Document creation device, document creation method, and document creation program

Abstract

The goal is to reduce the labor required and increase efficiency in the automatic creation of documents. [Solution] A document creation device is provided that has a template setting unit that sets a template for document creation, a template storage unit that stores the set templates, a template designation unit that designates a template to be used for document creation from the stored templates, a required information setting unit that sets necessary information that is information necessary to create a document using the designated template, a prompt generation unit that generates a prompt for creating the document in a large-scale language model using the designated template and the set necessary information, and a document creation unit that inputs the generated prompt into the large-scale language model to create the document.

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 daily for business implementation, and the improvement of the efficiency and labor-saving of document creation are 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 large language models (LLMs) such as ChatGPT (Non-Patent Document 1) to plugins for document creation software such as Word, attempts have been made to create documents using automatic generation of text by LLMs.

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 cope with the creation of documents in various formats.

[0007] In addition, in the technology related to 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 preconditions and matters to be considered for document creation as in the above-mentioned proposed documents, it is not easy to generate a prompt for instructing the LLM to create a document that fully reflects these. Also, when creating a large number of various documents, such difficult-to-generate prompts have to be generated each time, and the burden imposed on the user becomes large. Thus, the conventional technology 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 for setting a template for document creation, a template storage unit for storing the set template, a template designation unit for designating a template to be used for document creation from the stored templates, a necessary information setting unit for setting necessary information which is information necessary for creating a document using the designated template, a prompt generation unit for generating a prompt for causing the large language model to create the document using the designated template and the set necessary information, and a document creation unit for inputting the generated prompt to the large language model and creating the document.

[0009] In addition to the above features, a reference information setting unit for setting reference information which is information to be referred to in the creation of the document is further provided, and the prompt generation unit further generates the prompt using the set reference information.

[0010] In addition to the above features, a reshaping unit for reshaping the created document is further provided.

[0011] In addition to the above features, there is also provided a document creation device further having a verification unit for verifying the created document.

[0012] In addition to the above features, there is also provided a document creation device further having a prompt storage unit for storing the generated prompt.

[0013] Also, in a document creation device, there is provided a document creation method executed by a computer, the method including: a template setting step of setting a template for document creation; a template storage step of storing the set template; a template designation step of designating a template to be used for document creation from the stored templates; a necessary information setting step of setting necessary information, which is information required to create a document using the designated template; a prompt generation step of generating a prompt for causing the large language model to create the document using the designated template and the set necessary information; and a document creation step of inputting the generated prompt into the large language model to create the document.

[0014] Also, in a document creation device, there is provided a document creation program for causing a computer to execute: a template setting step of setting a template for document creation; a template storage step of storing the set template; a template designation step of designating a template to be used for document creation from the stored templates; a necessary information setting step of setting necessary information, which is information required to create a document using the designated template; a prompt generation step of generating a prompt for causing the large language model to create the document using the designated template and the set necessary information; and a document creation step of inputting the generated prompt into the large language model to create the document.

Advantages of the Invention

[0015] According to the present invention, desired documents can be efficiently created by using templates. [Brief explanation of the drawings]

[0016] [Figure 1] FIG. 1 is a block diagram showing an example of a functional configuration of a document creation device according to an embodiment of the present invention; [Figure 2] Conceptual diagram showing an example of the documents to be prepared and the required information [Figure 3] FIG. 1 is a conceptual diagram showing an example of the hardware configuration for realizing a document creation device according to an embodiment of the present invention. [Figure 4] FIG. 1 is a flow chart showing an example of a process flow of a document creation device according to an embodiment of the present invention; DETAILED DESCRIPTION OF THE INVENTION

[0017] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, the present invention should not be limited to these embodiments and can be embodied in various forms without departing from the spirit and scope of the present invention.

[0018] <Example> <Summary> For example, when creating documents that must be written according to specified guidelines, such as building confirmation applications submitted when constructing a building, using a large-scale language model (LLM; hereafter abbreviated as LLM), setting up and accumulating templates for each type of document can contribute to efficient document creation.

