system

Abstract

Provide a system. 【Solution means】 Means for obtaining information access rights from a user, Means for automatically collecting data via an interface for information exchange of a financial institution, Means for checking the integrity of the collected data and storing it in an information storage medium, Means for dividing the stored data into multiple classifications using a machine learning model, Means for automatically generating tax-related documents based on the classified data, Means for providing an interactive screen that allows a user to edit and confirm the generated tax-related documents, Means for electronically transmitting tax-related documents, Means for providing a function to notify daily expenditure status, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The creation of tax return documents is a process that takes time and effort for users. In particular, the process of collecting, organizing, and classifying financial information is complex. Also, entrusting an expert is costly. Therefore, there is a need for a system that can create return documents efficiently and at low cost, but currently there is no method that completely solves this problem.

Means for Solving the Problems

[0005] This invention provides a means for obtaining data access rights from users and automatically collecting transaction data through an application program interface of a financial institution. Furthermore, it maintains data integrity by including a function to check the integrity of the collected transaction data and store it in a database. Then, it achieves efficient data organization by classifying the stored transaction data into multiple categories using a machine learning algorithm. Finally, it automatically generates tax documents based on this classified data and provides an interface that users can edit and review, enabling users to easily create tax documents. Lastly, it completes the automated tax filing process by including a means for electronically submitting the generated tax documents.

[0006] "User" refers to an individual or organization that uses the system to prepare tax return documents.

[0007] "Data access permissions" refer to the permission that a user grants to a system to retrieve data from financial institutions or other sources.

[0008] "Financial institutions" refer to organizations that provide financial services, such as banks and credit card companies.

[0009] An "application program interface" refers to a set of protocols and tools that enable different computer programs to communicate with each other.

[0010] "Transaction data" refers to information related to financial transactions, including bank statements and credit card usage history.

[0011] A "machine learning algorithm" refers to a computational method that allows computers to learn from data and perform classification and predictions.

[0012] A "category" refers to a classification criterion or range used to organize data.

[0013] "Automatic generation" refers to the process by which documents and data are generated by a computer without human intervention.

[0014] "Interface" refers to the user interface or platform through which a user interacts with a system.

[0015] "Electronically submitted" refers to the process of sending or submitting documents using digital means such as the internet. [Brief explanation of the drawing]

[0016] [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]It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the language used in the following description will be explained.

[0019] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention provides a system for users to efficiently collect and classify financial information and automatically generate tax return documents. This system reduces the user's burden through multiple processing steps and creates highly accurate documents in a short amount of time.

[0038] First, the user accesses the system using a terminal. The user grants the system access rights to data from financial institutions whose financial information is collected. Through operations performed via the terminal, the system automatically retrieves transaction data from banks, credit card companies, and other financial institutions.

[0039] The server cleanses the retrieved transaction data through integrity checks, removing inconsistent data. The neatly organized data is stored in the database, ready for subsequent classification processing.

[0040] Next, the server uses machine learning algorithms to classify the data. By categorizing it by income, expenses, and customer, it facilitates data analysis. This classification model continuously learns and gradually improves its accuracy.

[0041] Based on the categorized data, the server automatically generates the necessary documents for tax filing. Users can review and edit the generated documents via their terminal and make any necessary adjustments. The interface is designed to be user-friendly, allowing for efficient editing.

[0042] Ultimately, the server electronically submits the user-verified documents to the tax authorities. This significantly reduces the time and cost associated with physical procedures for the user.

[0043] As a concrete example, consider a scenario where an accounting staff member at a certain company uses this system. The accounting staff member can automatically acquire monthly income and expense data and quickly generate other financial reports based on highly accurate analysis results. Automating this process significantly streamlines accounting tasks that were previously done manually, and reduces human error.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server receives the user's authentication information and obtains a token to access the financial institution's API. This allows the server to securely access the user's bank account and credit card information.

[0047] Step 2:

[0048] The server periodically retrieves transaction data from financial institutions' APIs based on a schedule, collecting the latest data. It can also collect new transaction data in real time if it is generated.

[0049] Step 3:

[0050] The system checks the integrity of transaction data retrieved by the server and filters out duplicate and incorrect data. Inconsistent data is logged, data cleaning is performed, and then the clean data is saved to the database.

[0051] Step 4:

[0052] The server processes the cleansed data in the database and performs automatic classification using machine learning models. For example, it analyzes the data using algorithms to classify it into categories such as income, expenses, and costs.

[0053] Step 5:

[0054] The device displays categorized data on a dashboard, allowing users to visually review the data. Users can interactively view revenue and expenditure trends and detailed information by category.

[0055] Step 6:

[0056] The server automatically generates the necessary documents for tax filing based on the classified data. Using standard templates, it creates documents that accurately reflect the collected data.

[0057] Step 7:

[0058] The user reviews the documents generated via the device and edits them as needed. They then save the edited data and prepare for the next step.

[0059] Step 8:

[0060] The server sends the finalized documents to the corresponding tax authority's electronic submission system, completing the submission process. It also notifies the user of the submission results and guides them through the necessary next steps.

[0061] (Example 1)

[0062] 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."

[0063] Automating the collection and organization of financial information reduces errors and wasted time associated with traditional manual data entry and classification, enabling the creation and submission of more accurate and efficient financial statements.

[0064] 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.

[0065] In this invention, the server includes means for obtaining information access rights from a user, means for automatically collecting financial data via an information exchange interface of a financial institution, means for checking the consistency of the collected financial data and storing it in a storage device, means for dividing the stored financial data into multiple classifications using a calculation method, means for providing an operation screen that allows the user to modify and confirm the generated financial documents, and means for digitally submitting financial documents. This enables increased efficiency and accuracy in financial operations, as well as faster procedures.

[0066] "Information access permission" refers to the permission granted to a user to access specific information or data.

[0067] An "information exchange interface" is a standardized communication method for exchanging data between financial institutions and systems.

[0068] "Financial data" refers to information about the financial activities of individuals or corporations, such as banking transactions and credit card usage information.

[0069] "Checking for consistency" is the process of verifying that there are no inconsistencies or errors in the collected data and ensuring its integrity.

[0070] A "storage device" refers to hardware or software that a system uses to store information.

[0071] "Computational methods" is a general term for algorithms and techniques used for data analysis and classification.

[0072] "Classifying" is the process of organizing data into different categories based on specific criteria.

[0073] An "operation screen" is a visual interface that users use to operate a system and to view or edit data.

[0074] "Applying digitally" refers to a process where documents are submitted online, eliminating the need to send physical documents.

[0075] As an embodiment of this invention, a system is constructed to streamline the management of financial information. This system operates via users, terminals, and servers and includes multiple technical components.

[0076] Users access the system through their terminals and grant the system access rights to financial institution information. This access allows the server to automatically retrieve financial data from banks, credit card companies, and other financial institutions using their information exchange interfaces. The server then verifies the consistency of this data before storing it in storage. This typically involves using programming languages ​​such as Python, and a database management system is used for data consistency verification.

[0077] Next, the server uses computational methods, specifically machine learning algorithms, to categorize the acquired data into multiple categories such as income, expenses, and business partners. This process is carried out using libraries such as Scikit-learn, and the classification model is continuously trained to improve the accuracy of data classification.

[0078] Based on the classified data, the server automatically generates financial statements. This document generation is carried out using templates, and users can review the generated financial statements on a terminal and make corrections as needed. This interface operates through a web browser and is intuitive to use.

[0079] Ultimately, the financial documents reviewed by the user are submitted digitally by the server. This submission is done through an online platform, reducing time and cost compared to paper-based submissions.

[0080] A concrete example is how an accounting staff member at a certain company uses this system to automatically retrieve monthly income and expense data and create quick and accurate financial reports. This reduces manual processes and improves accuracy.

[0081] An example of a prompt message is, "Please explain in detail how this system can be used to streamline monthly income and expense data and generate accurate financial reports."

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The user logs into the system using a terminal and enters authentication credentials to access financial institution information. The server receives the entered authentication credentials and uses them to obtain access rights to the financial institution. As an output, the server completes preparation to connect to the financial institution's information exchange interface.

[0085] Step 2:

[0086] The server automatically retrieves financial data from financial institutions using the acquired access permissions. The input is an API endpoint provided by the financial institution. The server accesses this endpoint and collects data including transaction history and account information. This data is aggregated on the server and output as an initial dataset.

[0087] Step 3:

[0088] The server inspects the collected financial data for consistency and performs integrity checks. It detects duplicate data and data in different formats and corrects or deletes them appropriately. The input is the raw acquired data, and the output is a cleansed database entry that is stored.

[0089] Step 4:

[0090] The server uses computational methods to divide the cleansed data into multiple categories. Machine learning algorithms are used to classify data into categories such as income, expenses, and business partners. It takes cleansed data as input and creates a classified dataset as output. This process is performed using libraries such as Scikit-learn.

[0091] Step 5:

[0092] The server automatically generates financial statements based on classified data. This process utilizes pre-configured templates, inserting data into the required fields to create the documents. The input is classified data, and the output is structured financial statements.

[0093] Step 6:

[0094] Users review the financial documents generated via their terminal and edit them as needed. Through the user interface, users visually check the data and correct figures and content. Input is the final document sent from the server, while output is the document approved or modified by the user.

[0095] Step 7:

[0096] The server digitally submits the financial documents that the user has reviewed and corrected. The documents are submitted to the appropriate tax authorities using the online application platform. The input documents are user-approved, and the output documents are officially submitted.

[0097] (Application Example 1)

[0098] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0099] Traditional systems placed a heavy burden on users in effectively managing financial information and automating tax-related documents, requiring manual input and classification. Furthermore, the lack of sufficient real-time spending and budgeting capabilities meant users were unable to accurately understand their own financial situation.

[0100] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0101] In this invention, the server includes means for obtaining information access rights from a user, means for automatically collecting data through an interface for information exchange between financial institutions, and means for checking the integrity of the collected data and storing it on an information storage medium. This automates the collection and integrity checking of financial information, thereby reducing the burden on the user. Furthermore, it provides an interactive screen that allows the user to edit and review tax-related documents generated based on classified data, and a display screen that allows the user to visually confirm classified data, thereby providing means for understanding budget achievement status in real time.

[0102] "Information access permissions" refer to the permissions that users need to obtain their own data from financial institutions or other data providers.

[0103] An "interface for information exchange" is a means of communication for efficiently collecting transaction data from financial institutions and other data providers into a system.

[0104] "Information storage medium" refers to computer systems or other storage devices used to store collected data.

[0105] A "machine learning model" is an algorithm that uses data to perform classification and prediction, and its performance is improved based on experience.

[0106] "Classification" is the process of dividing acquired data into different categories based on specific rules or patterns.

[0107] "Tax-related documents" refer to official documents required for tax filing and other financial reporting.

[0108] An "interactive screen" refers to a visual and interactive user interface used by users to view and edit data.

[0109] A "display screen" refers to the screen of a digital device that a user uses to obtain visual information.

[0110] "Budget achievement status" is an indicator that shows the progress of the user's actual spending against their budget plan.

[0111] The system implementing the present invention is configured in which a user, a server, and a terminal cooperate with each other. First, the user uses a terminal to grant the server access rights to information from financial institutions, credit card companies, etc. This operation enables the server to automatically collect transaction data through an information exchange interface provided by the financial institution. The server checks the integrity of the collected data and stores it in an organized format on an information storage medium.

[0112] The server uses a machine learning model to classify stored data into various categories. This machine learning model can evolve over time, improving the accuracy of its classifications. Based on the classified data, the server automatically generates tax-related documents, which users can view and edit from their terminals. The edited documents are then electronically transmitted from the server to the tax authorities.

[0113] Furthermore, the server provides interactive and display screens to the user's terminal, supporting real-time expenditure management and tracking of budget progress. Specifically, users can visually check their daily expenses and monitor their progress against their budget plans.

[0114] For example, when freelance users use this system, their monthly transactions are automatically recorded and categorized, making budget management easier. This eliminates the need to organize data for tax filing at the end of the month, saving time.

[0115] An example of a prompt to input into the generating AI model is, "Please provide the specifications for an application that automatically collects monthly financial data and generates tax return documents."

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

[0117] Step 1:

[0118] The server obtains access rights to financial institution information provided by the user via their terminal. This allows the server to retrieve the user's deposit information and expenditure data.

