Information generation support program, information generation support device, information generation support method, and recording medium

Abstract

This program provides artificial intelligence technology to assist in generating answers to questions. [Solution] The information generation support program disclosed herein includes an information acquisition procedure and an information generation procedure, The information acquisition procedure acquires information related to a question from a user, the generation procedure generates answer information to the question based on information selected from document data based on the information related to the question, and the answer information is answer information generated by a trained model. This is a program that causes a computer to execute each of the above procedures.

Description

Technical Field

[0001] The present disclosure relates to an information generation support program, an information generation support device, an information generation support method, and a recording medium.

Background Art

[0002] Patent Document 1 discloses an information processing system including a question reception processing unit that receives information regarding a question from a first terminal used by a first user, an answer reception processing unit that receives information regarding an answer to the question from a second terminal used by a second user, and an answer confirmation processing unit that enables the first user to view part or all of the information regarding the answer to the question after the arrival of the answer deadline for the question.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Recently, the development of artificial intelligence technology has been remarkable, and there is a possibility that the question-and-answer conducted between people as disclosed in Patent Document 1 can be replaced by applying artificial intelligence technology.

[0005] Therefore, an object of the present disclosure is to provide an information generation support program, an information generation support device, an information generation support method, and a recording medium for generating support for answers to questions by artificial intelligence technology.

Means for Solving the Problems

[0006] To achieve the above object, the information generation support program of the present disclosure includes an information acquisition procedure and a generation procedure, The aforementioned information acquisition procedure acquires information related to questions from the user, The above generation procedure generates answer information to the question based on information selected from document data based on the information relating to the question, The aforementioned response information is response information generated by a trained model. This is a program that instructs a computer to execute each step.

[0007] The information generation support device disclosed herein is: Including an information acquisition unit and an information generation unit, The aforementioned information acquisition unit acquires information related to questions from the user, The generation unit generates answer information to the question based on the information selected from the document data based on the information relating to the question. The aforementioned response information is a device that generates response information using a trained model.

[0008] The information generation support method disclosed herein is: Including information acquisition and generation processes, The aforementioned information acquisition process acquires information related to questions from the user, The generation process generates answer information to the question based on information selected from document data based on the information relating to the question. The aforementioned response information is response information generated by a trained model. This method involves each of the aforementioned steps being performed by a computer.

[0009] The recording medium of this disclosure is a computer-readable recording medium on which the program of this disclosure is recorded. [Effects of the Invention]

[0010] According to this disclosure, it is possible to provide an information generation support program, an information generation support device, an information generation support method, and a recording medium for using artificial intelligence technology to support the generation of answers to questions. [Brief explanation of the drawing]

[0011] [Figure 1] FIG. 1 is a block diagram showing a configuration example of an information generation support apparatus of the present disclosure. [Figure 2] FIG. 2 is a block diagram showing an example of a hardware configuration of the information generation support apparatus of the present disclosure. [Figure 3] FIG. 3 is a flowchart showing an example of a procedure in the information generation support program of the present disclosure. [Figure 4] FIG. 4 is a block diagram showing another example of a configuration of the information generation support apparatus of the present disclosure. [Figure 5] FIG. 5 is a flowchart showing another example of a procedure in the information generation support program of the present disclosure. [Figure 6] FIG. 6 is a schematic diagram showing an example of a method for generating response information by the information generation support apparatus of the present disclosure. [Figure 7] FIG. 7 is a schematic diagram showing another example of a method for generating response information by the information generation support apparatus of the present disclosure. [Figure 8] FIG. 8 is a diagram showing an example of specific image information.

MODE FOR CARRYING OUT THE INVENTION

[0012] Embodiments of the present disclosure will be described. Note that the present disclosure is not limited to the following embodiments. In the following figures, the same parts are denoted by the same reference numerals. Also, the descriptions of the respective embodiments can be mutually referred to unless otherwise specified. Further, the configurations of the respective embodiments can be combined unless otherwise specified. Also, each procedure described later in the program of the present disclosure can be read as "processing" instead of "procedure", for example.

[0013] [Embodiment 1] The information generation support program, information generation support apparatus, and information generation support method of the present disclosure will be described.

