Information processing device, information processing program, and information processing method

Abstract

Reduce the effort required to create deliverables in system development. [Solution] The information processing device of the present application includes a generation unit that generates a question by inputting a second prompt, which is a prompt that includes instructions to generate a question for a user who wishes to generate a deliverable to improve a first prompt that is input to a generation AI to generate a deliverable in system development, into the generation AI.

Description

[Technical Field]

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

[0002] Conventionally, various technologies for supporting developers in system development have been known. For example, there is a technology for supporting the management of documents (hereinafter, sometimes referred to as "deliverables") generated in each development step of software or system development processes (Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-47732 Summary of the Invention [Means for solving the problem]

[0004] The information processing device of the present application includes a generation unit that generates a question by inputting a second prompt, which is a prompt to be input to a generation AI to generate a deliverable in system development, into the generation AI, the second prompt including an instruction to generate a question for a user who wishes to generate the deliverable in order to improve the first prompt. [Brief explanation of the drawings]

[0005] [Figure 1] FIG. 1 is a diagram showing an overview of information processing according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an overview of information processing according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 5]FIG. 5 is a diagram illustrating an example of a prompt generation sheet according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a prompt generation sheet according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of a prompt generation sheet according to the embodiment. [Figure 8] FIG. 8 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device. DETAILED DESCRIPTION OF THE INVENTION

[0006] Hereinafter, an information processing device, an information processing program, and an information processing method according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, the information processing program, and the information processing method according to the present application are not limited to these embodiments. Furthermore, the same components in the following embodiments will be denoted by the same reference numerals, and duplicated descriptions will be omitted. Furthermore, hereinafter, AI (artificial intelligence) and machine learning model will be treated as synonymous terms.

[0007] (Embodiment) 1. Introduction Conventionally, various technologies are known to support those involved in system development (e.g., developers). For example, there is known a technology that supports the management of documents (hereinafter, sometimes referred to as "deliverables") generated in each development step of a software or system development process (Patent Document 1). However, conventional technologies that support the creation of deliverables in system development have not been sufficient.

[0008] System development deliverables include system requirements specifications and business requirements specifications. Traditionally, creating these deliverables required developers to collect, organize, and document the vast amount of information necessary for the creation of the deliverable. For example, creating a deliverable for a specific system development process (e.g., a system requirements specification) required information on deliverables corresponding to downstream processes (e.g., business requirements specifications). Therefore, traditionally, developers had to collect, organize, and document information on deliverables corresponding to downstream processes (hereinafter sometimes referred to as "downstream information"). Furthermore, traditionally, the developer and the client requesting the system development had to engage in multiple dialogues to collect, organize, and document the information necessary for the creation of the deliverable. As such, creating deliverables in system development traditionally required a great deal of effort.

[0009] In contrast, the information processing device 100 according to the embodiment uses a generation AI to generate questions for a user desiring to generate a deliverable and repeatedly obtains answers from the user. Specifically, the information processing device 100 generates a question by inputting a second prompt, which is a prompt including an instruction to generate a question for a user desiring to generate a deliverable in system development, to the generation AI. As a result, the information processing device 100 presents the question generated by the generation AI to the user and obtains an answer to the question from the user. Here, the question for the user corresponds, for example, to a question from a developer to a client who has requested system development. Obtaining an answer from the user corresponds, for example, to a developer obtaining an answer to a question from a client who has requested system development. As a result, the information processing device 100 can reduce the effort required to obtain information necessary to create a deliverable. For example, the information processing device 100 can reduce the effort required for multiple question-and-answer sessions between a client who has requested system development and a developer. Therefore, the information processing device 100 can reduce the effort required to create a deliverable in system development.

[0010] FIG. 1 is a diagram illustrating an overview of information processing according to an embodiment. FIG. 1 is a diagram illustrating an overview of information processing performed by an information processing device 100 according to an embodiment. In FIG. 1, the information processing device 100 acquires information (hereinafter, sometimes referred to as "downstream information") on a deliverable (e.g., a business requirements definition document) corresponding to a process downstream of a deliverable (e.g., a system requirements definition document) of a predetermined process desired by a user. The information processing device 100 inputs a first prompt 4, which is a prompt to be input to a generation AI to generate a deliverable in system development, a question 6 for a user who desires to generate a deliverable to improve the first prompt 4, and a second prompt 2, which includes instructions for generating a suggestion 5, which is reference information for the user to use when answering the question 6, to the generation AI, thereby generating the first prompt 4, the suggestion 5, and the question 6.

[0011] Furthermore, when the information processing device 100 generates a first prompt 4, a suggestion 5, and a question 6, it generates a prompt generation sheet, which is a spreadsheet including the first prompt 4, the suggestion 5, and the question 6. When the information processing device 100 generates the prompt generation sheet, it provides the prompt generation sheet to the user terminal 10 of the user. The user views the prompt generation sheet and inputs an answer 7 to the question 6 into the prompt generation sheet. The user terminal 10 transmits the prompt generation sheet with the answer 7 to the question 6 inputted to the information processing device 100. Furthermore, the information processing device 100 acquires the prompt generation sheet including the answer 7 from the user terminal 10 of the user. Furthermore, the information processing device 100 acquires the answer 7 from the prompt generation sheet. Furthermore, when the information processing device 100 acquires the answer 7, it generates an updated second prompt including the first prompt 4, the question 6, and the answer 7. Furthermore, the information processing device 100 inputs the updated second prompt into the generation AI to generate an improved first prompt, a new suggestion, and a new question.

