system

Abstract

We provide the system. [Solution] A means of collecting accounting standards and tax laws from each region and training a machine learning model with them, A means of collecting and analyzing organizational accounting data and related documents, A means of proposing appropriate tax adjustments and tax-saving measures based on the analysis results, A system that includes this.

Description

Technical Field

[0004] , , , ,

[0005] , , , , ,

[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, 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] Accounting standards and tax laws vary by region, and it is cumbersome to manually adjust these differences, making errors likely to occur. Also, in order for taxpaying corporations in each country to avoid penalties for rule violations, accurate tax adjustments are necessary. Furthermore, it is difficult to find efficient tax adjustments and appropriate tax-saving measures, and there is a possibility of overpayment of taxes. In view of such a situation, an object of the present invention is to provide a system that reduces the burden on tax officials and automatically performs optimal tax adjustments.

Means for Solving the Problems

[0005] This invention relates to a system that includes means for collecting regional accounting standards and tax laws and training a machine learning model with them, means for collecting and analyzing an organization's accounting data and related documents, and means for proposing appropriate tax adjustments and tax-saving measures based on the analysis results. This makes it possible to automatically analyze the differences between regional accounting standards and tax laws and display proposed tax adjustments and tax-saving measures by inputting data for a specific accounting period. The system of this invention realizes accurate and efficient tax adjustments and tax-saving measures automatically, reducing the burden on tax personnel and preventing overpayment of taxes.

[0006] "Accounting standards" are the principles and rules that an organization or company must follow when making financial reports.

[0007] "Tax law" refers to laws and regulations concerning taxes enacted by the government.

[0008] "Machine learning" is a field of artificial intelligence in which computers automatically learn patterns and rules using data.

[0009] "Accounting data" refers to information about an organization's or company's financial status and transactions.

[0010] "Related documents" refer to documents such as approval documents and manuals that are required along with accounting data.

[0011] "Analysis" is the process of examining data in detail and understanding its content and structure.

[0012] "Tax adjustments" refer to the amount necessary to correct the tax liability based on differences between accounting standards and tax laws.

[0013] "Tax-saving measures" refer to specific methods or means of reducing the amount of tax payable in accordance with the law.

[0014] A "system" refers to an entire structure in which multiple means or devices are combined and operate to achieve a specific objective.

Brief Description of Drawings

[0015] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes 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 signed 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 signed 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 signed storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[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] This invention provides a tax adjustment analysis and proposal system that utilizes generation AI. This system consists of the following main components.

[0037] Components

[0038] 1. Server

[0039] 2. Terminal

[0040] 3. User

[0041] server

[0042] The server performs the following functions:

[0043] Data collection: The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database.

[0044] Data Learning: The server trains a machine learning model based on collected accounting standards and tax law data. It also fine-tunes the model using historical accounting data and approval documents from within the company.

[0045] Data Analysis: The server analyzes accounting data received from terminals to identify the need for tax adjustments. Based on the analysis results, it calculates appropriate tax adjustment amounts and tax-saving strategies.

[0046] Proposal generation: The server proposes tax adjustments and tax-saving measures based on the analysis results and sends them to the terminal.

[0047] As a concrete example, the server learns Japanese accounting standards (J-GAAP) and tax laws, and combines them with past corporate accounting data to efficiently perform tax adjustments. Furthermore, the server analyzes data from a specific accounting period and proposes tax savings by reclassifying a portion of entertainment expenses as advertising expenses.

[0048] terminal

[0049] The device performs the following functions:

[0050] Data Entry: Users input data for a specific accounting period and related approval documents into a terminal. The terminal then transmits this data to the server.

[0051] Results display: The terminal displays to the user the tax adjustment amounts and tax saving suggestions received from the server.

[0052] As a concrete example, users can input their year-end accounting data into their terminal and check the linked tax adjustments and tax-saving strategies from the server.

[0053] User

[0054] The user performs the following actions:

[0055] Data entry: Users input data for each accounting period and related approval documents into the terminal.

[0056] Result Confirmation: The user reviews the tax adjustment amount and suggested tax-saving measures displayed on their device.

[0057] Application: The user applies the proposed adjustments to their actual accounting software.

[0058] As a concrete example, before the year-end accounting closing process, users can review the analysis results provided by the server, appropriately reclassify expenses from entertainment expenses to advertising expenses, and maximize tax benefits.

[0059] Thus, by using a generation AI, this invention automatically analyzes the differences between accounting data and tax laws, and provides appropriate tax adjustments and tax-saving measures. Furthermore, this reduces the burden on tax officials while enabling accurate tax payment and tax savings.

[0060] The following describes the processing flow.

[0061] Step 1:

[0062] Data collection

[0063] The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database.

[0064] Users import internal company accounting data and related documents into the terminal, and the terminal then sends this data to the server.

[0065] Step 2:

[0066] Data Learning

[0067] The server uses the collected accounting standards and tax law data to build and train a machine learning model.

[0068] The server uses the company's historical accounting data and approval documents to fine-tune the model, which improves the accuracy of the analysis.

[0069] Step 3:

[0070] Data entry

[0071] The user enters accounting data for a specific accounting period into the terminal.

[0072] The terminal sends the entered data to the server.

[0073] Step 4:

[0074] Data Analysis

[0075] The server analyzes the accounting data received from the terminal.

[0076] The server evaluates whether specific items of accounting data are appropriately classified for tax purposes, based on differences in accounting standards and tax laws in each region.

[0077] Step 5:

[0078] Calculation of tax adjustments and tax-saving measures

[0079] The server identifies the need for tax adjustments based on the analysis results and calculates the required amount of tax adjustments.

[0080] The server proposes tax-advantageous tax-saving strategies. For example, it may suggest reclassifying entertainment expenses as advertising expenses to achieve tax savings.

[0081] Step 6:

[0082] Proposal creation and submission

[0083] The server generates a list of calculated tax adjustments and proposed tax-saving strategies.

[0084] The server sends this information to the terminal.

[0085] Step 7:

[0086] Results display

[0087] The terminal displays the suggestions received from the server to the user.

[0088] The user reviews the tax adjustment amounts and suggested tax-saving measures displayed on the device and makes any necessary corrections.

[0089] Step 8:

[0090] Application of adjustments

[0091] The user applies the displayed suggestions to their accounting software.

[0092] Users review the adjusted data and use it for their final tax return.

[0093] By proceeding step by step in this manner, accurate and efficient tax adjustments and tax-saving strategies can be proposed.

[0094] (Example 1)

[0095] 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."

[0096] Traditional tax adjustments make it extremely difficult for companies to fully understand local accounting standards and tax laws and implement appropriate tax adjustments and tax-saving strategies based on them. Furthermore, manual adjustments and proposals are labor-intensive and prone to errors. Therefore, there is a need to automate these tasks in an efficient and accurate way to reduce the burden on tax professionals.

[0097] 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.

[0098] This invention includes a server that collects regional accounting standards and tax laws and uses them to train a machine learning model; a server that collects and analyzes an organization's accounting data and related documents; and a server that proposes appropriate tax adjustments and tax-saving measures based on the analysis results. This automates the process from collecting accounting data to proposing tax adjustments, enabling efficient and accurate tax processing.

[0099] "Accounting standards" are rules and criteria that companies must follow when preparing financial reports.

[0100] "Tax law" refers to the laws and regulations for calculating and reporting taxes on income and profits.

[0101] A "machine learning model" is a collection of algorithms that learn patterns and rules based on data and use them to make predictions and classifications on new data.

[0102] A "terminal" refers to a device or equipment used by a user to manipulate input data and communicate with a server.

[0103] A "server" is a computer system used to process and store data over a network.

[0104] "Accounting data" refers to data that includes information about a company's financial situation and transactions.

[0105] "Related documents" refer to documents related to accounting data, including approval documents and meeting minutes.

[0106] "Tax adjustment amount" refers to the final tax amount after making the necessary adjustments to calculate the appropriate tax.

[0107] "Tax-saving measures" refer to specific methods or means of legally reducing the tax burden.

[0108] This invention provides a tax adjustment analysis and proposal system that utilizes generation AI. This system mainly consists of three main components: a server, a terminal, and a user.

[0109] server

[0110] The server performs the following functions: First, it collects data on accounting standards and tax laws for each region from the internet and official documents and stores it in a database. A web crawler is used for this data collection, and the collected data is stored in JSON format. Subsequently, the server trains a machine learning model based on the collected accounting standards and tax law data. The Python TensorFlow library is used for this training. In addition, the model is fine-tuned based on past accounting data and approval documents within the company.

[0111] When accounting data is sent from the terminal, the server analyzes the data and identifies the need for tax adjustments. Specifically, it preprocesses the received data (imputing missing values, detecting outliers, etc.) and inputs it into a generating AI model to calculate appropriate tax adjustments and tax-saving measures. Based on these analysis results, the server automatically generates a report in PDF format and sends it to the terminal.

[0112] terminal

[0113] The terminal provides a means for users to input data and related approval documents for a specific accounting period. Users upload the necessary data to the terminal via Excel or CSV files. This data is converted to JSON format on the terminal and sent to the server.

[0114] Once the analysis results are returned from the server, the terminal displays the contents to the user. It has a function to read PDF files and visually display them on the dashboard using graphs and tables. This allows users to intuitively understand the analysis results.

[0115] User

[0116] Users input data for each accounting period and related approval documents into the terminal. Once the user inputs the data, the server analyzes it and proposes appropriate tax adjustments and tax-saving measures. Users can then review the proposed tax adjustments and tax-saving measures displayed on the terminal and apply them to their company's accounting software.

[0117] As a concrete example, a user can enter year-end accounting data and use prompts like the following:

[0118] "I have entered the year-end accounting data. Please provide suggestions regarding tax adjustments and tax-saving strategies."

[0119] By sending this prompt to the server, the server analyzes the input data and provides appropriate suggestions to the user. This automates the entire process, from collecting accounting data to suggesting tax adjustments, efficiently and accurately.

[0120] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0121] Step 1: Data Collection

[0122] The server collects data on regional accounting standards and tax laws from the internet and official sources. Specifically, it uses a web crawler to automatically collect data from national tax authorities and websites providing accounting standards. The collected data is stored in JSON format.

[0123] Input: List of URLs from the internet and official documents

[0124] Output: Accounting standards and tax law data in JSON format

[0125] Step 2: Data Training

[0126] The server trains a machine learning model based on collected accounting standards and tax law data. This process utilizes the Python TensorFlow library. Furthermore, the model is fine-tuned using historical internal accounting data and approval documents from the company.

[0127] Input: Accounting standards and tax law data in JSON format, historical accounting data, and approval documents.

[0128] Output: Trained machine learning model

[0129] Step 3: Data Entry

[0130] Users input data for a specific accounting period and related approval documents from their terminal. Specifically, this is done by uploading Excel or CSV files. The terminal converts this data into JSON format and sends it to the server.

[0131] Input: Accounting data and approval documents in Excel or CSV file format.

[0132] Output: Accounting data and approval documents converted to JSON format

[0133] Step 4: Data Analysis

[0134] The server analyzes the accounting data received from the terminal and identifies the need for tax adjustments. Here, the received data is preprocessed (such as imputing missing values ​​and detecting outliers) and input into a generative AI model. The results of the analysis by the generative AI model are then obtained.

[0135] Input: Accounting data in JSON format and approval documents

[0136] Output: Analysis results (necessity of tax adjustments and adjustment amount)

[0137] Step 5: Proposal Creation

[0138] Based on the analysis results, the server proposes appropriate tax adjustments and tax-saving strategies. During this process, the generated report is saved in PDF format and sent to the user's terminal.

[0139] Input: Analysis results (necessity of tax adjustments and adjustment amount)

[0140] Output: Tax adjustment proposal report in PDF format

[0141] Step 6: Display Results

[0142] The terminal displays tax adjustments and tax-saving strategies received from the server in PDF format to the user. Specifically, it reads the PDF file and displays it visually on the dashboard using graphs and tables.

[0143] Input: Tax adjustment proposal report in PDF format

[0144] Output: Visually displayed analysis results and proposed solutions

[0145] Step 7: Check results and apply

[0146] Users can review the tax adjustments and suggested tax-saving measures displayed on their device and apply them to their company's accounting software. They can also manually modify the adjustments as needed.

[0147] Input: Visually displayed analysis results and proposed content

[0148] Output: Corrected accounting data and applied adjustments

[0149] This automates the process from collecting accounting data to proposing tax adjustments efficiently and accurately.

[0150] (Application Example 1)

[0151] 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."

[0152] In modern business operations, tax adjustments require considerable effort and time. This is especially true for owners of brick-and-mortar stores and accounting staff, who often find it difficult to keep up with the latest accounting standards and tax law changes while performing tax adjustments as part of their daily work. Therefore, there is a need to improve the efficiency and accuracy of tax adjustments. Furthermore, there is a demand for systems that utilize generative AI models to automatically suggest appropriate tax-saving strategies.

[0153] 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.

[0154] This invention includes a server that collects regional accounting standards and tax laws and uses them to train a machine learning model; a server that collects and analyzes an organization's accounting data and related documents; a server that proposes appropriate tax adjustments and tax-saving measures based on the analysis results; a server that inputs accounting data into a smart device and displays the analysis results; and a server that generates tax adjustment proposals based on the analysis results using a generative AI model. This makes it possible for store owners and accountants to easily input accounting data and automatically receive accurate tax adjustment proposals and tax-saving measures.

[0155] "Accounting standards" are the rules and guidelines that companies and organizations must follow when preparing financial statements.

[0156] "Tax laws" refer to the laws and regulations established by the state or local government for the purpose of collecting taxes.

[0157] A "machine learning model" is an algorithm that learns from data, recognizes patterns, and makes predictions and classifications on new data.

[0158] "Accounting data" refers to data relating to the financial condition and operating results of a company or organization, and includes financial statements and transaction records.

[0159] "Related documents" refer to various documents accompanying accounting data, including approval documents and expense reports.

[0160] "Analysis results" refer to conclusions and indicators derived by a machine learning model from analyzing accounting data and related documents.

[0161] "Tax adjustment amount" refers to an amount that is modified based on tax regulations and standards.

[0162] "Tax-saving measures" refer to legal measures and methods taken to reduce the tax burden.

[0163] A "smart device" refers to a digital device, such as a smartphone or tablet, that can connect to the internet and perform a variety of functions.

[0164] A "generative AI model" is an artificial intelligence model used for natural language processing and data generation, and in particular, it generates new text based on a prompt.

[0165] A "prompt" is text input to a generative AI model, and it is an instruction that indicates the direction and content of the text that the AI ​​generates.

[0166] This invention provides a tax adjustment analysis and proposal system that utilizes generation AI. This system consists of three main components necessary for carrying out the invention: a server, a terminal, and a user.

[0167] server

[0168] The server performs the following functions:

[0169] 1. Data Collection: The server collects data on accounting standards and tax laws for each region from the internet and official documents, and stores it in a database. The specific software used is the Requests library.

[0170] 2. Data Learning: The server uses the LinearRegression algorithm of the Scikit-learn machine learning model to train on the collected accounting standards and tax law data. The model is also fine-tuned using historical accounting data and approval documents from within the company.

[0171] 3. Data Analysis: The server analyzes the accounting data received from the terminal and identifies the need for tax adjustments. During this process, the generation AI model uses Hugging Face Transformers' GPT-2 to process the analysis results based on the prompt text.

[0172] 4. Proposal Generation: Based on the analysis results, the server generates tax adjustments and tax-saving strategies using an AI model, creates a proposal, and sends it to the terminal. Examples of specific prompt messages:

[0173] Please resolve the gap and propose the optimal tax adjustment rules. Adjustment amount: 15 million yen

[0174] terminal

[0175] The device performs the following functions:

[0176] 1. Data Entry: Users enter data and related documents for a specific accounting period into a terminal. This is done using a smartphone app or other smart device.

[0177] 2. Display of Results: The terminal displays the tax adjustment amounts and tax-saving suggestions received from the server to the user. The display uses graphs and text in a format that is easy for the user to understand.

[0178] User

[0179] The user performs the following actions:

[0180] 1. Data entry: Users enter data and related documents for each accounting period into the terminal.

[0181] 2. Confirmation of results: The user checks the tax adjustment amount and suggested tax-saving measures displayed on the device.

[0182] 3. Application: The user applies the proposed adjustments to their actual accounting software. This ensures proper accounting treatment and maximizes tax benefits.

[0183] As a concrete example, a user inputs year-end accounting data into a smartphone app, a server analyzes that data, and generates appropriate tax adjustment proposals using a generative AI model based on prompt messages. The generated tax adjustment proposals are then displayed on the device, allowing the user to review the content and reflect it in their actual accounting processes. In this way, the efficiency and accuracy of tax adjustments are improved.

[0184] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0185] Step 1:

[0186] Data collection

[0187] The server collects data on accounting standards and tax laws for each region from the internet and official documents. Specifically, it uses the Requests library to retrieve information from official websites and APIs, and stores this data in a database.

[0188] Input: URLs from the internet or official documents

[0189] Output: Collected accounting standards and tax law data

[0190] Specific operation: Retrieve data from the internet in JSON format and save it to the database.

[0191] Step 2:

[0192] Data Learning

[0193] The server trains a machine learning model (Scikit-learn's LinearRegression algorithm) based on accounting standards and tax law data for each region. It also fine-tunes the model using historical accounting data and approval documents from within the company.

[0194] Input: Collected accounting standards and tax law data, historical accounting data of the company

[0195] Output: Trained machine learning model

[0196] Specific actions: Preprocess the data and fit it to a LinearRegression model.

[0197] Step 3:

[0198] Data entry

[0199] Users input data and related documents for a specific accounting period into their device (smartphone app). The app then transmits this data to the server in real time.

[0200] Input: Data for the accounting period, related documents

[0201] Output: Sending data to the server

[0202] Specific actions: Input data using a smartphone app and send it to the server.

[0203] Step 4:

[0204] Data Analysis

[0205] The server analyzes the received accounting data to identify the need for tax adjustments. It uses machine learning models to make predictions and generative AI models (GPT-2) to generate supplementary information.

[0206] Input: Accounting data submitted by the user

[0207] Output: Analysis results, necessary tax adjustments

[0208] Specific actions: Preprocess accounting data and feed it into a pre-trained model for analysis. Based on the analysis results, generate supplementary information using an AI model.

[0209] Step 5:

[0210] Proposal creation

[0211] The server generates tax adjustments and tax-saving strategies based on the analysis results, inputs them into the AI ​​model using appropriate prompts, and generates specific suggestions. This is then sent to the terminal.

[0212] Input: Analysis result, prompt message

[0213] Output: Tax adjustments and proposed tax-saving strategies

[0214] Specific operation: Create a prompt sentence based on the analysis results, input it into the generation AI model, and obtain new text suggestions.

[0215] Step 6:

[0216] Results display

[0217] The terminal displays tax adjustment proposals and tax-saving strategies received from the server to the user. The display is presented in graph and text format to aid user understanding.

[0218] Input: Suggestions from the server

[0219] Output: Tax adjustment proposals and tax saving strategies displayed to the user.

[0220] Specific action: Visualize the suggestions received via the smartphone app and display them to the user.

[0221] Step 7:

[0222] Result verification and application

[0223] The user reviews the tax adjustments and suggested tax-saving measures displayed on the terminal and applies them to their actual accounting software. This ensures proper accounting processing.

[0224] Input: Suggestions displayed on the device

[0225] Output: Application to actual accounting software

[0226] Specific actions: The user reviews the proposed adjustments and enters the data into the accounting software.

[0227] 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.

[0228] This invention combines an emotion engine with a tax adjustment analysis and proposal system that utilizes generation AI to realize a system that provides an interface and proposal content that takes user emotions into consideration. This system consists of the following main components.

[0229] Components

[0230] 1. Server

[0231] 2. Terminal

[0232] 3. Emotional Engine

[0233] 4. User

[0234] server

[0235] The server performs the following functions:

[0236] Data Collection: The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database.

[0237] Data Learning: The server builds and trains a machine learning model based on collected accounting standards and tax law data. It also fine-tunes the model using historical accounting data and approval documents from within the company.

[0238] Data Analysis: The server analyzes accounting data received from terminals to identify the need for tax adjustments. Based on the analysis results, it calculates appropriate tax adjustment amounts and tax-saving strategies.

[0239] Proposal generation: The server proposes tax adjustments and tax-saving measures based on the analysis results and sends them to the terminal.

[0240] As a concrete example, the server learns Japanese accounting standards (J-GAAP) and tax laws, and combines them with past corporate accounting data to efficiently perform tax adjustments. It also analyzes data from a specific accounting period and proposes tax savings by reclassifying a portion of entertainment expenses as advertising expenses.

[0241] terminal

[0242] The device performs the following functions:

[0243] Data Entry: Users input accounting data and related approval documents for a specific accounting period into a terminal. The terminal then transmits this data to the server.