[0014] The information generation support program of the present disclosure is a program for causing a computer to execute an information acquisition procedure and a generation procedure. The information generation support program of the present disclosure can also be said to be a program for causing a computer to function as an information acquisition procedure and a generation procedure. Further, the information generation support program of the present disclosure can also be said to be, for example, a program for causing a computer to execute each step of the information generation support method described later.

[0015] Next, an example of the information generation support device of the present disclosure will be described based on FIGS. 1 and 2.

[0016] FIG. 1 is a block diagram showing a configuration example of an information generation support device 10 (this device 10) of the present disclosure. As shown in FIG. 1, this device 10 includes an information acquisition unit 11 and a generation unit 12.

[0017] The device 10 may be, for example, a single device including the aforementioned parts, or it may be a device in which the aforementioned parts can be connected via a communication network. Furthermore, the device 10 can be connected to an external device described later via the communication network. The communication network is not particularly limited and can use a known network, for example, it may be wired or wireless. Examples of the communication network include the Internet, WWW (World Wide Web), telephone lines, LAN (Local Area Network), SAN (Storage Area Network), DTN (Delay Tolerant Networking), LPWA (Low Power Wide Area), L5G (Local 5G), etc. Examples of wireless communication include Wi-Fi (registered trademark), Bluetooth (registered trademark), Local 5G, LPWA, etc. The wireless communication may be in the form of direct communication between devices (Ad Hoc communication), infrastructure communication, indirect communication via an access point, etc. The device 10 may be, for example, incorporated into a server as a system. Furthermore, the device 10 may be, for example, a personal computer (PC, e.g., desktop or notebook), smartphone, tablet terminal, digital signage, etc., on which the program disclosed herein is installed. The device 10 may also be in the form of cloud computing or edge computing, for example, in which at least one of the aforementioned parts is on a server and the other parts are on a terminal.

[0018] Figure 2 illustrates a block diagram of the hardware configuration of the device 10. The device 10 includes, for example, a central processing unit (CPU, GPU, etc.) 101, memory 102, bus 103, storage device 104, input device 105, output device 106, communication device 107, etc. Each part of the device 10 is interconnected via the bus 103 through its respective interface (I / F).

[0019] The central processing unit 101 operates in cooperation with other components via controllers (system controller, I / O controller, etc.) and is responsible for the overall control of the device 10. In the device 10, the central processing unit 101 executes, for example, the program disclosed herein and other programs, and also reads and writes various types of information. Specifically, for example, the central processing unit 101 functions as an information acquisition unit 11 and an information generation unit 12. The central processing unit 101 may be equipped with a CPU, GPU (Graphics Processing Unit), APU (Accelerated Processing Unit), or a combination thereof as its arithmetic unit.

[0020] Bus 103 can also be connected to external devices, for example. Examples of such external devices include external storage devices such as external databases, printers, external input devices, external display devices, and external imaging devices. The device 10 can be connected to an external network (the aforementioned communication network) by a communication device 107 connected to bus 103, for example, and can also be connected to other devices via the external network.

[0021] Memory 102 may be, for example, main memory. When the central processing unit 101 performs processing, memory 102 reads various operational programs, such as the program of this disclosure, stored in the storage device 104 (described later), and the central processing unit 101 receives data from memory 102 and executes the program. The main memory may be, for example, RAM (random access memory). Alternatively, memory 102 may be, for example, ROM (read-only memory).

[0022] The storage device 104 is also called an auxiliary storage device, for example, in relation to the main memory (primary memory). As described above, the storage device 104 stores an operating program including the program of this disclosure. The storage device 104 may be, for example, a combination of a recording medium and a drive for reading and writing to the recording medium. The recording medium is not particularly limited and may be internal or external, for example, an HD (hard disk), CD-ROM, CD-R, CD-RW, MO, DVD, flash memory, memory card, etc. The storage device 104 may be, for example, a hard disk drive (HDD) in which the recording medium and the drive are integrated, or a solid state drive (SSD).