[0119] Step 2:

[0120] The server automatically collects transaction data using an interface for information exchange among financial institutions. The data is retrieved via an API and entered into the server as raw transaction data. Before being organized into a database, the retrieved data undergoes consistency checks to remove duplicates and inconsistencies, and is then processed in a clean manner.

[0121] Step 3:

[0122] The server stores consistent data on an information storage medium. This data forms the basis for future calculations and is recorded in a consistent format to improve the efficiency of classification.

[0123] Step 4:

[0124] The server uses machine learning models to classify stored data into various categories. For example, it can be divided into categories such as income, fixed costs, and variable costs. In this step, machine learning algorithms are used to analyze the data and classify it according to patterns and rules, thereby achieving highly accurate categorization.

[0125] Step 5:

[0126] The server automatically generates tax-related documents based on classified data. In many cases, this process involves using a generation AI model to convert documents belonging to different formats into a consistent template and output them in the optimal format. The output documents are displayed on the user's terminal for editing and review.

[0127] Step 6:

[0128] Users can review tax-related documents generated via their device and edit them as needed. This interface allows users to easily adjust information using operations such as drag-and-drop and filtering.

[0129] Step 7:

[0130] The server electronically transmits the tax-related documents that the user has finished editing to the tax authorities. The timing of transmission and the necessary authentication are adjusted according to the regulations set by the user. This process reduces the time and cost associated with sending physical documents.

[0131] Step 8:

[0132] The server provides users with notifications about their daily spending and budget progress. When pre-set conditions are met, a generated AI model sends alerts to the user's device, indicating budget overruns and savings progress. Based on this, users can effectively manage their daily financial activities.

[0133] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0134] This invention combines a system that automatically collects and classifies financial data and generates tax documents with an emotion engine that recognizes user emotions. This system provides a customized interface that responds to the user's emotions, resulting in a more user-friendly experience.

[0135] By incorporating an emotion engine, the system can collect emotional data through facial recognition and voice analysis as users interact with the system via their devices. The server analyzes this emotional data to understand the stress levels and emotional tendencies that users experience while entering data or creating declaration forms.

[0136] For example, if a user is experiencing stress while classifying large amounts of transaction data, the server can adjust the terminal's interface and display tutorials and help features to simplify the process. It can also suggest solutions to the user's challenges based on sentiment data.

[0137] Furthermore, the emotion engine can accumulate historical emotional data and display trends. This feature allows users to monitor their own emotional changes over the long term and plan for necessary support and skill development.

[0138] For example, when a user uses the system for the first time, if the emotion engine detects emotions such as anxiety or confusion, the server displays a guide on the interface to assist the user in starting operations smoothly. In this way, utilizing emotion recognition functionality can improve the user experience and enhance the overall usability and effectiveness of the system.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] The user logs into the system via their device, and the emotion engine begins operating. The system prepares to collect emotion data in real time through the user's facial recognition and voice analysis.

[0142] Step 2:

[0143] The device sends the acquired emotional data to the server. The server performs facial expression analysis and voice tone analysis to determine the user's current emotional state.

[0144] Step 3:

[0145] The server generates an interface tailored to the user's emotional state based on the emotion analysis results. For example, if the user is feeling stressed, the interface's color scheme is changed to one that promotes relaxation.

[0146] Step 4:

[0147] Users collect and categorize financial information. The device provides emotion-responsive user assistance features and displays guides to reduce the complexity of the operation.

[0148] Step 5:

[0149] The server continuously monitors the user's emotional changes during data entry and operation, sending alerts and push notifications as needed. This provides immediate support for any points that might cause the user anxiety.

[0150] Step 6:

[0151] Based on the categorized data, the server automatically generates tax return documents, which the user then reviews on their device. The system also considers the user's emotional state during the generation process, providing suggestions and optimizations.

[0152] Step 7:

[0153] After the user reviews and edits the document, the server manages the final submission and sends the document to the appropriate electronic submission system. At that time, a feedback message is displayed to provide reassurance based on the user's sentiment data.

[0154] (Example 2)

[0155] 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".

[0156] In modern financial data management and tax document preparation processes, users often expend considerable effort and experience significant mental stress. Furthermore, the uniformity of the system makes it difficult to provide services tailored to the individual needs of each user. There is a need for a system that improves this situation and provides a more efficient and user-friendly experience.

[0157] 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.

[0158] In this invention, the server includes means for obtaining data access rights from the user, means for automatically collecting transaction data via the financial institution's application program interface, and means for obtaining and analyzing the user's emotions using an emotion analysis engine. This not only automates the management of financial data and the creation of tax documents, but also enables dynamic interface adjustments in response to the user's emotional state, greatly improving the user experience.

[0159] "Data access permissions" refer to the permissions or authentication information required to allow a user to access data in a system.

[0160] An "application program interface" is an interface or protocol used to share data and functions between different software programs.

[0161] "Transaction data" refers to information and records related to financial transactions, including details such as date, amount, and trading partner.

[0162] "Data storage" refers to a system or device for storing electronic data, and is a device for the secure storage and management of data.

[0163] "Machine learning methods" is a general term for algorithms and methods aimed at enabling computers to learn patterns from data and perform future predictions and classifications.

[0164] A "tax report" is a tax-related report created based on financial transaction data, and is a document used to declare or pay taxes in accordance with the law.

[0165] A "user interface" is the operating environment that includes the screen display and operation methods used by a user to interact with a system.

[0166] An "emotion analysis engine" is software or an algorithm that analyzes data such as a user's facial expressions and voice to infer their emotional state.

[0167] "Dynamic interface tuning" is the process of changing or updating a program's user interface based on the user's current state and requirements.

[0168] This invention provides a system that allows users to efficiently manage their financial data while simultaneously reducing the emotional burden associated with doing so. An embodiment thereof is described below.

[0169] The server first obtains data access permissions from the user. When the user logs into the system through their device, the device uses its camera and microphone to acquire emotional data. This emotional data is sent from the device to the server in real time.

[0170] The server collects this emotional data and analyzes it using an emotion analysis engine. This analysis utilizes facial recognition and voice analysis technologies. Specifically, it uses general emotion analysis engines and tone analysis algorithms. This analysis identifies the user's emotional state (e.g., stress, anxiety, joy, etc.).

[0171] On the other hand, terminals access the financial institution's application program interface via the network and automatically collect transaction data. The server receives the collected transaction data, checks its integrity, and then stores it in data storage. The stored data is classified into multiple categories using machine learning methods. These processes enable the automatic generation of tax reports. This utilizes common data classification algorithms and database management systems.

[0172] The server also provides a user interface that allows users to review and edit generated tax reports. This user interface is dynamically adjusted based on sentiment analysis results. If the user experiences stress or anxiety, tutorials and help functions will appear in the interface to support the user in operating smoothly.

[0173] For example, when a user starts using the system for the first time, their emotions are analyzed, and if anxiety is detected, the server will display a prompt such as, "Would you like to see a guide on how to use the system?" An example of the prompt text would be, "This is your first time using the automated financial data processing system. Please suggest the content of the guide to display when the emotion analysis engine detects user anxiety."

[0174] Thus, the present invention provides a form that enables efficient and comfortable data management and tax document creation while taking user emotions into consideration.

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] The user logs into the system using a terminal. During this process, the user's authentication information is used as input. Upon successful authentication, the terminal activates its camera and microphone. Specifically, this involves taking a picture of the user's face with the camera and recording their voice with the microphone.

[0178] Step 2:

[0179] The device sends acquired facial image data and audio data to the server. The input consists of facial image data and audio data, and the output is the respective data provided to the server. The server receives this data and passes it to the emotion analysis engine. Specifically, it uses facial recognition and tone analysis algorithms to analyze the user's emotions.

[0180] Step 3:

[0181] The server uses an emotion analysis engine to analyze the user's emotional state. The input is emotion-related data from the previous step, and the output is information determining the user's emotional state (e.g., stress, anxiety, joy). Specifically, it generates emotion tags by comparing the collected data with an existing emotion analysis model.

[0182] Step 4:

[0183] The terminal accesses the financial institution's application program interface via the network and collects transaction data. The input is user-authorized access information to the financial institution, and the output is transaction data obtained via API. At this stage, the terminal collects data at regular intervals according to scheduled tasks.

[0184] Step 5:

[0185] The server receives the collected transaction data and verifies its integrity. The input is the transaction data received from the terminal, and the output is a data set with ensured integrity. Specific operations include data format validation and duplicate data removal.

[0186] Step 6:

[0187] The server stores consistent transaction data in data storage and uses this data to apply machine learning methods. The input is consistent data, and the output is classified data categories. The server repeatedly applies a specific algorithm to classify the data into multiple categories.

[0188] Step 7:

[0189] The server automatically generates tax reports based on classified data. The input is classified data, and the output is a formalized tax report. Specifically, the server arranges the necessary items according to a template and generates the report in PDF format.

[0190] Step 8:

[0191] The server provides a terminal interface that allows the user to edit and review the generated tax report. The input is the generated tax report, and the output is an editable screen that the user can manipulate. The interface dynamically changes according to the user's emotional state, and guides and help functions are added as needed.

[0192] (Application Example 2)

[0193] 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".

[0194] Existing financial data management systems often cause user stress because they classify data and create tax documents without considering user emotions. Furthermore, complex interfaces exacerbate the difficulty of operation, detracting from the user experience. Additionally, the lack of personalized support based on user emotions hinders the improvement of the user experience.

[0195] 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.

[0196] In this invention, the server includes means for automatically collecting transaction information via a financial institution's software program interface, means for analyzing the user's emotional state using an emotion recognition engine and personalizing the interface, and means for enabling the user to edit and review generated tax documents, with their display adjusted based on emotion. This enables user-friendly operation support, improving the user experience.

[0197] "Information access permission" is the process by which a user grants a system permission to access data.

[0198] A "software program interface" is an interface between applications that enables data exchange between different software programs.

[0199] "Transaction information" refers to records and data related to financial transactions.

[0200] An "information storage device" is hardware or media used to store data.

[0201] "Machine learning techniques" are methods that automatically build and train models through data analysis.

[0202] A "category" is a unit of classification that groups together data with similar characteristics.

[0203] "Tax documents" refer to the documents and papers necessary for tax procedures.

[0204] An "interface" is a screen or means of interaction that a user uses to communicate with a system.

[0205] An "emotion recognition engine" is software or algorithms used to analyze and judge a user's emotions.

[0206] A "display device" is a digital device or screen that allows a user to visually confirm information.

[0207] The system for implementing this invention mainly consists of a server, a terminal, and a user interface. The server collects transaction information through a financial institution's software program interface and uses an information storage device to store that information. The collected transaction information is automatically classified into multiple categories using machine learning techniques.

[0208] Meanwhile, the device is equipped with an emotion recognition engine that collects emotion data through facial recognition and voice analysis when the user inputs data. Using libraries such as OpenCV and Google® Cloud Speech-to-Text API, it analyzes the user's emotions and determines states such as stress and reassurance. The emotion data is sent to a server and used to adjust the user interface. The interface is optimized based on emotions, improving the user experience.

[0209] For example, if a user shows signs of tension or anxiety during the payment process, the system will detect this and offer relaxation options to simplify the user interface and streamline the payment process. This allows the user to complete the transaction with peace of mind.

[0210] As a concrete example, consider the prompt: "Suggest ways to optimize the UI when the user is feeling anxious." By inputting this prompt into the AI ​​model, the most appropriate interface adjustments for the user will be suggested.

[0211] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0212] Step 1:

[0213] The device is powered on, and the user's facial recognition and voice analysis functions are turned on. The user's face and voice are captured as input, and sentiment data is collected in real time using OpenCV and the Google Cloud Speech-to-Text API. The output is sent to the server as the user's current sentiment state.

[0214] Step 2:

[0215] The server automatically collects transaction information through the financial institution's software program interface. It uses transaction data obtained from the financial institution's API as input and stores the data in an information storage device. The output is a consistent collection of transaction information.

[0216] Step 3:

[0217] The server uses machine learning techniques to classify collected transaction information into multiple categories. Using the stored transaction information as input, the learning model processes the data based on its characteristics and outputs the category classification.

[0218] Step 4:

[0219] The terminal analyzes user emotion data received from the server, and the user interface is adjusted based on this analysis. The user's emotional state is used as input, and data calculations are performed to optimize the interface elements. The output is the adapted interface.

[0220] Step 5:

[0221] During the trading process, the user interacts with the user interface, inputting prompts into the generated AI model and selecting suggested actions. Specifically, the user reviews the presented relaxation options and support messages before proceeding. The input is the user's selection, and the output is either the completion of the trade or further guidance.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] [Second Embodiment]

[0226] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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).