[0012] FIG. 2 is a diagram illustrating an overview of information processing according to an embodiment. In FIG. 2, the information processing device 100 inputs an initial second prompt to a generation AI to generate a first first prompt 4-1, a first proposal 5-1, and a first question 6-1. Here, the initial second prompt may include an instruction statement that assigns the role of prompt designer to the generation AI. Furthermore, the initial second prompt may include an instruction statement instructing the generation AI to generate a prompt that best meets the user's needs in accordance with predetermined conditions. For example, the initial second prompt may include an instruction statement instructing the generation AI to use reference information as input information for the generation AI as a predetermined condition to generate an improved first prompt, proposal, and question by improving the first prompt. Furthermore, the initial second prompt may include an instruction statement instructing the generation AI to check the reference information as a predetermined condition. Furthermore, the initial second prompt may include, as reference information, information indicating the user's desire to create a desired deliverable.

[0013] When the information processing device 100 generates a first first prompt 4-1, a first suggestion 5-1, and a first question 6-1, it generates a first prompt generation sheet (see, for example, FIG. 5 described later) including the first first prompt 4-1, the first suggestion 5-1, and the first question 6-1. Furthermore, when the information processing device 100 generates the first prompt generation sheet, it provides the first prompt generation sheet to the user terminal 10 of the user. The user views the first prompt generation sheet and inputs a first answer 7-1 to the first question 6-1 into the first prompt generation sheet. The user terminal 10 transmits the first prompt generation sheet with the first answer 7-1 inputted to the information processing device 100. Furthermore, the information processing device 100 acquires the first prompt generation sheet including the first answer 7-1 from the user terminal 10 of the user. Furthermore, the information processing device 100 acquires the first answer 7-1 from the first prompt generation sheet.

[0014] Furthermore, when the information processing device 100 obtains the first answer 7-1, it generates an updated second prompt including the first first prompt 4-1, the first question 6-1, and the first answer 7-1. Here, the updated second prompt includes information included in the initial state of the second prompt. Furthermore, the updated second prompt may include, as reference information, an instruction statement instructing the generation AI to generate an improved first prompt, suggestion, and question by improving the first prompt using, as input information to the generation AI, the first prompt before improvement (e.g., the first first prompt 4-1), the question previously generated by the generation AI (e.g., the first question 6-1), and the answer to the question previously generated by the generation AI (e.g., the first answer 7-1). Furthermore, the information processing device 100 inputs the updated second prompt to the generation AI to generate an improved second first prompt 4-2, a second suggestion 5-2, and a second question 6-2.

[0015] Furthermore, when the information processing device 100 generates a second first prompt 4-2, a second suggestion 5-2, and a second question 6-2, it generates a second prompt generation sheet (see, for example, FIG. 6 described later) including the second first prompt 4-2, the second suggestion 5-2, and the second question 6-2. When the information processing device 100 generates the second prompt generation sheet, it provides the second prompt generation sheet to the user terminal 10 of the user. The user views the second prompt generation sheet and inputs a second answer 7-2 to the second question 6-2 into the second prompt generation sheet. The user terminal 10 transmits the second prompt generation sheet with the second answer 7-2 inputted to the information processing device 100. Furthermore, the information processing device 100 acquires the second prompt generation sheet including the second answer 7-2 from the user terminal 10 of the user. Furthermore, when the information processing device 100 obtains the second answer 7-2, it generates an updated second prompt including the second first prompt 4-2, the second question 6-2, and the second answer 7-2. Furthermore, the information processing device 100 inputs the updated second prompt into the generation AI to generate an improved third first prompt 4-3, a third suggestion 5-3, and a third question 6-3.

[0016] In this way, when the information processing device 100 generates the nth first prompt 4-n (n is a natural number greater than or equal to 1), the nth suggestion 5-n, and the nth question 6-n, it generates an nth prompt generation sheet including the nth first prompt 4-n, the nth suggestion 5-n, and the nth question 6-n. When the information processing device 100 generates the nth prompt generation sheet, it provides the nth prompt generation sheet to the user terminal 10 of the user. The user views the nth prompt generation sheet and inputs the nth answer 7-n to the nth question 6-n into the prompt generation sheet. The user terminal 10 transmits the nth prompt generation sheet with the nth answer 7-n inputted to the information processing device 100. The information processing device 100 also acquires the nth prompt generation sheet including the nth answer 7-n from the user terminal 10 of the user. Furthermore, when the information processing device 100 obtains the nth answer 7-n, it generates an updated second prompt including the nth first prompt 4-n, the nth question 6-n, and the nth answer 7-n. Furthermore, the information processing device 100 inputs the updated second prompt into the generation AI to generate an improved (n+1)th first prompt 4-(n+1), the (n+1)th suggestion 5-(n+1), and the (n+1)th question 6-(n+1). Note that as n increases, the content of the nth first prompt 4-n becomes more specific (see FIG. 7, which will be described later). Also, as n increases, the content and number of the nth questions 6-n converge (see FIG. 7, which will be described later). The information processing device 100 may terminate the process of generating a prompt generation sheet when n reaches a predetermined threshold (e.g., 10).

