending. The server also utilizes natural language processing technology to generate financial advice based on the user's financial data. For example, if a user's spending increases in a particular month, it provides advice on the causes and areas for improvement.

[0658] During tax filing season, the server aggregates the user's annual financial data and automatically generates the necessary documents for tax filing. This feature allows users to easily file their taxes without having to perform detailed accounting themselves.

[0659] For example, if a user wants to record a restaurant payment, they simply need to take a picture of the receipt and upload it to the application. The server classifies the image as "dining expenses" and provides the user with advice, including the percentage of that expense within the month's spending and a comparison with past data. In this way, the system of the present invention efficiently manages everyday economic activities and contributes to improving individuals' financial literacy.

[0660] The following describes the processing flow.

[0661] Step 1:

[0662] Users take photos of receipts and invoices using their device's camera and upload the image data to a dedicated messaging application.

[0663] Step 2:

[0664] The device sends image data to the LINE server, where it undergoes encoding processing for communication. This process includes checking the image format and, if necessary, compressing it.

[0665] Step 3:

[0666] The server analyzes the received image data. First, it uses optical character recognition (OCR) technology to extract text information from the image.

[0667] Step 4:

[0668] The server analyzes the extracted text information and classifies it into categories such as date, amount, and category (e.g., food and beverage expenses, transportation expenses). Based on this classification, it records the information in an accounting database.

[0669] Step 5:

[0670] The natural language processing AI on the server analyzes recorded data and generates appropriate financial advice for the user. In doing so, it takes into account the user's past data and market trends to provide the most optimal advice.

[0671] Step 6:

[0672] Users receive advice and analysis results from the server via the LINE application. If the user has further questions, they can enter their questions again in natural language, and the server will provide additional information.

[0673] Step 7:

[0674] The server aggregates users' income and expense data at the end of the fiscal year and automatically generates the necessary documents for filing tax returns. This allows users to easily prepare tax return documents and streamline the filing process.

[0675] (Example 1)

[0676] 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".

[0677] Managing personal finances in modern times is a time-consuming and complex task, encompassing a wide range of activities such as organizing receipts and invoices, classifying expenses, and preparing data for tax returns. Furthermore, these tasks require specialized knowledge, and accounting and tax filing, in particular, are difficult for many people. In this context, there is a need for a system that allows individuals to easily manage their finances and access financial advice.

[0678] 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.

[0679] In this invention, the server includes means for acquiring textual information from received digital data using image analysis means, means for classifying the acquired textual information and automatically categorizing it based on pre-set categories, and means for generating and providing financial advice to the user based on the classified information using natural language processing technology. As a result, users can manage their finances without hassle, easily grasp their financial situation without specialized knowledge, and receive advice for improvement.

[0680] "Image analysis means" refers to technologies and methods for obtaining textual information from received digital data.

[0681] "Textual information" refers to text data such as dates, numbers, and item names obtained from images and digital data.

[0682] A "category" refers to a classification item that has been pre-set for classifying the acquired text information.

[0683] "Natural language processing technology" refers to a set of technologies that generate financial advice in a form understandable to the user, based on textual information.

[0684] "Journaling" refers to the process of organizing and classifying acquired textual information based on pre-defined categories.

[0685] "Financial advice" refers to information that analyzes a user's financial situation based on acquired and categorized textual information, and provides suggestions and guidance for improvement.

[0686] This invention is a system for facilitating personal financial management and is primarily implemented through the cooperation of a server and a terminal.

[0687] Users take photos of everyday receipts and invoices using devices such as smartphones and tablets. The captured images are sent to a server via a dedicated application. The application provides a user-friendly interface, making it easy to upload images.

[0688] The server uses general-purpose image analysis techniques for image recognition. For example, it uses OCR technology to extract text information from images. The extracted text information is classified into data such as date, amount, and expenditure category. This allows for efficient organization of received digital data.

[0689] Furthermore, the server utilizes natural language processing technology to generate financial advice for the user. For example, it can provide specific advice such as, "Your food and beverage expenses have increased this month. Please consider ways to save money." The generated information is sent to the terminal application and notified to the user in real time.

[0690] The device features a financial management interface, allowing users to review collected information and make corrections if necessary. It also displays graphs and charts to visualize the user's financial situation, providing an easy-to-use dashboard.

[0691] For example, if a user wants to record a restaurant payment, they take a picture of the receipt with their device and upload the image to the application. The server retrieves the necessary information from the image and automatically categorizes it as "dining." The user then compares this to their past spending data and receives advice on how to manage future spending.

