Task management device, method for controlling the task management device, and control program for the task management device

Abstract

Properly managing tasks related to tax and accounting work. [Solution] A task management device for managing tasks related to the tax and accounting operations of a business operator, comprising: a task information generation unit that receives instruction information regarding task generation and generates task information; a display control unit that presents the task information to a user; and a task management unit that registers tasks based on the user's approval, wherein the task information generation unit generates the task information using publicly available information including at least laws and regulations and circulars related to tax and accounting, the business operator's past task information including at least one of the user's comments or revision history, and a generation AI model.

Description

Technical Field

[0001] The present invention relates to an apparatus for managing tasks related to the tax and accounting operations of businesses.

Background Art

[0002] Conventionally, a system has been known for sharing and managing tax-related task data between administrators such as certified public accountants and tax accountants, and management targets such as sole proprietors and client companies (Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the system described in Patent Document 1, it is premised that at least one of the administrator and the management target recognizes tasks related to tax procedures and the like with correct knowledge. However, tasks related to tax and accounting operations cover a wide range, and since legal amendments are frequent, it is necessary to always be familiar with the latest specialized knowledge, and task management has been a major burden for both the administrator and the management target.

[0005] Therefore, an object of the present invention is to assist in correctly managing tasks related to tax and accounting operations.

Means for Solving the Problems

[0006] To solve the above problems, the present invention provides a device for managing tasks related to the tax and accounting operations of a business operator, comprising: a task information generation unit that receives instruction information regarding task generation and generates task information; a display control unit that presents the task information to a user; and a task management unit that registers tasks based on the user's approval, wherein the task information generation unit generates the task information using publicly available information including at least laws and regulations and circulars related to tax and accounting, past task information of the business operator including at least one of the user's comments or revision history, and a generation AI model. [Effects of the Invention]

[0007] According to the present invention, tasks related to tax and accounting operations can be easily managed correctly. [Brief explanation of the drawing]

[0008] [Figure 1] This figure shows an example of the system configuration according to an embodiment of the present invention. [Figure 2] This is an example of a screen configuration according to an embodiment of the present invention. [Figure 3] This is an example of a screen configuration according to an embodiment of the present invention. [Figure 4] This is an example of a screen configuration according to an embodiment of the present invention. [Figure 5] This is an example of a screen configuration according to an embodiment of the present invention. [Figure 6] This is an example of a screen configuration according to an embodiment of the present invention. [Figure 7] This is an example of a screen configuration according to an embodiment of the present invention. [Figure 8] This is an example of the hardware configuration of Server 1 according to an embodiment of the present invention. [Figure 9] This is an example of the software configuration of Server 1 according to an embodiment of the present invention. [Figure 10] This is an example of the configuration of task information according to an embodiment of the present invention. [Figure 11] This is an example of a screen configuration according to an embodiment of the present invention. [Figure 12] This is an example of a screen configuration according to an embodiment of the present invention. [Figure 13] This is a processing flow diagram according to an embodiment of the present invention. [Modes for carrying out the invention]

[0009] Embodiments of the present invention will be described below with reference to the drawings. The embodiments described below are not intended to unduly limit the scope of the present invention as described in the claims. Furthermore, not all of the configurations described below are necessarily essential components of the present invention.

[0010] Figure 1 shows an example configuration of a task management support system according to one embodiment of the present invention. The task management support system includes at least a server 1 and a user terminal 2.

[0011] This invention relates to a device for supporting task management related to tax and accounting for businesses, including corporations and individuals operating sole proprietorships. Businesses face a variety of tax and accounting tasks throughout the year. These tasks include typical, routine tasks that apply to almost all businesses, such as filing corporate tax returns within two months of the closing date, performing year-end adjustments in December, and paying withholding income tax at the prescribed time. However, there are also a wide range of ad-hoc tasks, such as submitting pre-determined notifications for executive bonuses and handling administrative procedures related to employee retirements. In most cases, each of these tasks has a legal deadline.