[0017] Furthermore, when the information processing device 100 finishes the process of generating a prompt generation sheet, it acquires an nth first prompt that has been improved from the last generated prompt generation sheet. The information processing device 100 then inputs the nth first prompt and downstream information into the generation AI to generate a deliverable in system development. This allows the information processing device 100 to reduce the effort required to create a deliverable in system development. Furthermore, the information processing device 100 can generate a higher quality deliverable based on the first prompt that has been improved to have more specific content.

[0018] Furthermore, in the past, when a deliverable was created in system development, it was necessary to evaluate the created deliverable by having the development manager or the like review the deliverable. As such, in the past, evaluating a deliverable in system development required a lot of effort. In contrast, the information processing device 100 evaluates a deliverable in system development using a generative AI. This allows the information processing device 100 to reduce the effort required to evaluate a deliverable in system development.

[0019] The first to fifth prompts appearing in this specification may be user prompts. The first to fifth prompts may also be prompts generated by combining a system prompt with a user prompt. The first to fifth prompts may also be system prompts.

[0020] A system prompt is a prompt that provides formal instructions to an AI model. Specifically, the prompt may include, for example, the language to be used, the attributes of the AI ​​model that the AI ​​model should consider, the processing to be performed by the AI ​​model, and the output format. The language to be used may be, for example, Japanese, English, or French. The attributes of the AI ​​model that the AI ​​model should consider may be, for example, software engineer, programmer, project manager, or system architect. The processing to be performed by the AI ​​model may be, for example, reviewing a requirements specification document, assisting in the review of the contents of the requirements specification document, or organizing the items described in the requirements specification document. The output format may be, for example, plain text, structured data (JSON format, XML format, YAML format, etc.), or unstructured data (PDF, etc.).

[0021] A user prompt is a prompt that provides substantive instructions to an AI model. A user prompt may be prepared for each type of processing that the AI ​​model is to perform. Specifically, for example, there may be a user prompt that causes the AI ​​model to detect NG words, including similar expressions, contained in the requirements specification document, a user prompt that causes the AI ​​model to confirm that all items that should be included in the requirements specification document are included, or a user prompt that causes the AI ​​model to interactively collect content that should be included in the requirements specification document.

[0022] An execution prompt may be generated by combining a system prompt and a user prompt. For example, the execution prompt may simply be a combination of a system prompt and a user prompt, and a heading such as <user prompt> or <system prompt> may be added to each. The execution prompt may be selected arbitrarily, taking into consideration the learning content and degree of learning of the AI ​​model. For example, a user prompt that detects prohibited words included in a requirements specification document, including similar expressions, may specify, for example, the prohibited words to be detected, an instruction to suggest words with similar meanings to the prohibited words, the number of words to be suggested, designation of words to be excluded from similar prohibited words, whether duplication is allowed, etc. Furthermore, when outputting structured data, the specific structure and headings of the data may be specified.

[0023] [2. Information Processing System Configuration] Fig. 3 is a diagram showing an example of the configuration of an information processing system 1 according to an embodiment. As shown in Fig. 3, the information processing system 1 according to the embodiment includes a user terminal 10 and an information processing device 100. The user terminal 10 and the information processing device 100 are connected to each other via a predetermined communication network (network N) so as to be able to communicate with each other via wired or wireless communication.

[0024] The user terminal 10 is, for example, an information processing device used by a user who is a system developer. For example, the user terminal 10 is an information processing device such as a desktop PC (Personal Computer) or a notebook PC. The user terminal 10 may also be a smart device such as a smartphone or a tablet. The user terminal 10 displays information received from the information processing device 100 or the like using a web browser or an application.

[0025] The information processing device 100 is an information processing device that performs information processing according to the embodiment. The information processing device 100 is realized by a server device, a cloud system, etc. For example, the information processing device 100 may perform the information processing according to the embodiment in accordance with an information processing method realized by an information processing program according to the embodiment.

[0026] 3. Configuration of Information Processing Device 4 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. The information processing device 100 according to the embodiment includes a communication unit 110, a storage unit 120, and a control unit .

[0027] (Communication unit 110) The communication unit 110 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the user terminal 10. For example, the communication unit 110 is realized by a NIC (Network Interface Card), an antenna, or the like.

[0028] (Storage unit 120) The storage unit 120 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. Specifically, the storage unit 120 stores an information processing program according to the embodiment. The storage unit 120 also stores information related to the generation AI. For example, the storage unit 120 stores information related to large language models (LLMs) as the generation AI. The generation AI may be provided in the form of software as a service (SaaS).

[0029] (control unit 130) The control unit 130 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the information processing device 100 using RAM as a work area. The control unit 130 is also a controller, and is realized, for example, by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0030] The control unit 130 has an acquisition unit 131, a generation unit 132, and a provision unit 133 as functional units, and may realize or execute the information processing actions described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 4, and may have other configurations as long as they perform the information processing described below. Furthermore, each functional unit indicates a function of the control unit 130, and does not necessarily have to be physically distinct.