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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".

[0238] This invention provides a system for users to efficiently collect and classify financial information and automatically generate tax return documents. This system reduces the user's burden through multiple processing steps and creates highly accurate documents in a short amount of time.

[0239] First, the user accesses the system using a terminal. The user grants the system access rights to data from financial institutions whose financial information is collected. Through operations performed via the terminal, the system automatically retrieves transaction data from banks, credit card companies, and other financial institutions.

[0240] The server cleanses the retrieved transaction data through integrity checks, removing inconsistent data. The neatly organized data is stored in the database, ready for subsequent classification processing.

[0241] Next, the server uses machine learning algorithms to classify the data. By categorizing it by income, expenses, and customer, it facilitates data analysis. This classification model continuously learns and gradually improves its accuracy.

[0242] Based on the categorized data, the server automatically generates the necessary documents for tax filing. Users can review and edit the generated documents via their terminal and make any necessary adjustments. The interface is designed to be user-friendly, allowing for efficient editing.

[0243] Ultimately, the server electronically submits the user-verified documents to the tax authorities. This significantly reduces the time and cost associated with physical procedures for the user.

[0244] As a concrete example, consider a scenario where an accounting staff member at a certain company uses this system. The accounting staff member can automatically acquire monthly income and expense data and quickly generate other financial reports based on highly accurate analysis results. Automating this process significantly streamlines accounting tasks that were previously done manually, and reduces human error.

[0245] The following describes the processing flow.

[0246] Step 1:

[0247] The server receives the user's authentication information and obtains a token to access the financial institution's API. This allows the server to securely access the user's bank account and credit card information.

[0248] Step 2:

[0249] The server periodically retrieves transaction data from financial institutions' APIs based on a schedule, collecting the latest data. It can also collect new transaction data in real time if it is generated.

[0250] Step 3:

[0251] The system checks the integrity of transaction data retrieved by the server and filters out duplicate and incorrect data. Inconsistent data is logged, data cleaning is performed, and then the clean data is saved to the database.

[0252] Step 4:

[0253] The server processes the cleansed data in the database and performs automatic classification using machine learning models. For example, it analyzes the data using algorithms to classify it into categories such as income, expenses, and costs.

[0254] Step 5:

[0255] The device displays categorized data on a dashboard, allowing users to visually review the data. Users can interactively view revenue and expenditure trends and detailed information by category.

[0256] Step 6:

[0257] The server automatically generates the necessary documents for tax filing based on the classified data. Using standard templates, it creates documents that accurately reflect the collected data.

[0258] Step 7:

[0259] The user reviews the documents generated via the device and edits them as needed. They then save the edited data and prepare for the next step.

[0260] Step 8:

[0261] The server sends the finalized documents to the corresponding tax authority's electronic submission system, completing the submission process. It also notifies the user of the submission results and guides them through the necessary next steps.

[0262] (Example 1)

[0263] 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."

[0264] Automating the collection and organization of financial information reduces errors and wasted time associated with traditional manual data entry and classification, enabling the creation and submission of more accurate and efficient financial statements.

[0265] 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.

[0266] In this invention, the server includes means for obtaining information access rights from a user, means for automatically collecting financial data via an information exchange interface of a financial institution, means for checking the consistency of the collected financial data and storing it in a storage device, means for dividing the stored financial data into multiple classifications using a calculation method, means for providing an operation screen that allows the user to modify and confirm the generated financial documents, and means for digitally submitting financial documents. This enables increased efficiency and accuracy in financial operations, as well as faster procedures.

[0267] "Information access permission" refers to the permission granted to a user to access specific information or data.

[0268] An "information exchange interface" is a standardized communication method for exchanging data between financial institutions and systems.

[0269] "Financial data" refers to information about the financial activities of individuals or corporations, such as banking transactions and credit card usage information.

[0270] "Checking for consistency" is the process of verifying that there are no inconsistencies or errors in the collected data and ensuring its integrity.

[0271] A "storage device" refers to hardware or software that a system uses to store information.

[0272] "Computational methods" is a general term for algorithms and techniques used for data analysis and classification.

[0273] "Classifying" is the process of organizing data into different categories based on specific criteria.

[0274] An "operation screen" is a visual interface that users use to operate a system and to view or edit data.

[0275] "Applying digitally" refers to a process where documents are submitted online, eliminating the need to send physical documents.

[0276] As an embodiment of this invention, a system is constructed to streamline the management of financial information. This system operates via users, terminals, and servers and includes multiple technical components.

[0277] Users access the system through their terminals and grant the system access rights to financial institution information. This access allows the server to automatically retrieve financial data from banks, credit card companies, and other financial institutions using their information exchange interfaces. The server then verifies the consistency of this data before storing it in storage. This typically involves using programming languages ​​such as Python, and a database management system is used for data consistency verification.

[0278] Next, the server uses a calculation method, specifically a machine learning algorithm, to classify the acquired data into multiple categories such as income, expenditure, and trading partners. This process is implemented using libraries such as Scikit-learn, and the classification model is continuously trained to improve the accuracy of data classification.

[0279] Based on the classified data, the server automatically generates financial documents. This document generation is carried out using templates, and the user can check the financial documents on the generated operation screen using the terminal and make corrections if necessary. This interface operates through a web browser and is intuitively operable.

[0280] Finally, the financial documents confirmed by the user are digitally applied by the server. This application is carried out through an online platform, reducing time and costs compared to paper-based applications.

[0281] As a specific example, there is a scenario where an accounting staff of a certain company uses this system to automatically acquire monthly income and expenditure data and create a quick and accurate financial report. This realizes the reduction of manual processes and the improvement of accuracy.

[0282] As an example of a prompt sentence, there is "Please explain in detail how to streamline monthly income and expenditure data and generate accurate financial reports using this system."

[0283] The flow of the specific process in Example 1 will be described using FIG. 11.

[0284] Step 1:

[0285] The user uses the terminal to log in to the system and enters authentication information for accessing the information of the financial institution. The server receives the entered authentication information and obtains the access right to the financial institution based on this. As output, the server completes the preparation to connect to the information exchange interface of the financial institution.

[0286] Step 2:

[0287] The server automatically obtains financial data from the financial institution using the acquired access rights. As an input, there is an API endpoint provided by the financial institution. Access this endpoint and collect data including transaction history and account information. This data is aggregated on the server and output as an initial dataset.

[0288] Step 3:

[0289] The server inspects the consistency of the collected financial data and performs a validation check. Detect duplicate data and data in different formats, and appropriately modify or delete them. The input is the raw acquired data, and the output is a database entry that is cleansed and saved.

[0290] Step 4:

[0291] Based on the cleansed data, the server uses calculation methods to divide the data into multiple classifications. Use machine learning algorithms to classify it into categories such as income, expenditure, and business partners. Receive the cleansed data as an input and create a classified dataset as an output. This process is implemented using libraries such as Scikit-learn.

[0292] Step 5:

[0293] Based on the classified data, the server automatically generates financial documents. In this process, use a pre-set template and insert data into the necessary items to create the documents. The input is the classified data, and the output is a structured financial document.

[0294] Step 6:

[0295] Users review the financial documents generated via their terminal and edit them as needed. Through the user interface, users visually check the data and correct figures and content. Input is the final document sent from the server, while output is the document approved or modified by the user.

[0296] Step 7:

[0297] The server digitally submits the financial documents that the user has reviewed and corrected. The documents are submitted to the appropriate tax authorities using the online application platform. The input documents are user-approved, and the output documents are officially submitted.

[0298] (Application Example 1)

[0299] 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."

[0300] Traditional systems placed a heavy burden on users in effectively managing financial information and automating tax-related documents, requiring manual input and classification. Furthermore, the lack of sufficient real-time spending and budgeting capabilities meant users were unable to accurately understand their own financial situation.

[0301] 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.

[0302] In this invention, the server includes means for obtaining information access rights from a user, means for automatically collecting data via an interface for information exchange with financial institutions, and means for checking the integrity of the collected data and storing it in an information storage medium. As a result, the collection and integrity check of financial information are automated, making it possible to reduce the burden on the user. Also, by providing an interactive screen through which the user can edit and confirm tax-related documents generated based on the classified data, and by providing a display screen through which the user can view the visually classified data, means for grasping the budget achievement status in real time are provided.

[0303] "Information access rights" refers to the permission required for a user to obtain their own data from financial institutions or other data providers.

[0304] "Interface for information exchange" is a communication means for efficiently collecting transaction data from financial institutions or other data providers into the system.

[0305] "Information storage medium" refers to a computer system or other storage device for storing the collected data.

[0306] "Machine learning model" is an algorithm that classifies and predicts using data and improves performance based on experience.

[0307] "Classification" is an operation of dividing the acquired data into different categories based on specific rules or patterns.

[0308] "Tax-related document" refers to an official document required for tax declarations and other financial reports.

[0309] "Interactive screen" refers to a visual and operable user interface used when a user checks and edits data.

[0310] "Display screen" is the screen of a digital device used by a user to obtain visual information.

[0311] "Budget achievement status" is an indicator that shows the progress of the user's actual spending against their budget plan.

[0312] The system implementing the present invention is configured in which a user, a server, and a terminal cooperate with each other. First, the user uses a terminal to grant the server access rights to information from financial institutions, credit card companies, etc. This operation enables the server to automatically collect transaction data through an information exchange interface provided by the financial institution. The server checks the integrity of the collected data and stores it in an organized format on an information storage medium.

[0313] The server uses a machine learning model to classify stored data into various categories. This machine learning model can evolve over time, improving the accuracy of its classifications. Based on the classified data, the server automatically generates tax-related documents, which users can view and edit from their terminals. The edited documents are then electronically transmitted from the server to the tax authorities.

[0314] Furthermore, the server provides interactive and display screens to the user's terminal, supporting real-time expenditure management and tracking of budget progress. Specifically, users can visually check their daily expenses and monitor their progress against their budget plans.

[0315] For example, when freelance users use this system, their monthly transactions are automatically recorded and categorized, making budget management easier. This eliminates the need to organize data for tax filing at the end of the month, saving time.

[0316] An example of a prompt to input into the generating AI model is, "Please provide the specifications for an application that automatically collects monthly financial data and generates tax return documents."

[0317] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0318] Step 1:

[0319] The server obtains access rights to financial institution information provided by the user via their terminal. This allows the server to retrieve the user's deposit information and expenditure data.

[0320] Step 2:

[0321] The server automatically collects transaction data using an interface for information exchange among financial institutions. The data is retrieved via an API and entered into the server as raw transaction data. Before being organized into a database, the retrieved data undergoes consistency checks to remove duplicates and inconsistencies, and is then processed in a clean manner.

[0322] Step 3:

[0323] The server stores consistent data on an information storage medium. This data forms the basis for future calculations and is recorded in a consistent format to improve the efficiency of classification.

[0324] Step 4:

[0325] The server uses machine learning models to classify stored data into various categories. For example, it can be divided into categories such as income, fixed costs, and variable costs. In this step, machine learning algorithms are used to analyze the data and classify it according to patterns and rules, thereby achieving highly accurate categorization.

[0326] Step 5:

[0327] The server automatically generates tax-related documents based on classified data. In many cases, this process involves using a generation AI model to convert documents belonging to different formats into a consistent template and output them in the optimal format. The output documents are displayed on the user's terminal for editing and review.

[0328] Step 6:

[0329] Users can review tax-related documents generated via their device and edit them as needed. This interface allows users to easily adjust information using operations such as drag-and-drop and filtering.

[0330] Step 7:

[0331] The server electronically transmits the tax-related documents that the user has finished editing to the tax authorities. The timing of transmission and the necessary authentication are adjusted according to the regulations set by the user. This process reduces the time and cost associated with sending physical documents.

[0332] Step 8:

[0333] The server provides users with notifications about their daily spending and budget progress. When pre-set conditions are met, a generated AI model sends alerts to the user's device, indicating budget overruns and savings progress. Based on this, users can effectively manage their daily financial activities.

[0334] 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.

[0335] This invention combines a system that automatically collects and classifies financial data and generates tax documents with an emotion engine that recognizes user emotions. This system provides a customized interface that responds to the user's emotions, resulting in a more user-friendly experience.

[0336] By incorporating an emotion engine, the system can collect emotional data through facial recognition and voice analysis as users interact with the system via their devices. The server analyzes this emotional data to understand the stress levels and emotional tendencies that users experience while entering data or creating declaration forms.