[0012] In this invention, the "user" may be the business owner themselves, or a supporter such as a tax accountant's office or accounting firm that supports the business owner. If the user is the business owner, they can use the device of this invention to recognize all of their tasks and manage them to complete them within the deadline, even if they lack specialized knowledge. If the user is a supporter such as a tax accountant's office or accounting firm, they can recognize all of their client business owner's tasks and support their work to complete them within the deadline. Furthermore, while the tasks related to tax and accounting in this invention typically concern accounting processing and filing declarations and notifications to the tax office, they may also include tasks related to social insurance, labor insurance, pensions, personnel, and labor.

[0013] Figures 2 to 7 illustrate the basic functions of the task management support system according to the present invention. Figures 2 to 7 show examples of screen configurations of the task management support system according to the present invention when the user is a supporter such as a tax accountant's office or accounting firm. Figure 2 shows an example of the home screen configuration of the application of the task management support system according to the present invention. The task status display area at the top shows the status of tasks for all of the client businesses of the supporter, who is the user, and as an example, it displays the total number of unprocessed tasks. "Overdue Tasks" is the number of tasks that have exceeded the deadline set when registering a task in this task management support system. "Tasks for This Month" is the number of registered tasks whose deadline is in the current month. "Tax Categories for This Month" represents the number of tax categories related to tasks whose deadline is in the current month. A tax category is a concept that indicates the classification of tasks, such as "Corporate Tax Settlement / Filing" or "Consumption Tax Filing". Multiple specific tasks will belong to each tax category.

[0014] At the lower part of the screen, a task status display column for each client is provided, which shows the status of tasks for each client. As an example, for each client, the client name, closing month, number of overdue tasks, number of tasks this month, and number of tax categories this month are aggregated and displayed. In the example of Fig. 2, for Company BBB, there are 4 overdue tasks, 6 tasks this month, and 2 tax categories this month, namely "Corporate Tax Settlement & Declaration" and "Consumption Tax Declaration". For the tasks of Company AAA and Company CCC, it shows that there are no overdue tasks and no tasks this month. With this screen, the user, who is the supporter, can comprehensively grasp the status of tasks for all clients in a list-like manner.

[0015] Fig. 3 is a configuration example of a screen that displays a list of clients of the user who is the supporter. The user can register the information of business clients in this system and register them as clients. When registering, basic information of the client such as the client name, whether it is a corporation or an individual, closing month, location, representative name, etc. can be input, and a person in charge on the supporter side can also be assigned. The user, who is the supporter, can centrally manage multiple clients on this screen.

[0016] Fig. 4 is a configuration example of a screen that displays a list of tasks. In the list display column, information such as the task name, tax category, status, client name, closing month, task assignee, deadline, etc. can be displayed as the information of the tasks to be listed, but it is not limited to this. The items to be displayed can be changed as appropriate and can also be customized by the user. Also, in Fig. 4, an example of listing the tasks of Company BBB is shown, but the tasks of all clients can also be listed in ascending order of proximity to the deadline. As an example, it may have a filter function to display only tasks whose each item has specific content. By specifying the content of any item in the filter setting column, only the corresponding tasks can be listed and displayed. In Fig. 4, it is shown that an input has been made in the filter setting column with the content that the status is "uncompleted" and the client is "Company BBB".

[0017] Figure 5 shows an example of the screen layout when tasks are displayed in a calendar format. The calendar for a given month is displayed in calendar format, and the number of tasks with deadlines set for each day is shown numerically. Even when displaying in calendar format, the filter function can be used in the same way as described above.

[0018] Next, Figure 6 shows an example of a screen configuration where one of the tasks of BBB Co., Ltd., listed in Figure 4, is selected, and the details of the task are displayed. For the task named "Preparation for Collection of All Documents Required for Consumption Tax Filing," the person in charge, start date, deadline, checklist, and comments section are displayed. However, the detailed information that can be displayed is not limited to this and can be set as appropriate, and may be made changeable by the user. The checklist may be a list of more specific actions to take when performing the task, or points to be careful about when performing the task. A check box is provided for each check item, and a check box can be checked when the task is completed. The comments section is a free-form field for the task. For example, a supervisor (e.g., the managing tax accountant) may write instructions for the person in charge regarding the task, or the person in charge may display notes they made when performing the task in the previous period, regarding handover points for the next period. In addition, when the task is completed, the status of the task can be changed from "Incomplete" to "Completed" by clicking the "Task Complete" button in the upper right corner of the screen.

