Computer-assisted accounting document creation system using conversational AI

Abstract

By providing appropriate prompts to the conversational generation AI, it becomes possible to easily and quickly create analyzed and organized digital rules suitable for use in multitasking management systems and the like. [Solution] When creating accounting documents, the interactive generation AI 30 is given prompts P, including an overview and explanation of the analysis and organization method 1000, an explanation of the division categories 1100, the name and explanation of the work to be analyzed and organized this time 1200, special notes 1400, and other requests 1500, and is prompted to respond with the analyzed and organized digital rules.

Description

Technical Field

[0001] The present invention relates to Computer the creation support of accounting documents Device using an interactive generative AI, and particularly, it is suitable for use in the analysis and organization in a multitask management system Mu and relates to the creation support of accounting documents using an interactive generative AI that can simply and quickly create analyzed and organized digital rules. Computer the creation support of accounting documents Device related thereto.

Background Art

[0002] The applicant has proposed a multitask management system in Patent Document 1 that can classify (analyze and organize) all work into project tasks, ToDo, etc., making it easy to learn the latest work, improving the quality of work, and preventing delays and omissions.

[0003] To execute a multitask management system, among various tasks, analysis and organization for optimal work progress (including reconstruction of work progress) are important.

[0004] The analyzed and organized result is called a digital rule (also referred to as a D rule), but conventionally, it has not been possible to simply create a digital rule.

[0005] Although Patent Documents 2 and 3 have proposed systems for performing information processing or generating questions using generative AI, it has not been considered for use in creating digital rules.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Patent Document 2

Patent Document 3

[0007] This invention was made to solve the aforementioned conventional problems. ,Ma Multitask management system Mu It is suitable for use in analysis and organization, and allows for the simple and rapid creation of analyzed and organized digital rules. This will optimize business processes and workflows. This is the challenge. [Means for solving the problem]

[0008] The present invention Computers using conversational generative AI Preparation of accounting documents A support device , The system is designed to output the most appropriate response to the instruction entered as a prompt. Conversational Generative AI This multitasking management system divides all work under analysis into three categories: projects that show an overview of the entire job, tasks that are subcategories, and ToDos that are the actual individual actions, and organizes the importance and time required for each task to create a recipe for the work, and the aforementioned multitasking management system is a fixed text Overview and description of features, The fixed phrases are the aforementioned project, task, and to-do. Please explain the division categories and organize the information for this analysis. Includes pre- and post-work and checking procedures. Job title and description, special notes, This is a fixed statement, including the importance of the task, the time required, and the necessary skills. prompt Means for creating and , A means for inputting the created prompt to the conversational generation AI, and by the conversational generation AI Analyzed and organized Answer Digital Rules A means for outputting as, Features of conversational generative AI Computer Support for creating accounting documents Device This solves the aforementioned problem. [Effects of the Invention]

[0012] According to the present invention, by generating AI For multitasking management systems This makes it possible to easily create digital rules. Consequently, routine tasks can be analyzed and organized more efficiently, improving accuracy and speed. Furthermore, progress becomes more visible, and contact with supervisors and managers is drastically reduced, thus reducing stress for supervisors, managers, and workers. [Brief explanation of the drawing]

[0013] [Figure 1] Block diagram showing the functional configuration of an information processing system for carrying out the present invention. [Figure 2] Block diagram showing the functional configuration of the terminal device. [Figure 3] Block diagram showing the functional configuration of the server [Figure 4] Block diagram showing the basic hardware configuration of a computer [Figure 5] Diagram showing an example of the configuration of a prompt [Figure 6] Diagram showing a detailed explanation as well [Figure 7] Diagram showing an example of an answer from a conversational generation AI [Figure 8] Diagram showing a specific answer example of a project as well [Figure 9] Diagram showing a specific answer example of a task as well [Figure 10] Diagram showing a specific answer example of a ToDo as well [Figure 11] Diagram showing a specific answer example of the required time as well [Figure 12] Diagram showing a specific answer example of the required skills as well [Figure 13] Diagram showing a specific example of a checklist created by a generation AI as well

Mode for Carrying Out the Invention

[0014] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Note that the present invention is not limited to the content described in the following embodiments. Also, the constituent elements in the following embodiments include those that can be easily assumed by those skilled in the art, those that are substantially the same, and those within the so-called equivalent range. Furthermore, the constituent elements disclosed in the following embodiments may be combined as appropriate or selected and used as appropriate.

[0015] FIG. 1 is a block diagram illustrating the functional configuration of an information processing system used in an embodiment of the present invention.

[0016] As shown in Figure 1, the information processing system 1 includes a terminal device 10, a server 20, an interactive automatic generation AI (simply referred to as the generation AI) 30, and a network 40. The number of terminal devices 10 and servers 20 included in system 1 is not limited to one; there may be two or more.