[0337] For example, if a user is experiencing stress while classifying large amounts of transaction data, the server can adjust the terminal's interface and display tutorials and help features to simplify the process. It can also suggest solutions to the user's challenges based on sentiment data.

[0338] Furthermore, the emotion engine can accumulate historical emotional data and display trends. This feature allows users to monitor their own emotional changes over the long term and plan for necessary support and skill development.

[0339] For example, when a user uses the system for the first time, if the emotion engine detects emotions such as anxiety or confusion, the server displays a guide on the interface to assist the user in starting operations smoothly. In this way, utilizing emotion recognition functionality can improve the user experience and enhance the overall usability and effectiveness of the system.

[0340] The following describes the processing flow.

[0341] Step 1:

[0342] The user logs into the system via their device, and the emotion engine begins operating. The system prepares to collect emotion data in real time through the user's facial recognition and voice analysis.

[0343] Step 2:

[0344] The device sends the acquired emotional data to the server. The server performs facial expression analysis and voice tone analysis to determine the user's current emotional state.

[0345] Step 3:

[0346] The server generates an interface tailored to the user's emotional state based on the emotion analysis results. For example, if the user is feeling stressed, the interface's color scheme is changed to one that promotes relaxation.

[0347] Step 4:

[0348] Users collect and categorize financial information. The device provides emotion-responsive user assistance features and displays guides to reduce the complexity of the operation.

[0349] Step 5:

[0350] The server continuously monitors the user's emotional changes during data entry and operation, sending alerts and push notifications as needed. This provides immediate support for any points that might cause the user anxiety.

[0351] Step 6:

[0352] Based on the categorized data, the server automatically generates tax return documents, which the user then reviews on their device. The system also considers the user's emotional state during the generation process, providing suggestions and optimizations.

[0353] Step 7:

[0354] After the user reviews and edits the document, the server manages the final submission and sends the document to the appropriate electronic submission system. At that time, a feedback message is displayed to provide reassurance based on the user's sentiment data.

[0355] (Example 2)

[0356] 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".

[0357] In modern financial data management and tax document preparation processes, users often expend considerable effort and experience significant mental stress. Furthermore, the uniformity of the system makes it difficult to provide services tailored to the individual needs of each user. There is a need for a system that improves this situation and provides a more efficient and user-friendly experience.

[0358] 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.

[0359] In this invention, the server includes means for obtaining data access rights from the user, means for automatically collecting transaction data via the financial institution's application program interface, and means for obtaining and analyzing the user's emotions using an emotion analysis engine. This not only automates the management of financial data and the creation of tax documents, but also enables dynamic interface adjustments in response to the user's emotional state, greatly improving the user experience.

[0360] "Data access permissions" refer to the permissions or authentication information required to allow a user to access data in a system.

[0361] An "application program interface" is an interface or protocol used to share data and functions between different software programs.

[0362] "Transaction data" refers to information and records related to financial transactions, including details such as date, amount, and trading partner.

[0363] "Data storage" refers to a system or device for storing electronic data, and is a device for the secure storage and management of data.

[0364] "Machine learning methods" is a general term for algorithms and methods aimed at enabling computers to learn patterns from data and perform future predictions and classifications.

[0365] A "tax report" is a tax-related report created based on financial transaction data, and is a document used to declare or pay taxes in accordance with the law.

[0366] A "user interface" is the operating environment that includes the screen display and operation methods used by a user to interact with a system.

[0367] An "emotion analysis engine" is software or an algorithm that analyzes data such as a user's facial expressions and voice to infer their emotional state.

[0368] "Dynamic interface tuning" is the process of changing or updating a program's user interface based on the user's current state and requirements.

[0369] This invention provides a system that allows users to efficiently manage their financial data while simultaneously reducing the emotional burden associated with doing so. An embodiment thereof is described below.

[0370] The server first obtains data access permissions from the user. When the user logs into the system through their device, the device uses its camera and microphone to acquire emotional data. This emotional data is sent from the device to the server in real time.

[0371] The server collects this emotional data and analyzes it using an emotion analysis engine. This analysis utilizes facial recognition and voice analysis technologies. Specifically, it uses general emotion analysis engines and tone analysis algorithms. This analysis identifies the user's emotional state (e.g., stress, anxiety, joy, etc.).

[0372] On the other hand, terminals access the financial institution's application program interface via the network and automatically collect transaction data. The server receives the collected transaction data, checks its integrity, and then stores it in data storage. The stored data is classified into multiple categories using machine learning methods. These processes enable the automatic generation of tax reports. This utilizes common data classification algorithms and database management systems.

[0373] The server also provides a user interface that allows users to review and edit generated tax reports. This user interface is dynamically adjusted based on sentiment analysis results. If the user experiences stress or anxiety, tutorials and help functions will appear in the interface to support the user in operating smoothly.

[0374] For example, when a user starts using the system for the first time, their emotions are analyzed, and if anxiety is detected, the server will display a prompt such as, "Would you like to see a guide on how to use the system?" An example of the prompt text would be, "This is your first time using the automated financial data processing system. Please suggest the content of the guide to display when the emotion analysis engine detects user anxiety."

[0375] Thus, the present invention provides a form that enables efficient and comfortable data management and tax document creation while taking user emotions into consideration.

[0376] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0377] Step 1:

[0378] The user logs into the system using a terminal. During this process, the user's authentication information is used as input. Upon successful authentication, the terminal activates its camera and microphone. Specifically, this involves taking a picture of the user's face with the camera and recording their voice with the microphone.

[0379] Step 2:

[0380] The device sends acquired facial image data and audio data to the server. The input consists of facial image data and audio data, and the output is the respective data provided to the server. The server receives this data and passes it to the emotion analysis engine. Specifically, it uses facial recognition and tone analysis algorithms to analyze the user's emotions.

[0381] Step 3:

[0382] The server uses an emotion analysis engine to analyze the user's emotional state. The input is emotion-related data from the previous step, and the output is information determining the user's emotional state (e.g., stress, anxiety, joy). Specifically, it generates emotion tags by comparing the collected data with an existing emotion analysis model.

[0383] Step 4:

[0384] The terminal accesses the financial institution's application program interface via the network and collects transaction data. The input is user-authorized access information to the financial institution, and the output is transaction data obtained via API. At this stage, the terminal collects data at regular intervals according to scheduled tasks.

[0385] Step 5:

[0386] The server receives the collected transaction data and verifies its integrity. The input is the transaction data received from the terminal, and the output is a data set with ensured integrity. Specific operations include data format validation and duplicate data removal.

[0387] Step 6:

[0388] The server stores consistent transaction data in data storage and uses this data to apply machine learning methods. The input is consistent data, and the output is classified data categories. The server repeatedly applies a specific algorithm to classify the data into multiple categories.

[0389] Step 7:

[0390] The server automatically generates tax reports based on classified data. The input is classified data, and the output is a formalized tax report. Specifically, the server arranges the necessary items according to a template and generates the report in PDF format.

[0391] Step 8:

[0392] The server provides a terminal interface that allows the user to edit and review the generated tax report. The input is the generated tax report, and the output is an editable screen that the user can manipulate. The interface dynamically changes according to the user's emotional state, and guides and help functions are added as needed.

[0393] (Application Example 2)

[0394] 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."

[0395] Existing financial data management systems often cause user stress because they classify data and create tax documents without considering user emotions. Furthermore, complex interfaces exacerbate the difficulty of operation, detracting from the user experience. Additionally, the lack of personalized support based on user emotions hinders the improvement of the user experience.

[0396] 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.

[0397] In this invention, the server includes means for automatically collecting transaction information via a financial institution's software program interface, means for analyzing the user's emotional state using an emotion recognition engine and personalizing the interface, and means for enabling the user to edit and review generated tax documents, with their display adjusted based on emotion. This enables user-friendly operation support, improving the user experience.

[0398] "Information access permission" is the process by which a user grants a system permission to access data.

[0399] A "software program interface" is an interface between applications that enables data exchange between different software programs.

[0400] "Transaction information" refers to records and data related to financial transactions.

[0401] An "information storage device" is hardware or media used to store data.

[0402] "Machine learning techniques" are methods that automatically build and train models through data analysis.

[0403] A "category" is a unit of classification that groups together data with similar characteristics.

[0404] "Tax documents" refer to the documents and papers necessary for tax procedures.

[0405] An "interface" is a screen or means of interaction that a user uses to communicate with a system.

[0406] An "emotion recognition engine" is software or algorithms used to analyze and judge a user's emotions.

[0407] A "display device" is a digital device or screen that allows a user to visually confirm information.

[0408] The system for implementing this invention mainly consists of a server, a terminal, and a user interface. The server collects transaction information through a financial institution's software program interface and uses an information storage device to store that information. The collected transaction information is automatically classified into multiple categories using machine learning techniques.

[0409] Meanwhile, the device is equipped with an emotion recognition engine that collects emotional data through facial recognition and voice analysis when the user inputs data. Using libraries such as OpenCV and Google Cloud Speech-to-Text API, it analyzes the user's emotions and determines states such as stress and reassurance. The emotional data is sent to a server and used to adjust the user interface. The interface is optimized based on emotions, improving the user experience.

[0410] For example, if a user shows signs of tension or anxiety during the payment process, the system will detect this and offer relaxation options to simplify the user interface and streamline the payment process. This allows the user to complete the transaction with peace of mind.

[0411] As a concrete example, consider the prompt: "Suggest ways to optimize the UI when the user is feeling anxious." By inputting this prompt into the AI ​​model, the most appropriate interface adjustments for the user will be suggested.

[0412] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0413] Step 1:

[0414] The device is powered on, and the user's facial recognition and voice analysis functions are turned on. The user's face and voice are captured as input, and sentiment data is collected in real time using OpenCV and the Google Cloud Speech-to-Text API. The output is sent to the server as the user's current sentiment state.

[0415] Step 2:

[0416] The server automatically collects transaction information through the financial institution's software program interface. It uses transaction data obtained from the financial institution's API as input and stores the data in an information storage device. The output is a consistent collection of transaction information.

[0417] Step 3:

[0418] The server uses machine learning techniques to classify collected transaction information into multiple categories. Using the stored transaction information as input, the learning model processes the data based on its characteristics and outputs the category classification.

[0419] Step 4:

[0420] The terminal analyzes user emotion data received from the server, and the user interface is adjusted based on this analysis. The user's emotional state is used as input, and data calculations are performed to optimize the interface elements. The output is the adapted interface.

[0421] Step 5:

[0422] During the trading process, the user interacts with the user interface, inputting prompts into the generated AI model and selecting suggested actions. Specifically, the user reviews the presented relaxation options and support messages before proceeding. The input is the user's selection, and the output is either the completion of the trade or further guidance.

[0423] 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.

[0424] 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.

[0425] 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.

[0426] [Third Embodiment]

[0427] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0428] 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.

[0429] 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).

[0430] 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.

[0431] 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.

[0432] 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).

[0433] 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.

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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".

[0439] This invention provides a system for users to efficiently collect and classify financial information and automatically generate tax return documents. This system reduces the user's burden through multiple processing steps and creates highly accurate documents in a short amount of time.

[0440] First, the user accesses the system using a terminal. The user grants the system access rights to data from financial institutions whose financial information is collected. Through operations performed via the terminal, the system automatically retrieves transaction data from banks, credit card companies, and other financial institutions.

[0441] The server cleanses the retrieved transaction data through integrity checks, removing inconsistent data. The neatly organized data is stored in the database, ready for subsequent classification processing.

[0442] Next, the server uses machine learning algorithms to classify the data. By categorizing it by income, expenses, and customer, it facilitates data analysis. This classification model continuously learns and gradually improves its accuracy.

[0443] Based on the categorized data, the server automatically generates the necessary documents for tax filing. Users can review and edit the generated documents via their terminal and make any necessary adjustments. The interface is designed to be user-friendly, allowing for efficient editing.

[0444] Ultimately, the server electronically submits the user-verified documents to the tax authorities. This significantly reduces the time and cost associated with physical procedures for the user.

[0445] As a concrete example, consider a scenario where an accounting staff member at a certain company uses this system. The accounting staff member can automatically acquire monthly income and expense data and quickly generate other financial reports based on highly accurate analysis results. Automating this process significantly streamlines accounting tasks that were previously done manually, and reduces human error.

[0446] The following describes the processing flow.

[0447] Step 1:

[0448] The server receives the user's authentication information and obtains a token to access the financial institution's API. This allows the server to securely access the user's bank account and credit card information.