[0019] Figure 7 shows an example of the task registration input screen when registering a new task. The items to be entered when registering a task may include information such as client, tax category, title, memo, period, and assigned person, but are not limited to these. These can be changed as appropriate and may be made customizable by the user.

[0020] The above shows a basic example of the screen configuration of the task management support system according to the present invention. However, this is merely one example of a screen configuration, and any configuration is acceptable as long as each element of the present invention described below is executable.

[0021] Figure 1 illustrates the task management support system of the present invention. Server 1 functions as a platform providing the task management support system and outputs task information to user terminals 2 connected via network 3. As will be described in detail later, Server 1 generates tasks and documents related to tasks while exchanging information with user terminals 2. At this time, Server 1 uses a large-scale language model to generate tasks and documents related to tasks.

[0022] Large language models (LLMs) are a type of generative AI (Artificial Intelligence) model specialized in natural language processing (NLP). They are sophisticated language models that achieve natural language generation by deep learning from vast amounts of text data. A language model, in general, is a mechanism that understands patterns in natural language used by humans and predicts the word that will follow a given word by analyzing the probability of word occurrence. Examples of large language models include ChatGPT (Chat Generative Pre-trained Transformer) (registered trademark), Gemini (registered trademark), PaLM2 (registered trademark), and LaMDA2 (registered trademark). The words and sentences used as instructions to input into these large language models are generally called prompts.

[0023] Server 1 can be any information processing device capable of realizing the functions described in each embodiment. Server 1 includes, for example, a server device, a computer (e.g., a desktop, laptop, tablet, etc.). Although Server 1 is shown alone in Figure 1, it is not limited to this. That is, each function described as being provided by Server 1 may be realized by multiple servers or by a single server. Also, a large-scale language model may be provided by another server. Furthermore, Server 1 may be a distributed server system that operates cooperatively by communicating over a network, for example, or a so-called cloud server. In other words, Server 1 is not limited to a physical server, but may also include a virtual server created by software.

[0024] User terminal 2 is a communication terminal used by a user of the task management support device. It has an application installed for using the task management support device and is capable of sending and receiving various information with server 1. However, installing the application on user terminal 2 is not mandatory. The user may access a web page for using the task management support service provided by server 1 via a web browser or the like from user terminal 2 and send and receive various information with server 1.

[0025] User terminal 2 can be any device that can implement the functions described below. For example, user terminal 2 may be a computer (e.g., a desktop PC, laptop computer, tablet, etc.), a smartphone, etc.

[0026] The task management support system may further include a database server (not shown) that stores various types of information (data) used by the task management support system. These types of information (data) may include, for example, training data, prompts, and user information input to a large-scale language model.

[0027] Network 3 may include wireless and wired networks, such as wireless LANs (WLANs), wide area networks (WANs), ISDNs (integrated service digital networks), wireless LANs, CDMA (code division multiple access), LTE (long term evolution), LTE-Advanced, 4G, 5G, and 6G and later mobile communication systems. Network 3 is not limited to these examples and may also include, for example, public switched telephone networks (PSTNs), Bluetooth (registered trademark), optical lines, satellite communication networks, etc. Network 3 may also be a combination of these.

[0028] Next, using Figure 8, the hardware configuration and functional configuration of Server 1 and User Terminal 2 according to one embodiment of the present invention will be described.

[0029] Server 1 and user terminal 2 each include at least a processor 10, memory 11, storage 12, a transceiver 13, an input / output unit 14, etc., and these are electrically connected to each other via a bus 15.

[0030] The processor 10 is a computing unit that controls the operation of the entire server 1, controls the transmission and reception of data between each element, and performs information processing necessary for the execution of applications. For example, the processor 10 is a CPU (Central Processing Unit) and executes programs stored in the storage 12 and loaded into the memory 11 to perform various information processing tasks.