[0023] In this device 10, the memory 102 and storage device 104 can also store various types of information, such as log information, information obtained from an external database (not shown) or external devices, information generated by this device 10, and information used by this device 10 when executing processing. In this case, the memory 102 and storage device 104 may store, for example, question information, image information, elements, and answer information, as described later. At least some of the information may be stored on an external server other than the memory 102 and storage device 104, or it may be stored in a distributed manner across multiple terminals using blockchain technology or the like.

[0024] The device 10 further includes, for example, an input device 105 and an output device 106. The input device 105 may include, for example, a pointing device such as a touch panel, trackpad, or mouse; a keyboard; imaging means such as a camera or scanner; a card reader such as an IC card reader or magnetic card reader; an audio input means such as a microphone; and so on. The output device 106 may include, for example, a display device such as an LED display or liquid crystal display; an audio output device such as a speaker; a printer; and so on. In this disclosure, the input device 105 and the output device 106 are configured separately, but the input device 105 and the output device 106 may be configured as an integrated unit, such as a touch panel display.

[0025] First, an example of the processing of the information generation support program disclosed herein will be specifically explained based on Figure 3. Figure 3 is a flowchart showing an example of each step of the information generation support program disclosed herein.

[0026] The information acquisition unit 11 acquires information related to the user's question (S11, information acquisition procedure). The user may be, for example, an employee of an administrative agency, a legal professional, an auditor of a certain organization, or a professional in a specialized field. The administrative agency may be, for example, the Fire and Disaster Management Agency, the National Police Agency, the Ministry of Finance, the Ministry of Health, Labour and Welfare, the Ministry of Economy, Trade and Industry, the Ministry of Land, Infrastructure, Transport and Tourism, the Ministry of the Environment, the Ministry of Internal Affairs and Communications, the National Tax Agency, the Fair Trade Commission, the Financial Services Agency, the Immigration Services Agency, or the Japan Coast Guard. The legal professional may be, for example, a lawyer, prosecutor, judge, legal officer, patent attorney, notary public, administrative scrivener, judicial scrivener, or social insurance labor consultant. The legal professional may be, for example, someone who holds the qualifications for the legal profession, or someone who assists someone who holds the qualifications. The organization may be, for example, a company, a public institution, a government-related institution, a non-profit organization, a social organization, a certification body, or a standardization body. Examples of auditors include ISO internal auditors, quality control auditors, environmental auditors, security auditors, information systems auditors, occupational safety and health auditors, financial auditors, compliance auditors, corporate ethics auditors, and supply chain auditors. Examples of specialized services include insurance, construction, finance, legal, medical, and real estate services.

[0027] The aforementioned questions include, for example, questions relating to hard law and soft law. Hard law includes, for example, the Constitution, laws, government ordinances, Cabinet Office ordinances, ministerial ordinances, regulations, orders, directives, terms and conditions, and contracts. Soft law includes, for example, public notices, circulars, notifications, rules, standards, outlines, regulations, rules, recommendations, instructions, guidelines, and manuals.

[0028] The information acquisition unit 11 may, for example, further acquire image information and elements necessary for performing a certain evaluation (hereinafter sometimes simply referred to as "necessary elements"). The image information may include, for example, a photograph of the subject of the evaluation. The image information may also include metadata such as the date and time the image was created and location information. The evaluation may include, for example, at least one of the following: inspection, audit, investigation, certification, review, confirmation, monitoring, inspection, evaluation, and verification. The necessary elements may include, for example, points to focus on in the evaluation and the subject.

[0029] The information acquisition unit 11 may, for example, acquire necessary information from information input by the input device 105, or it may acquire necessary information from information stored in the storage device 104 or other devices.

[0030] Next, the generation unit 12 generates answer information to the question based on information selected from the document data based on the information relating to the question (S12, generation procedure). The answer information is answer information generated by a trained model. The trained model can be said to be, for example, a trained model that, when information relating to the question is input, generates answer information to the question based on information selected from the document data. The trained model is, for example, a large-scale language model. The document data may be, for example, document data stored in the storage device 104 or another device. That is, the generation unit 12 may generate answer information to the question based on information selected from the document data stored in the storage device 104 based on the information relating to the question, or it may generate answer information to the question based on information selected from document data stored in another device (for example, data stored in the cloud, etc.). The selection of the document data may be performed, for example, by the selection unit (not shown) if the device 10 has a selection unit (selection procedure). The selection may be, for example, a search. The generation may be, for example, Retrieval-Augmented Generation (RAG). The Retrieval-Augmented Generation may be performed, for example, by a conventionally known method.