[0692] Examples of prompts include "Please tell me about your spending this month" and "What caused the increase in your food and beverage expenses?", which allow users to receive advanced financial analysis through a generated AI model.

[0693] This system makes it easy for individuals to manage their finances without specialized knowledge, and also simplifies tax filing.

[0694] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0695] Step 1:

[0696] The user launches the device's camera application and takes a picture of a receipt or invoice. The input is a paper receipt, and the output is a digital image file. The image is saved in JPEG or PNG format and passed on to the next processing step.

[0697] Step 2:

[0698] The device uploads captured image files to the server via a dedicated messaging application. When the user selects an image within the application and presses the send button, the input image data is sent to the server via the internet. The output is the received image data, ready for analysis by the server.

[0699] Step 3:

[0700] The server applies image analysis technology to the received image data. Specifically, it uses an OCR (Optical Character Recognition) engine to extract text information from the image. The input is the received image data, and the output is the extracted text information, which includes information such as the date, amount, and store name.

[0701] Step 4:

[0702] The server automatically categorizes extracted text information into pre-defined categories (e.g., food and drink, transportation, education). The input is extracted text information, and the output is data organized by category. Each item is appropriately categorized using rule-based or machine learning-based classification algorithms.

[0703] Step 5:

[0704] The server uses organized data and natural language processing techniques to generate financial advice for the user. The input is categorized financial data, and the output is advice in a human-readable format. The generated advice includes monthly spending trends and suggestions for future improvements.

[0705] Step 6:

[0706] The terminal displays advice messages and organized financial data sent from the server to the user. Through the terminal's interface, the user can review their spending and compare it to past data. Input is response data from the server, and output is visual data such as graphs and charts presented to the user. The user can also modify the data as needed.

[0707] (Application Example 1)

[0708] 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".

[0709] There is a need to provide a system that reduces the burden of daily expense management and tax filing, and that can automatically classify and analyze expense information, especially in the case of electronic payments. Existing methods have problems such as the effort required for users to manually input and verify information, and insufficient analysis and management of expenses, so improvements are needed.

[0710] 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.

[0711] In this invention, the server includes means for extracting textual information from received image data using image recognition technology, means for classifying the extracted textual information and automatically sorting it into pre-set classifications, and means for generating and transmitting financial advice to the user based on the classified information using natural language processing technology. This enables users to automatically manage their spending by using electronic payments and to efficiently perform monthly analysis and budget management.

[0712] "Image recognition technology" is a technology that automatically detects and extracts specific information from image data acquired using cameras and sensors.

[0713] "Textual information" refers to text data extracted from image data, including specific information such as dates, amounts, and names.

[0714] "Classification" is the process of organizing extracted information according to predefined categories or types.

[0715] "Natural language processing technology" is a technology that enables computers to understand and process human language, and it is also applied to the generation of advice.

[0716] "Means for generating and transmitting advice" refers to a method for creating and providing specific financial advice to users.

[0717] "Means of managing expense details" refers to methods for recording information such as the date, amount, and category of a transaction, and allowing users to review and modify it.

[0718] "Expenditure analysis and budget management" is the process of analyzing users' spending data, evaluating consumption trends, suggesting areas for improvement, and planning and managing budgets.

[0719] The system for realizing this invention involves a smartphone or tablet working in conjunction with a server possessing advanced analytical capabilities. The terminal is used by the user for everyday payments, and when electronic payment is made, it has a function to automatically capture an image of the receipt. The server receives this image data, performs image recognition using the Google Cloud Vision API, and extracts text information. The extracted text information is analyzed by a natural language processing system running in a Node.js environment and classified into expenditure categories. The classified data is stored in MongoDB, and users can easily access and manage it through a frontend developed with React Native.

[0720] The server analyzes monthly spending and generates advice for budget management. This includes comparing past spending patterns with current spending and providing tips for improvement and savings.

[0721] For example, when a user dines at a restaurant, the receipt is automatically photographed at the time of payment and categorized as "food and beverage expenses." At the end of the month, the server uses this data to send a notification asking whether the food expenses are within budget.

[0722] By utilizing a generative AI model, it is possible to receive inquiries from users and generate answers in response to prompts such as "What is the total amount of food expenses for this month?".

