Document preparation device, document preparation method, and document preparation program
The document creation device addresses the inefficiencies of existing technologies by using a template-based approach with AI models to automate document generation, reducing user burden and improving flexibility and accuracy.
Patent Information
- Application Number
- JP2025002390
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-01-09
- Filing Date
- 2025-01-07
- Publication Date
- 2025-07-22
AI Technical Summary
Existing document creation technologies struggle to efficiently generate documents in various formats and impose a significant burden on users due to the complexity of generating prompts for large language models, lacking flexibility and labor-saving capabilities.
A document creation device that includes a template setting unit, template storage unit, template designation unit, necessary information setting unit, and a document creation unit that utilizes a learned AI model to create documents using predefined templates, necessary information, and reference information, with optional reshaping and verification units to enhance efficiency.
Enables efficient and flexible document creation by reducing the need for manual prompt generation, allowing users to create documents quickly and accurately using predefined templates and information, with verification to ensure quality.
Smart Images

Figure 2025107985000001_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to a document creation apparatus for improving the efficiency and labor saving of document creation.
Background Art
[0002] Regardless of the industry, a large number of documents are created every day for business operations, and the improvement of the efficiency and labor saving of document creation is always required. Therefore, technologies for automatically creating predetermined documents have been developed. For example, Patent Document 1 discloses a technology for automatically creating an invoice based on order data and progress status.
[0003] In recent years, by applying a large language model (LLM) such as ChatGPT (Non-Patent Document 1) to a plug-in for document creation software such as Word, document creation using automatic generation of sentences by the LLM has been attempted.
Prior Art Documents
Patent Documents
[0004]
Patent Document 1
Non-Patent Documents
[0005]
Non-Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0006] The technology according to Patent Document 1 only calculates a fee based on order data and progress status, and drops the calculation result into a predefined format to create an invoice. Therefore, this technology cannot flexibly respond to the creation of documents in various formats.
[0007] In addition, in the technology described in Non-Patent Document 1, in order to create documents according to individual formats and described contents, it is not easy to generate a prompt to be input to the LLM. Since there are various premises and matters to be considered in document creation like the above-mentioned proposed documents, it is not easy to generate a prompt for instructing the LLM to create a document in which these are sufficiently reflected. Also, when creating a large number of various documents, such not-easy prompt generation has to be performed each time, and the burden imposed on the user becomes large. Thus, the prior art cannot meet the demands for labor saving and efficiency improvement in automatic document creation.
Means for Solving the Problems
[0008] Therefore, in order to solve the above problems, the present invention provides the following document creation device and the like. That is, a template setting unit that accepts setting of a template for document creation, a template storage unit that stores the template that has accepted the setting, a template designation unit that accepts designation of a template to be used for document creation from the stored templates, a necessary information setting unit that accepts setting of necessary information including information necessary for creating a document using the designated template, and a document creation unit that inputs the designated template and the accepted necessary information into a learned AI model to create the document. The template includes a document creation device including a layout, description items, and a description method indicated by sentences.
[0009] In addition to the above features, the learned AI model is a large language model, providing a document creation device.
[0010] In addition to the above features, it further has a reference information setting unit that accepts setting of reference information that is information to be referred to in the creation of the document. The document creation unit further inputs the accepted reference information into the learned AI model to create the document, providing a document creation device.
[0011] In addition to the above features, there is provided a document creation device further including a reshaping unit that reshapes the created document.
[0012] In addition to the above features, there is provided a document creation device further including a verification unit that verifies the created document.
[0013] Also, there is provided a document creation method executed by a document creation device, including a template setting step of receiving a setting of a template for document creation, a template storage step of storing the received template, a template designation step of receiving a designation of a template to be used for document creation from the stored templates, a necessary information setting step of receiving a setting of necessary information including information required to create a document using the received template, and a document creation step of inputting the received template and the received necessary information into a learned AI model to create the document. The template includes a layout, described items, and a description guideline indicated by a sentence.
[0014] Also, there is provided a document creation program for causing a document creation device to execute a template setting step of receiving a setting of a template for document creation, a template storage step of storing the received template, a template designation step of receiving a designation of a template to be used for document creation from the stored templates, a necessary information setting step of receiving a setting of necessary information including information required to create a document using the received template, and a document creation step of inputting the received template and the received necessary information into a learned AI model to create the document. The template includes a layout, described items, and a description guideline indicated by a sentence.
Advantages of the Invention
[0015] According to the present invention, a desired document can be efficiently created by using a template.