[0031] Memory 11 includes main memory, which is composed of volatile storage devices such as DRAM (Dynamic Random Access Memory), and auxiliary memory, which is composed of non-volatile storage devices such as flash memory and HDD (Hard Disk Drive). Memory 11 is used as a work area for the processor 10, and also stores the BIOS (Basic Input / Output System) that is executed when the server 1 starts up, as well as various configuration information.

[0032] Storage 12 stores various programs, such as application programs. A database containing data used for each process may also be built on storage 12.

[0033] The transmitting / receiving unit 13 connects the server 1 to the network 3. The transmitting / receiving unit 13 may also be equipped with Bluetooth® and BLE (Bluetooth Low Energy) short-range communication interfaces.

[0034] The input / output section 14 includes information input devices such as keyboards and mice, and output devices such as displays, which are used as needed.

[0035] Bus 15 is connected in common to all of the above elements and transmits, for example, address signals, data signals, and various control signals.

[0036] Figure 9 shows an example of the software configuration of Server 1. Server 1 comprises a task management unit 21, an acquisition unit 22, a preprocessing unit 23, a task information generation unit 24, a document information generation unit 25, a display control unit 26, a task management information storage unit 31, a publicly known information storage unit 32, and a business operator data storage unit 33.

[0037] The task management unit 21, acquisition unit 22, preprocessing unit 23, task information generation unit 24, document information generation unit 25, and display control unit 26 are realized by the processor 10 of the server 1 reading programs stored in the storage 12 into the memory 11 and executing them. The task management information storage unit 31, publicly known information storage unit 32, and business operator data storage unit 33 are realized as part of the storage area provided by at least one of the memory 11 and the storage 12.

[0038] The task management information storage unit 31 holds task information for each business operator registered in this task management system. Figure 10 shows an example of the configuration of task information stored in the task management information storage unit 31. Task information may be managed by creating a table for each business operator, or tasks for each business operator may be managed by including information that identifies the business operator within the task information. Task information can hold predetermined items (task name, status, start date, deadline, memo, order, time required, etc.) for each tax category, but the types of items are not limited to these.

[0039] The task management unit 21 manages task information. Specifically, it performs processes such as task registration, status changes, and user notifications. Task registration is performed by recording the task information in the user's task management information storage unit 31 when the user inputs an instruction to approve a task generated by the task information generation unit 24, as described later. Status changes are updated by user actions, such as when the user executes a task and selects the "Task Complete" button, as illustrated in Figure 6, to change the status of the task to "Completed." In addition, if there are tasks whose start date or deadline has arrived, the user can be notified accordingly.

[0040] The database unit may have a publicly known information storage unit 32 that holds various publicly available information related to tax and accounting, and a business data storage unit 33 that holds user-specific business information. The publicly known information storage unit 32 typically includes information on laws and regulations such as laws, ministerial ordinances, and cabinet orders, as well as notices, standards, guidelines, and procedural outlines published by public institutions such as the national government, prefectures, and municipalities. In addition, it may also include precedents, news, and explanatory articles related to tax and accounting, and the database unit can always be updated with the latest information. The business information stored in the business data storage unit 33 may include business-specific information such as past tax documents such as various declarations, notifications, applications, and payment slips, accounting data (journal entry data and various ledger data), articles of incorporation, registration records, complete historical records, number of employees, hiring and termination information, payroll calculation data, industry information, minutes of shareholder meetings and board of directors meetings, and shareholder registers. The business data storage unit 33 may hold business-specific information only about the business that is the target of task generation, or it may also include business-specific information of other businesses that are not the target of task generation. Business-specific information of other businesses can be selected and included from businesses with similar capital, number of employees, or similar industry information. It may also include an accessible external database. This external database could be a database aggregating data on startup companies. If the user is a supporter such as a tax accounting firm, it may include business-specific information of other client businesses. Alternatively, it may select businesses with similar capital, number of employees, or similar industry information from among other client businesses and include them in the database. The various data included in the database unit may be mapped by theme as needed. For example, by setting multiple themes related to tax and accounting, such as data on withholding income tax, executive compensation, and social insurance, and mapping them, the accuracy of data generation by the large-scale language model can be improved. The publicly known information storage unit 32 and the business operator data storage unit 33 may be separate databases or an integrated database, and their format is not limited.

