Program, method, information processing apparatus, and system

Abstract

To provide a program, a method, an information processing apparatus, and a system for creating suitable FAQs.SOLUTION: A method executes: a document acquisition step S101; a first generation step S102 of generating a first prompt for creating a question sentence related to the details described in a first portion that is part of predetermined document information acquired in the document acquisition step; a first acquisition step S103 of acquiring a predetermined question sentence that is output by inputting the generated first prompt to generative AI; a portion extraction step of extracting a second portion that is a part related to the acquired predetermined question sentence; a second generation step S104 of generating a second prompt including the extracted second portion and for creating an answer sentence to the predetermined question sentence; and a second acquisition step S105 of acquiring a predetermined answer sentence that is output by inputting the generated second prompt to generative AI.SELECTED DRAWING: Figure 7

Description

[Technical Field]

[0001] The present disclosure relates to a program, a method, an information processing device, and a system. [Background technology]

[0002] An information processing system for processing information about FAQs (Frequently Asked Questions) consisting of pairs of questions and answers is known. Patent Document 1 discloses a technology that enables a chatbot to automatically respond to inquiries from users, and when the time comes for a live person to take over, to seamlessly hand over the response to the respondent. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2022-189237 Summary of the Invention [Problem to be solved by the invention]

[0004] There is an issue in that suitable FAQs have not been created. Therefore, the present disclosure has been made to solve the above-mentioned problems, and its purpose is to provide a technology for creating suitable FAQs. [Means for solving the problem]

[0005] A program to be executed by a computer having a processor and a memory unit, wherein the processor executes the following steps: a document acquisition step of acquiring specified document information; a first generation step of generating a first prompt for creating a question related to the content described in the first portion, including a first portion that is part of the specified document information acquired in the document acquisition step; a first acquisition step of acquiring the specified question by inputting the first prompt generated in the first generation step into a generation AI; a part extraction step of extracting a second portion from the specified document information acquired in the document acquisition step that is related to the specified question acquired in the first acquisition step; a second generation step of generating a second prompt for creating an answer to the specified question, including the second portion extracted in the part extraction step; a second acquisition step of acquiring the specified answer by inputting the second prompt generated in the second generation step into a generation AI; and an FAQ storage step of associating and storing the specified question and the specified answer. [Effects of the Invention]

[0006] According to the present disclosure, it is possible to create suitable FAQs. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 2 is a block diagram showing the functional configuration of the system 1. [Figure 2] FIG. 2 is a block diagram showing the functional configuration of the server 10. [Figure 3] FIG. 2 is a block diagram showing the functional configuration of a user terminal 20. [Figure 4] FIG. 10 is a diagram showing the data structure of a user table 1012. [Figure 5] FIG. 10 is a diagram showing the data structure of a document table 1013. [Figure 6] FIG. 10 is a diagram showing the data structure of a page table 1014. [Figure 7] 10 is a flowchart showing the operation of an FAQ creation process. [Figure 8] FIG. 2 is a block diagram showing the basic hardware configuration of a computer 90. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all drawings describing the embodiments, common components are designated by the same reference numerals, and repeated description will be omitted. Note that the following embodiments do not unduly limit the content of the present disclosure described in the claims. Furthermore, not all components shown in the embodiments are necessarily essential components of the present disclosure. Furthermore, each drawing is a schematic diagram and is not necessarily a precise illustration.

[0009] <System 1 Configuration> The system 1 in the present disclosure is an information processing system that provides an information processing service for creating FAQs consisting of pairs of questions and answers. The system 1 includes an information processing device including a server 10, a user terminal 20, and a generating AI 50, all of which are connected via a network N. FIG. 1 is a block diagram showing the functional configuration of the system 1. As shown in FIG. FIG. 2 is a block diagram showing the functional configuration of the server 10. As shown in FIG. FIG. 3 is a block diagram showing the functional configuration of the user terminal 20. As shown in FIG.

[0010] Each information processing device is configured by a computer equipped with an arithmetic unit and a storage device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For each of the server 10, the user terminal 20, and the generation AI 50, descriptions that overlap with the basic hardware configuration and basic functional configuration of the computer will be omitted.

[0011] <Server 10 configuration> The server 10 is an information processing device that provides an information processing service for creating FAQs consisting of pairs of questions and answers. The server 10 includes a storage unit 101 and a control unit 104 .

[0012] <Configuration of the storage unit 101 of the server 10> The storage unit 101 of the server 10 includes an application program 1011 , a user table 1012 , a document table 1013 , and a page table 1014 .

