system

Abstract

We provide the system. [Solution] Means for obtaining user income data and financial data, Means for standardizing acquired data, A means of analyzing users' spending patterns and income structure using standardized data, A means of generating individual tax-saving plans based on analysis results, A means of notifying the user of the generated tax-saving plan, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Since the tax system is complex and it is difficult for individuals and small and medium-sized enterprises to find an optimal tax-saving plan by themselves, there is a need for a system that can comprehensively analyze income and financial situations and propose individually optimized tax-saving measures. Also, in enterprises, the burden of salary calculation and tax processing hinders cost reduction and improvement of business efficiency.

Means for Solving the Problems

[0005] This invention provides a system that uses means to acquire user income and financial data, standardizes this data, and analyzes the income structure and expenditure patterns using an AI agent. It also includes means to generate individual tax-saving plans based on the analysis results and notify the user. Furthermore, by including means to support the implementation of the proposed tax-saving plans and means to automate corporate payroll and tax processing, it enables cost reduction and improved operational efficiency.

[0006] "User" refers to an individual or small business that uses the system.

[0007] "Income data" refers to data that includes information about a user's salary and other sources of income.

[0008] "Financial data" refers to data that includes information related to a user's overall financial situation, such as assets, liabilities, and expenses.

[0009] "Standardization" refers to the process of unifying the format of acquired data so that systems can interpret the data consistently.

[0010] An "AI agent" refers to a program that performs data analysis using machine learning and other artificial intelligence technologies.

[0011] A "tax-saving plan" refers to a customized strategy or action plan provided to minimize the tax burden.

[0012] "Payroll calculation" refers to the process of calculating salaries, allowances, deductions, etc., for employees' work within a company.

[0013] "Tax processing" refers to the process of handling tasks such as preparing tax-related documents, calculations, and filing tax returns.

[0014] "Automation" refers to the efficient execution of processes using computer systems to minimize human involvement. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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.

[0019] 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.

[0020] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] The system according to the present invention consists of multiple modules that work together to streamline tax-related operations for users and companies. A specific embodiment thereof is described below.

[0037] First, the server retrieves the user's income and financial data. This is done using APIs provided by financial institutions and employers, reducing the effort required for users to manually enter information.

[0038] The acquired data is then standardized by the server. Unifying the data format enables consistent data processing across the entire system. For example, converting transaction information received from different bank accounts into a standard format makes analysis easier.

[0039] Next, an AI agent on the server performs data analysis using standardized data. The AI ​​utilizes machine learning algorithms to comprehensively analyze the user's spending patterns and income structure. This analysis forms the basis for creating an optimal tax-saving plan for the user.

[0040] Once the analysis results are integrated, the server generates personalized tax-saving plans, designed to maximize the user's tax benefits. These plans include strategies for utilizing hometown tax donations and simulation results for mortgage interest deductions.

[0041] The generated plan is notified to the user via the device. Based on this information, the user can choose whether or not to take the suggested action. For example, if a proposal for hometown tax donation is made, the device will display a link guiding the user through the donation process.

[0042] Furthermore, for enterprise clients, the server automates payroll and tax processing. This module accurately calculates salaries and deductions based on employee work time data. This allows companies to reduce costs and improve operational efficiency.

[0043] Thus, the present invention provides an effective solution to reduce the tax burden on users and strengthen the competitiveness of companies.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server starts upon receiving a request from the user. The server uses an API to retrieve the user's income and financial data from financial institutions and employers. At this stage, the data is encrypted and securely stored on the server.

[0047] Step 2:

[0048] The server standardizes the acquired data. It unifies differences in data formats and units, converting them into a format that is easy to analyze. For example, it processes data by standardizing dates in different formats or different currency units into a common format.

[0049] Step 3:

[0050] An AI agent on the server analyzes standardized data. This analysis uses machine learning algorithms to identify the user's spending trends and income patterns. As a result, foundational data is obtained to determine which tax-saving plan is optimal.

[0051] Step 4:

[0052] The server generates a personalized tax-saving plan optimized for the user based on the AI ​​analysis results. This plan includes suggestions for specific tax-saving items, such as the optimal amount for hometown tax donations or simulation results for home loans.

[0053] Step 5:

[0054] The terminal notifies the user of a tax-saving plan sent from the server. The user can review the proposed plan through an application on the terminal. Specific implementation steps and necessary links are also provided here.

[0055] Step 6:

[0056] If the user decides to implement the presented tax-saving plan, the device will assist with the process. For example, it will display a link to the online procedure page for making a hometown tax donation, ensuring the user can complete the process smoothly.

[0057] Step 7:

[0058] The server runs modules for businesses to automate payroll and tax processing. Based on employee work hour data and other information, it automatically calculates salaries and deductions, streamlining the company's human resources operations.

[0059] (Example 1)

[0060] 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."

[0061] Many individuals and businesses are seeking ways to efficiently handle complex tax-related procedures. However, these procedures are generally time-consuming, and determining how to maximize tax benefits presents a challenge.

[0062] 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.

[0063] In this invention, the server includes means for acquiring user economic and financial data, means for unifying the acquired data, and means for analyzing the user's spending trends and income distribution using the unified data. This makes it possible to create and implement tax strategies optimized for each individual user.

[0064] "Economic data" refers to a collection of numerical information related to a user's income and expenses, including information such as financial transactions, investments, and salaries.

[0065] "Financial data" refers to information about bank accounts, credit cards, loans, etc., held by individuals or companies, and constitutes a part of economic data.

[0066] "Unification" refers to converting information from different formats into a consistent format, making it analyzable.

[0067] "Spending trends" refer to the characteristics and tendencies that show how users spend their money over a certain period of time.

[0068] "Revenue allocation" refers to information that shows the sources from which a user's revenue is obtained and how it is distributed or used.

[0069] "Analysis" refers to the process of discovering specific patterns or trends based on data and drawing conclusions based on them.

[0070] "Tax planning" refers to plans and measures designed to minimize the tax burden within the bounds of the law.

[0071] To implement this invention, it is necessary to form a system that primarily utilizes multiple modules. The main components of this system include a server for acquiring, unifying, and analyzing the user's economic and financial data.

[0072] The server uses APIs to retrieve critical financial information from users, provided by external financial institutions and employers. This eliminates the need for manual data entry. After the data is retrieved, the server unifies different data formats into a consistent format. Database utilization is particularly key in this process. The unified information is then analyzed using machine learning algorithms to reveal the user's spending trends and income distribution.

[0073] The device notifies the user of tax measures based on the analysis results and provides guidance on how to implement the suggested measures. For example, if a suggestion for hometown tax donation is made, the device will display a link to facilitate the donation process.

[0074] In enterprise applications, the server will automate payroll calculations and tax processing based on data such as working hours.

[0075] As a concrete example, if a user has two different financial accounts, the data obtained from each is unified by the server, analyzed by an AI agent, and then the optimal tax strategy is developed. An example of a prompt message generated during this process would be the following:

[0076] "Analyze the user's income and expenditure data and create the optimal tax-saving plan. Specifically, propose ways to maximize the use of hometown tax donations and mortgage interest deductions."

[0077] In this way, the entire system becomes more efficient, making it possible to provide beneficial tax solutions for users and businesses.

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

[0079] Step 1:

[0080] The server retrieves user economic and financial data from external data sources via APIs. This step uses OAuth authentication for secure data access, retrieving user bank account and credit card transaction information. The input is raw transaction data obtained via the API, while the output is structured data stored on the server.

[0081] Step 2:

[0082] The server unifies the acquired data into a consistent format. This involves integrating different data formats, standardizing date formats, and converting currency units. The input is transaction data in various formats, and the output is a standardized dataset suitable for analysis. For example, it can convert transaction histories from different banks into a common format (e.g., CSV or a database table).

[0083] Step 3:

[0084] An AI agent on the server analyzes the user's spending trends and income distribution using standardized data. The technology used in this step is a machine learning algorithm, which performs pattern recognition and trend analysis. The input is the standardized data from step 2, and the output is insights and reports on the user's financial behavior. Specifically, it calculates income-to-expense ratios and trends in consumption increases and decreases.

[0085] Step 4:

[0086] Based on the analysis results, the server utilizes a generated AI model to construct individual tax strategies. In this step, a tax-saving plan optimized for the user is created and customized as needed. The input is the analysis report obtained in step 3, and the output is the recommended specific tax strategy. Specific actions include calculating the effective amount for hometown tax donations and simulating the optimal amount for mortgage interest deductions.

[0087] Step 5:

[0088] The terminal notifies the user of the generated tax measures and provides guidance for implementing the suggested measures. Here, the user's screen displays actionable steps and provides links to further financial procedures. The input is the tax measures plan created in step 4, and the output is the notification and implementation support for the user. Specifically, the terminal screen displays a link to a hometown tax donation website.

[0089] (Application Example 1)

[0090] 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."

[0091] In today's complex tax environment, effectively managing individual income and expenses and providing optimal tax-saving strategies presents a challenge. Traditional methods require users to manually input and manage diverse information, which is far from efficient. Furthermore, the difficulty in receiving timely tax advice can result in insufficient optimization of individual tax practices.

[0092] 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.

[0093] In this invention, the server includes means for acquiring electronic payment data, means for standardizing the acquired data, and means for generating individual tax optimization plans using the standardized data. This makes it possible to automatically manage the user's spending and income data and provide timely and effective individual tax saving plans and real-time tax advice.

[0094] "Electronic payment data" refers to information related to payments and income made by users using electronic means.

[0095] "Means of standardization" refers to a function that converts data acquired in different formats or types into a unified format.

[0096] A "personalized tax optimization plan" refers to a personalized tax strategy and tax-saving proposal created based on the user's income and expense data.

[0097] "Means of notifying users" refers to communication methods that have the function of providing generated information or plans to the target users.

[0098] "Push notifications" refer to a technology that proactively sends information from a server to a user's device, providing information in real time.

[0099] The embodiment of this invention is a system mainly consisting of a server and a user's terminal. The server begins by acquiring electronic payment data, which is automatically collected via APIs provided by financial institutions and online payment platforms. This processing is carried out using software such as Python or Flask.

[0100] The acquired data is then standardized. Unifying the data format enables consistent data processing and facilitates subsequent analysis. Income and expenditure patterns are analyzed on the server using machine learning frameworks such as TENSORFLOW®.

[0101] Based on an analysis of the user's income structure and spending patterns, a personalized tax optimization plan is generated. This allows the user to maximize their tax benefits. This plan is immediately notified to the user's device, providing real-time tax advice. For example, it may show the user's food spending for the current month or suggest donation destinations for next month's hometown tax donations. The server has the functionality to send the generated plan as a push notification to the device, allowing users to easily take action towards tax optimization in their daily lives.

[0102] An example of a prompt is the instruction, "Analyze spending data and provide users with appropriate tax-saving advice in real time." Through such prompts, the generating AI model provides information that contributes to generating optimal advice.

[0103] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0104] Step 1:

[0105] The server collects user spending and income data via APIs for electronic payment services. These APIs provide data from financial institutions and online payment platforms. The input is user transaction data, and the output is raw transaction data stored on the server.

[0106] Step 2:

[0107] The server standardizes the raw transaction data it receives. It converts the amount, date, category, and other details of each transaction into a unified format. The input is raw transaction data, and the output is data formatted in a standard format. This data processing makes it possible to compare data from different sources.

[0108] Step 3:

[0109] The server analyzes the user's income structure and spending patterns using standardized data. It employs generative AI models and runs machine learning algorithms such as TensorFlow. The input is standardized data, and the output is an analytical report based on the user's income and spending. This report provides the foundational information for optimal tax advice.

[0110] Step 4:

[0111] The server generates a personalized tax optimization plan based on the analysis results. This plan includes specific actions that contribute to tax savings. The input is an analysis report, and the output is a tax-saving plan optimized for the user. This allows the user to receive specific tax-saving suggestions.

[0112] Step 5:

[0113] The server sends the generated tax optimization plan to the user's device as a push notification. The user can then review the plan and follow the suggested actions through their device. The input is the generated plan, and the output is the notification message displayed on the device. This process allows the user to receive useful tax information in real time.

[0114] 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.

[0115] This invention combines a system that analyzes a user's income and financial data to provide an optimal tax-saving plan with an emotion engine. A specific embodiment of this system is shown below.