[0031] The document data may include, for example, hard law and soft law. The document data may include, for example, at least one of electronic data and paper data. The document data may include, for example, current document data and past document data. The response information may include, for example, summary information of the document data. The summary information may be generated, for example, by a conventionally known method. The summary information may be, for example, extracted summary information or generated summary information.

[0032] The aforementioned response information may include, for example, information relating to the aforementioned evaluation from the aforementioned administrative agency, the aforementioned legal professional, or the aforementioned certain organization. The aforementioned response information may include, but is not limited to, information relating to fire inspections, fire report preparation, corporate audits, insurance counter services, and building compliance survey services. The aforementioned response information may also include, for example, grounds relating to the aforementioned hard law and soft law. The aforementioned grounds may include, for example, article numbers, page numbers, precedents, statistical data, and literature.

[0033] The generation unit 12 further generates, for example, image information in which the evaluation points are identified (hereinafter sometimes simply referred to as "identified image information") based on the image information and the elements. The identified image information is, for example, image information generated by an image recognition model. The image recognition model may be, for example, a conventionally known image recognition model. Methods for identifying the points include, for example, enclosing the object that will be the point displayed in the image with lines such as circles or squares; color coding; marker display; pointing with dots, lines, and arrows, etc.; zooming in or out; displaying with text, symbols, etc. The identified image information may be, for example, information in which the content of the image information has been converted into text.

[0034] At least one of the generated response information and image information may be output by, for example, the output device 106 or another device. The output response information and image information may include, for example, at least one of text, tables, images, and audio.

[0035] The generation unit 12 may, for example, generate answer information to the question based on information selected from the document data based on the information relating to the question and the image information. The generation unit 12 may, for example, generate answer information to the question based on the information relating to the question and the metadata. Specifically, the document data is, for example, the document data selected based on the metadata that is optimal for generating answer information to the question. For example, if the metadata includes the date and time of shooting and location information, the document data of the most appropriate year (e.g., a law) is selected as the document data based on the date and time of shooting and location information, and answer information to the question that matches the date and time of shooting and location information included in the metadata is generated based on the selected document data.

[0036] The generation unit 12 may, for example, generate a management tool related to the evaluation. Examples of such management tools include checklists, to-do lists, process maps, action plans, and schedules. The management tool may also relate to the evaluation points, for example.

[0037] Furthermore, the exchange of various types of information in this device 10 may be carried out by at least one of the following methods: chat, voice interaction, email, etc. This also applies to this device 10A, which will be described later.

[0038] Next, the information generation support method of this disclosure will be explained. The information generation support method of this disclosure can be understood by referring to the descriptions in the information generation support program and information generation support device of this disclosure. The information generation support method of this disclosure is a method implemented by, for example, replacing each "procedure" in the program of this disclosure with a "process". Specifically, the information generation support method of this disclosure includes an information acquisition process and an information generation process. The information generation support method of this disclosure can be implemented, for example, using the device 10 in Figure 1. However, the information generation support method of this disclosure is not limited to the use of the device 10 in Figure 1.

[0039] According to this disclosure, the information acquisition procedure acquires information related to a user's question, and the generation procedure generates answer information to the question based on the information related to the question. The answer information is generated by a trained model that has learned based on document data. Therefore, artificial intelligence technology can be used to support the generation of answers to questions. Furthermore, this can reduce the time required to research legal and other documents to prepare answers to questions in evaluation work such as inspections, and to understand such documents in advance. In addition, in evaluation work such as inspections, users can perform the work with the same level of competence regardless of their years of experience.

[0040] [Embodiment 2] Further explanation is provided regarding the information generation support program, information generation support device, and information generation support method disclosed herein.

[0041] The information generation support program disclosed herein is a program that causes a computer to execute a document creation procedure. It can also be described as a program that causes a computer to function as a document creation procedure. Furthermore, it can be described as a program that causes a computer to execute each step of the information generation support method described later.

