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

Abstract

This invention provides an information processing device, method, and program that assist in the creation of documentation related to system development. [Solution] The information processing device includes: an input unit that receives input of summary information indicating an outline of the document to be generated; a first generation unit that generates item information corresponding to each item in the document to be generated based on the summary information; a determination unit that determines the similarity between past documents and the document to be generated for each item based on the item information corresponding to items contained in past documents and the item information generated by the first generation unit; an output unit that outputs a predetermined number of first past documents for each item, starting with the one with the highest similarity; and a second generation unit that generates new item information corresponding to each item in the document to be generated based on the item information corresponding to items contained in the first past documents output by the output unit and selected by the user, and the item information generated by the first generation unit.

Description

Technical Field

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

Background Art

[0002] Conventionally, there is known a technology that supports the management of documents generated in each development step of software development or system development processes (hereinafter may be referred to as "development documents"). For example, design document information related to a project and discussion information related to records of project activities are associated with each other. Further, a technology is known that maintains the number of pages of a software design document created as the project progresses, based on the associated information.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Means for Solving the Problems

[0004] The information processing device according to the present application includes: an input unit that receives input of summary information indicating an outline of the documents to be generated relating to the target system development; a first generation unit that generates item information corresponding to each item of the documents to be generated based on the summary information; a determination unit that determines the similarity between the past documents and the documents to be generated for each item based on item information corresponding to items contained in past documents which are documents relating to past system development and item information generated by the first generation unit; an output unit that outputs a predetermined number of first past documents for each item, starting with the one with the highest similarity; and a second generation unit that generates new item information corresponding to each item of the documents to be generated based on item information corresponding to items contained in the first past documents selected by the user from among the first past documents output by the output unit and item information generated by the first generation unit. [Brief explanation of the drawing]

[0005] [Figure 1] Figure 1 is a diagram illustrating the development process of a system and the development documents, which are the deliverables corresponding to each development process. [Figure 2] Figure 2 shows an example of the configuration of an information processing device according to the embodiment. [Figure 3] Figure 3 shows an example of a UI screen according to the embodiment. [Figure 4] Figure 4 shows an example of a UI screen according to the embodiment. [Figure 5] Figure 5 shows an example of a UI screen according to the embodiment. [Figure 6] Figure 6 shows an example of a UI screen according to the present invention. [Figure 7] Figure 7 shows an example of a UI screen according to the embodiment. [Figure 8] Figure 8 shows an example of a UI screen according to this embodiment. [Figure 9] Figure 9 shows an example of a UI screen according to this embodiment. [Figure 10] Figure 10 shows an example of a UI screen according to the embodiment. [Figure 11] Figure 11 shows an example of a UI screen according to the embodiment. [Figure 12] Figure 12 shows an example of a UI screen according to the embodiment. [Figure 13] Figure 13 shows an example of a UI screen according to the embodiment. [Figure 14] Figure 14 shows an example of a UI screen according to the embodiment. [Figure 15] Figure 15 is a flowchart showing an example of information processing by the information processing device according to the embodiment. [Figure 16] Figure 16 shows an example of a hardware configuration. [Modes for carrying out the invention]

[0006] The following describes in detail, with reference to the drawings, the embodiments for implementing the information processing device, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing device, information processing method, and information processing program according to the present application. Furthermore, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant descriptions are omitted.

[0007] (Embodiment) [1. Introduction] First, Figure 1 will be used to explain the system development process and the development documents, which are the deliverables corresponding to each development process. Figure 1 is a diagram for explaining the system development process and the development documents, which are the deliverables corresponding to each development process. Figure 1 shows an example of a system development process generally known as the waterfall model. Waterfall system development is divided into multiple development processes, such as business requirements definition, system requirements definition, basic design, detailed design, system implementation (manufacturing), unit testing, integration testing, comprehensive testing, and user acceptance testing, and each development process has a specific sequence.

[0008] Furthermore, in system development, the development personnel and development managers (hereinafter sometimes referred to as "development personnel") create development documents, which are deliverables corresponding to each development stage of the system development. When the development personnel complete the creation of the development documents, the development stage corresponding to the development documents is completed. In other words, the status of the creation of the development documents (hereinafter also referred to as "progress status") corresponds to the progress status of the development stage corresponding to the development documents. Note that the status of the creation of the development documents can also be rephrased as the status of the completion of the development documents.

[0009] Here, "development documentation" is a general term for the deliverables in system development. Specifically, for example, development documentation may include development plans, requirements definitions, various design documents, various specifications, coding conventions, review results, or meeting minutes created in each development stage of system development. Although the term "document" is used for explanatory purposes, as mentioned above, development documentation is a concept that encompasses various deliverables created as results of system development and is not limited to document-format files. Development documentation may be data recorded in any data format (file format) as long as it relates to the deliverables in system development.

[0010] Although not illustrated in Figure 1, a development process for determining a system development plan, i.e., a development planning development process, may be included before the business requirement definition development process. The development document that is the deliverable corresponding to the development planning development process is a development plan document.

[0011] In Figure 1, the system development process starts with the business requirement definition development process. In the business requirement definition development process, development stakeholders interview the requester about the business processes that they wish to implement via systemization, and compile the business requirements into a business requirement definition document. That is, the development document that is the deliverable corresponding to the business requirement definition development process is the business requirement definition document. The business requirements are compiled from perspectives including what tasks or issues in the business form the background for requiring system development, and what kind of business flow is desired to be realized as the final goal. Business requirements are defined from the perspective of the requester and users.

[0012] Subsequent to the business requirement definition development process, the process proceeds to the system requirement definition development process. In the system requirement definition development process, development stakeholders compile system requirements such as functions and performance to be installed in the system into a system requirement definition document, in order to realize the contents compiled in the business requirement definition document. That is, the development document that is the deliverable corresponding to the system requirement definition development process is the system requirement definition document. The system requirements are classified into functional requirements that define functions to be implemented, and non-functional requirements that define contents to be satisfied other than functions, such as performance, stability, and security level.

[0013] Subsequent to the system requirement definition development process, the process proceeds to the basic design development process. In the basic design development process, development stakeholders specify the functions to be implemented in the system in order to realize the contents compiled in the system requirement definition document, and compile them into a basic design document. That is, the development document that is the deliverable corresponding to the basic design development process is the basic design document. The basic design is also referred to as external design, and development stakeholders determine the specifications of the appearance (the external part of the system) such as screens used by the requester and users, from the perspective of the requester and users who actually use the system.