[0723] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0724] Step 1:

[0725] The terminal automatically captures an image of the receipt when the user completes an electronic payment. The input is the electronic payment completion signal, and the output is the captured receipt image data. This image data is usually saved to the terminal in JPEG or PNG format.

[0726] Step 2:

[0727] The terminal sends receipt image data to the server via the internet. The input is the image data generated in step 1, and the output is the image data sent to the server. The HTTPS protocol is used for this communication to securely transfer the data.

[0728] Step 3:

[0729] The server uses the Google Cloud Vision API to extract text information from received image data. The input is receipt image data, and the output is extracted text information. This text information includes the date, amount, store name, etc. The API uses OCR technology to detect the text.

[0730] Step 4:

[0731] The server uses a natural language processing system running in a Node.js environment to analyze extracted text information and classify it into the appropriate expenditure category. The input is text information, and the output is category information and text information. For example, if the name of a restaurant is "restaurant", it will be classified as "food expenses".

[0732] Step 5:

[0733] The server stores the analyzed and categorized spending data in MongoDB. This database records the details of each user transaction and is used later for analysis and reference. The input is category information and text information, and the output is the record stored in the database.

[0734] Step 6:

[0735] Users can view their spending data in real time through an app implemented with React Native, and edit or modify it as needed. Input is the user's actions (e.g., changing categories), and output is the updated spending data. This interface features an intuitive and user-friendly design.

[0736] Step 7:

[0737] The server analyzes monthly spending patterns and generates and sends budget management advice to the user. The input is historical spending data stored in a database, and the output is an advice message. The advice message is processed by a generative AI model and expressed in natural language.

[0738] Step 8:

[0739] Users can ask questions within the app using prompts and receive real-time answers based on a generative AI model. The input is the prompt from the user, and the output is the answer from the AI ​​model. For example, in response to a question like "What is the total amount spent on food this month?", the system will provide information on the total amount based on the latest data.

[0740] 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.

[0741] This invention is an advanced system for assisting personal financial management, realized by combining image recognition technology, natural language processing technology, and an emotion engine. The system includes the user's terminal, processing functions on a server, and interaction with the user.

[0742] Users use devices such as smartphones or tablets to take pictures of receipts and invoices, and send the images to a server through a dedicated application. Upon receiving the image data, the server uses optical character recognition (OCR) technology to extract text information, including the date, amount, and item, from the image and automatically categorizes it into pre-configured categories.

[0743] Furthermore, this system incorporates an emotion engine that recognizes the user's emotions from their text input, video calls, and voice. Based on this emotion data, the server adjusts the content and wording of financial advice given to the user. For example, if the user is feeling stressed, the advice can be given using gentle language to help them calm down.

[0744] Using natural language processing technology, the server continuously interacts with the user. When a user asks a question to the system, the server considers the emotional context and dynamically creates a response. This feature helps users feel comfortable receiving advice and having their questions answered.

[0745] For example, if a user asks, "My food expenses have been high lately, how can I save money?", the server can analyze past spending data while also considering the user's current emotional state, and gently suggest recommended ways to save money. In this way, the present invention supports the improvement of personal financial literacy and asset management while being attentive to the user's emotions.

[0746] The following describes the processing flow.

[0747] Step 1:

[0748] Users take photos of receipts and invoices with their devices and send the image data to the server via a dedicated application.

[0749] Step 2:

[0750] To analyze the image data received by the server, optical character recognition (OCR) technology is used to extract text information from the image, including the date, amount, and category.

[0751] Step 3:

[0752] The server analyzes the extracted text information, automatically categorizes it into predefined categories (e.g., food and beverage expenses, transportation expenses), and stores it in a database.

[0753] Step 4:

[0754] The device receives input from the user. For example, the user may ask a question or seek advice via text or voice.

[0755] Step 5:

[0756] The server interprets user input using natural language processing technology to understand the user's inquiry. During this process, an emotion engine identifies emotions from the user's text and voice.

[0757] Step 6:

[0758] The server generates personalized financial advice based on the results of the emotion engine. It adjusts the content and tone of the advice according to the user's emotions, creating a personalized message.

[0759] Step 7:

[0760] The terminal notifies the user of advice provided by the server. The user then considers actions to improve their financial management based on this feedback.

[0761] Step 8:

[0762] The server aggregates user data annually and prepares to automatically generate tax returns. This data is used when users file their tax returns.

[0763] (Example 2)

[0764] 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".