[0244] Results display: The terminal displays to the user the tax adjustment amounts and tax saving suggestions received from the server.

[0245] As a concrete example, users can input their year-end accounting data into their terminal and check the linked tax adjustments and tax-saving strategies from the server.

[0246] Emotional Engine

[0247] The emotion engine performs the following functions:

[0248] Emotion Recognition: Analyzes user input data and operation history to recognize user emotions.

[0249] Emotion Adjustment: The emotion engine adjusts how analysis results and suggestions are displayed based on the user's emotions.

[0250] Additional support provided: Provide additional support and explanations based on the user's needs and feelings.

[0251] For example, if a user feels uneasy about a suggestion from the system, the emotion engine will display detailed explanations and supplementary information to help the user understand.

[0252] User

[0253] The user performs the following actions:

[0254] Data entry: Users input data for each accounting period and related approval documents into the terminal.

[0255] Result Confirmation: The user reviews the tax adjustment amount and suggested tax-saving measures displayed on their device.

[0256] Application: The user applies the proposed adjustments to their actual accounting software.

[0257] For example, before year-end accounting closing, users can review analysis results provided by the server, appropriately reclassify expenses from entertainment expenses to advertising expenses, and maximize tax benefits. Furthermore, the emotion engine recognizes user stress and anxiety, providing supplementary information and support to deliver a superior user experience.

[0258] Thus, by using generation AI, the present invention not only automatically analyzes the differences between accounting data and tax laws and provides appropriate tax adjustments and tax-saving measures, but also provides an interface and support that takes user emotions into consideration, thereby further reducing the burden on tax personnel while achieving accurate tax payment and tax savings.

[0259] The following describes the processing flow.

[0260] Step 1:

[0261] Data collection

[0262] The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database.

[0263] Users import internal company accounting data and related documents into the terminal, and the terminal then sends this data to the server.

[0264] Step 2:

[0265] Data Learning

[0266] The server uses the collected accounting standards and tax law data to train a machine learning model and understand the differences in rules across regions.

[0267] The server uses the company's historical accounting data and documents to fine-tune the model and further improve its accuracy.

[0268] Step 3:

[0269] Data entry

[0270] The user enters accounting data for a specific accounting period into the terminal.

[0271] The terminal sends the entered data to the server.

[0272] Step 4:

[0273] Data Analysis

[0274] The server analyzes the accounting data sent by the user in real time.

[0275] The server identifies the necessary tax adjustments for specific transactions and items, taking into account differences in accounting standards and tax laws in each region.

[0276] Step 5:

[0277] Calculation of tax adjustments and tax-saving measures

[0278] The server calculates the necessary tax adjustments based on the analysis results.

[0279] The server proposes optimal tax-saving strategies. For example, it can reduce the tax burden by properly reclassifying entertainment expenses.

[0280] Step 6:

[0281] Proposal creation and submission

[0282] The server creates a list of the calculated tax adjustment amounts and the proposed tax-saving measures.

[0283] The server sends these proposed contents to the terminal.

[0284] Step 7:

[0285] Emotion recognition

[0286] The emotion engine in the terminal analyzes the user's operations and input data, and recognizes the user's emotions in real time.

[0287] For example, if the user is recognized as feeling anxious or confused, the emotion engine conducts an analysis.

[0288] Step 8:

[0289] Result display and emotion response

[0290] The terminal displays the tax adjustment amount and the tax-saving measures sent from the server to the user.

[0291] If the user is recognized as anxious by the emotion engine, the terminal displays additional support information and explanations.

[0292] [[ID=*39]] Step 9:

[0293] User confirmation and application

[0294] The user checks the displayed proposed contents and applies the necessary adjustments to the accounting software.

[0295] Based on the information judged to be appropriate by the emotion engine, the user proceeds with the process with confidence.

[0296] Step 10:

[0297] Final confirmation

[0298] Users review the adjusted data and use it for their final tax return.

[0299] The server stores adjustment data and provides feedback for future learning.

[0300] Through the above process, the present invention can provide users with intuitive, efficient, and accurate tax adjustment and tax saving strategies. Furthermore, by combining it with an emotion engine, the aim is to provide an interface and support that responds to the user's emotions, thereby realizing a stress-free user experience.

[0301] (Example 2)

[0302] 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".

[0303] Conventional tax adjustment systems failed to adequately analyze the differences between regional accounting standards and tax laws, and lacked the means to adjust suggestions to take user sentiment into consideration, often causing stress and anxiety. As a result, tax adjustments and tax-saving strategies were not properly proposed, leading to problems with reduced tax efficiency.

[0304] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting accounting standards and tax laws of each region and training a machine learning model with them; means for inputting the organization's accounting data and related documents and analyzing them; means for proposing appropriate tax adjustments and tax saving measures based on the analysis results and displaying the results; and means for analyzing user sentiment data and adjusting the proposed content and display method according to the sentiment. This enables appropriate tax adjustments and tax saving by automatically analyzing the differences between accounting standards and tax laws of each region and providing an interface that takes the user's sentiment into consideration.

[0305] "Accounting standards" refer to a set of rules and guidelines related to financial reporting and accounting processes, which are used for recording, reporting, and analyzing accounting data in a specific region or country.

[0306] "Tax law" refers to a system of rules and laws regarding the calculation, declaration, and payment methods of taxes imposed by the government on individuals and corporations.

[0307] "Machine learning model" refers to an algorithm or mathematical model that learns patterns and rules from data and uses them to analyze and predict new data.

[0308] "Accounting data" refers to numerical data and related documents indicating the financial status and business performance of an organization, including information such as income, expenses, assets, and liabilities.

[0309] "Analysis" refers to the process of examining data or information in detail to understand its meaning and relationships.

[0310] "Tax adjustment amount" refers to the amount calculated based on specific tax laws and accounting standards to adjust the tax payable.

[0311] "Tax-saving measures" refer to methods and means for legally and efficiently reducing the tax payable.

[0312] "Result display" refers to the act of visualizing the analysis results and proposed content processed by the server on the user interface and presenting them to the user.

[0313] "Emotion data" refers to data indicating the emotional state of a user, which is inferred from operation history, input speed, usage frequency, etc., and is used to analyze that state.

[0314] "Proposed content" refers to proposals regarding tax adjustments and tax-saving measures generated based on the analysis results, including specific action plans and recommendations.

[0315] This invention is a system that combines an emotion engine with a tax adjustment analysis and proposal system utilizing generative AI to provide an interface and proposal content that takes user emotions into consideration. This system consists of the following main components.

[0316] 1. Server

[0317] 2. Terminal

[0318] 3. Emotional Engine

[0319] 4. User

[0320] server

[0321] The server performs the following functions:

[0322] Data Collection: The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database. Specifically, commercial database servers and cloud servers are used as hardware. Software used includes web scraping techniques using Python scripts and API integration tools. The collected data is stored in MySQL or PostgreSQL.

[0323] Data Learning: The server builds and trains a machine learning model based on collected accounting standards and tax law data. Specific software used includes machine learning libraries such as TensorFlow and PyTorch. The model is also fine-tuned using historical accounting data and approval documents from within the company. Historical company accounting data is imported from CSV files or Excel spreadsheets, and data preprocessing is performed automatically.

[0324] Data Analysis: The server analyzes accounting data received from terminals to identify the need for tax adjustments. The analysis utilizes data analysis algorithms based on machine learning models. Specifically, Python and R are used for data analysis. Based on the analysis results, appropriate tax adjustments and tax-saving strategies are calculated. For example, by analyzing data for a specific accounting period, the system might propose tax savings by reclassifying a portion of entertainment expenses as advertising expenses.

[0325] Proposal Generation: Based on the analysis results, the server proposes tax adjustments and tax-saving strategies and sends them to the terminal. The generated proposal is converted to JSON format and sent to the terminal using the HTTPS protocol.

[0326] terminal

[0327] The device performs the following functions:

[0328] Data Entry: Users input accounting data and related approval documents for a specific accounting period into the terminal. The terminal provides an upload function for Excel and CSV files. The uploaded data is validated internally and then prepared for transmission to the server.

[0329] Results Display: The terminal displays tax adjustments and tax-saving suggestions received from the server to the user. A web browser-based dashboard interface is used for display, and the data is provided visually in table and graph formats. This makes it easy for the user to understand the suggestions.

[0330] Emotional Engine

[0331] The emotion engine performs the following functions:

[0332] Emotion Recognition: This involves analyzing user input data and operation history to recognize the user's emotions. Natural language processing and machine learning techniques are used for emotion recognition. For example, emotional states are estimated by analyzing user keystroke data, mouse movements, and browsing time.

[0333] Emotion Adjustment: The emotion engine adjusts how analysis results and suggestions are displayed based on the user's emotions. Specifically, if it determines that the user is feeling stressed or anxious, it displays more detailed text and visual guides explaining the suggestions.

[0334] Additional support provided: Provide additional support and explanations based on the user's emotions. For example, if a user feels uneasy about a suggestion from the system, the emotion engine will display detailed explanations and supplementary information to help the user understand.

[0335] User

[0336] The user performs the following actions:

[0337] Data entry: Users input data for each accounting period and related approval documents into the terminal.

[0338] Result Confirmation: The user reviews the tax adjustment amounts and suggested tax-saving measures displayed on the device. For example, they might enter a prompt message such as, "I uploaded last year's entertainment expenses and accounting data; please tell me the appropriate tax adjustment method."

[0339] Application: The user applies the proposed adjustments to their actual accounting software. For example, they input data into their accounting software based on the suggestions and perform tax adjustments.

[0340] Thus, by using generation AI, the present invention not only automatically analyzes the differences between accounting data and tax laws and provides appropriate tax adjustments and tax-saving measures, but also provides an interface and support that takes user emotions into consideration, thereby further reducing the burden on tax personnel while achieving accurate tax payment and tax savings.

[0341] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0342] Step 1: Data Collection

[0343] The server collects data on accounting standards and tax laws for each region from the internet and official documents, and stores it in a database. Specific examples of the data collected include tax law documents and accounting standards provided by government agencies and public accounting bodies.

[0344] Input: Data source URLs for accounting standards and tax laws

[0345] Data Processing: Using Python or R, data is acquired using web scraping techniques. The acquired data is converted to JSON format, and unnecessary information is filtered out.

[0346] Output: Accounting standards and tax law data stored in the database

[0347] Specifically, the server is configured to retrieve data from a specified URL at regular intervals every day and automatically save it to the local database.

[0348] Step 2: Data Entry

[0349] The user enters accounting data and related approval documents for a specific accounting period into the terminal. The data entered by the user is sent to the server.

[0350] Input: Accounting data such as Excel files and CSV files.

[0351] Data processing: The terminal validates the format and content of uploaded files and displays an error message to the user if there are formatting issues.

[0352] Output: Data that has passed validation is sent to the server.

[0353] Specifically, the user drags and drops the year-end accounting data into a dedicated input form on the terminal and presses the upload button.

[0354] Step 3: Data Training

[0355] The server trains a machine learning model based on collected accounting standards and tax law data. It also fine-tunes the model using historical accounting data and approval documents from within the company.

[0356] Input: Accounting standards and tax law data, historical accounting data

[0357] Data processing: Build machine learning models using TensorFlow or PyTorch, and perform cross-validation and holdout validation on the data.

[0358] Output: Highly accurate machine learning model

[0359] Specifically, the server uses accounting data from the past five years to train the model, and then retrains the model regularly every month.

[0360] Step 4: Data analysis and proposal creation

[0361] The server analyzes accounting data received from the terminal to identify the need for tax adjustments. Based on the analysis results, it calculates appropriate tax adjustment amounts and tax-saving measures, and generates proposals.

[0362] Input: Accounting data submitted by the user

[0363] Data Processing: Using a pre-trained machine learning model, data analysis is performed to identify the need for tax adjustments. The analysis results are output in JSON format.

[0364] Output: Tax adjustment amounts and proposed tax-saving measures.

[0365] In terms of specific operations, the server analyzes accounting data and generates concrete suggestions such as, "By reclassifying this as advertising expenses, you can save 500,000 yen in taxes."

[0366] Step 5: Display Results

[0367] The terminal displays tax adjustments and tax-saving suggestions received from the server to the user. A web browser-based dashboard interface is used for this display.

[0368] Input: Parsing results in JSON format received from the server.

[0369] Data processing: Parse data and convert it into a format suitable for the user interface. Display it visually in an easy-to-understand format using graphs and tables.

[0370] Output: User result display screen

[0371] Specifically, users log in to the device's dashboard and view suggested tax adjustments and tax-saving strategies in real time.

[0372] Step 6: Emotion Recognition and Adjustment

[0373] The emotion engine analyzes user input data and operation history to recognize the user's emotions. Based on the recognized emotions, it adjusts the suggested content and display methods.

[0374] Input: User operation history data such as input speed, mouse movements, and browsing time.

[0375] Data processing: Emotion recognition is performed using machine learning algorithms. Emotional data is extracted using natural language processing techniques.

[0376] Output: Emotion-based interface adjustments and additional support information

[0377] Specifically, if the sentiment engine determines that the user is feeling anxious while reviewing the suggestions, it will display detailed explanations or additional visual guides.

[0378] Step 7: Apply

[0379] The user applies the proposed adjustments to their actual accounting software. Based on the suggestions, they reclassify and adjust their accounting data.

[0380] Input: Proposed tax adjustments and tax-saving measures

[0381] Data processing: Manually enter data into accounting software and make necessary adjustments.

[0382] Output: Adjusted accounting data

[0383] Specifically, the user logs into the accounting software, applies the proposed tax adjustments, and completes the process.

[0384] In this way, the system performs specific data input, data processing, and data output at each step, providing suggestions that are easy for users to understand and apply.

[0385] (Application Example 2)

[0386] 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".

[0387] Conventional tax adjustment systems can propose tax adjustments and tax-saving measures through the analysis of accounting data and related documents, but they cannot provide comprehensive suggestions for inventory management or cost reduction. Furthermore, they often fail to provide user-friendly interfaces and support, thus failing to alleviate user stress and anxiety. This invention aims to solve these problems by providing a system that not only makes tax adjustments but also proposes inventory management and cost reduction, and further provides user-friendly interfaces and support.

[0388] 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.

[0389] This invention includes a server that provides means for collecting regional accounting standards and tax laws and training a machine learning model with them; means for collecting and analyzing organizational accounting data and related documents; means for proposing appropriate tax adjustments and tax-saving measures based on the analysis results; means for collecting and analyzing inventory data to propose optimal inventory levels and cost reduction measures; and means for analyzing user sentiment and adjusting the interface display accordingly. This enables not only tax adjustments but also inventory management and cost reduction suggestions, and further realizes a system that provides an interface and support that takes user sentiment into consideration.

[0390] "Accounting standards" refer to the rules and guidelines regarding financial reporting established in each region and country.

[0391] "Tax law" refers to laws and regulations concerning taxes imposed on organizations and individuals.

[0392] A "machine learning model" is a computational model that learns patterns and rules based on large amounts of data, and uses that knowledge to analyze new data.

[0393] "Analysis" is the process of breaking down data and information to understand its constituent elements and meaning.

[0394] "Tax adjustments" refer to the amount necessary to adjust the appropriate tax amount based on accounting data.

[0395] "Tax-saving measures" refer to methods and strategies for legally reducing taxes in accordance with the law.

[0396] "Inventory data" refers to information about the quantity and types of goods stored in warehouses, stores, etc.

[0397] "Cost reduction measures" refer to methods and strategies for securing profits by reducing necessary expenditures.

[0398] An "emotion engine" is a system that detects a user's emotions and adjusts the interface and support based on those emotions.

[0399] "Interface display" refers to the screens and information displayed when a user operates a system.

[0400] This invention provides a system that combines an emotion engine with a tax adjustment analysis and proposal system that utilizes generation AI. The specific configuration and processing for realizing this system will be described below.

[0401] System components

[0402] 1. Server

[0403] The server performs several main functions:

[0404] Data Collection: The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database. Inventory data collected by robots within the factory is also stored here.

[0405] Data Learning: The server builds and trains a machine learning model based on collected accounting standards and tax law data. Furthermore, it also collects inventory data to learn optimal inventory levels and cost reduction strategies.

[0406] Data Analysis: The server analyzes accounting and inventory data received from terminals to identify the need for tax adjustments and optimization of inventory management. Based on the analysis results, it calculates appropriate tax adjustment amounts, tax-saving measures, and inventory management suggestions.

[0407] Proposal generation: Based on the analysis results, the server sends tax adjustments, tax saving strategies, and inventory management suggestions to the terminal.

[0408] 2. Terminal

[0409] The device has the following features:

[0410] Data Entry: Users input accounting data and related approval documents for a specific accounting period into the terminal. Inventory data collected by the robot is also sent to the server via the terminal.

[0411] Results display: The terminal displays to the user the tax adjustment amounts, tax saving strategies, and inventory management suggestions received from the server.

[0412] 3. Emotional Engine

[0413] The emotion engine has the following functions:

[0414] Emotion Recognition: Analyzes user input data and operation history to recognize user emotions.

[0415] Emotion Adjustment: The emotion engine adjusts how analysis results and suggestions are displayed based on the user's emotions.

[0416] Additional support provided: Provide additional support and explanations based on the user's needs and feelings.

[0417] Program Processing Description

[0418] The server stores regional accounting standards and tax laws, as well as inventory data collected by robots within the factory, in a database, obtained from the internet and official documents. Next, it builds machine learning models based on the collected data and uses generative AI models to analyze tax adjustments, tax saving strategies, and inventory management suggestions. For data analysis, Python's pandas and scikit-learn are used as data analysis tools, and TensorFlow and PyTorch are used for the machine learning models.

[0419] Accounting and inventory data are entered from the user's terminal and sent to the server. The server analyzes the received data and sends the results back to the terminal. The user then reviews the results through the terminal and applies them.

[0420] The emotion engine analyzes the user's emotions based on their operation history and input data, and adjusts how the analysis results and suggestions are displayed. Emotion recognition uses NLP (Natural Language Processing) technology, employing Python NLP libraries (e.g., spaCy, Transformers).

[0421] Specific example

[0422] For example, if a user enters year-end accounting data into the system to check appropriate tax adjustments and tax-saving strategies, the system will provide efficient suggestions based on past accounting and inventory data. At the same time, if the emotion engine senses user anxiety, it will provide detailed explanations and visual data to help the user understand.

[0423] A concrete example of a prompt statement is as follows:

[0424] "We want to develop an application that uses generative AI and an emotion engine to analyze inventory data, propose optimal inventory levels and cost reduction measures, and alleviate manager stress. Please write the program."

[0425] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0426] Step 1:

[0427] The server collects data on regional accounting standards and tax laws from the internet and official documents and stores it in a database. Web scraping tools and APIs are used to obtain the data. After storage in the database, data cleaning is performed to process the data into a well-formed format. This ensures high-quality data in a consistent format. Input is from the internet and official documents, and output is the cleaned data.

[0428] Step 2:

[0429] The server also stores inventory data collected by robots within the factory into its database. The robots perform inventory counts and wirelessly transmit the data to the server. The server cleans the received data again and stores it in the database. This ensures that the latest inventory status is always available. The input is the inventory data provided by the robots, and the output is the cleaned inventory data.

[0430] Step 3:

[0431] The server builds and trains a machine learning model based on collected accounting standards, tax laws, and inventory data. TensorFlow and PyTorch are used for machine learning. The model is trained using the accounting standards and tax law datasets, as well as historical accounting and inventory data. This improves the accuracy of future tax adjustment predictions and inventory management optimization suggestions. The inputs are accounting standards, tax law data, and inventory data, and the output is the trained machine learning model.

[0432] Step 4:

[0433] The user uses a terminal to input accounting data and related approval documents for a specific accounting period. The terminal receives the input from the user and sends that data to the server. The user's input includes year-end accounting data and important approval documents. The input is accounting data and approval documents, and the output is the data sent to the server.

[0434] Step 5:

[0435] The server analyzes received accounting and inventory data to identify the need for tax adjustments, optimal inventory levels, and cost reduction strategies. Python's pandas and scikit-learn libraries are used for data analysis. The analysis results calculate the required tax adjustments, appropriate inventory levels, and efficient cost reduction measures. The input is accounting and inventory data, and the output is the analysis results.

[0436] Step 6:

[0437] The server generates specific tax adjustments, tax-saving strategies, and inventory management suggestions based on the analysis results, and sends them to the terminal. These suggestions include details of tax adjustments, tax-saving strategies, and specific methods for inventory adjustment. The input is the analysis results, and the output is the suggestions sent to the terminal.

[0438] Step 7:

[0439] The terminal displays suggestions received from the server to the user. The user reviews the displayed suggestions and applies them as needed. The display clearly explains the details of the suggestions. The input is the suggestions from the server, and the output is what is displayed to the user.