[0014] Further, after the development process of the basic design, the process proceeds to the development process of the detailed design. In the development process of the detailed design, development personnel perform detailed design on how to implement the functions to be implemented in the system in order to realize the contents compiled in the basic design document, and compile the results into a detailed design document. That is, the development document which is the deliverable corresponding to the development process of the detailed design is the detailed design document. The detailed design is also referred to as internal design, and the development personnel determine the internal specifications of the system from the viewpoint of the developer.

[0015] Further, after the development process of the detailed design, the process proceeds to the development process of system implementation (manufacturing). In the development process of system implementation (manufacturing), development personnel perform programming based on the detailed design document to create source code constituting the system to be developed. For example, the development document which is the deliverable corresponding to the development process of system implementation (manufacturing) may be source code. The system to be developed is created by combining a plurality of pieces of source code. For example, the source code is source code corresponding to a module that is a program component.

[0016] Further, after the development process of system implementation (manufacturing), the process proceeds to the development process of unit testing. In the development process of unit testing, development personnel verify whether the program operates normally on a per-function basis. In the development process of unit testing, testing is performed to check whether modules, which are program components, function without problems. In other words, unit testing is testing performed to confirm the quality of each module included in the system to be developed. The content verified in the unit testing corresponds to the content of the detailed design document. In addition, the development personnel compile information related to the verification content of the unit testing into a unit test specification. That is, the development document which is the deliverable corresponding to the development process of unit testing is the unit test specification.

[0017] Next, following the unit testing development phase, the development process moves on to the integration testing phase. In the integration testing phase, development personnel verify that the functions are combined and work correctly. In addition to testing the combination of modules, integration testing also verifies the integration with external modules. In other words, integration testing is performed to verify the quality of the combination of multiple modules included in the system under development. The content verified in integration testing corresponds to the content of the basic design document. Furthermore, development personnel compile information on the verification content of the integration testing into an integration test specification document. That is, the development document that corresponds to the integration testing development phase is the integration test specification document.

[0018] Next, following the integration testing development phase, the development process moves on to the system testing phase. In the system testing phase, development personnel verify that all functions are combined and the system operates correctly. In other words, system testing is conducted to confirm the overall quality of the system under development. The content verified in system testing corresponds to the content of the system requirements definition document. Furthermore, development personnel compile information regarding the verification content of system testing into a system testing specification document. That is, the development document that corresponds to the system testing development phase is the system testing specification document.

[0019] Next, following the development phase of integrated testing, the development phase moves on to the user acceptance testing phase. In the user acceptance testing phase, development personnel verify whether the system functions correctly in the actual operating environment used by the client or users. In other words, user acceptance testing is a test that checks the quality of the system under development in the actual operating environment used by the client or users. The content verified in user acceptance testing corresponds to the content of the business requirements definition document. Furthermore, development personnel compile information regarding the verification content of user acceptance testing into a user acceptance testing specification document. That is, the development document that corresponds to the user acceptance testing phase is the user acceptance testing specification document.

[0020] The development documents according to this embodiment may be direct deliverables in development, such as development plans, requirements specifications, various design documents (screen design documents, interface design documents, program design documents, non-functional design documents), and test specifications (specifications for various tests such as unit tests, integration tests, system tests, and acceptance tests). They may also be indirect deliverables in development, such as minutes of meetings related to development and checklists containing items to be checked during reviews. Furthermore, the development documents may be written in natural language. In addition, the development documents can be rephrased as documents related to system development.

[0021] Traditionally, technologies have been known to support the management of development documents (documents related to system development) as described above. In contrast, technologies to support the creation of system development documents have not been sufficient until now.

[0022] Therefore, the information processing device according to this embodiment accepts input summary information that shows an overview of the document to be generated related to the target system development. The information processing device then generates item information corresponding to each item in the document to be generated based on the summary information. The information processing device also determines the similarity between the past document and the document to be generated for each item, based on the item information corresponding to items contained in past documents, which are documents related to past system development, and the generated item information. The information processing device then outputs a predetermined number of first past documents for each item, starting with those with the highest similarity. The information processing device then generates new item information corresponding to each item in the document to be generated, based on the item information corresponding to items contained in the first past document selected by the user from among the output first past documents, and the generated item information. In this way, the information processing device can support the creation of documents related to system development.

[0023] Here, the items in this embodiment may refer to a list of items described in a system development document. Specifically, for example, an item may be each of the headings listed in the table of contents of a system development document. Furthermore, the item information in this embodiment may refer to text or the like that describes the items described in the system development document.

[0024] Specifically, for example, if a document related to system development is a system requirements specification document, the items included in the system requirements specification document would be items such as "background objectives," "business requirements," and "assumptions and constraints." The system requirements specification document would then describe in natural language specific information such as the background and objectives of the system development, the requirements for the system, and the assumptions and constraints in the development and operation process of the system. In other words, an item refers to each of the headings such as "background objectives," "business requirements," and "assumptions and constraints," and item information can be text that describes specific information such as the background and objectives of the system development, the requirements for the system, and the assumptions and constraints in the development and operation process of the system. It should be noted that although the explanation was given using the example of a system requirements specification document related to system development, the content of items and item information is not limited to the example given above, and appropriate items and item information can be selected according to the content and purpose of the document related to system development. That is, for example, if a document related to system development is a development plan that describes a schedule, it is not necessary to generate items such as "business requirements."

[0025] The information processing device according to this embodiment may store the type of document relating to system development and one or more items described in the document relating to system development in association with each other.

[0026] [2. Configuration of the Information Processing Device] An example configuration of the information processing device 100 according to the embodiment will be described using Figure 2. Figure 2 is a diagram showing an example configuration of the information processing device 100 according to the embodiment. The information processing device 100 includes a communication unit 110, a storage unit 120, an input unit 130, an output unit 140, and a control unit 150.

[0027] The information processing device 100 is an information processing device that provides a service to support the generation of documents related to the target system development. For example, the information processing device 100 may be a server in a cloud environment (cloud server). Here, the documents to be generated are development documents that will be generated. The documents to be generated are development documents that the user desires to be created. The following explanation describes the case where the documents to be generated are system requirements specifications, but the documents to be generated are not limited to system requirements specifications. For example, the documents to be generated may be development documents other than system requirements specifications, such as development plans, business requirements specifications, basic design documents, detailed design documents, source code, unit test specifications, integration test specifications, comprehensive test specifications, and user acceptance test specifications.