[0042] Next, another example of the information generation support device disclosed herein will be described based on Figure 4.

[0043] Figure 4 is a block diagram showing an example configuration of the information generation support device 10A (the device 10A) of the present disclosure. As shown in Figure 4, the device 10A includes a document creation unit 13 in addition to the configuration of the device 10.

[0044] In this device 10A, the central processing unit 101 functions as an information acquisition unit 11, an information generation unit 12, and a document creation unit 13. The other hardware configurations are the same as those of this device 10, except that the central processing unit in Figure 2 is further equipped with a document creation unit 13.

[0045] Next, another example of the processing of the information generation support program of this disclosure will be specifically explained based on Figure 5. Figure 5 is a flowchart showing another example of each step of the information generation support program of this disclosure.

[0046] The information acquisition unit 11 further acquires a record document created by the user (S111). Examples of such record documents include reports, records, memos, meeting minutes, and minutes. The record document may be, for example, text or an image containing text. In the case of an image containing text, for example, the text contained in the image may be recognized using conventionally known character recognition technology, and a report document, as described later, may be created based on the recognized characters. Otherwise, the procedure is the same as that of S11 and S12 performed by the information acquisition unit 11 and the generation unit 12 described above.

[0047] Next, the document creation unit 13 creates a report document based on the record document (S13, document creation procedure). The report document is, for example, a report document generated by a document creation model based on the record document. The document creation model can also be described as a trained model that creates the report document when the record document is input. The report document is, for example, a report relating to the evaluation. The document creation unit 13 may create the document based on, for example, a predetermined format and at least one of other information. The other information may be, for example, information relating to the subject of the evaluation. The predetermined format and other information may be stored in, for example, a storage device 104 or another device.

[0048] The generated report document may be output by, for example, output device 106 or another device. The output report document may include, for example, at least one of text, tables, images, and audio.

[0049] In Figure 5, the steps of S12 and S13 are shown in parallel, but this is not the only way to proceed. For example, S13 may be performed after S12, or S12 may be performed after S13.

[0050] Next, the information generation support method of this disclosure will be further explained. The information generation support method of this disclosure can be described by referring to the descriptions in the information generation support program and information generation support device of this disclosure. The information generation support method of this disclosure is a method that is implemented by, for example, replacing each "procedure" in the program of this disclosure with a "process". Specifically, the information generation support method of this disclosure further includes a document creation process. The information generation support method of this disclosure can be implemented, for example, using the device 10A in Figure 4. However, the information generation support method of this disclosure is not limited to the use of the device 10A in Figure 4.

[0051] According to this disclosure, a document creation procedure further generates a document related to the response information. Therefore, for example, the burden of creating a document related to the response information can be reduced.

[0052] [Embodiment 3] An example of a method for generating response information using the information generation support device disclosed herein will be explained with specific examples shown in Figures 6-8. While this disclosure shows examples using device 10 or 10A, it is not limited to these. Furthermore, while this disclosure uses fire department inspections as an example of generating response information, it is not limited to this.

[0053] Figure 6 shows an example of a method for generating response information using the device 10. First, the device 10 acquires information related to a question from a firefighter who is a user of the device 10. This question information may be obtained, for example, from a communication terminal (personal computer, smartphone, etc.) owned by the firefighter. In Figure 6, the information related to the question from the firefighter could be, for example, information related to the Fire Service Act that arose during an inspection conducted by the fire department. Based on the information related to the question, the device 10 generates response information to the question based on information selected from document data. This response information is generated by a trained model. In Figure 6, a large-scale language model is used as the trained model. In Figure 6, electronic data including laws and regulations, as well as paper data such as past notices and manuals within the fire department, are searched as document data, and the large-scale language model generates response information to the question based on the information retrieved from these. Note that the electronic data may be, for example, public data such as e-Gov, commercial data, or data stored on other devices (for example, data stored in the cloud). Subsequently, the aforementioned response information is output to the communication terminal held by the firefighter. This allows firefighters to obtain answers to questions that they previously had to resolve by referring to manuals or legal texts, more easily than before.