[0031] (Acquisition part 131) The acquisition unit 131 acquires various information. The acquisition unit 131 acquires downstream information extracted from downstream deliverables corresponding to processes downstream of the process corresponding to the deliverable among the processes of system development. The acquisition unit 131 acquires downstream information extracted from deliverables (e.g., business requirements definition documents) corresponding to processes downstream of the deliverables (e.g., system requirements definition documents) of a predetermined process desired by the user. Specifically, the acquisition unit 131 acquires the downstream deliverables from a deliverable database that stores information about deliverables. For example, the acquisition unit 131 acquires downstream deliverables generated in the form of a spreadsheet. For example, the acquisition unit 131 acquires a spreadsheet that is a business requirements definition document corresponding to a process downstream of the process corresponding to the system requirements definition document. Next, the acquisition unit 131 extracts text contained in each cell from the spreadsheet that is the downstream deliverable as downstream information. For example, the acquisition unit 131 extracts text from each cell of the spreadsheet that is the business requirements definition document.

[0032] (Generation unit 132) The generation unit 132 generates various types of information. The generation unit 132 inputs a second prompt (second prompt 2 in FIG. 1) that is a prompt including an instruction to generate a question (question 6 in FIG. 1) for a user who desires to generate a deliverable to improve a first prompt (first prompt 4 in FIG. 1), which is a prompt to be input to the generation AI to generate a deliverable in system development, to the generation AI, thereby generating a question for improving the first prompt. Specifically, the generation unit 132 inputs the second prompt (second prompt 2 in FIG. 1) that includes an instruction to generate the first prompt (first prompt 4 in FIG. 1) to the generation AI to generate the first prompt, and inputs the second prompt that includes an instruction to generate a question (question 6 in FIG. 1) to improve the generated first prompt to the generation AI, thereby generating a question for improving the generated first prompt.

[0033] Furthermore, the generation unit 132 inputs a second prompt (second prompt 2 in FIG. 1) including an instruction to generate a proposal (proposal 5 in FIG. 1) that serves as reference information for the user when responding to a question (question 6 in FIG. 1) for improving the first prompt into the generation AI, thereby generating a proposal. For example, the generation unit 132 inputs a second prompt including an instruction to generate a question (question 6 in FIG. 1) into the generation AI to generate the question, and inputs a second prompt including an instruction to generate a proposal (proposal 5 in FIG. 1) that serves as reference information for the user when responding to the generated question into the generation AI, thereby generating a proposal.

[0034] Here, the generative AI is a generative AI that generates text. For example, the generative AI is a language model that can generate sentences using natural language processing. For example, the generative AI is a large-scale language model (LLM). For example, the generative AI is a generative pre-trained transformer (GPT).

[0035] For example, the generation unit 132 may input a second prompt including an instruction statement assigning the role of prompt designer to the generation AI to generate the first prompt, question, and proposal. The generation unit 132 may also input a second prompt including an instruction statement instructing the generation AI to generate a prompt that best meets the user's needs in accordance with predetermined conditions to generate the first prompt, question, and proposal. For example, the generation unit 132 may input a second prompt including an instruction statement instructing the generation AI to generate an improved first prompt, suggestion, and question by improving the first prompt, using reference information as input information for the generation AI as a predetermined condition, to generate the improved first prompt, suggestion, and question. The generation unit 132 may also input a second prompt including an instruction statement instructing the generation AI to check reference information as a predetermined condition to generate the first prompt, question, and proposal. For example, the generation unit 132 may input, as reference information, a second prompt including information indicating the user's desire to create a desired deliverable to the generation AI, and generate a first prompt, a question, and a proposal. The generation unit 132 may also input, as reference information, a second prompt including the first prompt before improvement, a question previously generated by the generation AI, and an answer to the question previously generated by the generation AI, and generate the first prompt, a question, and a proposal. The generation unit 132 may also input, as reference information, a second prompt including an instruction to write the improved first prompt, proposal, and question in a predetermined structured data format (e.g., JSON format, etc.), and generate the first prompt, a question, and a proposal. The generation unit 132 may also input, as reference information, a second prompt including downstream information to the generation AI, and generate the first prompt, a question, and a proposal.

[0036] Furthermore, when the generation unit 132 generates a first prompt, a suggestion, and a question, it generates a prompt generation sheet, which is a spreadsheet that includes the first prompt, the suggestion, and the question. FIGS. 5 to 7 are diagrams showing examples of prompt generation sheets according to the embodiment. FIG. 5 shows a prompt generation sheet SS1 (the first prompt generation sheet described in FIG. 2) that is generated the first time. In FIG. 5, the generation unit 132 generates a prompt generation sheet SS1 that includes a cell P11 that includes the first first prompt, a cell S11 that includes the first suggestion, a plurality of cells Q11 to Q15 that include each of a plurality of first questions, and a plurality of cells A11 to A15 into which the user inputs answers to each of the plurality of first questions.

[0037] As shown in cell P11 in FIG. 5, the generation unit 132 generates the following text as the first prompt: "You would like to create a system requirements specification document. To do so, detailed information such as the system's purpose, functions, performance requirements, user interface, system interface, data management, and constraints is required. Could you please provide this information?". Also, as shown in cell S11 in FIG. 5, the generation unit 132 generates the following text as the first suggestion: "To create a system requirements specification document, detailed information about the specific system is required. Therefore, I suggest that you format the prompt in the form of a specific question so that the user can provide specific information."