[0028] (Communications Department 110) The communication unit 110 is implemented using a NIC (Network Interface Card), an antenna, etc. The communication unit 110 is connected to various networks by wired or wireless means, and for example, transmits and receives information with other information processing devices other than the information processing device 100.

[0029] (Storage unit 120) The memory unit 120 is implemented by, for example, a semiconductor memory element such as RAM (Random Access Memory) or flash memory, or a storage device such as a hard disk or optical disc. Specifically, the memory unit 120 stores an information processing program according to the embodiment. Furthermore, the memory unit 120 may store various types of information, not limited to the above. For example, the memory unit 120 stores information related to the generation model. The memory unit 120 also stores information related to past documents, which are documents related to past system development.

[0030] (Input section 130) The input unit 130 is an input device that receives various inputs from the outside. The input unit 130 is equipped with an operating device that receives input operations from the user. The operating device is, for example, a keyboard, mouse, or operation keys, a device for the user to perform various operations. If the information processing device 100 employs a touch panel, the touch panel is also included as an operating device. In this case, the user performs various operations by touching the screen with their finger or stylus. Alternatively, the operating device may be a voice input device (for example, a microphone) that receives input operations from the user's voice.

[0031] (Output section 140) The output unit 140 is a display device that displays various types of information. The output unit 140 may be, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display. If a touch panel is used in the information processing device 100, the output unit 140 may be an integrated device with the operating device of the input unit 130. The output unit 140 displays various types of information and provides it to the user. In the following description, the output unit 140 may be referred to as the screen.

[0032] Figure 3 shows an example of a UI screen according to the embodiment. In Figure 3, the output unit 140 displays a UI screen 10 that includes an area 11 where information that can identify the target system can be entered, an area 12 where summary information showing an overview of the documents to be generated related to the development of the target system can be entered, and a button 13. For example, the output unit 140 displays an area 11 that allows the user to select information that can identify a predetermined system from a list of information that can identify each of multiple systems. The input unit 130 accepts input of information that can identify the target system selected by the user from a list of information that can identify each of multiple systems.

[0033] In Figure 3, the output unit 140 displays an area 12 where summary information indicating an overview of the documents to be generated related to the target system development can be entered as text. The input unit 130 accepts input of summary information indicating an overview of the documents to be generated related to the target system development. As an example of a document to be generated, the input unit 130 accepts input of summary information indicating an overview of the system requirements definition document. For example, the input unit 130 accepts summary information, which is text entered by the user in area 12. For example, the input unit 130 accepts the operation to select button 13 when predetermined information has been entered in area 11 and area 12, respectively. When the input unit 130 accepts the operation to select button 13, it accepts the information entered in area 11 and area 12, respectively.

[0034] (Control unit 150) The control unit 150 is a controller, and is implemented, for example, by a CPU (Central Processing Unit) or MPU (Micro Processing Unit) executing various programs stored in the memory device inside the information processing device 100 using RAM as the working area. Alternatively, the control unit 150 is a controller and can be implemented, for example, by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).

[0035] The control unit 150 has a first generation unit 151, a determination unit 152, and a second generation unit 153 as functional units, and may realize or execute the information processing operations described below. Note that the internal configuration of the control unit 150 is not limited to the configuration shown in Figure 2, and other configurations are also possible as long as they perform the information processing described later. In addition, each functional unit represents the function of the control unit 150 and does not necessarily have to be physically separated.

[0036] (First generation unit 151) The first generation unit 151 generates item information corresponding to each item in the document to be generated, based on the summary information received by the input unit 130. The first generation unit 151 generates item information corresponding to each item in the document to be generated, based on the summary information. In other words, the first generation unit 151 generates multiple items of information corresponding to each of the multiple items included in the document to be generated, based on the summary information. For example, the first generation unit 151 generates item information corresponding to each item that is typically included in the document to be generated, based on the summary information.

[0037] For example, the first generation unit 151 inputs a prompt to the generation model, along with summary information, instructing it to generate item information corresponding to each item in the document to be generated, and generates item information corresponding to each item in the document to be generated. In other words, the first generation unit 151 inputs a prompt to the generation model, along with summary information, instructing it to generate multiple item information corresponding to each of the multiple items contained in the document to be generated, and generates multiple item information corresponding to each of the multiple items contained in the document to be generated. Here, the generation model is, for example, a text generation model that has been trained on data published on the internet. For example, the generation model may be implemented using AI (Artificial Intelligence) such as GPT (Generative Pre-trained Transformer). GPT is a text generation AI and a language model capable of generating text using natural language processing. For example, the generation model is a Large-Scale Language Model (LLM).

[0038] For example, the first generation unit 151 generates item information corresponding to each item in the system requirements definition document based on summary information that shows an overview of the system requirements definition document. The first generation unit 151 generates multiple item information corresponding to each of the multiple items included in the system requirements definition document based on the summary information. For example, along with the summary information, the first generation unit 151 inputs a prompt to the generation model instructing it to generate item information corresponding to each item that is normally included in the system requirements definition document, and generates item information corresponding to each item that is normally included in the system requirements definition document. For example, the items that are normally included in the system requirements definition document include multiple items such as background objectives, business requirements, assumptions and constraints, systemization function overview, screen requirements, etc. The first generation unit 151 inputs prompts to the generation model, instructing it to generate item information corresponding to each item, such as background objectives, business requirements, assumptions and constraints, system function overview, screen requirements, etc., along with the overview information, and generates item information corresponding to each item, such as background objectives, business requirements, assumptions and constraints, system function overview, screen requirements, etc.

[0039] The output unit 140 displays item information 24 generated by the first generation unit 151. Figure 4 is a diagram showing an example of a UI screen according to the embodiment. In Figure 4, the output unit 140 displays a screen 20 that associates items 23 corresponding to the system requirements definition document with item information 24 corresponding to item 23. Specifically, the output unit 140 associates each of the multiple items 23A to 23E, such as background objectives, business requirements, assumptions and constraints, systemization function overview, screen requirements, etc., with item information 24A to 24E corresponding to each of the multiple items 23A to 23E.

[0040] Furthermore, the first generation unit 151 generates attribute information for the target system development based on the overview information. For example, the first generation unit 151 inputs a prompt to the generation model, along with the overview information, instructing it to generate attribute information corresponding to each attribute of the target system development, and generates attribute information corresponding to each attribute of the target system development. The attributes of the target system development include multiple attributes such as business domain, operational domain, characteristics, etc. The first generation unit 151 inputs a prompt to the generation model, along with the overview information, instructing it to generate attribute information corresponding to each attribute such as business domain, operational domain, characteristics, etc., and generates attribute information corresponding to each attribute such as business domain, operational domain, characteristics, etc.