[0449] Step 2:

[0450] The server periodically retrieves transaction data from financial institutions' APIs based on a schedule, collecting the latest data. It can also collect new transaction data in real time if it is generated.

[0451] Step 3:

[0452] The system checks the integrity of transaction data retrieved by the server and filters out duplicate and incorrect data. Inconsistent data is logged, data cleaning is performed, and then the clean data is saved to the database.

[0453] Step 4:

[0454] The server processes the cleansed data in the database and performs automatic classification using machine learning models. For example, it analyzes the data using algorithms to classify it into categories such as income, expenses, and costs.

[0455] Step 5:

[0456] The device displays categorized data on a dashboard, allowing users to visually review the data. Users can interactively view revenue and expenditure trends and detailed information by category.

[0457] Step 6:

[0458] The server automatically generates the necessary documents for tax filing based on the classified data. Using standard templates, it creates documents that accurately reflect the collected data.

[0459] Step 7:

[0460] The user reviews the documents generated via the device and edits them as needed. They then save the edited data and prepare for the next step.

[0461] Step 8:

[0462] The server sends the finalized documents to the corresponding tax authority's electronic submission system, completing the submission process. It also notifies the user of the submission results and guides them through the necessary next steps.

[0463] (Example 1)

[0464] 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."

[0465] Automating the collection and organization of financial information reduces errors and wasted time associated with traditional manual data entry and classification, enabling the creation and submission of more accurate and efficient financial statements.

[0466] 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.

[0467] In this invention, the server includes means for obtaining information access rights from a user, means for automatically collecting financial data via an information exchange interface of a financial institution, means for checking the consistency of the collected financial data and storing it in a storage device, means for dividing the stored financial data into multiple classifications using a calculation method, means for providing an operation screen that allows the user to modify and confirm the generated financial documents, and means for digitally submitting financial documents. This enables increased efficiency and accuracy in financial operations, as well as faster procedures.

[0468] "Information access permission" refers to the permission granted to a user to access specific information or data.

[0469] An "information exchange interface" is a standardized communication method for exchanging data between financial institutions and systems.

[0470] "Financial data" refers to information about the financial activities of individuals or corporations, such as banking transactions and credit card usage information.

[0471] "Checking for consistency" is the process of verifying that there are no inconsistencies or errors in the collected data and ensuring its integrity.

[0472] A "storage device" refers to hardware or software that a system uses to store information.

[0473] "Computational methods" is a general term for algorithms and techniques used for data analysis and classification.

[0474] "Classifying" is the process of organizing data into different categories based on specific criteria.

[0475] An "operation screen" is a visual interface that users use to operate a system and to view or edit data.

[0476] "Applying digitally" refers to a process where documents are submitted online, eliminating the need to send physical documents.

[0477] As an embodiment of this invention, a system is constructed to streamline the management of financial information. This system operates via users, terminals, and servers and includes multiple technical components.

[0478] Users access the system through their terminals and grant the system access rights to financial institution information. This access allows the server to automatically retrieve financial data from banks, credit card companies, and other financial institutions using their information exchange interfaces. The server then verifies the consistency of this data before storing it in storage. This typically involves using programming languages ​​such as Python, and a database management system is used for data consistency verification.

[0479] Next, the server uses computational methods, specifically machine learning algorithms, to categorize the acquired data into multiple categories such as income, expenses, and business partners. This process is carried out using libraries such as Scikit-learn, and the classification model is continuously trained to improve the accuracy of data classification.

[0480] Based on the classified data, the server automatically generates financial statements. This document generation is carried out using templates, and users can review the generated financial statements on a terminal and make corrections as needed. This interface operates through a web browser and is intuitive to use.

[0481] Ultimately, the financial documents reviewed by the user are submitted digitally by the server. This submission is done through an online platform, reducing time and cost compared to paper-based submissions.

[0482] A concrete example is how an accounting staff member at a certain company uses this system to automatically retrieve monthly income and expense data and create quick and accurate financial reports. This reduces manual processes and improves accuracy.

[0483] An example of a prompt message is, "Please explain in detail how this system can be used to streamline monthly income and expense data and generate accurate financial reports."

[0484] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0485] Step 1:

[0486] The user logs into the system using a terminal and enters authentication credentials to access financial institution information. The server receives the entered authentication credentials and uses them to obtain access rights to the financial institution. As an output, the server completes preparation to connect to the financial institution's information exchange interface.

[0487] Step 2:

[0488] The server automatically retrieves financial data from financial institutions using the acquired access permissions. The input is an API endpoint provided by the financial institution. The server accesses this endpoint and collects data including transaction history and account information. This data is aggregated on the server and output as an initial dataset.

[0489] Step 3:

[0490] The server inspects the collected financial data for consistency and performs integrity checks. It detects duplicate data and data in different formats and corrects or deletes them appropriately. The input is the raw acquired data, and the output is a cleansed database entry that is stored.

[0491] Step 4:

[0492] The server uses computational methods to divide the cleansed data into multiple categories. Machine learning algorithms are used to classify data into categories such as income, expenses, and business partners. It takes cleansed data as input and creates a classified dataset as output. This process is performed using libraries such as Scikit-learn.

[0493] Step 5:

[0494] The server automatically generates financial statements based on classified data. This process utilizes pre-configured templates, inserting data into the required fields to create the documents. The input is classified data, and the output is structured financial statements.

[0495] Step 6:

[0496] Users review the financial documents generated via their terminal and edit them as needed. Through the user interface, users visually check the data and correct figures and content. Input is the final document sent from the server, while output is the document approved or modified by the user.

[0497] Step 7:

[0498] The server digitally submits the financial documents that the user has reviewed and corrected. The documents are submitted to the appropriate tax authorities using the online application platform. The input documents are user-approved, and the output documents are officially submitted.

[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] Traditional systems placed a heavy burden on users in effectively managing financial information and automating tax-related documents, requiring manual input and classification. Furthermore, the lack of sufficient real-time spending and budgeting capabilities meant users were unable to accurately understand their own financial situation.

[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 obtaining information access rights from a user, means for automatically collecting data through an interface for information exchange between financial institutions, and means for checking the integrity of the collected data and storing it on an information storage medium. This automates the collection and integrity checking of financial information, thereby reducing the burden on the user. Furthermore, it provides an interactive screen that allows the user to edit and review tax-related documents generated based on classified data, and a display screen that allows the user to visually confirm classified data, thereby providing means for understanding budget achievement status in real time.

[0504] "Information access permissions" refer to the permissions that users need to obtain their own data from financial institutions or other data providers.

[0505] An "interface for information exchange" is a means of communication for efficiently collecting transaction data from financial institutions and other data providers into a system.

[0506] "Information storage medium" refers to computer systems or other storage devices used to store collected data.

[0507] A "machine learning model" is an algorithm that uses data to perform classification and prediction, and its performance is improved based on experience.

[0508] "Classification" is the process of dividing acquired data into different categories based on specific rules or patterns.

[0509] "Tax-related documents" refer to official documents required for tax filing and other financial reporting.

[0510] An "interactive screen" refers to a visual and interactive user interface used by users to view and edit data.

[0511] A "display screen" refers to the screen of a digital device that a user uses to obtain visual information.

[0512] "Budget achievement status" is an indicator that shows the progress of the user's actual spending against their budget plan.

[0513] The system implementing the present invention is configured in which a user, a server, and a terminal cooperate with each other. First, the user uses a terminal to grant the server access rights to information from financial institutions, credit card companies, etc. This operation enables the server to automatically collect transaction data through an information exchange interface provided by the financial institution. The server checks the integrity of the collected data and stores it in an organized format on an information storage medium.

[0514] The server uses a machine learning model to classify stored data into various categories. This machine learning model can evolve over time, improving the accuracy of its classifications. Based on the classified data, the server automatically generates tax-related documents, which users can view and edit from their terminals. The edited documents are then electronically transmitted from the server to the tax authorities.

[0515] Furthermore, the server provides interactive and display screens to the user's terminal, supporting real-time expenditure management and tracking of budget progress. Specifically, users can visually check their daily expenses and monitor their progress against their budget plans.

[0516] For example, when freelance users use this system, their monthly transactions are automatically recorded and categorized, making budget management easier. This eliminates the need to organize data for tax filing at the end of the month, saving time.

[0517] An example of a prompt to input into the generating AI model is, "Please provide the specifications for an application that automatically collects monthly financial data and generates tax return documents."

[0518] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0519] Step 1:

[0520] The server obtains access rights to financial institution information provided by the user via their terminal. This allows the server to retrieve the user's deposit information and expenditure data.

[0521] Step 2:

[0522] The server automatically collects transaction data using an interface for information exchange among financial institutions. The data is retrieved via an API and entered into the server as raw transaction data. Before being organized into a database, the retrieved data undergoes consistency checks to remove duplicates and inconsistencies, and is then processed in a clean manner.

[0523] Step 3:

[0524] The server stores consistent data on an information storage medium. This data forms the basis for future calculations and is recorded in a consistent format to improve the efficiency of classification.

[0525] Step 4:

[0526] The server uses machine learning models to classify stored data into various categories. For example, it can be divided into categories such as income, fixed costs, and variable costs. In this step, machine learning algorithms are used to analyze the data and classify it according to patterns and rules, thereby achieving highly accurate categorization.

[0527] Step 5:

[0528] The server automatically generates tax-related documents based on classified data. In many cases, this process involves using a generation AI model to convert documents belonging to different formats into a consistent template and output them in the optimal format. The output documents are displayed on the user's terminal for editing and review.

[0529] Step 6:

[0530] Users can review tax-related documents generated via their device and edit them as needed. This interface allows users to easily adjust information using operations such as drag-and-drop and filtering.

[0531] Step 7:

[0532] The server electronically transmits the tax-related documents that the user has finished editing to the tax authorities. The timing of transmission and the necessary authentication are adjusted according to the regulations set by the user. This process reduces the time and cost associated with sending physical documents.

[0533] Step 8:

[0534] The server provides users with notifications about their daily spending and budget progress. When pre-set conditions are met, a generated AI model sends alerts to the user's device, indicating budget overruns and savings progress. Based on this, users can effectively manage their daily financial activities.

[0535] 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.

[0536] This invention combines a system that automatically collects and classifies financial data and generates tax documents with an emotion engine that recognizes user emotions. This system provides a customized interface that responds to the user's emotions, resulting in a more user-friendly experience.

[0537] By incorporating an emotion engine, the system can collect emotional data through facial recognition and voice analysis as users interact with the system via their devices. The server analyzes this emotional data to understand the stress levels and emotional tendencies that users experience while entering data or creating declaration forms.

[0538] For example, if a user is experiencing stress while classifying large amounts of transaction data, the server can adjust the terminal's interface and display tutorials and help features to simplify the process. It can also suggest solutions to the user's challenges based on sentiment data.

[0539] Furthermore, the emotion engine can accumulate historical emotional data and display trends. This feature allows users to monitor their own emotional changes over the long term and plan for necessary support and skill development.

[0540] For example, when a user uses the system for the first time, if the emotion engine detects emotions such as anxiety or confusion, the server displays a guide on the interface to assist the user in starting operations smoothly. In this way, utilizing emotion recognition functionality can improve the user experience and enhance the overall usability and effectiveness of the system.

[0541] The following describes the processing flow.

[0542] Step 1:

[0543] The user logs into the system via their device, and the emotion engine begins operating. The system prepares to collect emotion data in real time through the user's facial recognition and voice analysis.

[0544] Step 2:

[0545] The device sends the acquired emotional data to the server. The server performs facial expression analysis and voice tone analysis to determine the user's current emotional state.

[0546] Step 3:

[0547] The server generates an interface tailored to the user's emotional state based on the emotion analysis results. For example, if the user is feeling stressed, the interface's color scheme is changed to one that promotes relaxation.

[0548] Step 4:

[0549] Users collect and categorize financial information. The device provides emotion-responsive user assistance features and displays guides to reduce the complexity of the operation.

[0550] Step 5:

[0551] The server continuously monitors the user's emotional changes during data entry and operation, sending alerts and push notifications as needed. This provides immediate support for any points that might cause the user anxiety.

[0552] Step 6:

[0553] Based on the categorized data, the server automatically generates tax return documents, which the user then reviews on their device. The system also considers the user's emotional state during the generation process, providing suggestions and optimizations.