Brief Description of Drawings
[0016]
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Modes for Carrying Out the Invention
[0017] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. It should be noted that the present invention should not be limited to these embodiments, and can be implemented in various modes without departing from the gist thereof.
[0018] <Example 1> <Overview> For example, when creating a document that should be described according to a predetermined description format, such as a building construction confirmation application form submitted when building a building, by setting and storing templates according to various documents, it is possible to contribute to efficient document creation.
[0019] The following describes the functions and processing flow of the document creation device, as well as the details of the hardware. Note that the functional blocks of this device described below can be realized as a combination of hardware and software. Specifically, if a computer is used, it includes hardware components such as a CPU (Central Processing Unit), main memory, bus, or secondary storage device (hard disk drive, non-volatile memory, storage media such as CDs and DVDs, and their reading drives), input devices used for information input, printing equipment, display devices, and other external peripheral devices, as well as interfaces for those external peripheral devices, communication interfaces, driver programs for controlling those hardware, and other application programs, and application programs for the user interface. Then, through the arithmetic processing of the CPU according to the program developed on the main memory, data input from input devices and other interfaces and held in the memory or hard disk is processed and stored, or instructions for controlling the above-mentioned hardware and software are generated. Alternatively, the functional blocks of this device may be realized by dedicated hardware.
[0020] In addition, this invention can be realized not only as a device but also as a method. Also, a part of such an invention can be configured as software. Furthermore, the program used to cause a computer to execute such software and the recording medium on which the program is fixed are naturally included in the technical scope of this invention (the same applies throughout this specification).
[0021] <Functional Configuration> FIG. 1 is a block diagram showing an example of the functional configuration of the document creation device of this embodiment. As shown in FIG. 1, the document creation device 100 includes a template setting unit 101, a template storage unit 102, a template designation unit 103, a necessary information setting unit 104, a reference information setting unit 105, a prompt generation unit 106, a document creation unit 107, a reforming unit 108, a verification unit 109, and a prompt storage unit 110.
[0022] The document creation device 100 is a device for creating documents. This device is embodied as a functional extension (plugin) in a document creation application such as Word, for example, but may also be realized in a web application or the like. Also, as an example of the document to be created, it is a document for which it is determined what should be described to a certain extent. For example, it is a building confirmation application form that is required to be submitted when constructing a building.
[0023] This device assumes that particularly favorable effects can be obtained when creating a large number of business documents created in companies, offices, etc. That is, since business documents are documents created according to a predetermined format or style, such as the above-mentioned building confirmation application form, the description items and the description guidelines can be generalized. By templatizing these description items and description guidelines, it is possible to save labor in describing the same stereotypical matters each time of creation.
[0024] <Template setting section> The template setting section 101 has a function of setting a template for document creation. The template is according to the type of document, etc., and is the layout of the document (what to place where and how), the description items arranged according to the layout, and the description guidelines thereof. The description items are determined according to the type and use of the document, etc. For example, in the case of the template of the building confirmation application form, it has description items such as the names of architects and construction contractors, the address of the building, the usage area, the site area, the building area, and the floor area.
[0025] The description guidelines are those that relatively specifically show the key points and methods in the description. For each description item included in the document, the key points and methods, etc. are often shown. For example, the description items and their description guidelines in the case of the building application form are set as follows respectively. "1. Building owner": "Describe the information of the building owner." "2. Agent": "The agent usually becomes the designer." "3. Designer": "Describe the representative designer of this object. In case of design by multiple design offices, etc., list the relevant designers in the column of other designers." For the sake of convenience in explanation, the description items and the description guidelines are presented side by side, but the description guidelines of a single document may also define the description items and the description guidelines for each description item.
[0026] In the template settings, the layout may be preset, or in the necessary information setting section described later, the layout may be set more specifically as necessary information. As an example of the latter, in the case of documents with different layouts for each local government, set the layout used by the local government, etc. in the case to be created as necessary information.
[0027] The setting of the template including the layout, description items, and description guidelines may be configured so that this device or the application related to this device performs it in advance, or it can also be configured so that the user can perform it himself / herself.
[0028] <Template storage section> The template storage section 102 has a function of storing the set templates. By attaching a unique ID and name to each of the set templates and storing them, the user can specify an arbitrary template in the template specifying section described later. Note that the above-mentioned template setting and template storage can also be configured so that various document templates are set and stored in advance when the user uses this document creation device.