[0440] Step 8:

[0441] The emotion engine analyzes the user's input history and operation data to recognize their emotions. It utilizes NLP (Natural Language Processing) techniques, employing Python NLP libraries (e.g., spaCy, Transformers). Based on the emotions, it adjusts the display of analysis results and suggestions to reduce user stress and anxiety. Input is the user's operation data and input history, while output is the adjusted interface display.

[0442] 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.

[0443] 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.

[0444] 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.

[0445] [Second Embodiment]

[0446] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0447] 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.

[0448] 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).

[0449] 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.

[0450] 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.

[0451] 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).

[0452] 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.

[0453] 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.

[0454] 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.

[0455] 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.

[0456] 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.

[0457] 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".

[0458] This invention provides a tax adjustment analysis and proposal system that utilizes generation AI. This system consists of the following main components.

[0459] Components

[0460] 1. Server

[0461] 2. Terminal

[0462] 3. User

[0463] server

[0464] The server performs the following functions:

[0465] Data collection: The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database.

[0466] Data Learning: The server trains a machine learning model based on collected accounting standards and tax law data. It also fine-tunes the model using historical accounting data and approval documents from within the company.

[0467] Data Analysis: The server analyzes accounting data received from terminals to identify the need for tax adjustments. Based on the analysis results, it calculates appropriate tax adjustment amounts and tax-saving strategies.

[0468] Proposal generation: The server proposes tax adjustments and tax-saving measures based on the analysis results and sends them to the terminal.

[0469] As a concrete example, the server learns Japanese accounting standards (J-GAAP) and tax laws, and combines them with past corporate accounting data to efficiently perform tax adjustments. Furthermore, the server analyzes data from a specific accounting period and proposes tax savings by reclassifying a portion of entertainment expenses as advertising expenses.

[0470] terminal

[0471] The device performs the following functions:

[0472] Data Entry: Users input data for a specific accounting period and related approval documents into a terminal. The terminal then transmits this data to the server.

[0473] Results display: The terminal displays to the user the tax adjustment amounts and tax saving suggestions received from the server.

[0474] As a concrete example, users can input their year-end accounting data into their terminal and check the linked tax adjustments and tax-saving strategies from the server.

[0475] User

[0476] The user performs the following actions:

[0477] Data entry: Users input data for each accounting period and related approval documents into the terminal.

[0478] Result Confirmation: The user reviews the tax adjustment amount and suggested tax-saving measures displayed on their device.

[0479] Application: The user applies the proposed adjustments to their actual accounting software.

[0480] As a concrete example, before the year-end accounting closing process, users can review the analysis results provided by the server, appropriately reclassify expenses from entertainment expenses to advertising expenses, and maximize tax benefits.

[0481] Thus, by using a generation AI, this invention automatically analyzes the differences between accounting data and tax laws, and provides appropriate tax adjustments and tax-saving measures. Furthermore, this reduces the burden on tax officials while enabling accurate tax payment and tax savings.

[0482] The following describes the processing flow.

[0483] Step 1:

[0484] Data collection

[0485] The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database.

[0486] Users import internal company accounting data and related documents into the terminal, and the terminal then sends this data to the server.

[0487] Step 2:

[0488] Data Learning

[0489] The server uses the collected accounting standards and tax law data to build and train a machine learning model.

[0490] The server uses the company's historical accounting data and approval documents to fine-tune the model, which improves the accuracy of the analysis.

[0491] Step 3:

[0492] Data entry

[0493] The user enters accounting data for a specific accounting period into the terminal.

[0494] The terminal sends the entered data to the server.

[0495] Step 4:

[0496] Data Analysis

[0497] The server analyzes the accounting data received from the terminal.

[0498] The server evaluates whether specific items of accounting data are appropriately classified for tax purposes, based on differences in accounting standards and tax laws in each region.

[0499] Step 5:

[0500] Calculation of tax adjustments and tax-saving measures

[0501] The server identifies the need for tax adjustments based on the analysis results and calculates the required amount of tax adjustments.

[0502] The server proposes tax-advantageous tax-saving strategies. For example, it may suggest reclassifying entertainment expenses as advertising expenses to achieve tax savings.

[0503] Step 6:

[0504] Proposal creation and submission

[0505] The server generates a list of calculated tax adjustments and proposed tax-saving strategies.

[0506] The server sends this information to the terminal.

[0507] Step 7:

[0508] Results display

[0509] The terminal displays the suggestions received from the server to the user.

[0510] The user reviews the tax adjustment amounts and suggested tax-saving measures displayed on the device and makes any necessary corrections.

[0511] Step 8:

[0512] Application of adjustments

[0513] The user applies the displayed suggestions to their accounting software.

[0514] Users review the adjusted data and use it for their final tax return.

[0515] By proceeding step by step in this manner, accurate and efficient tax adjustments and tax-saving strategies can be proposed.

[0516] (Example 1)

[0517] 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".

[0518] Traditional tax adjustments make it extremely difficult for companies to fully understand local accounting standards and tax laws and implement appropriate tax adjustments and tax-saving strategies based on them. Furthermore, manual adjustments and proposals are labor-intensive and prone to errors. Therefore, there is a need to automate these tasks in an efficient and accurate way to reduce the burden on tax professionals.

[0519] 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.

[0520] This invention includes a server that collects regional accounting standards and tax laws and uses them to train a machine learning model; a server that collects and analyzes an organization's accounting data and related documents; and a server that proposes appropriate tax adjustments and tax-saving measures based on the analysis results. This automates the process from collecting accounting data to proposing tax adjustments, enabling efficient and accurate tax processing.

[0521] "Accounting standards" are rules and criteria that companies must follow when preparing financial reports.

[0522] "Tax law" refers to the laws and regulations for calculating and reporting taxes on income and profits.

[0523] A "machine learning model" is a collection of algorithms that learn patterns and rules based on data and use them to make predictions and classifications on new data.

[0524] A "terminal" refers to a device or equipment used by a user to manipulate input data and communicate with a server.

[0525] A "server" is a computer system used to process and store data over a network.

[0526] "Accounting data" refers to data that includes information about a company's financial situation and transactions.

[0527] "Related documents" refer to documents related to accounting data, including approval documents and meeting minutes.

[0528] "Tax adjustment amount" refers to the final tax amount after making the necessary adjustments to calculate the appropriate tax.

[0529] "Tax-saving measures" refer to specific methods or means of legally reducing the tax burden.

[0530] This invention provides a tax adjustment analysis and proposal system that utilizes generation AI. This system mainly consists of three main components: a server, a terminal, and a user.

[0531] server

[0532] The server performs the following functions: First, it collects data on accounting standards and tax laws for each region from the internet and official documents and stores it in a database. A web crawler is used for this data collection, and the collected data is stored in JSON format. Subsequently, the server trains a machine learning model based on the collected accounting standards and tax law data. The Python TensorFlow library is used for this training. In addition, the model is fine-tuned based on past accounting data and approval documents within the company.

[0533] When accounting data is sent from the terminal, the server analyzes the data and identifies the need for tax adjustments. Specifically, it preprocesses the received data (imputing missing values, detecting outliers, etc.) and inputs it into a generating AI model to calculate appropriate tax adjustments and tax-saving measures. Based on these analysis results, the server automatically generates a report in PDF format and sends it to the terminal.

[0534] terminal

[0535] The terminal provides a means for users to input data and related approval documents for a specific accounting period. Users upload the necessary data to the terminal via Excel or CSV files. This data is converted to JSON format on the terminal and sent to the server.

[0536] Once the analysis results are returned from the server, the terminal displays the contents to the user. It has a function to read PDF files and visually display them on the dashboard using graphs and tables. This allows users to intuitively understand the analysis results.

[0537] User

[0538] Users input data for each accounting period and related approval documents into the terminal. Once the user inputs the data, the server analyzes it and proposes appropriate tax adjustments and tax-saving measures. Users can then review the proposed tax adjustments and tax-saving measures displayed on the terminal and apply them to their company's accounting software.

[0539] As a concrete example, a user can enter year-end accounting data and use prompts like the following:

[0540] "I have entered the year-end accounting data. Please provide suggestions regarding tax adjustments and tax-saving strategies."

[0541] By sending this prompt to the server, the server analyzes the input data and provides appropriate suggestions to the user. This automates the entire process, from collecting accounting data to suggesting tax adjustments, efficiently and accurately.

[0542] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0543] Step 1: Data Collection

[0544] The server collects data on regional accounting standards and tax laws from the internet and official sources. Specifically, it uses a web crawler to automatically collect data from national tax authorities and websites providing accounting standards. The collected data is stored in JSON format.

[0545] Input: List of URLs from the internet and official documents

[0546] Output: Accounting standards and tax law data in JSON format

[0547] Step 2: Data Training

[0548] The server trains a machine learning model based on collected accounting standards and tax law data. This process utilizes the Python TensorFlow library. Furthermore, the model is fine-tuned using historical internal accounting data and approval documents from the company.

[0549] Input: Accounting standards and tax law data in JSON format, historical accounting data, and approval documents.

[0550] Output: Trained machine learning model

[0551] Step 3: Data Entry

[0552] Users input data for a specific accounting period and related approval documents from their terminal. Specifically, this is done by uploading Excel or CSV files. The terminal converts this data into JSON format and sends it to the server.

[0553] Input: Accounting data and approval documents in Excel or CSV file format.

[0554] Output: Accounting data and approval documents converted to JSON format

[0555] Step 4: Data Analysis

[0556] The server analyzes the accounting data received from the terminal and identifies the need for tax adjustments. Here, the received data is preprocessed (such as imputing missing values ​​and detecting outliers) and input into a generative AI model. The results of the analysis by the generative AI model are then obtained.

[0557] Input: Accounting data in JSON format and approval documents

[0558] Output: Analysis results (necessity of tax adjustments and adjustment amount)

[0559] Step 5: Proposal Creation

[0560] Based on the analysis results, the server proposes appropriate tax adjustments and tax-saving strategies. During this process, the generated report is saved in PDF format and sent to the user's terminal.

[0561] Input: Analysis results (necessity of tax adjustments and adjustment amount)

[0562] Output: Tax adjustment proposal report in PDF format

[0563] Step 6: Display Results

[0564] The terminal displays tax adjustments and tax-saving strategies received from the server in PDF format to the user. Specifically, it reads the PDF file and displays it visually on the dashboard using graphs and tables.

[0565] Input: Tax adjustment proposal report in PDF format

[0566] Output: Visually displayed analysis results and proposed solutions

[0567] Step 7: Check results and apply

[0568] Users can review the tax adjustments and suggested tax-saving measures displayed on their device and apply them to their company's accounting software. They can also manually modify the adjustments as needed.

[0569] Input: Visually displayed analysis results and proposed content

[0570] Output: Corrected accounting data and applied adjustments

[0571] This automates the process from collecting accounting data to proposing tax adjustments efficiently and accurately.

[0572] (Application Example 1)

[0573] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0574] In modern business operations, tax adjustments require considerable effort and time. This is especially true for owners of brick-and-mortar stores and accounting staff, who often find it difficult to keep up with the latest accounting standards and tax law changes while performing tax adjustments as part of their daily work. Therefore, there is a need to improve the efficiency and accuracy of tax adjustments. Furthermore, there is a demand for systems that utilize generative AI models to automatically suggest appropriate tax-saving strategies.

[0575] 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.

[0576] This invention includes a server that collects regional accounting standards and tax laws and uses them to train a machine learning model; a server that collects and analyzes an organization's accounting data and related documents; a server that proposes appropriate tax adjustments and tax-saving measures based on the analysis results; a server that inputs accounting data into a smart device and displays the analysis results; and a server that generates tax adjustment proposals based on the analysis results using a generative AI model. This makes it possible for store owners and accountants to easily input accounting data and automatically receive accurate tax adjustment proposals and tax-saving measures.

[0577] "Accounting standards" are the rules and guidelines that companies and organizations must follow when preparing financial statements.

[0578] "Tax laws" refer to the laws and regulations established by the state or local government for the purpose of collecting taxes.

[0579] A "machine learning model" is an algorithm that learns from data, recognizes patterns, and makes predictions and classifications on new data.

[0580] "Accounting data" refers to data relating to the financial condition and operating results of a company or organization, and includes financial statements and transaction records.

[0581] "Related documents" refer to various documents accompanying accounting data, including approval documents and expense reports.

[0582] "Analysis results" refer to conclusions and indicators derived by a machine learning model from analyzing accounting data and related documents.

[0583] "Tax adjustment amount" refers to an amount that is modified based on tax regulations and standards.

[0584] "Tax-saving measures" refer to legal measures and methods taken to reduce the tax burden.

[0585] A "smart device" refers to a digital device, such as a smartphone or tablet, that can connect to the internet and perform a variety of functions.

[0586] A "generative AI model" is an artificial intelligence model used for natural language processing and data generation, and in particular, it generates new text based on a prompt.

[0587] A "prompt" is text input to a generative AI model, and it is an instruction that indicates the direction and content of the text that the AI ​​generates.

[0588] This invention provides a tax adjustment analysis and proposal system that utilizes generation AI. This system consists of three main components necessary for carrying out the invention: a server, a terminal, and a user.

[0589] server

[0590] The server performs the following functions:

[0591] 1. Data Collection: The server collects data on accounting standards and tax laws for each region from the internet and official documents, and stores it in a database. The specific software used is the Requests library.

[0592] 2. Data Learning: The server uses the LinearRegression algorithm of the Scikit-learn machine learning model to train on the collected accounting standards and tax law data. The model is also fine-tuned using historical accounting data and approval documents from within the company.

[0593] 3. Data Analysis: The server analyzes the accounting data received from the terminal and identifies the need for tax adjustments. During this process, the generation AI model uses Hugging Face Transformers' GPT-2 to process the analysis results based on the prompt text.

[0594] 4. Proposal Generation: Based on the analysis results, the server generates tax adjustments and tax-saving strategies using an AI model, creates a proposal, and sends it to the terminal. Examples of specific prompt messages:

[0595] Please resolve the gap and propose the optimal tax adjustment rules. Adjustment amount: 15 million yen

[0596] terminal

[0597] The device performs the following functions:

[0598] 1. Data Entry: Users enter data and related documents for a specific accounting period into a terminal. This is done using a smartphone app or other smart device.

[0599] 2. Display of Results: The terminal displays the tax adjustment amounts and tax-saving suggestions received from the server to the user. The display uses graphs and text in a format that is easy for the user to understand.

[0600] User

[0601] The user performs the following actions:

[0602] 1. Data entry: Users enter data and related documents for each accounting period into the terminal.

[0603] 2. Confirmation of results: The user checks the tax adjustment amount and suggested tax-saving measures displayed on the device.

[0604] 3. Application: The user applies the proposed adjustments to their actual accounting software. This ensures proper accounting treatment and maximizes tax benefits.

[0605] As a concrete example, a user inputs year-end accounting data into a smartphone app, a server analyzes that data, and generates appropriate tax adjustment proposals using a generative AI model based on prompt messages. The generated tax adjustment proposals are then displayed on the device, allowing the user to review the content and reflect it in their actual accounting processes. In this way, the efficiency and accuracy of tax adjustments are improved.

[0606] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0607] Step 1:

[0608] Data collection

[0609] The server collects data on accounting standards and tax laws for each region from the internet and official documents. Specifically, it uses the Requests library to retrieve information from official websites and APIs, and stores this data in a database.

[0610] Input: URLs from the internet or official documents

[0611] Output: Collected accounting standards and tax law data

[0612] Specific operation: Retrieve data from the internet in JSON format and save it to the database.

[0613] Step 2:

[0614] Data Learning

[0615] The server trains a machine learning model (Scikit-learn's LinearRegression algorithm) based on accounting standards and tax law data for each region. It also fine-tunes the model using historical accounting data and approval documents from within the company.

[0616] Input: Collected accounting standards and tax law data, historical accounting data of the company

[0617] Output: Trained machine learning model

[0618] Specific actions: Preprocess the data and fit it to a LinearRegression model.

[0619] Step 3:

[0620] Data entry

[0621] Users input data and related documents for a specific accounting period into their device (smartphone app). The app then transmits this data to the server in real time.

[0622] Input: Data for the accounting period, related documents

[0623] Output: Sending data to the server

[0624] Specific actions: Input data using a smartphone app and send it to the server.

[0625] Step 4:

[0626] Data Analysis

[0627] The server analyzes the received accounting data to identify the need for tax adjustments. It uses machine learning models to make predictions and generative AI models (GPT-2) to generate supplementary information.

[0628] Input: Accounting data submitted by the user

[0629] Output: Analysis results, necessary tax adjustments

[0630] Specific actions: Preprocess accounting data and feed it into a pre-trained model for analysis. Based on the analysis results, generate supplementary information using an AI model.

[0631] Step 5:

[0632] Proposal creation

[0633] The server generates tax adjustments and tax-saving strategies based on the analysis results, inputs them into the AI ​​model using appropriate prompts, and generates specific suggestions. This is then sent to the terminal.

[0634] Input: Analysis result, prompt message

[0635] Output: Tax adjustments and proposed tax-saving strategies

[0636] Specific operation: Create a prompt sentence based on the analysis results, input it into the generation AI model, and obtain new text suggestions.

[0637] Step 6:

[0638] Results display

[0639] The terminal displays tax adjustment proposals and tax-saving strategies received from the server to the user. The display is presented in graph and text format to aid user understanding.

[0640] Input: Suggestions from the server

[0641] Output: Tax adjustment proposals and tax saving strategies displayed to the user.

[0642] Specific action: Visualize the suggestions received via the smartphone app and display them to the user.

[0643] Step 7:

[0644] Result verification and application

[0645] The user reviews the tax adjustments and suggested tax-saving measures displayed on the terminal and applies them to their actual accounting software. This ensures proper accounting processing.

[0646] Input: Suggestions displayed on the device

[0647] Output: Application to actual accounting software

[0648] Specific actions: The user reviews the proposed adjustments and enters the data into the accounting software.

[0649] 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.

[0650] This invention combines an emotion engine with a tax adjustment analysis and proposal system that utilizes generation AI to realize a system that provides an interface and proposal content that takes user emotions into consideration. This system consists of the following main components.

[0651] Components

[0652] 1. Server

[0653] 2. Terminal

[0654] 3. Emotional Engine

[0655] 4. User

[0656] server

[0657] The server performs the following functions:

[0658] Data Collection: The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database.

[0659] Data Learning: The server builds and trains a machine learning model based on collected accounting standards and tax law data. It also fine-tunes the model using historical accounting data and approval documents from within the company.

[0660] Data Analysis: The server analyzes accounting data received from terminals to identify the need for tax adjustments. Based on the analysis results, it calculates appropriate tax adjustment amounts and tax-saving strategies.

[0661] Proposal generation: The server proposes tax adjustments and tax-saving measures based on the analysis results and sends them to the terminal.

[0662] As a concrete example, the server learns Japanese accounting standards (J-GAAP) and tax laws, and combines them with past corporate accounting data to efficiently perform tax adjustments. It also analyzes data from a specific accounting period and proposes tax savings by reclassifying a portion of entertainment expenses as advertising expenses.

[0663] terminal

[0664] The device performs the following functions:

[0665] Data Entry: Users input accounting data and related approval documents for a specific accounting period into a terminal. The terminal then transmits this data to the server.

[0666] Results display: The terminal displays to the user the tax adjustment amounts and tax saving suggestions received from the server.

[0667] As a concrete example, users can input their year-end accounting data into their terminal and check the linked tax adjustments and tax-saving strategies from the server.

[0668] Emotional Engine

[0669] The emotion engine performs the following functions:

[0670] Emotion Recognition: Analyzes user input data and operation history to recognize user emotions.

[0671] Emotion Adjustment: The emotion engine adjusts how analysis results and suggestions are displayed based on the user's emotions.

[0672] Additional support provided: Provide additional support and explanations based on the user's needs and feelings.

[0673] For example, if a user feels uneasy about a suggestion from the system, the emotion engine will display detailed explanations and supplementary information to help the user understand.

[0674] User

[0675] The user performs the following actions:

[0676] Data entry: Users input data for each accounting period and related approval documents into the terminal.

[0677] Result Confirmation: The user reviews the tax adjustment amount and suggested tax-saving measures displayed on their device.

[0678] Application: The user applies the proposed adjustments to their actual accounting software.

[0679] For example, before year-end accounting closing, users can review analysis results provided by the server, appropriately reclassify expenses from entertainment expenses to advertising expenses, and maximize tax benefits. Furthermore, the emotion engine recognizes user stress and anxiety, providing supplementary information and support to deliver a superior user experience.

[0680] Thus, by using generation AI, the present invention not only automatically analyzes the differences between accounting data and tax laws and provides appropriate tax adjustments and tax-saving measures, but also provides an interface and support that takes user emotions into consideration, thereby further reducing the burden on tax personnel while achieving accurate tax payment and tax savings.

[0681] The following describes the processing flow.