[0041] The output unit 140 displays attribute information generated by the first generation unit 151. In Figure 4, the output unit 140 displays a screen 20 that shows the attributes 21 of the target system development and the attribute information 22 corresponding to the attributes 21. Specifically, the output unit 140 displays each of the multiple attributes 21A to 21C, such as business domain, operational domain, and characteristics, and the attribute information 22A to 22C corresponding to each of the multiple attributes 21A to 21C.

[0042] (Judgment unit 152) The determination unit 152 determines, item by item, the similarity between past documents, which are documents related to past system development, and the document to be generated, based on past documents whose attribute information matches that of the target system development. Here, past documents are development documents that were generated in the past. Past documents are existing development documents. The following description will focus on the case where the past document is a system requirements definition document, but past documents are not limited to system requirements definition documents. For example, past documents may be development documents other than system requirements definition documents, such as development plans, business requirements definition documents, basic design documents, detailed design documents, source code, unit test specifications, integration test specifications, comprehensive test specifications, and user acceptance test specifications.

[0043] The memory unit 120 stores information relating past documents, specifically information that associates past documents with attribute information of past system developments. For example, when the first generation unit 151 generates attribute information for the target system development, the determination unit 152 refers to the memory unit 120 to obtain information relating to past documents. Subsequently, the determination unit 152 obtains past documents from among the past documents in which the attribute information of the target system development matches the attribute information of past system developments. Next, the determination unit 152 determines the similarity between the past documents in which the attribute information of the target system development matches the attribute information of past system developments and the document to be generated, item by item.

[0044] For example, the determination unit 152 determines the similarity between the past document and the document to be generated on an item-by-item basis, based on item information corresponding to items contained in the past document, which is a document relating to past system development, and item information generated by the first generation unit 151. For example, if the determination unit 152 obtains a past document in which the attribute information of the target system development matches the attribute information of past system development, it determines the similarity between the past document and the document to be generated on an item-by-item basis. For example, the determination unit 152 uses RAG (Search Enhanced Generation) technology to determine the similarity between the past document and the document to be generated on an item-by-item basis.

[0045] In the following, item information corresponding to items contained in past documents may be referred to as "item information contained in past documents." For example, the determination unit 152 inputs past documents into the generation model and generates past vectors, which are vectors corresponding to past documents, for each item. More specifically, the determination unit 152 inputs item information contained in past documents into the generation model and generates past vectors, which are vectors corresponding to item information contained in past documents, for each item. In this case, an Embedding model may be used as the generation model.

[0046] The method for generating past vectors is merely an example and is not limited to the above example. The determination unit 152 may generate past vectors using conventionally known methods. Specifically, for example, the determination unit 152 may generate past vectors using the tf-idf (Term Frequency and Inverse Frequency) or BoW (Bag of Words) model.

[0047] Furthermore, the determination unit 152 inputs the item information generated by the first generation unit 151 into the generation model and generates a target vector for each item, which is a vector corresponding to the document to be generated. In other words, the determination unit 152 inputs the item information generated by the first generation unit 151 into the generation model and generates a target vector for each item, which is a vector corresponding to the item information generated by the first generation unit 151. In this case, an Embedding model may be used as the generation model.

[0048] The above method for generating the target vector is merely an example and is not limited to this example. The determination unit 152 may generate the target vector using conventionally known methods. Specifically, for example, the determination unit 152 may generate past vectors using tf-idf (Term Frequency and Inverse Frequency) or BoW (Bag of Words) models.

[0049] Furthermore, the determination unit 152 determines the similarity between past documents and the document to be generated for each item by determining the similarity between past vectors and the target vector for each item. For example, the determination unit 152 determines the similarity between past documents and the document to be generated for each item by determining the similarity between past vectors that match the items of the target vector and the items of past vectors for each item. The similarity between past vectors and the target vector may be determined, for example, by cosine similarity.

[0050] The method for determining the similarity between the past vector and the target vector is not limited to the above example, and may be determined by conventionally known methods. Specifically, for example, the determination unit 152 may determine the similarity between the past vector and the target vector using the Jacquard coefficient. Furthermore, the method for determining the similarity between the past document and the document to be generated is not limited to the above example, and may be determined by conventionally known methods. Specifically, for example, the determination unit 152 may determine the similarity between the past document and the document to be generated using Gestalt pattern matching, Levenshtein distance, etc.

[0051] Furthermore, when determining the similarity between past documents and the documents to be generated, a method that can take into account the meaning of both documents is particularly preferable.

[0052] Furthermore, the output unit 140 outputs a predetermined number of past documents for each item, starting with those with the highest similarity determined by the determination unit 152. The output unit 140 outputs a predetermined number of first past documents for each item, starting with those with the highest similarity. For example, the output unit 140 displays a thumbnail of each past document for each item, visually displaying the title, release date, and a summary of the item information. In the following, displaying past documents may mean displaying thumbnails of past documents.

[0053] Figures 5 and 6 show examples of UI screens according to the embodiment. In Figures 5 and 6, the output unit 140 displays a screen 30 that associates items 33 included in past documents with a predetermined number of past documents 34 that correspond to item 33 and have a high degree of similarity to the document to be generated. Specifically, the output unit 140 associates each of the multiple items 33A to 33G, such as background objectives, business requirements, prerequisites and constraints, system function overview, screen requirements, batch requirements, performance requirements, etc., with a predetermined number of past documents that correspond to each of the multiple items 33A to 33G. The output unit 140 also displays past documents that the user desires from among the predetermined number of past documents, allowing the user to select them.

[0054] For example, the determination unit 152 determines the similarity between past documents relating to the background purpose and the document to be generated by determining the similarity between the past vector of the item relating to the background purpose and the target vector of the item relating to the background purpose. The output unit 140 displays the item 33A relating to the background purpose and the three past documents 341A to 343A relating to item 33A, in descending order of similarity to the document to be generated. For example, the output unit 140 displays the three past documents 341A to 343A arranged from left to right in descending order of similarity to the document to be generated.

[0055] Furthermore, the output unit 140 displays past documents 341A to 343A, allowing the user to select the desired past document. For example, the output unit 140 displays radio buttons for selecting each of the past documents 341A to 343A superimposed on each of the past documents 341A to 343A. Figure 5 shows the user selecting radio button 35A, which is superimposed on past document 341A.