[0054] Figure 7 shows an example of a method for generating response information using the device 10A. The process up to obtaining information related to the question is the same as in Figure 6. In Figure 7, the device 10A further acquires image information and elements necessary for performing a certain evaluation (inspection). In Figure 7, the image information is obtained from firefighters, who have taken photographs of the inspection site, and the necessary elements are obtained from the device 10A's storage device, who have acquired points and targets to focus on during the inspection. Subsequently, the device 10A generates image information with identified inspection points (specific image information) based on the image information and the necessary elements. In Figure 7, the specific image information is generated by an image recognition model. Figure 8 shows an example of the specific image information. The upper part of Figure 8 is a photograph of the site taken by firefighters during the inspection, and the lower part of Figure 8 is the specific image information. As shown in the lower part of Figure 8, in the specific image information, objects that are points of inspection are enclosed by dotted lines. For example, if specific image information is output to a communication terminal held by a firefighter, the firefighter can easily identify key points during an inspection by checking the specific image information.

[0055] The device 10A may generate the response information using the information related to the question and metadata contained in the image information (for example, location information of the photograph, date and time of shooting, and information such as the year of construction that can be determined from the building database).

[0056] In Figure 7, the device 10A further acquires the record documents (reports) created by the user. The device 10A then creates a report document (report) based on the report. In Figure 7, the report is generated by a document creation model. In this way, the device 10A creates the report document, reducing the burden on firefighters to create reports (report documents) based on record documents such as reports.

[0057] [Embodiment 5] The program of this disclosure may be recorded on, for example, a computer-readable storage medium. The storage medium is, for example, a non-transitory computer-readable storage medium. The storage medium is not particularly limited and includes, for example, random access memory (RAM), read-only memory (ROM), hard disk (HD), flash memory (e.g., USB flash memory, SD / SDHC card, etc.), optical disc (e.g., CD-R / CD-RW, DVD-R / DVD-RW, BD-R / BD-RE, etc.), magneto-optical disk (MO), floppy disk (FD), etc. The program of this disclosure (for example, also referred to as a programming product or program product) may also be delivered, for example, from an external computer. The “delivery” may be, for example, delivered via a communication network or delivered via a wired device. The program of this disclosure may be installed and executed on the delivered device, or it may be executed without being installed.

[0058] Although the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. The configuration and conditions of the present disclosure can be modified in various ways that can be understood by those skilled in the art within the scope of the present disclosure.