[0682] Step 1:

[0683] Data collection

[0684] The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database.

[0685] Users import internal company accounting data and related documents into the terminal, and the terminal then sends this data to the server.

[0686] Step 2:

[0687] Data Learning

[0688] The server uses the collected accounting standards and tax law data to train a machine learning model and understand the differences in rules across regions.

[0689] The server uses the company's historical accounting data and documents to fine-tune the model and further improve its accuracy.

[0690] Step 3:

[0691] Data entry

[0692] The user enters accounting data for a specific accounting period into the terminal.

[0693] The terminal sends the entered data to the server.

[0694] Step 4:

[0695] Data Analysis

[0696] The server analyzes the accounting data sent by the user in real time.

[0697] The server identifies the necessary tax adjustments for specific transactions and items, taking into account differences in accounting standards and tax laws in each region.

[0698] Step 5:

[0699] Calculation of tax adjustments and tax-saving measures

[0700] The server calculates the necessary tax adjustments based on the analysis results.

[0701] The server proposes optimal tax-saving strategies. For example, it can reduce the tax burden by properly reclassifying entertainment expenses.

[0702] Step 6:

[0703] Proposal creation and submission

[0704] The server generates a list of calculated tax adjustments and proposed tax-saving strategies.

[0705] The server sends these suggestions to the terminal.

[0706] Step 7:

[0707] emotion recognition

[0708] The emotion engine within the device analyzes user actions and input data to recognize the user's emotions in real time.

[0709] For example, if the system detects that a user is feeling anxious or confused, the emotion engine will perform an analysis.

[0710] Step 8:

[0711] Result display and emotional response

[0712] The terminal displays tax adjustments and tax-saving strategies sent from the server to the user.

[0713] If the emotion engine detects that the user is experiencing anxiety, the device will display additional support information and explanations.

[0714] Step 9:

[0715] User verification and application

[0716] The user reviews the displayed suggestions and applies any necessary adjustments to the accounting software.

[0717] Based on information deemed appropriate by the emotion engine, users proceed with processing with confidence.

[0718] Step 10:

[0719] Final confirmation

[0720] Users review the adjusted data and use it for their final tax return.

[0721] The server stores adjustment data and provides feedback for future learning.

[0722] Through the above process, the present invention can provide users with intuitive, efficient, and accurate tax adjustment and tax saving strategies. Furthermore, by combining it with an emotion engine, the aim is to provide an interface and support that responds to the user's emotions, thereby realizing a stress-free user experience.

[0723] (Example 2)

[0724] 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".

[0725] Conventional tax adjustment systems failed to adequately analyze the differences between regional accounting standards and tax laws, and lacked the means to adjust suggestions to take user sentiment into consideration, often causing stress and anxiety. As a result, tax adjustments and tax-saving strategies were not properly proposed, leading to problems with reduced tax efficiency.

[0726] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting accounting standards and tax laws of each region and training a machine learning model with them; means for inputting the organization's accounting data and related documents and analyzing them; means for proposing appropriate tax adjustments and tax saving measures based on the analysis results and displaying the results; and means for analyzing user sentiment data and adjusting the proposed content and display method according to the sentiment. This enables appropriate tax adjustments and tax saving by automatically analyzing the differences between accounting standards and tax laws of each region and providing an interface that takes the user's sentiment into consideration.

[0727] "Accounting standards" are a set of rules and guidelines concerning financial reporting and accounting practices, used for recording, reporting, and analyzing accounting data in a specific region or country.

[0728] "Tax law" refers to a system of rules and laws governing the calculation, reporting, and payment of taxes imposed by the government on citizens and corporations.

[0729] A "machine learning model" is an algorithm or mathematical model that learns patterns and rules from data and uses them to analyze and predict new data.

[0730] "Accounting data" refers to numerical data and related documents that show an organization's financial condition and operating results, and includes information such as income, expenses, assets, and liabilities.

[0731] "Analysis" is the process of examining data or information in detail to understand its meaning and relationships.

[0732] A "tax adjustment" is an amount calculated based on specific tax laws or accounting standards to adjust the amount of tax payable.

[0733] "Tax-saving measures" refer to methods and means of legally and efficiently reducing the amount of tax owed.

[0734] "Result display" refers to the act of visualizing the analysis results and suggestions processed on the server and presenting them to the user through the user interface.

[0735] "Emotional data" refers to data that indicates a user's emotional state. This data is inferred from factors such as operation history, input speed, and frequency of use, and is used to analyze that state.

[0736] "Proposed content" refers to suggestions regarding tax adjustments and tax-saving measures generated based on the analysis results, and includes specific action plans and recommendations.

[0737] This invention is a system that combines an emotion engine with a tax adjustment analysis and proposal system utilizing generative AI to provide an interface and proposal content that takes user emotions into consideration. This system consists of the following main components.

[0738] 1. Server

[0739] 2. Terminal

[0740] 3. Emotional Engine

[0741] 4. User

[0742] server

[0743] The server performs the following functions:

[0744] Data Collection: The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database. Specifically, commercial database servers and cloud servers are used as hardware. Software used includes web scraping techniques using Python scripts and API integration tools. The collected data is stored in MySQL or PostgreSQL.

[0745] Data Learning: The server builds and trains a machine learning model based on collected accounting standards and tax law data. Specific software used includes machine learning libraries such as TensorFlow and PyTorch. The model is also fine-tuned using historical accounting data and approval documents from within the company. Historical company accounting data is imported from CSV files or Excel spreadsheets, and data preprocessing is performed automatically.

[0746] Data Analysis: The server analyzes accounting data received from terminals to identify the need for tax adjustments. The analysis utilizes data analysis algorithms based on machine learning models. Specifically, Python and R are used for data analysis. Based on the analysis results, appropriate tax adjustments and tax-saving strategies are calculated. For example, by analyzing data for a specific accounting period, the system might propose tax savings by reclassifying a portion of entertainment expenses as advertising expenses.

[0747] Proposal Generation: Based on the analysis results, the server proposes tax adjustments and tax-saving strategies and sends them to the terminal. The generated proposal is converted to JSON format and sent to the terminal using the HTTPS protocol.

[0748] terminal

[0749] The device performs the following functions:

[0750] Data Entry: Users input accounting data and related approval documents for a specific accounting period into the terminal. The terminal provides an upload function for Excel and CSV files. The uploaded data is validated internally and then prepared for transmission to the server.

[0751] Results Display: The terminal displays tax adjustments and tax-saving suggestions received from the server to the user. A web browser-based dashboard interface is used for display, and the data is provided visually in table and graph formats. This makes it easy for the user to understand the suggestions.

[0752] Emotional Engine

[0753] The emotion engine performs the following functions:

[0754] Emotion Recognition: This involves analyzing user input data and operation history to recognize the user's emotions. Natural language processing and machine learning techniques are used for emotion recognition. For example, emotional states are estimated by analyzing user keystroke data, mouse movements, and browsing time.

[0755] Emotion Adjustment: The emotion engine adjusts how analysis results and suggestions are displayed based on the user's emotions. Specifically, if it determines that the user is feeling stressed or anxious, it displays more detailed text and visual guides explaining the suggestions.

[0756] Additional support provided: Provide additional support and explanations based on the user's emotions. For example, if a user feels uneasy about a suggestion from the system, the emotion engine will display detailed explanations and supplementary information to help the user understand.

[0757] User

[0758] The user performs the following actions:

[0759] Data entry: Users input data for each accounting period and related approval documents into the terminal.

[0760] Result Confirmation: The user reviews the tax adjustment amounts and suggested tax-saving measures displayed on the device. For example, they might enter a prompt message such as, "I uploaded last year's entertainment expenses and accounting data; please tell me the appropriate tax adjustment method."

[0761] Application: The user applies the proposed adjustments to their actual accounting software. For example, they input data into their accounting software based on the suggestions and perform tax adjustments.

[0762] Thus, by using generation AI, the present invention not only automatically analyzes the differences between accounting data and tax laws and provides appropriate tax adjustments and tax-saving measures, but also provides an interface and support that takes user emotions into consideration, thereby further reducing the burden on tax personnel while achieving accurate tax payment and tax savings.

[0763] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0764] Step 1: Data Collection

[0765] The server collects data on accounting standards and tax laws for each region from the internet and official documents, and stores it in a database. Specific examples of the data collected include tax law documents and accounting standards provided by government agencies and public accounting bodies.

[0766] Input: Data source URLs for accounting standards and tax laws

[0767] Data Processing: Using Python or R, data is acquired using web scraping techniques. The acquired data is converted to JSON format, and unnecessary information is filtered out.

[0768] Output: Accounting standards and tax law data stored in the database

[0769] Specifically, the server is configured to retrieve data from a specified URL at regular intervals every day and automatically save it to the local database.

[0770] Step 2: Data Entry

[0771] The user enters accounting data and related approval documents for a specific accounting period into the terminal. The data entered by the user is sent to the server.

[0772] Input: Accounting data such as Excel files and CSV files.

[0773] Data processing: The terminal validates the format and content of uploaded files and displays an error message to the user if there are formatting issues.

[0774] Output: Data that has passed validation is sent to the server.

[0775] Specifically, the user drags and drops the year-end accounting data into a dedicated input form on the terminal and presses the upload button.

[0776] Step 3: Data Training

[0777] The server trains a machine learning model based on collected accounting standards and tax law data. It also fine-tunes the model using historical accounting data and approval documents from within the company.

[0778] Input: Accounting standards and tax law data, historical accounting data

[0779] Data processing: Build machine learning models using TensorFlow or PyTorch, and perform cross-validation and holdout validation on the data.

[0780] Output: Highly accurate machine learning model

[0781] Specifically, the server uses accounting data from the past five years to train the model, and then retrains the model regularly every month.

[0782] Step 4: Data analysis and proposal creation

[0783] The server analyzes accounting data received from the terminal to identify the need for tax adjustments. Based on the analysis results, it calculates appropriate tax adjustment amounts and tax-saving measures, and generates proposals.

[0784] Input: Accounting data submitted by the user

[0785] Data Processing: Using a pre-trained machine learning model, data analysis is performed to identify the need for tax adjustments. The analysis results are output in JSON format.

[0786] Output: Tax adjustment amounts and proposed tax-saving measures.

[0787] In terms of specific operations, the server analyzes accounting data and generates concrete suggestions such as, "By reclassifying this as advertising expenses, you can save 500,000 yen in taxes."

[0788] Step 5: Display Results

[0789] The terminal displays tax adjustments and tax-saving suggestions received from the server to the user. A web browser-based dashboard interface is used for this display.

[0790] Input: Parsing results in JSON format received from the server.

[0791] Data processing: Parse data and convert it into a format suitable for the user interface. Display it visually in an easy-to-understand format using graphs and tables.

[0792] Output: User result display screen

[0793] Specifically, users log in to the device's dashboard and view suggested tax adjustments and tax-saving strategies in real time.

[0794] Step 6: Emotion Recognition and Adjustment

[0795] The emotion engine analyzes user input data and operation history to recognize the user's emotions. Based on the recognized emotions, it adjusts the suggested content and display methods.

[0796] Input: User operation history data such as input speed, mouse movements, and browsing time.

[0797] Data processing: Emotion recognition is performed using machine learning algorithms. Emotional data is extracted using natural language processing techniques.

[0798] Output: Emotion-based interface adjustments and additional support information

[0799] Specifically, if the sentiment engine determines that the user is feeling anxious while reviewing the suggestions, it will display detailed explanations or additional visual guides.

[0800] Step 7: Apply

[0801] The user applies the proposed adjustments to their actual accounting software. Based on the suggestions, they reclassify and adjust their accounting data.

[0802] Input: Proposed tax adjustments and tax-saving measures

[0803] Data processing: Manually enter data into accounting software and make necessary adjustments.

[0804] Output: Adjusted accounting data

[0805] Specifically, the user logs into the accounting software, applies the proposed tax adjustments, and completes the process.

[0806] In this way, the system performs specific data input, data processing, and data output at each step, providing suggestions that are easy for users to understand and apply.

[0807] (Application Example 2)

[0808] 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."

[0809] Conventional tax adjustment systems can propose tax adjustments and tax-saving measures through the analysis of accounting data and related documents, but they cannot provide comprehensive suggestions for inventory management or cost reduction. Furthermore, they often fail to provide user-friendly interfaces and support, thus failing to alleviate user stress and anxiety. This invention aims to solve these problems by providing a system that not only makes tax adjustments but also proposes inventory management and cost reduction, and further provides user-friendly interfaces and support.

[0810] 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.

[0811] This invention includes a server that provides means for collecting regional accounting standards and tax laws and training a machine learning model with them; means for collecting and analyzing organizational accounting data and related documents; means for proposing appropriate tax adjustments and tax-saving measures based on the analysis results; means for collecting and analyzing inventory data to propose optimal inventory levels and cost reduction measures; and means for analyzing user sentiment and adjusting the interface display accordingly. This enables not only tax adjustments but also inventory management and cost reduction suggestions, and further realizes a system that provides an interface and support that takes user sentiment into consideration.

[0812] "Accounting standards" refer to the rules and guidelines regarding financial reporting established in each region and country.

[0813] "Tax law" refers to laws and regulations concerning taxes imposed on organizations and individuals.

[0814] A "machine learning model" is a computational model that learns patterns and rules based on large amounts of data, and uses that knowledge to analyze new data.

[0815] "Analysis" is the process of breaking down data and information to understand its constituent elements and meaning.

[0816] "Tax adjustments" refer to the amount necessary to adjust the appropriate tax amount based on accounting data.

[0817] "Tax-saving measures" refer to methods and strategies for legally reducing taxes in accordance with the law.

[0818] "Inventory data" refers to information about the quantity and types of goods stored in warehouses, stores, etc.

[0819] "Cost reduction measures" refer to methods and strategies for securing profits by reducing necessary expenditures.

[0820] An "emotion engine" is a system that detects a user's emotions and adjusts the interface and support based on those emotions.

[0821] "Interface display" refers to the screens and information displayed when a user operates a system.

[0822] This invention provides a system that combines an emotion engine with a tax adjustment analysis and proposal system that utilizes generation AI. The specific configuration and processing for realizing this system will be described below.

[0823] System components

[0824] 1. Server

[0825] The server performs several main functions:

[0826] Data Collection: The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database. Inventory data collected by robots within the factory is also stored here.

[0827] Data Learning: The server builds and trains a machine learning model based on collected accounting standards and tax law data. Furthermore, it also collects inventory data to learn optimal inventory levels and cost reduction strategies.

[0828] Data Analysis: The server analyzes accounting and inventory data received from terminals to identify the need for tax adjustments and optimization of inventory management. Based on the analysis results, it calculates appropriate tax adjustment amounts, tax-saving measures, and inventory management suggestions.

[0829] Proposal generation: Based on the analysis results, the server sends tax adjustments, tax saving strategies, and inventory management suggestions to the terminal.

[0830] 2. Terminal

[0831] The device has the following features:

[0832] Data Entry: Users input accounting data and related approval documents for a specific accounting period into the terminal. Inventory data collected by the robot is also sent to the server via the terminal.

[0833] Results display: The terminal displays to the user the tax adjustment amounts, tax saving strategies, and inventory management suggestions received from the server.

[0834] 3. Emotional Engine

[0835] The emotion engine has the following functions:

[0836] Emotion Recognition: Analyzes user input data and operation history to recognize user emotions.

[0837] Emotion Adjustment: The emotion engine adjusts how analysis results and suggestions are displayed based on the user's emotions.

[0838] Additional support provided: Provide additional support and explanations based on the user's needs and feelings.

[0839] Program Processing Description

[0840] The server stores regional accounting standards and tax laws, as well as inventory data collected by robots within the factory, in a database, obtained from the internet and official documents. Next, it builds machine learning models based on the collected data and uses generative AI models to analyze tax adjustments, tax saving strategies, and inventory management suggestions. For data analysis, Python's pandas and scikit-learn are used as data analysis tools, and TensorFlow and PyTorch are used for the machine learning models.

[0841] Accounting and inventory data are entered from the user's terminal and sent to the server. The server analyzes the received data and sends the results back to the terminal. The user then reviews the results through the terminal and applies them.

[0842] The emotion engine analyzes the user's emotions based on their operation history and input data, and adjusts how the analysis results and suggestions are displayed. Emotion recognition uses NLP (Natural Language Processing) technology, employing Python NLP libraries (e.g., spaCy, Transformers).

[0843] Specific example

[0844] For example, if a user enters year-end accounting data into the system to check appropriate tax adjustments and tax-saving strategies, the system will provide efficient suggestions based on past accounting and inventory data. At the same time, if the emotion engine senses user anxiety, it will provide detailed explanations and visual data to help the user understand.

[0845] A concrete example of a prompt statement is as follows:

[0846] "We want to develop an application that uses generative AI and an emotion engine to analyze inventory data, propose optimal inventory levels and cost reduction measures, and alleviate manager stress. Please write the program."

[0847] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0848] Step 1:

[0849] The server collects data on regional accounting standards and tax laws from the internet and official documents and stores it in a database. Web scraping tools and APIs are used to obtain the data. After storage in the database, data cleaning is performed to process the data into a well-formed format. This ensures high-quality data in a consistent format. Input is from the internet and official documents, and output is the cleaned data.

[0850] Step 2:

[0851] The server also stores inventory data collected by robots within the factory into its database. The robots perform inventory counts and wirelessly transmit the data to the server. The server cleans the received data again and stores it in the database. This ensures that the latest inventory status is always available. The input is the inventory data provided by the robots, and the output is the cleaned inventory data.

[0852] Step 3:

[0853] The server builds and trains a machine learning model based on collected accounting standards, tax laws, and inventory data. TensorFlow and PyTorch are used for machine learning. The model is trained using the accounting standards and tax law datasets, as well as historical accounting and inventory data. This improves the accuracy of future tax adjustment predictions and inventory management optimization suggestions. The inputs are accounting standards, tax law data, and inventory data, and the output is the trained machine learning model.

[0854] Step 4:

[0855] The user uses a terminal to input accounting data and related approval documents for a specific accounting period. The terminal receives the input from the user and sends that data to the server. The user's input includes year-end accounting data and important approval documents. The input is accounting data and approval documents, and the output is the data sent to the server.

[0856] Step 5:

[0857] The server analyzes received accounting and inventory data to identify the need for tax adjustments, optimal inventory levels, and cost reduction strategies. Python's pandas and scikit-learn libraries are used for data analysis. The analysis results calculate the required tax adjustments, appropriate inventory levels, and efficient cost reduction measures. The input is accounting and inventory data, and the output is the analysis results.

[0858] Step 6:

[0859] The server generates specific tax adjustments, tax-saving strategies, and inventory management suggestions based on the analysis results, and sends them to the terminal. These suggestions include details of tax adjustments, tax-saving strategies, and specific methods for inventory adjustment. The input is the analysis results, and the output is the suggestions sent to the terminal.

[0860] Step 7:

[0861] The terminal displays suggestions received from the server to the user. The user reviews the displayed suggestions and applies them as needed. The display clearly explains the details of the suggestions. The input is the suggestions from the server, and the output is what is displayed to the user.

[0862] Step 8:

[0863] The emotion engine analyzes the user's input history and operation data to recognize their emotions. It utilizes NLP (Natural Language Processing) techniques, employing Python NLP libraries (e.g., spaCy, Transformers). Based on the emotions, it adjusts the display of analysis results and suggestions to reduce user stress and anxiety. Input is the user's operation data and input history, while output is the adjusted interface display.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] [Third Embodiment]

[0868] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0869] 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.

[0870] 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).

[0871] 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.

[0872] 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.

[0873] 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).

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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".

[0880] This invention provides a tax adjustment analysis and proposal system that utilizes generation AI. This system consists of the following main components.

[0881] Components

[0882] 1. Server

[0883] 2. Terminal

[0884] 3. User

[0885] server

[0886] The server performs the following functions:

[0887] Data collection: The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database.

[0888] Data Learning: The server trains a machine learning model based on collected accounting standards and tax law data. It also fine-tunes the model using historical accounting data and approval documents from within the company.

[0889] Data Analysis: The server analyzes accounting data received from terminals to identify the need for tax adjustments. Based on the analysis results, it calculates appropriate tax adjustment amounts and tax-saving strategies.

[0890] Proposal generation: The server proposes tax adjustments and tax-saving measures based on the analysis results and sends them to the terminal.

[0891] As a concrete example, the server learns Japanese accounting standards (J-GAAP) and tax laws, and combines them with past corporate accounting data to efficiently perform tax adjustments. Furthermore, the server analyzes data from a specific accounting period and proposes tax savings by reclassifying a portion of entertainment expenses as advertising expenses.

[0892] terminal

[0893] The device performs the following functions:

[0894] Data Entry: Users input data for a specific accounting period and related approval documents into a terminal. The terminal then transmits this data to the server.