[0765] In personal financial management, efficiently extracting information from paper receipts and invoices and accurately recording and classifying it is a time-consuming and laborious task. Furthermore, providing appropriate financial advice that takes user emotions into account presents a challenge. Additionally, there is a need to simplify the management of daily financial information and the generation of data for tax filing.

[0766] 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.

[0767] In this invention, the server includes means for extracting textual information from received visual information using image recognition technology, means for classifying the extracted textual information and automatically sorting it into pre-set categories, and means for analyzing the user's emotional state using emotion recognition technology and adjusting the content and expression of financial advice. This makes it possible to efficiently manage paper-based information in digital format and provide timely advice that takes the user's emotions into consideration.

[0768] "Image recognition technology" is a technology that processes visual information as digital data and extracts and recognizes specific patterns or character information.

[0769] "Textual information" refers to text data extracted from visual information, including information such as dates, amounts, and item names.

[0770] "Natural language processing technology" is a technology that enables computers to understand and generate human language, and is used for dialogue and information provision.

[0771] "Emotion recognition technology" is a technology that analyzes and determines the emotional state of a user from their voice and visual data.

[0772] A "category" is a pre-defined classification used to organize extracted textual information, and it has a structure that includes various items related to finance.

[0773] "Financial advice" refers to recommendations and guidelines provided based on a user's financial situation, intended to support their economic decisions.

[0774] A "tax return format" is a format that organizes the information required for tax filing and complies with laws and regulations.

[0775] This invention is a system that electronically supports personal financial management. Users take photos of paper receipts and invoices using a device such as a smartphone or tablet. A dedicated application on the device has the function of transmitting the captured image data to a server in the cloud. The transmitted data is protected by a secure communication protocol.

[0776] The server uses Optical Character Recognition (OCR) technology as its image recognition technology. Specifically, a platform specialized in image processing is used as a common software example to extract text information from images. This allows the date, amount, and item name to be entered into the database.

[0777] Furthermore, the server utilizes emotion recognition technology to analyze emotions from the user's input text and voice data. This analysis combines speech processing and natural language processing technologies. Specifically, a general emotion engine is used for emotion analysis to determine whether the user is experiencing stress, among other things.

[0778] Furthermore, the server uses natural language processing technology to interact with the user. Generative AI models are utilized to respond instantly to user questions. For example, if a user asks, "My food expenses have been high lately, how can I save money?", the server will refer to past spending data, take the user's emotional state into consideration, and provide helpful information.

[0779] A possible example of a specific prompt message from the system would be, "Generate a conversational message that would offer gentle money-saving advice to a user who is feeling stressed." This system configuration would allow users to manage their finances efficiently and with emotional consideration.

[0780] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0781] Step 1:

[0782] Users take photos of receipts and invoices using their smartphones or tablets. The input is image data of the paper documents. The captured image data is set up to be automatically transferred to a cloud server via a dedicated application.

[0783] Step 2:

[0784] The terminal transmits image data to the server using a secure communication protocol. The input is image data on the terminal, and the output is a digital image stored on the cloud server. Through this transmission, the data is stored in a protected format for analysis processing on the server.

[0785] Step 3:

[0786] The server uses optical character recognition (OCR) technology to extract text information from received image data. The input is image data on the server, and the output is text information such as dates, amounts, and item names. OCR technology is used to extract text from images with high accuracy, and this data is stored in a database.

[0787] Step 4:

[0788] The server automatically classifies the extracted textual information. The input is textual information, and the output is the classification result into pre-defined financial categories (e.g., food expenses, transportation expenses, etc.). A rule-based system based on the textual information sorts the information into matching categories.

[0789] Step 5:

[0790] When a user sends text input or a voice message to the server, the server uses sentiment recognition technology to analyze the user's emotional state. The input is text or voice data from the user, and the output is the result of the sentiment analysis. This result is then used to provide subsequent financial advice.

[0791] Step 6:

[0792] The server uses natural language processing technology to generate financial advice for the user. The input consists of classified information and sentiment analysis data, and the output is financial advice expressed in a gentle, emotion-based manner. A generative AI model is used to construct a conversation based on prompt sentences.

[0793] Step 7:

[0794] The server sends the generated financial advice to the user's terminal. The input is the financial advice generated on the server, and the output is the advice message displayed on the user's terminal. This allows the user to manage their finances accurately while being mindful of their own emotions.

[0795] The above is the system's processing flow, and the coordinated interaction of each step enables effective financial management support.

[0796] (Application Example 2)

[0797] 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".