[0013] The application program 1011 is a program for causing the control unit 104 of the server 10 to function as each functional unit. Application programs 1011 include applications such as a web browser application.

[0014] User table 1012 is a table that stores and manages information about member users (hereinafter, "users") who use the service. When a user registers to use the service, the user's information is stored in a new record in user table 1012. This allows the user to use the service according to the present disclosure. The user table 1012 is a table having columns of user ID, user name, and user data, with the user ID as the primary key. FIG. 4 is a diagram showing the data structure of the user table 1012. As shown in FIG.

[0015] The user ID is an item that stores user identification information for identifying a user. The user identification information is an item that is set with a unique value for each user. The user name is an item for storing the name of the user. The user name may be set to any character string such as a nickname instead of a name. The user data includes information specific to the individual user and attribute information relating to the user's characteristics and background. The user's unique information includes information unique to the user, such as the user's date of birth (age), sex, and the like. The user's attribute information includes information such as the user's educational history (highest level of education, major, graduation year), occupation, work history, interests, place of residence, and language.

[0016] The document table 1013 is a table for storing and managing information about documents (document information). The document table 1013 is a table having a document ID as a primary key and columns of document ID and document data. FIG. 5 is a diagram showing the data structure of the document table 1013.

[0017] The document ID is an item that stores document identification information for identifying a document. The document identification information is an item in which a unique value is set for each piece of document information. The document data is an item that stores information about a document. Specifically, the document data stores any electronic data related to a document, such as PDF (Portable Document Format), HTML, XML, Word, Excel, PowerPoint, or any other text data. In particular, this disclosure discloses document data in a format in which documents are stored page by page, such as PDF, as an example. Note that this disclosure does not necessarily have to be applied only to document data in a format in which documents are stored page by page, but can be applied to document data in any format. The document data stores documents such as work procedures and manuals related to products, services, and businesses.

[0018] The page table 1014 is a table for storing and managing information about pages (page information). The page table 1014 is a table having a page ID as a primary key and columns of page ID, document ID, page data, and structured data. FIG. 6 is a diagram showing the data structure of the page table 1014.

[0019] The page ID is an item that stores page identification information for identifying a page. The page identification information is an item that has a unique value set for each piece of page information. The document ID is an item for storing document identification information for identifying a document. The page data is an item for storing document data relating to a specific page (hereinafter referred to as page data). The document data is the same as the document data item in the document table 1013. The structured data is an item that stores structured text data relating to the content written on a specific page, which is obtained by analyzing the page data. Specifically, the structured data stores text data structured for each heading, such as chapter, section, paragraph, etc., in markdown, XML, HTML, etc., regarding the content written on a specific page.

[0020] <Configuration of the control unit 104 of the server 10> The control unit 104 of the server 10 includes a user registration control unit 1041. The control unit 104 executes an application program 1011 stored in the storage unit 101, thereby realizing each functional unit.

[0021] The user registration control unit 1041 performs processing to store information about users who wish to use the service according to the present disclosure in the user table 1012. The information stored in the user table 1012 is generated when a user opens a web page operated by a service provider from any information processing terminal, enters information into a predetermined input form, and transmits the information to the server 10. The user registration control unit 1041 stores the received information in a new record in the user table 1012, completing the user registration. This allows the user stored in the user table 1012 to use the service. Before the user registration control unit 1041 registers the user information in the user table 1012, the service provider may conduct a predetermined examination to restrict whether or not the user is permitted to use the service. The user ID may be any character string or number that can identify the user, any character string or number desired by the user, or may be automatically set by the user registration control unit 1041.

[0022] <Configuration of User Terminal 20> The user terminal 20 is an information processing device operated by a user who uses a service. The user terminal 20 may be, for example, a mobile terminal such as a smartphone or tablet, a stationary personal computer (PC) or a laptop PC, or a wearable terminal such as a head mounted display (HMD) or a wristwatch terminal. The user terminal 20 includes a storage unit 201 , a control unit 204 , an input device 206 , and an output device 208 .

[0023] <Configuration of the storage unit 201 of the user terminal 20> The storage unit 201 of the user terminal 20 includes a user ID 2011 and an application program 2012 .

[0024] The user ID 2011 is the user's account ID. The user transmits the user ID 2011 from the user terminal 20 to the server 10. The server 10 identifies the user based on the user ID 2011 and provides the user with the service according to the present disclosure. The user ID 2011 includes information such as a session ID temporarily assigned by the server 10 to identify the user using the user terminal 20.