[0017] The terminal device 10 shown in Figure 1 may be implemented by, for example, a stationary personal computer PC, a laptop PC, a smartphone compatible with a mobile communication system, a tablet, or other mobile terminal.

[0018] The terminal device 10 includes a communication interface IF 12, an input device 13, an output device 14, memory 15, storage 16, and a processor 19. The input device 13 is a device for receiving input operations from the user (e.g., a touch panel, touchpad, keyboard, mouse, etc.). The output device 14 is a device for presenting information to the user (e.g., a display, speaker, etc.).

[0019] The server 20 is implemented, for example, by an information processing device connected to the network 40. As shown in Figure 1, the server 20 includes a communication IF 22, an I / O IF 23, memory 25, storage 26, and a processor 29. The I / O IF 23 functions as an interface for an input device to receive input operations from the user and an output device to present information to the user.

[0020] The Generative AI 30 is an artificial intelligence model executed by one or more information processing devices connected to the network 40. The Generative AI 30 generates output based on user input (prompt text, images, etc.) using a pre-trained model. An example of the Generative AI 30 is ChatGPT. The Generative AI 30 may also be a model capable of processing multiple types of data, such as text, images, audio, and video, all at once. In this disclosure, a large-scale language model that primarily outputs text information as output information is described as a type of Generative AI 30. The Generative AI 30 may also be incorporated into the server 20.

[0021] Each information processing device consists of a computer equipped with an arithmetic unit and a memory device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by said hardware configuration will be described later. For each of the terminal device 10, server 20, and generation AI 30, explanations that overlap with the basic hardware configuration and basic functional configuration of the computer described later will be omitted.

[0022] Figure 2 is a block diagram showing an example configuration of the terminal device 10 shown in Figure 1. As shown in Figure 2, the terminal device 10 comprises a communication unit 120, an input device 13, an output device 14, an audio processing unit 17, a microphone 171, a speaker 172, a storage unit 180, and a control unit 190. Each block included in the terminal device 10 is electrically connected, for example, by a bus.

[0023] The communication unit 120 performs processing such as modulation and demodulation processing for the terminal device 10 to communicate with other devices. The communication unit 120 performs transmission processing on the signal generated by the control unit 190 and transmits it to an external source (for example, the server 20). The communication unit 120 performs reception processing on the signal received from an external source and outputs it to the control unit 190.

[0024] The input device 13 is a device for a user operating the terminal device 10 to input instructions or information. The input device 13 can be implemented by a reader, mouse 131, keyboard 132, etc. The input device 13 may also be implemented by a contact sensing device that inputs instructions by touching an operating surface. The input device 13 converts the instructions input by the user into electrical signals and outputs the electrical signals to the control unit 190. The input device 13 may also include, for example, a receiving port that accepts electrical signals input from an external input device.

[0025] The output device 14 is a device for presenting information to the user operating the terminal device 10. The output device 14 is implemented, for example, by a display 141. The display 141 displays data according to the control of the control unit 190. The display 141 is implemented, for example, by a liquid crystal display (LCD) or an organic electroluminescent display (EL display).

[0026] The audio processing unit 17 performs, for example, digital-to-analog conversion processing of the audio signal. The audio processing unit 17 converts the signal received from the microphone 171 into a digital signal and provides the converted signal to the control unit 190. The audio processing unit 17 also provides the audio signal to the speaker 172. The audio processing unit 17 is implemented, for example, by an audio processing processor. The microphone 171 receives an audio input and provides the audio signal corresponding to that audio input to the audio processing unit 17. The speaker 172 converts the audio signal received from the audio processing unit 17 into audio and outputs the audio to the outside of the terminal device 10.

[0027] The storage unit 180 is implemented, for example, by the memory 15 and storage 16 shown in Figure 1, and stores data and programs used by the terminal device 10. The storage unit 180 stores, for example, user information 181.

[0028] User information 181 stores information about the user performing the operation. User information includes, for example, user ID, name, age, address, date of birth, and date of registration for the service.

[0029] The control unit 190 is realized when the processor 19 reads a program stored in the memory unit 180 and executes instructions contained in the program. The control unit 190 controls the operation of the terminal device 10. By operating according to the program, the control unit 190 performs the functions of an operation reception unit 191, a transmission / reception unit 192, and a presentation control unit 193.

[0030] The operation reception unit 191 performs processing to receive instructions or information input from the input device 13.

[0031] Furthermore, the operation reception unit 191 receives voice information input from the microphone 171. Specifically, for example, the operation reception unit 191 receives voice data input from the microphone 171 and converted into digital data by the voice processing unit 17.