[0056] Furthermore, the determination unit 152 determines the similarity between past documents relating to the business requirements and the document to be generated by determining the similarity between the past vector of the item relating to the business requirements and the target vector of the item relating to the business requirements. The output unit 140 displays the item 33B relating to the business requirements and the three past documents 341B to 343B relating to the item 33B, in descending order of similarity to the document to be generated. For example, the output unit 140 displays the three past documents 341B to 343B arranged from left to right in descending order of similarity to the document to be generated.

[0057] Furthermore, the output unit 140 displays past documents 341B to 343B, allowing the user to select the desired past document. For example, the output unit 140 displays radio buttons for selecting each of the past documents 341B to 343B superimposed on each of the past documents 341B to 343B. Figure 5 shows the user selecting the radio button superimposed on past document 342B.

[0058] Furthermore, the determination unit 152 determines the similarity between past documents relating to the presuppositions and constraints and the document to be generated by determining the similarity between the past vector of the item corresponding to the presuppositions and constraints and the target vector of the item corresponding to the presuppositions and constraints. The output unit 140 displays the item 33C corresponding to the presuppositions and constraints, and the three past documents 341C to 343C corresponding to item 33C, in descending order of similarity to the document to be generated. For example, the output unit 140 displays the three past documents 341C to 343C arranged from left to right in descending order of similarity to the document to be generated.

[0059] Furthermore, the output unit 140 displays past documents 341C to 343C, allowing the user to select the desired past document. For example, the output unit 140 displays radio buttons for selecting each of the past documents 341C to 343C superimposed on each of the past documents 341C to 343C. Figure 5 shows the result of the user selecting the radio button superimposed on past document 341C.

[0060] Furthermore, the determination unit 152 determines the similarity between past documents relating to the systemization function overview and the document to be generated by determining the similarity between the past vector of the item corresponding to the systemization function overview and the target vector of the item corresponding to the systemization function overview. The output unit 140 displays the item 33D corresponding to the systemization function overview and the three past documents 341D to 343D corresponding to item 33D, in descending order of similarity to the document to be generated. For example, the output unit 140 displays the three past documents 341D to 343D arranged from left to right in descending order of similarity to the document to be generated.

[0061] Although not shown in the diagram, the output unit 140 displays the past documents 341D to 343D, allowing the user to select the desired past document. For example, the output unit 140 displays radio buttons for selecting each of the past documents 341D to 343D superimposed on each of the past documents 341D to 343D.

[0062] Furthermore, the determination unit 152 determines the similarity between past documents relating to the screen requirements and the document to be generated by determining the similarity between the past vector of the item corresponding to the screen requirements and the target vector of the item corresponding to the screen requirements. The output unit 140 displays the item 33E corresponding to the screen requirements and the three past documents 341E to 343E corresponding to the item 33E, in descending order of similarity to the document to be generated. For example, the output unit 140 displays the three past documents 341E to 343E arranged from left to right in descending order of similarity to the document to be generated.

[0063] Furthermore, in Figure 6, the output unit 140 displays the past documents 341E to 343E, allowing the user to select the desired past document. For example, the output unit 140 displays radio buttons for selecting each of the past documents 341E to 343E superimposed on each of the past documents 341E to 343E.

[0064] Furthermore, the determination unit 152 determines the similarity between past documents relating to items corresponding to batch requirements and the document to be generated by determining the similarity between the past vector of the item corresponding to the batch requirement and the target vector of the item corresponding to the batch requirement. The output unit 140 displays the item 33F corresponding to the batch requirement and the three past documents 341F to 343F that correspond to item 33F, in descending order of similarity to the document to be generated. For example, the output unit 140 displays the three past documents 341F to 343F arranged from left to right in descending order of similarity to the document to be generated.

[0065] Furthermore, in Figure 6, the output unit 140 displays the past documents 341F to 343F in a way that allows the user to select the desired past document. For example, the output unit 140 displays radio buttons for selecting each of the past documents 341F to 343F superimposed on each of the past documents 341F to 343F.

[0066] Furthermore, the determination unit 152 determines the similarity between past documents relating to the items corresponding to the performance requirements and the document to be generated by determining the similarity between the past vector of the item corresponding to the performance requirements and the target vector of the item corresponding to the performance requirements. The output unit 140 displays the item 33G corresponding to the performance requirements and the three past documents 341G to 343G corresponding to the item 33G, in descending order of similarity to the document to be generated. For example, the output unit 140 displays the three past documents 341G to 343G arranged from left to right in descending order of similarity to the document to be generated.

[0067] Furthermore, in Figure 6, the output unit 140 displays the past documents 341G to 343G, allowing the user to select the desired past document. For example, the output unit 140 displays radio buttons for selecting each of the past documents 341G to 343G, superimposed on each of the past documents 341G to 343G.

[0068] In the embodiment described above, the output unit 140 displays radio buttons superimposed on each of a predetermined number of past documents, allowing the user to select each document. However, the invention is not limited to this. For example, the output unit 140 may display past documents in a manner that allows the user to select the desired past document from among a predetermined number of past documents. For example, instead of radio buttons, the output unit 140 may display checkboxes superimposed on each of a predetermined number of past documents, allowing the user to select each document. Alternatively, instead of displaying radio buttons or checkboxes, the output unit 140 may accept selection operations (e.g., tap, flick, click, double-click, etc.) for each of the predetermined number of past documents.

[0069] Furthermore, the output unit 140 outputs attribute information of past system developments that matches the attribute information of the target system development, along with the past documents. For example, as described above, the determination unit 152 extracts past documents from the past documents in which the attribute information of the target system development matches the attribute information of the past system development. The output unit 140 outputs the attribute information of past system developments that the determination unit 152 has determined to match the attribute information of the target system development, along with the past documents. In Figures 5 and 6, the output unit 140 displays tags indicating these attribute information superimposed on the past documents when the system of the target system development and the system of the past system development match, the business domain of the target system development and the business domain of the past system development match, the characteristics of the system of the target system development and the past system development match, and the characteristics of the project of the target system development and the past system development match. In Figure 5, the determination unit 152 determines that the attribute information, such as the system, business domain, and project characteristics, matches between the document to be generated and the past document 341A. At this time, the output unit 140 overlays tags on the past document 341A indicating that the systems match, the business domains match, and the characteristics of the cases match.

[0070] Although not shown in the diagram, the output unit 140 outputs a quality score indicating the high quality of the past document along with the past document. For example, the determination unit 152 inputs a prompt to the generation model instructing it to determine a quality score indicating the high quality of the past document based on evaluation indicators for evaluating the quality of the past document, along with the past document, and determines the quality score indicating the high quality of the past document. The output unit 140 also displays the quality score determined by the determination unit 152 superimposed on the past document.