[0116] First, the server obtains income and financial data through APIs of financial institutions and employers, with the user's consent. The obtained data is encrypted and stored securely.

[0117] Data standardization is performed by the server, ensuring all data is in a unified format. This process makes the data analyzable, improving the accuracy of subsequent analyses.

[0118] Subsequently, the AI ​​agent and emotion engine on the server work together to analyze the data. The AI ​​agent uses machine learning models to identify the user's income structure and spending patterns. Meanwhile, the emotion engine recognizes the user's emotions from past user interactions and survey data, and matches them with the data.

[0119] Based on these analysis results, the server generates a tax-saving plan optimized for the user. In particular, based on emotional data obtained from the emotion engine, it can select a plan structure and communication method that is more likely to convince the user. For example, if the user shows a tendency to dislike risk, the plan will be adjusted to include many proposals that minimize risk.

[0120] The generated plan is notified to the user via their device. The plan details and the steps required for implementation are also displayed, allowing the user to choose their course of action. The sentiment engine also records the user's feedback, which is used to improve future suggestions.

[0121] Furthermore, the server offers enterprise-grade modules for automating payroll and tax processing. This automation allows businesses to improve cost-effectiveness and enhance their competitiveness.

[0122] Thus, the present invention realizes a system that enhances the efficiency and effectiveness of the economic activities of individuals and companies by providing an optimal tax-saving plan that takes into account the user's emotions.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] The server obtains user consent and collects income and financial data from financial institutions and employers via API. This data is securely stored on the server in an encrypted state.

[0126] Step 2:

[0127] The data acquired by the server will be standardized. Different data formats will be unified, and units such as dates and currency will be adjusted to prepare the data for improved accuracy in analysis.

[0128] Step 3:

[0129] An AI agent on the server analyzes standardized data to identify income structures and spending patterns. This analysis provides the information necessary to generate data-driven tax-saving plans.

[0130] Step 4:

[0131] The emotion engine installed on the server extracts emotional data from the user's past interactions and feedback. This process involves emotion recognition to identify the user's risk tendencies and interests.

[0132] Step 5:

[0133] The server integrates the analysis results from the AI ​​agent and the emotion engine to generate a personalized tax-saving plan for the user. Specifically, it adjusts the plan content to take the user's emotions into consideration and selects an appropriate communication strategy.

[0134] Step 6:

[0135] The device notifies the user of the generated tax-saving plan. The device displays detailed information and implementation steps for the proposed plan, allowing the user to choose their course of action.

[0136] Step 7:

[0137] After the user decides whether to accept the suggestion, the device sends the user's choice and feedback back to the emotion engine. This allows the emotion engine to accumulate data and use it to optimize future suggestions.

[0138] Step 8:

[0139] The server runs modules for businesses that automate payroll and tax processing. Based on employee data, accurate payroll and tax processing are performed, streamlining the company's human resources operations.

[0140] (Example 2)

[0141] 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".

[0142] In modern economic activity, individuals and organizations need efficient tax burden reduction measures, but often face challenges such as the significant effort required to collect and interpret relevant information, and a lack of proposals that take into account individual emotional states. In addition, organizations face operational costs due to insufficient automation of payroll and tax management.

[0143] 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.

[0144] In this invention, the server includes means for acquiring the user's economic information, means for converting the acquired information into a unified format, means for analyzing the user's spending tendencies and income structure using the information converted into the unified format, means for generating individual tax burden reduction measures based on the analysis results, means for notifying the user of the generated tax burden reduction measures, means for determining the user's emotional state and adjusting the proposals accordingly, and means for automating the organization's payroll calculation and tax management. This enables the provision of efficient tax-saving plans tailored to individual characteristics and reduces operating costs for companies.

[0145] "Economic information" refers to financial data related to a user's income, expenses, and taxes.

[0146] "Converting to a unified format" refers to the process of aligning data acquired in different formats or types to a consistent standard.

[0147] "Spending trends" refer to data that shows patterns and trends in users' consumption behavior.

[0148] "Revenue structure" refers to information that systematically captures a user's sources of income and types of income.

[0149] "Tax burden reduction measures" refer to specific plans and methods designed to minimize the amount of taxes a user pays.

[0150] "Emotional state" refers to information that indicates a user's psychological tendencies and preferences.

[0151] "Payroll calculation" refers to the process of calculating and paying employee wages within an organization.

[0152] "Tax management" refers to the administrative tasks required for an organization or individual to calculate, file, and pay taxes in accordance with tax laws.

[0153] In a configuration for implementing this invention, the server is first built on a cloud platform and has the function of collecting users' economic information. The server collects data from financial institutions and employers using a dedicated API. The collected data is securely stored using AES encryption.

[0154] The server then uses ETL (Extract, Transform, Load) tools to standardize income and expenditure information into a unified format. This ensures that data in any format can be consistently analyzed. For example, unifying different date formats into one enables time-series analysis.

[0155] In the next step, the server uses an AI agent to analyze the user's spending habits and income structure. This AI agent is based on a machine learning model, and particularly utilizes reinforcement learning to improve its accuracy over time. The emotion engine analyzes past survey results and user-entered feedback to recognize individual emotional states, such as whether the user tends to be risk-averse.

[0156] Based on the analysis results, the server utilizes information from the emotion engine to generate a tax burden reduction plan optimized for the user. The generated plan is then notified to the user via their device. To aid user understanding, specific steps and expected effects are also presented in detail.

[0157] Furthermore, the server has the capability to automate the organization's payroll and tax management and integrates with the company's ERP system. This integration allows organizations to reduce data entry and manual calculations, improving operational efficiency.

[0158] For example, if a user states that they "want to save money for an overseas trip," the AI ​​agent will analyze this information and suggest tax-saving methods to free up funds for the trip from their income and expenses. In this case, a prompt containing the keyword "travel" might be something like, "Generate tax-saving suggestions based on the areas the user is interested in. The current interest is 'travel.' Please come up with recommended tax-saving plans to fund the trip."

[0159] As described above, this invention provides a system that enables highly accurate and efficient management and analysis of economic information tailored to the needs of individuals and businesses, and in particular, makes it possible to make suggestions that take into account the emotional state of the user.

[0160] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0161] Step 1:

[0162] The server collects economic information from financial institutions and employers via APIs, with the user's permission. The input for this step is raw data obtained through the API, and the output is the encrypted form of the obtained data. Specifically, it sends a request to the API, receives the response data, and protects it using AES encryption technology.

[0163] Step 2:

[0164] The server decrypts the encrypted data and uses ETL tools to convert the data into a unified format. The input for this step is encrypted data, and the output is standardized data. Specific standardization operations include unifying date formats and converting numerical units. This process transforms information in different formats into a consistent, parseable structure.

[0165] Step 3:

[0166] The server inputs standardized data into an AI agent to analyze user spending patterns and income structure. This analysis utilizes a machine learning model, with input consisting of standardized data and historical datasets, and outputting information on analyzed consumption patterns and income composition. Specifically, it employs reinforcement learning algorithms for pattern recognition and prediction.

[0167] Step 4:

[0168] The server uses an emotion engine to determine the user's emotional state and combines it with the output of an AI agent to generate tax reduction strategies. The input for this step is analyzed economic information and user emotion data, and the output is a tax-saving plan optimized for the user. Specifically, it performs emotion analysis on past surveys and feedback data and provides advice based on the user profile.

[0169] Step 5:

[0170] The terminal notifies the user of tax reduction measures obtained from the server. The input here is the tax-saving plan generated by the server, and the output is the specific plan information displayed on the user's terminal. Specifically, the proposed content is visualized using text and graphics to make it easy for the user to understand.

[0171] Step 6:

[0172] Users review the tax reduction measures displayed on their devices and provide feedback. The input consists of user feedback information, while the output is sentiment and feedback data sent to the server. Specifically, this involves collecting user satisfaction and areas for improvement through open-ended and multiple-choice questionnaires.

[0173] Step 7:

[0174] The server performs functions to automate the organization's payroll and tax management, integrating data into the company's ERP system. The input for this step is the company's employee data and tax information, and the output is automatically processed payroll calculations and tax reports. Specific operations include aggregating payroll data, calculating taxes, and generating reports that comply with regulations.

[0175] (Application Example 2)

[0176] 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".

[0177] In recent years, both individuals and businesses have been seeking efficient financial management and tax savings. However, existing tax-saving solutions fail to consider users' emotions and payment history, lacking optimal planning that is easy for users to implement. Therefore, there is a need to develop a system that can provide the most suitable tax-saving strategy for each user.

[0178] 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.

[0179] In this invention, the server includes means for acquiring the user's economic and financial data, means for unifying the acquired data, means for analyzing the user's consumption trends and income structure using the unified data, and means for analyzing electronic transaction history and providing tax-saving suggestions based on that analysis. This makes it possible to present appropriate tax-saving measures in real time based on the user's payment history and emotions.

[0180] "User economic data" refers to the collective information regarding an individual's or company's income, assets, liabilities, and expenses.

[0181] "Financial data" refers to information such as income and expenditure, deposits, and investments that is necessary to show a financial situation.

[0182] "Standardization" refers to the process of aligning data from different formats into a common format.

[0183] "Consumer trends" refer to the tendency of users to spend money on goods and services on a daily basis.

[0184] "Income structure" refers to the breakdown of a user's income and its fluctuations.

[0185] "Analysis" is the process of analyzing data to find specific patterns or meanings.

[0186] "Electronic transaction history" refers to records of past payments and purchases made by a user, recorded in a digital format.

[0187] A "tax-saving proposal" refers to specific measures or plans aimed at reducing the tax burden while complying with the law.

[0188] This invention provides a system that enables individuals and businesses to effectively reduce their taxes. This system consists of a server and user terminals, and utilizes various software to perform data processing and provide information.

[0189] First, the server collects users' income and financial data from financial institutions and related data providers via APIs. This data is encrypted for security reasons and stored securely. Software such as Python and APIs are used.

[0190] Next, the server unifies the collected data and converts it to a standard format. This makes data analysis easier. Then, machine learning models are introduced to analyze user consumption trends and revenue structures. Libraries such as Scikit-Learn are used for this purpose.

[0191] Furthermore, the server analyzes the user's electronic transaction history and generates optimal tax-saving suggestions based on the user's spending habits. In this process, an emotion engine is used to consider the user's emotional data, enabling more personalized suggestions.

[0192] The generated tax-saving suggestions are notified to the user's device. This is done via devices such as smartphones and smart glasses, making them easily accessible. Based on this information, the user can choose specific tax-saving actions.

[0193] For example, a user who tends to eat out more often at the end of the month can be prompted with "Would you like some tax-saving strategies to reduce your dining-out expenses this month?" based on their past spending and sentiment data. An example of the prompt would be: "Analyze the user's spending data, predict the spending categories likely to increase next, and generate relevant tax-saving suggestions." This allows for the presentation of appropriate tax-saving strategies to the user in real time.

[0194] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0195] Step 1:

[0196] The server retrieves user income and financial data from financial institutions and related data providers via APIs. The input is raw data provided by the APIs, and the output is encrypted data. This data is stored using encryption technology for security reasons.

[0197] Step 2:

[0198] The server standardizes the acquired raw data into a unified format. By using encrypted data as input and performing data format conversion, analyzable data is obtained as output. Schema mapping technology is used in this process to maintain data integrity.

[0199] Step 3:

[0200] The server analyzes user consumption trends and income structures using standardized data. The input is unified data, and the output is the analysis results regarding user spending patterns and income structures. Here, machine learning libraries such as Scikit-Learn are utilized to apply classification and clustering models.

[0201] Step 4:

[0202] The server further analyzes the electronic transaction history based on the analyzed data and generates appropriate tax-saving suggestions. The inputs are the analysis results and transaction history, and the output is a proposed tax-saving strategy. This suggestion is based on the user's past transaction history, while also considering the user's preferences as perceived by the emotion engine.

[0203] Step 5:

[0204] The terminal notifies the user of the generated tax-saving proposals. The input is tax-saving proposal information from the server, and the output is a notification message to the user. The user receives this notification and can refer to the specific proposal details to take action.

