Information processing apparatus, control method of information processing apparatus, and program

Abstract

To provide an information processing apparatus which contributes to enabling a user to generate a more accurate requirements definition.SOLUTION: An information processing apparatus includes structuring control means and concretization control means. The structuring control means acquires request information described in a natural language, generates at least one requirement information candidates based on the acquired request information, and structures the generated at least one requirement information candidates. The concretization control means concretizes the at least one structured requirement information candidates.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] There are technologies that assist in the design of systems and software.

[0003] For example, Patent Document 1 discloses a method for model-based design of safety-critical software. The system disclosed in Patent Document 1 receives natural language software requirements, develops a specification model by implementing semantic modeling or graphical modeling, and applies formal requirements analysis to the specification model. The system then automatically generates requirements-based and robustness test cases from the specification model, develops a design model based on the specification model, applies the test cases to the design model, and automatically generates source code using the design model. The system then verifies the source code using both the test cases and static analysis techniques, and compiles executable object code from the verified source code. If the results of the analysis of the software specification or design model are unsatisfactory, the system then adjusts the specification or design model to correct any inconsistencies and repeats the analysis and test cases. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2017-033562 Summary of the Invention [Problem to be solved by the invention]

[0005] Requirements definition is important in system development (system design) for large-scale networks, etc. In particular, requirements definition is important in developing systems that combine multiple components based on diverse system requirements.

[0006] Requirements definitions are generated from system requirements. For example, if an inexperienced engineer generates requirements definitions, they may contain contradictions or lack information.

[0007] A main object of the present invention is to provide an information processing device, a control method for an information processing device, and a program that contribute to enabling a user to generate a more accurate requirements definition. [Means for solving the problem]

[0008] According to a first aspect of the present invention, there is provided an information processing device including: a structuring control means for acquiring requirement information written in a natural language, generating at least one or more requirement information candidates based on the acquired requirement information, and structuring the generated at least one or more requirement information candidates; and a concretization control means for concretizing the at least one or more structured requirement information candidates.

[0009] According to a second aspect of the present invention, there is provided a control method for an information processing device, comprising: a structuring control step of acquiring requirement information written in a natural language, generating at least one or more requirement information candidates based on the acquired requirement information, and structuring the generated at least one or more requirement information candidates; and a concretization control step of concretizing the at least one or more structured requirement information candidates.

[0010] According to a third aspect of the present invention, there is provided a program for causing a computer mounted on an information processing device to execute a structuring control process of acquiring requirement information written in a natural language, generating at least one or more requirement information candidates based on the acquired requirement information, and structuring the generated at least one or more requirement information candidates, and a concretization control process of concretizing the at least one or more structured requirement information candidates. [Effects of the Invention]

[0011] According to each aspect of the present invention, an information processing device, a control method for an information processing device, and a program are provided that contribute to enabling a user to generate a more accurate requirements definition. Note that the effects of the present invention are not limited to those described above. The present invention may achieve other effects instead of or in addition to the effects described above. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram for explaining an outline of an embodiment. [Figure 2] FIG. 2 is a flowchart illustrating the operation of one embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of a schematic configuration of an information processing system according to an embodiment of the present disclosure. [Figure 4] FIG. 4 is a diagram illustrating an example of a processing configuration of the support device according to an embodiment of the present disclosure. [Figure 5] FIG. 5 is a diagram illustrating an example of a display on a terminal according to an embodiment of the present disclosure. [Figure 6] FIG. 6 is a flowchart illustrating an example of the operation of the assistance device according to an embodiment of the present disclosure. [Figure 7] FIG. 7 is a diagram for explaining the operation of the assistance device according to the embodiment of the present disclosure. [Figure 8] FIG. 8 is a diagram illustrating an example of a display on a terminal according to a modified example of the embodiment of the present disclosure. [Figure 9] FIG. 9 is a diagram illustrating an example of a processing configuration of the support device according to an embodiment of the present disclosure. [Figure 10] FIG. 10 is a diagram illustrating an example of a hardware configuration of the support device according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0013] First, an overview of one embodiment will be described. Note that the reference numerals in the drawings are added to each element for convenience as an example to facilitate understanding, and the description of this overview is not intended to be limiting in any way. Furthermore, unless otherwise specified, the blocks shown in each drawing represent functional units, not hardware units. Connection lines between blocks in each drawing include both bidirectional and unidirectional lines. Unidirectional arrows are used to schematically indicate the flow of main signals (data) and do not exclude bidirectionality. Note that in this specification and drawings, elements that can be similarly described may be assigned the same reference numerals to avoid redundant explanation.

[0014] An information processing device 100 according to one embodiment includes a structuring control means 101 and a concretization control means 102 (see FIG. 1). The structuring control means 101 acquires requirement information written in a natural language, generates at least one or more requirement information candidates based on the acquired requirement information, and structures the generated at least one or more requirement information candidates (step S1 in FIG. 2). The concretization control means 102 concretizes the at least one or more structured requirement information candidates (step S2).

[0015] When the information processing device 100 acquires a system requirement from a user, it generates at least one or more requirement information candidates corresponding to the system requirement. More specifically, the information processing device 100 interprets elements obtained from the system requirement from various perspectives and generates multiple requirement information candidates by combining the acquired new elements. The information processing device 100 converts each of the multiple requirement information candidates into a machine-processable format to generate structured requirement information candidates. The information processing device 100 attempts to concretize each of the multiple structured requirement information candidates. The information processing device 100 can provide the user with information about requirement information candidates that have been successfully concretized (requirement information candidates for which specific design proposals have been obtained). The user is provided with requirement information candidates that are determined to be feasible. The user can generate more accurate requirement information (requirements definition) by verifying the provided requirement information candidates.