[0029] <Template specifying section> The template specification section 103 has a function of specifying a template to be used for document creation from the stored templates. If the layout of the specified template is not set, the layout is set in the necessary information setting section as described above. If the layout of the specified template has been set, the layout, description items, and description details of the document to be created by specifying any template will all be specified. The specification of the template may be configured to be hierarchical. For example, for a building confirmation application form, by subdividing and presetting templates for each application object (such as buildings, elevators, building equipment other than elevators, etc.) and the local government to which it is submitted, it becomes easier for the user to specify the template to be used for the document to be created.
[0030] <Necessary information setting section> The necessary information setting section 104 has a function of setting necessary information including the information necessary for creating a document using the specified template. This necessary information is specific to the document to be created. For example, when creating a building confirmation application form, it is information such as the architectural drawings and wiring diagrams of the actual building that is the subject of the application. Also, if the layout of the document is not set, a predetermined layout according to the application destination, etc. is set as necessary information.
[0031] Figure 2 is a conceptual diagram showing an example of a document to be created and necessary information. As shown in the figure, for example, when creating the "Architectural Plan Outline" 201 in a building confirmation application form, items such as the "Surrounding Sketch" 202 and the "Layout Plan" 203 must be described. These descriptions are based on the "Map" 204 showing the location where the application object exists and the "Layout Plan" 205 of the object, and these "Map" and "Layout Plan" correspond to the necessary information.
[0032] The necessary information can be set by extracting specific descriptions as described above or by setting the location (address, path, etc.) of the corresponding information. Also, as long as the necessary information is included, any information can be set by the necessary information setting unit. For example, it is also possible to roughly set up a database, a disk drive, cloud storage, etc., and have the large language model refer to the necessary information from among them. More specifically, the necessary information setting unit designates a large database and makes a description such as "Retrieve all building information including layout diagrams from the database, calculate the average area, and write it here." By doing so, the large language model can extract the necessary information from the database and create a document.
[0033] Also, the setting of the necessary information is not limited to cases that require explicit or direct operations, and can be configured such that the necessary information is set by executing operations related to document creation. For example, when the user selects a predetermined document creation file, based on the location of the file (such as the directory position opened at the time of operation execution), the directory itself is set as the target of the necessary information. Then, all of the file data grouped or hierarchized by this directory can be set as the necessary information. By configuring it in this way, it is possible to save the trouble of setting the necessary information deliberately, and by starting document creation, the necessary information is set naturally (without requiring special operations), and a document creation device with better convenience can be provided.
[0034] <Reference information setting unit> The reference information setting unit 105 has a function of setting reference information, which is information referred to in the creation of the document.
[0035] Reference information is the content described in documents that are relevant or similar to the content of the document to be created. For example, in the creation of a building confirmation application, it is the content described in the building confirmation applications submitted when constructing similar buildings. By referring to past cases as reference information, it can be used as a reference for creating the current document. The reference information may be, for example, information such as data, files, and documents held by this device, information stored in an external database, or information existing on the WEB.
[0036] Also, the setting of reference information can be done not only by specifically designating documents etc. as described above, but also abstractly. For example, it may be set in the form of "Use the content described in the building confirmation applications submitted for buildings similar to this case as reference information." Furthermore, more detailed conditions may be added. For example, reference information can also be set to include conditions such as "building confirmation applications for elevators" or "cases where the application destination is in ○○ Prefecture △△ City".
[0037] Also, a manual for document creation etc. may be set as reference information. For example, when creating a "building confirmation application", set "how to write a building confirmation application" etc. as reference information.
[0038] Both the necessary information and the reference information described above are information used for document creation. Therefore, for the user, there is no need to recognize them as separate entities, and they may be configured so that both can be set integrally.
[0039] In addition, as a preferable mode of a database that accumulates various types of information and documents that can serve as reference information, it is preferable that it is not only a device that scans documents and converts them into electronic form, but also a device that individually structures, accumulates, and manages the contents of the description items included in the documents. For example, the contents for each description item of the document are input and held in a spreadsheet in the form of rows and columns. In order to structure the description contents in the document in this way, in addition to manually inputting from paper documents into spreadsheet software, etc., after scanning and converting into electronic image data or PDF and converting it into text by OCR (Optical Character Recognition), it is made into a database. Such a document DB may be provided in the present document creation device, or may be an external device capable of exchanging information with the present document creation device.