[0205] Step 6:

[0206] Users provide feedback based on the tax-saving suggestions they receive from their devices. This feedback information is sent to the server to improve the quality of future suggestions, and is continuously analyzed by an emotion engine. The input is user feedback, and the output is data that leads to the optimization of suggestions.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] [Second Embodiment]

[0211] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0212] 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.

[0213] 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).

[0214] 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.

[0215] 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.

[0216] 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).

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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".

[0223] The system according to the present invention consists of multiple modules that work together to streamline tax-related operations for users and companies. A specific embodiment thereof is described below.

[0224] First, the server retrieves the user's income and financial data. This is done using APIs provided by financial institutions and employers, reducing the effort required for users to manually enter information.

[0225] The acquired data is then standardized by the server. Unifying the data format enables consistent data processing across the entire system. For example, converting transaction information received from different bank accounts into a standard format makes analysis easier.

[0226] Next, an AI agent on the server performs data analysis using standardized data. The AI ​​utilizes machine learning algorithms to comprehensively analyze the user's spending patterns and income structure. This analysis forms the basis for creating an optimal tax-saving plan for the user.

[0227] Once the analysis results are integrated, the server generates personalized tax-saving plans, designed to maximize the user's tax benefits. These plans include strategies for utilizing hometown tax donations and simulation results for mortgage interest deductions.

[0228] The generated plan is notified to the user via the device. Based on this information, the user can choose whether or not to take the suggested action. For example, if a proposal for hometown tax donation is made, the device will display a link guiding the user through the donation process.

[0229] Furthermore, for enterprise clients, the server automates payroll and tax processing. This module accurately calculates salaries and deductions based on employee work time data. This allows companies to reduce costs and improve operational efficiency.

[0230] Thus, the present invention provides an effective solution to reduce the tax burden on users and strengthen the competitiveness of companies.

[0231] The following describes the processing flow.

[0232] Step 1:

[0233] The server starts upon receiving a request from the user. The server uses an API to retrieve the user's income and financial data from financial institutions and employers. At this stage, the data is encrypted and securely stored on the server.

[0234] Step 2:

[0235] The server standardizes the acquired data. It unifies differences in data formats and units, converting them into a format that is easy to analyze. For example, it processes data by standardizing dates in different formats or different currency units into a common format.

[0236] Step 3:

[0237] An AI agent on the server analyzes standardized data. This analysis uses machine learning algorithms to identify the user's spending trends and income patterns. As a result, foundational data is obtained to determine which tax-saving plan is optimal.

[0238] Step 4:

[0239] The server generates a personalized tax-saving plan optimized for the user based on the AI ​​analysis results. This plan includes suggestions for specific tax-saving items, such as the optimal amount for hometown tax donations or simulation results for home loans.

[0240] Step 5:

[0241] The terminal notifies the user of a tax-saving plan sent from the server. The user can review the proposed plan through an application on the terminal. Specific implementation steps and necessary links are also provided here.

[0242] Step 6:

[0243] If the user decides to implement the presented tax-saving plan, the device will assist with the process. For example, it will display a link to the online procedure page for making a hometown tax donation, ensuring the user can complete the process smoothly.

[0244] Step 7:

[0245] The server runs modules for businesses to automate payroll and tax processing. Based on employee work hour data and other information, it automatically calculates salaries and deductions, streamlining the company's human resources operations.

[0246] (Example 1)

[0247] 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."

[0248] Many individuals and businesses are seeking ways to efficiently handle complex tax-related procedures. However, these procedures are generally time-consuming, and determining how to maximize tax benefits presents a challenge.

[0249] 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.

[0250] In this invention, the server includes means for acquiring user economic and financial data, means for unifying the acquired data, and means for analyzing the user's spending trends and income distribution using the unified data. This makes it possible to create and implement tax strategies optimized for each individual user.

[0251] "Economic data" refers to a collection of numerical information related to a user's income and expenses, including information such as financial transactions, investments, and salaries.

[0252] "Financial data" refers to information about bank accounts, credit cards, loans, etc., held by individuals or companies, and constitutes a part of economic data.

[0253] "Unification" refers to converting information from different formats into a consistent format, making it analyzable.

[0254] "Spending trends" refer to the characteristics and tendencies that show how users spend their money over a certain period of time.

[0255] "Revenue allocation" refers to information that shows the sources from which a user's revenue is obtained and how it is distributed or used.

[0256] "Analysis" refers to the process of discovering specific patterns or trends based on data and drawing conclusions based on them.

[0257] "Tax planning" refers to plans and measures designed to minimize the tax burden within the bounds of the law.

[0258] To implement this invention, it is necessary to form a system that primarily utilizes multiple modules. The main components of this system include a server for acquiring, unifying, and analyzing the user's economic and financial data.

[0259] The server uses APIs to retrieve critical financial information from users, provided by external financial institutions and employers. This eliminates the need for manual data entry. After the data is retrieved, the server unifies different data formats into a consistent format. Database utilization is particularly key in this process. The unified information is then analyzed using machine learning algorithms to reveal the user's spending trends and income distribution.

[0260] The device notifies the user of tax measures based on the analysis results and provides guidance on how to implement the suggested measures. For example, if a suggestion for hometown tax donation is made, the device will display a link to facilitate the donation process.

[0261] In enterprise applications, the server will automate payroll calculations and tax processing based on data such as working hours.

[0262] As a concrete example, if a user has two different financial accounts, the data obtained from each is unified by the server, analyzed by an AI agent, and then the optimal tax strategy is developed. An example of a prompt message generated during this process would be the following:

[0263] "Analyze the user's income and expenditure data and create the optimal tax-saving plan. Specifically, propose ways to maximize the use of hometown tax donations and mortgage interest deductions."

[0264] In this way, the entire system becomes more efficient, making it possible to provide beneficial tax solutions for users and businesses.

[0265] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0266] Step 1:

[0267] The server retrieves user economic and financial data from external data sources via APIs. This step uses OAuth authentication for secure data access, retrieving user bank account and credit card transaction information. The input is raw transaction data obtained via the API, while the output is structured data stored on the server.

[0268] Step 2:

[0269] The server unifies the acquired data into a consistent format. This involves integrating different data formats, standardizing date formats, and converting currency units. The input is transaction data in various formats, and the output is a standardized dataset suitable for analysis. For example, it can convert transaction histories from different banks into a common format (e.g., CSV or a database table).

[0270] Step 3:

[0271] An AI agent on the server analyzes the user's spending trends and income distribution using standardized data. The technology used in this step is a machine learning algorithm, which performs pattern recognition and trend analysis. The input is the standardized data from step 2, and the output is insights and reports on the user's financial behavior. Specifically, it calculates income-to-expense ratios and trends in consumption increases and decreases.

[0272] Step 4:

[0273] Based on the analysis results, the server utilizes a generated AI model to construct individual tax strategies. In this step, a tax-saving plan optimized for the user is created and customized as needed. The input is the analysis report obtained in step 3, and the output is the recommended specific tax strategy. Specific actions include calculating the effective amount for hometown tax donations and simulating the optimal amount for mortgage interest deductions.

[0274] Step 5:

[0275] The terminal notifies the user of the generated tax measures and provides guidance for implementing the suggested measures. Here, the user's screen displays actionable steps and provides links to further financial procedures. The input is the tax measures plan created in step 4, and the output is the notification and implementation support for the user. Specifically, the terminal screen displays a link to a hometown tax donation website.

[0276] (Application Example 1)

[0277] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0278] In the modern complex tax environment, there is a problem that it is difficult to effectively manage personal income and expenses and provide optimal tax-saving measures. In the conventional method, the user needs to manually input and manage various information, which is hardly efficient. Also, since it is difficult to receive timely tax advice, personal tax optimization may be insufficient.

[0279] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0280] In this invention, the server includes means for acquiring electronic payment data, means for standardizing the acquired data, and means for generating an individual tax optimization plan using the standardized data. Thereby, by automatically managing the user's expenditure and income data, it becomes possible to provide timely and effective individual tax-saving plans and real-time tax advice.

[0281] "Electronic payment data" refers to information related to payments and income made by the user using electronic means.

[0282] "Means for standardizing" refers to a function for converting data acquired in different forms or formats into a unified form.

[0283] "Individual tax optimization plan" refers to a proposal for a tax strategy and tax-saving measures specialized for an individual, created based on the user's income and expenditure data.

[0284] "Means for notifying the user" refers to a communication method having a function of providing the generated information and plan to the target user.

[0285] "Push notification" refers to a technology that actively transmits information from a server to a user's terminal and provides information in real time.

[0286] The form for implementing this invention is mainly a system composed of a server and a user's terminal. The server begins by acquiring electronic payment data, which is automatically collected via APIs provided by financial institutions or online payment platforms. This processing is performed using software such as Python and Flask.

[0287] The acquired data is then standardized. By unifying the data format, consistent data processing is enabled and preparations are made for subsequent analysis to proceed smoothly. Using a machine learning framework such as TensorFlow, data on income and expenditure patterns is analyzed within the server.

[0288] Based on the analysis results of the user's income structure and expenditure patterns, an individual tax optimization plan is generated. As a result, the user can obtain the maximum tax benefits. This plan is immediately notified to the user's terminal, providing real-time tax advice. For example, it may show the status of this month's food expenses or propose hometown tax payment destinations for next month. The server has the function of sending the generated plan to the terminal as a push notification, enabling the user to easily take action towards tax optimization in daily life.

[0289] As an example of a prompt sentence, there is an instruction such as "Analyze the expenditure data and provide appropriate tax-saving advice to the user in real time." Through such a prompt, the generative AI model provides information useful for generating optimal advice.

[0290] The flow of specific processing in Application Example 1 will be described using Figure 12.

[0291] Step 1:

[0292] The server collects user spending and income data via APIs for electronic payment services. These APIs provide data from financial institutions and online payment platforms. The input is user transaction data, and the output is raw transaction data stored on the server.

[0293] Step 2:

[0294] The server standardizes the raw transaction data it receives. It converts the amount, date, category, and other details of each transaction into a unified format. The input is raw transaction data, and the output is data formatted in a standard format. This data processing makes it possible to compare data from different sources.

[0295] Step 3:

[0296] The server analyzes the user's income structure and spending patterns using standardized data. It employs generative AI models and runs machine learning algorithms such as TensorFlow. The input is standardized data, and the output is an analytical report based on the user's income and spending. This report provides the foundational information for optimal tax advice.

[0297] Step 4:

[0298] The server generates a personalized tax optimization plan based on the analysis results. This plan includes specific actions that contribute to tax savings. The input is an analysis report, and the output is a tax-saving plan optimized for the user. This allows the user to receive specific tax-saving suggestions.

[0299] Step 5:

[0300] The server sends the generated tax optimization plan to the user's device as a push notification. The user can then review the plan and follow the suggested actions through their device. The input is the generated plan, and the output is the notification message displayed on the device. This process allows the user to receive useful tax information in real time.

[0301] 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.

[0302] This invention combines a system that analyzes a user's income and financial data to provide an optimal tax-saving plan with an emotion engine. A specific embodiment of this system is shown below.

[0303] First, the server obtains income and financial data through APIs of financial institutions and employers, with the user's consent. The obtained data is encrypted and stored securely.

[0304] Data standardization is performed by the server, ensuring all data is in a unified format. This process makes the data analyzable, improving the accuracy of subsequent analyses.

[0305] Subsequently, the AI ​​agent and emotion engine on the server work together to analyze the data. The AI ​​agent uses machine learning models to identify the user's income structure and spending patterns. Meanwhile, the emotion engine recognizes the user's emotions from past user interactions and survey data, and matches them with the data.

[0306] Based on these analysis results, the server generates a tax-saving plan optimized for the user. In particular, based on the emotion data obtained from the emotion engine, it is possible to select a plan configuration and communication method that are easy for the user to accept. For example, if the user shows a tendency to dislike risks, the plan is adjusted to include many proposals that minimize risks.

[0307] The generated plan is notified to the user via the terminal. The specific details of the plan and the procedures required for execution are also displayed, and the user can select actions based on this reference. In addition, the emotion engine records what kind of feedback the user has given and utilizes it for improving future proposals.

[0308] Furthermore, as a function for enterprises, the server provides modules that automate salary calculation and tax processing. Through the automation of these operations, enterprises can enhance cost-effectiveness and competitiveness.