[0016] Specific embodiments will be described in more detail below with reference to the drawings.

[0017] [First embodiment] The first embodiment will be described in more detail with reference to the drawings.

[0018] [System configuration and outline of operation] As shown in FIG. 3, the information processing system according to the first embodiment includes a support device 10 and a terminal 20.

[0019] The support device 10 is an information processing device that supports a user in system design. For example, the support device 10 is a server installed on a network (on the cloud).

[0020] A user operates the terminal 20 to access the assistance device 10. The user inputs various pieces of information to the assistance device 10 and obtains various pieces of information from the assistance device 10.

[0021] The support device 10 acquires system requirements (functions and objectives required for a system) called business requirement definitions or systemization requirement definitions. For example, the support device 10 acquires system requirements (requirement information) written in natural language from a user.

[0022] For example, the support device 10 acquires a system request from a person in charge of a vendor company in charge of system development. The person in charge of the vendor company inputs the client company's requests for the system into the support device 10 as the system request.

[0023] The support device 10 generates at least one or more system requirement candidates (information that organizes functions and non-functions required for the system) based on the acquired system requirements (requirement information including natural language). The support device 10 generates system requirement candidates (requirement information) that consist of system components and performance indicators linked to the components.

[0024] The support device 10 structures at least one or more generated requirement information candidates (hereinafter referred to as requirement information candidates). The support device 10 structures the requirement information candidates by converting each requirement information candidate into a predetermined format that can be processed by a machine.

[0025] The support device 10 generates design information that embodies components and / or performance indicators for each structured requirements information candidate. In the process of generating the design information for each requirements information candidate, the support device 10 determines the feasibility of each requirements information candidate.

[0026] The support device 10 provides the user with design information (system configuration plan) corresponding to a requirement information candidate that has been determined to be feasible from among at least one or more structured requirement information candidates.

[0027] For example, the support device 10 acquires a system requirement from a user, such as "a video distribution system that can be viewed by 1000 people simultaneously." The support device 10 generates a plurality of requirement information candidates from the system requirement.

[0028] For example, in the above example, the support device 10 generates requirement information candidates (requirement definition candidates) such as "network line; fixed line, communication quality; 100Mbps" and "network line; mobile line, communication quality; 10Mbps."

[0029] The support device 10 structures each of the generated requirement information candidates. Note that structuring the requirement information candidates includes converting the requirement information candidates into a predetermined format or expressing the requirement information candidates using a predetermined vocabulary. For example, the support device 10 converts each requirement information candidate into a predetermined format such as the JSON (JavaScript Object Notation) format. For example, the JSON format defines what key is used to express a concept, and when structuring is performed, an appropriate key for expressing the concept is selected. For example, when "Memory" is defined as a key to express computer memory, the key (vocabulary) is unified to the expression "Memory" without using expressions such as "main memory device" or "RAM."

[0030] Furthermore, the support device 10 generates a specific system configuration plan for realizing the requirement information candidate (a requirement definition candidate including components and / or performance indicators). For example, the support device 10 generates design information of the requirement information candidate by specifically specifying a line method (for example, optical line, analog line, etc.) and communication equipment to be used (router, hub, etc.), and provides the design information to the user.

[0031] The user reviews at least one or more candidate requirements information and corresponding design information provided. The user selects requirements information from the candidate requirements information provided, or makes necessary modifications to the candidate requirements information, and generates final requirements information (system requirements, requirements definition). Since the user is provided with a system requirements proposal accompanied by design information, etc., that is premised on the realization of the system, the user can generate more accurate (appropriate) requirements information.

[0032] 3 is an example and is not intended to limit the configuration. For example, the information processing system may include multiple support devices 10. Load balancing and redundancy may be achieved by using multiple support devices 10.

[0033] Next, the support device 10 according to the first embodiment will be described in detail.

[0034] 4 is a diagram illustrating an example of a processing configuration (processing module) of the assistance device 10 according to an embodiment of the present disclosure. Referring to FIG. 4, the assistance device 10 includes a communication control unit 201, a structuring control unit 202, a concretization control unit 203, an information provision control unit 204, and a storage unit 205.

[0035] The communication control unit 201 is a means for controlling communication with other devices. For example, the communication control unit 201 receives data (packets) from the terminal 20. The communication control unit 201 also transmits data to the terminal 20. The communication control unit 201 passes data received from other devices to other processing modules. The communication control unit 201 transmits data acquired from other processing modules to other devices. In this way, other processing modules transmit and receive data to and from other devices via the communication control unit 201. The communication control unit 201 has a function as a receiving unit that receives data from other devices and a function as a transmitting unit that transmits data to other devices.

[0036] The structuring control unit 202 is a means for controlling the structuring of system requirements (requirement definitions) acquired from users. The structuring control unit 202 acquires requirement information written in natural language, and generates at least one or more requirement information candidates based on the acquired requirement information. Furthermore, the structuring control unit 202 structures the generated at least one or more requirement information candidates.

[0037] Specifically, the structuring control unit 202 acquires a system request from a user (user terminal 20) who has accessed the assistance device 10. For example, the structuring control unit 202 acquires the system request using a GUI (Graphical User Interface) or the like.

[0038] The structuring control unit 202 extracts elements (components and / or performance indicators) related to the system that is required to be realized based on the acquired system requirements. The structuring control unit 202 extracts the components and performance indicators from the system requirements using any method.

[0039] For example, the structuring control unit 202 extracts components, etc. by referring to table information that stores correspondence between wording that may be written in a system requirement and elements (components, performance indicators) that may be extracted from the wording.

[0040] For example, by referencing the table information, the structuring control unit 202 extracts the component "network line" and the performance indicator "communication quality" from the phrase "video distribution system" written in the system request. Alternatively, the structuring control unit 202 extracts the component "distribution server" and the performance indicator "response time" from "video distribution system."