[0025] The application program 2012 may be stored in advance in the storage unit 201, or may be configured to be downloaded from a web server or the like operated by a service provider via a communication IF. The application programs 2012 include applications such as a web browser application. The application program 2012 includes an interpreted programming language such as JavaScript (registered trademark) that runs on a web browser application stored on the user terminal 20.

[0026] <Configuration of the control unit 204 of the user terminal 20> The control unit 204 of the user terminal 20 includes an input control unit 2041 and an output control unit 2042. The control unit 204 executes an application program 2012 stored in the storage unit 201, thereby realizing each functional unit.

[0027] <Configuration of the input device 206 of the user terminal 20> The input device 206 of the user terminal 20 includes a camera 2061 , a microphone 2062 , a position information sensor 2063 , a motion sensor 2064 , and a touch device 2065 .

[0028] <Configuration of the output device 208 of the user terminal 20> The output device 208 of the user terminal 20 includes a display 2081 and a speaker 2082 .

[0029] <Configuration of generated AI50> Generative AI50 refers to large-scale artificial intelligence models used in the field of natural language processing (NLP). These models are trained on large amounts of text data (web pages, books, articles, etc.) to understand patterns in human language and perform natural language generation (NLG) tasks effectively. Generative AI 50 is used in many NLP tasks, such as generating answers to specific questions, automatically generating sentences, summarizing text, translation, and sentiment analysis. It can also be used for a variety of applications, including education, entertainment, customer service, and product development. Examples of generative AI 50 include the following. In this disclosure, a large-scale language model that primarily outputs text information as output information will be described as a type of generative AI 50. OpenAI ChatGPT Google Gemini Stable Diffusion Midjourney The generated AI 50 may be configured to be implemented as a part of the functions of the server 10.

[0030] <System 1 Operation> Each process of the system 1 will be explained below. FIG. 7 is a flowchart showing the operation of the FAQ creation process.

[0031] <FAQ Creation Process> The FAQ creation process is a process of creating FAQs (Frequently Asked Questions) based on document data such as manuals. An FAQ, also called "Frequently Asked Questions," is information including text, images, photos, etc. regarding pairs of questions frequently asked by customers or employees within the company regarding products, services, or business content, and their answers.

[0032] <Overview of FAQ Creation Process> The FAQ creation process is a series of processes that accepts registration of document data such as manuals, extracts text information page by page from the accepted document data, creates a first FAQ using a large language model based on a part of the extracted text information (for example, a predetermined page), and creates a second FAQ from the questions of the created first FAQ and the entire document data.

[0033] <Details of FAQ Creation Process> The details of the FAQ creation process will be described below.

[0034] In step S , the processing unit 1042 of the server 10 executes a document acquisition step of acquiring predetermined document information. Specifically, the processing unit 1042 of the server 10 acquires document data by referring to the document table 1013. Note that the processing unit 1042 of the server 10 may acquire the document data stored in the path based on the information specifying the path on the network such as a shared drive where the pre-stored document data is stored. The document data may be stored in the server 10 in advance by an administrator or the like, who is an employee of an operator or the like providing the information processing service according to the present disclosure, by operating an information processing device. Alternatively, the processing unit 1042 of the server 10 may acquire the document data stored at an arbitrary location on the network or the Internet via the network N.

[0035] In step S102, the processing unit 1042 of the server 10 executes a first generation step of generating a first prompt for creating an interrogation sentence regarding the content described in a first portion, which includes a first portion that is part of the predetermined document information acquired in the document acquisition step. The first generation step is a step of generating a first prompt for creating FAQ data consisting of pairs of questions and answers regarding the content described in the first portion. The first generation step executes a step of generating a first prompt including a first portion which is a predetermined page of the predetermined document information acquired in the document acquisition step.

[0036] Specifically, the processing unit 1042 of the server 10 extracts a part (first portion) of the document data acquired in step S101. For example, when the document data is document data in which documents are stored in page units, the processing unit 1042 of the server 10 extracts the document data included in a predetermined page (first portion). For example, when first executing FAQ creation processing on predetermined document data, the first page of the document data may be extracted as the first portion. The processing unit 1042 of the server 10 generates a prompt for creating an FAQ consisting of pairs of questions and answers including the extracted portion (first portion) as follows. Note that the document data related to the extracted first portion is inserted into the "first portion of the document data" part of the prompt. Note that the inserted document data may include text data, image data, a combination of text data and image data, and the like. Also, in the present disclosure, although Q&A (pairs of questions and answers) is output, it may be configured to output only one of questions or answers.