[0040] In addition, the database may be constructed by extracting and structuring the information of individual items described in documents in various formats using an LLM. For example, when extracting the "drawing number" described in a document, a sentence such as ""Please extract the value of the 'drawing number'. The 'drawing number' is the ID of the file and is composed only of alphanumeric characters and hyphens. Also, it conforms to the following regular expression [A-Z]-\d{5}." is input into the LLM as a prompt, and by having it process a large number of documents scanned and converted into electronic image data or PDF and converted into text by OCR, the information of the "drawing number" can be obtained as the answer, and a document DB can be constructed. Note that the specific means for extracting information, structuring it, and constructing a document DB is not particularly limited. It can be realized by appropriately using appropriate technologies.
[0041] Note that the construction of the database as described above is time-consuming, but regarding the above-described data extraction technology using an LLM for labor-saving and efficiency improvement, the inventor of the present application has invented it and has already filed a patent application (Application No.: PCT / JP2023 / 034488).
[0042] <Prompt generation unit> The prompt generation unit 106 has a function of generating a prompt for causing the learned AI model to create the document using the specified template and the set necessary information. The learned AI model is a machine learning model that has been pre-trained to handle general tasks. As a typical example, the large language model (LLM) is well-known, but it may also be different ones such as a small-scale language model or a multimodal language model that can handle images and other formats. Hereinafter, it will be described using a typical large language model.
[0043] Also, the prompt may be generated by further using the set reference information. For example, a sentence such as "Please create an 'Architectural Plan Outline Drawing' of the building confirmation application form for the water supply and drainage facilities of 〇〇. Search for information on the water supply and drainage facilities of cases similar to this case and refer to the information obtained as a result." is generated. The prompt may be generated by the user inputting such a coherent sentence, or it may be configured such that the user inputs the case name, the document to be created, the template to be used, the necessary information, and the reference information individually to generate the prompt.
[0044] Also, it may be configured to further add a prompt for instructing the LLM about more detailed conditions and settings for the document to be created. For example, a prompt regarding the maximum number of characters of the document to be created and conditions regarding the output mode (text only, adding a table to the text, including numerical data, etc.) is added. Also, it can be configured to add a prompt regarding whether to perform reshaping and verification processing on the created document, and how to perform them if reshaping and verification are to be performed. Reshaping and verification will be described later.
[0045] <Prompt storage unit> The prompt storage unit 110 has a function of storing the generated prompts. By storing the prompts, it is convenient for the user to reuse them by creating documents again or modifying them when creating documents for other cases. Also, it may be stored in association with the templates specified during storage, the necessary information and reference information set.
[0046] <Document creation unit> The document creation unit 107 has a function of inputting the generated prompts into the large language model to create the documents. The creation of documents using the LLM may be performed, for example, as a function extension in a document creation application such as word, or may be provided as a web application. Also, it is not necessarily only when creating the entire document, but may also be when creating one or more items included in the document. Also, it can be configured to create documents in a plurality of variations according to the instructions of one prompt, present those multiple documents, and accept the user's selection. Also, the created document can be configured to be editable by the user.
[0047] Also, it is preferable to configure it to show the created document and which part of the set reference information was referred to. This will show the process and basis for arriving at the creation result, which is useful when the user judges the right or wrong of the creation result.
[0048] <Reshaping unit> The reshaping unit 108 has a function of reshaping the created document. Reshaping means shaping the document created by the document creation unit according to a specified sample, format, etc. Reshaping may be performed using the LLM with the instruction included in the prompt, or may be performed by inputting a separate script for instructing reshaping.
[0049] <Verification unit> The verification unit 109 has a function of verifying the created document. Verification means checking whether the created document conforms to predetermined conditions and specifications. Further, the verification results confirmed as necessary are output, or the verification results are reflected in the recreation of the document. For example, verification is performed such as checking whether it is not similar to a specified negative sample, verifying whether a specific phrase (for example, the phrase "building restrictions within setback") is included in the created document, and confirming the validity of the created document compared with a specified sample.
[0050] If the verification result is not positive, for example, if it resembles a specified negative sample, does not contain a specific phrase, or lacks validity, it is also preferable to display such a result as a message. Further, by inputting an instruction to recreate to the LLM together with the message and causing the creation process to be performed, it becomes possible to create a more preferable document in which the verification results are reflected.
[0051] The verification by the verification unit may be performed after or before the reshaping by the above-described reshaping unit. Also, similar to the reshaping, the instruction may be included in the prompt and performed using the LLM, or it may be performed by inputting a script for instructing verification separately.