[0554] Step 7:

[0555] After the user reviews and edits the document, the server manages the final submission and sends the document to the appropriate electronic submission system. At that time, a feedback message is displayed to provide reassurance based on the user's sentiment data.

[0556] (Example 2)

[0557] 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."

[0558] In modern financial data management and tax document preparation processes, users often expend considerable effort and experience significant mental stress. Furthermore, the uniformity of the system makes it difficult to provide services tailored to the individual needs of each user. There is a need for a system that improves this situation and provides a more efficient and user-friendly experience.

[0559] 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.

[0560] In this invention, the server includes means for obtaining data access rights from the user, means for automatically collecting transaction data via the financial institution's application program interface, and means for obtaining and analyzing the user's emotions using an emotion analysis engine. This not only automates the management of financial data and the creation of tax documents, but also enables dynamic interface adjustments in response to the user's emotional state, greatly improving the user experience.

[0561] "Data access permissions" refer to the permissions or authentication information required to allow a user to access data in a system.

[0562] An "application program interface" is an interface or protocol used to share data and functions between different software programs.

[0563] "Transaction data" refers to information and records related to financial transactions, including details such as date, amount, and trading partner.

[0564] "Data storage" refers to a system or device for storing electronic data, and is a device for the secure storage and management of data.

[0565] "Machine learning methods" is a general term for algorithms and methods aimed at enabling computers to learn patterns from data and perform future predictions and classifications.

[0566] A "tax report" is a tax-related report created based on financial transaction data, and is a document used to declare or pay taxes in accordance with the law.

[0567] A "user interface" is the operating environment that includes the screen display and operation methods used by a user to interact with a system.

[0568] An "emotion analysis engine" is software or an algorithm that analyzes data such as a user's facial expressions and voice to infer their emotional state.

[0569] "Dynamic interface tuning" is the process of changing or updating a program's user interface based on the user's current state and requirements.

[0570] This invention provides a system that allows users to efficiently manage their financial data while simultaneously reducing the emotional burden associated with doing so. An embodiment thereof is described below.

[0571] The server first obtains data access permissions from the user. When the user logs into the system through their device, the device uses its camera and microphone to acquire emotional data. This emotional data is sent from the device to the server in real time.

[0572] The server collects this emotional data and analyzes it using an emotion analysis engine. This analysis utilizes facial recognition and voice analysis technologies. Specifically, it uses general emotion analysis engines and tone analysis algorithms. This analysis identifies the user's emotional state (e.g., stress, anxiety, joy, etc.).

[0573] On the other hand, terminals access the financial institution's application program interface via the network and automatically collect transaction data. The server receives the collected transaction data, checks its integrity, and then stores it in data storage. The stored data is classified into multiple categories using machine learning methods. These processes enable the automatic generation of tax reports. This utilizes common data classification algorithms and database management systems.

[0574] The server also provides a user interface that allows users to review and edit generated tax reports. This user interface is dynamically adjusted based on sentiment analysis results. If the user experiences stress or anxiety, tutorials and help functions will appear in the interface to support the user in operating smoothly.

[0575] For example, when a user starts using the system for the first time, their emotions are analyzed, and if anxiety is detected, the server will display a prompt such as, "Would you like to see a guide on how to use the system?" An example of the prompt text would be, "This is your first time using the automated financial data processing system. Please suggest the content of the guide to display when the emotion analysis engine detects user anxiety."

[0576] Thus, the present invention provides a form that enables efficient and comfortable data management and tax document creation while taking user emotions into consideration.

[0577] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0578] Step 1:

[0579] The user logs into the system using a terminal. During this process, the user's authentication information is used as input. Upon successful authentication, the terminal activates its camera and microphone. Specifically, this involves taking a picture of the user's face with the camera and recording their voice with the microphone.

[0580] Step 2:

[0581] The device sends acquired facial image data and audio data to the server. The input consists of facial image data and audio data, and the output is the respective data provided to the server. The server receives this data and passes it to the emotion analysis engine. Specifically, it uses facial recognition and tone analysis algorithms to analyze the user's emotions.

[0582] Step 3:

[0583] The server uses an emotion analysis engine to analyze the user's emotional state. The input is emotion-related data from the previous step, and the output is information determining the user's emotional state (e.g., stress, anxiety, joy). Specifically, it generates emotion tags by comparing the collected data with an existing emotion analysis model.

[0584] Step 4:

[0585] The terminal accesses the financial institution's application program interface via the network and collects transaction data. The input is user-authorized access information to the financial institution, and the output is transaction data obtained via API. At this stage, the terminal collects data at regular intervals according to scheduled tasks.

[0586] Step 5:

[0587] The server receives the collected transaction data and verifies its integrity. The input is the transaction data received from the terminal, and the output is a data set with ensured integrity. Specific operations include data format validation and duplicate data removal.

[0588] Step 6:

[0589] The server stores consistent transaction data in data storage and uses this data to apply machine learning methods. The input is consistent data, and the output is classified data categories. The server repeatedly applies a specific algorithm to classify the data into multiple categories.

[0590] Step 7:

[0591] The server automatically generates tax reports based on classified data. The input is classified data, and the output is a formalized tax report. Specifically, the server arranges the necessary items according to a template and generates the report in PDF format.

[0592] Step 8:

[0593] The server provides a terminal interface that allows the user to edit and review the generated tax report. The input is the generated tax report, and the output is an editable screen that the user can manipulate. The interface dynamically changes according to the user's emotional state, and guides and help functions are added as needed.

[0594] (Application Example 2)

[0595] 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."

[0596] Existing financial data management systems often cause user stress because they classify data and create tax documents without considering user emotions. Furthermore, complex interfaces exacerbate the difficulty of operation, detracting from the user experience. Additionally, the lack of personalized support based on user emotions hinders the improvement of the user experience.

[0597] 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.

[0598] In this invention, the server includes means for automatically collecting transaction information via a financial institution's software program interface, means for analyzing the user's emotional state using an emotion recognition engine and personalizing the interface, and means for enabling the user to edit and review generated tax documents, with their display adjusted based on emotion. This enables user-friendly operation support, improving the user experience.

[0599] "Information access permission" is the process by which a user grants a system permission to access data.

[0600] A "software program interface" is an interface between applications that enables data exchange between different software programs.

[0601] "Transaction information" refers to records and data related to financial transactions.

[0602] An "information storage device" is hardware or media used to store data.

[0603] "Machine learning techniques" are methods that automatically build and train models through data analysis.

[0604] A "category" is a unit of classification that groups together data with similar characteristics.

[0605] "Tax documents" refer to the documents and papers necessary for tax procedures.

[0606] An "interface" is a screen or means of interaction that a user uses to communicate with a system.

[0607] An "emotion recognition engine" is software or algorithms used to analyze and judge a user's emotions.

[0608] A "display device" is a digital device or screen that allows a user to visually confirm information.

[0609] The system for implementing this invention mainly consists of a server, a terminal, and a user interface. The server collects transaction information through a financial institution's software program interface and uses an information storage device to store that information. The collected transaction information is automatically classified into multiple categories using machine learning techniques.

[0610] Meanwhile, the device is equipped with an emotion recognition engine that collects emotional data through facial recognition and voice analysis when the user inputs data. Using libraries such as OpenCV and Google Cloud Speech-to-Text API, it analyzes the user's emotions and determines states such as stress and reassurance. The emotional data is sent to a server and used to adjust the user interface. The interface is optimized based on emotions, improving the user experience.

[0611] For example, if a user shows signs of tension or anxiety during the payment process, the system will detect this and offer relaxation options to simplify the user interface and streamline the payment process. This allows the user to complete the transaction with peace of mind.

[0612] As a concrete example, consider the prompt: "Suggest ways to optimize the UI when the user is feeling anxious." By inputting this prompt into the AI ​​model, the most appropriate interface adjustments for the user will be suggested.

[0613] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0614] Step 1:

[0615] The device is powered on, and the user's facial recognition and voice analysis functions are turned on. The user's face and voice are captured as input, and sentiment data is collected in real time using OpenCV and the Google Cloud Speech-to-Text API. The output is sent to the server as the user's current sentiment state.

[0616] Step 2:

[0617] The server automatically collects transaction information through the financial institution's software program interface. It uses transaction data obtained from the financial institution's API as input and stores the data in an information storage device. The output is a consistent collection of transaction information.

[0618] Step 3:

[0619] The server uses machine learning techniques to classify collected transaction information into multiple categories. Using the stored transaction information as input, the learning model processes the data based on its characteristics and outputs the category classification.

[0620] Step 4:

[0621] The terminal analyzes user emotion data received from the server, and the user interface is adjusted based on this analysis. The user's emotional state is used as input, and data calculations are performed to optimize the interface elements. The output is the adapted interface.

[0622] Step 5:

[0623] During the trading process, the user interacts with the user interface, inputting prompts into the generated AI model and selecting suggested actions. Specifically, the user reviews the presented relaxation options and support messages before proceeding. The input is the user's selection, and the output is either the completion of the trade or further guidance.

[0624] 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.

[0625] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0626] 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.

[0627] [Fourth Embodiment]

[0628] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0629] 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.

[0630] 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).

[0631] 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.

[0632] 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.

[0633] 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).

[0634] 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.

[0635] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0636] 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.

[0637] 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.

[0638] 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.

[0639] 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.

[0640] 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".

[0641] This invention provides a system for users to efficiently collect and classify financial information and automatically generate tax return documents. This system reduces the user's burden through multiple processing steps and creates highly accurate documents in a short amount of time.

[0642] First, the user accesses the system using a terminal. The user grants the system access rights to data from financial institutions whose financial information is collected. Through operations performed via the terminal, the system automatically retrieves transaction data from banks, credit card companies, and other financial institutions.

[0643] The server cleanses the retrieved transaction data through integrity checks, removing inconsistent data. The neatly organized data is stored in the database, ready for subsequent classification processing.

[0644] Next, the server uses machine learning algorithms to classify the data. By categorizing it by income, expenses, and customer, it facilitates data analysis. This classification model continuously learns and gradually improves its accuracy.

[0645] Based on the categorized data, the server automatically generates the necessary documents for tax filing. Users can review and edit the generated documents via their terminal and make any necessary adjustments. The interface is designed to be user-friendly, allowing for efficient editing.

[0646] Ultimately, the server electronically submits the user-verified documents to the tax authorities. This significantly reduces the time and cost associated with physical procedures for the user.

[0647] As a concrete example, consider a scenario where an accounting staff member at a certain company uses this system. The accounting staff member can automatically acquire monthly income and expense data and quickly generate other financial reports based on highly accurate analysis results. Automating this process significantly streamlines accounting tasks that were previously done manually, and reduces human error.

[0648] The following describes the processing flow.

[0649] Step 1:

[0650] The server receives the user's authentication information and obtains a token to access the financial institution's API. This allows the server to securely access the user's bank account and credit card information.

[0651] Step 2:

[0652] The server periodically retrieves transaction data from financial institutions' APIs based on a schedule, collecting the latest data. It can also collect new transaction data in real time if it is generated.

[0653] Step 3:

[0654] The system checks the integrity of transaction data retrieved by the server and filters out duplicate and incorrect data. Inconsistent data is logged, data cleaning is performed, and then the clean data is saved to the database.

[0655] Step 4:

[0656] The server processes the cleansed data in the database and performs automatic classification using machine learning models. For example, it analyzes the data using algorithms to classify it into categories such as income, expenses, and costs.

[0657] Step 5:

[0658] The device displays categorized data on a dashboard, allowing users to visually review the data. Users can interactively view revenue and expenditure trends and detailed information by category.

[0659] Step 6:

[0660] The server automatically generates the necessary documents for tax filing based on the classified data. Using standard templates, it creates documents that accurately reflect the collected data.

[0661] Step 7:

[0662] The user reviews the documents generated via the device and edits them as needed. They then save the edited data and prepare for the next step.

[0663] Step 8:

[0664] The server sends the finalized documents to the corresponding tax authority's electronic submission system, completing the submission process. It also notifies the user of the submission results and guides them through the necessary next steps.

[0665] (Example 1)

[0666] 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".

[0667] Automating the collection and organization of financial information reduces errors and wasted time associated with traditional manual data entry and classification, enabling the creation and submission of more accurate and efficient financial statements.

[0668] 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.

[0669] In this invention, the server includes means for obtaining information access rights from a user, means for automatically collecting financial data via an information exchange interface of a financial institution, means for checking the consistency of the collected financial data and storing it in a storage device, means for dividing the stored financial data into multiple classifications using a calculation method, means for providing an operation screen that allows the user to modify and confirm the generated financial documents, and means for digitally submitting financial documents. This enables increased efficiency and accuracy in financial operations, as well as faster procedures.