[0037] <Prompt for creating <FAQ (abridged version)>> You are an expert in writing FAQs. Given a document, please create 10 Q&As based on the document. #Document 〔First portion of document data〕

[0038] The "first portion of document data" included in the prompt may include data obtained by applying any processing to the first portion, or may include data obtained by converting the first portion.

[0039] The processing unit 1042 of the server 10 executes a document conversion step of converting the predetermined document information acquired in the document acquisition step into structured data including a plurality of structured text data. For example, assume that the document data is PDF data consisting of image data (jpg, png format, etc.) of multiple pages obtained by scanning a paper document spanning multiple pages. In this case, the document data for the first part may be text data related to a character string written on a specific page obtained by applying OCR (Optical Character Recognition) to the image data of the specific page (first part). Typically, text data obtained by applying OCR consists of multiple string information pieces consisting of pairs of coordinates and text, but the text data obtained by combining these multiple string information pieces may also be used as document data for the first part. The processing unit 1042 of the server 10 may convert the text data into structured data. The structured data is the same as the structured data items in the page table 1014. Specifically, the processing unit 1042 of the server 10 may convert the text data related to the first portion into structured data using machine learning, deep learning, generative AI, or any other artificial intelligence model.

[0040] The processing unit 1042 of the server 10 stores the document ID of the document data acquired in step S101 and each of the multiple page data obtained by dividing the document data in the document ID and page data fields of a new record in the page table 1014, respectively. The processing unit 1042 of the server 10 stores one or more structured text data obtained by converting the specified page data (stored in the page table 1014 in association with the specified page ID) in the structured data item of the record identified by the specified page ID in the page table 1014. In the present disclosure, a configuration in which document data is divided into multiple pages and each of the divided pages is converted into one or more structured text data is described as an example, but this is not limiting. For example, processing unit 1042 of server 10 may convert document data directly into one or more structured text data without dividing the document data into pages. In this case, the document data is associated with the one or more structured text data and stored in the structured data field of document table 1013.

[0041] The first generation step executes a step of generating a first prompt including first structured data consisting of one or more structured text data relating to a first portion of the structured data converted in the document conversion step. Specifically, the processing unit 1042 of the server 10 generates a prompt for creating the FAQ already described by inserting text data relating to the extracted first part and structured text data relating to the extracted first part into the prompt "first part of document data." For example, when the structured text data relating to the first part includes a plurality of structured text data consisting of chapters, sections, and paragraphs, the processing unit 1042 of the server 10 may include some or all of the plurality of structured text data in the prompt.

[0042] In step S103, the processing unit 1042 of the server 10 executes a first acquisition step of acquiring a predetermined question sentence that is output by inputting the first prompt generated in the first generation step to the generation AI. The first acquisition step executes a step of acquiring first FAQ data consisting of a question and answer pair including the predetermined question sentence. The processing unit 1042 of the server 10 transmits a request including the prompt generated in step S102 to a URL related to a predetermined API (Application Programming Interface) endpoint provided by the generation AI 50. The processing unit 1042 of the server 10 receives and obtains a response including the following FAQ (First FAQ data) from the generation AI 50.

[0043] <FAQ (Simplified version)> Q1. ··· A1. ··· Q2. ··· A2. ··· Q3. ··· A3. ···

[0044] In step S104, the processing unit 1042 of the server 10 executes a partial extraction step of extracting a second part, which is a part related to the predetermined question sentence obtained in the first acquisition step, from the predetermined document information obtained in the document acquisition step. Specifically, the processing unit 1042 of the server 10 extracts a part (second part) of the document data obtained in step S101 based on the first FAQ data (including at least one or more of the questions and answers such as Q1, A1, Q2, A2,... which are part of the first FAQ data) obtained in step S103. The first FAQ data may include at least one of the question or the answer. The details of the partial extraction step will be described below. Note that the second part of the document data may include the first part of the document data. Also, the second part of the document data may be a part other than the first part of the document data (a part that does not include the first part).

[0045] <Second part extraction step (First embodiment)> The partial extraction step executes a step of extracting a second part including at least one of the pages before or after a predetermined page from the predetermined document information. Specifically, the processing unit 1042 of the server 10 may extract, as the second part, document data relating to pages before and after the predetermined page (first part) acquired in step S101. This is because, in general, descriptions on pages (second parts) before and after the predetermined page (first part) are generally related to the description on the predetermined page. Note that if the predetermined page is the first (first page), it is possible to extract only the subsequent pages as the second part, and if the predetermined page is the last, it is possible to extract only the previous pages as the second part.