[0019] The following describes the functions and processing flow of the document creation device, as well as the hardware details. The functional blocks of the device described below can be realized as a combination of hardware and software. Specifically, if a computer is used, these include hardware components such as a CPU (central processing unit), main memory, bus, or secondary storage device (such as a hard disk drive, nonvolatile memory, or storage media such as CDs or DVDs, and drives for reading these media), input devices used to input information, printers, display devices, and other external peripheral devices, as well as interfaces for these external peripheral devices, communication interfaces, driver programs and other application programs for controlling these hardware, and user interface applications. The CPU processes data entered from input devices and other interfaces and stored in memory or on a hard disk in accordance with a program loaded in main memory, processing and storing the data, and generating commands to control the above hardware and software. Alternatively, the functional blocks of the device can be realized by dedicated hardware.

[0020] Furthermore, this invention can be realized not only as an apparatus but also as a method. Furthermore, a part of such an invention can be configured as software. Furthermore, a program used to cause a computer to execute such software, and a recording medium on which the program is fixed, are naturally included within 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 a document creation device according to 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 reformatting 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, for example, as a functional extension (plugin) in a document creation application such as Word, 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 is assumed to obtain particularly favorable effects 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 is placed 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, 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": "Enter the designer who will be the main designer for this property. If the design was done by multiple design offices, enter the designers involved in the design in the "Other Designers" column." For ease of explanation, the items to be described and the description guidelines are listed side by side, but the description guidelines for one document may also define the items to be described and the description guidelines for each item.

[0026] In setting the template, the layout may be set in advance, or the layout may be set more specifically as required information in the required information setting section described later. As an example of the latter, in the case of a document whose layout differs depending on the local government, the layout used by the local government for the case to be created is set as required information. The template settings, including the layout, items to be written, and writing instructions, may be configured to be performed in advance by the device or an application related to the device, or may be configured so that the user can perform them themselves.

[0027] <Template storage section> The template storage unit 102 has the function of storing set templates. By storing set templates with a unique ID and name assigned to each, the user can specify any template in the template designation unit described below. Note that the above-described 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.

[0028] <Template specification section> The template designation unit 103 has a function of designating a template to be used for document creation from stored templates. If the layout of the designated template has not been set, the layout is set in the necessary information setting unit as described above. If the layout of the designated template has already been set, designating one of the templates will designate the layout, items to be entered, and instructions for filling out the document to be created. Template designation may be configured to be performed hierarchically. For example, for a building confirmation application, by subdividing templates for the application subject (building, elevator, building equipment other than elevator, etc.) and the local government to which the application will be submitted, the user can easily designate the template to be used for the document to be created.

[0029] <Required information setting section> The required information setting unit 104 has a function of setting the required information, which is information required to create a document using the specified template. This required information is specific to the document to be created. For example, when creating a building confirmation application, this information includes architectural drawings and wiring diagrams of the actual building that is the subject of the application. Furthermore, if the layout of the document has not been set, a predetermined layout according to the application destination, etc. is set as the required information.

[0030] Figure 2 is a conceptual diagram showing an example of documents to be created and the necessary information. As shown in the figure, when creating a "construction plan summary" 201 for a building confirmation application, for example, a "neighborhood floor plan" 202 and a "layout plan" 203 must be included as description items. These descriptions are based on a "map" 204 showing the location of the object of the application and a "layout plan" 205 of that object, and these "maps" and "layout plans" correspond to the necessary information.

[0031] The necessary information may be set by extracting specific descriptions as described above, or by setting the location of the relevant information (address, path, etc.).

[0032] <Reference information setting section> The reference information setting unit 105 has a function of setting reference information which is information referred to in the creation of the document.

[0033] The reference information is the described content of documents that have relevance or similarity to the content of the document to be created. For example, in the creation of a building confirmation application, it is the described content of 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 the current document creation. 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.