[0059] <Note> Some or all of the above embodiments may be described as follows, but are not limited to the following: (Note 1) This includes information acquisition procedures and generation procedures. The aforementioned information acquisition procedure acquires information related to questions from the user, The above generation procedure generates answer information to the question based on information selected from document data based on the information relating to the question, The aforementioned response information is response information generated by a trained model. An information generation support program that causes a computer to perform each of the above steps. (Note 2) The aforementioned information acquisition procedure further acquires image information and elements necessary for performing a certain evaluation. The generation procedure further generates image information in which the evaluation points have been identified, based on the image information and the elements. The information generation support program described in Appendix 1. (Note 3) The image information from which the evaluation points were identified is image information generated by an image recognition model. The information generation support program described in Appendix 2. (Note 4) The aforementioned image information includes metadata, The generation procedure generates answer information to the question based on the information relating to the question and the information selected from the document data based on the metadata. Information generation support program as described in Appendix 2 or 3. (Note 5) The document data is the document data selected based on the metadata that is optimal for generating answer information to the question. Information generation support program as described in Appendix 4. (Note 6) The aforementioned trained model is a large-scale language model. An information generation support program as described in any of the appendices 1 to 5. (Note 7) The aforementioned document data includes hard law and soft law, An information generation support program as described in any of the appendices 1 to 6. (Note 8) The aforementioned response information includes summary information of the document data, An information generation support program as described in any of the appendices 1 through 7. (Note 9) The aforementioned response information is information related to fire department inspections. An information generation support program described in any of the appendices 1 through 8. (Note 10) Furthermore, including the document creation procedure, The aforementioned information acquisition procedure further acquires user-created record documents, The document creation procedure described above involves creating a report document based on the record document. An information generation support program as described in any of the appendices 1 through 9. (Note 11) The aforementioned report document is a report document generated by a document creation model based on the aforementioned record document. Information generation support program as described in Appendix 10. (Note 12) Including an information acquisition unit and an information generation unit, The aforementioned information acquisition unit acquires information related to questions from the user, The generation unit generates answer information to the question based on the information selected from the document data based on the information relating to the question. The aforementioned response information is response information generated by a trained model. Information generation support device. (Note 13) The information acquisition unit further acquires image information and elements necessary for performing a certain evaluation. The generation unit further generates image information in which the evaluation points have been identified, based on the image information and the elements. Information generation support device as described in Appendix 12. (Note 14) The image information from which the evaluation points were identified is image information generated by an image recognition model. Information generation support device as described in Appendix 13. (Note 15) The aforementioned image information includes metadata, The generation unit generates answer information to the question based on the information relating to the question and the information selected from the document data based on the metadata. Information generation support device as described in Appendix 13 or 14. (Note 16) The document data is the document data selected based on the metadata that is optimal for generating answer information to the question. Information generation support device as described in Appendix 15. (Note 17) The aforementioned trained model is a large-scale language model. An information generation support device as described in any of Appendix 12 to 16. (Note 18) The aforementioned document data includes hard law and soft law, An information generation support device as described in any of Appendix 12 to 17. (Note 19) The aforementioned response information includes summary information of the document data, An information generation support device as described in any of Appendix 12 to 18. (Note 20) The aforementioned response information is information related to fire department inspections. An information generation support device as described in any of the appendices 12 to 19. (Note 21) Furthermore, including the document creation section, The aforementioned information acquisition unit further acquires the record document created by the user, The document creation unit creates a report document based on the record document. An information generation support device as described in any of Appendix 12 to 20. (Note 22) The aforementioned report document is a report document generated by a document creation model based on the aforementioned record document. Information generation support device as described in Appendix 21. (Note 23) Including information acquisition and generation processes, The aforementioned information acquisition process acquires information related to questions from the user, The generation process generates answer information to the question based on information selected from document data based on the information relating to the question. The aforementioned response information is response information generated by a trained model. An information generation support method in which each of the above steps is performed by a computer. (Note 24) The aforementioned information acquisition process further acquires image information and elements necessary for performing a certain evaluation. The generation step further generates image information in which the evaluation points have been identified, based on the image information and the elements. Information generation support method as described in Appendix 23. (Note 25) The image information from which the evaluation points were identified is image information generated by an image recognition model. Information generation support method as described in Appendix 24. (Note 26) The aforementioned image information includes metadata, The generation process generates answer information to the question based on the information related to the question and the information selected from the document data based on the metadata. Information generation support method as described in Appendix 24 or 25. (Note 27) The document data is the document data selected based on the metadata that is optimal for generating answer information to the question. Information generation support method as described in Appendix 26. (Note 28) The aforementioned trained model is a large-scale language model. Information generation support method as described in any of Appendix 23 to 27. (Note 29) The aforementioned document data includes hard law and soft law, Information generation support method as described in any of Appendix 23 to 28. (Note 30) The aforementioned response information includes summary information of the document data, Information generation support method as described in any of Appendix 23 to 29. (Note 31) The aforementioned response information is information related to fire department inspections. Information generation support method as described in any of the appendices 23 to 30. (Note 32) Furthermore, including the document creation process, The aforementioned information acquisition process further acquires the record documents created by the user, The document creation process involves creating a report document based on the record document. Information generation support method as described in any of the appendices 23 to 31. (Note 33) The aforementioned report document is a report document generated by a document creation model based on the aforementioned record document. Information generation support method as described in Appendix 32. (Note 34) This includes information acquisition procedures and generation procedures. The aforementioned information acquisition procedure acquires information related to questions from the user, The above generation procedure generates answer information to the question based on information selected from document data based on the information relating to the question, The aforementioned response information is response information generated by a trained model. A computer-readable recording medium containing a program that causes a computer to perform each of the aforementioned steps. (Note 35) The aforementioned information acquisition procedure further acquires image information and elements necessary for performing a certain evaluation. The generation procedure further generates image information in which the evaluation points have been identified, based on the image information and the elements. Recording medium as described in Appendix 34. (Note 36) The image information from which the evaluation points were identified is image information generated by an image recognition model. Recording medium as described in Appendix 35. (Note 37) The aforementioned image information includes metadata, The generation procedure generates answer information to the question based on the information relating to the question and the information selected from the document data based on the metadata. Recording medium as described in Appendix 35 or 36. (Note 38) The document data is the document data selected based on the metadata that is optimal for generating answer information to the question. Recording medium as described in Appendix 37. (Note 39) The aforementioned trained model is a large-scale language model. A recording medium as described in any of the appendices 34 to 38. (Note 40) The aforementioned document data includes hard law and soft law, A recording medium as described in any of the appendices 34 to 39. (Note 41) The aforementioned response information includes summary information of the document data, A recording medium as described in any of the appendices 34 to 40. (Note 42) The aforementioned response information is information related to fire department inspections. A recording medium as described in any of the appendices 34 to 41. (Note 43) Furthermore, including the document creation procedure, The aforementioned information acquisition procedure further acquires user-created record documents, The document creation procedure described above involves creating a report document based on the record document. A recording medium as described in any of the appendices 34 to 42. (Note 44) The aforementioned report document is a report document generated by a document creation model based on the aforementioned record document. Recording medium as described in Appendix 43. [Industrial applicability]