[0046] <Second Part Extraction Step (Second Embodiment)> The part extraction step executes a step of extracting a second part, which is a part related to the first FAQ data acquired in the first acquisition step, from the predetermined document information acquired in the document acquisition step. Specifically, the processing unit 1042 of the server 10 divides the document data acquired in step S101 into a plurality of parts (pages, chapters, sections, paragraphs, etc.). The processing unit 1042 of the server 10 calculates the similarity between the first FAQ data and the plurality of parts. Any similarity index can be used for the similarity, such as cosine similarity, Jaccard similarity, n-gram similarity, or the inverse of the Levenshtein distance. The processing unit 1042 of the server 10 extracts a predetermined number of parts in descending order of similarity, or one or more parts whose similarity is equal to or greater than a predetermined value, as parts (second parts) related to the first FAQ data.

[0047] The part extraction step executes a step of extracting a second part from the structured data converted in the document conversion step, the second part including second structured data consisting of one or more structured text data similar to the specified question acquired in the first acquisition step. Specifically, the processing unit 1042 of the server 10 converts the document data acquired in step S101 into structured text data. The conversion of structured data has already been described in step S102. The processing unit 1042 of server 10 calculates the similarity between the first FAQ data and a plurality of structured text data (chapters, sections, items) included in the document data. The processing unit 1042 of server 10 extracts a predetermined number of structured text data in descending order of similarity and one or more structured text data with a similarity equal to or higher than a predetermined value as a portion (second portion) related to the first FAQ data.

[0048] In step S104, the processing unit 1042 of server 10 executes a second generation step of generating a second prompt for creating an answer sentence for a predetermined question sentence, including the second portion extracted in the partial extraction step. The second generation step includes the second portion extracted in the partial extraction step and the first FAQ data, and executes a step of generating a second prompt for creating FAQ data obtained by improving the first FAQ data. Specifically, the processing unit 1042 of server 10 generates a prompt for creating a FAQ consisting of a pair of questions and answers, including the first FAQ data and the extracted portion (second portion), as follows. In the "first FAQ data" part of the prompt, the first FAQ data is inserted, and in the "second part of the document data" part, the document data related to the extracted second part is inserted. The inserted document data may include text data, image data, a combination of text data and image data, and the like.

[0049] <Prompt for creating <FAQ (detailed version)>> You are an expert in writing FAQs. Given a document and a question, please output an improved version of the question sentence and a kind and detailed answer based on the content of the document. <A #Document 〔Second part of the document data〕 #Question 〔First FAQ data〕

[0050] In step S105, the processing unit 1042 of the server 10 executes a second acquisition step of acquiring a predetermined response sentence output by inputting the second prompt generated in the second generation step to the generation AI. The second acquisition step executes a step of acquiring second FAQ data including a predetermined response sentence obtained by improving the first FAQ data. The processing unit 1042 of the server 10 transmits a request including the prompt generated in step S102 to a URL related to a predetermined API endpoint provided by the generation AI 50. The processing unit 1042 of the server 10 receives and acquires a response including the following FAQ (second FAQ data) from the generation AI 50. The first FAQ is generated based on the first part, while the second FAQ is generated in consideration of the data of the first FAQ and the second part of the document data. Therefore, it is possible to acquire a high-quality FAQ including more detailed content compared to the FAQ (abbreviated version).

[0051] <FAQ (detailed)> Q1. ··· A1. ··· Q2. ··· A2. ··· Q3. ··· A3. ···

[0052] In step S105, the processing unit 1042 of the server 10 executes a FAQ storage step of associating and storing a predetermined question sentence and a predetermined response sentence. Specifically, the processing unit 1042 of the server 10 stores the page ID of the page related to the first part specified in step S102, the question and answer of the first FAQ, and the question and answer of the second FAQ in the items of page ID, first question data, first answer data, second question data, and second answer data of a new record in the FAQ table 1015. As a result, the first part (page) extracted in step S102 and the questions and answers of the first FAQ and the questions and answers of the second FAQ generated based on that page are stored in association with each other. Similarly, the questions and answers of the first FAQ and the questions and answers of the second FAQ may be stored in association with the first part (chapter, section, paragraph).

[0053] In step S106, processing unit 1042 of server 10 determines whether the first part identified in step S102 is the final page of the document data acquired in step S101. If the first part is a chapter, section, paragraph, or the like of structured text data, it may be configured to determine whether it is the final element (chapter, section, paragraph) of the document data acquired in step S101.