[0309] In this way, the present invention realizes a system for enhancing the efficiency and effectiveness in the economic activities of individuals and enterprises by providing an optimal tax-saving plan that takes into account the emotions of users.

[0310] The following describes the processing flow.

[0311] Step 1:

[0312] The server obtains consent from the user and collects income data and financial data from financial institutions and employers via the API. This data is securely stored on the server in an encrypted state.

[0313] Step 2:

[0314] The server standardizes the data obtained. It unifies different data formats, adjusts units such as dates and currencies, and prepares for improving the accuracy of data analysis.

[0315] Step 3:

[0316] An AI agent on the server analyzes standardized data to identify income structures and spending patterns. This analysis provides the information necessary to generate data-driven tax-saving plans.

[0317] Step 4:

[0318] The emotion engine installed on the server extracts emotional data from the user's past interactions and feedback. This process involves emotion recognition to identify the user's risk tendencies and interests.

[0319] Step 5:

[0320] The server integrates the analysis results from the AI ​​agent and the emotion engine to generate a personalized tax-saving plan for the user. Specifically, it adjusts the plan content to take the user's emotions into consideration and selects an appropriate communication strategy.

[0321] Step 6:

[0322] The device notifies the user of the generated tax-saving plan. The device displays detailed information and implementation steps for the proposed plan, allowing the user to choose their course of action.

[0323] Step 7:

[0324] After the user decides whether to accept the suggestion, the device sends the user's choice and feedback back to the emotion engine. This allows the emotion engine to accumulate data and use it to optimize future suggestions.

[0325] Step 8:

[0326] The server runs modules for businesses that automate payroll and tax processing. Based on employee data, accurate payroll and tax processing are performed, streamlining the company's human resources operations.

[0327] (Example 2)

[0328] 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".

[0329] In modern economic activity, individuals and organizations need efficient tax burden reduction measures, but often face challenges such as the significant effort required to collect and interpret relevant information, and a lack of proposals that take into account individual emotional states. In addition, organizations face operational costs due to insufficient automation of payroll and tax management.

[0330] 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.

[0331] In this invention, the server includes means for acquiring the user's economic information, means for converting the acquired information into a unified format, means for analyzing the user's spending tendencies and income structure using the information converted into the unified format, means for generating individual tax burden reduction measures based on the analysis results, means for notifying the user of the generated tax burden reduction measures, means for determining the user's emotional state and adjusting the proposals accordingly, and means for automating the organization's payroll calculation and tax management. This enables the provision of efficient tax-saving plans tailored to individual characteristics and reduces operating costs for companies.

[0332] "Economic information" refers to financial data related to a user's income, expenses, and taxes.

[0333] "Converting to a unified format" refers to the process of aligning data acquired in different formats or types to a consistent standard.

[0334] "Spending trends" refer to data that shows patterns and trends in users' consumption behavior.

[0335] "Revenue structure" refers to information that systematically captures a user's sources of income and types of income.

[0336] "Tax burden reduction measures" refer to specific plans and methods designed to minimize the amount of taxes a user pays.

[0337] "Emotional state" refers to information that indicates a user's psychological tendencies and preferences.

[0338] "Payroll calculation" refers to the process of calculating and paying employee wages within an organization.

[0339] "Tax management" refers to the administrative tasks required for an organization or individual to calculate, file, and pay taxes in accordance with tax laws.

[0340] In a configuration for implementing this invention, the server is first built on a cloud platform and has the function of collecting users' economic information. The server collects data from financial institutions and employers using a dedicated API. The collected data is securely stored using AES encryption.

[0341] The server then uses ETL (Extract, Transform, Load) tools to standardize income and expenditure information into a unified format. This ensures that data in any format can be consistently analyzed. For example, unifying different date formats into one enables time-series analysis.

[0342] In the next step, the server uses an AI agent to analyze the user's spending habits and income structure. This AI agent is based on a machine learning model, and particularly utilizes reinforcement learning to improve its accuracy over time. The emotion engine analyzes past survey results and user-entered feedback to recognize individual emotional states, such as whether the user tends to be risk-averse.

[0343] Based on the analysis results, the server utilizes information from the emotion engine to generate a tax burden reduction plan optimized for the user. The generated plan is then notified to the user via their device. To aid user understanding, specific steps and expected effects are also presented in detail.

[0344] Furthermore, the server has the capability to automate the organization's payroll and tax management and integrates with the company's ERP system. This integration allows organizations to reduce data entry and manual calculations, improving operational efficiency.

[0345] For example, if a user states that they "want to save money for an overseas trip," the AI ​​agent will analyze this information and suggest tax-saving methods to free up funds for the trip from their income and expenses. In this case, a prompt containing the keyword "travel" might be something like, "Generate tax-saving suggestions based on the areas the user is interested in. The current interest is 'travel.' Please come up with recommended tax-saving plans to fund the trip."

[0346] As described above, this invention provides a system that enables highly accurate and efficient management and analysis of economic information tailored to the needs of individuals and businesses, and in particular, makes it possible to make suggestions that take into account the emotional state of the user.

[0347] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0348] Step 1:

[0349] The server collects economic information from financial institutions and employers via APIs, with the user's permission. The input for this step is raw data obtained through the API, and the output is the encrypted form of the obtained data. Specifically, it sends a request to the API, receives the response data, and protects it using AES encryption technology.

[0350] Step 2:

[0351] The server decrypts the encrypted data and uses ETL tools to convert the data into a unified format. The input for this step is encrypted data, and the output is standardized data. Specific standardization operations include unifying date formats and converting numerical units. This process transforms information in different formats into a consistent, parseable structure.

[0352] Step 3:

[0353] The server inputs standardized data into an AI agent to analyze user spending patterns and income structure. This analysis utilizes a machine learning model, with input consisting of standardized data and historical datasets, and outputting information on analyzed consumption patterns and income composition. Specifically, it employs reinforcement learning algorithms for pattern recognition and prediction.

[0354] Step 4:

[0355] The server uses an emotion engine to determine the user's emotional state and combines it with the output of an AI agent to generate tax reduction strategies. The input for this step is analyzed economic information and user emotion data, and the output is a tax-saving plan optimized for the user. Specifically, it performs emotion analysis on past surveys and feedback data and provides advice based on the user profile.

[0356] Step 5:

[0357] The terminal notifies the user of tax reduction measures obtained from the server. The input here is the tax-saving plan generated by the server, and the output is the specific plan information displayed on the user's terminal. Specifically, the proposed content is visualized using text and graphics to make it easy for the user to understand.

[0358] Step 6:

[0359] Users review the tax reduction measures displayed on their devices and provide feedback. The input consists of user feedback information, while the output is sentiment and feedback data sent to the server. Specifically, this involves collecting user satisfaction and areas for improvement through open-ended and multiple-choice questionnaires.

[0360] Step 7:

[0361] The server performs functions to automate the organization's payroll and tax management, integrating data into the company's ERP system. The input for this step is the company's employee data and tax information, and the output is automatically processed payroll calculations and tax reports. Specific operations include aggregating payroll data, calculating taxes, and generating reports that comply with regulations.

[0362] (Application Example 2)

[0363] 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."

[0364] In recent years, both individuals and businesses have been seeking efficient financial management and tax savings. However, existing tax-saving solutions fail to consider users' emotions and payment history, lacking optimal planning that is easy for users to implement. Therefore, there is a need to develop a system that can provide the most suitable tax-saving strategy for each user.

[0365] 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.

[0366] In this invention, the server includes means for acquiring the user's economic and financial data, means for unifying the acquired data, means for analyzing the user's consumption trends and income structure using the unified data, and means for analyzing electronic transaction history and providing tax-saving suggestions based on that analysis. This makes it possible to present appropriate tax-saving measures in real time based on the user's payment history and emotions.

[0367] "User economic data" refers to the collective information regarding an individual's or company's income, assets, liabilities, and expenses.

[0368] "Financial data" refers to information such as income and expenditure, deposits, and investments that is necessary to show a financial situation.

[0369] "Standardization" refers to the process of aligning data from different formats into a common format.

[0370] "Consumer trends" refer to the tendency of users to spend money on goods and services on a daily basis.

[0371] "Income structure" refers to the breakdown of a user's income and its fluctuations.

[0372] "Analysis" is the process of analyzing data to find specific patterns or meanings.

[0373] "Electronic transaction history" refers to records of past payments and purchases made by a user, recorded in a digital format.

[0374] A "tax-saving proposal" refers to specific measures or plans aimed at reducing the tax burden while complying with the law.

[0375] This invention provides a system that enables individuals and businesses to effectively reduce their taxes. This system consists of a server and user terminals, and utilizes various software to perform data processing and provide information.

[0376] First, the server collects users' income and financial data from financial institutions and related data providers via APIs. This data is encrypted for security reasons and stored securely. Software such as Python and APIs are used.

[0377] Next, the server unifies the collected data and converts it to a standard format. This makes data analysis easier. Then, machine learning models are introduced to analyze user consumption trends and revenue structures. Libraries such as Scikit-Learn are used for this purpose.

[0378] Furthermore, the server analyzes the user's electronic transaction history and generates optimal tax-saving suggestions based on the user's spending habits. In this process, an emotion engine is used to consider the user's emotional data, enabling more personalized suggestions.

[0379] The generated tax-saving suggestions are notified to the user's device. This is done via devices such as smartphones and smart glasses, making them easily accessible. Based on this information, the user can choose specific tax-saving actions.

[0380] For example, a user who tends to eat out more often at the end of the month can be prompted with "Would you like some tax-saving strategies to reduce your dining-out expenses this month?" based on their past spending and sentiment data. An example of the prompt would be: "Analyze the user's spending data, predict the spending categories likely to increase next, and generate relevant tax-saving suggestions." This allows for the presentation of appropriate tax-saving strategies to the user in real time.

[0381] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0382] Step 1:

[0383] The server retrieves user income and financial data from financial institutions and related data providers via APIs. The input is raw data provided by the APIs, and the output is encrypted data. This data is stored using encryption technology for security reasons.

[0384] Step 2:

[0385] The server standardizes the acquired raw data into a unified format. By using encrypted data as input and performing data format conversion, analyzable data is obtained as output. Schema mapping technology is used in this process to maintain data integrity.

[0386] Step 3:

[0387] The server analyzes user consumption trends and income structures using standardized data. The input is unified data, and the output is the analysis results regarding user spending patterns and income structures. Here, machine learning libraries such as Scikit-Learn are utilized to apply classification and clustering models.

[0388] Step 4:

[0389] The server further analyzes the electronic transaction history based on the analyzed data and generates appropriate tax-saving suggestions. The inputs are the analysis results and transaction history, and the output is a proposed tax-saving strategy. This suggestion is based on the user's past transaction history, while also considering the user's preferences as perceived by the emotion engine.

[0390] Step 5:

[0391] The terminal notifies the user of the generated tax-saving proposals. The input is tax-saving proposal information from the server, and the output is a notification message to the user. The user receives this notification and can refer to the specific proposal details to take action.

[0392] Step 6:

[0393] Users provide feedback based on the tax-saving suggestions they receive from their devices. This feedback information is sent to the server to improve the quality of future suggestions, and is continuously analyzed by an emotion engine. The input is user feedback, and the output is data that leads to the optimization of suggestions.

[0394] 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.

[0395] 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.

[0396] 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.

[0397] [Third Embodiment]

[0398] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0399] 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.

[0400] 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).

[0401] 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.

[0402] 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.

[0403] 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).

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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".

[0410] The system according to the present invention consists of multiple modules that work together to streamline tax-related operations for users and companies. A specific embodiment thereof is described below.

[0411] First, the server retrieves the user's income and financial data. This is done using APIs provided by financial institutions and employers, reducing the effort required for users to manually enter information.

[0412] The acquired data is then standardized by the server. Unifying the data format enables consistent data processing across the entire system. For example, converting transaction information received from different bank accounts into a standard format makes analysis easier.

[0413] Next, an AI agent on the server performs data analysis using standardized data. The AI ​​utilizes machine learning algorithms to comprehensively analyze the user's spending patterns and income structure. This analysis forms the basis for creating an optimal tax-saving plan for the user.

[0414] Once the analysis results are integrated, the server generates personalized tax-saving plans, designed to maximize the user's tax benefits. These plans include strategies for utilizing hometown tax donations and simulation results for mortgage interest deductions.