[0041] Alternatively, the structuring control unit 202 may extract components and performance indicators by inputting the system requirements into a language model.

[0042] As an example, the language model may be, but is not limited to, what is called a large-scale language model.

[0043] A language model is a machine learning model (also called a generative model) that takes language as input and outputs language. A language model learns the relationships between words in a sentence and generates related strings from a target string. By using a language model that has been trained on sentences and sentences from various contexts, it is possible to generate related strings with appropriate content that are related to the target string.

[0044] When a prompt (query) including instructions regarding a response is input, the language model outputs an answer corresponding to the prompt.

[0045] The learning method of the language model is not particularly limited, but as an example, the language model may be learned to output at least one sentence including an input string. As a specific example, the language model is a GPT (Generative Pre-Transformer) that outputs a sentence including an input string by predicting a string that is likely to follow the input string.

[0046] Other examples of language models include T5 (Text-to-Text Transfer Transformer), BERT (Bidirectional Encoder Representations from Transformers), RoBERTa (Robustly optimized BERT approach), and ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately).

[0047] A system administrator or the like prepares a language model to be implemented in the support device 10 using a large amount of design materials, specifications, etc. related to system design.

[0048] For example, the structuring control unit 202 generates a prompt including a system requirement and an instruction to extract elements (components, performance indicators) from the system requirement. The structuring control unit 202 extracts the components and performance indicators by inputting the generated prompt into a language model.

[0049] When elements (components, performance indicators) related to the system are extracted, the structuring control unit 202 "interprets" each of the extracted elements (components, performance indicators) from various perspectives, thereby generating multiple new elements (components, performance indicators) from a single element.

[0050] For example, the structuring control unit 202 generates specific components (plurality of components) for realizing the extracted components from the components. For example, the structuring control unit 202 generates new components such as "fixed line" and "mobile line" from the component "network line."

[0051] Alternatively, the structuring control unit 202 generates other components associated with the extracted components. For example, the structuring control unit 202 generates a plurality of new components, such as a component "transmission server" and a component "receiving terminal," associated with the component "network line."

[0052] Alternatively, the structuring control unit 202 generates multiple performance indicators by converting the extracted performance indicators into specific numerical values. For example, the structuring control unit 202 generates multiple performance indicators such as "10 Mbps," "100 Mbps," and "1 Gbps" from the performance indicator "communication quality."

[0053] Alternatively, the structuring control unit 202 can generate multiple components and multiple performance indicators using multiple types of documents related to requirements definition as input (using multiple types of documents). For example, the structuring control unit 202 may use multiple documents with different requirements definition guidelines to generate multiple components and performance indicators with different interpretations from the extracted components and performance indicators.

[0054] The structuring control unit 202 may generate multiple elements by referring to table information that stores elements (component elements, performance indicators) extracted from the system requirements in association with multiple other elements (component elements, performance indicators). A system administrator, engineer, or the like generates the table information so that multiple elements are generated from one element from multiple perspectives, different perspectives, etc. It is preferable that the system administrator, or the like generates the table information so as to cover all other elements that can be generated from one element.

[0055] Alternatively, the structuring control unit 202 may generate a plurality of elements from each element using a language model.

[0056] For example, the structuring control unit 202 generates a prompt including an instruction to generate another element (a plurality of other elements) from an element extracted from the system requirement. For example, the structuring control unit 202 generates a prompt such as "Please generate two or more components and performance indicators related to LABEL1," and inputs the generated prompt into a language model to obtain a plurality of elements.

[0057] The extracted element is set to LABEL1 written in the above prompt. For example, in the above example, words such as "network line" and "communication quality" are set to LABEL1.

[0058] It goes without saying that the prompts input to the language model are not limited to the above examples.

[0059] For example, the structuring control unit 202 may generate multiple prompts with different instruction contents and input each prompt into a language model to obtain multiple elements from one element. For example, the structuring control unit 202 may generate multiple prompts including instructions to output elements from different perspectives for elements extracted from a system requirement. Alternatively, the structuring control unit 202 may generate multiple prompts that have the same meaning but different expressions.

[0060] For example, the structuring control unit 202 may generate a prompt including an instruction to output cost-oriented components or performance-oriented performance indicators. In the former case, an example of the prompt is, "For LABE1, please select multiple components with a focus on cost." In the latter case, an example of the prompt is, "For LABE1, please select multiple components with a focus on performance."

[0061] When a plurality of new elements are obtained for each element (configuration requirement, performance index) extracted from the system requirement, the structuring control unit 202 combines the plurality of elements to generate a plurality of requirement information candidates.

[0062] For example, the structuring control unit 202 generates multiple requirement information candidates by combining the components "fixed line" and "mobile line" obtained from the component "network line" with the performance indicators "10 Mbps" and "100 Mbps" obtained from the performance indicator "communication quality." In this case, the following four requirement information candidates are generated:

[0063] Requirement information candidate 1 = "Network line; fixed line, communication quality; 10Mbps". Requirement information candidate 2 = "Network line: fixed line, communication quality: 100Mbps". Requirement information candidate 3 = "Network line; mobile line, communication quality; 10Mbps". Requirement information candidate 4 = "Network line; mobile line, communication quality; 100Mbps".

[0064] For ease of understanding, four requirement information candidates each containing one component and a corresponding performance indicator are shown as an example, but in reality, requirement information candidates consisting of multiple components and multiple performance indicators can be generated. For example, a requirement information candidate with the following content may be generated: "Network line: fixed line, communication quality: 10 Mbps, distribution server: physical machine, response speed: 5 ms."

[0065] After generating the multiple requirement information candidates, the structuring control unit 202 structures each of the multiple requirement information candidates. The structuring control unit 202 converts each requirement information candidate into requirement information (requirement information candidate) having a predetermined structure.