[0052] <Hardware Configuration> FIG. 3 is a conceptual diagram showing a configuration example of the hardware that realizes the document creation apparatus according to the first embodiment. As shown in the figure, the document creation apparatus 300 includes a CPU 301 that performs various arithmetic processes, a RAM 302 that is a volatile recording medium, a storage 303 such as a flash memory or an HDD that is a non-volatile storage medium, a communication interface 304, and an input / output interface 305. The RAM 302 reads out a program for causing the CPU 301 to perform various arithmetic processes and provides a work area for the program. In addition, a plurality of addresses are assigned to the RAM 302, and programs executed by the CPU 301 can exchange data with each other by specifying and accessing those addresses, making it possible to perform processing (the same applies throughout this specification).
[0053] Here, the functions of the template setting unit 101, the template specifying unit 103, the necessary information setting unit 104, the reference information setting unit 105, the prompt generation unit 106, the document creation unit 107, the reforming unit 108, and the verification unit 109 of the document creation apparatus 100 in FIG. 1 are mainly realized by the CPU 301 and the RAM 302 in FIG. 3. In addition, the functions of the template storage unit 102 and the prompt storage unit 110 are mainly realized by the storage 303 in FIG. 3. Further, when the document DB exists externally or when the document creation unit 105 uses an LLM existing externally, each function is realized by exchanging signals and information with each other via the communication interface 304 and the input / output interface 305.
[0054] <Flow of processing> FIG. 4 is a flowchart briefly showing an example of the processing flow of the document creation apparatus according to the first embodiment. First, description items and description guidelines are set as a template for document creation (S401: Template setting step). Then, the set template is stored (S402: Template setting step). Then, a template to be used for document creation is specified from the stored templates (S403: Template specification step). Then, necessary information including information necessary for creating a document is set using the specified template (S404: Necessary information setting step). Then, reference information which is information to be referred to for document creation is set (S405: Reference information setting step). Then, a prompt for causing the large language model to create the document is generated using the specified template, the set necessary information, and the set reference information (S406: Prompt generation step). Then, the generated prompt is input to the large language model to create a document (S407: Document creation step). Then, the created document is reformatted (S408: Reformating step). Then, the created document is verified (S409: Verification step). Note that the verification step may be performed before the reformating step. Also, although not shown, it may include a prompt storage step of storing the prompt generated in the prompt generation step. Also, it may not include the reference information setting step.
[0055] <Effect> According to the document creation apparatus of the present embodiment, a desired document can be efficiently created by using a template.
[0056] <Second Embodiment> <Overview> The document creation apparatus of the present embodiment is based on the document creation apparatus of the first embodiment. In the first embodiment, a document is created by inputting the generated prompt into a pre-trained AI model, whereas in the present embodiment, a document is created by inputting a template and necessary information into the pre-trained AI model. This eliminates the need to separately create a prompt for document creation.
[0057] <Functional Configuration> FIG. 5 is a block diagram showing an example of the functional configuration of the document creation apparatus according to the present embodiment. As shown in FIG. 5, the document creation apparatus 500 includes a template setting unit 501, a template storage unit 502, a template designation unit 503, a necessary information setting unit 504, a reference information setting unit 505, a document creation unit 506, a reforming unit 507, and a verification unit 508. Since each configuration other than the document creation unit 506 has the same function as the configuration with the same name in the first embodiment, the description thereof is omitted.
[0058] <Document Creation Unit> The document creation unit 506 has a function of inputting the template that has received the designation and the necessary information that has received the setting into the learned AI model, and creating the document.
[0059] As described for the template setting unit of the first embodiment, the template includes a layout, description items, and description guidelines indicated by sentences. The description items and their description guidelines in the case of the exemplified building application form are set as follows, respectively. "1. Building Owner": "Describe the information of the building owner." "2. Agent": "The agent usually becomes the designer." "3. Designer": "Describe the designer who represents this property. In the case of designing by multiple design offices, etc., list the relevant designers in the column for other designers." By each description guideline consisting of these sentences functioning as a prompt for the learned AI model, the learned AI model appropriately extracts information from the necessary information and embeds it in the template according to the instructions (description guidelines) in the template, thereby enabling the creation of a document.
[0060] Note that the description guidelines in the template may be preferably described in a manner distinguishable from other sentences (for example, in red text) at the description position along the format of the document. Also, the description guidelines can be configured to be set by the user after uploading a document creation file such as a word that constitutes the template.
[0061] In addition, in this embodiment, the document creation unit can further input the reference information that has received the setting into the learned AI model to create the document. For the document created by the document creation unit, the reshaping process and the verification process can be performed in the same manner as in the first embodiment.