[0415] The generated plan is notified to the user via the device. Based on this information, the user can choose whether or not to take the suggested action. For example, if a proposal for hometown tax donation is made, the device will display a link guiding the user through the donation process.

[0416] Furthermore, for enterprise clients, the server automates payroll and tax processing. This module accurately calculates salaries and deductions based on employee work time data. This allows companies to reduce costs and improve operational efficiency.

[0417] Thus, the present invention provides an effective solution to reduce the tax burden on users and strengthen the competitiveness of companies.

[0418] The following describes the processing flow.

[0419] Step 1:

[0420] The server starts upon receiving a request from the user. The server uses an API to retrieve the user's income and financial data from financial institutions and employers. At this stage, the data is encrypted and securely stored on the server.

[0421] Step 2:

[0422] The server standardizes the acquired data. It unifies differences in data formats and units, converting them into a format that is easy to analyze. For example, it processes data by standardizing dates in different formats or different currency units into a common format.

[0423] Step 3:

[0424] An AI agent on the server analyzes standardized data. This analysis uses machine learning algorithms to identify the user's spending trends and income patterns. As a result, foundational data is obtained to determine which tax-saving plan is optimal.

[0425] Step 4:

[0426] The server generates a personalized tax-saving plan optimized for the user based on the AI ​​analysis results. This plan includes suggestions for specific tax-saving items, such as the optimal amount for hometown tax donations or simulation results for home loans.

[0427] Step 5:

[0428] The terminal notifies the user of a tax-saving plan sent from the server. The user can review the proposed plan through an application on the terminal. Specific implementation steps and necessary links are also provided here.

[0429] Step 6:

[0430] If the user decides to implement the presented tax-saving plan, the device will assist with the process. For example, it will display a link to the online procedure page for making a hometown tax donation, ensuring the user can complete the process smoothly.

[0431] Step 7:

[0432] The server runs modules for businesses to automate payroll and tax processing. Based on employee work hour data and other information, it automatically calculates salaries and deductions, streamlining the company's human resources operations.

[0433] (Example 1)

[0434] 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."

[0435] Many individuals and businesses are seeking ways to efficiently handle complex tax-related procedures. However, these procedures are generally time-consuming, and determining how to maximize tax benefits presents a challenge.

[0436] 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.

[0437] In this invention, the server includes means for acquiring user economic and financial data, means for unifying the acquired data, and means for analyzing the user's spending trends and income distribution using the unified data. This makes it possible to create and implement tax strategies optimized for each individual user.

[0438] "Economic data" refers to a collection of numerical information related to a user's income and expenses, including information such as financial transactions, investments, and salaries.

[0439] "Financial data" refers to information about bank accounts, credit cards, loans, etc., held by individuals or companies, and constitutes a part of economic data.

[0440] "Unification" refers to converting information from different formats into a consistent format, making it analyzable.

[0441] "Spending trends" refer to the characteristics and tendencies that show how users spend their money over a certain period of time.

[0442] "Revenue allocation" refers to information that shows the sources from which a user's revenue is obtained and how it is distributed or used.

[0443] "Analysis" refers to the process of discovering specific patterns or trends based on data and drawing conclusions based on them.

[0444] "Tax planning" refers to plans and measures designed to minimize the tax burden within the bounds of the law.

[0445] To implement this invention, it is necessary to form a system that primarily utilizes multiple modules. The main components of this system include a server for acquiring, unifying, and analyzing the user's economic and financial data.

[0446] The server uses APIs to retrieve critical financial information from users, provided by external financial institutions and employers. This eliminates the need for manual data entry. After the data is retrieved, the server unifies different data formats into a consistent format. Database utilization is particularly key in this process. The unified information is then analyzed using machine learning algorithms to reveal the user's spending trends and income distribution.

[0447] The device notifies the user of tax measures based on the analysis results and provides guidance on how to implement the suggested measures. For example, if a suggestion for hometown tax donation is made, the device will display a link to facilitate the donation process.

[0448] In enterprise applications, the server will automate payroll calculations and tax processing based on data such as working hours.

[0449] As a concrete example, if a user has two different financial accounts, the data obtained from each is unified by the server, analyzed by an AI agent, and then the optimal tax strategy is developed. An example of a prompt message generated during this process would be the following:

[0450] "Analyze the user's income and expenditure data and create the optimal tax-saving plan. Specifically, propose ways to maximize the use of hometown tax donations and mortgage interest deductions."

[0451] In this way, the entire system becomes more efficient, making it possible to provide beneficial tax solutions for users and businesses.

[0452] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0453] Step 1:

[0454] The server retrieves user economic and financial data from external data sources via APIs. This step uses OAuth authentication for secure data access, retrieving user bank account and credit card transaction information. The input is raw transaction data obtained via the API, while the output is structured data stored on the server.

[0455] Step 2:

[0456] The server unifies the acquired data into a consistent format. This involves integrating different data formats, standardizing date formats, and converting currency units. The input is transaction data in various formats, and the output is a standardized dataset suitable for analysis. For example, it can convert transaction histories from different banks into a common format (e.g., CSV or a database table).

[0457] Step 3:

[0458] An AI agent on the server analyzes the user's spending trends and income distribution using standardized data. The technology used in this step is a machine learning algorithm, which performs pattern recognition and trend analysis. The input is the standardized data from step 2, and the output is insights and reports on the user's financial behavior. Specifically, it calculates income-to-expense ratios and trends in consumption increases and decreases.

[0459] Step 4:

[0460] Based on the analysis results, the server utilizes a generated AI model to construct individual tax strategies. In this step, a tax-saving plan optimized for the user is created and customized as needed. The input is the analysis report obtained in step 3, and the output is the recommended specific tax strategy. Specific actions include calculating the effective amount for hometown tax donations and simulating the optimal amount for mortgage interest deductions.

[0461] Step 5:

[0462] The terminal notifies the user of the generated tax measures and provides guidance for implementing the suggested measures. Here, the user's screen displays actionable steps and provides links to further financial procedures. The input is the tax measures plan created in step 4, and the output is the notification and implementation support for the user. Specifically, the terminal screen displays a link to a hometown tax donation website.

[0463] (Application Example 1)

[0464] 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."

[0465] In today's complex tax environment, effectively managing individual income and expenses and providing optimal tax-saving strategies presents a challenge. Traditional methods require users to manually input and manage diverse information, which is far from efficient. Furthermore, the difficulty in receiving timely tax advice can result in insufficient optimization of individual tax practices.

[0466] 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.

[0467] In this invention, the server includes means for acquiring electronic payment data, means for standardizing the acquired data, and means for generating individual tax optimization plans using the standardized data. This makes it possible to automatically manage the user's spending and income data and provide timely and effective individual tax saving plans and real-time tax advice.

[0468] "Electronic payment data" refers to information related to payments and income made by users using electronic means.

[0469] "Means of standardization" refers to a function that converts data acquired in different formats or types into a unified format.

[0470] A "personalized tax optimization plan" refers to a personalized tax strategy and tax-saving proposal created based on the user's income and expense data.

[0471] "Means of notifying users" refers to communication methods that have the function of providing generated information or plans to the target users.

[0472] "Push notifications" refer to a technology that proactively sends information from a server to a user's device, providing information in real time.

[0473] The embodiment of this invention is a system mainly consisting of a server and a user's terminal. The server begins by acquiring electronic payment data, which is automatically collected via APIs provided by financial institutions and online payment platforms. This processing is carried out using software such as Python or Flask.

[0474] The acquired data is then standardized. Unifying the data format enables consistent data processing and facilitates smooth subsequent analysis. Income and expenditure patterns are analyzed on the server using machine learning frameworks such as TensorFlow.

[0475] Based on an analysis of the user's income structure and spending patterns, a personalized tax optimization plan is generated. This allows the user to maximize their tax benefits. This plan is immediately notified to the user's device, providing real-time tax advice. For example, it may show the user's food spending for the current month or suggest donation destinations for next month's hometown tax donations. The server has the functionality to send the generated plan as a push notification to the device, allowing users to easily take action towards tax optimization in their daily lives.

[0476] An example of a prompt is the instruction, "Analyze spending data and provide users with appropriate tax-saving advice in real time." Through such prompts, the generating AI model provides information that contributes to generating optimal advice.

[0477] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0478] Step 1:

[0479] The server collects user spending and income data via APIs for electronic payment services. These APIs provide data from financial institutions and online payment platforms. The input is user transaction data, and the output is raw transaction data stored on the server.

[0480] Step 2:

[0481] The server standardizes the raw transaction data it receives. It converts the amount, date, category, and other details of each transaction into a unified format. The input is raw transaction data, and the output is data formatted in a standard format. This data processing makes it possible to compare data from different sources.

[0482] Step 3:

[0483] The server analyzes the user's income structure and spending patterns using standardized data. It employs generative AI models and runs machine learning algorithms such as TensorFlow. The input is standardized data, and the output is an analytical report based on the user's income and spending. This report provides the foundational information for optimal tax advice.

[0484] Step 4:

[0485] The server generates a personalized tax optimization plan based on the analysis results. This plan includes specific actions that contribute to tax savings. The input is an analysis report, and the output is a tax-saving plan optimized for the user. This allows the user to receive specific tax-saving suggestions.

[0486] Step 5:

[0487] The server sends the generated tax optimization plan to the user's device as a push notification. The user can then review the plan and follow the suggested actions through their device. The input is the generated plan, and the output is the notification message displayed on the device. This process allows the user to receive useful tax information in real time.

[0488] 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.

[0489] This invention combines a system that analyzes a user's income and financial data to provide an optimal tax-saving plan with an emotion engine. A specific embodiment of this system is shown below.

[0490] First, the server obtains income and financial data through APIs of financial institutions and employers, with the user's consent. The obtained data is encrypted and stored securely.

[0491] Data standardization is performed by the server, ensuring all data is in a unified format. This process makes the data analyzable, improving the accuracy of subsequent analyses.

[0492] Subsequently, the AI ​​agent and emotion engine on the server work together to analyze the data. The AI ​​agent uses machine learning models to identify the user's income structure and spending patterns. Meanwhile, the emotion engine recognizes the user's emotions from past user interactions and survey data, and matches them with the data.

[0493] Based on these analysis results, the server generates a tax-saving plan optimized for the user. In particular, based on emotional data obtained from the emotion engine, it can select a plan structure and communication method that is more likely to convince the user. For example, if the user shows a tendency to dislike risk, the plan will be adjusted to include many proposals that minimize risk.

[0494] The generated plan is notified to the user via their device. The plan details and the steps required for implementation are also displayed, allowing the user to choose their course of action. The sentiment engine also records the user's feedback, which is used to improve future suggestions.

[0495] Furthermore, the server offers enterprise-grade modules for automating payroll and tax processing. This automation allows businesses to improve cost-effectiveness and enhance their competitiveness.

[0496] Thus, the present invention realizes a system that enhances the efficiency and effectiveness of the economic activities of individuals and companies by providing an optimal tax-saving plan that takes into account the user's emotions.

[0497] The following describes the processing flow.

[0498] Step 1:

[0499] The server obtains user consent and collects income and financial data from financial institutions and employers via API. This data is securely stored on the server in an encrypted state.

[0500] Step 2:

[0501] The data acquired by the server will be standardized. Different data formats will be unified, and units such as dates and currency will be adjusted to prepare the data for improved accuracy in analysis.

[0502] Step 3:

[0503] An AI agent on the server analyzes standardized data to identify income structures and spending patterns. This analysis provides the information necessary to generate data-driven tax-saving plans.

[0504] Step 4:

[0505] The emotion engine installed on the server extracts emotional data from the user's past interactions and feedback. This process involves emotion recognition to identify the user's risk tendencies and interests.

[0506] Step 5:

[0507] The server integrates the analysis results from the AI ​​agent and the emotion engine to generate a personalized tax-saving plan for the user. Specifically, it adjusts the plan content to take the user's emotions into consideration and selects an appropriate communication strategy.

[0508] Step 6:

[0509] The device notifies the user of the generated tax-saving plan. The device displays detailed information and implementation steps for the proposed plan, allowing the user to choose their course of action.

[0510] Step 7:

[0511] After the user decides whether to accept the suggestion, the device sends the user's choice and feedback back to the emotion engine. This allows the emotion engine to accumulate data and use it to optimize future suggestions.