[0060] This disclosure makes it possible to provide an information generation support program, an information generation support device, an information generation support method, and a recording medium for using artificial intelligence technology to assist in generating answers to questions. The fields to which this disclosure can be applied are not limited, and it is useful in various fields using the program of this disclosure. [Explanation of Symbols]

[0061] 10, 10A information generation support device 11 Information acquisition department 12 Generation part 13 Document Creation Department 101 CPU 102 memory 103 Bus 104 Storage device 105 Input device 106 Output device 107 Communication devices

Claims

1. This includes information acquisition procedures and generation procedures. The aforementioned information acquisition procedure acquires information related to questions from the user, The above generation procedure generates answer information to the question based on information selected from document data based on the information relating to the question, The aforementioned response information is response information generated by a trained model. An information generation support program that causes a computer to perform each of the above steps.

2. The aforementioned information acquisition procedure further acquires image information and elements necessary for performing a certain evaluation. The generation procedure further generates image information in which the evaluation points have been identified, based on the image information and the elements. The information generation support program according to claim 1.

3. The image information from which the evaluation points were identified is image information generated by an image recognition model. The information generation support program according to claim 2.

4. The aforementioned image information includes metadata, The generation procedure generates answer information to the question based on the information relating to the question and the information selected from the document data based on the metadata. The information generation support program according to claim 2 or 3.

5. The document data is the document data selected based on the metadata that is optimal for generating answer information to the question. The information generation support program according to claim 4.

6. The aforementioned document data includes hard law and soft law, An information generation support program according to any one of claims 1 to 3.

7. Furthermore, including the document creation procedure, The aforementioned information acquisition procedure further acquires user-created record documents, The document creation procedure described above involves creating a report document based on the record document. An information generation support program according to any one of claims 1 to 3.

8. Including an information acquisition unit and an information generation unit, The aforementioned information acquisition unit acquires information related to questions from the user, The generation unit generates answer information to the question based on the information selected from the document data based on the information relating to the question. The aforementioned response information is response information generated by a trained model. Information generation support device.

9. Including information acquisition and generation processes, The aforementioned information acquisition process acquires information related to questions from the user, The generation process generates answer information to the question based on information selected from document data based on the information relating to the question. The aforementioned response information is response information generated by a trained model. An information generation support method in which each of the above steps is performed by a computer.

10. This includes information acquisition procedures and generation procedures. The aforementioned information acquisition procedure acquires information related to questions from the user, The above generation procedure generates answer information to the question based on information selected from document data based on the information relating to the question, The aforementioned response information is response information generated by a trained model. A computer-readable recording medium containing a program that causes a computer to perform each of the aforementioned steps.

Images