[0041] Furthermore, the database unit can include past task information of the client. That is, it holds past task information registered by the task management support device according to the present invention. The task management information storage unit 31 holds information about tasks to be executed, but for example, information on completed tasks may be transferred to the business data storage unit 33 as needed so that it becomes the input for the generated AI model when the task information generation unit 24 generates tasks. The timing for transferring task information to the business data storage unit 33 can be set as appropriate, and tasks for the completed fiscal year may be transferred when the fiscal year ends. Past task information included in the business data storage unit 33 can include information such as the actual start date, completion date, person in charge of the work, comments, and information on the revision history of these items. By using past task information as input, the task information generation unit 24 can, for example, set the start date earlier than usual if there is a comment such as "it would be better to start earlier" in the comment field related to past task information. Also, if there are multiple tasks for a single tax category, the order in which each task is started can be adjusted based on the actual start date and completion date related to past task information.

[0042] The acquisition unit 22 acquires task generation instructions related to tax and accounting from the user. The user inputs task generation instructions into the application of the task management support system according to the present invention via the input / output unit of the user terminal 2, and the acquisition unit 22 can acquire the task generation instructions. Task generation instructions are instruction information related to task generation, and may be in the form of a question about tasks related to a specific event, such as "An employee will be leaving at the end of next month, so please tell me what tasks are needed," or they may be in the form of a question about tax and accounting, such as "Can we pay bonuses to executives?" In other words, task generation instruction data does not necessarily have to be an instruction to directly generate a task, and may be a somewhat vague question about tax and accounting. Task generation instructions may be input as text data or as image data. For example, a task generation instruction may be input by uploading an image of a notice received from the tax office to the application.

[0043] The preprocessing unit 23 preprocesses the task generation instruction data from the user acquired by the acquisition unit 22 as needed, and generates preprocessed task generation instruction data. In the following description, task generation instruction data that was not preprocessed because it was not necessary is also referred to as preprocessed task generation instruction data. As described later, the task information generation unit 24 generates task information using a generation AI model based on the preprocessed task generation instruction data, but the task generation instruction data can be processed to make it easier for the generation AI model to function. Preprocessing can be performed as appropriate, such as adjusting the format of the task generation instruction data, such as the number of characters, or, if the task generation instruction data is image data, converting it to text data using image analysis technology such as OCR. The preprocessing unit 23 may also generate prompt data that can be input to the generation AI model based on the preprocessed task generation instruction data. Prompt data can be generated by preparing a prompt template that pre-defines the prompts necessary to generate a task, and applying the preprocessed task generation instruction data to the prompt template.

[0044] The task information generation unit 24 generates task information based on pre-processed task generation instruction data using a large-scale language model. In one embodiment of the present invention, the task information generation unit 24 can extract publicly available information and business information related to the pre-processed task generation instruction data from the database unit. The task information generation unit 24 can also extract past task information (including comments and revision history) related to the pre-processed task generation instruction data from the database unit.

[0045] The task information generation unit 24 can generate task information such as tax category, title, start date, deadline, and assigned worker using publicly available information, business information, past task information, and a generation AI model. The task information generation unit 24 can generate task information by providing a large-scale language model with prompts including publicly available information, business information, and pre-processed task generation instruction data. If multiple tasks are required for a single tax category, information regarding their order can also be read from the database unit and included in the prompts. For tasks where the deadline is determined by basic information such as each business's fiscal year-end, the deadline can be determined by referring to each business's basic information. For example, the start date can be determined by estimating the work time related to the task and working backward from the deadline.

[0046] The display control unit 26 displays the task information generated by the task information generation unit 24 on the user terminal. If the user gives an instruction to approve a task generated by the task information generation unit 24, the task management unit 21 registers the task information in the user's task management information storage unit 31.