[0512] Step 8:

[0513] The server runs modules for businesses that automate payroll and tax processing. Based on employee data, accurate payroll and tax processing are performed, streamlining the company's human resources operations.

[0514] (Example 2)

[0515] 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."

[0516] In modern economic activity, individuals and organizations need efficient tax burden reduction measures, but often face challenges such as the significant effort required to collect and interpret relevant information, and a lack of proposals that take into account individual emotional states. In addition, organizations face operational costs due to insufficient automation of payroll and tax management.

[0517] 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.

[0518] In this invention, the server includes means for acquiring the user's economic information, means for converting the acquired information into a unified format, means for analyzing the user's spending tendencies and income structure using the information converted into the unified format, means for generating individual tax burden reduction measures based on the analysis results, means for notifying the user of the generated tax burden reduction measures, means for determining the user's emotional state and adjusting the proposals accordingly, and means for automating the organization's payroll calculation and tax management. This enables the provision of efficient tax-saving plans tailored to individual characteristics and reduces operating costs for companies.

[0519] "Economic information" refers to financial data related to a user's income, expenses, and taxes.

[0520] "Converting to a unified format" refers to the process of aligning data acquired in different formats or types to a consistent standard.

[0521] "Spending trends" refer to data that shows patterns and trends in users' consumption behavior.

[0522] "Revenue structure" refers to information that systematically captures a user's sources of income and types of income.

[0523] "Tax burden reduction measures" refer to specific plans and methods designed to minimize the amount of taxes a user pays.

[0524] "Emotional state" refers to information that indicates a user's psychological tendencies and preferences.

[0525] "Payroll calculation" refers to the process of calculating and paying employee wages within an organization.

[0526] "Tax management" refers to the administrative tasks required for an organization or individual to calculate, file, and pay taxes in accordance with tax laws.

[0527] In a configuration for implementing this invention, the server is first built on a cloud platform and has the function of collecting users' economic information. The server collects data from financial institutions and employers using a dedicated API. The collected data is securely stored using AES encryption.

[0528] The server then uses ETL (Extract, Transform, Load) tools to standardize income and expenditure information into a unified format. This ensures that data in any format can be consistently analyzed. For example, unifying different date formats into one enables time-series analysis.

[0529] In the next step, the server uses an AI agent to analyze the user's spending habits and income structure. This AI agent is based on a machine learning model, and particularly utilizes reinforcement learning to improve its accuracy over time. The emotion engine analyzes past survey results and user-entered feedback to recognize individual emotional states, such as whether the user tends to be risk-averse.

[0530] Based on the analysis results, the server utilizes information from the emotion engine to generate a tax burden reduction plan optimized for the user. The generated plan is then notified to the user via their device. To aid user understanding, specific steps and expected effects are also presented in detail.

[0531] Furthermore, the server has the capability to automate the organization's payroll and tax management and integrates with the company's ERP system. This integration allows organizations to reduce data entry and manual calculations, improving operational efficiency.

[0532] For example, if a user states that they "want to save money for an overseas trip," the AI ​​agent will analyze this information and suggest tax-saving methods to free up funds for the trip from their income and expenses. In this case, a prompt containing the keyword "travel" might be something like, "Generate tax-saving suggestions based on the areas the user is interested in. The current interest is 'travel.' Please come up with recommended tax-saving plans to fund the trip."

[0533] As described above, this invention provides a system that enables highly accurate and efficient management and analysis of economic information tailored to the needs of individuals and businesses, and in particular, makes it possible to make suggestions that take into account the emotional state of the user.

[0534] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0535] Step 1:

[0536] The server collects economic information from financial institutions and employers via APIs, with the user's permission. The input for this step is raw data obtained through the API, and the output is the encrypted form of the obtained data. Specifically, it sends a request to the API, receives the response data, and protects it using AES encryption technology.

[0537] Step 2:

[0538] The server decrypts the encrypted data and uses ETL tools to convert the data into a unified format. The input for this step is encrypted data, and the output is standardized data. Specific standardization operations include unifying date formats and converting numerical units. This process transforms information in different formats into a consistent, parseable structure.

[0539] Step 3:

[0540] The server inputs standardized data into an AI agent to analyze user spending patterns and income structure. This analysis utilizes a machine learning model, with input consisting of standardized data and historical datasets, and outputting information on analyzed consumption patterns and income composition. Specifically, it employs reinforcement learning algorithms for pattern recognition and prediction.

[0541] Step 4:

[0542] The server uses an emotion engine to determine the user's emotional state and combines it with the output of an AI agent to generate tax reduction strategies. The input for this step is analyzed economic information and user emotion data, and the output is a tax-saving plan optimized for the user. Specifically, it performs emotion analysis on past surveys and feedback data and provides advice based on the user profile.

[0543] Step 5:

[0544] The terminal notifies the user of tax reduction measures obtained from the server. The input here is the tax-saving plan generated by the server, and the output is the specific plan information displayed on the user's terminal. Specifically, the proposed content is visualized using text and graphics to make it easy for the user to understand.

[0545] Step 6:

[0546] Users review the tax reduction measures displayed on their devices and provide feedback. The input consists of user feedback information, while the output is sentiment and feedback data sent to the server. Specifically, this involves collecting user satisfaction and areas for improvement through open-ended and multiple-choice questionnaires.

[0547] Step 7:

[0548] The server performs functions to automate the organization's payroll and tax management, integrating data into the company's ERP system. The input for this step is the company's employee data and tax information, and the output is automatically processed payroll calculations and tax reports. Specific operations include aggregating payroll data, calculating taxes, and generating reports that comply with regulations.

[0549] (Application Example 2)

[0550] 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."

[0551] In recent years, both individuals and businesses have been seeking efficient financial management and tax savings. However, existing tax-saving solutions fail to consider users' emotions and payment history, lacking optimal planning that is easy for users to implement. Therefore, there is a need to develop a system that can provide the most suitable tax-saving strategy for each user.

[0552] 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.

[0553] In this invention, the server includes means for acquiring the user's economic and financial data, means for unifying the acquired data, means for analyzing the user's consumption trends and income structure using the unified data, and means for analyzing electronic transaction history and providing tax-saving suggestions based on that analysis. This makes it possible to present appropriate tax-saving measures in real time based on the user's payment history and emotions.

[0554] "User economic data" refers to the collective information regarding an individual's or company's income, assets, liabilities, and expenses.

[0555] "Financial data" refers to information such as income and expenditure, deposits, and investments that is necessary to show a financial situation.

[0556] "Standardization" refers to the process of aligning data from different formats into a common format.

[0557] "Consumer trends" refer to the tendency of users to spend money on goods and services on a daily basis.

[0558] "Income structure" refers to the breakdown of a user's income and its fluctuations.

[0559] "Analysis" is the process of analyzing data to find specific patterns or meanings.

[0560] "Electronic transaction history" refers to records of past payments and purchases made by a user, recorded in a digital format.

[0561] A "tax-saving proposal" refers to specific measures or plans aimed at reducing the tax burden while complying with the law.

[0562] This invention provides a system that enables individuals and businesses to effectively reduce their taxes. This system consists of a server and user terminals, and utilizes various software to perform data processing and provide information.

[0563] First, the server collects users' income and financial data from financial institutions and related data providers via APIs. This data is encrypted for security reasons and stored securely. Software such as Python and APIs are used.

[0564] Next, the server unifies the collected data and converts it to a standard format. This makes data analysis easier. Then, machine learning models are introduced to analyze user consumption trends and revenue structures. Libraries such as Scikit-Learn are used for this purpose.

[0565] Furthermore, the server analyzes the user's electronic transaction history and generates optimal tax-saving suggestions based on the user's spending habits. In this process, an emotion engine is used to consider the user's emotional data, enabling more personalized suggestions.

[0566] The generated tax-saving suggestions are notified to the user's device. This is done via devices such as smartphones and smart glasses, making them easily accessible. Based on this information, the user can choose specific tax-saving actions.

[0567] For example, a user who tends to eat out more often at the end of the month can be prompted with "Would you like some tax-saving strategies to reduce your dining-out expenses this month?" based on their past spending and sentiment data. An example of the prompt would be: "Analyze the user's spending data, predict the spending categories likely to increase next, and generate relevant tax-saving suggestions." This allows for the presentation of appropriate tax-saving strategies to the user in real time.

[0568] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0569] Step 1:

[0570] The server retrieves user income and financial data from financial institutions and related data providers via APIs. The input is raw data provided by the APIs, and the output is encrypted data. This data is stored using encryption technology for security reasons.

[0571] Step 2:

[0572] The server standardizes the acquired raw data into a unified format. By using encrypted data as input and performing data format conversion, analyzable data is obtained as output. Schema mapping technology is used in this process to maintain data integrity.

[0573] Step 3:

[0574] The server analyzes user consumption trends and income structures using standardized data. The input is unified data, and the output is the analysis results regarding user spending patterns and income structures. Here, machine learning libraries such as Scikit-Learn are utilized to apply classification and clustering models.

[0575] Step 4:

[0576] The server further analyzes the electronic transaction history based on the analyzed data and generates appropriate tax-saving suggestions. The inputs are the analysis results and transaction history, and the output is a proposed tax-saving strategy. This suggestion is based on the user's past transaction history, while also considering the user's preferences as perceived by the emotion engine.

[0577] Step 5:

[0578] The terminal notifies the user of the generated tax-saving proposals. The input is tax-saving proposal information from the server, and the output is a notification message to the user. The user receives this notification and can refer to the specific proposal details to take action.

[0579] Step 6:

[0580] Users provide feedback based on the tax-saving suggestions they receive from their devices. This feedback information is sent to the server to improve the quality of future suggestions, and is continuously analyzed by an emotion engine. The input is user feedback, and the output is data that leads to the optimization of suggestions.

[0581] 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.

[0582] 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.

[0583] 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.

[0584] [Fourth Embodiment]

[0585] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0586] 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.

[0587] 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).

[0588] 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.

[0589] 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.

[0590] 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).

[0591] 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.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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".

[0598] The system according to the present invention consists of multiple modules that work together to streamline tax-related operations for users and companies. A specific embodiment thereof is described below.

[0599] First, the server retrieves the user's income and financial data. This is done using APIs provided by financial institutions and employers, reducing the effort required for users to manually enter information.

[0600] The acquired data is then standardized by the server. Unifying the data format enables consistent data processing across the entire system. For example, converting transaction information received from different bank accounts into a standard format makes analysis easier.

[0601] Next, an AI agent on the server performs data analysis using standardized data. The AI ​​utilizes machine learning algorithms to comprehensively analyze the user's spending patterns and income structure. This analysis forms the basis for creating an optimal tax-saving plan for the user.

[0602] Once the analysis results are integrated, the server generates personalized tax-saving plans, designed to maximize the user's tax benefits. These plans include strategies for utilizing hometown tax donations and simulation results for mortgage interest deductions.

[0603] The generated plan is notified to the user via the device. Based on this information, the user can choose whether or not to take the suggested action. For example, if a proposal for hometown tax donation is made, the device will display a link guiding the user through the donation process.

[0604] Furthermore, for enterprise clients, the server automates payroll and tax processing. This module accurately calculates salaries and deductions based on employee work time data. This allows companies to reduce costs and improve operational efficiency.

[0605] Thus, the present invention provides an effective solution to reduce the tax burden on users and strengthen the competitiveness of companies.

[0606] The following describes the processing flow.

[0607] Step 1:

[0608] The server starts upon receiving a request from the user. The server uses an API to retrieve the user's income and financial data from financial institutions and employers. At this stage, the data is encrypted and securely stored on the server.

[0609] Step 2:

[0610] The server standardizes the acquired data. It unifies differences in data formats and units, converting them into a format that is easy to analyze. For example, it processes data by standardizing dates in different formats or different currency units into a common format.

[0611] Step 3:

[0612] An AI agent on the server analyzes standardized data. This analysis uses machine learning algorithms to identify the user's spending trends and income patterns. As a result, foundational data is obtained to determine which tax-saving plan is optimal.

[0613] Step 4:

[0614] The server generates a personalized tax-saving plan optimized for the user based on the AI ​​analysis results. This plan includes suggestions for specific tax-saving items, such as the optimal amount for hometown tax donations or simulation results for home loans.