[0054] If the processing unit 1042 of the server 10 does not determine that it is the last page (last element), it increments (adds 1 to) the page number of the predetermined page and executes the processes from step S102 to step S105. If the processing unit 1042 of the server 10 determines that it is the last page (last element), it ends the process. This makes it possible to create a first FAQ and a second FAQ based on the contents of all pages from the first page to the last page of the document data acquired in step S101. Although the present disclosure has disclosed an example in which the FAQ creation process is executed for all pages of document data, it is not necessary to execute the FAQ creation process for all pages. The FAQ creation process may be executed excluding pages that are not related to the FAQ, such as the table of contents and author biographies. Alternatively, the FAQ creation process may be configured so that each step is executed for each arbitrary chapter, section, or paragraph included in the structured text data, rather than for each page.

[0055] <Basic computer hardware configuration> 8 is a block diagram showing the basic hardware configuration of a computer 90. The computer 90 includes at least a processor 901, a main memory device 902, an auxiliary memory device 903, and a communication IF 991 (interface), which are electrically connected to one another by a communication bus 921.

[0056] The processor 901 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, and the like.

[0057] The main memory device 902 is used to temporarily store programs, data to be processed by the programs, etc. For example, it is a volatile memory such as a DRAM (Dynamic Random Access Memory).

[0058] The auxiliary storage device 903 is a storage device for saving data and programs, such as a flash memory, a hard disk drive (HDD), a magneto-optical disk, a CD-ROM, a DVD-ROM, or a semiconductor memory.

[0059] The communication IF 991 is an interface for inputting and outputting signals for communicating with other computers via a network using wired or wireless communication standards. The network is composed of the Internet, a LAN, various mobile communication systems constructed by wireless base stations, etc. For example, the network includes 3G, 4G, and 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks (e.g., Wi-Fi (registered trademark)) that can connect to the Internet via a predetermined access point. In the case of a wireless connection, communication protocols include, for example, Z-Wave (registered trademark), ZigBee (registered trademark), and Bluetooth (registered trademark). In the case of a wired connection, the network also includes a direct connection using a USB (Universal Serial Bus) cable, etc.

[0060] It should be noted that the computer 90 can be virtually realized by distributing all or part of each hardware configuration across multiple computers 90 and interconnecting them via a network. In this way, the computer 90 is a concept that includes not only a computer 90 housed in a single housing or case, but also a virtualized computer system.

[0061] <Basic functional configuration of computer 90> The following describes the functional configuration of a computer realized by the basic hardware configuration (FIG. 8) of the computer 90. The computer includes at least the functional units of a control unit, a storage unit, and a communication unit.

[0062] The functional units of the computer 90 can also be realized by distributing all or part of the functional units among multiple computers 90 interconnected via a network. The computer 90 is a concept that includes not only a single computer 90 but also a virtualized computer system.

[0063] The control unit is realized by the processor 901 reading out various programs stored in the auxiliary storage device 903, expanding them in the main storage device 902, and executing processing in accordance with the programs. The control unit can realize functional units that perform various types of information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.

[0064] The functions performed by the components described herein may be implemented in circuitry or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to perform the described functions. A processor includes transistors and other circuits and is considered to be circuitry or processing circuitry. A processor may also be a programmed processor that executes programs stored in memory. In this specification, a circuitry, unit, or means is hardware that is programmed to realize or performs the described functions, which may be any hardware disclosed herein or any hardware known to be programmed to realize or perform the described functions. If the hardware is a processor considered to be a type of circuitry, the circuitry, means, or unit is a combination of the hardware and software used to configure the hardware and / or processor.

[0065] The storage unit is realized by a main storage device 902 and an auxiliary storage device 903. The storage unit stores data, various programs, and various databases. Furthermore, the processor 901 can allocate a storage area corresponding to the storage unit in the main storage device 902 or the auxiliary storage device 903 in accordance with the programs. Furthermore, the control unit can cause the processor 901 to execute processes for adding, updating, and deleting data stored in the storage unit in accordance with the various programs.

[0066] A database refers to a relational database, which manages data sets called masters and tables in a tabular format structurally defined by rows and columns, by relating them to each other. In a database, a table is called a table, a master, a column in a table is called a column, and a row in a table is called a record. In a relational database, relationships between tables and masters can be set and associated. Typically, each table and each master has a column set as a primary key to uniquely identify a record, but setting a primary key to a column is not essential. The control unit can cause the processor 901 to add, delete, or update records in specific tables and masters stored in the storage unit according to various programs. Furthermore, by storing data, various programs, and various databases in the storage unit, it can be considered that the information processing device and information processing system according to the present disclosure have been manufactured.