[0032] The transmitting / receiving unit 192 performs processing to enable the terminal device 10 to send and receive data with an external device such as the server 20 in accordance with a communication protocol. Specifically, for example, the transmitting / receiving unit 192 sends instructions input by the user to the server 20. The transmitting / receiving unit 192 receives information provided by the server 20.

[0033] The presentation control unit 193 controls the output device 14 and other devices in order to present information such as information provided by the server 20 to the user.

[0034] Figure 3 shows an example of the functional configuration of server 20. As shown in Figure 3, server 20 functions as a communication unit 201, a storage unit 202, and a control unit 203.

[0035] The communications unit 201 performs processing to enable the server 20 to communicate with external devices.

[0036] The storage unit 202 includes, for example, a user table 2021, an accounting table 2022, an image table 2023, a document type table 2024, an output format table 2025, a document table 2026, a log management table 2027, and so on.

[0037] User Table 2021 is a table that stores information about users registered with the service according to this embodiment. In this embodiment, a user is, for example, a person who performs the task of creating documents related to the draft documents generated in this embodiment.

[0038] The accounting table 2022 is a table that stores information related to accounting.

[0039] Image Table 2023 is a table that stores information about images related to accounting.

[0040] The Document Type Table 2024 is a table that manages the types of documents that are created.

[0041] The output format table 2025 is a table that stores information about the format or output examples of the text to be included in the document being created.

[0042] Document table 2026 is a table that stores information about documents included in records of accounting activities. Specifically, document table 2026 stores information used to generate draft documents for accounting activities, information about those draft documents, and information about the documents created based on those draft documents.

[0043] Log management table 2027 is a table that stores log information, which is information that associates the status of accounting documents with the time (or date without time) when that status was created or recorded.

[0044] The control unit 203 is realized when the processor 29 reads a program stored in the memory unit 202 and executes instructions contained in the program. By operating according to the program, the control unit 203 performs functions such as a receive control module 2031, a transmit control module 2032, a prompt generation module 2033, an evaluation module 2034, a log management module 2035, a presentation module 2036, etc.

[0045] The receive control module 2031 controls the process by which the server 20 receives signals from external devices according to a communication protocol. Specifically, for example, the receive control module 2031 receives signals transmitted from the terminal device 10 and the large-scale language model.

[0046] The transmission control module 2032 controls the process by which the server 20 transmits signals to external devices according to a communication protocol. For example, the transmission control module 2032 transmits information related to various user interface UIs (described later) to the terminal device 10, which will be displayed on the terminal device 10's display 141. For example, the transmission control module 2032 transmits a request including a prompt to the large-scale language model.

[0047] The prompt generation module 2033 generates prompts for input into large-scale language models. Prompts are "instructions" or "questions" that tell the AI ​​to do something. The quality of the AI's output (answers, generated text, etc.) largely depends on the accuracy of the prompts, so it is important to give clear and specific instructions. Better results can be obtained by clearly communicating what you want from the AI, including the expected format and background information.

[0048] A prompt is input data used to instruct a large-scale language model to generate output data or to guide the content of the output data. Prompts can contain information in various formats, including text data and image data (including still images and videos). Image data included in a prompt may be in any image format such as JPEG, or it may be encoded in text format, etc. A prompt may also include a link, such as a URL or file path, to the location where the image data is stored, thereby allowing the large-scale language model to load the image data.

[0049] Figure 4 is a block diagram showing the basic hardware configuration of computer 50. Computer 50 includes at least a processor 51, main memory 52, auxiliary storage 53, and a communication interface 54. These are electrically connected to each other by a bus.

[0050] The processor 51 is hardware for executing the instruction set described in the program. The processor 51 consists of an arithmetic unit, registers, peripheral circuits, etc.

[0051] The main memory 52 is for temporarily storing programs and data processed by programs, etc. For example, it is a volatile memory such as dynamic random access memory (DRAM).

[0052] The auxiliary storage device 53 is a storage device for storing data and programs. Examples include flash memory, hard disk drive (HDD), magneto-optical disk, CD-ROM, DVD-ROM, semiconductor memory, etc.

[0053] The communication IF54 is an interface for inputting and outputting signals for communication with other computers over a network using wired or wireless communication standards.

[0054] The network 40 shown in Figure 1 consists of various mobile communication systems, such as the Internet, LANs, and wireless base stations.

[0055] Furthermore, by distributing all or part of each hardware configuration across multiple computers 50 and connecting them to each other via a network 40, the computers 50 can be virtually realized. Thus, the concept of computer 50 includes not only computers 50 housed in a single enclosure or case, but also virtualized computer systems.

[0056] Figure 5 shows the basic configuration of prompt P generated by prompt generation module 2033.