[0615] Step 5:

[0616] The terminal notifies the user of a tax-saving plan sent from the server. The user can review the proposed plan through an application on the terminal. Specific implementation steps and necessary links are also provided here.

[0617] Step 6:

[0618] If the user decides to implement the presented tax-saving plan, the device will assist with the process. For example, it will display a link to the online procedure page for making a hometown tax donation, ensuring the user can complete the process smoothly.

[0619] Step 7:

[0620] The server runs modules for businesses to automate payroll and tax processing. Based on employee work hour data and other information, it automatically calculates salaries and deductions, streamlining the company's human resources operations.

[0621] (Example 1)

[0622] 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".

[0623] Many individuals and businesses are seeking ways to efficiently handle complex tax-related procedures. However, these procedures are generally time-consuming, and determining how to maximize tax benefits presents a challenge.

[0624] 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.

[0625] In this invention, the server includes means for acquiring user economic and financial data, means for unifying the acquired data, and means for analyzing the user's spending trends and income distribution using the unified data. This makes it possible to create and implement tax strategies optimized for each individual user.

[0626] "Economic data" refers to a collection of numerical information related to a user's income and expenses, including information such as financial transactions, investments, and salaries.

[0627] "Financial data" refers to information about bank accounts, credit cards, loans, etc., held by individuals or companies, and constitutes a part of economic data.

[0628] "Unification" refers to converting information from different formats into a consistent format, making it analyzable.

[0629] "Spending trends" refer to the characteristics and tendencies that show how users spend their money over a certain period of time.

[0630] "Revenue allocation" refers to information that shows the sources from which a user's revenue is obtained and how it is distributed or used.

[0631] "Analysis" refers to the process of discovering specific patterns or trends based on data and drawing conclusions based on them.

[0632] "Tax planning" refers to plans and measures designed to minimize the tax burden within the bounds of the law.

[0633] To implement this invention, it is necessary to form a system that primarily utilizes multiple modules. The main components of this system include a server for acquiring, unifying, and analyzing the user's economic and financial data.

[0634] The server uses APIs to retrieve critical financial information from users, provided by external financial institutions and employers. This eliminates the need for manual data entry. After the data is retrieved, the server unifies different data formats into a consistent format. Database utilization is particularly key in this process. The unified information is then analyzed using machine learning algorithms to reveal the user's spending trends and income distribution.

[0635] The device notifies the user of tax measures based on the analysis results and provides guidance on how to implement the suggested measures. For example, if a suggestion for hometown tax donation is made, the device will display a link to facilitate the donation process.

[0636] In enterprise applications, the server will automate payroll calculations and tax processing based on data such as working hours.

[0637] As a concrete example, if a user has two different financial accounts, the data obtained from each is unified by the server, analyzed by an AI agent, and then the optimal tax strategy is developed. An example of a prompt message generated during this process would be the following:

[0638] "Analyze the user's income and expenditure data and create the optimal tax-saving plan. Specifically, propose ways to maximize the use of hometown tax donations and mortgage interest deductions."

[0639] In this way, the entire system becomes more efficient, making it possible to provide beneficial tax solutions for users and businesses.

[0640] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0641] Step 1:

[0642] The server retrieves user economic and financial data from external data sources via APIs. This step uses OAuth authentication for secure data access, retrieving user bank account and credit card transaction information. The input is raw transaction data obtained via the API, while the output is structured data stored on the server.

[0643] Step 2:

[0644] The server unifies the acquired data into a consistent format. This involves integrating different data formats, standardizing date formats, and converting currency units. The input is transaction data in various formats, and the output is a standardized dataset suitable for analysis. For example, it can convert transaction histories from different banks into a common format (e.g., CSV or a database table).

[0645] Step 3:

[0646] An AI agent on the server analyzes the user's spending trends and income distribution using standardized data. The technology used in this step is a machine learning algorithm, which performs pattern recognition and trend analysis. The input is the standardized data from step 2, and the output is insights and reports on the user's financial behavior. Specifically, it calculates income-to-expense ratios and trends in consumption increases and decreases.

[0647] Step 4:

[0648] Based on the analysis results, the server utilizes a generated AI model to construct individual tax strategies. In this step, a tax-saving plan optimized for the user is created and customized as needed. The input is the analysis report obtained in step 3, and the output is the recommended specific tax strategy. Specific actions include calculating the effective amount for hometown tax donations and simulating the optimal amount for mortgage interest deductions.

[0649] Step 5:

[0650] The terminal notifies the user of the generated tax measures and provides guidance for implementing the suggested measures. Here, the user's screen displays actionable steps and provides links to further financial procedures. The input is the tax measures plan created in step 4, and the output is the notification and implementation support for the user. Specifically, the terminal screen displays a link to a hometown tax donation website.

[0651] (Application Example 1)

[0652] 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".

[0653] In today's complex tax environment, effectively managing individual income and expenses and providing optimal tax-saving strategies presents a challenge. Traditional methods require users to manually input and manage diverse information, which is far from efficient. Furthermore, the difficulty in receiving timely tax advice can result in insufficient optimization of individual tax practices.

[0654] 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.

[0655] In this invention, the server includes means for acquiring electronic payment data, means for standardizing the acquired data, and means for generating individual tax optimization plans using the standardized data. This makes it possible to automatically manage the user's spending and income data and provide timely and effective individual tax saving plans and real-time tax advice.

[0656] "Electronic payment data" refers to information related to payments and income made by users using electronic means.

[0657] "Means of standardization" refers to a function that converts data acquired in different formats or types into a unified format.

[0658] A "personalized tax optimization plan" refers to a personalized tax strategy and tax-saving proposal created based on the user's income and expense data.

[0659] "Means of notifying users" refers to communication methods that have the function of providing generated information or plans to the target users.

[0660] "Push notifications" refer to a technology that proactively sends information from a server to a user's device, providing information in real time.

[0661] The embodiment of this invention is a system mainly consisting of a server and a user's terminal. The server begins by acquiring electronic payment data, which is automatically collected via APIs provided by financial institutions and online payment platforms. This processing is carried out using software such as Python or Flask.

[0662] The acquired data is then standardized. Unifying the data format enables consistent data processing and facilitates smooth subsequent analysis. Income and expenditure patterns are analyzed on the server using machine learning frameworks such as TensorFlow.

[0663] Based on an analysis of the user's income structure and spending patterns, a personalized tax optimization plan is generated. This allows the user to maximize their tax benefits. This plan is immediately notified to the user's device, providing real-time tax advice. For example, it may show the user's food spending for the current month or suggest donation destinations for next month's hometown tax donations. The server has the functionality to send the generated plan as a push notification to the device, allowing users to easily take action towards tax optimization in their daily lives.

[0664] An example of a prompt is the instruction, "Analyze spending data and provide users with appropriate tax-saving advice in real time." Through such prompts, the generating AI model provides information that contributes to generating optimal advice.

[0665] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0666] Step 1:

[0667] The server collects user spending and income data via APIs for electronic payment services. These APIs provide data from financial institutions and online payment platforms. The input is user transaction data, and the output is raw transaction data stored on the server.

[0668] Step 2:

[0669] The server standardizes the raw transaction data it receives. It converts the amount, date, category, and other details of each transaction into a unified format. The input is raw transaction data, and the output is data formatted in a standard format. This data processing makes it possible to compare data from different sources.

[0670] Step 3:

[0671] The server analyzes the user's income structure and spending patterns using standardized data. It employs generative AI models and runs machine learning algorithms such as TensorFlow. The input is standardized data, and the output is an analytical report based on the user's income and spending. This report provides the foundational information for optimal tax advice.

[0672] Step 4:

[0673] The server generates a personalized tax optimization plan based on the analysis results. This plan includes specific actions that contribute to tax savings. The input is an analysis report, and the output is a tax-saving plan optimized for the user. This allows the user to receive specific tax-saving suggestions.

[0674] Step 5:

[0675] The server sends the generated tax optimization plan to the user's device as a push notification. The user can then review the plan and follow the suggested actions through their device. The input is the generated plan, and the output is the notification message displayed on the device. This process allows the user to receive useful tax information in real time.

[0676] 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.

[0677] This invention combines a system that analyzes a user's income and financial data to provide an optimal tax-saving plan with an emotion engine. A specific embodiment of this system is shown below.

[0678] First, the server obtains income and financial data through APIs of financial institutions and employers, with the user's consent. The obtained data is encrypted and stored securely.

[0679] Data standardization is performed by the server, ensuring all data is in a unified format. This process makes the data analyzable, improving the accuracy of subsequent analyses.

[0680] Subsequently, the AI ​​agent and emotion engine on the server work together to analyze the data. The AI ​​agent uses machine learning models to identify the user's income structure and spending patterns. Meanwhile, the emotion engine recognizes the user's emotions from past user interactions and survey data, and matches them with the data.

[0681] Based on these analysis results, the server generates a tax-saving plan optimized for the user. In particular, based on emotional data obtained from the emotion engine, it can select a plan structure and communication method that is more likely to convince the user. For example, if the user shows a tendency to dislike risk, the plan will be adjusted to include many proposals that minimize risk.

[0682] The generated plan is notified to the user via their device. The plan details and the steps required for implementation are also displayed, allowing the user to choose their course of action. The sentiment engine also records the user's feedback, which is used to improve future suggestions.

[0683] Furthermore, the server offers enterprise-grade modules for automating payroll and tax processing. This automation allows businesses to improve cost-effectiveness and enhance their competitiveness.

[0684] Thus, the present invention realizes a system that enhances the efficiency and effectiveness of the economic activities of individuals and companies by providing an optimal tax-saving plan that takes into account the user's emotions.

[0685] The following describes the processing flow.

[0686] Step 1:

[0687] The server obtains user consent and collects income and financial data from financial institutions and employers via API. This data is securely stored on the server in an encrypted state.

[0688] Step 2:

[0689] The data acquired by the server will be standardized. Different data formats will be unified, and units such as dates and currency will be adjusted to prepare the data for improved accuracy in analysis.

[0690] Step 3:

[0691] An AI agent on the server analyzes standardized data to identify income structures and spending patterns. This analysis provides the information necessary to generate data-driven tax-saving plans.

[0692] Step 4:

[0693] The emotion engine installed on the server extracts emotional data from the user's past interactions and feedback. This process involves emotion recognition to identify the user's risk tendencies and interests.

[0694] Step 5:

[0695] The server integrates the analysis results from the AI ​​agent and the emotion engine to generate a personalized tax-saving plan for the user. Specifically, it adjusts the plan content to take the user's emotions into consideration and selects an appropriate communication strategy.

[0696] Step 6:

[0697] The device notifies the user of the generated tax-saving plan. The device displays detailed information and implementation steps for the proposed plan, allowing the user to choose their course of action.

[0698] Step 7:

[0699] After the user decides whether to accept the suggestion, the device sends the user's choice and feedback back to the emotion engine. This allows the emotion engine to accumulate data and use it to optimize future suggestions.

[0700] Step 8:

[0701] The server runs modules for businesses that automate payroll and tax processing. Based on employee data, accurate payroll and tax processing are performed, streamlining the company's human resources operations.

[0702] (Example 2)

[0703] 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".

[0704] In modern economic activity, individuals and organizations need efficient tax burden reduction measures, but often face challenges such as the significant effort required to collect and interpret relevant information, and a lack of proposals that take into account individual emotional states. In addition, organizations face operational costs due to insufficient automation of payroll and tax management.

[0705] 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.

[0706] In this invention, the server includes means for acquiring the user's economic information, means for converting the acquired information into a unified format, means for analyzing the user's spending tendencies and income structure using the information converted into the unified format, means for generating individual tax burden reduction measures based on the analysis results, means for notifying the user of the generated tax burden reduction measures, means for determining the user's emotional state and adjusting the proposals accordingly, and means for automating the organization's payroll calculation and tax management. This enables the provision of efficient tax-saving plans tailored to individual characteristics and reduces operating costs for companies.

[0707] "Economic information" refers to financial data related to a user's income, expenses, and taxes.

[0708] "Converting to a unified format" refers to the process of aligning data acquired in different formats or types to a consistent standard.

[0709] "Spending trends" refer to data that shows patterns and trends in users' consumption behavior.