[0071] Figure 7 shows an example of a UI screen according to the embodiment. In Figures 5 and 6, the output unit 140 displays a "See More" button superimposed on the past document. When the input unit 130 accepts the selection operation of the "See More" button, the output unit 140 displays content that displays item information included in the past document. In Figure 7, when the input unit 130 accepts the selection operation of the "See More" button superimposed on the past document 341A of the item corresponding to the background purpose shown in Figure 5, the output unit 140 displays content 38 that displays item information corresponding to the background purpose of the past document 341A. The content 38 includes a close button 39. When the input unit 130 accepts the selection operation of the close button 39, the output unit 140 closes the content 38.

[0072] (Second generation unit 153) The second generation unit 153 generates new item information corresponding to each item in the document to be generated, based on the item information corresponding to the items in the first past document selected by the user from among the first past documents output by the output unit 140, and the item information generated by the first generation unit 151. For example, as shown in Figure 6, the output unit 140 displays a screen 30 including a button 37. When the input unit 130 receives a selection operation for the button 37 while a past document corresponding to each item has been selected from among the past documents output by the output unit 140, it accepts input of item information corresponding to the items in the past document selected by the user. Hereinafter, the item information corresponding to the items in the past document selected by the user may be referred to as the item information selected by the user. Also, the generation of new item information corresponding to each item in the document to be generated may be referred to as generating new item information corresponding to the document to be generated.

[0073] Furthermore, the second generation unit 153 inputs a prompt to the generation model instructing it to generate new item information corresponding to the target document, based on the item information selected by the user and the item information generated by the first generation unit 151, and generates new item information corresponding to the target document. Hereinafter, the new item information corresponding to the target document may be referred to as new item information.

[0074] Figures 8 and 9 show examples of UI screens according to the embodiment. In Figures 8 and 9, the output unit 140 displays a screen 40 that associates an item 41 corresponding to the document to be generated, item information 42 generated by the first generation unit 151 corresponding to item 41, item information 43 selected by the user corresponding to item 41, and new item information 44 corresponding to item 41. Specifically, the output unit 140 displays a screen 40 that associates each of the multiple items 41A to 41G, such as background objectives, business requirements, prerequisites and constraints, system function overview, screen requirements, batch requirements, performance requirements, etc., with the item information 42A to 42G generated by the first generation unit 151 corresponding to each of the multiple items 41A to 41G. The output unit 140 also displays a screen 40 that associates each of the multiple items 41A to 41G with the item information 43A to 43G selected by the user corresponding to each of the multiple items 41A to 41G. Furthermore, the output unit 140 displays a screen 40 that shows the association between each of the multiple items 41A to 41G and the new item information 44A to 44G corresponding to each of the multiple items 41A to 41G.

[0075] Furthermore, the output unit 140 displays screen 40 including buttons 45 to 47. For example, when the input unit 130 receives an operation to select button 47, the second generation unit 153 generates a document to be generated based on the new item information. In other words, the second generation unit 153 generates a document to be generated that includes the new item information. The output unit 140 displays the document to be generated generated by the second generation unit 153. For example, when the input unit 130 receives an operation to select button 47, the second generation unit 153 generates a document to be generated that displays each of the multiple items 41A to 41G described in Figures 8 and 9 in association with the new item information 44A to 44G corresponding to each of the multiple items 41A to 41G. Figure 10 is a diagram showing an example of a UI screen according to the embodiment. In Figure 10, the output unit 140 displays the document to be generated generated by the second generation unit 153. The output unit 140 displays the system requirements definition document generated by the second generation unit 153. Specifically, the output unit 140 displays a document to be generated, which shows the association between each of the multiple items 41A to 41G described in Figures 8 and 9 and the new item information 44A to 44G corresponding to each of the multiple items 41A to 41G.

[0076] Furthermore, when the input unit 130 accepts the operation to select button 45, the determination unit 152 determines the similarity between the past document and the document to be generated for each item, based on the item information corresponding to the items contained in the past document and the new item information generated by the second generation unit 153. For example, the determination unit 152 inputs the past document into the generation model and generates a past vector, which is a vector corresponding to the past document, for each item. More specifically, the determination unit 152 inputs the item information contained in the past document into the generation model and generates a past vector, which is a vector corresponding to the item information contained in the past document, for each item.

[0077] Furthermore, the determination unit 152 inputs the new item information generated by the second generation unit 153 into the generation model and generates a second target vector for each item, which is a vector corresponding to the document to be generated. In other words, the determination unit 152 inputs the new item information generated by the second generation unit 153 into the generation model and generates a second target vector for each item, which is a vector corresponding to the new item information generated by the second generation unit 153.

[0078] Furthermore, the determination unit 152 determines the similarity between past documents and the document to be generated on a per-item basis by determining the similarity between past vectors and second target vectors on a per-item basis. For example, the determination unit 152 determines the similarity between past documents and the document to be generated on a per-item basis by determining the similarity between past vectors that match items in the second target vector and items in the past vector, on a per-item basis.

[0079] The output unit 140 outputs a predetermined number of second past documents, sorted by item, starting with those with the highest similarity. For example, the output unit 140 displays a screen like screen 30, as described in Figures 5 and 6.

[0080] The second generation unit 153 generates further new item information corresponding to each item in the document to be generated, based on the item information corresponding to the items contained in the second past document selected by the user from the second past document output by the output unit 140, and the new item information. For example, the second generation unit 153 inputs a prompt to the generation model instructing it to generate further new item information corresponding to the document to be generated, based on the item information contained in the second past document selected by the user, the new item information, and the second past document item information selected by the user, and the new item information, and generates further new item information corresponding to the document to be generated.

[0081] Furthermore, if the input unit 130 accepts the operation to select button 46, the second generation unit 153 generates a provisional document to be generated based on the new item information. The determination unit 152 also evaluates the quality of the provisionally generated document to be generated. Figures 11 to 14 show examples of UI screens according to the embodiment. In the following, the provisionally generated document to be generated may be referred to as the provisional document to be generated.

[0082] In Figure 11, the determination unit 152 inputs a prompt to the generation model instructing it to determine a score for evaluating the quality of the provisional target document, along with the provisional target document, from the perspective of item coverage and the quality of the provisional target document. The output unit 140 displays a screen 61 showing the score determined by the determination unit 152. The determination unit 152 also inputs a prompt to the generation model instructing it to generate comments regarding item coverage and quality of the provisional target document. The output unit 140 then generates comments regarding item coverage and quality of the provisional target document. The output unit 140 displays the comments regarding item coverage and quality of the provisional target document generated by the determination unit 152.