[0066] For example, the structuring control unit 202 sequentially inputs each requirement information candidate into a language model to acquire the corresponding structured requirement information candidate. For example, the structuring control unit 202 inputs a query such as "Please convert the requirement information of LABEL2 into JSON format" into the language model to acquire the corresponding requirement information candidate. Note that specific content such as those shown in the above requirement information candidates 1 to 4 is set in LABEL2.

[0067] The structuring control unit 202 generates a plurality of structured requirement information candidates by sequentially converting the plurality of requirement information candidates using a language model.

[0068] The structuring control unit 202 delivers at least one structured requirement information candidate to the instantiation control unit 203 .

[0069] In this way, the structuring control unit 202 generates at least one or more requirement information candidates (requirement candidate group) from requirement information (system requirements, system requirement definition) written in natural language. In doing so, the structuring control unit 202 interprets each element included in the acquired requirement information from different perspectives to generate multiple new elements corresponding to each of the elements. The structuring control unit 202 generates at least one or more requirement information candidates by combining the multiple generated new elements. The structuring control unit 202 structures each of the generated requirement information candidates. Specifically, the structuring control unit 202 converts each requirement information candidate into a requirement information candidate written in a predetermined format (grammar, vocabulary).

[0070] The concretization control unit 203 is a means for controlling the concretization of requirement information candidates (generation of a concrete design proposal). The concretization control unit 203 concretizes at least one structured requirement information candidate.

[0071] The concretization control unit 203 generates specific design information for each requirement information candidate (structured requirement information candidate) using any means. The concretization control unit 203 narrows down the optimal system configuration from multiple system configurations obtained by concretizing the components and performance indicators included in the requirement information candidate, and generates the narrowed down system configuration as design information.

[0072] For example, the concretization control unit 203 generates concrete design information using various algorithms related to multi-objective optimization problems. The requirement information candidates handled by the concretization control unit 203 are structured to enable mechanical processing. Therefore, the concretization control unit 203 can generate concrete design information by applying an algorithm for solving a multi-objective optimization problem to the structured requirement information candidates.

[0073] At this time, the concretization control unit 203 may generate concrete design information of the structured requirement information candidate using technical information prepared in advance.

[0074] The technical information includes a list of parts that can be used in the system (a list including the performance indexes and prices of available parts) and general technical knowledge (general restrictions; for example, the maximum length of a LAN (Local Area Network) cable).

[0075] The concretization control unit 203 uses the technical information and the like to generate concrete design information for each requirement information candidate from the viewpoint of system reliability, system consistency, appropriateness of the cost required for system construction, and the like.

[0076] For example, with regard to system consistency, the concretization control unit 203 selects components that satisfy the structured requirement information candidate from a list of available components, and if there is a combination of components that satisfies all requirements (purposes), it determines that the structured requirement information candidate is feasible. The concretization control unit 203 adopts the combination of components that is determined to be feasible as concrete design information of the requirement candidate information.

[0077] On the other hand, if there is no combination of parts that satisfies all the requirements, the instantiation control unit 203 determines that the structured requirement information candidate is not realizable.

[0078] Alternatively, the concretization control unit 203 generates specific design information for the requirements information candidate using the technical information and the performance index described in the structured requirements information candidate. The concretization control unit 203 refers to the cost and performance of the parts described in the technical information or common technical knowledge, and determines that design information cannot be generated for requirements information candidates that require extremely low cost or extremely high performance, or that are physically impossible to realize.

[0079] In this way, the concretization control unit 203 determines that a requirement information candidate that has yielded a concrete system configuration that optimizes at least one or more objectives (for example, system reliability, consistency, cost appropriateness) is "feasible."

[0080] Note that the algorithm for solving the multi-objective optimization problem is different from the gist of the present disclosure, and therefore a detailed description thereof will be omitted.

[0081] Alternatively, the concretization control unit 203 may utilize the automated design technology disclosed in Reference 1 below, which is specialized for system development, to determine whether each candidate requirement information can be realized and generate specific design information.

[0082] Reference 1: JP 2021-135625 A

[0083] Reference 1 discloses a technique for generating concrete design information by repeating an operation for gradually concretely configuring an abstract system included in given system requirements.

[0084] The automatic design algorithm disclosed in Reference 1 targets configuration information such as requirements written in a predetermined format. The configuration information is described by multiple components and the relationships between the components. For example, in the configuration information, the components are represented as nodes in a graph, and the relationships between the components are represented as edges in the graph. Each component and relationship has a unique ID, a type that indicates its type, attribute values, etc.

[0085] When elements (components, relationships between components) are abstract, automated design algorithms use concretization rules that define options for realizing the abstract elements (concretization methods). Furthermore, automated design algorithms take configuration information (requirements to be concretized) as input and derive design proposals by stepwise and exploratory concretization of the input. The path of this search is recorded to form a tree-structured search tree. The nodes of the search tree correspond to requirements, configuration proposals, or design results, and the edges correspond to single-stage concretization operations that generate configuration proposals from requirements or generate other configuration proposals or design results from configuration proposals.

[0086] The automated design algorithm performs a search process with the input requirements (requirements information) as the initial state and a specific design result as the target state. The automated design algorithm selects a state corresponding to a promising configuration plan and repeats the process of generating multiple next states by concretizing that configuration plan until a specific configuration is obtained. When the automated design algorithm first obtains a specific configuration plan, it outputs that specific configuration plan as the design result (design information).

[0087] Note that the automatic design algorithm (automatic design technology) is different from the gist of the present disclosure, and therefore a detailed description thereof will be omitted.