[0038] 5, the generation unit 132 generates the text "What is the purpose of the system?" as the first question. In response to this question, the user inputs the text "an e-commerce site for purchasing smartphones" as shown in cell A11 of FIG. 5. In response to this question, the user inputs text indicating three functions of the smartphone, namely, a smartphone search function, a smartphone comparison function, and a purchase function, as well as text indicating an overview and details of each of the three functions as shown in cell A12 of FIG. 5. In response to this question, the user inputs text indicating three functions of the smartphone, namely, a smartphone search function, a smartphone comparison function, and a purchase function, as well as text indicating an overview and details of each of the three functions as shown in cell Q13 of FIG. 5. In response to this question, the user inputs text indicating the performance requirements of the system as shown in cell A13 of FIG. 5. In response to this question, the user inputs text indicating the processing of user screen operations within one second as shown in cell A13 of FIG. 5. In response to this question, the user inputs text indicating the processing of user screen operations within one second as shown in cell Q14 of FIG. 5. In response to this question, the user inputs the text "A user interface in a browser will be provided for PCs and smartphones," as shown in cell A14 of Fig. 5. Furthermore, as shown in cell Q15 of Fig. 5, the generation unit 132 generates the text "What is the system interface like?" as the first question. In response to this question, the user inputs the text "Payment processing will be performed by the payment management system, so payment information will be linked to the payment management system when purchasing a smartphone," as shown in cell A15 of Fig. 5.

[0039] Fig. 6 shows the prompt generation sheet SS2 generated for the second time (the second prompt generation sheet described in Fig. 2). In Fig. 6, the generation unit 132 generates the prompt generation sheet SS2 that includes a cell P21 that includes a second first prompt that is an improvement on the first first prompt, a cell S21 that includes a second suggestion, a plurality of cells Q21 to Q26 that include each of a plurality of questions for the second time, and a plurality of cells A21 to A26 into which the user inputs their answers to each of the plurality of questions.

[0040] As shown in cell P21 in Figure 6, the generation unit 132 generates the following text as the second first prompt: "You want to create a system requirements specification document for an e-commerce site where smartphones are purchased. To do so, you need detailed information such as the system's purpose, functions, performance requirements, user interface, system interface, data management, and constraints. Your system provides three main functions: searching, comparing, and purchasing smartphones. Its performance requirement is that user screen operations must be completed within one second. The user interface will be provided via a browser for PCs and smartphones, and data management will be performed via an RDB. There are no particular constraints. Payment processing will be performed via a payment management system, and payment information will be linked to the payment management system when a smartphone is purchased. Based on this information, could you please tell me more detailed requirements?" In this way, the second first prompt is improved to be more specific than the first first prompt, taking into account the content of the first question and the first answer. Furthermore, as shown in cell S21 in FIG. 6, the generation unit 132 generates the following text as a second proposal: "More specific information is needed about the system's functions. For example, if there were functions for specific operation flows and screen designs, such as what search conditions can be set in the smartphone's search function, or what information can be compared in the comparison function, more specific requirements definition would be possible."

[0041] 6, the generation unit 132 generates the text "What kind of search conditions can be set in the search function of the smartphone?" as the second question. In response to this question, the user inputs the text "manufacturer, model name, price (range), color (multiple selections possible), storage capacity" as shown in cell A21 of FIG. 6. In response to this question, the user inputs the text "manufacturer, CPU, price (range), color (multiple selections possible), storage capacity, resolution, camera performance" as shown in cell A22 of FIG. 6. In response to this question, the user inputs the text "manufacturer, CPU, price (range), color (multiple selections possible), storage capacity, resolution, camera performance" as shown in cell Q23 of FIG. 6. In response to this question, the generation unit 132 generates the text "What payment methods can be selected in the purchase function?" as shown in cell A23 of FIG. 6. Furthermore, as shown in cell Q24 of FIG. 6 , the generation unit 132 generates the text "What are the details of the user interface?" as the second question. In response to this question, the user inputs the text "The screen will be displayed in HTML," as shown in cell A24 of FIG. 6 . Furthermore, as shown in cell Q25 of FIG. 6 , the generation unit 132 generates the text "What are the details of the system interface?" as the second question. In response to this question, the user inputs the text "Communication will be via HTTPS, and requests and responses will be in JSON format," as shown in cell A25 of FIG. 6 . Furthermore, as shown in cell Q26 of FIG. 6 , the generation unit 132 generates the text "Regarding data management, what kind of data will be managed?" as the second question. In response to this question, the user inputs the text "User information, payment information, and user access history," as shown in cell A26 of FIG. 6 . In this way, the content of the second question is more specific than the content of the first question, taking into account the second suggestion.

[0042] Figure 7 shows the prompt generation sheet SS5 generated for the fifth time. Figure 7 shows how, as n increases, the content of the first prompt becomes more specific and the number and content of questions converge. In Figure 7, the generation unit 132 generates a prompt generation sheet SS5 that includes cell P51 containing the fifth first prompt that was improved from the fourth first prompt, cell S51 containing the fifth suggestion, multiple cells Q51 to Q53 containing each of the multiple questions from the fifth time, and multiple cells A51 to A53 into which the user enters their answers to each of the multiple questions.