[0067] Note that the databases and masters in this disclosure may include any data structure in which information is structurally defined (such as a list, dictionary, associative array, or object). The data structure also includes data that can be considered as a data structure by combining data with functions, classes, methods, etc. written in any programming language.

[0068] The communication unit is realized by the communication IF 991. The communication unit realizes a function of communicating with other computers 90 via a network. The communication unit can receive information transmitted from other computers 90 and input the information to the control unit. The control unit can cause the processor 901 to execute information processing on the received information in accordance with various programs. In addition, the communication unit can transmit information output from the control unit to other computers 90.

[0069] <Additional Notes> The matters described in the above embodiments will be supplemented below.

[0070] (Appendix 1) a first generation step (S102) of generating a first prompt for creating a question related to the content described in the first portion, the first portion being a part of the specified document information acquired in the document acquisition step; a first acquisition step (S103) of acquiring the specified question by inputting the first prompt generated in the first generation step into a generation AI; a part extraction step (S104) of extracting a second portion from the specified document information acquired in the document acquisition step that is related to the specified question acquired in the first acquisition step; a second generation step (S104) of generating a second prompt for creating a question, the second portion being extracted in the part extraction step, the second prompt being used to create a question; a second acquisition step (S105) of acquiring the specified answer by inputting the second prompt generated in the second generation step into a generation AI; and an FAQ storage step (S105) of associating and storing the specified question and the specified answer. As a result, after creating a predetermined question based on a first portion of a document, a more detailed predetermined answer to the question can be obtained by taking into account a second portion of the document other than the first portion that is related to the question. Based on a question based on one portion of a document, a more detailed answer can be created by referencing other portions of the document. Therefore, an appropriate FAQ can be created based on the document.

[0071] (Appendix 2) The program described in Appendix 1 executes the following steps: a first generation step (S102) is a step of generating a first prompt for creating FAQ data consisting of question and answer pairs regarding the content described in the first part; and a first acquisition step (S103) is a step of acquiring first FAQ data consisting of question and answer pairs including a predetermined question sentence. This allows concise FAQ data consisting of pairs of questions and answers to be created based on the first part of the document.

[0072] (Appendix 3) The program described in Appendix 2, wherein the second generation step (S104) is a step of generating a second prompt for creating FAQ data that includes the second part extracted in the part extraction step and the first FAQ data and is an improvement on the first FAQ data, and the second acquisition step (S105) is a step of acquiring second FAQ data that includes a predetermined answer sentence and is an improvement on the first FAQ data. This allows more detailed FAQ data to be created by referring to the second part other than the first part of the document related to at least the question contained in the concise FAQ data.

[0073] (Appendix 4) A program described in Appendix 2 or 3, wherein the part extraction step (S104) is a step of extracting a second part from the specified document information acquired in the document acquisition step, which is the part related to the first FAQ data acquired in the first acquisition step. This allows for the creation of higher quality FAQ data.

[0074] (Appendix 5) The program according to any one of appendices 1 to 4, wherein the first generating step (S102) is a step of generating a first prompt including a first portion that is a predetermined page of the predetermined document information acquired in the document acquiring step. This allows for creating a suitable FAQ based on a document, even for a document in page units such as a PDF (Portable Document Format).

[0075] (Appendix 6) 6. The program according to claim 5, wherein the part extraction step (S104) is a step of extracting a second part including at least one of a page before or after the predetermined page from the predetermined document information. This allows for the creation of higher quality FAQ data by taking into consideration the pages before and after the first part, which is the predetermined page.

[0076] (Appendix 7) A program described in any of Appendices 1 to 6, wherein a processor executes a document conversion step (S102) in which the processor converts the specified document information acquired in the document acquisition step into structured data including a plurality of structured text data, and a first generation step (S102) is a step in which a first prompt is generated including first structured data consisting of one or more structured text data relating to a first portion of the structured data converted in the document conversion step. This allows you to create higher quality FAQ data by converting documents into text data structured by headings such as chapters, sections, and paragraphs in markdown, XML, HTML, etc.

[0077] (Appendix 8) The program described in Appendix 7, wherein the part extraction step (S104) is a step of extracting a second part from the structured data converted in the document conversion step, the second part including second structured data consisting of one or more structured text data similar to the specified question acquired in the first acquisition step. This allows for the creation of higher quality FAQ data by using one or more structured text data similar to a given question.