[0088] The concretization control unit 203 determines that a requirement information candidate is feasible if design information (system configuration) corresponding to the requirement information candidate is obtained using the technology disclosed in Reference 1. On the other hand, if design information corresponding to the requirement information candidate is not obtained, the concretization control unit 203 determines that the requirement information candidate is not feasible.

[0089] In this way, the concretization control unit 203 determines whether each requirement information candidate can be realized. The concretization control unit 203 passes the determination result of whether each requirement information candidate can be realized and specific design information if it can be realized to the information provision control unit 204.

[0090] Regardless of whether an algorithm for solving a multi-objective optimization problem or an automated design algorithm is used, requirement information candidates that have no errors or contradictions between elements (components, performance indicators) are judged to be "feasible." That is, in the process of generating specific design information for each requirement information candidate, the concretization control unit 203 eliminates requirement information candidates that have errors in their content or contradictions between elements, and selects requirement information candidates that have no defects from among the multiple requirement information candidates.

[0091] For example, if a solution (design information) is not output because the performance indexes in the requirements information candidate are inconsistent, it is interpreted that the requirements information candidate has a problem in terms of consistency or reliability.

[0092] The concretization control unit 203 passes the selected requirement information candidates and corresponding design information to the information provision control unit 204 .

[0093] For example, consider a case where, of the above four requirement information candidates, requirement information candidate 4 cannot obtain design information (reasonable design information in terms of cost, etc.) that achieves a communication speed of 100 Mbps on a mobile line, but design information can be obtained for the other requirement information candidates. In this case, requirement information candidates 1 to 3 are handed over to the information provision control unit 204 as feasible requirement information candidates.

[0094] In this way, the concretization control unit 203 generates design information of at least one or more structured requirement information candidates by concretizing at least one or more structured requirement information candidates. In other words, the concretization control unit 203 determines the feasibility of each of the at least one or more structured requirement information candidates by attempting to concretize each of the at least one or more structured requirement information candidates.

[0095] The information provision control unit 204 is a means for controlling the provision of information to the user. The information provision control unit 204 provides the user with the information acquired from the concretization control unit 203 (information obtained by concretizing the requirement information candidates).

[0096] More specifically, the information provision control unit 204 presents the design information etc. obtained by the concretization by the concretization control unit 203 to the user and requests the user to confirm the presented design information etc. For example, the information provision control unit 204 provides the user with information on requirement information candidates that are determined to be feasible among multiple requirement information candidates.

[0097] For example, the information provision control unit 204 displays the system requirements input by the user and the design information corresponding to the requirement information candidates determined to be "feasible" among the multiple requirement information candidates generated from the system requirements on the terminal 20. For example, the information provision control unit 204 displays a screen such as that shown in FIG.

[0098] In this way, the information provision control unit 204 provides the user with the design information etc. generated by the concretization control unit 203. Specifically, the information provision control unit 204 provides the user with the requirement information candidate that is determined to be feasible from among at least one or more structured requirement information candidates and the corresponding design information.

[0099] There may be cases where there are no requirement information candidates determined to be "feasible" by the concretization control unit 203. In this case, the information provision control unit 204 may notify the user of this (the absence of requirement information candidates determined to be feasible). In other words, when there are no requirement information candidates determined to be feasible, the information provision control unit 204 may notify the user of the absence of feasible design information.

[0100] The storage unit 205 is a means for storing information necessary for the operation of the assistance device 10.

[0101] The operation of the support device 10 can be summarized as shown in the flowchart of FIG.

[0102] The structuring control unit 202 of the support device 10 acquires a system request from a user (step S101).

[0103] The structuring control unit 202 generates multiple requirement information candidates from the acquired system requirements (step S102). Specifically, the structuring control unit 202 extracts components and performance indicators from the system requirements, and generates multiple new elements for each extracted element. The structuring control unit 202 generates multiple requirement information candidates by combining multiple elements obtained from each element.

[0104] The structuring control unit 202 structures the generated multiple requirement information candidates (step S103). For example, the structuring control unit 202 instructs the language model to convert each requirement information candidate into a predetermined format (for example, JSON format) and acquires the structured requirement information candidates.

[0105] The concretization control unit 203 generates specific design information for each structured requirement information candidate (step S104). The concretization control unit 203 determines that a requirement information candidate for which specific design information can be obtained is "realizable." The concretization control unit 203 determines that a requirement information candidate for which specific design information cannot be obtained is "not realizable."

[0106] The information provision control unit 204 provides information on the requirement information candidates that have been determined to be feasible (step S105).

[0107] Next, the operation of the support device 10 will be described from the perspective of data (information) handled by the support device 10.

[0108] As shown in Figure 7, multiple requirement information candidates are generated from the system requirements. These multiple requirement information candidates are structured. An attempt is made to concretize each structured requirement information candidate using an algorithm for solving a multi-objective optimization problem. In this process, requirement information candidates with errors in content or contradictions between elements (components, performance indicators) are judged to be "unrealizable." Requirement information candidates judged to be "realizable" are presented to the user.

[0109] [Device] Detailed description of the terminal 20 will be omitted. Examples of the terminal 20 include mobile terminal devices such as smartphones, mobile phones, game consoles, and tablets, as well as computers (personal computers, laptop computers). The terminal 20 can be any equipment or device that can accept user operations and communicate with the assistance device 10.

[0110] Next, a modified example of the first embodiment will be described.

[0111] <Variation 1> When there are multiple requirement information candidates that are determined to be feasible, the concretization control unit 203 may assign priorities to the multiple requirement information candidates. For example, the concretization control unit 203 calculates a score for each requirement information candidate that is determined to be feasible from the viewpoint of cost or performance.

[0112] For example, the instantiation control unit 203 calculates the cost required to realize the requirement information candidate by adding up the prices of each part adopted in the generated design information. The instantiation control unit 203 assigns a high score to a requirement information candidate with a low cost.