[0034] 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 described content of the building confirmation applications submitted for buildings similar to this case as reference information." Furthermore, more detailed conditions may be added. For example, it is also possible to set the reference information to include conditions such as "building confirmation applications for elevators" or "cases where the application destination is ○○ Prefecture △△ City".

[0035] 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" as reference information.

[0036] 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 to be set integrally.

[0037] Furthermore, a preferred embodiment of a database for storing various information and documents that can serve as reference information is a device that not only digitizes documents by scanning them, but also structures and stores and manages the content of each item contained in the document. For example, the content of each item in a document can be entered into a spreadsheet with rows and columns and stored. To structure the content of a document in this way, the data can be manually entered from paper documents into a spreadsheet, or scanned and digitized image data or PDFs can be converted into text using OCR (Optical Character Recognition) and then stored in a database. Such a document DB may be included in the document creation device, or it may be an external device that can exchange information with the document creation device.

[0038] The database may also be constructed by using the LLM to extract and structure information for individual items contained in documents of various formats. For example, to extract the "drawing number" contained in a document, a prompt such as "Please extract the value of 'Drawing Number'. 'Drawing Number' is a file ID and consists only of alphanumeric characters and hyphens. It conforms to the following regular expression: [AZ]-\d{5}" can be entered into the LLM as a prompt, and processing can be performed on numerous documents that have been scanned and digitized as image data or converted to text using OCR from PDFs. The "drawing number" information can be obtained as a response, allowing the construction of a document database. Note that the specific means for extracting and structuring information to construct a document database are not particularly limited. This can be achieved using any appropriate technology.

[0039] Building a database such as the one described above is a time-consuming process, but the inventor of the present application has invented a data extraction technology using the LLM described above that reduces the labor and efficiency of the process, and has already filed a patent application (application number: PCT / JP2023 / 034488).

[0040] <Prompt generation part> The prompt generation unit 106 has a function of generating a prompt for creating the document in a large-scale language model using the specified template and the set required information. The prompt may also be generated using set reference information. For example, a sentence such as "Please create a 'construction plan outline' for the building confirmation application for the water supply and drainage system of XX. Search for information on water supply and drainage systems of projects similar to this project and refer to the information obtained as a result" may be generated. The prompt may be generated by the user inputting such a set of sentences, or the prompt may be generated by the user individually inputting the project name, the document to be created, the template to be used, the required information, and the reference information.

[0041] It is also possible to configure the LLM to add further prompts to instruct the LLM on more detailed conditions and settings for the document to be created. For example, prompts can be added regarding the maximum number of characters in the document to be created and conditions regarding the output format (text only, text with tables, including numerical data, etc.). It is also possible to configure the LLM to add prompts regarding whether to reformat or validate the created document, and if so, how to perform the reformat or validation. Reformatting and validation will be described later.

[0042] <Prompt accumulation section> The prompt storage unit 110 has a function of storing the generated prompts. Storing the prompts is convenient for the user because it allows them to create documents again or to modify and use them when creating documents for other projects. Furthermore, the prompts may be stored in association with a specified template and set required information and reference information.

[0043] <Document Creation Department> The document creation unit 107 has a function of inputting the generated prompt into the large language model to create the document. The creation of a document using an 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 the case that the entire document is created, but one or more items included in the document may be created. Further, it is also possible to configure to create documents in a plurality of variations according to the instruction of one prompt, present these plurality of documents, and accept the selection of the user. Also, the created document can be configured to be editable by the user.

[0044] Further, it is also preferable to configure to show the created document and show 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.

[0045] <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 an LLM with the instruction included in the prompt, or may be performed by inputting a script that separately instructs reshaping.

[0046] <Verification unit> The verification unit 109 has a function of verifying the created document. Verification means confirming whether the created document conforms to predetermined conditions and specifications. Further, if necessary, the verified result is output, or the verified result is reflected in the re-creation of the document. For example, verification such as verifying whether it is not similar to a specified negative sample, verifying whether a specific phrase (for example, the phrase "building restrictions within the setback") is included in the created document, and confirming the validity of the created document compared with the specified sample is performed.