[0895] Results display: The terminal displays to the user the tax adjustment amounts and tax saving suggestions received from the server.

[0896] As a concrete example, users can input their year-end accounting data into their terminal and check the linked tax adjustments and tax-saving strategies from the server.

[0897] User

[0898] The user performs the following actions:

[0899] Data entry: Users input data for each accounting period and related approval documents into the terminal.

[0900] Result Confirmation: The user reviews the tax adjustment amount and suggested tax-saving measures displayed on their device.

[0901] Application: The user applies the proposed adjustments to their actual accounting software.

[0902] As a concrete example, before the year-end accounting closing process, users can review the analysis results provided by the server, appropriately reclassify expenses from entertainment expenses to advertising expenses, and maximize tax benefits.

[0903] Thus, by using a generation AI, this invention automatically analyzes the differences between accounting data and tax laws, and provides appropriate tax adjustments and tax-saving measures. Furthermore, this reduces the burden on tax officials while enabling accurate tax payment and tax savings.

[0904] The following describes the processing flow.

[0905] Step 1:

[0906] Data collection

[0907] The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database.

[0908] Users import internal company accounting data and related documents into the terminal, and the terminal then sends this data to the server.

[0909] Step 2:

[0910] Data Learning

[0911] The server uses the collected accounting standards and tax law data to build and train a machine learning model.

[0912] The server uses the company's historical accounting data and approval documents to fine-tune the model, which improves the accuracy of the analysis.

[0913] Step 3:

[0914] Data entry

[0915] The user enters accounting data for a specific accounting period into the terminal.

[0916] The terminal sends the entered data to the server.

[0917] Step 4:

[0918] Data Analysis

[0919] The server analyzes the accounting data received from the terminal.

[0920] The server evaluates whether specific items of accounting data are appropriately classified for tax purposes, based on differences in accounting standards and tax laws in each region.

[0921] Step 5:

[0922] Calculation of tax adjustments and tax-saving measures

[0923] The server identifies the need for tax adjustments based on the analysis results and calculates the required amount of tax adjustments.

[0924] The server proposes tax-advantageous tax-saving strategies. For example, it may suggest reclassifying entertainment expenses as advertising expenses to achieve tax savings.

[0925] Step 6:

[0926] Proposal creation and submission

[0927] The server generates a list of calculated tax adjustments and proposed tax-saving strategies.

[0928] The server sends this information to the terminal.

[0929] Step 7:

[0930] Results display

[0931] The terminal displays the suggestions received from the server to the user.

[0932] The user reviews the tax adjustment amounts and suggested tax-saving measures displayed on the device and makes any necessary corrections.

[0933] Step 8:

[0934] Application of adjustments

[0935] The user applies the displayed suggestions to their accounting software.

[0936] Users review the adjusted data and use it for their final tax return.

[0937] By proceeding step by step in this manner, accurate and efficient tax adjustments and tax-saving strategies can be proposed.

[0938] (Example 1)

[0939] 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."

[0940] Traditional tax adjustments make it extremely difficult for companies to fully understand local accounting standards and tax laws and implement appropriate tax adjustments and tax-saving strategies based on them. Furthermore, manual adjustments and proposals are labor-intensive and prone to errors. Therefore, there is a need to automate these tasks in an efficient and accurate way to reduce the burden on tax professionals.

[0941] 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.

[0942] This invention includes a server that collects regional accounting standards and tax laws and uses them to train a machine learning model; a server that collects and analyzes an organization's accounting data and related documents; and a server that proposes appropriate tax adjustments and tax-saving measures based on the analysis results. This automates the process from collecting accounting data to proposing tax adjustments, enabling efficient and accurate tax processing.

[0943] "Accounting standards" are rules and criteria that companies must follow when preparing financial reports.

[0944] "Tax law" refers to the laws and regulations for calculating and reporting taxes on income and profits.

[0945] A "machine learning model" is a collection of algorithms that learn patterns and rules based on data and use them to make predictions and classifications on new data.

[0946] A "terminal" refers to a device or equipment used by a user to manipulate input data and communicate with a server.

[0947] A "server" is a computer system used to process and store data over a network.

[0948] "Accounting data" refers to data that includes information about a company's financial situation and transactions.

[0949] "Related documents" refer to documents related to accounting data, including approval documents and meeting minutes.

[0950] "Tax adjustment amount" refers to the final tax amount after making the necessary adjustments to calculate the appropriate tax.

[0951] "Tax-saving measures" refer to specific methods or means of legally reducing the tax burden.

[0952] This invention provides a tax adjustment analysis and proposal system that utilizes generation AI. This system mainly consists of three main components: a server, a terminal, and a user.

[0953] server

[0954] The server performs the following functions: First, it collects data on accounting standards and tax laws for each region from the internet and official documents and stores it in a database. A web crawler is used for this data collection, and the collected data is stored in JSON format. Subsequently, the server trains a machine learning model based on the collected accounting standards and tax law data. The Python TensorFlow library is used for this training. In addition, the model is fine-tuned based on past accounting data and approval documents within the company.

[0955] When accounting data is sent from the terminal, the server analyzes the data and identifies the need for tax adjustments. Specifically, it preprocesses the received data (imputing missing values, detecting outliers, etc.) and inputs it into a generating AI model to calculate appropriate tax adjustments and tax-saving measures. Based on these analysis results, the server automatically generates a report in PDF format and sends it to the terminal.

[0956] terminal

[0957] The terminal provides a means for users to input data and related approval documents for a specific accounting period. Users upload the necessary data to the terminal via Excel or CSV files. This data is converted to JSON format on the terminal and sent to the server.

[0958] Once the analysis results are returned from the server, the terminal displays the contents to the user. It has a function to read PDF files and visually display them on the dashboard using graphs and tables. This allows users to intuitively understand the analysis results.

[0959] User

[0960] Users input data for each accounting period and related approval documents into the terminal. Once the user inputs the data, the server analyzes it and proposes appropriate tax adjustments and tax-saving measures. Users can then review the proposed tax adjustments and tax-saving measures displayed on the terminal and apply them to their company's accounting software.

[0961] As a concrete example, a user can enter year-end accounting data and use prompts like the following:

[0962] "I have entered the year-end accounting data. Please provide suggestions regarding tax adjustments and tax-saving strategies."

[0963] By sending this prompt to the server, the server analyzes the input data and provides appropriate suggestions to the user. This automates the entire process, from collecting accounting data to suggesting tax adjustments, efficiently and accurately.

[0964] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0965] Step 1: Data Collection

[0966] The server collects data on regional accounting standards and tax laws from the internet and official sources. Specifically, it uses a web crawler to automatically collect data from national tax authorities and websites providing accounting standards. The collected data is stored in JSON format.

[0967] Input: List of URLs from the internet and official documents

[0968] Output: Accounting standards and tax law data in JSON format

[0969] Step 2: Data Training

[0970] The server trains a machine learning model based on collected accounting standards and tax law data. This process utilizes the Python TensorFlow library. Furthermore, the model is fine-tuned using historical internal accounting data and approval documents from the company.

[0971] Input: Accounting standards and tax law data in JSON format, historical accounting data, and approval documents.

[0972] Output: Trained machine learning model

[0973] Step 3: Data Entry

[0974] Users input data for a specific accounting period and related approval documents from their terminal. Specifically, this is done by uploading Excel or CSV files. The terminal converts this data into JSON format and sends it to the server.

[0975] Input: Accounting data and approval documents in Excel or CSV file format.

[0976] Output: Accounting data and approval documents converted to JSON format

[0977] Step 4: Data Analysis

[0978] The server analyzes the accounting data received from the terminal and identifies the need for tax adjustments. Here, the received data is preprocessed (such as imputing missing values ​​and detecting outliers) and input into a generative AI model. The results of the analysis by the generative AI model are then obtained.

[0979] Input: Accounting data in JSON format and approval documents

[0980] Output: Analysis results (necessity of tax adjustments and adjustment amount)

[0981] Step 5: Proposal Creation

[0982] Based on the analysis results, the server proposes appropriate tax adjustments and tax-saving strategies. During this process, the generated report is saved in PDF format and sent to the user's terminal.

[0983] Input: Analysis results (necessity of tax adjustments and adjustment amount)

[0984] Output: Tax adjustment proposal report in PDF format

[0985] Step 6: Display Results

[0986] The terminal displays tax adjustments and tax-saving strategies received from the server in PDF format to the user. Specifically, it reads the PDF file and displays it visually on the dashboard using graphs and tables.

[0987] Input: Tax adjustment proposal report in PDF format

[0988] Output: Visually displayed analysis results and proposed solutions

[0989] Step 7: Check results and apply

[0990] Users can review the tax adjustments and suggested tax-saving measures displayed on their device and apply them to their company's accounting software. They can also manually modify the adjustments as needed.

[0991] Input: Visually displayed analysis results and proposed content

[0992] Output: Corrected accounting data and applied adjustments

[0993] This automates the process from collecting accounting data to proposing tax adjustments efficiently and accurately.

[0994] (Application Example 1)

[0995] 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."

[0996] In modern business operations, tax adjustments require considerable effort and time. This is especially true for owners of brick-and-mortar stores and accounting staff, who often find it difficult to keep up with the latest accounting standards and tax law changes while performing tax adjustments as part of their daily work. Therefore, there is a need to improve the efficiency and accuracy of tax adjustments. Furthermore, there is a demand for systems that utilize generative AI models to automatically suggest appropriate tax-saving strategies.

[0997] 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.

[0998] This invention includes a server that collects regional accounting standards and tax laws and uses them to train a machine learning model; a server that collects and analyzes an organization's accounting data and related documents; a server that proposes appropriate tax adjustments and tax-saving measures based on the analysis results; a server that inputs accounting data into a smart device and displays the analysis results; and a server that generates tax adjustment proposals based on the analysis results using a generative AI model. This makes it possible for store owners and accountants to easily input accounting data and automatically receive accurate tax adjustment proposals and tax-saving measures.

[0999] "Accounting standards" are the rules and guidelines that companies and organizations must follow when preparing financial statements.

[1000] "Tax laws" refer to the laws and regulations established by the state or local government for the purpose of collecting taxes.

[1001] A "machine learning model" is an algorithm that learns from data, recognizes patterns, and makes predictions and classifications on new data.

[1002] "Accounting data" refers to data relating to the financial condition and operating results of a company or organization, and includes financial statements and transaction records.

[1003] "Related documents" refer to various documents accompanying accounting data, including approval documents and expense reports.

[1004] "Analysis results" refer to conclusions and indicators derived by a machine learning model from analyzing accounting data and related documents.

[1005] "Tax adjustment amount" refers to an amount that is modified based on tax regulations and standards.

[1006] "Tax-saving measures" refer to legal measures and methods taken to reduce the tax burden.

[1007] A "smart device" refers to a digital device, such as a smartphone or tablet, that can connect to the internet and perform a variety of functions.

[1008] A "generative AI model" is an artificial intelligence model used for natural language processing and data generation, and in particular, it generates new text based on a prompt.

[1009] A "prompt" is text input to a generative AI model, and it is an instruction that indicates the direction and content of the text that the AI ​​generates.

[1010] This invention provides a tax adjustment analysis and proposal system that utilizes generation AI. This system consists of three main components necessary for carrying out the invention: a server, a terminal, and a user.

[1011] server

[1012] The server performs the following functions:

[1013] 1. Data Collection: The server collects data on accounting standards and tax laws for each region from the internet and official documents, and stores it in a database. The specific software used is the Requests library.

[1014] 2. Data Learning: The server uses the LinearRegression algorithm of the Scikit-learn machine learning model to train on the collected accounting standards and tax law data. The model is also fine-tuned using historical accounting data and approval documents from within the company.

[1015] 3. Data Analysis: The server analyzes the accounting data received from the terminal and identifies the need for tax adjustments. During this process, the generation AI model uses Hugging Face Transformers' GPT-2 to process the analysis results based on the prompt text.

[1016] 4. Proposal Generation: Based on the analysis results, the server generates tax adjustments and tax-saving strategies using an AI model, creates a proposal, and sends it to the terminal. Examples of specific prompt messages:

[1017] Please resolve the gap and propose the optimal tax adjustment rules. Adjustment amount: 15 million yen

[1018] terminal

[1019] The device performs the following functions:

[1020] 1. Data Entry: Users enter data and related documents for a specific accounting period into a terminal. This is done using a smartphone app or other smart device.

[1021] 2. Display of Results: The terminal displays the tax adjustment amounts and tax-saving suggestions received from the server to the user. The display uses graphs and text in a format that is easy for the user to understand.

[1022] User

[1023] The user performs the following actions:

[1024] 1. Data entry: Users enter data and related documents for each accounting period into the terminal.

[1025] 2. Confirmation of results: The user checks the tax adjustment amount and suggested tax-saving measures displayed on the device.

[1026] 3. Application: The user applies the proposed adjustments to their actual accounting software. This ensures proper accounting treatment and maximizes tax benefits.

[1027] As a concrete example, a user inputs year-end accounting data into a smartphone app, a server analyzes that data, and generates appropriate tax adjustment proposals using a generative AI model based on prompt messages. The generated tax adjustment proposals are then displayed on the device, allowing the user to review the content and reflect it in their actual accounting processes. In this way, the efficiency and accuracy of tax adjustments are improved.

[1028] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1029] Step 1:

[1030] Data collection

[1031] The server collects data on accounting standards and tax laws for each region from the internet and official documents. Specifically, it uses the Requests library to retrieve information from official websites and APIs, and stores this data in a database.

[1032] Input: URLs from the internet or official documents

[1033] Output: Collected accounting standards and tax law data

[1034] Specific operation: Retrieve data from the internet in JSON format and save it to the database.

[1035] Step 2:

[1036] Data Learning

[1037] The server trains a machine learning model (Scikit-learn's LinearRegression algorithm) based on accounting standards and tax law data for each region. It also fine-tunes the model using historical accounting data and approval documents from within the company.

[1038] Input: Collected accounting standards and tax law data, historical accounting data of the company

[1039] Output: Trained machine learning model

[1040] Specific actions: Preprocess the data and fit it to a LinearRegression model.

[1041] Step 3:

[1042] Data entry

[1043] Users input data and related documents for a specific accounting period into their device (smartphone app). The app then transmits this data to the server in real time.

[1044] Input: Data for the accounting period, related documents

[1045] Output: Sending data to the server

[1046] Specific actions: Input data using a smartphone app and send it to the server.

[1047] Step 4:

[1048] Data Analysis

[1049] The server analyzes the received accounting data to identify the need for tax adjustments. It uses machine learning models to make predictions and generative AI models (GPT-2) to generate supplementary information.

[1050] Input: Accounting data submitted by the user

[1051] Output: Analysis results, necessary tax adjustments

[1052] Specific actions: Preprocess accounting data and feed it into a pre-trained model for analysis. Based on the analysis results, generate supplementary information using an AI model.

[1053] Step 5:

[1054] Proposal creation

[1055] The server generates tax adjustments and tax-saving strategies based on the analysis results, inputs them into the AI ​​model using appropriate prompts, and generates specific suggestions. This is then sent to the terminal.

[1056] Input: Analysis result, prompt message

[1057] Output: Tax adjustments and proposed tax-saving strategies

[1058] Specific operation: Create a prompt sentence based on the analysis results, input it into the generation AI model, and obtain new text suggestions.

[1059] Step 6:

[1060] Results display

[1061] The terminal displays tax adjustment proposals and tax-saving strategies received from the server to the user. The display is presented in graph and text format to aid user understanding.

[1062] Input: Suggestions from the server

[1063] Output: Tax adjustment proposals and tax saving strategies displayed to the user.

[1064] Specific action: Visualize the suggestions received via the smartphone app and display them to the user.

[1065] Step 7:

[1066] Result verification and application

[1067] The user reviews the tax adjustments and suggested tax-saving measures displayed on the terminal and applies them to their actual accounting software. This ensures proper accounting processing.

[1068] Input: Suggestions displayed on the device

[1069] Output: Application to actual accounting software

[1070] Specific actions: The user reviews the proposed adjustments and enters the data into the accounting software.

[1071] 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.

[1072] This invention combines an emotion engine with a tax adjustment analysis and proposal system that utilizes generation AI to realize a system that provides an interface and proposal content that takes user emotions into consideration. This system consists of the following main components.

[1073] Components

[1074] 1. Server

[1075] 2. Terminal

[1076] 3. Emotional Engine

[1077] 4. User

[1078] server

[1079] The server performs the following functions:

[1080] Data Collection: The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database.

[1081] Data Learning: The server builds and trains a machine learning model based on collected accounting standards and tax law data. It also fine-tunes the model using historical accounting data and approval documents from within the company.

[1082] Data Analysis: The server analyzes accounting data received from terminals to identify the need for tax adjustments. Based on the analysis results, it calculates appropriate tax adjustment amounts and tax-saving strategies.

[1083] Proposal generation: The server proposes tax adjustments and tax-saving measures based on the analysis results and sends them to the terminal.

[1084] As a concrete example, the server learns Japanese accounting standards (J-GAAP) and tax laws, and combines them with past corporate accounting data to efficiently perform tax adjustments. It also analyzes data from a specific accounting period and proposes tax savings by reclassifying a portion of entertainment expenses as advertising expenses.

[1085] terminal

[1086] The device performs the following functions:

[1087] Data Entry: Users input accounting data and related approval documents for a specific accounting period into a terminal. The terminal then transmits this data to the server.

[1088] Results display: The terminal displays to the user the tax adjustment amounts and tax saving suggestions received from the server.

[1089] As a concrete example, users can input their year-end accounting data into their terminal and check the linked tax adjustments and tax-saving strategies from the server.

[1090] Emotional Engine

[1091] The emotion engine performs the following functions:

[1092] Emotion Recognition: Analyzes user input data and operation history to recognize user emotions.

[1093] Emotion Adjustment: The emotion engine adjusts how analysis results and suggestions are displayed based on the user's emotions.

[1094] Additional support provided: Provide additional support and explanations based on the user's needs and feelings.

[1095] For example, if a user feels uneasy about a suggestion from the system, the emotion engine will display detailed explanations and supplementary information to help the user understand.

[1096] User

[1097] The user performs the following actions:

[1098] Data entry: Users input data for each accounting period and related approval documents into the terminal.

[1099] Result Confirmation: The user reviews the tax adjustment amount and suggested tax-saving measures displayed on their device.

[1100] Application: The user applies the proposed adjustments to their actual accounting software.

[1101] For example, before year-end accounting closing, users can review analysis results provided by the server, appropriately reclassify expenses from entertainment expenses to advertising expenses, and maximize tax benefits. Furthermore, the emotion engine recognizes user stress and anxiety, providing supplementary information and support to deliver a superior user experience.

[1102] Thus, by using generation AI, the present invention not only automatically analyzes the differences between accounting data and tax laws and provides appropriate tax adjustments and tax-saving measures, but also provides an interface and support that takes user emotions into consideration, thereby further reducing the burden on tax personnel while achieving accurate tax payment and tax savings.

[1103] The following describes the processing flow.

[1104] Step 1:

[1105] Data collection

[1106] The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database.

[1107] Users import internal company accounting data and related documents into the terminal, and the terminal then sends this data to the server.

[1108] Step 2:

[1109] Data Learning

[1110] The server uses the collected accounting standards and tax law data to train a machine learning model and understand the differences in rules across regions.

[1111] The server uses the company's historical accounting data and documents to fine-tune the model and further improve its accuracy.

[1112] Step 3:

[1113] Data entry

[1114] The user enters accounting data for a specific accounting period into the terminal.

[1115] The terminal sends the entered data to the server.

[1116] Step 4:

[1117] Data Analysis

[1118] The server analyzes the accounting data sent by the user in real time.

[1119] The server identifies the necessary tax adjustments for specific transactions and items, taking into account differences in accounting standards and tax laws in each region.

[1120] Step 5:

[1121] Calculation of tax adjustments and tax-saving measures

[1122] The server calculates the necessary tax adjustments based on the analysis results.

[1123] The server proposes optimal tax-saving strategies. For example, it can reduce the tax burden by properly reclassifying entertainment expenses.

[1124] Step 6:

[1125] Proposal creation and submission

[1126] The server generates a list of calculated tax adjustments and proposed tax-saving strategies.

[1127] The server sends these suggestions to the terminal.

[1128] Step 7:

[1129] emotion recognition

[1130] The emotion engine within the device analyzes user actions and input data to recognize the user's emotions in real time.

[1131] For example, if the system detects that a user is feeling anxious or confused, the emotion engine will perform an analysis.

[1132] Step 8:

[1133] Result display and emotional response

[1134] The terminal displays tax adjustments and tax-saving strategies sent from the server to the user.

[1135] If the emotion engine detects that the user is experiencing anxiety, the device will display additional support information and explanations.

[1136] Step 9:

[1137] User verification and application

[1138] The user reviews the displayed suggestions and applies any necessary adjustments to the accounting software.