[0798] Personal financial management involves a wide range of tasks, from tracking daily expenses to preparing tax returns, and is often emotionally stressful. This makes it difficult for individuals to grasp and properly manage their overall financial situation. Furthermore, emotions often influence personal financial decisions, and existing systems lack consideration for these emotional factors. Addressing these challenges is crucial.

[0799] 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.

[0800] In this invention, the server includes means for extracting information from received image data, means for classifying the extracted information and automatically categorizing it into pre-set categories, and means for analyzing the user's emotions and adapting the content and expression of advice accordingly. This enables individuals to manage their finances effectively in an intuitive and emotionally responsive manner.

[0801] "Image recognition technology" is a technology that identifies and extracts specific information or features from digital images or videos.

[0802] "Natural language processing technology" is a technology that enables computers to understand, interpret, and generate human language, and is particularly important in human-computer interaction.

[0803] "Emotion recognition technology" is a technology that detects and analyzes a user's emotions from their voice or text, and can adjust responses and advice based on the results.

[0804] "Optical character recognition technology" is a technology that identifies characters within image data and converts them into digital text data.

[0805] A "tax return format" is a document that is automatically generated in a format that includes all necessary information, organized from financial information for tax filing purposes.

[0806] "Financial advice" refers to suggestions for improvement or savings methods provided based on the user's financial and emotional situation.

[0807] The system for implementing this invention uses a terminal such as a smartphone or smart glasses and a server. The terminal is responsible for transmitting image data of receipts and invoices taken by the user to the server. In this process, the smartphone's camera or a dedicated application is used.

[0808] The server performs the following processes: First, it uses optical character recognition (OCR), an image recognition technology, to extract information such as dates, amounts, and items from image data. Software such as Tesseract OCR is used for this process. The extracted information is automatically classified based on pre-configured categories. This makes it possible to efficiently manage the user's financial information.

[0809] Next, the server uses natural language processing technology to analyze user questions and inquiries and generate financial advice. This process utilizes the Google Cloud Natural Language API for user interaction. It also uses IBM Watson Tone Analyzer to analyze the user's emotions and adjust the content and wording of the advice accordingly. For example, if the system determines that the user is stressed, it will provide advice in a gentler, more reassuring tone.

[0810] For example, if a user asks, "I'm going on a trip next month and want to save money on food, do you have any good suggestions?", the system analyzes past spending data to identify the spending categories the user uses most often. Based on this, it then suggests realistic ways to save money based on sentiment analysis. For instance, it might say, "Looking at your recent spending, it seems you eat out a lot. For example, increasing the frequency of cooking at home might help you save money without feeling overwhelmed. Try to save money in a fun and relaxed way."

[0811] In this way, the system provided by the server creates an environment where users can effectively manage their finances without feeling emotionally burdened.

[0812] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0813] Step 1:

[0814] The user takes a picture of the receipt or invoice using their device.

[0815] Input: Paper receipts and invoices

[0816] Specific operation: Take an image with the camera of a smartphone or smart glasses and send the image data to the server via a dedicated application.

[0817] Step 2:

[0818] The server processes the received image data using optical character recognition (OCR) technology.

[0819] Input: Image data submitted by the user

[0820] Data processing: Use Tesseract OCR to extract text information (date, time, amount, item, etc.) from images.

[0821] Output: Extracted text information

[0822] Step 3:

[0823] The server categorizes the extracted text information.

[0824] Input: Extracted text information

[0825] Data processing: Automatically sorts information based on pre-defined categories.

[0826] Output: Categorized financial data

[0827] Step 4:

[0828] The user asks questions using natural language via a device.

[0829] Input: Questions via voice or text

[0830] Specific operation: Questions entered within the smartphone application are sent to the server.

[0831] Step 5:

[0832] The server uses emotion recognition technology to analyze the user's emotions.

[0833] Input: User questions and audio data

[0834] Data processing: Emotions are analyzed using IBM Watson Tone Analyzer to identify their state.

[0835] Output: Analyzed sentiment information

[0836] Step 6:

[0837] The server uses natural language processing technology to generate financial advice.

[0838] Input: Categorized financial data and analyzed sentiment information

[0839] Data processing: Analyze the question content using the Google Cloud Natural Language API and generate advice that takes sentiment into account.

[0840] Output: Financial advice that takes user emotions into consideration.

[0841] Step 7:

[0842] The server sends the generated advice to the user's terminal and displays it to the user.