[0670] "Information access permission" refers to the permission granted to a user to access specific information or data.

[0671] An "information exchange interface" is a standardized communication method for exchanging data between financial institutions and systems.

[0672] "Financial data" refers to information about the financial activities of individuals or corporations, such as banking transactions and credit card usage information.

[0673] "Checking for consistency" is the process of verifying that there are no inconsistencies or errors in the collected data and ensuring its integrity.

[0674] A "storage device" refers to hardware or software that a system uses to store information.

[0675] "Computational methods" is a general term for algorithms and techniques used for data analysis and classification.

[0676] "Classifying" is the process of organizing data into different categories based on specific criteria.

[0677] An "operation screen" is a visual interface that users use to operate a system and to view or edit data.

[0678] "Applying digitally" refers to a process where documents are submitted online, eliminating the need to send physical documents.

[0679] As an embodiment of this invention, a system is constructed to streamline the management of financial information. This system operates via users, terminals, and servers and includes multiple technical components.

[0680] Users access the system through their terminals and grant the system access rights to financial institution information. This access allows the server to automatically retrieve financial data from banks, credit card companies, and other financial institutions using their information exchange interfaces. The server then verifies the consistency of this data before storing it in storage. This typically involves using programming languages ​​such as Python, and a database management system is used for data consistency verification.

[0681] Next, the server uses computational methods, specifically machine learning algorithms, to categorize the acquired data into multiple categories such as income, expenses, and business partners. This process is carried out using libraries such as Scikit-learn, and the classification model is continuously trained to improve the accuracy of data classification.

[0682] Based on the classified data, the server automatically generates financial statements. This document generation is carried out using templates, and users can review the generated financial statements on a terminal and make corrections as needed. This interface operates through a web browser and is intuitive to use.

[0683] Ultimately, the financial documents reviewed by the user are submitted digitally by the server. This submission is done through an online platform, reducing time and cost compared to paper-based submissions.

[0684] A concrete example is how an accounting staff member at a certain company uses this system to automatically retrieve monthly income and expense data and create quick and accurate financial reports. This reduces manual processes and improves accuracy.

[0685] An example of a prompt message is, "Please explain in detail how this system can be used to streamline monthly income and expense data and generate accurate financial reports."

[0686] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0687] Step 1:

[0688] The user logs into the system using a terminal and enters authentication credentials to access financial institution information. The server receives the entered authentication credentials and uses them to obtain access rights to the financial institution. As an output, the server completes preparation to connect to the financial institution's information exchange interface.

[0689] Step 2:

[0690] The server automatically retrieves financial data from financial institutions using the acquired access permissions. The input is an API endpoint provided by the financial institution. The server accesses this endpoint and collects data including transaction history and account information. This data is aggregated on the server and output as an initial dataset.

[0691] Step 3:

[0692] The server inspects the collected financial data for consistency and performs integrity checks. It detects duplicate data and data in different formats and corrects or deletes them appropriately. The input is the raw acquired data, and the output is a cleansed database entry that is stored.

[0693] Step 4:

[0694] The server uses computational methods to divide the cleansed data into multiple categories. Machine learning algorithms are used to classify data into categories such as income, expenses, and business partners. It takes cleansed data as input and creates a classified dataset as output. This process is performed using libraries such as Scikit-learn.

[0695] Step 5:

[0696] The server automatically generates financial statements based on classified data. This process utilizes pre-configured templates, inserting data into the required fields to create the documents. The input is classified data, and the output is structured financial statements.

[0697] Step 6:

[0698] Users review the financial documents generated via their terminal and edit them as needed. Through the user interface, users visually check the data and correct figures and content. Input is the final document sent from the server, while output is the document approved or modified by the user.

[0699] Step 7:

[0700] The server digitally submits the financial documents that the user has reviewed and corrected. The documents are submitted to the appropriate tax authorities using the online application platform. The input documents are user-approved, and the output documents are officially submitted.

[0701] (Application Example 1)

[0702] 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".

[0703] Traditional systems placed a heavy burden on users in effectively managing financial information and automating tax-related documents, requiring manual input and classification. Furthermore, the lack of sufficient real-time spending and budgeting capabilities meant users were unable to accurately understand their own financial situation.

[0704] 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.

[0705] In this invention, the server includes means for obtaining information access rights from a user, means for automatically collecting data through an interface for information exchange between financial institutions, and means for checking the integrity of the collected data and storing it on an information storage medium. This automates the collection and integrity checking of financial information, thereby reducing the burden on the user. Furthermore, it provides an interactive screen that allows the user to edit and review tax-related documents generated based on classified data, and a display screen that allows the user to visually confirm classified data, thereby providing means for understanding budget achievement status in real time.

[0706] "Information access permissions" refer to the permissions that users need to obtain their own data from financial institutions or other data providers.

[0707] An "interface for information exchange" is a means of communication for efficiently collecting transaction data from financial institutions and other data providers into a system.

[0708] "Information storage medium" refers to computer systems or other storage devices used to store collected data.

[0709] A "machine learning model" is an algorithm that uses data to perform classification and prediction, and its performance is improved based on experience.

[0710] "Classification" is the process of dividing acquired data into different categories based on specific rules or patterns.

[0711] "Tax-related documents" refer to official documents required for tax filing and other financial reporting.

[0712] An "interactive screen" refers to a visual and interactive user interface used by users to view and edit data.

[0713] A "display screen" refers to the screen of a digital device that a user uses to obtain visual information.

[0714] "Budget achievement status" is an indicator that shows the progress of the user's actual spending against their budget plan.

[0715] The system implementing the present invention is configured in which a user, a server, and a terminal cooperate with each other. First, the user uses a terminal to grant the server access rights to information from financial institutions, credit card companies, etc. This operation enables the server to automatically collect transaction data through an information exchange interface provided by the financial institution. The server checks the integrity of the collected data and stores it in an organized format on an information storage medium.

[0716] The server uses a machine learning model to classify stored data into various categories. This machine learning model can evolve over time, improving the accuracy of its classifications. Based on the classified data, the server automatically generates tax-related documents, which users can view and edit from their terminals. The edited documents are then electronically transmitted from the server to the tax authorities.

[0717] Furthermore, the server provides interactive and display screens to the user's terminal, supporting real-time expenditure management and tracking of budget progress. Specifically, users can visually check their daily expenses and monitor their progress against their budget plans.

[0718] For example, when freelance users use this system, their monthly transactions are automatically recorded and categorized, making budget management easier. This eliminates the need to organize data for tax filing at the end of the month, saving time.

[0719] An example of a prompt to input into the generating AI model is, "Please provide the specifications for an application that automatically collects monthly financial data and generates tax return documents."

[0720] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0721] Step 1:

[0722] The server obtains access rights to financial institution information provided by the user via their terminal. This allows the server to retrieve the user's deposit information and expenditure data.

[0723] Step 2:

[0724] The server automatically collects transaction data using an interface for information exchange among financial institutions. The data is retrieved via an API and entered into the server as raw transaction data. Before being organized into a database, the retrieved data undergoes consistency checks to remove duplicates and inconsistencies, and is then processed in a clean manner.

[0725] Step 3:

[0726] The server stores consistent data on an information storage medium. This data forms the basis for future calculations and is recorded in a consistent format to improve the efficiency of classification.

[0727] Step 4:

[0728] The server uses machine learning models to classify stored data into various categories. For example, it can be divided into categories such as income, fixed costs, and variable costs. In this step, machine learning algorithms are used to analyze the data and classify it according to patterns and rules, thereby achieving highly accurate categorization.

[0729] Step 5:

[0730] The server automatically generates tax-related documents based on classified data. In many cases, this process involves using a generation AI model to convert documents belonging to different formats into a consistent template and output them in the optimal format. The output documents are displayed on the user's terminal for editing and review.

[0731] Step 6:

[0732] Users can review tax-related documents generated via their device and edit them as needed. This interface allows users to easily adjust information using operations such as drag-and-drop and filtering.

[0733] Step 7:

[0734] The server electronically transmits the tax-related documents that the user has finished editing to the tax authorities. The timing of transmission and the necessary authentication are adjusted according to the regulations set by the user. This process reduces the time and cost associated with sending physical documents.

[0735] Step 8:

[0736] The server provides users with notifications about their daily spending and budget progress. When pre-set conditions are met, a generated AI model sends alerts to the user's device, indicating budget overruns and savings progress. Based on this, users can effectively manage their daily financial activities.

[0737] 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.

[0738] This invention combines a system that automatically collects and classifies financial data and generates tax documents with an emotion engine that recognizes user emotions. This system provides a customized interface that responds to the user's emotions, resulting in a more user-friendly experience.

[0739] By incorporating an emotion engine, the system can collect emotional data through facial recognition and voice analysis as users interact with the system via their devices. The server analyzes this emotional data to understand the stress levels and emotional tendencies that users experience while entering data or creating declaration forms.

[0740] For example, if a user is experiencing stress while classifying large amounts of transaction data, the server can adjust the terminal's interface and display tutorials and help features to simplify the process. It can also suggest solutions to the user's challenges based on sentiment data.

[0741] Furthermore, the emotion engine can accumulate historical emotional data and display trends. This feature allows users to monitor their own emotional changes over the long term and plan for necessary support and skill development.

[0742] For example, when a user uses the system for the first time, if the emotion engine detects emotions such as anxiety or confusion, the server displays a guide on the interface to assist the user in starting operations smoothly. In this way, utilizing emotion recognition functionality can improve the user experience and enhance the overall usability and effectiveness of the system.

[0743] The following describes the processing flow.

[0744] Step 1:

[0745] The user logs into the system via their device, and the emotion engine begins operating. The system prepares to collect emotion data in real time through the user's facial recognition and voice analysis.

[0746] Step 2:

[0747] The device sends the acquired emotional data to the server. The server performs facial expression analysis and voice tone analysis to determine the user's current emotional state.

[0748] Step 3:

[0749] The server generates an interface tailored to the user's emotional state based on the emotion analysis results. For example, if the user is feeling stressed, the interface's color scheme is changed to one that promotes relaxation.

[0750] Step 4:

[0751] Users collect and categorize financial information. The device provides emotion-responsive user assistance features and displays guides to reduce the complexity of the operation.

[0752] Step 5:

[0753] The server continuously monitors the user's emotional changes during data entry and operation, sending alerts and push notifications as needed. This provides immediate support for any points that might cause the user anxiety.

[0754] Step 6:

[0755] Based on the categorized data, the server automatically generates tax return documents, which the user then reviews on their device. The system also considers the user's emotional state during the generation process, providing suggestions and optimizations.

[0756] Step 7:

[0757] After the user reviews and edits the document, the server manages the final submission and sends the document to the appropriate electronic submission system. At that time, a feedback message is displayed to provide reassurance based on the user's sentiment data.

[0758] (Example 2)

[0759] 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".

[0760] In modern financial data management and tax document preparation processes, users often expend considerable effort and experience significant mental stress. Furthermore, the uniformity of the system makes it difficult to provide services tailored to the individual needs of each user. There is a need for a system that improves this situation and provides a more efficient and user-friendly experience.

[0761] 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.

[0762] In this invention, the server includes means for obtaining data access rights from the user, means for automatically collecting transaction data via the financial institution's application program interface, and means for obtaining and analyzing the user's emotions using an emotion analysis engine. This not only automates the management of financial data and the creation of tax documents, but also enables dynamic interface adjustments in response to the user's emotional state, greatly improving the user experience.

[0763] "Data access permissions" refer to the permissions or authentication information required to allow a user to access data in a system.

[0764] An "application program interface" is an interface or protocol used to share data and functions between different software programs.

[0765] "Transaction data" refers to information and records related to financial transactions, including details such as date, amount, and trading partner.

[0766] "Data storage" refers to a system or device for storing electronic data, and is a device for the secure storage and management of data.

[0767] "Machine learning methods" is a general term for algorithms and methods aimed at enabling computers to learn patterns from data and perform future predictions and classifications.

[0768] A "tax report" is a tax-related report created based on financial transaction data, and is a document used to declare or pay taxes in accordance with the law.

[0769] A "user interface" is the operating environment that includes the screen display and operation methods used by a user to interact with a system.

[0770] An "emotion analysis engine" is software or an algorithm that analyzes data such as a user's facial expressions and voice to infer their emotional state.