[1139] Based on information deemed appropriate by the emotion engine, users proceed with processing with confidence.

[1140] Step 10:

[1141] Final confirmation

[1142] Users review the adjusted data and use it for their final tax return.

[1143] The server stores adjustment data and provides feedback for future learning.

[1144] Through the above process, the present invention can provide users with intuitive, efficient, and accurate tax adjustment and tax saving strategies. Furthermore, by combining it with an emotion engine, the aim is to provide an interface and support that responds to the user's emotions, thereby realizing a stress-free user experience.

[1145] (Example 2)

[1146] 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."

[1147] Conventional tax adjustment systems failed to adequately analyze the differences between regional accounting standards and tax laws, and lacked the means to adjust suggestions to take user sentiment into consideration, often causing stress and anxiety. As a result, tax adjustments and tax-saving strategies were not properly proposed, leading to problems with reduced tax efficiency.

[1148] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting accounting standards and tax laws of each region and training a machine learning model with them; means for inputting the organization's accounting data and related documents and analyzing them; means for proposing appropriate tax adjustments and tax saving measures based on the analysis results and displaying the results; and means for analyzing user sentiment data and adjusting the proposed content and display method according to the sentiment. This enables appropriate tax adjustments and tax saving by automatically analyzing the differences between accounting standards and tax laws of each region and providing an interface that takes the user's sentiment into consideration.

[1149] "Accounting standards" are a set of rules and guidelines concerning financial reporting and accounting practices, used for recording, reporting, and analyzing accounting data in a specific region or country.

[1150] "Tax law" refers to a system of rules and laws governing the calculation, reporting, and payment of taxes imposed by the government on citizens and corporations.

[1151] A "machine learning model" is an algorithm or mathematical model that learns patterns and rules from data and uses them to analyze and predict new data.

[1152] "Accounting data" refers to numerical data and related documents that show an organization's financial condition and operating results, and includes information such as income, expenses, assets, and liabilities.

[1153] "Analysis" is the process of examining data or information in detail to understand its meaning and relationships.

[1154] A "tax adjustment" is an amount calculated based on specific tax laws or accounting standards to adjust the amount of tax payable.

[1155] "Tax-saving measures" refer to methods and means of legally and efficiently reducing the amount of tax owed.

[1156] "Result display" refers to the act of visualizing the analysis results and suggestions processed on the server and presenting them to the user through the user interface.

[1157] "Emotional data" refers to data that indicates a user's emotional state. This data is inferred from factors such as operation history, input speed, and frequency of use, and is used to analyze that state.

[1158] "Proposed content" refers to suggestions regarding tax adjustments and tax-saving measures generated based on the analysis results, and includes specific action plans and recommendations.

[1159] This invention is a system that combines an emotion engine with a tax adjustment analysis and proposal system utilizing generative AI to provide an interface and proposal content that takes user emotions into consideration. This system consists of the following main components.

[1160] 1. Server

[1161] 2. Terminal

[1162] 3. Emotional Engine

[1163] 4. User

[1164] server

[1165] The server performs the following functions:

[1166] Data Collection: The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database. Specifically, commercial database servers and cloud servers are used as hardware. Software used includes web scraping techniques using Python scripts and API integration tools. The collected data is stored in MySQL or PostgreSQL.

[1167] Data Learning: The server builds and trains a machine learning model based on collected accounting standards and tax law data. Specific software used includes machine learning libraries such as TensorFlow and PyTorch. The model is also fine-tuned using historical accounting data and approval documents from within the company. Historical company accounting data is imported from CSV files or Excel spreadsheets, and data preprocessing is performed automatically.

[1168] Data Analysis: The server analyzes accounting data received from terminals to identify the need for tax adjustments. The analysis utilizes data analysis algorithms based on machine learning models. Specifically, Python and R are used for data analysis. Based on the analysis results, appropriate tax adjustments and tax-saving strategies are calculated. For example, by analyzing data for a specific accounting period, the system might propose tax savings by reclassifying a portion of entertainment expenses as advertising expenses.

[1169] Proposal Generation: Based on the analysis results, the server proposes tax adjustments and tax-saving strategies and sends them to the terminal. The generated proposal is converted to JSON format and sent to the terminal using the HTTPS protocol.

[1170] terminal

[1171] The device performs the following functions:

[1172] Data Entry: Users input accounting data and related approval documents for a specific accounting period into the terminal. The terminal provides an upload function for Excel and CSV files. The uploaded data is validated internally and then prepared for transmission to the server.

[1173] Results Display: The terminal displays tax adjustments and tax-saving suggestions received from the server to the user. A web browser-based dashboard interface is used for display, and the data is provided visually in table and graph formats. This makes it easy for the user to understand the suggestions.

[1174] Emotional Engine

[1175] The emotion engine performs the following functions:

[1176] Emotion Recognition: This involves analyzing user input data and operation history to recognize the user's emotions. Natural language processing and machine learning techniques are used for emotion recognition. For example, emotional states are estimated by analyzing user keystroke data, mouse movements, and browsing time.

[1177] Emotion Adjustment: The emotion engine adjusts how analysis results and suggestions are displayed based on the user's emotions. Specifically, if it determines that the user is feeling stressed or anxious, it displays more detailed text and visual guides explaining the suggestions.

[1178] Additional support provided: Provide additional support and explanations based on the user's emotions. For example, if a user feels uneasy about a suggestion from the system, the emotion engine will display detailed explanations and supplementary information to help the user understand.

[1179] User

[1180] The user performs the following actions:

[1181] Data entry: Users input data for each accounting period and related approval documents into the terminal.

[1182] Result Confirmation: The user reviews the tax adjustment amounts and suggested tax-saving measures displayed on the device. For example, they might enter a prompt message such as, "I uploaded last year's entertainment expenses and accounting data; please tell me the appropriate tax adjustment method."

[1183] Application: The user applies the proposed adjustments to their actual accounting software. For example, they input data into their accounting software based on the suggestions and perform tax adjustments.

[1184] Thus, by using generation AI, the present invention not only automatically analyzes the differences between accounting data and tax laws and provides appropriate tax adjustments and tax-saving measures, but also provides an interface and support that takes user emotions into consideration, thereby further reducing the burden on tax personnel while achieving accurate tax payment and tax savings.

[1185] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1186] Step 1: Data Collection

[1187] The server collects data on accounting standards and tax laws for each region from the internet and official documents, and stores it in a database. Specific examples of the data collected include tax law documents and accounting standards provided by government agencies and public accounting bodies.

[1188] Input: Data source URLs for accounting standards and tax laws

[1189] Data Processing: Using Python or R, data is acquired using web scraping techniques. The acquired data is converted to JSON format, and unnecessary information is filtered out.

[1190] Output: Accounting standards and tax law data stored in the database

[1191] Specifically, the server is configured to retrieve data from a specified URL at regular intervals every day and automatically save it to the local database.

[1192] Step 2: Data Entry

[1193] The user enters accounting data and related approval documents for a specific accounting period into the terminal. The data entered by the user is sent to the server.

[1194] Input: Accounting data such as Excel files and CSV files.

[1195] Data processing: The terminal validates the format and content of uploaded files and displays an error message to the user if there are formatting issues.

[1196] Output: Data that has passed validation is sent to the server.

[1197] Specifically, the user drags and drops the year-end accounting data into a dedicated input form on the terminal and presses the upload button.

[1198] Step 3: Data Training

[1199] The server trains a machine learning model based on collected accounting standards and tax law data. It also fine-tunes the model using historical accounting data and approval documents from within the company.

[1200] Input: Accounting standards and tax law data, historical accounting data

[1201] Data processing: Build machine learning models using TensorFlow or PyTorch, and perform cross-validation and holdout validation on the data.

[1202] Output: Highly accurate machine learning model

[1203] Specifically, the server uses accounting data from the past five years to train the model, and then retrains the model regularly every month.

[1204] Step 4: Data analysis and proposal creation

[1205] The server analyzes accounting data received from the terminal to identify the need for tax adjustments. Based on the analysis results, it calculates appropriate tax adjustment amounts and tax-saving measures, and generates proposals.

[1206] Input: Accounting data submitted by the user

[1207] Data Processing: Using a pre-trained machine learning model, data analysis is performed to identify the need for tax adjustments. The analysis results are output in JSON format.

[1208] Output: Tax adjustment amounts and proposed tax-saving measures.

[1209] In terms of specific operations, the server analyzes accounting data and generates concrete suggestions such as, "By reclassifying this as advertising expenses, you can save 500,000 yen in taxes."

[1210] Step 5: Display Results

[1211] The terminal displays tax adjustments and tax-saving suggestions received from the server to the user. A web browser-based dashboard interface is used for this display.

[1212] Input: Parsing results in JSON format received from the server.

[1213] Data processing: Parse data and convert it into a format suitable for the user interface. Display it visually in an easy-to-understand format using graphs and tables.

[1214] Output: User result display screen

[1215] Specifically, users log in to the device's dashboard and view suggested tax adjustments and tax-saving strategies in real time.

[1216] Step 6: Emotion Recognition and Adjustment

[1217] The emotion engine analyzes user input data and operation history to recognize the user's emotions. Based on the recognized emotions, it adjusts the suggested content and display methods.

[1218] Input: User operation history data such as input speed, mouse movements, and browsing time.

[1219] Data processing: Emotion recognition is performed using machine learning algorithms. Emotional data is extracted using natural language processing techniques.

[1220] Output: Emotion-based interface adjustments and additional support information

[1221] Specifically, if the sentiment engine determines that the user is feeling anxious while reviewing the suggestions, it will display detailed explanations or additional visual guides.

[1222] Step 7: Apply

[1223] The user applies the proposed adjustments to their actual accounting software. Based on the suggestions, they reclassify and adjust their accounting data.

[1224] Input: Proposed tax adjustments and tax-saving measures

[1225] Data processing: Manually enter data into accounting software and make necessary adjustments.

[1226] Output: Adjusted accounting data

[1227] Specifically, the user logs into the accounting software, applies the proposed tax adjustments, and completes the process.

[1228] In this way, the system performs specific data input, data processing, and data output at each step, providing suggestions that are easy for users to understand and apply.

[1229] (Application Example 2)

[1230] 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."

[1231] Conventional tax adjustment systems can propose tax adjustments and tax-saving measures through the analysis of accounting data and related documents, but they cannot provide comprehensive suggestions for inventory management or cost reduction. Furthermore, they often fail to provide user-friendly interfaces and support, thus failing to alleviate user stress and anxiety. This invention aims to solve these problems by providing a system that not only makes tax adjustments but also proposes inventory management and cost reduction, and further provides user-friendly interfaces and support.

[1232] 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.

[1233] This invention includes a server that provides means for collecting regional accounting standards and tax laws and training a machine learning model with them; means for collecting and analyzing organizational accounting data and related documents; means for proposing appropriate tax adjustments and tax-saving measures based on the analysis results; means for collecting and analyzing inventory data to propose optimal inventory levels and cost reduction measures; and means for analyzing user sentiment and adjusting the interface display accordingly. This enables not only tax adjustments but also inventory management and cost reduction suggestions, and further realizes a system that provides an interface and support that takes user sentiment into consideration.

[1234] "Accounting standards" refer to the rules and guidelines regarding financial reporting established in each region and country.

[1235] "Tax law" refers to laws and regulations concerning taxes imposed on organizations and individuals.

[1236] A "machine learning model" is a computational model that learns patterns and rules based on large amounts of data, and uses that knowledge to analyze new data.

[1237] "Analysis" is the process of breaking down data and information to understand its constituent elements and meaning.

[1238] "Tax adjustments" refer to the amount necessary to adjust the appropriate tax amount based on accounting data.

[1239] "Tax-saving measures" refer to methods and strategies for legally reducing taxes in accordance with the law.

[1240] "Inventory data" refers to information about the quantity and types of goods stored in warehouses, stores, etc.

[1241] "Cost reduction measures" refer to methods and strategies for securing profits by reducing necessary expenditures.

[1242] An "emotion engine" is a system that detects a user's emotions and adjusts the interface and support based on those emotions.

[1243] "Interface display" refers to the screens and information displayed when a user operates a system.

[1244] This invention provides a system that combines an emotion engine with a tax adjustment analysis and proposal system that utilizes generation AI. The specific configuration and processing for realizing this system will be described below.

[1245] System components

[1246] 1. Server

[1247] The server performs several main functions:

[1248] Data Collection: The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database. Inventory data collected by robots within the factory is also stored here.

[1249] Data Learning: The server builds and trains a machine learning model based on collected accounting standards and tax law data. Furthermore, it also collects inventory data to learn optimal inventory levels and cost reduction strategies.

[1250] Data Analysis: The server analyzes accounting and inventory data received from terminals to identify the need for tax adjustments and optimization of inventory management. Based on the analysis results, it calculates appropriate tax adjustment amounts, tax-saving measures, and inventory management suggestions.

[1251] Proposal generation: Based on the analysis results, the server sends tax adjustments, tax saving strategies, and inventory management suggestions to the terminal.

[1252] 2. Terminal

[1253] The device has the following features:

[1254] Data Entry: Users input accounting data and related approval documents for a specific accounting period into the terminal. Inventory data collected by the robot is also sent to the server via the terminal.

[1255] Results display: The terminal displays to the user the tax adjustment amounts, tax saving strategies, and inventory management suggestions received from the server.

[1256] 3. Emotional Engine

[1257] The emotion engine has the following functions:

[1258] Emotion Recognition: Analyzes user input data and operation history to recognize user emotions.

[1259] Emotion Adjustment: The emotion engine adjusts how analysis results and suggestions are displayed based on the user's emotions.

[1260] Additional support provided: Provide additional support and explanations based on the user's needs and feelings.

[1261] Program Processing Description

[1262] The server stores regional accounting standards and tax laws, as well as inventory data collected by robots within the factory, in a database, obtained from the internet and official documents. Next, it builds machine learning models based on the collected data and uses generative AI models to analyze tax adjustments, tax saving strategies, and inventory management suggestions. For data analysis, Python's pandas and scikit-learn are used as data analysis tools, and TensorFlow and PyTorch are used for the machine learning models.

[1263] Accounting and inventory data are entered from the user's terminal and sent to the server. The server analyzes the received data and sends the results back to the terminal. The user then reviews the results through the terminal and applies them.

[1264] The emotion engine analyzes the user's emotions based on their operation history and input data, and adjusts how the analysis results and suggestions are displayed. Emotion recognition uses NLP (Natural Language Processing) technology, employing Python NLP libraries (e.g., spaCy, Transformers).

[1265] Specific example

[1266] For example, if a user enters year-end accounting data into the system to check appropriate tax adjustments and tax-saving strategies, the system will provide efficient suggestions based on past accounting and inventory data. At the same time, if the emotion engine senses user anxiety, it will provide detailed explanations and visual data to help the user understand.

[1267] A concrete example of a prompt statement is as follows:

[1268] "We want to develop an application that uses generative AI and an emotion engine to analyze inventory data, propose optimal inventory levels and cost reduction measures, and alleviate manager stress. Please write the program."

[1269] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1270] Step 1:

[1271] The server collects data on regional accounting standards and tax laws from the internet and official documents and stores it in a database. Web scraping tools and APIs are used to obtain the data. After storage in the database, data cleaning is performed to process the data into a well-formed format. This ensures high-quality data in a consistent format. Input is from the internet and official documents, and output is the cleaned data.

[1272] Step 2:

[1273] The server also stores inventory data collected by robots within the factory into its database. The robots perform inventory counts and wirelessly transmit the data to the server. The server cleans the received data again and stores it in the database. This ensures that the latest inventory status is always available. The input is the inventory data provided by the robots, and the output is the cleaned inventory data.

[1274] Step 3:

[1275] The server builds and trains a machine learning model based on collected accounting standards, tax laws, and inventory data. TensorFlow and PyTorch are used for machine learning. The model is trained using the accounting standards and tax law datasets, as well as historical accounting and inventory data. This improves the accuracy of future tax adjustment predictions and inventory management optimization suggestions. The inputs are accounting standards, tax law data, and inventory data, and the output is the trained machine learning model.

[1276] Step 4:

[1277] The user uses a terminal to input accounting data and related approval documents for a specific accounting period. The terminal receives the input from the user and sends that data to the server. The user's input includes year-end accounting data and important approval documents. The input is accounting data and approval documents, and the output is the data sent to the server.

[1278] Step 5:

[1279] The server analyzes received accounting and inventory data to identify the need for tax adjustments, optimal inventory levels, and cost reduction strategies. Python's pandas and scikit-learn libraries are used for data analysis. The analysis results calculate the required tax adjustments, appropriate inventory levels, and efficient cost reduction measures. The input is accounting and inventory data, and the output is the analysis results.

[1280] Step 6:

[1281] The server generates specific tax adjustments, tax-saving strategies, and inventory management suggestions based on the analysis results, and sends them to the terminal. These suggestions include details of tax adjustments, tax-saving strategies, and specific methods for inventory adjustment. The input is the analysis results, and the output is the suggestions sent to the terminal.

[1282] Step 7:

[1283] The terminal displays suggestions received from the server to the user. The user reviews the displayed suggestions and applies them as needed. The display clearly explains the details of the suggestions. The input is the suggestions from the server, and the output is what is displayed to the user.

[1284] Step 8:

[1285] The emotion engine analyzes the user's input history and operation data to recognize their emotions. It utilizes NLP (Natural Language Processing) techniques, employing Python NLP libraries (e.g., spaCy, Transformers). Based on the emotions, it adjusts the display of analysis results and suggestions to reduce user stress and anxiety. Input is the user's operation data and input history, while output is the adjusted interface display.

[1286] 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.

[1287] 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.

[1288] 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.

[1289] [Fourth Embodiment]

[1290] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1291] 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.

[1292] 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).

[1293] 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.

[1294] 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.

[1295] 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).

[1296] 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.

[1297] 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.

[1298] 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.

[1299] 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.

[1300] 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.

[1301] 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.

[1302] 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".

[1303] This invention provides a tax adjustment analysis and proposal system that utilizes generation AI. This system consists of the following main components.

[1304] Components

[1305] 1. Server

[1306] 2. Terminal

[1307] 3. User

[1308] server

[1309] The server performs the following functions:

[1310] Data collection: The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database.

[1311] Data Learning: The server trains a machine learning model based on collected accounting standards and tax law data. It also fine-tunes the model using historical accounting data and approval documents from within the company.

[1312] Data Analysis: The server analyzes accounting data received from terminals to identify the need for tax adjustments. Based on the analysis results, it calculates appropriate tax adjustment amounts and tax-saving strategies.

[1313] Proposal generation: The server proposes tax adjustments and tax-saving measures based on the analysis results and sends them to the terminal.

[1314] As a concrete example, the server learns Japanese accounting standards (J-GAAP) and tax laws, and combines them with past corporate accounting data to efficiently perform tax adjustments. Furthermore, the server analyzes data from a specific accounting period and proposes tax savings by reclassifying a portion of entertainment expenses as advertising expenses.

[1315] terminal

[1316] The device performs the following functions:

[1317] Data Entry: Users input data for a specific accounting period and related approval documents into a terminal. The terminal then transmits this data to the server.

[1318] Results display: The terminal displays to the user the tax adjustment amounts and tax saving suggestions received from the server.

[1319] As a concrete example, users can input their year-end accounting data into their terminal and check the linked tax adjustments and tax-saving strategies from the server.

[1320] User

[1321] The user performs the following actions:

[1322] Data entry: Users input data for each accounting period and related approval documents into the terminal.

[1323] Result Confirmation: The user reviews the tax adjustment amount and suggested tax-saving measures displayed on their device.

[1324] Application: The user applies the proposed adjustments to their actual accounting software.

[1325] As a concrete example, before the year-end accounting closing process, users can review the analysis results provided by the server, appropriately reclassify expenses from entertainment expenses to advertising expenses, and maximize tax benefits.

[1326] Thus, by using a generation AI, this invention automatically analyzes the differences between accounting data and tax laws, and provides appropriate tax adjustments and tax-saving measures. Furthermore, this reduces the burden on tax officials while enabling accurate tax payment and tax savings.

[1327] The following describes the processing flow.

[1328] Step 1:

[1329] Data collection

[1330] The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database.

[1331] Users import internal company accounting data and related documents into the terminal, and the terminal then sends this data to the server.

[1332] Step 2:

[1333] Data Learning

[1334] The server uses the collected accounting standards and tax law data to build and train a machine learning model.

[1335] The server uses the company's historical accounting data and approval documents to fine-tune the model, which improves the accuracy of the analysis.

[1336] Step 3:

[1337] Data entry

[1338] The user enters accounting data for a specific accounting period into the terminal.

[1339] The terminal sends the entered data to the server.

[1340] Step 4:

[1341] Data Analysis

[1342] The server analyzes the accounting data received from the terminal.