[0843] Input: Generated financial advice

[0844] Specific action: Display advice to the user via an application on their smartphone.

[0845] Output: Displayed financial advice

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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."

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] The following is further disclosed regarding the embodiments described above.

[0868] (Claim 1)

[0869] A means for extracting text information from received image data using image recognition technology,

[0870] A means of classifying extracted text information and automatically sorting it into pre-defined categories,

[0871] A means for generating and transmitting financial advice to a user based on classified information using natural language processing technology,

[0872] A means of automatically generating the data required for the tax return format,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1, which uses optical character recognition technology to detect a date, amount, and item from received image data.

[0876] (Claim 3)

[0877] The system according to claim 1, which engages in dialogue with users in natural language and dynamically provides financial information.

[0878] "Example 1"

[0879] (Claim 1)

[0880] A means for obtaining character information from received digital data using image analysis means,

[0881] A means for classifying acquired text information and automatically sorting it based on pre-set categories,

[0882] A means of generating and providing financial advice to users based on classified information using natural language processing technology,

[0883] A means for automatically generating the information required for a prescribed declaration format,

[0884] A means of providing a screen that allows users to view and modify financial information in conjunction with a terminal,

[0885] A system that includes this.

[0886] (Claim 2)

[0887] The system according to claim 1, which uses character recognition technology to obtain a date, a number, and an item from received digital data.

[0888] (Claim 3)

[0889] The system according to claim 1, which engages in dialogue with users in natural language and dynamically provides financial information.

[0890] "Application Example 1"

[0891] (Claim 1)

[0892] A means for extracting text information from received image data using image recognition technology,

[0893] A means for classifying extracted text information and automatically sorting it into pre-set categories,

[0894] A means for generating and transmitting financial advice to users based on classified information using natural language processing technology,

[0895] A means of automatically generating the information necessary for the format of financial reports,

[0896] A method for automatically taking photos of receipt information at the time of payment and managing the details of expenses,

[0897] A means of providing monthly expenditure analysis and budget management,

[0898] A system that includes this.

[0899] (Claim 2)

[0900] The system according to claim 1, which uses optical character recognition technology to detect the date and time, amount, and type from received image data.

[0901] (Claim 3)

[0902] The system according to claim 1, which engages in conversation with users in natural language and dynamically provides financial information.

[0903] "Example 2 of combining an emotion engine"

[0904] (Claim 1)

[0905] A means for extracting textual information from received visual information using image recognition technology,

[0906] A means for classifying extracted text information and automatically sorting it into pre-defined categories,

[0907] A means for generating and transmitting financial advice to a user based on classified information using natural language processing technology,

[0908] A means of analyzing the user's emotional state using emotion recognition technology and adjusting the content and expression of financial advice,

[0909] A means of automatically generating the data required for filing tax returns,

[0910] A system that includes this.

[0911] (Claim 2)

[0912] The system according to claim 1, which uses optical character recognition technology to detect a date, amount, and item from received visual information.

[0913] (Claim 3)

[0914] The system according to claim 1, which engages in dialogue with users in natural language and dynamically provides financial information.

[0915] "Application example 2 when combining with an emotional engine"

[0916] (Claim 1)

[0917] A means for extracting information from received image data using image recognition technology,

[0918] A means of classifying the extracted information and automatically sorting it into pre-defined categories,

[0919] A means of generating and transmitting financial advice to an individual based on classified information using natural language processing technology,

[0920] Using emotion recognition technology to analyze the user's emotions, a means of adapting the content and expression of advice,

[0921] A means of automatically generating the information necessary for filing tax returns,

[0922] A system that includes this.

[0923] (Claim 2)

[0924] The system according to claim 1, which uses optical character recognition technology to detect time, numerical values, and content from received image data.

[0925] (Claim 3)

[0926] The system according to claim 1, which engages in dialogue with individuals in natural language, dynamically provides financial information, and takes emotion-based context into consideration. [Explanation of Symbols]

[0927] 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. A means for extracting text information from received image data using image recognition technology, A means of classifying extracted text information and automatically sorting it into pre-defined categories, A means for generating and transmitting financial advice to a user based on classified information using natural language processing technology, A means of automatically generating the data required for the tax return format, A system that includes this.

2. The system according to claim 1, which uses optical character recognition technology to detect the date, amount, and item from received image data.

3. The system according to claim 1, which engages in dialogue with users in natural language and dynamically provides financial information.

Images