[0043] As shown in cell P51 in Figure 7, the generation unit 132 outputs the following as the first prompt for the fifth time: "You want to create a system requirements specification document for an e-commerce site where smartphones are purchased. To do this, you need detailed information such as the system's purpose, functions, performance requirements, user interface, system interface, data management, and constraints. Your system provides three main functions: searching for, comparing, and purchasing smartphones. The search function allows you to set conditions such as manufacturer, model name, price (range), color (multiple selections possible), storage capacity, and resolution. The comparison function allows you to compare manufacturer, CPU, price (range), color (multiple selections possible), storage capacity, resolution, and camera performance. The purchase function allows you to select convenience store payment, lump-sum payment from Company A, or credit card. You have a performance requirement that user screen operations be completed within one second. The user interface is displayed on the screen in HTML." The system is provided via a browser for PCs and smartphones. The system interface communicates via HTTPS, and requests and responses are in JSON format. Data management is performed using an RDB, managing user information, payment information, and user access history. There are no particular constraints. Payment processing is performed using a payment management system, and payment information is linked to the payment management system when a smartphone is purchased. System operation and maintenance requirements include server, machine, and application health monitoring, application error log monitoring, and backups that are acquired by date and time and stored for one week. System security requirements include completing an internal vulnerability assessment before release and resolving critical issues. The system also has a redundant configuration to address errors and exceptional situations. Based on this information, the text "Could you please provide more detailed requirements?" is generated. Thus, the content of the first prompt in the fifth session is significantly more specific than the first prompt in the first session and the first prompt in the second session, taking into account the questions and answers from the first through fourth sessions.Furthermore, as shown in cell S51 in FIG. 7, the generation unit 132 generates the following text as the fifth suggestion: "To make the prompt more specific, it would be a good idea to add specific procedures for operating and maintaining the system, detailed standards for security requirements, and specific countermeasures for errors and exceptional situations."

[0044] 7, the generation unit 132 generates the text "What are the specific procedures for system operation and maintenance?" as the fifth question. In response to this question, as shown in cell A51 of FIG. 7, the user inputs text indicating that the monitoring requirements are server alive monitoring, alive monitoring of various MWs, and alive monitoring of applications, and that the maintenance requirements are to provide a maintenance in progress screen in consideration of maintenance. In response to this question, as shown in cell Q52 of FIG. 7, the generation unit 132 generates the text "What are the detailed criteria for security requirements?" as the fifth question. In response to this question, the user inputs the text "None in particular" as shown in cell A52 of FIG. 7. In response to this question, as shown in cell Q53 of FIG. 7, the generation unit 132 generates the text "What are the specific countermeasures for errors and exceptional situations?" as the fifth question. In response to this question, the user inputs the text "None in particular" as shown in cell A53 of FIG. 7. In this way, the content of the fifth question converges compared to the content of the first and second questions. Also, the number of questions asked in the fifth round will become smaller (converge) compared to the number of questions asked in the first and second rounds.

[0045] (Provider 133) The providing unit 133 provides various types of information. The providing unit 133 transmits various types of information to the user terminal 10 of the user. Specifically, the providing unit 134 provides the prompt generation sheet generated by the generating unit 132 to the user terminal 10 of the user. For example, when a prompt generation sheet is generated by the generating unit 132, the providing unit 134 transmits the prompt generation sheet to the user terminal 10 of the user. When the user terminal 10 receives the prompt generation sheet, it displays the prompt generation sheet on its screen. The user views the prompt generation sheet displayed on the screen of the user terminal 10 and inputs an answer to a question into the prompt generation sheet. Furthermore, in response to the user's operation to transmit the prompt generation sheet to the information processing device 100, the user terminal 10 transmits the prompt generation sheet with the answer to the question input to the information processing device 100. The acquiring unit 131 acquires the prompt generation sheet including the answer from the user terminal 10 of the user. Furthermore, the acquiring unit 131 acquires the answer from the prompt generation sheet. In this way, the acquiring unit 131 acquires the user's answer to the question.

[0046] Furthermore, when an answer is acquired by the acquisition unit 131, the generation unit 132 generates an updated second prompt including the first prompt, a question, and the answer. Furthermore, the generation unit 132 inputs the updated second prompt to the generation AI to generate an improved first prompt, suggestion, and question. For example, the generation unit 132 inputs, together with the answer, a second prompt including an instruction to generate an improved first prompt that has been improved based on the content of the answer to the generation AI to generate the improved first prompt.

[0047] Furthermore, the generation unit 132 inputs the improved first prompt into the generation AI to generate a deliverable. For example, the generation unit 132 determines whether the number of times a prompt generation sheet has been generated has reached a predetermined threshold (e.g., 10 times). If the generation unit 132 determines that the number of times a prompt generation sheet has been generated has reached the predetermined threshold, the generation unit 132 obtains an improved first prompt from the last generated prompt generation sheet. If the generation unit 132 obtains an improved first prompt, the generation unit 132 inputs the improved first prompt into the generation AI to generate a deliverable.

[0048] Furthermore, the generation unit 132 inputs the downstream information into the generation AI to generate a deliverable. For example, the generation unit 132 inputs the downstream information as input information for the generation AI together with an instruction statement instructing the generation AI to generate a deliverable, thereby generating the deliverable. The generation unit 132 inputs the improved first prompt and the downstream information into the generation AI to generate the deliverable.

[0049] Furthermore, the generation unit 132 generates a deliverable described in a predetermined structured data format (for example, JSON format, etc.). For example, the generation unit 132 inputs a prompt to the generation AI to instruct it to generate a deliverable described in the predetermined structured data format, and generates a deliverable described in the predetermined structured data format.