[0083] In Figure 12, the determination unit 152 inputs a prompt to the generation model instructing it to determine whether the provisional target document contains any NG words or similar words, along with a list of provisional target documents and NG words to be checked. The determination unit 152 then determines whether the provisional target document contains any NG words or similar words. If the provisional target document contains any NG words or similar words, the determination unit 152 inputs a prompt to the generation model instructing it to output the detected NG words or similar words along with the corresponding locations, and outputs the detected NG words or similar words. The output unit 140 displays a screen 62 showing the determination results from the determination unit 152. For example, the output unit 140 displays a screen 62 showing the NG words or similar words detected by the determination unit 152 along with the corresponding locations.

[0084] In Figure 13, the determination unit 152 inputs a prompt to the generation model instructing it to output a list of provisional target documents and past failures or lessons learned to be checked, along with a determination result for each item indicating whether the provisional target document corresponds to a past failure or lesson learned. The determination unit 152 then outputs a determination result for each item indicating whether the provisional target document corresponds to a past failure or lesson learned. The determination unit 152 also inputs a prompt to the generation model instructing it to output the determination reason for each item along with the determination result, and outputs the determination reason for each item indicating whether the provisional target document corresponds to a past failure or lesson learned. The output unit 140 displays the determination result and determination reason from the determination unit 152 for each item.

[0085] In Figure 14, the determination unit 152 inputs a prompt to the generation model instructing it to output a list of provisional target documents and gate check items, along with a determination result for each item indicating whether the provisional target documents correspond to the gate check items. The determination unit 152 then outputs the determination result for each item. The determination unit 152 also inputs a prompt to the generation model instructing it to output the determination reason for each item along with the determination result. The determination unit 152 then outputs the determination reason for each item indicating whether the provisional target documents correspond to the gate check items. The output unit 140 displays the determination result and determination reason from the determination unit 152 for each item.

[0086] [3. Information Processing Procedures] Next, an example of information processing by the information processing device according to the embodiment will be described using Figure 15. Figure 15 is a flowchart showing an example of information processing by the information processing device according to the embodiment. In Figure 15, the input unit 130 of the information processing device 100 determines whether or not it has received input of summary information indicating an outline of the document to be generated related to the target system development (step S101). If the input unit 130 determines that it has not received input of summary information (step S101; No), it determines whether or not it has received input of summary information (step S101).

[0087] On the other hand, if the first generation unit 151 of the information processing device 100 determines that it has received summary information from the input unit 130 (step S101; Yes), it generates item information corresponding to each item in the document to be generated based on the summary information (step S102). The determination unit 152 of the information processing device 100 also retrieves past documents from among past documents in which the attribute information of the target system development matches the attribute information of past system developments (step S103). The determination unit 152 also determines the similarity between the past documents and the document to be generated for each item (step S104).

[0088] Furthermore, the output unit 140 of the information processing device 100 outputs a predetermined number of past documents, sorted by item, starting with those with the highest similarity (step S105). The second generation unit 153 of the information processing device 100 generates new item information corresponding to each item in the document to be generated, based on the item information corresponding to the items in the past documents selected by the user from among the past documents output by the output unit 140, and the item information generated by the first generation unit 151 (step S106). The second generation unit 153 then generates the document to be generated based on the new item information (step S107).

[0089] [4. Effects] As described above, the information processing device 100 according to the embodiment includes an input unit 130, a first generation unit 151, a determination unit 152, an output unit 140, and a second generation unit 153. The input unit 130 receives input of summary information indicating an overview of the documents to be generated related to the target system development. The first generation unit 151 generates item information corresponding to each item corresponding to the documents to be generated based on the summary information. The determination unit 152 determines the similarity between the past documents and the documents to be generated for each item, based on the item information corresponding to items contained in past documents, which are documents related to past system development, and the item information generated by the first generation unit 151. The output unit 140 outputs a predetermined number of first past documents for each item, starting with the one with the highest similarity. The second generation unit 153 generates new item information corresponding to each item corresponding to the documents to be generated, based on the item information corresponding to items contained in the first past documents selected by the user from among the first past documents output by the output unit 140, and the item information generated by the first generation unit 151.

[0090] This allows the information processing device 100 to assist in the creation of documentation related to system development. Furthermore, because the information processing device 100 can assist in the creation of documentation related to system development, it can contribute to achieving Sustainable Development Goal (SDG) 9, "Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation."

[0091] Furthermore, the determination unit 152 determines the similarity between the past document and the document to be generated for each item, based on the item information corresponding to the items contained in the past document and the new item information generated by the second generation unit 153. The output unit 140 outputs a predetermined number of second past documents for each item, starting with those with the highest similarity. The second generation unit 153 generates further new item information corresponding to each item in the document to be generated, based on the item information corresponding to the items contained in the second past document selected by the user from among the second past documents output by the output unit 140, and the new item information.

[0092] This allows the information processing device 100 to improve the accuracy of creating documents related to system development.

[0093] Furthermore, the determination unit 152 determines, item by item, the similarity between past documents whose attribute information matches that of the target system development and the document to be generated.

[0094] As a result, the information processing device 100 can retrieve past documents relating to past system developments that match the attribute information of the target system development from a vast amount of past documents.

[0095] Furthermore, the output unit 140 outputs attribute information of past system developments that matches the attribute information of the target system development, along with past documents.

[0096] This allows the information processing device 100 to assist users in selecting past documents by referring to attribute information of past system developments that match the attribute information of the target system development.

[0097] Furthermore, the output unit 140 outputs a quality score, which indicates the high quality of past documents, along with the past documents themselves.

[0098] This allows the information processing device 100 to assist users in selecting past documents by referring to a quality score that indicates the quality of the past documents.

[0099] [5. Hardware Configuration] Furthermore, the information processing device 100 according to the above-described embodiment is realized by a computer 1000 having a configuration such as that shown in Figure 16. The following explanation will use the information processing device 100 as an example. Figure 16 is a diagram showing an example of the hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which an arithmetic unit 1030, a primary storage device 1040, a secondary storage device 1050, an output interface 1060, an input interface 1070, and a network interface 1080 are connected by a bus 1090.

[0100] The arithmetic unit 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, as well as programs read from the input device 1020, and executes various processes. The arithmetic unit 1030 can be implemented using, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), or an FPGA (Field Programmable Gate Array).