[0057] This prompt P includes fixed text describing the overview and functions of the multitasking management system (1000), fixed text describing the project, task, and to-do categories (1100), the name and description of the task to be analyzed and organized (1200), fixed text describing the importance, time, and required skills of the task (1300), special notes (1400), and other requests (1500).

[0058] Specifically, as shown in Figure 6, the generating AI30 is given the following explanation as an "introductory explanation": "Our patented multitasking management system divides all work into three categories and organizes the importance and time required for each task, thereby creating a work recipe. By inputting this information into the job system, new knowledge and know-how can be learned at any time, allowing tasks to be performed even with insufficient skills, eliminating delays and omissions, and reducing the burden on supervisors and managers by having the system manage the progress."

[0059] Next, under the heading "The classifications of multitasking management systems are as follows," the following classifications are explained.

[0060] Project = Overview of the work, key points, knowledge and know-how, work recipe Tasks = Categorizing ongoing tasks, creating ToDo items for each task (pre- and post-task tasks are each considered separate tasks). ToDo = Each actual action, unit of work, order of procedure, and completion check entry.

[0061] Then, as the task to be analyzed and organized, the following description is given: "Please divide the year-end tax adjustment procedures, which involve adjusting the wages received and taxes paid by workers during the year, into three parts: project, task, and to-do. In the to-do section, please organize the tasks in the order they will be performed. This includes pre- and post-task work, checking tasks, etc."

[0062] Furthermore, the "things you want to learn" should indicate "the importance of the task, the time required, and the necessary skills."

[0063] Furthermore, under "Special Notes," it should be indicated that "these digital rules are an example of general year-end tax adjustments."

[0064] Figure 7 shows an example of the interactive generation AI30's response to this.

[0065] "Understood. I will explain the administrative procedures for the year-end tax adjustment example, organized according to the patented 'three-category method,' and will also include an estimate of the time required and the necessary skills."

[0066] 1. Figure 8 shows the specific details of the project (overview of the entire job, knowledge, and recipe). The questions "What is year-end tax adjustment?", "Key points," and "Outline of the recipe" are answered.

[0067] Furthermore, Figure 9 shows specific examples of 2. Tasks (Category Classification). The responses include "1. Pre-preparation tasks," "2. Calculation / Input tasks," "3. Checking tasks," and "4. Post-processing tasks."

[0068] Furthermore, Figure 10 shows specific examples of 3. ToDo (specific actions, checklist items).

[0069] Figure 11 also shows an example of the time required.

[0070] Figure 12 shows examples of answers regarding necessary skills. Both "essential skills" and "desirable skills" are listed.

[0071] Organizing things in this way allows for hierarchical management within the system: "Project; Year-end adjustment" → "Task; Pre-preparation, calculation, checking, and post-processing" → "To-Do; Specific input and checking actions," making it easier to prevent omissions and track progress.

[0072] Figure 13 shows an example of the above content being converted into a checklist format (including required time and necessary skills) and output by the generating AI.

[0073] If you import this table directly into a spreadsheet program like Excel, it becomes much easier to manage progress and assign tasks.

[0074] Furthermore, although the above-described embodiment applies the present invention to the preparation of year-end tax adjustment documents, the scope of application of the present invention is not limited to this, and it can be similarly applied to assisting in the preparation of other accounting documents and general bookkeeping documents other than year-end tax adjustment documents. ,new It can be applied not only to new business processes but also to the restructuring of existing ones. [Explanation of Symbols]

[0075] 1... System 10…Terminal device 12…Communication IF 120... Communications Department 13…Input device 14…Output device 141…Display 15…Memory 16…Storage 17…Sound Processing Unit 180...Storage section 19… Processor 190... Control Unit 20... Server 2033... Prompt generation module 30…(Interactive Automatic) Generating AI 40…Network P, 1000, 1100, 1200, 1300, 1400, 1500… prompt

Claims

[Claim 1] A computer-based accounting document creation support device using interactive generation AI, An interactive generation AI designed to output the most appropriate response to the instruction text entered as a prompt, A multitasking management system that divides all work to be analyzed into three categories: a project that shows the overall overview of the work, tasks that are subcategories, and To-Dos that are the actual individual actions, and then organizes the importance and time required for each task to create a work recipe. A fixed text describing the overview and functions of the multitasking management system, a fixed text describing the division categories of project, task, and to-do, the name and description of the work including pre- and post-work and checking tasks to be analyzed and organized, special notes, and a means for creating prompts including the importance of the work, the time required, and the necessary skills, A means for inputting the created prompt to the conversational generation AI, A means for outputting the answers analyzed and organized by the aforementioned interactive generation AI as digital rules, A computer-based accounting document creation support device using interactive generation AI, characterized by having the following features.

Images