[0047] When the verification result is not positive, for example, if it resembles the specified negative sample, does not contain specific words, or lacks validity, it is also preferable to display such a result as a message. Furthermore, by inputting an instruction to create again together with the message into the LLM to perform the creation process, it becomes possible to create a more preferable document in which the verification result is reflected.

[0048] 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 may be performed by inputting a script for instructing verification separately.

[0049] <Hardware Configuration> FIG. 3 is a conceptual diagram showing a configuration example of the hardware that realizes the document creation apparatus according to the 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 (working area) for the program. Also, a plurality of addresses are assigned to the RAM 302, and the programs executed by the CPU 301 can exchange data with each other by specifying and accessing the addresses and perform processes (the same applies throughout this specification).

[0050] Here, the functions of the template setting unit 101, template specifying unit 103, necessary information setting unit 104, reference information setting unit 105, prompt generation unit 106, document creation unit 107, reshaping unit 108, and verification unit 109 of the document creation apparatus 100 in FIG. 1 are mainly realized by the CPU 301 and RAM 302 in FIG. 3. Further, 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 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.

[0051] <Flow of processing> FIG. 4 is a flowchart briefly showing an example of the flow of processing of the document creation apparatus. First, the described items and the description details 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 specifying step). Then, necessary information, which is information necessary for creating a document using the specified template, is set (S404: necessary information setting step). Then, reference information, which is information to be referred to for creating a document, 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 reshaped (S408: reshaping step). Then, the created document is verified (S409: verification step). Note that the verification step may be performed before the reshaping step. Further, although not shown, it may include a prompt storage step of storing the prompt generated in the prompt generation step. Further, it may not include the reference information setting step.

[0052] <Effect> According to the document creation device of this embodiment, by using a template, a desired document can be created efficiently.

Explanation of Signs

[0053] 100: Document creation device 101: Template setting unit 102: Template storage unit 103: Template specifying unit 104: Necessary information setting unit 105: Reference information setting unit 106: Prompt generation unit 107: Document creation unit 108: Reshaping unit 109: 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 receives settings for templates for document creation, A template storage unit that stores the templates that have received the settings, A template designation unit that receives a designation of a template to be used for document creation from the stored templates, A necessary information setting unit that receives settings for necessary information, which is information necessary for creating a document using the designated template, A prompt generation unit that generates a prompt for causing the large language model to create the document using the designated template and the necessary information that has received the settings, A document creation unit that inputs the generated prompt into the large language model and creates the document, and has, The template includes a layout, description items, and a description method indicated by sentences, A document creation device.

2. Further having a reference information setting unit that receives settings for reference information, which is information to be referred to in the creation of the document, The prompt generation unit further generates the prompt using the received reference information, The document creation unit shows the created document and indicates which part of the reference information was referred to. The document creation device according to claim 1.

3. The document creation device according to claim 1 or 2, further having a reshaping unit that reshapes the created document.

4. The document creation device according to claim 1 or 2, further having a verification unit that verifies the created document.

5. The document creation device according to claim 1 or 2, further having a prompt storage unit that stores the generated prompt.

6. In a document creation device, a document creation method executed by a computer, comprising: A template setting step of receiving settings for templates for document creation, A template storage step of storing the templates that have received the settings, 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 settings for necessary information, which is information necessary for creating a document using the designated template, A prompt generation step of generating a prompt for causing the large language model to create the document using the designated template and the necessary information that has received the settings, A document creation step of inputting the generated prompt into the large language model to create the document, The template includes a layout, described items, and a description guideline indicated by sentences, Document creation method.

7. In a document creation device, 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 which is information necessary for creating a document using the designated template, A prompt generation step of generating a prompt for causing the large language model to create the document using the designated template and the received necessary information, A document creation program for causing a computer to execute a document creation step of inputting the generated prompt into the large language model to create the document, The template includes a layout, described items, and a description guideline indicated by sentences, Document creation program.

Images