[0113] Alternatively, the instantiation control unit 203 calculates a performance index of a system realized by the generated design information. For example, the instantiation control unit 203 calculates the performance index of the system based on specifications related to the performance of adopted components. For example, in the case of a communication system, the slowest communication speed among the communication speeds of the elements (network line, router, hub, access point, receiving terminal, etc.) that make up the communication system is calculated as the system performance index (performance index related to communication speed). The instantiation control unit 203 assigns a high score to a requirement information candidate with a high performance index.

[0114] The concretization control unit 203 assigns a priority to each requirement information candidate based on the calculated score (for example, a score related to cost, a score related to performance, or the total value of the scores related to cost and performance). The concretization control unit 203 assigns a higher priority to a requirement information candidate with a higher score. The concretization control unit 203 treats a requirement information candidate with a higher priority (score) as a requirement information candidate with a higher possibility of realization.

[0115] The concretization control unit 203 may deliver, for each requirement information candidate determined to be feasible, specific design information together with accompanying information to the information provision control unit 204. For example, the concretization control unit 203 may deliver information such as the calculated score and priority to the information provision control unit 204 as accompanying information of the design information.

[0116] The information provision control unit 204 may provide information on requirement information candidates using accompanying information in addition to design information, etc. For example, the information provision control unit 204 selects requirement information candidates with high priority and presents them to the user.

[0117] In this way, the concretization control unit 203 may calculate a score from a predetermined viewpoint for each of at least one or more structured requirement information candidates. The information provision control unit 204 may determine (select) information to be provided to the user based on the score for each of at least one or more structured requirement information candidates.

[0118] <Variation 2> The support device 10 may accept a modification of the system requirement from the user and provide the user with requirement information candidates, design information, and associated information, etc., corresponding to the accepted system requirement. In this case, the concretization control unit 203 stores the system requirement input by the user in association with the generated requirement information candidates, design information, etc.

[0119] The concretization control unit 203 generates requirement information candidates, design information, etc. based on the system requirement newly input by the user. The concretization control unit 203 delivers the new system requirement, requirement information candidates, design information, etc., and the stored system requirement, requirement information candidates, design information, etc., to the information provision control unit 204.

[0120] For example, the information provision control unit 204 may summarize or emphasize design information generated based on new system requirements and provide the design information to the user.

[0121] Alternatively, the information provision control unit 204 may extract differences in the acquired design information, etc., and provide the newly generated design information to the user while emphasizing the extracted differences. Alternatively, the information provision control unit 204 may summarize (summarize using a language model), highlight, excerpt, etc. the newly generated design information, etc. For example, as shown in FIG. 8, the information provision control unit 204 may highlight a component, etc. newly added to the design information by displaying the added component in bold.

[0122] In this way, the information provision control unit 204 may provide the user with the result of executing at least one of a process of summarizing, extracting, and highlighting all or part of the design information or the like.

[0123] <Variation 3> In the above embodiment, when no requirement information candidate determined to be "realizable" is obtained, the information provision control unit 204 notifies the user of that fact. However, in such a case, the support device 10 regenerates the requirement information candidates by, for example, deleting some of the requirements included in each requirement information candidate. The support device 10 may re-execute the concretization process using the regenerated requirement information candidates.

[0124] For example, if a requirement information candidate including requirements A to E is determined to be "unrealizable," the concretization control unit 203 deletes one of requirements A to E and generates a new requirement information candidate. For example, the concretization control unit 203 generates a requirement information candidate including requirements A to D. The concretization control unit 203 re-executes the concretization process of the generated requirement information candidate.

[0125] If a requirement information candidate determined to be "realizable" cannot be obtained even after deleting a requirement (deleting any of A to E above), the concretization control unit 203 may increase the number of requirements to be deleted and generate new requirement information candidates, and execute a concretization process for the generated new requirement information candidates. For example, the concretization control unit 203 may execute a concretization process for requirement information candidates including requirements A to C, and determine whether the new requirement information candidates can be realized.

[0126] The concretization control unit 203 can obtain requirement information candidates that are determined to be feasible by repeating the deletion of requirements and the concretization process for new requirement information candidates. In particular, the concretization control unit 203 can obtain requirement information candidates from which contradictory requirements have been deleted (requirement information candidates that are determined to be feasible) by repeating the deletion of requirements and the concretization process for each of the multiple requirement information candidates generated by the structuring control unit 202.

[0127] The concretization control unit 203 passes the requirement information candidates determined to be feasible to the information provision control unit 204. The information provision control unit 204 provides the acquired requirement information candidates to the user. The concretization control unit 203 may also provide the user, via the information provision control unit 204, with information on requirements that were deleted to obtain the requirement information candidates determined to be feasible. Alternatively, when assigning scores to the requirement information candidates, the concretization control unit 203 may assign a higher score to requirement information candidates with fewer deleted requirements.

[0128] As described above, the support device 10 according to the first embodiment acquires system requirements from a user and generates multiple requirement information candidates from the acquired system requirements. The support device 10 converts each of the multiple requirement information candidates into a machine-processable format to generate structured requirement information candidates. The support device 10 determines the feasibility of each of the multiple structured requirement information candidates in the process of verifying the concretization of each of the multiple structured requirement information candidates. The support device 10 also acquires corresponding design information (system configuration proposal) by concretizing each requirement information candidate. The support device 10 provides the user with requirement information that is determined to be feasible (requirement information candidates for which specific design proposals have been obtained) and the corresponding design information. The user can generate more accurate requirement information (requirements definition) by verifying the provided requirement information and design information.