[0047] Figure 11 shows an example of a task generation screen. In Figure 11, the user inputs the text "How do I qualify for simplified taxation?" as task generation instruction data. In response, the task information generation unit 24 generates the following text data as an answer: "To qualify for simplified taxation, you must follow these steps: 1. Check if you are eligible - Taxable sales for the tax period must be 50 million yen or less: For sole proprietors, the taxable sales for the year before last must be 50 million yen or less; for corporations, the taxable sales for the fiscal year before last must be 50 million yen or less. - Type of business: The simplified taxation system does not apply to all businesses. Please check with the tax office regarding the types of businesses that are eligible. 2. Submit a Simplified Taxation System Selection Notification Form - Submission destination: The tax office with jurisdiction over your tax payment location - Submission deadline: Up to one month before the start of the tax period 3. Prepare the necessary documents - Consumption tax Simplified Taxation System Selection Notification Form: Can be downloaded from the tax office's website - Documents related to your business: Tax returns, etc., that can confirm the details of your business" and displays this text data to the user. Furthermore, it displays a message including a task generation link that says, "Click the link to generate a task for simplified taxation."

[0048] When a user receives the message, "Click the link to generate a simplified tax task," if they wish to generate a task, they click the text portion "Generate a simplified tax task" (task generation link), which takes them to the task registration screen shown in Figure 12. On the task registration screen, the task information generation unit 24 displays a task registration format where the user can register each item necessary for task registration, such as "Tax Category," "Title," "Memo," "Deadline," and "Assigned Person," with appropriate content already filled in. The user can then check the content of each item, correct it if necessary, and click "Register Task" to add and register a task related to simplified taxation in this task management system. In this way, the task information generation unit 24 can answer user questions with information including explanations about tasks, and generate a task registration format with the necessary information for task registration entered. The task information generation unit 24 generates the answers and the necessary information for task registration using a generation AI model that is fed information obtained from the database mentioned above, so that it can always propose tax and accounting tasks based on the latest publicly available information. Furthermore, since the database unit includes past user task information and basic information of businesses, task information can be generated that is optimized for each user.

[0049] The task information generation unit 24 can generate a task registration format, for example, in the form of a parameterized URL. In the example above, the generated parameterized URL is something like "...client=Test Co., Ltd.&title=Application for Simplified Taxation&memo=Content: By the day before the first day of the tax period, submit the "Notification of Selection of Simplified Consumption Taxation System" to the tax office with jurisdiction over your tax domicile... (omitted)" and this URL is linked in the message "Click the link to generate a task for simplified taxation." The task information generation unit 24 may also generate information in a format other than a parameterized URL, as long as it can display the task registration format.

[0050] The task information generation unit 24 can also generate task information by combining a generation AI model and a rule-based approach. For example, a task related to corporate tax filing is a task common to all corporations, and its deadline is fixed at two months after the closing date. Therefore, at least the information regarding the deadline can be generated using a rule-based approach based on the basic information of the business operator. On the other hand, for items that may vary depending on the business operator or user (e.g., person in charge, memos, start date, order, etc.), it is more appropriate to generate them using a generation AI model that includes past user task information as prompts, as this allows for the generation of tasks that better reflect the actual circumstances of each business operator. The task information generation unit 24 can be pre-configured to determine the content of standard task items using a rule-based approach, and to determine the content of others using a generation AI model.

[0051] The task information generation unit 24 can regenerate task information if the generated task information does not match the user's task generation instruction data. For example, it can determine the matching rate between the generated task information and the keywords included in the user's task generation instruction data, and if the matching rate is low, it can determine that the quality of the generated task information is poor and regenerate the task information. If necessary, it may also prompt the user to re-enter the task generation instruction data by displaying a message such as, "Please enter a more specific question," or "Is this question about XX?"

[0052] The document information generation unit 25 can generate tax and accounting documents using an AI generation model when necessary. In the example in Figure 11, since it is necessary to submit a "Notification of Selection of Simplified Consumption Tax System," the document information generation unit 25 creates the document. Documents may include, but are not limited to, notifications, declarations, applications, payment slips and other documents to be submitted to tax offices, local governments, social insurance offices, etc., minutes of general shareholders' meetings, minutes of board of directors' meetings, and various internal company documents such as shareholder registers. The document information generation unit 25 may also generate documents based on instructions from the user regarding document creation. In the example in Figure 11, if the user additionally inputs instructions to create a document, such as "Create a Notification of Selection of Simplified Consumption Tax System," the document can be generated. Alternatively, text such as "Click the link to create a Notification of Selection of Simplified Consumption Tax System" may be displayed, and the document may be generated when the link is clicked. Furthermore, if the task information includes document generation, the document may be generated automatically, and the generated document may be displayed along with the "answer" as shown in Figure 11.