[1343] The server evaluates whether specific items of accounting data are appropriately classified for tax purposes, based on differences in accounting standards and tax laws in each region.

[1344] Step 5:

[1345] Calculation of tax adjustments and tax-saving measures

[1346] The server identifies the need for tax adjustments based on the analysis results and calculates the required amount of tax adjustments.

[1347] The server proposes tax-advantageous tax-saving strategies. For example, it may suggest reclassifying entertainment expenses as advertising expenses to achieve tax savings.

[1348] Step 6:

[1349] Proposal creation and submission

[1350] The server generates a list of calculated tax adjustments and proposed tax-saving strategies.

[1351] The server sends this information to the terminal.

[1352] Step 7:

[1353] Results display

[1354] The terminal displays the suggestions received from the server to the user.

[1355] The user reviews the tax adjustment amounts and suggested tax-saving measures displayed on the device and makes any necessary corrections.

[1356] Step 8:

[1357] Application of adjustments

[1358] The user applies the displayed suggestions to their accounting software.

[1359] Users review the adjusted data and use it for their final tax return.

[1360] By proceeding step by step in this manner, accurate and efficient tax adjustments and tax-saving strategies can be proposed.

[1361] (Example 1)

[1362] 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".

[1363] Traditional tax adjustments make it extremely difficult for companies to fully understand local accounting standards and tax laws and implement appropriate tax adjustments and tax-saving strategies based on them. Furthermore, manual adjustments and proposals are labor-intensive and prone to errors. Therefore, there is a need to automate these tasks in an efficient and accurate way to reduce the burden on tax professionals.

[1364] 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.

[1365] This invention includes a server that collects regional accounting standards and tax laws and uses them to train a machine learning model; a server that collects and analyzes an organization's accounting data and related documents; and a server that proposes appropriate tax adjustments and tax-saving measures based on the analysis results. This automates the process from collecting accounting data to proposing tax adjustments, enabling efficient and accurate tax processing.

[1366] "Accounting standards" are rules and criteria that companies must follow when preparing financial reports.

[1367] "Tax law" refers to the laws and regulations for calculating and reporting taxes on income and profits.

[1368] A "machine learning model" is a collection of algorithms that learn patterns and rules based on data and use them to make predictions and classifications on new data.

[1369] A "terminal" refers to a device or equipment used by a user to manipulate input data and communicate with a server.

[1370] A "server" is a computer system used to process and store data over a network.

[1371] "Accounting data" refers to data that includes information about a company's financial situation and transactions.

[1372] "Related documents" refer to documents related to accounting data, including approval documents and meeting minutes.

[1373] "Tax adjustment amount" refers to the final tax amount after making the necessary adjustments to calculate the appropriate tax.

[1374] "Tax-saving measures" refer to specific methods or means of legally reducing the tax burden.

[1375] This invention provides a tax adjustment analysis and proposal system that utilizes generation AI. This system mainly consists of three main components: a server, a terminal, and a user.

[1376] server

[1377] The server performs the following functions: First, it collects data on accounting standards and tax laws for each region from the internet and official documents and stores it in a database. A web crawler is used for this data collection, and the collected data is stored in JSON format. Subsequently, the server trains a machine learning model based on the collected accounting standards and tax law data. The Python TensorFlow library is used for this training. In addition, the model is fine-tuned based on past accounting data and approval documents within the company.

[1378] When accounting data is sent from the terminal, the server analyzes the data and identifies the need for tax adjustments. Specifically, it preprocesses the received data (imputing missing values, detecting outliers, etc.) and inputs it into a generating AI model to calculate appropriate tax adjustments and tax-saving measures. Based on these analysis results, the server automatically generates a report in PDF format and sends it to the terminal.

[1379] terminal

[1380] The terminal provides a means for users to input data and related approval documents for a specific accounting period. Users upload the necessary data to the terminal via Excel or CSV files. This data is converted to JSON format on the terminal and sent to the server.

[1381] Once the analysis results are returned from the server, the terminal displays the contents to the user. It has a function to read PDF files and visually display them on the dashboard using graphs and tables. This allows users to intuitively understand the analysis results.

[1382] User

[1383] Users input data for each accounting period and related approval documents into the terminal. Once the user inputs the data, the server analyzes it and proposes appropriate tax adjustments and tax-saving measures. Users can then review the proposed tax adjustments and tax-saving measures displayed on the terminal and apply them to their company's accounting software.

[1384] As a concrete example, a user can enter year-end accounting data and use prompts like the following:

[1385] "I have entered the year-end accounting data. Please provide suggestions regarding tax adjustments and tax-saving strategies."

[1386] By sending this prompt to the server, the server analyzes the input data and provides appropriate suggestions to the user. This automates the entire process, from collecting accounting data to suggesting tax adjustments, efficiently and accurately.

[1387] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1388] Step 1: Data Collection

[1389] The server collects data on regional accounting standards and tax laws from the internet and official sources. Specifically, it uses a web crawler to automatically collect data from national tax authorities and websites providing accounting standards. The collected data is stored in JSON format.

[1390] Input: List of URLs from the internet and official documents

[1391] Output: Accounting standards and tax law data in JSON format

[1392] Step 2: Data Training

[1393] The server trains a machine learning model based on collected accounting standards and tax law data. This process utilizes the Python TensorFlow library. Furthermore, the model is fine-tuned using historical internal accounting data and approval documents from the company.

[1394] Input: Accounting standards and tax law data in JSON format, historical accounting data, and approval documents.

[1395] Output: Trained machine learning model

[1396] Step 3: Data Entry

[1397] Users input data for a specific accounting period and related approval documents from their terminal. Specifically, this is done by uploading Excel or CSV files. The terminal converts this data into JSON format and sends it to the server.

[1398] Input: Accounting data and approval documents in Excel or CSV file format.

[1399] Output: Accounting data and approval documents converted to JSON format

[1400] Step 4: Data Analysis

[1401] The server analyzes the accounting data received from the terminal and identifies the need for tax adjustments. Here, the received data is preprocessed (such as imputing missing values ​​and detecting outliers) and input into a generative AI model. The results of the analysis by the generative AI model are then obtained.

[1402] Input: Accounting data in JSON format and approval documents

[1403] Output: Analysis results (necessity of tax adjustments and adjustment amount)

[1404] Step 5: Proposal Creation

[1405] Based on the analysis results, the server proposes appropriate tax adjustments and tax-saving strategies. During this process, the generated report is saved in PDF format and sent to the user's terminal.

[1406] Input: Analysis results (necessity of tax adjustments and adjustment amount)

[1407] Output: Tax adjustment proposal report in PDF format

[1408] Step 6: Display Results

[1409] The terminal displays tax adjustments and tax-saving strategies received from the server in PDF format to the user. Specifically, it reads the PDF file and displays it visually on the dashboard using graphs and tables.

[1410] Input: Tax adjustment proposal report in PDF format

[1411] Output: Visually displayed analysis results and proposed solutions

[1412] Step 7: Check results and apply

[1413] Users can review the tax adjustments and suggested tax-saving measures displayed on their device and apply them to their company's accounting software. They can also manually modify the adjustments as needed.

[1414] Input: Visually displayed analysis results and proposed content

[1415] Output: Corrected accounting data and applied adjustments

[1416] This automates the process from collecting accounting data to proposing tax adjustments efficiently and accurately.

[1417] (Application Example 1)

[1418] 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".

[1419] In modern business operations, tax adjustments require considerable effort and time. This is especially true for owners of brick-and-mortar stores and accounting staff, who often find it difficult to keep up with the latest accounting standards and tax law changes while performing tax adjustments as part of their daily work. Therefore, there is a need to improve the efficiency and accuracy of tax adjustments. Furthermore, there is a demand for systems that utilize generative AI models to automatically suggest appropriate tax-saving strategies.

[1420] 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.

[1421] This invention includes a server that collects regional accounting standards and tax laws and uses them to train a machine learning model; a server that collects and analyzes an organization's accounting data and related documents; a server that proposes appropriate tax adjustments and tax-saving measures based on the analysis results; a server that inputs accounting data into a smart device and displays the analysis results; and a server that generates tax adjustment proposals based on the analysis results using a generative AI model. This makes it possible for store owners and accountants to easily input accounting data and automatically receive accurate tax adjustment proposals and tax-saving measures.

[1422] "Accounting standards" are the rules and guidelines that companies and organizations must follow when preparing financial statements.

[1423] "Tax laws" refer to the laws and regulations established by the state or local government for the purpose of collecting taxes.

[1424] A "machine learning model" is an algorithm that learns from data, recognizes patterns, and makes predictions and classifications on new data.

[1425] "Accounting data" refers to data relating to the financial condition and operating results of a company or organization, and includes financial statements and transaction records.

[1426] "Related documents" refer to various documents accompanying accounting data, including approval documents and expense reports.

[1427] "Analysis results" refer to conclusions and indicators derived by a machine learning model from analyzing accounting data and related documents.

[1428] "Tax adjustment amount" refers to an amount that is modified based on tax regulations and standards.

[1429] "Tax-saving measures" refer to legal measures and methods taken to reduce the tax burden.

[1430] A "smart device" refers to a digital device, such as a smartphone or tablet, that can connect to the internet and perform a variety of functions.

[1431] A "generative AI model" is an artificial intelligence model used for natural language processing and data generation, and in particular, it generates new text based on a prompt.

[1432] A "prompt" is text input to a generative AI model, and it is an instruction that indicates the direction and content of the text that the AI ​​generates.

[1433] This invention provides a tax adjustment analysis and proposal system that utilizes generation AI. This system consists of three main components necessary for carrying out the invention: a server, a terminal, and a user.

[1434] server

[1435] The server performs the following functions:

[1436] 1. Data Collection: The server collects data on accounting standards and tax laws for each region from the internet and official documents, and stores it in a database. The specific software used is the Requests library.

[1437] 2. Data Learning: The server uses the LinearRegression algorithm of the Scikit-learn machine learning model to train on the collected accounting standards and tax law data. The model is also fine-tuned using historical accounting data and approval documents from within the company.

[1438] 3. Data Analysis: The server analyzes the accounting data received from the terminal and identifies the need for tax adjustments. During this process, the generation AI model uses Hugging Face Transformers' GPT-2 to process the analysis results based on the prompt text.

[1439] 4. Proposal Generation: Based on the analysis results, the server generates tax adjustments and tax-saving strategies using an AI model, creates a proposal, and sends it to the terminal. Examples of specific prompt messages:

[1440] Please resolve the gap and propose the optimal tax adjustment rules. Adjustment amount: 15 million yen

[1441] terminal

[1442] The device performs the following functions:

[1443] 1. Data Entry: Users enter data and related documents for a specific accounting period into a terminal. This is done using a smartphone app or other smart device.

[1444] 2. Display of Results: The terminal displays the tax adjustment amounts and tax-saving suggestions received from the server to the user. The display uses graphs and text in a format that is easy for the user to understand.

[1445] User

[1446] The user performs the following actions:

[1447] 1. Data entry: Users enter data and related documents for each accounting period into the terminal.

[1448] 2. Confirmation of results: The user checks the tax adjustment amount and suggested tax-saving measures displayed on the device.

[1449] 3. Application: The user applies the proposed adjustments to their actual accounting software. This ensures proper accounting treatment and maximizes tax benefits.

[1450] As a concrete example, a user inputs year-end accounting data into a smartphone app, a server analyzes that data, and generates appropriate tax adjustment proposals using a generative AI model based on prompt messages. The generated tax adjustment proposals are then displayed on the device, allowing the user to review the content and reflect it in their actual accounting processes. In this way, the efficiency and accuracy of tax adjustments are improved.

[1451] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1452] Step 1:

[1453] Data collection

[1454] The server collects data on accounting standards and tax laws for each region from the internet and official documents. Specifically, it uses the Requests library to retrieve information from official websites and APIs, and stores this data in a database.

[1455] Input: URLs from the internet or official documents

[1456] Output: Collected accounting standards and tax law data

[1457] Specific operation: Retrieve data from the internet in JSON format and save it to the database.

[1458] Step 2:

[1459] Data Learning

[1460] The server trains a machine learning model (Scikit-learn's LinearRegression algorithm) based on accounting standards and tax law data for each region. It also fine-tunes the model using historical accounting data and approval documents from within the company.

[1461] Input: Collected accounting standards and tax law data, historical accounting data of the company

[1462] Output: Trained machine learning model

[1463] Specific actions: Preprocess the data and fit it to a LinearRegression model.

[1464] Step 3:

[1465] Data entry

[1466] Users input data and related documents for a specific accounting period into their device (smartphone app). The app then transmits this data to the server in real time.

[1467] Input: Data for the accounting period, related documents

[1468] Output: Sending data to the server

[1469] Specific actions: Input data using a smartphone app and send it to the server.

[1470] Step 4:

[1471] Data Analysis

[1472] The server analyzes the received accounting data to identify the need for tax adjustments. It uses machine learning models to make predictions and generative AI models (GPT-2) to generate supplementary information.

[1473] Input: Accounting data submitted by the user

[1474] Output: Analysis results, necessary tax adjustments

[1475] Specific actions: Preprocess accounting data and feed it into a pre-trained model for analysis. Based on the analysis results, generate supplementary information using an AI model.

[1476] Step 5:

[1477] Proposal creation

[1478] The server generates tax adjustments and tax-saving strategies based on the analysis results, inputs them into the AI ​​model using appropriate prompts, and generates specific suggestions. This is then sent to the terminal.

[1479] Input: Analysis result, prompt message

[1480] Output: Tax adjustments and proposed tax-saving strategies

[1481] Specific operation: Create a prompt sentence based on the analysis results, input it into the generation AI model, and obtain new text suggestions.

[1482] Step 6:

[1483] Results display

[1484] The terminal displays tax adjustment proposals and tax-saving strategies received from the server to the user. The display is presented in graph and text format to aid user understanding.

[1485] Input: Suggestions from the server

[1486] Output: Tax adjustment proposals and tax saving strategies displayed to the user.

[1487] Specific action: Visualize the suggestions received via the smartphone app and display them to the user.

[1488] Step 7:

[1489] Result verification and application

[1490] The user reviews the tax adjustments and suggested tax-saving measures displayed on the terminal and applies them to their actual accounting software. This ensures proper accounting processing.

[1491] Input: Suggestions displayed on the device

[1492] Output: Application to actual accounting software

[1493] Specific actions: The user reviews the proposed adjustments and enters the data into the accounting software.

[1494] 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.

[1495] This invention combines an emotion engine with a tax adjustment analysis and proposal system that utilizes generation AI to realize a system that provides an interface and proposal content that takes user emotions into consideration. This system consists of the following main components.

[1496] Components

[1497] 1. Server

[1498] 2. Terminal

[1499] 3. Emotional Engine

[1500] 4. User

[1501] server

[1502] The server performs the following functions:

[1503] Data Collection: The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database.

[1504] Data Learning: The server builds and trains a machine learning model based on collected accounting standards and tax law data. It also fine-tunes the model using historical accounting data and approval documents from within the company.

[1505] Data Analysis: The server analyzes accounting data received from terminals to identify the need for tax adjustments. Based on the analysis results, it calculates appropriate tax adjustment amounts and tax-saving strategies.

[1506] Proposal generation: The server proposes tax adjustments and tax-saving measures based on the analysis results and sends them to the terminal.

[1507] As a concrete example, the server learns Japanese accounting standards (J-GAAP) and tax laws, and combines them with past corporate accounting data to efficiently perform tax adjustments. It also analyzes data from a specific accounting period and proposes tax savings by reclassifying a portion of entertainment expenses as advertising expenses.

[1508] terminal

[1509] The device performs the following functions:

[1510] Data Entry: Users input accounting data and related approval documents for a specific accounting period into a terminal. The terminal then transmits this data to the server.

[1511] Results display: The terminal displays to the user the tax adjustment amounts and tax saving suggestions received from the server.

[1512] As a concrete example, users can input their year-end accounting data into their terminal and check the linked tax adjustments and tax-saving strategies from the server.

[1513] Emotional Engine

[1514] The emotion engine performs the following functions:

[1515] Emotion Recognition: Analyzes user input data and operation history to recognize user emotions.

[1516] Emotion Adjustment: The emotion engine adjusts how analysis results and suggestions are displayed based on the user's emotions.

[1517] Additional support provided: Provide additional support and explanations based on the user's needs and feelings.

[1518] For example, if a user feels uneasy about a suggestion from the system, the emotion engine will display detailed explanations and supplementary information to help the user understand.

[1519] User

[1520] The user performs the following actions:

[1521] Data entry: Users input data for each accounting period and related approval documents into the terminal.

[1522] Result Confirmation: The user reviews the tax adjustment amount and suggested tax-saving measures displayed on their device.

[1523] Application: The user applies the proposed adjustments to their actual accounting software.

[1524] For example, before year-end accounting closing, users can review analysis results provided by the server, appropriately reclassify expenses from entertainment expenses to advertising expenses, and maximize tax benefits. Furthermore, the emotion engine recognizes user stress and anxiety, providing supplementary information and support to deliver a superior user experience.

[1525] Thus, by using generation AI, the present invention not only automatically analyzes the differences between accounting data and tax laws and provides appropriate tax adjustments and tax-saving measures, but also provides an interface and support that takes user emotions into consideration, thereby further reducing the burden on tax personnel while achieving accurate tax payment and tax savings.

[1526] The following describes the processing flow.

[1527] Step 1:

[1528] Data collection

[1529] The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database.

[1530] Users import internal company accounting data and related documents into the terminal, and the terminal then sends this data to the server.

[1531] Step 2:

[1532] Data Learning

[1533] The server uses the collected accounting standards and tax law data to train a machine learning model and understand the differences in rules across regions.

[1534] The server uses the company's historical accounting data and documents to fine-tune the model and further improve its accuracy.

[1535] Step 3:

[1536] Data entry

[1537] The user enters accounting data for a specific accounting period into the terminal.

[1538] The terminal sends the entered data to the server.

[1539] Step 4:

[1540] Data Analysis

[1541] The server analyzes the accounting data sent by the user in real time.

[1542] The server identifies the necessary tax adjustments for specific transactions and items, taking into account differences in accounting standards and tax laws in each region.

[1543] Step 5:

[1544] Calculation of tax adjustments and tax-saving measures

[1545] The server calculates the necessary tax adjustments based on the analysis results.

[1546] The server proposes optimal tax-saving strategies. For example, it can reduce the tax burden by properly reclassifying entertainment expenses.

[1547] Step 6:

[1548] Proposal creation and submission

[1549] The server generates a list of calculated tax adjustments and proposed tax-saving strategies.

[1550] The server sends these suggestions to the terminal.

[1551] Step 7:

[1552] emotion recognition

[1553] The emotion engine within the device analyzes user actions and input data to recognize the user's emotions in real time.

[1554] For example, if the system detects that a user is feeling anxious or confused, the emotion engine will perform an analysis.

[1555] Step 8:

[1556] Result display and emotional response

[1557] The terminal displays tax adjustments and tax-saving strategies sent from the server to the user.

[1558] If the emotion engine detects that the user is experiencing anxiety, the device will display additional support information and explanations.

[1559] Step 9:

[1560] User verification and application

[1561] The user reviews the displayed suggestions and applies any necessary adjustments to the accounting software.

[1562] Based on information deemed appropriate by the emotion engine, users proceed with processing with confidence.

[1563] Step 10:

[1564] Final confirmation

[1565] Users review the adjusted data and use it for their final tax return.

[1566] The server stores adjustment data and provides feedback for future learning.

[1567] Through the above process, the present invention can provide users with intuitive, efficient, and accurate tax adjustment and tax saving strategies. Furthermore, by combining it with an emotion engine, the aim is to provide an interface and support that responds to the user's emotions, thereby realizing a stress-free user experience.

[1568] (Example 2)

[1569] 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".

[1570] Conventional tax adjustment systems failed to adequately analyze the differences between regional accounting standards and tax laws, and lacked the means to adjust suggestions to take user sentiment into consideration, often causing stress and anxiety. As a result, tax adjustments and tax-saving strategies were not properly proposed, leading to problems with reduced tax efficiency.

[1571] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting accounting standards and tax laws of each region and training a machine learning model with them; means for inputting the organization's accounting data and related documents and analyzing them; means for proposing appropriate tax adjustments and tax saving measures based on the analysis results and displaying the results; and means for analyzing user sentiment data and adjusting the proposed content and display method according to the sentiment. This enables appropriate tax adjustments and tax saving by automatically analyzing the differences between accounting standards and tax laws of each region and providing an interface that takes the user's sentiment into consideration.

[1572] "Accounting standards" are a set of rules and guidelines concerning financial reporting and accounting practices, used for recording, reporting, and analyzing accounting data in a specific region or country.

[1573] "Tax law" refers to a system of rules and laws governing the calculation, reporting, and payment of taxes imposed by the government on citizens and corporations.

[1574] A "machine learning model" is an algorithm or mathematical model that learns patterns and rules from data and uses them to analyze and predict new data.