[0129] Here, it is assumed that the system requirements acquired by the support device 10 contain various deficiencies. Specifically, it is assumed that the system requirements lack information necessary for system design or contain contradictions. The support device 10 acquires the system requirements including various problems, etc., and generates requirements information to be used in a subsequent process (requirements definition process) based on the acquired system requirements. For example, the support device 10 generates a requirements definition that includes information on the system components (hardware, software) that are to be realized by the system requirements and performance indicators related to the performance of the system, etc.

[0130] Furthermore, the support device 10 acquires system requirements with diverse vocabulary and expression methods (system requirements that are easy for humans to understand). That is, the support device 10 acquires system requirements that are unstructured and have a wide variety of expressions. The support device 10 generates requirement information candidates based on the acquired system requirements. The support device 10 converts the generated requirement information candidates into a format in which the vocabulary and expression methods are strictly defined (a format that can be handled by algorithms for multi-objective optimization problems, etc.). That is, the support device 10 generates structured requirement information candidates with a small variety of expressions. Generating structured requirement information candidates makes it easy to apply various algorithms.

[0131] [Second embodiment] Next, the second embodiment will be described in detail with reference to the drawings.

[0132] In the second embodiment, the support device 10 will be described as using past design documents of systems that have been designed in the past, guidelines related to the system to be designed, standard specifications, etc. to verify candidate requirement information (generate specific design information).

[0133] The configuration of the information processing system according to the second embodiment can be the same as that of the first embodiment, and therefore a description corresponding to FIG. 3 will be omitted.

[0134] The following description will focus on the differences between the first and second embodiments.

[0135] 9 is a diagram illustrating an example of a processing configuration (processing module) of the assistance device 10 according to an embodiment of the present disclosure. Referring to FIG. 9, a knowledge management unit 206 is added to the configuration of the assistance device 10 according to the first embodiment.

[0136] The knowledge management unit 206 is a means for controlling and managing the above-mentioned past design documents, guidelines, standard specifications, product catalogs, etc. The knowledge management unit 206 structures past know-how, technical common sense, etc. in system design.

[0137] The knowledge management unit 206 acquires past design documents and the like as “system design information.” For example, a system administrator or the like inputs past design documents and the like into the support device 10 as system design information.

[0138] The knowledge management unit 206 extracts information such as constraints in system design, common technical knowledge, rules of thumb, etc. from the acquired system design information as "knowledge information."

[0139] For example, frequently used components, performance indicators, parameter settings, or combinations thereof can be obtained from past design documents as knowledge information. Alternatively, recommended components, performance indicators, parameter settings, or combinations thereof can be obtained from guidelines and standard specifications as knowledge information. Alternatively, part costs and performance can be obtained from product catalogs as knowledge information.

[0140] That is, the knowledge management unit 206 extracts know-how such as constraints in system design and common technical knowledge as knowledge information from past design documents, etc. For example, the knowledge management unit 206 extracts knowledge information by inputting the acquired system design information together with appropriate instructions into a language model.

[0141] For example, the knowledge management unit 206 extracts constraint information relating to components used in the system and system performance.

[0142] For example, the knowledge management unit 206 extracts information on constraints on the cost and performance of parts from a product catalog. For example, the knowledge management unit 206 extracts constraint information such as "a reasonable price for a camera should be A yen or less," "there are no cameras with a resolution of B pixels or more," and "there are no cameras with a resolution of D pixels or more that cost C yen or less."

[0143] Alternatively, the knowledge management unit 206 extracts constraints (constraint information) related to system performance. For example, the knowledge management unit 206 extracts information related to performance that is difficult to achieve in a system (e.g., video quality and communication delay) as constraint information. For example, the knowledge management unit 206 extracts constraint information such as "video quality of 10 Mbps or more and communication delay of 5 ms or less are difficult to achieve in a system."

[0144] Alternatively, the knowledge management unit 206 extracts standard information relating to component and system performance standards.

[0145] For example, the knowledge management unit 206 extracts standard parts that are often used in systems as standard information. Alternatively, the knowledge management unit 206 extracts performance that is considered standard in a system (for example, a communication speed of 100 Mbps or less is standard) as standard information.

[0146] The knowledge management unit 206 structures the acquired knowledge information and stores it in the storage unit 205. The knowledge management unit 206 converts the acquired knowledge information into a format that can be referenced by the concretization control unit 203. For example, the knowledge management unit 206 structures the knowledge information by inputting the knowledge information together with appropriate instructions into a language model.

[0147] Note that an engineer or the like may generate knowledge information and register the generated knowledge information in the support device 10. Alternatively, an engineer or the like may register structured knowledge information in the support device 10. The knowledge management unit 206 may store the structured knowledge information in the storage unit 205 using any means.

[0148] In this way, the knowledge management unit 206 acquires information related to system design as system design information, and extracts know-how and the like in system design from the acquired system design information as knowledge information. The knowledge management unit 206 structures the extracted knowledge information and stores it in the storage unit 205.

[0149] The concretization control unit 203 according to the second embodiment can concretize at least one structured requirement information candidate by using the structured knowledge information. That is, the concretization control unit 203 uses the knowledge information stored in the storage unit 205 to determine the feasibility of the requirement information candidate (to generate concrete design information).

[0150] In this way, the concretization control unit 203 may generate concrete design information for each requirement information candidate using not only general technical information but also knowledge information specific to the target system, thereby enabling the concretization control unit 203 to generate more accurate design information.

[0151] Next, a modified example of the second embodiment will be described.

[0152] <Variation 1> The concretization control unit 203 may add predetermined constraints or new components to the requirement information candidates determined to be unrealizable (requirement information candidates for which no specific design information has been obtained) to determine whether they can be realized. In this case, the concretization control unit 203 may determine the predetermined constraints and the components to be added based on knowledge information.