[0053] The document information generation unit 25 can generate a document by extracting necessary items to be included in the document and the instructions for describing those items from the publicly known information storage unit 32, and further extracting business information to be described in those items from the business data storage unit 33. The business data storage unit 33 contains business information such as past declarations, tax returns, applications, payment slips and other submitted documents and their attachments, minutes of general shareholders' meetings and board of directors' meetings, and various internal documents such as shareholder registers. The document information generation unit 25 extracts this business information from the business data storage unit 33, extracts publicly available information including the description instructions from the publicly known information storage unit 32, and provides the extracted publicly available information and business information to the generation AI model as prompts. This allows the AI ​​model to infer where to pull numbers and information from the business data for the necessary items to be included in the document, and to create a document with the information entered into the necessary items in a predetermined format defined for each document. The user can review the generated document, and if necessary, the system accepts corrections to the items. Once the user approves, the document file can be output in PDF format, Word format, etc.

[0054] Figure 13 shows the basic processing flow for task generation according to the present invention. First, the acquisition unit 22 acquires task generation instruction data from the user (S101). The task generation instruction information may be text data or image data, and the format is not limited. The task generation instruction information may also be instruction sentences, questions, or interrogative sentences, and the user can input them freely. The preprocessing unit 23 preprocesses the acquired task generation instruction information as needed (S102). This step S102 is optional. The length of characters in the task generation instruction information can be modified so that it becomes a string that is easy for the generation AI model to process, or image data can be converted to text data by image analysis (OCR, etc.).

[0055] The task information generation unit 24 generates task information using a generation AI model (S103). The task information generation unit 24 reads public information, business information, and task information from the public information storage unit 32 and the business data storage unit 33, and provides the read information and pre-processed task generation instruction data to the generation AI model to generate a response to the user and task information based on the task generation instruction data. The task information can be presented to the user in a format in which the necessary information is entered into a task registration format, but the format is not limited to this. If the quality of the generated task information does not meet a certain standard (S104=NO), the task information generation unit 24 recreates the task information (S105). For example, S104 can be performed by checking for keyword matching between the task generation instruction data and the generated task information. If the task information is determined to be correct (S104=Yes), the display control unit 26 displays a task registration screen like the one in Figure 12 on the user terminal based on the task information (S106). The user can register task information by modifying the task information as needed and approving it (S107). When the task management unit 21 receives an instruction to register task information, it registers the task information in the user's task management information storage unit 31 and performs task management.

[0056] Next, the flow for generating a document will be explained. If document generation is necessary based on the task generation instruction information entered by the user, the document information generation unit 25 generates document information (S201). The display control unit 26 presents the generated document to the user (S202), and the user makes any necessary corrections to the document information and approves it (S203), thereby outputting the document (S204). Similar to S104, a step may be provided to determine whether the generated document information is correct or not, and the document may be recreated if the predetermined conditions are not met.

[0057] The above shows an example of a processing flow, but the order and other elements can be changed as appropriate to the extent that the objectives of the present invention can be achieved.

[0058] According to the present invention, tasks and documents can be automatically generated by a generation AI model, allowing users to appropriately manage tax and accounting tasks even without specialized knowledge, and significantly reducing working time. In this invention, the database is constantly updated, making it possible to respond in real time to frequent legal revisions. Furthermore, by including not only publicly available information but also data such as past tax documents (including various declarations and notifications) of the user (or the client business if the user is a supporter such as a tax accountant), accounting data (journal entry data and various ledger data), articles of incorporation, registration records, minutes of general meetings of shareholders and board of directors meetings, etc., as well as past task information, in the prompts, it is possible to accurately generate tasks and documents tailored to the user's circumstances. In addition, although the above explanation was given using the example of a supporter, the user may be the business itself, and a mechanism may be provided that allows supporters and businesses to share task information, and both parties may register and update task information.