[1575] "Accounting data" refers to numerical data and related documents that show an organization's financial condition and operating results, and includes information such as income, expenses, assets, and liabilities.

[1576] "Analysis" is the process of examining data or information in detail to understand its meaning and relationships.

[1577] A "tax adjustment" is an amount calculated based on specific tax laws or accounting standards to adjust the amount of tax payable.

[1578] "Tax-saving measures" refer to methods and means of legally and efficiently reducing the amount of tax owed.

[1579] "Result display" refers to the act of visualizing the analysis results and suggestions processed on the server and presenting them to the user through the user interface.

[1580] "Emotional data" refers to data that indicates a user's emotional state. This data is inferred from factors such as operation history, input speed, and frequency of use, and is used to analyze that state.

[1581] "Proposed content" refers to suggestions regarding tax adjustments and tax-saving measures generated based on the analysis results, and includes specific action plans and recommendations.

[1582] This invention is a system that combines an emotion engine with a tax adjustment analysis and proposal system utilizing generative AI to provide an interface and proposal content that takes user emotions into consideration. This system consists of the following main components.

[1583] 1. Server

[1584] 2. Terminal

[1585] 3. Emotional Engine

[1586] 4. User

[1587] server

[1588] The server performs the following functions:

[1589] Data Collection: The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database. Specifically, commercial database servers and cloud servers are used as hardware. Software used includes web scraping techniques using Python scripts and API integration tools. The collected data is stored in MySQL or PostgreSQL.

[1590] Data Learning: The server builds and trains a machine learning model based on collected accounting standards and tax law data. Specific software used includes machine learning libraries such as TensorFlow and PyTorch. The model is also fine-tuned using historical accounting data and approval documents from within the company. Historical company accounting data is imported from CSV files or Excel spreadsheets, and data preprocessing is performed automatically.

[1591] Data Analysis: The server analyzes accounting data received from terminals to identify the need for tax adjustments. The analysis utilizes data analysis algorithms based on machine learning models. Specifically, Python and R are used for data analysis. Based on the analysis results, appropriate tax adjustments and tax-saving strategies are calculated. For example, by analyzing data for a specific accounting period, the system might propose tax savings by reclassifying a portion of entertainment expenses as advertising expenses.

[1592] Proposal Generation: Based on the analysis results, the server proposes tax adjustments and tax-saving strategies and sends them to the terminal. The generated proposal is converted to JSON format and sent to the terminal using the HTTPS protocol.

[1593] terminal

[1594] The device performs the following functions:

[1595] Data Entry: Users input accounting data and related approval documents for a specific accounting period into the terminal. The terminal provides an upload function for Excel and CSV files. The uploaded data is validated internally and then prepared for transmission to the server.

[1596] Results Display: The terminal displays tax adjustments and tax-saving suggestions received from the server to the user. A web browser-based dashboard interface is used for display, and the data is provided visually in table and graph formats. This makes it easy for the user to understand the suggestions.

[1597] Emotional Engine

[1598] The emotion engine performs the following functions:

[1599] Emotion Recognition: This involves analyzing user input data and operation history to recognize the user's emotions. Natural language processing and machine learning techniques are used for emotion recognition. For example, emotional states are estimated by analyzing user keystroke data, mouse movements, and browsing time.

[1600] Emotion Adjustment: The emotion engine adjusts how analysis results and suggestions are displayed based on the user's emotions. Specifically, if it determines that the user is feeling stressed or anxious, it displays more detailed text and visual guides explaining the suggestions.

[1601] Additional support provided: Provide additional support and explanations based on the user's emotions. For example, if a user feels uneasy about a suggestion from the system, the emotion engine will display detailed explanations and supplementary information to help the user understand.

[1602] User

[1603] The user performs the following actions:

[1604] Data entry: Users input data for each accounting period and related approval documents into the terminal.

[1605] Result Confirmation: The user reviews the tax adjustment amounts and suggested tax-saving measures displayed on the device. For example, they might enter a prompt message such as, "I uploaded last year's entertainment expenses and accounting data; please tell me the appropriate tax adjustment method."

[1606] Application: The user applies the proposed adjustments to their actual accounting software. For example, they input data into their accounting software based on the suggestions and perform tax adjustments.

[1607] Thus, by using generation AI, the present invention not only automatically analyzes the differences between accounting data and tax laws and provides appropriate tax adjustments and tax-saving measures, but also provides an interface and support that takes user emotions into consideration, thereby further reducing the burden on tax personnel while achieving accurate tax payment and tax savings.

[1608] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1609] Step 1: Data Collection

[1610] The server collects data on accounting standards and tax laws for each region from the internet and official documents, and stores it in a database. Specific examples of the data collected include tax law documents and accounting standards provided by government agencies and public accounting bodies.

[1611] Input: Data source URLs for accounting standards and tax laws

[1612] Data Processing: Using Python or R, data is acquired using web scraping techniques. The acquired data is converted to JSON format, and unnecessary information is filtered out.

[1613] Output: Accounting standards and tax law data stored in the database

[1614] Specifically, the server is configured to retrieve data from a specified URL at regular intervals every day and automatically save it to the local database.

[1615] Step 2: Data Entry

[1616] The user enters accounting data and related approval documents for a specific accounting period into the terminal. The data entered by the user is sent to the server.

[1617] Input: Accounting data such as Excel files and CSV files.

[1618] Data processing: The terminal validates the format and content of uploaded files and displays an error message to the user if there are formatting issues.

[1619] Output: Data that has passed validation is sent to the server.

[1620] Specifically, the user drags and drops the year-end accounting data into a dedicated input form on the terminal and presses the upload button.

[1621] Step 3: Data Training

[1622] The server trains a machine learning model based on collected accounting standards and tax law data. It also fine-tunes the model using historical accounting data and approval documents from within the company.

[1623] Input: Accounting standards and tax law data, historical accounting data

[1624] Data processing: Build machine learning models using TensorFlow or PyTorch, and perform cross-validation and holdout validation on the data.

[1625] Output: Highly accurate machine learning model

[1626] Specifically, the server uses accounting data from the past five years to train the model, and then retrains the model regularly every month.

[1627] Step 4: Data analysis and proposal creation

[1628] The server analyzes accounting data received from the terminal to identify the need for tax adjustments. Based on the analysis results, it calculates appropriate tax adjustment amounts and tax-saving measures, and generates proposals.

[1629] Input: Accounting data submitted by the user

[1630] Data Processing: Using a pre-trained machine learning model, data analysis is performed to identify the need for tax adjustments. The analysis results are output in JSON format.

[1631] Output: Tax adjustment amounts and proposed tax-saving measures.

[1632] In terms of specific operations, the server analyzes accounting data and generates concrete suggestions such as, "By reclassifying this as advertising expenses, you can save 500,000 yen in taxes."

[1633] Step 5: Display Results

[1634] The terminal displays tax adjustments and tax-saving suggestions received from the server to the user. A web browser-based dashboard interface is used for this display.

[1635] Input: Parsing results in JSON format received from the server.

[1636] Data processing: Parse data and convert it into a format suitable for the user interface. Display it visually in an easy-to-understand format using graphs and tables.

[1637] Output: User result display screen

[1638] Specifically, users log in to the device's dashboard and view suggested tax adjustments and tax-saving strategies in real time.

[1639] Step 6: Emotion Recognition and Adjustment

[1640] The emotion engine analyzes user input data and operation history to recognize the user's emotions. Based on the recognized emotions, it adjusts the suggested content and display methods.

[1641] Input: User operation history data such as input speed, mouse movements, and browsing time.

[1642] Data processing: Emotion recognition is performed using machine learning algorithms. Emotional data is extracted using natural language processing techniques.

[1643] Output: Emotion-based interface adjustments and additional support information

[1644] Specifically, if the sentiment engine determines that the user is feeling anxious while reviewing the suggestions, it will display detailed explanations or additional visual guides.

[1645] Step 7: Apply

[1646] The user applies the proposed adjustments to their actual accounting software. Based on the suggestions, they reclassify and adjust their accounting data.

[1647] Input: Proposed tax adjustments and tax-saving measures

[1648] Data processing: Manually enter data into accounting software and make necessary adjustments.

[1649] Output: Adjusted accounting data

[1650] Specifically, the user logs into the accounting software, applies the proposed tax adjustments, and completes the process.

[1651] In this way, the system performs specific data input, data processing, and data output at each step, providing suggestions that are easy for users to understand and apply.

[1652] (Application Example 2)

[1653] 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".

[1654] Conventional tax adjustment systems can propose tax adjustments and tax-saving measures through the analysis of accounting data and related documents, but they cannot provide comprehensive suggestions for inventory management or cost reduction. Furthermore, they often fail to provide user-friendly interfaces and support, thus failing to alleviate user stress and anxiety. This invention aims to solve these problems by providing a system that not only makes tax adjustments but also proposes inventory management and cost reduction, and further provides user-friendly interfaces and support.

[1655] 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.

[1656] This invention includes a server that provides means for collecting regional accounting standards and tax laws and training a machine learning model with them; means for collecting and analyzing organizational accounting data and related documents; means for proposing appropriate tax adjustments and tax-saving measures based on the analysis results; means for collecting and analyzing inventory data to propose optimal inventory levels and cost reduction measures; and means for analyzing user sentiment and adjusting the interface display accordingly. This enables not only tax adjustments but also inventory management and cost reduction suggestions, and further realizes a system that provides an interface and support that takes user sentiment into consideration.

[1657] "Accounting standards" refer to the rules and guidelines regarding financial reporting established in each region and country.

[1658] "Tax law" refers to laws and regulations concerning taxes imposed on organizations and individuals.

[1659] A "machine learning model" is a computational model that learns patterns and rules based on large amounts of data, and uses that knowledge to analyze new data.

[1660] "Analysis" is the process of breaking down data and information to understand its constituent elements and meaning.

[1661] "Tax adjustments" refer to the amount necessary to adjust the appropriate tax amount based on accounting data.

[1662] "Tax-saving measures" refer to methods and strategies for legally reducing taxes in accordance with the law.

[1663] "Inventory data" refers to information about the quantity and types of goods stored in warehouses, stores, etc.

[1664] "Cost reduction measures" refer to methods and strategies for securing profits by reducing necessary expenditures.

[1665] An "emotion engine" is a system that detects a user's emotions and adjusts the interface and support based on those emotions.

[1666] "Interface display" refers to the screens and information displayed when a user operates a system.

[1667] This invention provides a system that combines an emotion engine with a tax adjustment analysis and proposal system that utilizes generation AI. The specific configuration and processing for realizing this system will be described below.

[1668] System components

[1669] 1. Server

[1670] The server performs several main functions:

[1671] Data Collection: The server collects data on regional accounting standards and tax laws from the internet and official documents, and stores it in a database. Inventory data collected by robots within the factory is also stored here.

[1672] Data Learning: The server builds and trains a machine learning model based on collected accounting standards and tax law data. Furthermore, it also collects inventory data to learn optimal inventory levels and cost reduction strategies.

[1673] Data Analysis: The server analyzes accounting and inventory data received from terminals to identify the need for tax adjustments and optimization of inventory management. Based on the analysis results, it calculates appropriate tax adjustment amounts, tax-saving measures, and inventory management suggestions.

[1674] Proposal generation: Based on the analysis results, the server sends tax adjustments, tax saving strategies, and inventory management suggestions to the terminal.

[1675] 2. Terminal

[1676] The device has the following features:

[1677] Data Entry: Users input accounting data and related approval documents for a specific accounting period into the terminal. Inventory data collected by the robot is also sent to the server via the terminal.

[1678] Results display: The terminal displays to the user the tax adjustment amounts, tax saving strategies, and inventory management suggestions received from the server.

[1679] 3. Emotional Engine

[1680] The emotion engine has the following functions:

[1681] Emotion Recognition: Analyzes user input data and operation history to recognize user emotions.

[1682] Emotion Adjustment: The emotion engine adjusts how analysis results and suggestions are displayed based on the user's emotions.

[1683] Additional support provided: Provide additional support and explanations based on the user's needs and feelings.

[1684] Program Processing Description

[1685] The server stores regional accounting standards and tax laws, as well as inventory data collected by robots within the factory, in a database, obtained from the internet and official documents. Next, it builds machine learning models based on the collected data and uses generative AI models to analyze tax adjustments, tax saving strategies, and inventory management suggestions. For data analysis, Python's pandas and scikit-learn are used as data analysis tools, and TensorFlow and PyTorch are used for the machine learning models.

[1686] Accounting and inventory data are entered from the user's terminal and sent to the server. The server analyzes the received data and sends the results back to the terminal. The user then reviews the results through the terminal and applies them.

[1687] The emotion engine analyzes the user's emotions based on their operation history and input data, and adjusts how the analysis results and suggestions are displayed. Emotion recognition uses NLP (Natural Language Processing) technology, employing Python NLP libraries (e.g., spaCy, Transformers).

[1688] Specific example

[1689] For example, if a user enters year-end accounting data into the system to check appropriate tax adjustments and tax-saving strategies, the system will provide efficient suggestions based on past accounting and inventory data. At the same time, if the emotion engine senses user anxiety, it will provide detailed explanations and visual data to help the user understand.

[1690] A concrete example of a prompt statement is as follows:

[1691] "We want to develop an application that uses generative AI and an emotion engine to analyze inventory data, propose optimal inventory levels and cost reduction measures, and alleviate manager stress. Please write the program."

[1692] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1693] Step 1:

[1694] The server collects data on regional accounting standards and tax laws from the internet and official documents and stores it in a database. Web scraping tools and APIs are used to obtain the data. After storage in the database, data cleaning is performed to process the data into a well-formed format. This ensures high-quality data in a consistent format. Input is from the internet and official documents, and output is the cleaned data.

[1695] Step 2:

[1696] The server also stores inventory data collected by robots within the factory into its database. The robots perform inventory counts and wirelessly transmit the data to the server. The server cleans the received data again and stores it in the database. This ensures that the latest inventory status is always available. The input is the inventory data provided by the robots, and the output is the cleaned inventory data.

[1697] Step 3:

[1698] The server builds and trains a machine learning model based on collected accounting standards, tax laws, and inventory data. TensorFlow and PyTorch are used for machine learning. The model is trained using the accounting standards and tax law datasets, as well as historical accounting and inventory data. This improves the accuracy of future tax adjustment predictions and inventory management optimization suggestions. The inputs are accounting standards, tax law data, and inventory data, and the output is the trained machine learning model.

[1699] Step 4:

[1700] The user uses a terminal to input accounting data and related approval documents for a specific accounting period. The terminal receives the input from the user and sends that data to the server. The user's input includes year-end accounting data and important approval documents. The input is accounting data and approval documents, and the output is the data sent to the server.

[1701] Step 5:

[1702] The server analyzes received accounting and inventory data to identify the need for tax adjustments, optimal inventory levels, and cost reduction strategies. Python's pandas and scikit-learn libraries are used for data analysis. The analysis results calculate the required tax adjustments, appropriate inventory levels, and efficient cost reduction measures. The input is accounting and inventory data, and the output is the analysis results.

[1703] Step 6:

[1704] The server generates specific tax adjustments, tax-saving strategies, and inventory management suggestions based on the analysis results, and sends them to the terminal. These suggestions include details of tax adjustments, tax-saving strategies, and specific methods for inventory adjustment. The input is the analysis results, and the output is the suggestions sent to the terminal.

[1705] Step 7:

[1706] The terminal displays suggestions received from the server to the user. The user reviews the displayed suggestions and applies them as needed. The display clearly explains the details of the suggestions. The input is the suggestions from the server, and the output is what is displayed to the user.

[1707] Step 8:

[1708] The emotion engine analyzes the user's input history and operation data to recognize their emotions. It utilizes NLP (Natural Language Processing) techniques, employing Python NLP libraries (e.g., spaCy, Transformers). Based on the emotions, it adjusts the display of analysis results and suggestions to reduce user stress and anxiety. Input is the user's operation data and input history, while output is the adjusted interface display.

[1709] 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.

[1710] 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.

[1711] 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.

[1712] 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.

[1713] 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.

[1714] 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.

[1715] 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.

[1716] 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.

[1717] 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."

[1718] 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.

[1719] 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.

[1720] 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.

[1721] 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.

[1722] 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.

[1723] 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.

[1724] 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.

[1725] 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.

[1726] 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.

[1727] 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.

[1728] 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.

[1729] 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.

[1730] The following is further disclosed regarding the embodiments described above.

[1731] (Claim 1)

[1732] A means of collecting accounting standards and tax laws from each region and training a machine learning model with them,

[1733] A means of collecting and analyzing organizational accounting data and related documents,

[1734] A means of proposing appropriate tax adjustments and tax-saving measures based on the analysis results,

[1735] A system that includes this.

[1736] (Claim 2)

[1737] The system according to claim 1, wherein a machine learning model automatically analyzes the differences between accounting standards and tax laws in each region.

[1738] (Claim 3)

[1739] The system according to claim 1, having means for inputting data for a specific accounting period of an organization and displaying proposed tax adjustments and tax saving measures.

[1740]

[1741] "Example 1"

[1742] (Claim 1)

[1743] A means of collecting accounting standards and tax laws from each region and training a machine learning model with them,

[1744] A means of collecting and analyzing organizational accounting data and related documents,

[1745] A means of proposing appropriate tax adjustments and tax-saving measures based on the analysis results,

[1746] A means of inputting accounting data and related documents from a terminal,

[1747] A means of displaying tax adjustment amounts and tax saving strategies on a terminal,

[1748] A system that includes this.

[1749] (Claim 2)

[1750] The system according to claim 1, wherein a machine learning model automatically analyzes the differences between accounting standards and tax laws in each region.

[1751] (Claim 3)

[1752] The system according to claim 1, having means for inputting data for a specific accounting period of an organization and displaying proposed tax adjustments and tax saving measures.

[1753] "Application Example 1"

[1754] (Claim 1)

[1755] A means of collecting accounting standards and tax laws from each region and training a machine learning model with them,

[1756] A means of collecting and analyzing organizational accounting data and related documents,

[1757] A means of proposing appropriate tax adjustments and tax-saving measures based on the analysis results,

[1758] A means of inputting accounting data into a smart device and displaying the analysis results,

[1759] A means of generating tax adjustment proposals based on analysis results using a generative AI model,

[1760] A system that includes this.

[1761] (Claim 2)

[1762] The system according to claim 1, wherein a machine learning model automatically analyzes the differences between accounting standards and tax laws in each region.

[1763] (Claim 3)

[1764] The system according to claim 1, having means for inputting data for a specific accounting period of an organization and displaying proposed tax adjustments and tax saving measures, and generating detailed suggestions using prompt statements to a generating AI model.

[1765] "Example 2 of combining an emotion engine"

[1766] (Claim 1)

[1767] A means of collecting accounting standards and tax laws from each region and training a machine learning model with them,

[1768] A means of inputting organizational accounting data and related documents and analyzing them,

[1769] Based on the analysis results, it proposes appropriate tax adjustments and tax-saving measures, and provides a means to display the results.

[1770] A means of analyzing user emotion data and adjusting the suggested content and display method according to the emotion,

[1771] A system that includes this.

[1772] (Claim 2)

[1773] The system according to claim 1, wherein a machine learning model automatically analyzes the differences between accounting standards and tax laws in each region.

[1774] (Claim 3)

[1775] The system according to claim 1, which has means for inputting data for a specific accounting period of an organization, displaying proposed tax adjustments and tax-saving measures, and providing additional support based on the user's sentiment.

[1776] "Application example 2 when combining with an emotional engine"

[1777] (Claim 1)

[1778] A means of collecting accounting standards and tax laws from each region and training a machine learning model with them,

[1779] A means of collecting and analyzing organizational accounting data and related documents,

[1780] A means of proposing appropriate tax adjustments and tax-saving measures based on the analysis results,

[1781] A method for collecting inventory data, analyzing it, and proposing optimal inventory levels and cost reduction measures,

[1782] A means for analyzing user emotions and adjusting the interface display based on this,

[1783] A system that includes this.

[1784] (Claim 2)

[1785] The system according to claim 1, wherein a machine learning model automatically analyzes the differences between accounting standards and tax laws in each region.

[1786] (Claim 3)

[1787] The system according to claim 1, having means for inputting data for a specific accounting period of an organization and displaying proposed tax adjustments and tax saving measures. [Explanation of Symbols]

[1788] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting accounting standards and tax laws from each region and training a machine learning model with them, A means of collecting and analyzing organizational accounting data and related documents, A means of proposing appropriate tax adjustments and tax-saving measures based on the analysis results, A system that includes this.

2. The system according to claim 1, wherein a machine learning model automatically analyzes the differences between accounting standards and tax laws in each region.

3. The system according to claim 1, comprising means for inputting data for a specific accounting period of an organization and displaying proposed tax adjustments and tax saving measures.

Images