[0101] The primary storage device 1040 is a memory device, such as RAM (Random Access Memory), that temporarily stores data used by the arithmetic unit 1030 for various calculations. The secondary storage device 1050 is a storage device where data used by the arithmetic unit 1030 for various calculations and various databases are registered, and can be implemented using ROM (Read Only Memory), HDD (Hard Disk Drive), SSD (Solid State Drive), flash memory, etc. The secondary storage device 1050 may be internal storage or external storage. The secondary storage device 1050 may also be a removable storage medium such as USB (Universal Serial Bus) memory or SD (Secure Digital) memory card. The secondary storage device 1050 may also be cloud storage (online storage), NAS (Network Attached Storage), file server, etc.

[0102] The output I / F 1060 is an interface for transmitting information to be output to output devices 1010, such as displays, projectors, and printers, and is implemented using connectors of standards such as USB (Universal Serial Bus), DVI (Digital Visual Interface), and HDMI (High Definition Multimedia Interface). The input I / F 1070 is an interface for receiving information from various input devices 1020, such as mice, keyboards, keypads, buttons, and scanners, and is implemented using, for example, USB.

[0103] Furthermore, the output interface 1060 and input interface 1070 may be wirelessly connected to the output device 1010 and input device 1020, respectively. In other words, the output device 1010 and input device 1020 may be wireless devices.

[0104] Furthermore, the output device 1010 and the input device 1020 may be integrated as a touch panel. In this case, the output I / F 1060 and the input I / F 1070 may also be integrated as an input / output I / F.

[0105] The input device 1020 may also be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), DVD (Digital Versatile Disc), or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0106] The network interface 1080 receives data from other devices via network N and sends it to the computing unit 1030, and also transmits data generated by the computing unit 1030 to other devices via network N.

[0107] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output interface 1060 and the input interface 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0108] For example, when computer 1000 functions as an information processing device 100, the arithmetic unit 1030 of computer 1000 realizes the functions of the control unit 150 by executing a program loaded onto the primary storage device 1040. Alternatively, the arithmetic unit 1030 of computer 1000 may load a program obtained from another device via the network interface 1080 onto the primary storage device 1040 and execute the loaded program. Furthermore, the arithmetic unit 1030 of computer 1000 may cooperate with other devices via the network interface 1080 and call and use program functions, data, etc., from other programs on other devices.

[0109] [6. Other] Although embodiments of the present invention have been described above, the present invention is not limited by the content of these embodiments. Furthermore, the aforementioned components include those that can be easily conceived by those skilled in the art, those that are substantially the same, and those that fall within the so-called equivalent range. Moreover, the aforementioned components can be combined as appropriate. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the gist of the embodiments described above.

[0110] Furthermore, among the processes described in the above embodiments, 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 by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0111] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0112] For example, the information processing device 100 described above may be implemented using multiple server computers, and depending on the function, it may be implemented by calling external platforms, etc., via APIs (Application Programming Interfaces) or network computing, allowing for flexible configuration changes.

[0113] Furthermore, the embodiments and modifications described above can be combined as appropriate, provided that the processing content is not inconsistent. [Explanation of Symbols]

[0114] 100 Information Processing Devices 110 Communications Department 120 Storage section 130 Input section 140 Output section 150 Control Unit 151 1st generation part 152 Judgment section 153 Second generation part

Claims

1. An input section that accepts input of summary information showing an overview of the documents to be generated related to the target system development, A first generation unit generates item information corresponding to each item in the document to be generated, based on the summary information, A determination unit determines the degree of similarity between the past document and the document to be generated for each item, based on item information corresponding to items contained in the past document, which is a document relating to past system development, and item information generated by the first generation unit. An output unit that outputs a predetermined number of first past documents, sorted by item, from those with the highest similarity, A second generation unit inputs a prompt to the generation model instructing it to generate new item information corresponding to each item in the target document, based on the item information corresponding to an item in the first past document selected by the user from the first past document output by the output unit and the item information generated by the first generation unit, and generates new item information corresponding to each item in the target document, An information processing device equipped with the following features.

2. The determination unit, Based on the item information corresponding to the items contained in the aforementioned past document and the new item information generated by the second generation unit, the degree of similarity between the aforementioned past document and the document to be generated is determined for each item. The output unit is, A predetermined number of second past documents are output for each item, starting with those with the highest similarity. The second generation unit is, Based on the item information corresponding to the items included in the second past document selected by the user from the second past document output by the output unit, and the new item information, further new item information corresponding to the items in the document to be generated is generated for each item in the target document. The information processing apparatus according to claim 1.

3. The determination unit, The similarity between the past documents whose attribute information matches that of the target system development and the document to be generated is determined item by item. The information processing apparatus according to claim 1.

4. The output unit is, The attribute information of past system developments that matches the attribute information of the target system development is output along with the past documents. The information processing apparatus according to claim 3.

5. The output unit is, The system outputs a quality score indicating the high quality of the aforementioned past documents, along with the documents themselves. The information processing apparatus according to claim 1.

6. An information processing method implemented by a program executed by an information processing device, An input process that accepts input of summary information that shows an overview of the documents to be generated related to the target system development, A first generation step in which, based on the summary information, item information corresponding to each item in the document to be generated is generated, A determination step that determines the degree of similarity between the past document and the document to be generated for each item, based on item information corresponding to items contained in the past document, which is a document relating to past system development, and item information generated by the first generation step, An output process that outputs a predetermined number of first past documents, item by item, starting with those with the highest similarity, A second generation step involves inputting a prompt to the generation model instructing it to generate new item information corresponding to each item in the target document, based on the item information corresponding to an item in the first past document selected by the user from the output step, and the item information generated by the first generation step, thereby generating new item information corresponding to each item in the target document; Information processing methods including

7. An input procedure that accepts input of summary information showing an overview of the documents to be generated related to the target system development, A first generation procedure that generates item information corresponding to each item corresponding to the document to be generated, based on the summary information, A determination procedure for determining the similarity between the past document and the document to be generated for each item, based on item information corresponding to items contained in the past document, which is a document relating to past system development, and item information generated by the first generation procedure, An output procedure for outputting a predetermined number of first past documents, item by item, starting with those with the highest similarity, A second generation procedure involves inputting a prompt to the generation model instructing it to generate new item information corresponding to each item in the target document, based on the item information corresponding to an item in the first past document selected by the user from the first past document output by the output procedure and the item information generated by the first generation procedure, thereby generating new item information corresponding to each item in the target document; An information processing program that causes a computer to execute something.

Images