[0059] The embodiments described above are merely illustrative to facilitate understanding of the present invention and are not intended to limit its interpretation. The present invention can be modified and improved without departing from its spirit, and it goes without saying that the present invention includes equivalents thereof.

[0060] For example, in this embodiment, information read from the database unit is included in the prompt and provided to the large-scale language model, but the generating AI model may be fine-tuned. In this case, the generating AI model that generates task information can be fine-tuned using the latest publicly available information each time the latest publicly available information is acquired, or the latest publicly available information is stored and fine-tuned at regular intervals. The generating AI model can also be fine-tuned using the latest business information each time the latest business information is acquired, or the latest business information is stored and fine-tuned at regular intervals. Furthermore, the generating AI model can be fine-tuned based on the task information (including revision history and comments) each time task information is completed, or the completed task information is stored and fine-tuned at regular intervals. The generating AI model used by the document information generation unit 25 can also be fine-tuned using various internal documents such as various notification forms, declaration forms, application forms, payment slips and other submitted documents and their attachments, minutes of general shareholders' meetings and board of directors' meetings, and shareholder registers.

[0061] Furthermore, learning through fine-tuning may be combined with learning by providing data extracted from the database as prompts (one-shot / future-shot learning). For example, the generative AI model can be fine-tuned using information up to a certain date and time, that date and time can be stored, information after that date and time can be read from the database, and prompts containing the read information can be provided to the generative AI model, which has been fine-tuned with information before that date and time, to generate task information. [Explanation of Symbols]

[0062] 1 server 2 User terminals 3 Network

Claims

1. A device for managing tasks related to the tax and accounting operations of a business operator, A task information generation unit receives instruction information regarding task generation and generates task information, A display control unit that presents the task information to the user, The system includes a task management unit that registers tasks based on the user's approval, The task management device is characterized in that the task information generation unit generates the task information using publicly available information, including at least laws and regulations and circulars relating to tax and accounting, the past task information of the business operator, including at least one of the user's comments or revision history, and a generation AI model.

2. The task management device according to claim 1, characterized in that the display control unit presents the task information to the user with at least a portion of the necessary items pre-entered into the task information registration format.

3. The task management device according to claim 1, characterized in that the task information generation unit extracts the public information and past task information relating to the instruction information from a database containing the public information and past task information, and generates the task information by providing a generation AI model with a prompt including the extracted public information and past task information and the instruction information.

4. The task management device according to claim 1, characterized in that the generating AI model periodically or irregularly learns the publicly available information and the past task information, and the task information generation unit generates the task information by providing the instruction information to the generating AI model.

5. The task management device according to claim 1, characterized in that the database includes the unique information of the business operator, and the task information generation unit extracts the public information relating to the instruction information, the task information, and the unique information and provides them to the generated AI model.

6. The task management device according to claim 3, wherein the database includes registration information relating to the business operator, and the task information generation unit extracts the public information relating to the instruction information, the task information, and the registration information and provides them to the generated AI model.

7. A document information generation unit that generates document information, The business information relating to the aforementioned business operator, further comprising, The task management device according to claim 1, characterized in that the document information generation unit generates the document information by providing the publicly available information and the business operator information to a generating AI model.

8. A control method for a task management device for managing tasks related to the tax and accounting operations of a business operator, A task information generation step that receives instruction information regarding task generation and generates task information, A display control step that presents the task information to the user, A task management step is performed to register a task based on the user's approval, A method for controlling a task management device, characterized in that the task information generation step generates the task information using publicly available information including at least laws and regulations and circulars relating to tax and accounting, past task information of the business operator including at least one of the user's comments or revision history, and a generation AI model.

9. A control program for a task management device for managing tasks related to the tax and accounting operations of a business operator, which is installed on a computer. A task information generation function that receives instruction information regarding task creation and generates task information, A display control function that presents the aforementioned task information to the user, A task management function is implemented that registers tasks based on the approval of the user. The task information generation function is a control program for a task management device, characterized in that it generates task information using publicly available information, including at least laws and regulations and circulars relating to tax and accounting, past task information of the business operator, including at least one of user comments or revision history, and a generation AI model.

Images