[0078] (Appendix 9) A computer-implemented method comprising a processor and a memory, wherein the processor performs all of the steps performed in the invention according to any one of appendices 1 to 8. As a result, after creating a predetermined question based on a first portion of a document, a more detailed predetermined answer to the question can be obtained by taking into account a second portion of the document other than the first portion that is related to the question. Based on a question based on one portion of a document, a more detailed answer can be created by referencing other portions of the document. Therefore, an appropriate FAQ can be created based on the document.

[0079] (Appendix 10) An information processing device comprising a control unit and a storage unit, wherein the control unit executes all of the steps executed in the invention according to any one of Supplementary Note 1 to Supplementary Note 8. As a result, after creating a predetermined question based on a first portion of a document, a more detailed predetermined answer to the question can be obtained by taking into account a second portion of the document other than the first portion that is related to the question. Based on a question based on one portion of a document, a more detailed answer can be created by referencing other portions of the document. Therefore, an appropriate FAQ can be created based on the document.

[0080] (Appendix 11) A system comprising means for performing all steps performed in any of the inventions according to any one of appendixes 1 to 8. As a result, after creating a predetermined question based on a first portion of a document, a more detailed predetermined answer to the question can be obtained by taking into account a second portion of the document other than the first portion that is related to the question. Based on a question based on one portion of a document, a more detailed answer can be created by referencing other portions of the document. Therefore, an appropriate FAQ can be created based on the document. [Explanation of symbols]

[0081] 1 System, 10 Server, 101 Memory Unit, 104 Control Unit, 106 Input Device, 108 Output Device, 20 User Terminal, 201 Memory Unit, 204 Control Unit, 206 Input Device, 208 Output Device, 50 Generation AI, 501 Memory Unit, 504 Control Unit, 506 Input Device, 508 Output Device

Claims

1. A program to be executed by a computer having a processor and a storage unit, the processor: a document acquisition step of acquiring predetermined document information; a first generation step of generating a first prompt for creating a question regarding content described in a first portion, the first portion being a part of the predetermined document information acquired in the document acquisition step; a first acquisition step of acquiring a predetermined question sentence to be output by inputting the first prompt generated in the first generation step into a generation AI; a part extraction step of extracting a second part, which is a part related to the predetermined question acquired in the first acquisition step, from the predetermined document information acquired in the document acquisition step; a second generation step of generating a second prompt including the second portion extracted in the portion extraction step, for generating an answer sentence to the predetermined question sentence; a second acquisition step of acquiring a predetermined answer sentence to be output by inputting the second prompt generated in the second generation step into a generation AI; an FAQ storage step of storing the predetermined question sentence and the predetermined answer sentence in association with each other; A program that executes.

2. the first generation step is a step of generating the first prompt for creating FAQ data consisting of pairs of questions and answers regarding the content described in the first portion; the first acquisition step is a step of acquiring first FAQ data consisting of pairs of questions and answers including the predetermined question sentence, To execute The program according to claim 1.

3. the second generation step is a step of generating the second prompt for creating FAQ data that includes the second part extracted in the part extraction step and the first FAQ data and that improves the first FAQ data; The second acquisition step is a step of acquiring second FAQ data including the predetermined answer sentence obtained by improving the first FAQ data. The program according to claim 2.

4. The part extraction step is a step of extracting the second part, which is a part related to the first FAQ data acquired in the first acquisition step, from the predetermined document information acquired in the document acquisition step. The program according to claim 2.

5. the first generating step is a step of generating the first prompt including the first portion, which is a predetermined page of the predetermined document information acquired in the document acquiring step; The program according to claim 1.

6. the portion extracting step is a step of extracting the second portion from the predetermined document information, the second portion including at least one of a page before or a page after the predetermined page; The program according to claim 5.

7. the processor: a document conversion step of converting the predetermined document information acquired in the document acquisition step into structured data including a plurality of structured text data; Run the first generating step is a step of generating the first prompt including first structured data consisting of one or more structured text data relating to the first portion of the structured data converted in the document converting step; The program according to claim 1.

8. the part extraction step is a step of extracting, from the structured data converted in the document conversion step, the second part including second structured data consisting of one or more structured text data similar to the predetermined question sentence acquired in the first acquisition step; The program according to claim 7.

9. A method implemented on a computer having a processor and a memory, wherein the processor performs all of the steps performed in the invention according to any one of claims 1 to 8.

10. 9. An information processing device comprising a control unit and a storage unit, wherein the control unit executes all of the steps executed in the invention according to any one of claims 1 to 8.

11. A system comprising means for executing all steps performed in the invention according to any one of claims 1 to 8.

Images