[0771] "Dynamic interface tuning" is the process of changing or updating a program's user interface based on the user's current state and requirements.

[0772] This invention provides a system that allows users to efficiently manage their financial data while simultaneously reducing the emotional burden associated with doing so. An embodiment thereof is described below.

[0773] The server first obtains data access permissions from the user. When the user logs into the system through their device, the device uses its camera and microphone to acquire emotional data. This emotional data is sent from the device to the server in real time.

[0774] The server collects this emotional data and analyzes it using an emotion analysis engine. This analysis utilizes facial recognition and voice analysis technologies. Specifically, it uses general emotion analysis engines and tone analysis algorithms. This analysis identifies the user's emotional state (e.g., stress, anxiety, joy, etc.).

[0775] On the other hand, terminals access the financial institution's application program interface via the network and automatically collect transaction data. The server receives the collected transaction data, checks its integrity, and then stores it in data storage. The stored data is classified into multiple categories using machine learning methods. These processes enable the automatic generation of tax reports. This utilizes common data classification algorithms and database management systems.

[0776] The server also provides a user interface that allows users to review and edit generated tax reports. This user interface is dynamically adjusted based on sentiment analysis results. If the user experiences stress or anxiety, tutorials and help functions will appear in the interface to support the user in operating smoothly.

[0777] For example, when a user starts using the system for the first time, their emotions are analyzed, and if anxiety is detected, the server will display a prompt such as, "Would you like to see a guide on how to use the system?" An example of the prompt text would be, "This is your first time using the automated financial data processing system. Please suggest the content of the guide to display when the emotion analysis engine detects user anxiety."

[0778] Thus, the present invention provides a form that enables efficient and comfortable data management and tax document creation while taking user emotions into consideration.

[0779] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0780] Step 1:

[0781] The user logs into the system using a terminal. During this process, the user's authentication information is used as input. Upon successful authentication, the terminal activates its camera and microphone. Specifically, this involves taking a picture of the user's face with the camera and recording their voice with the microphone.

[0782] Step 2:

[0783] The device sends acquired facial image data and audio data to the server. The input consists of facial image data and audio data, and the output is the respective data provided to the server. The server receives this data and passes it to the emotion analysis engine. Specifically, it uses facial recognition and tone analysis algorithms to analyze the user's emotions.

[0784] Step 3:

[0785] The server uses an emotion analysis engine to analyze the user's emotional state. The input is emotion-related data from the previous step, and the output is information determining the user's emotional state (e.g., stress, anxiety, joy). Specifically, it generates emotion tags by comparing the collected data with an existing emotion analysis model.

[0786] Step 4:

[0787] The terminal accesses the financial institution's application program interface via the network and collects transaction data. The input is user-authorized access information to the financial institution, and the output is transaction data obtained via API. At this stage, the terminal collects data at regular intervals according to scheduled tasks.

[0788] Step 5:

[0789] The server receives the collected transaction data and verifies its integrity. The input is the transaction data received from the terminal, and the output is a data set with ensured integrity. Specific operations include data format validation and duplicate data removal.

[0790] Step 6:

[0791] The server stores consistent transaction data in data storage and uses this data to apply machine learning methods. The input is consistent data, and the output is classified data categories. The server repeatedly applies a specific algorithm to classify the data into multiple categories.

[0792] Step 7:

[0793] The server automatically generates tax reports based on classified data. The input is classified data, and the output is a formalized tax report. Specifically, the server arranges the necessary items according to a template and generates the report in PDF format.

[0794] Step 8:

[0795] The server provides a terminal interface that allows the user to edit and review the generated tax report. The input is the generated tax report, and the output is an editable screen that the user can manipulate. The interface dynamically changes according to the user's emotional state, and guides and help functions are added as needed.

[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] Existing financial data management systems often cause user stress because they classify data and create tax documents without considering user emotions. Furthermore, complex interfaces exacerbate the difficulty of operation, detracting from the user experience. Additionally, the lack of personalized support based on user emotions hinders the improvement of the user experience.

[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 automatically collecting transaction information via a financial institution's software program interface, means for analyzing the user's emotional state using an emotion recognition engine and personalizing the interface, and means for enabling the user to edit and review generated tax documents, with their display adjusted based on emotion. This enables user-friendly operation support, improving the user experience.

[0801] "Information access permission" is the process by which a user grants a system permission to access data.

[0802] A "software program interface" is an interface between applications that enables data exchange between different software programs.

[0803] "Transaction information" refers to records and data related to financial transactions.

[0804] An "information storage device" is hardware or media used to store data.

[0805] "Machine learning techniques" are methods that automatically build and train models through data analysis.

[0806] A "category" is a unit of classification that groups together data with similar characteristics.

[0807] "Tax documents" refer to the documents and papers necessary for tax procedures.

[0808] An "interface" is a screen or means of interaction that a user uses to communicate with a system.

[0809] An "emotion recognition engine" is software or algorithms used to analyze and judge a user's emotions.

[0810] A "display device" is a digital device or screen that allows a user to visually confirm information.

[0811] The system for implementing this invention mainly consists of a server, a terminal, and a user interface. The server collects transaction information through a financial institution's software program interface and uses an information storage device to store that information. The collected transaction information is automatically classified into multiple categories using machine learning techniques.

[0812] Meanwhile, the device is equipped with an emotion recognition engine that collects emotional data through facial recognition and voice analysis when the user inputs data. Using libraries such as OpenCV and Google Cloud Speech-to-Text API, it analyzes the user's emotions and determines states such as stress and reassurance. The emotional data is sent to a server and used to adjust the user interface. The interface is optimized based on emotions, improving the user experience.

[0813] For example, if a user shows signs of tension or anxiety during the payment process, the system will detect this and offer relaxation options to simplify the user interface and streamline the payment process. This allows the user to complete the transaction with peace of mind.

[0814] As a concrete example, consider the prompt: "Suggest ways to optimize the UI when the user is feeling anxious." By inputting this prompt into the AI ​​model, the most appropriate interface adjustments for the user will be suggested.

[0815] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0816] Step 1:

[0817] The device is powered on, and the user's facial recognition and voice analysis functions are turned on. The user's face and voice are captured as input, and sentiment data is collected in real time using OpenCV and the Google Cloud Speech-to-Text API. The output is sent to the server as the user's current sentiment state.

[0818] Step 2:

[0819] The server automatically collects transaction information through the financial institution's software program interface. It uses transaction data obtained from the financial institution's API as input and stores the data in an information storage device. The output is a consistent collection of transaction information.

[0820] Step 3:

[0821] The server uses machine learning techniques to classify collected transaction information into multiple categories. Using the stored transaction information as input, the learning model processes the data based on its characteristics and outputs the category classification.

[0822] Step 4:

[0823] The terminal analyzes user emotion data received from the server, and the user interface is adjusted based on this analysis. The user's emotional state is used as input, and data calculations are performed to optimize the interface elements. The output is the adapted interface.

[0824] Step 5:

[0825] During the trading process, the user interacts with the user interface, inputting prompts into the generated AI model and selecting suggested actions. Specifically, the user reviews the presented relaxation options and support messages before proceeding. The input is the user's selection, and the output is either the completion of the trade or further guidance.

[0826] 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.

[0827] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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."

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] The following is further disclosed regarding the embodiments described above.

[0848] (Claim 1)

[0849] Means of obtaining data access permissions from users,

[0850] A means of automatically collecting transaction data through the application program interface of a financial institution,

[0851] A means of checking the integrity of the collected transaction data and saving it to a database,

[0852] A method for classifying stored transaction data into multiple categories using machine learning algorithms,

[0853] A method for automatically generating tax documents based on classified data,

[0854] A means of providing an interface that allows users to edit and review the generated tax documents,

[0855] Methods for submitting tax documents electronically,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, wherein a machine learning algorithm continuously learns a classification model in order to improve the classification accuracy of transaction data.

[0859] (Claim 3)

[0860] The system according to claim 1, comprising an interface that provides a dashboard on which a user can view visually classified data.

[0861] "Example 1"

[0862] (Claim 1)

[0863] Means of obtaining information access rights from users,

[0864] A means of automatically collecting financial data through an information exchange interface between financial institutions,

[0865] A means of checking the consistency of collected financial data and storing it in a storage device,

[0866] A method for dividing stored financial data into multiple classifications using calculation techniques,

[0867] A method for automatically generating financial statements based on classified data,

[0868] A means of providing an operation screen that allows users to modify and review the generated financial statements,

[0869] Methods for submitting financial statements digitally,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, wherein the computational method continuously learns a classification model in order to improve the classification accuracy of financial data.

[0873] (Claim 3)

[0874] The system according to claim 1, comprising an information display screen that allows the user to view visually classified data.

[0875] "Application Example 1"

[0876] (Claim 1)

[0877] Means of obtaining information access rights from users,

[0878] A means of automatically collecting data through an interface for information exchange among financial institutions,

[0879] A means of checking the integrity of the collected data and saving it to an information storage medium,

[0880] A method for dividing stored data into multiple classifications using a machine learning model,

[0881] A means of automatically generating tax-related documents based on classified data,

[0882] A means of providing an interactive screen that allows users to edit and review generated tax-related documents,

[0883] Means for electronically transmitting tax-related documents,

[0884] A means of providing a function to notify about daily spending status,

[0885] A system that includes this.

[0886] (Claim 2)

[0887] The system according to claim 1, wherein a machine learning model continuously learns classification in order to improve the classification accuracy of transaction data, and the system also automatically records the user's financial activities.

[0888] (Claim 3)

[0889] The system according to claim 1, which provides a display screen that allows users to view visually categorized data and has a function to notify users of budget achievement status in real time.

[0890] "Example 2 of combining an emotion engine"

[0891] (Claim 1)

[0892] Means of obtaining data access permissions from users,

[0893] A means of automatically collecting transaction data via a financial institution's application program interface over a network,

[0894] A means of verifying the integrity of the collected transaction data and saving it to data storage,

[0895] A method for classifying stored transaction data into multiple categories using machine learning methods,

[0896] A method for automatically generating tax reports based on classified data,

[0897] A means of providing a user interface that allows users to edit and review the generated tax report,

[0898] Means of electronically transmitting tax reports,

[0899] A means for acquiring and analyzing user emotions using an emotion analysis engine,

[0900] A means of dynamically adjusting the user interface based on the analysis results,

[0901] A system that includes this.

[0902] (Claim 2)

[0903] The system according to claim 1, wherein a machine learning method continuously learns the classification model and sentiment analysis function in order to improve the classification accuracy of transaction data and the user experience.

[0904] (Claim 3)

[0905] The system according to claim 1, comprising a user interface that provides a dashboard on which the user can view visually classified data and sentiment trends.

[0906] "Application example 2 when combining with an emotional engine"

[0907] (Claim 1)

[0908] Means of obtaining access permission for information from a user,

[0909] A means of automatically collecting transaction information through a financial institution's software program interface,

[0910] A means for checking the integrity of collected transaction information and storing it in an information storage device,

[0911] A means of classifying stored transaction information into multiple categories using machine learning techniques,

[0912] A means of automatically generating tax documents based on classified information,

[0913] A means of providing an interface that allows users to edit and review the generated tax documents,

[0914] Methods for submitting tax documents electronically,

[0915] A means of personalizing an interface using an emotion recognition engine that recognizes the user's emotions,

[0916] A system that includes this.

[0917] (Claim 2)

[0918] The system according to claim 1, wherein a machine learning method continuously learns the classification model and analyzes the user's emotional state in order to improve the accuracy of classifying transaction information.

[0919] (Claim 3)

[0920] The system according to claim 1, comprising a user interface that provides a display device that allows a user to view visually classified information, wherein the display is adjusted based on the user's emotional state. [Explanation of Symbols]

[0921] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of obtaining information access rights from users, A means of automatically collecting data through an interface for information exchange among financial institutions, A means of checking the integrity of the collected data and saving it to an information storage medium, A method for dividing stored data into multiple classifications using a machine learning model, A means of automatically generating tax-related documents based on classified data, A means of providing an interactive screen that allows users to edit and review generated tax-related documents, Means for electronically transmitting tax-related documents, A means of providing a function to notify about daily spending status, A system that includes this.

2. The system according to claim 1, wherein a machine learning model continuously learns classification in order to improve the classification accuracy of transaction data, and the system automatically records the user's financial activities.

3. The system according to claim 1, which provides a display screen that allows the user to view visually classified data and has a function to notify the user of budget achievement status in real time.

Images