[0050] The generation unit 132 also inputs a third prompt, which is a prompt including an instruction to acquire synonyms of the NG word in the deliverable, to the generation AI, thereby acquiring the synonyms of the NG word. For example, the generation unit 132 inputs a third prompt, which instructs the generation AI to generate a list of synonyms for the expression "NG word," to acquire the list of synonyms of the NG word. The generation unit 132 also inputs a fourth prompt, which is a prompt including an instruction to acquire a determination result as to whether the deliverable contains the NG word and its synonym, to the generation AI, thereby acquiring the determination result as to whether the deliverable contains the NG word and its synonym. For example, the generation unit 132 inputs the fourth prompt, which instructs the generation AI to generate a determination result as to whether the deliverable contains the expression "NG word" and words included in the list of synonyms of the NG word, and the deliverable, to the generation AI, thereby acquiring the determination result as to whether the deliverable contains the NG word and its synonym.

[0051] Furthermore, the generation unit 132 inputs a fifth prompt, which is a prompt including an instruction to obtain a determination result as to whether each of the plurality of designated items to be included in the deliverable is included in the deliverable, to the generation AI, thereby obtaining the determination result as to whether each of the plurality of designated items is included in the deliverable. For example, the generation unit 132 inputs a fifth prompt, which instructs the generation AI to generate a list of the plurality of designated items and a determination result as to whether each of the plurality of designated items is included in the deliverable, to the generation AI, thereby obtaining the determination result as to whether each of the plurality of designated items is included in the deliverable.

[0052] [4. Effects] As described above, the information processing device 100 according to the embodiment includes the generation unit 132. The generation unit 132 generates a question by inputting a second prompt, which is a prompt including an instruction to generate a question for a user who desires to generate a deliverable in system development, to the generation AI. The second prompt is a prompt to be input to the generation AI in order to generate a deliverable in system development.

[0053] As a result, the information processing device 100 can present a question generated by the generation AI to a user and obtain an answer to the question from the user. Here, the question to the user corresponds, for example, to a question from a developer to a client who has requested system development. Furthermore, obtaining an answer from the user corresponds, for example, to a developer obtaining an answer to a question from a client who has requested system development. As a result, the information processing device 100 can reduce the effort required to obtain information necessary to create a deliverable. For example, the information processing device 100 can reduce the effort required for multiple question-and-answer sessions between a client who has requested system development and a developer. Therefore, the information processing device 100 can reduce the effort required to create a deliverable in system development. Furthermore, because the information processing device 100 can reduce the effort required to create a deliverable in system development, it can contribute to achieving Goal 9 of the Sustainable Development Goals (SDGs), "Build resilient infrastructure, promote inclusive and sustainable industrialization, and build resilient technological infrastructure."

[0054] In addition, the generation unit 132 inputs a second prompt including instructions to generate a first prompt into the generation AI to generate the first prompt, and inputs a second prompt including instructions to generate a question for improving the generated first prompt into the generation AI to generate a question for improving the generated first prompt.

[0055] As a result, the information processing device 100 can generate prompts to be input into the generation AI to generate deliverables in system development, present questions to the user to improve the generated prompts, and obtain answers to the questions from the user.

[0056] Information processing device 100 also includes an acquisition unit 131. Acquisition unit 131 acquires a user's answer to a question. Generation unit 132 inputs the answer and a second prompt including an instruction to generate an improved first prompt that has been improved based on the content of the answer to a generation AI, thereby generating an improved first prompt.

[0057] This allows information processing device 100 to obtain an answer to the question from the user. Furthermore, information processing device 100 can generate an improved prompt based on the answer obtained from the user, thereby generating a higher quality deliverable.

[0058] Furthermore, the generation unit 132 inputs a second prompt, which includes an instruction to generate a proposal that is reference information for the user when answering the question, to the generation AI, and generates a proposal.

[0059] This allows the information processing device 100 to help the user input an appropriate answer to the question.

[0060] Furthermore, the generation unit 132 inputs the improved first prompt into the generation AI to generate a deliverable.

[0061] This allows information processing device 100 to generate a higher quality product based on a prompt that has been improved to have more specific content.

[0062] Furthermore, the generating unit 132 generates a deliverable described in a predetermined structured data format.

[0063] This allows the information processing device 100 to generate a deliverable described in a predetermined structured data format.

[0064] The acquisition unit 131 also acquires downstream information extracted from downstream deliverables corresponding to processes downstream of the process corresponding to the deliverable among the processes of the system development. The generation unit 132 inputs the downstream information into a generation AI to generate the deliverable.

[0065] This allows the information processing device 100 to reduce the effort required to collect downstream information.

[0066] In addition, the generation unit 132 inputs a third prompt, which is a prompt including an instruction to obtain synonyms of the NG words in the deliverable, to the generation AI to obtain the synonyms of the NG words, and inputs a fourth prompt, which is a prompt including an instruction to obtain a determination result as to whether the deliverable contains the NG words and synonyms, to the generation AI to obtain the determination result as to whether the deliverable contains the NG words and synonyms.

[0067] This allows the information processing device 100 to reduce the effort required to evaluate whether or not the deliverable contains NG words and synonyms.

[0068] In addition, the generation unit 132 inputs a fifth prompt, which is a prompt including an instruction to obtain a determination result as to whether each of the multiple specified items to be included in the deliverable is included in the deliverable, into the generation AI, and obtains a determination result as to whether each of the multiple specified items is included in the deliverable.

[0069] This allows information processing device 100 to reduce the effort required to evaluate whether or not each of the multiple designated items that should be included in the deliverable is included in the deliverable.