[0062] <Hardware Configuration> The document creation apparatus of this embodiment can be realized by the hardware configuration shown in FIG. 3 according to the first embodiment. The document creation apparatus 500 of the second embodiment shown in FIG. 5 includes a template setting unit 501, a template designation unit 503, a necessary information setting unit 504, a reference information setting unit 505, and the functions of the document creation unit 506, the reshaping unit 507, and the verification unit 508 are mainly realized by the CPU 301 and the RAM 302 in FIG. 3. In addition, the function of the template storage unit 502 is mainly realized by the storage 303 in FIG. 3. When the template storage unit 502 also uses an external storage or the document creation unit 506 uses a learned AI model existing outside, each function is realized by mutually exchanging signals and information via the communication interface 304 and the input / output interface 305.
[0063] <Flow of Processing> FIG. 6 is a flowchart briefly showing an example of the processing flow of the document creation apparatus according to the first embodiment. First, reception of a template setting for document creation is performed (S601: Template setting step). This template includes a layout, description items, and a description guideline indicated by text. Then, the received template is stored (S602: Template storage step). And, from the stored templates, reception of designation of a template to be used for document creation is performed (S603: Template designation step). And, reception of setting of necessary information including information necessary for creating a document using the received template is performed (S604: Necessary information setting step). And, reception of setting of reference information which is information to be referred to for creation of the document is performed (S605: Reference information setting step). And, the received template, the received necessary information, and the reference information are input into a learned AI model to create the document (S606: Document creation step). And, the created document is reformatted (S607: Reformatting step). And, the created document is verified (S608: Verification step). Note that the verification step may be performed before the reformatting step. Also, the reformatting step, the verification step, and the reference information setting step may not be included, and in that case, in the document creation step, the received template and the received necessary information are input into a learned AI model to create the document.
[0064] <Effect> According to the document creation apparatus of the present embodiment, by inputting a template and necessary information into a learned AI model, it is possible to create an appropriate document according to the description guideline included in the template without creating a prompt for document creation.
Description of reference numerals
[0065] 100, 500: Document creation apparatus 101, 501: Template setting unit 102, 502: Template storage unit 103, 503: Template designation unit 104, 504: Necessary Information Setting Unit 105, 505: Reference Information Setting Unit 106: Prompt Generation Unit 107, 506: Document Creation Unit 108, 507: Reshaping Unit 109, 508: Verification Unit 110: Prompt Storage Unit 301: CPU 302: RAM 303: Storage 304: Communication Interface 305: Input / Output Interface
Claims
1. A template setting unit that accepts settings for templates for document creation, A template storage unit that stores the templates that have accepted the settings, A template specification unit that accepts a specification of a template to be used for document creation from the stored templates, A necessary information setting unit that accepts a setting of necessary information including information necessary for creating a document using the accepted template, A document creation unit that inputs the accepted template and the accepted necessary information into a learned AI model to create the document, and has, The template includes a layout, description items, and a description method indicated by text, a document creation device.
2. The document creation device according to claim 1, wherein the learned AI model is a large language model.
3. Further comprising a reference information setting unit that accepts a setting of reference information that is information to be referred to in the creation of the document, The document creation unit further inputs the accepted reference information into the learned AI model to create the document, the document creation device according to claim 1 or 2.
4. The document creation device according to claim 1 or 2, further comprising a reshaping unit that reshapes the created document.
5. The document creation device according to claim 1 or 2, further comprising a verification unit that verifies the created document.
6. A document creation method executed by a document creation device, A template setting step of accepting a setting of a template for document creation, A template storage step of storing the accepted template, A template specification step of accepting a specification of a template to be used for document creation from the stored templates, A necessary information setting step unit that accepts a setting of necessary information including information necessary for creating a document using the accepted template, A document creation step of inputting the accepted template and the accepted necessary information into a learned AI model to create the document, and including, The template includes a layout, description items, and a description method indicated by text, a document creation method.
7. A template setting step of accepting a setting of a template for document creation, A template storage step of storing the accepted template, A template specifying step for receiving a specification of a template to be used for document creation from the stored templates; A necessary information setting step portion for receiving a setting of necessary information including information necessary for creating a document using the template that has received the specification; A document creation program for causing a document creation device to execute a document creation step of inputting the specified template and the received necessary information into a learned AI model to create the document. The template includes a layout, description items, and a description style indicated by sentences, and is a document creation program.
Citation Information
Patent Citations
Automatic invoice creation device, automatic invoice creation method, and automatic invoice creation program
JP2020194603A