[0710] "Revenue structure" refers to information that systematically captures a user's sources of income and types of income.

[0711] "Tax burden reduction measures" refer to specific plans and methods designed to minimize the amount of taxes a user pays.

[0712] "Emotional state" refers to information that indicates a user's psychological tendencies and preferences.

[0713] "Payroll calculation" refers to the process of calculating and paying employee wages within an organization.

[0714] "Tax management" refers to the administrative tasks required for an organization or individual to calculate, file, and pay taxes in accordance with tax laws.

[0715] In a configuration for implementing this invention, the server is first built on a cloud platform and has the function of collecting users' economic information. The server collects data from financial institutions and employers using a dedicated API. The collected data is securely stored using AES encryption.

[0716] The server then uses ETL (Extract, Transform, Load) tools to standardize income and expenditure information into a unified format. This ensures that data in any format can be consistently analyzed. For example, unifying different date formats into one enables time-series analysis.

[0717] In the next step, the server uses an AI agent to analyze the user's spending habits and income structure. This AI agent is based on a machine learning model, and particularly utilizes reinforcement learning to improve its accuracy over time. The emotion engine analyzes past survey results and user-entered feedback to recognize individual emotional states, such as whether the user tends to be risk-averse.

[0718] Based on the analysis results, the server utilizes information from the emotion engine to generate a tax burden reduction plan optimized for the user. The generated plan is then notified to the user via their device. To aid user understanding, specific steps and expected effects are also presented in detail.

[0719] Furthermore, the server has the capability to automate the organization's payroll and tax management and integrates with the company's ERP system. This integration allows organizations to reduce data entry and manual calculations, improving operational efficiency.

[0720] For example, if a user states that they "want to save money for an overseas trip," the AI ​​agent will analyze this information and suggest tax-saving methods to free up funds for the trip from their income and expenses. In this case, a prompt containing the keyword "travel" might be something like, "Generate tax-saving suggestions based on the areas the user is interested in. The current interest is 'travel.' Please come up with recommended tax-saving plans to fund the trip."

[0721] As described above, this invention provides a system that enables highly accurate and efficient management and analysis of economic information tailored to the needs of individuals and businesses, and in particular, makes it possible to make suggestions that take into account the emotional state of the user.

[0722] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0723] Step 1:

[0724] The server collects economic information from financial institutions and employers via APIs, with the user's permission. The input for this step is raw data obtained through the API, and the output is the encrypted form of the obtained data. Specifically, it sends a request to the API, receives the response data, and protects it using AES encryption technology.

[0725] Step 2:

[0726] The server decrypts the encrypted data and uses ETL tools to convert the data into a unified format. The input for this step is encrypted data, and the output is standardized data. Specific standardization operations include unifying date formats and converting numerical units. This process transforms information in different formats into a consistent, parseable structure.

[0727] Step 3:

[0728] The server inputs standardized data into an AI agent to analyze user spending patterns and income structure. This analysis utilizes a machine learning model, with input consisting of standardized data and historical datasets, and outputting information on analyzed consumption patterns and income composition. Specifically, it employs reinforcement learning algorithms for pattern recognition and prediction.

[0729] Step 4:

[0730] The server uses an emotion engine to determine the user's emotional state and combines it with the output of an AI agent to generate tax reduction strategies. The input for this step is analyzed economic information and user emotion data, and the output is a tax-saving plan optimized for the user. Specifically, it performs emotion analysis on past surveys and feedback data and provides advice based on the user profile.

[0731] Step 5:

[0732] The terminal notifies the user of tax reduction measures obtained from the server. The input here is the tax-saving plan generated by the server, and the output is the specific plan information displayed on the user's terminal. Specifically, the proposed content is visualized using text and graphics to make it easy for the user to understand.

[0733] Step 6:

[0734] Users review the tax reduction measures displayed on their devices and provide feedback. The input consists of user feedback information, while the output is sentiment and feedback data sent to the server. Specifically, this involves collecting user satisfaction and areas for improvement through open-ended and multiple-choice questionnaires.

[0735] Step 7:

[0736] The server performs functions to automate the organization's payroll and tax management, integrating data into the company's ERP system. The input for this step is the company's employee data and tax information, and the output is automatically processed payroll calculations and tax reports. Specific operations include aggregating payroll data, calculating taxes, and generating reports that comply with regulations.

[0737] (Application Example 2)

[0738] 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".

[0739] In recent years, both individuals and businesses have been seeking efficient financial management and tax savings. However, existing tax-saving solutions fail to consider users' emotions and payment history, lacking optimal planning that is easy for users to implement. Therefore, there is a need to develop a system that can provide the most suitable tax-saving strategy for each user.

[0740] 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.

[0741] In this invention, the server includes means for acquiring the user's economic and financial data, means for unifying the acquired data, means for analyzing the user's consumption trends and income structure using the unified data, and means for analyzing electronic transaction history and providing tax-saving suggestions based on that analysis. This makes it possible to present appropriate tax-saving measures in real time based on the user's payment history and emotions.

[0742] "User economic data" refers to the collective information regarding an individual's or company's income, assets, liabilities, and expenses.

[0743] "Financial data" refers to information such as income and expenditure, deposits, and investments that is necessary to show a financial situation.

[0744] "Standardization" refers to the process of aligning data from different formats into a common format.

[0745] "Consumer trends" refer to the tendency of users to spend money on goods and services on a daily basis.

[0746] "Income structure" refers to the breakdown of a user's income and its fluctuations.

[0747] "Analysis" is the process of analyzing data to find specific patterns or meanings.

[0748] "Electronic transaction history" refers to records of past payments and purchases made by a user, recorded in a digital format.

[0749] A "tax-saving proposal" refers to specific measures or plans aimed at reducing the tax burden while complying with the law.

[0750] This invention provides a system that enables individuals and businesses to effectively reduce their taxes. This system consists of a server and user terminals, and utilizes various software to perform data processing and provide information.

[0751] First, the server collects users' income and financial data from financial institutions and related data providers via APIs. This data is encrypted for security reasons and stored securely. Software such as Python and APIs are used.

[0752] Next, the server unifies the collected data and converts it to a standard format. This makes data analysis easier. Then, machine learning models are introduced to analyze user consumption trends and revenue structures. Libraries such as Scikit-Learn are used for this purpose.

[0753] Furthermore, the server analyzes the user's electronic transaction history and generates optimal tax-saving suggestions based on the user's spending habits. In this process, an emotion engine is used to consider the user's emotional data, enabling more personalized suggestions.

[0754] The generated tax-saving suggestions are notified to the user's device. This is done via devices such as smartphones and smart glasses, making them easily accessible. Based on this information, the user can choose specific tax-saving actions.

[0755] For example, a user who tends to eat out more often at the end of the month can be prompted with "Would you like some tax-saving strategies to reduce your dining-out expenses this month?" based on their past spending and sentiment data. An example of the prompt would be: "Analyze the user's spending data, predict the spending categories likely to increase next, and generate relevant tax-saving suggestions." This allows for the presentation of appropriate tax-saving strategies to the user in real time.

[0756] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0757] Step 1:

[0758] The server retrieves user income and financial data from financial institutions and related data providers via APIs. The input is raw data provided by the APIs, and the output is encrypted data. This data is stored using encryption technology for security reasons.

[0759] Step 2:

[0760] The server standardizes the acquired raw data into a unified format. By using encrypted data as input and performing data format conversion, analyzable data is obtained as output. Schema mapping technology is used in this process to maintain data integrity.

[0761] Step 3:

[0762] The server analyzes user consumption trends and income structures using standardized data. The input is unified data, and the output is the analysis results regarding user spending patterns and income structures. Here, machine learning libraries such as Scikit-Learn are utilized to apply classification and clustering models.

[0763] Step 4:

[0764] The server further analyzes the electronic transaction history based on the analyzed data and generates appropriate tax-saving suggestions. The inputs are the analysis results and transaction history, and the output is a proposed tax-saving strategy. This suggestion is based on the user's past transaction history, while also considering the user's preferences as perceived by the emotion engine.

[0765] Step 5:

[0766] The terminal notifies the user of the generated tax-saving proposals. The input is tax-saving proposal information from the server, and the output is a notification message to the user. The user receives this notification and can refer to the specific proposal details to take action.

[0767] Step 6:

[0768] Users provide feedback based on the tax-saving suggestions they receive from their devices. This feedback information is sent to the server to improve the quality of future suggestions, and is continuously analyzed by an emotion engine. The input is user feedback, and the output is data that leads to the optimization of suggestions.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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."

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] The following is further disclosed regarding the embodiments described above.

[0791] (Claim 1)

[0792] Means for obtaining user income data and financial data,

[0793] Means for standardizing acquired data,

[0794] A means of analyzing users' spending patterns and income structure using standardized data,

[0795] A means of generating individual tax-saving plans based on analysis results,

[0796] A means of notifying the user of the generated tax-saving plan,

[0797] A system that includes this.

[0798] (Claim 2)

[0799] The system according to claim 1, further comprising means for assisting the user in implementing a proposed tax-saving plan.

[0800] (Claim 3)

[0801] The system according to claim 1, further comprising means for automating corporate payroll and tax processing.

[0802]

[0803] "Example 1"

[0804] (Claim 1)

[0805] Means for acquiring users' economic and financial data,

[0806] A means of unifying the acquired data,

[0807] A means of analyzing users' spending trends and income distribution using unified data,

[0808] A means of constructing individual tax strategies based on analysis results,

[0809] A means of delivering the constructed tax strategies to users,

[0810] A system that includes this.

[0811] (Claim 2)

[0812] The system according to claim 1, further comprising means for assisting the user in implementing proposed tax measures.

[0813] (Claim 3)

[0814] The system according to claim 1, further comprising means for automating corporate payroll and tax processing.

[0815] "Application Example 1"

[0816] (Claim 1)

[0817] Means of obtaining electronic payment data,

[0818] Means for standardizing acquired data,

[0819] A means of generating individual tax optimization plans using standardized data,

[0820] A means of notifying the user of the generated plan,

[0821] A means of sending push notifications to the user's device,

[0822] A system that includes this.

[0823] (Claim 2)

[0824] The system according to claim 1, further comprising means for providing users with real-time tax-saving advice.

[0825] (Claim 3)

[0826] The system according to claim 1, further comprising means for supporting tax optimization through the analysis of expenditure and income data.

[0827] "Example 2 of combining an emotion engine"

[0828] (Claim 1)

[0829] Means of obtaining users' economic information,

[0830] A means of converting acquired information into a unified format,

[0831] A means for analyzing a user's spending trends and income structure using information converted into a unified format,

[0832] A means for generating individual tax burden reduction measures based on analysis results,

[0833] A means of notifying users of the generated tax burden reduction measures,

[0834] A means of determining the user's emotional state and adjusting suggestions based on that,

[0835] A system that includes this.

[0836] (Claim 2)

[0837] The system according to claim 1, further comprising means for assisting the implementation of tax burden reduction measures provided to the user.

[0838] (Claim 3)

[0839] The system according to claim 1, further comprising means for automating the payroll calculation and tax management of an organization.

[0840] "Application example 2 when combining with an emotional engine"

[0841] (Claim 1)

[0842] Means for obtaining users' economic and financial data,

[0843] A means of unifying the acquired data,

[0844] A means of analyzing user consumption trends and income structure using standardized data,

[0845] A means of generating individual tax-saving plans based on analysis results,

[0846] A means of analyzing electronic transaction history and providing tax-saving proposals based on that analysis,

[0847] A means of notifying the user of the generated tax-saving plan,

[0848] A system that includes this.

[0849] (Claim 2)

[0850] The system according to claim 1, further comprising means for assisting the user in implementing a proposed tax-saving plan.

[0851] (Claim 3)

[0852] The system according to claim 1, further comprising means for automating corporate payment calculations and tax processing. [Explanation of Symbols]

[0853] 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 for obtaining user income data and financial data, Means for standardizing acquired data, A means of analyzing users' spending patterns and income structure using standardized data, A means of generating individual tax-saving plans based on analysis results, A means of notifying the user of the generated tax-saving plan, A system that includes this.

2. The system according to claim 1, further comprising means for assisting the user in implementing a proposed tax-saving plan.

3. The system according to claim 1, further comprising means for automating corporate payroll and tax processing.

Images