[0070] [5. Hardware Configuration] The information processing device 100 according to the embodiment described above is realized by, for example, a computer 1000 configured as shown in Fig. 8. Fig. 8 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 100. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0071] The CPU 1100 operates and controls each unit based on programs stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0072] The HDD 1400 stores programs executed by the CPU 1100, data used by these programs, etc. The communication interface 1500 receives data from other devices via a predetermined communication network and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the predetermined communication network.

[0073] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0074] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1200. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded program. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0075] For example, when the computer 1000 functions as the information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 130. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0076] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0077] [6. Other] Furthermore, among the processes described in the above embodiments and modifications, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0078] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0079] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0080] The present disclosure may be implemented as, for example, a software program that runs on a personal computer or an application that runs on a smartphone. The method and program according to the present disclosure may also be provided in a SaaS format. [Explanation of symbols]

[0081] 100 Information processing device 110 Communications Department 120 Storage section 130 Control Unit 131 Acquisition Department 132 Generation part 133 Provision Department

Claims

1. a generation unit that inputs a second prompt, which is a prompt to be input to a generation AI to generate a deliverable in system development, to the generation AI, the second prompt including an instruction to generate a question for a user who desires to generate the deliverable in order to improve the first prompt; and an acquisition unit that acquires the user's answer to the question; Equipped with The generation unit inputting the second prompt, which includes an instruction to generate an improved first prompt based on the content of the answer, together with the answer, to the generation AI to generate the improved first prompt; Information processing device.

2. A generation unit is provided that inputs a second prompt, which is a prompt input to a generation AI to generate a deliverable in system development, into the generation AI to generate the question, the second prompt including an instruction to generate a question for a user who desires to generate the deliverable in order to improve the first prompt; The generation unit inputting the second prompt, which includes an instruction to generate a proposal that is reference information for the user to answer the question, to the generation AI to generate the proposal; Information processing device.

3. The generation unit inputting the second prompt, which includes an instruction for generating the first prompt, into the generation AI to generate the first prompt; and inputting the second prompt, which includes an instruction for generating the question for improving the generated first prompt, into the generation AI to generate the question for improving the generated first prompt.

3. The information processing device according to claim 1.

4. The generation unit inputting the improved first prompt into the generating AI to generate the deliverable; The information processing device according to claim 1 .

5. The generation unit generating the deliverable described in a predetermined structured data format; The information processing device according to claim 4 .

6. The acquisition unit acquiring downstream information extracted from a downstream deliverable corresponding to a process downstream of the process corresponding to the deliverable among the processes of the system development; The generation unit inputting the downstream information into the generation AI to generate the deliverable; The information processing device according to claim 4 .

7. The generation unit inputting a third prompt, which is a prompt including an instruction to acquire synonyms of the NG word in the deliverable, into the generation AI to acquire the synonyms of the NG word; inputting a fourth prompt, which is a prompt including an instruction to acquire a determination result as to whether the NG word and the synonym are included in the deliverable, into the generation AI to acquire a determination result as to whether the NG word and the synonym are included in the deliverable; The information processing device according to claim 4 .

8. The generation unit inputting a fifth prompt, which is a prompt including an instruction to obtain a determination result as to whether each of a plurality of specified items to be included in the deliverable is included in the deliverable, into the generation AI, and obtaining a determination result as to whether each of the plurality of specified items is included in the deliverable; The information processing device according to claim 4 .

9. a generation procedure for inputting a second prompt, which is a prompt to be input to the generation AI to generate a deliverable in system development, into the generation AI, the second prompt including an instruction to generate a question for a user who desires to generate the deliverable in order to improve the first prompt; and an acquisition step of acquiring the user's answer to the question; on the computer, The generating procedure includes: inputting the second prompt, which includes an instruction to generate an improved first prompt based on the content of the answer, together with the answer, to the generation AI to generate the improved first prompt; Information processing program.

10. A method for generating a deliverable in system development by inputting a second prompt, which is a prompt to be input to a generation AI to generate the deliverable in system development, and which includes an instruction to generate a question for a user who desires to generate the deliverable in order to improve the first prompt, into the generation AI, and having a computer execute a generation procedure to generate the question; The generating procedure includes: inputting the second prompt, which includes an instruction to generate a proposal that is reference information for the user to answer the question, to the generation AI to generate the proposal; Information processing program.

11. An information processing method realized by a program executed by an information processing device, a generation process of inputting a second prompt, which is a prompt to be input to the generation AI to generate a deliverable in system development, into the generation AI, the second prompt including an instruction to generate a question for a user who desires to generate the deliverable in order to improve the first prompt; an acquisition step of acquiring an answer from the user to the question; Including, The generating step includes: inputting the second prompt, which includes an instruction to generate an improved first prompt based on the content of the answer, together with the answer, to the generation AI to generate the improved first prompt; An information processing method including:

12. An information processing method realized by a program executed by an information processing device, comprising: a generation step of inputting a second prompt, which is a prompt to be input to a generation AI to generate a deliverable in system development, into the generation AI, the second prompt including an instruction to generate a question for a user who desires to generate the deliverable in order to improve the first prompt, and generating the question; The generating step includes: inputting the second prompt, which includes an instruction to generate a proposal that is reference information for the user to answer the question, to the generation AI to generate the proposal; Information processing methods.

Images