[0153] For example, when general technical information is used, consider a case where a requirement information candidate of "video quality of 10 Mbps or more, communication delay of 1 ms or less" is determined to be impossible to realize. In this case, the concretization control unit 203 refers to the performance-related constraint information in the knowledge information, "video quality of 10 Mbps or more and communication delay of 5 ms or less are difficult to achieve at the same time," and applies a constraint (modification) to the requirement information candidate.

[0154] For example, the concretization control unit 203 imposes a constraint on the performance index "communication delay" such as "communication delay 5 ms or less." The concretization control unit 203 determines whether the requirement information candidate to which the constraint is imposed can be realized (whether concrete design information can be generated).

[0155] Alternatively, the concretization control unit 203 may add new components obtained from knowledge information to a requirement information candidate that has been determined to be unrealizable, and determine whether the requirement information candidate can be realized.

[0156] If specific design information is obtained, the instantiation control unit 203 sets the requirement information candidate before the constraints are added as a "conditional requirement information candidate." If specific design information is not obtained even after adding constraints and components, the instantiation control unit 203 treats the requirement information candidate before the constraints, etc. are added as infeasible.

[0157] In this way, the concretization control unit 203 may add predetermined constraints or components to the requirement information candidate and determine whether the requirement information candidate can be realized. For a requirement information candidate that is determined to be realizable by adding predetermined constraints or the like, the concretization control unit 203 determines that the added constraints or components are insufficient.

[0158] Note that, for a requirement information candidate that is determined to be unrealizable even after adding constraints, etc., the concretization control unit 203 may determine that there is an error in the selection of the constraints, etc. to be added. In this case, the concretization control unit 203 may add constraints or components from a different perspective to the requirement information candidate instead of the constraints, etc. that have already been added, and determine whether or not it can be realized.

[0159] The concretization control unit 203 delivers the generated conditional requirement information candidates and corresponding design information to the information provision control unit 204 .

[0160] When acquiring the conditional requirement information candidates, the information provision control unit 204 may present the conditional requirement information candidates and design information to the user in a manner that allows the user to distinguish them from normal requirement information candidates.

[0161] In this way, the concretization control unit 203 may add constraints or components obtained from knowledge information to at least one or more structured requirement information candidates, and concretize at least one or more structured requirement information candidates to which the constraints or components have been added.

[0162] <Variation 2> The information provision control unit 204 may reflect the presence or absence of addition of constraints, etc. to the requirement information candidate and the content of the addition in the score (priority). Specifically, the information provision control unit 204 may assign a lower score to a requirement information candidate to which many constraints, etc. have been added. Alternatively, the information provision control unit 204 may assign a weight to the added content and assign a score to the requirement information candidate.

[0163] Alternatively, the information provision control unit 204 may assign scores to requirement information candidates using knowledge information (information obtained from past design documents, guidelines (security guidelines), standard specifications, etc.). For example, the information provision control unit 204 assigns a high score to a requirement information candidate that employs a component that has been used frequently in past designs. Alternatively, the information provision control unit 204 assigns a high score to a requirement information candidate that employs a component that has been used more recently in past designs. Alternatively, the information provision control unit 204 assigns a high score to a requirement information candidate that employs a component whose use is recommended in a security guideline or standard specification. On the other hand, the information provision control unit 204 assigns a low score to a requirement information candidate that employs a component whose use is recommended not to be used in a security guideline or standard specification.

[0164] As described above, the support device 10 according to the second embodiment may generate knowledge information using system design information such as past design documents, guidelines, standard specifications, etc. The support device 10 can more accurately determine whether the requirement information candidate can be realized by specifying the requirement information candidate using the knowledge information.

[0165] Next, the hardware of each device constituting the information processing system will be described. Fig. 10 is a diagram showing an example of the hardware configuration of the support device 10.

[0166] The support device 10 can be configured by an information processing device (so-called computer), and has the configuration exemplified in Fig. 10. For example, the support device 10 includes a processor 311, a memory 312, an input / output interface 313, and a communication interface 314. The components such as the processor 311 are connected by an internal bus or the like, and are configured to be able to communicate with each other.

[0167] However, the configuration shown in Fig. 10 is not intended to limit the hardware configuration of the support device 10. The support device 10 may include hardware not shown, and may not include the input / output interface 313 as necessary. Furthermore, the number of processors 311 and the like included in the support device 10 is not intended to be limited to the example shown in Fig. 10, and for example, the support device 10 may include multiple processors 311.

[0168] The processor 311 is a programmable device such as a central processing unit (CPU), a micro processing unit (MPU), a digital signal processor (DSP), a tensor processing unit (TPU), or a graphics processing unit (GPU). Alternatively, the processor 311 may be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or other device. The processor 311 executes various programs including an operating system (OS).

[0169] The memory 312 is a random access memory (RAM), a read only memory (ROM), a hard disk drive (HDD), a solid state drive (SSD), etc. The memory 312 stores an OS program, application programs, and various data.

[0170] The input / output interface 313 is an interface for a display device and an input device (not shown). The display device is, for example, a liquid crystal display. The input device is, for example, a device that accepts user operations such as a keyboard or a mouse.

[0171] The communication interface 314 is a circuit, module, etc. that communicates with other devices. For example, the communication interface 314 includes a network interface card (NIC).

[0172] The functions of the assistance device 10 are realized by various processing modules. The processing modules are realized, for example, by the processor 311 executing a program stored in the memory 312. The program can be recorded on a computer-readable storage medium. The storage medium can be a non-transitory medium such as a semiconductor memory, a hard disk, a magnetic recording medium, or an optical recording medium. That is, the present invention can also be embodied as a computer program product. The program can be downloaded via a network or updated using a storage medium storing the program. The processing modules can also be realized by a semiconductor chip.

[0173] The terminal 20 can also be configured by an information processing device, similar to the support device 10, and its basic hardware configuration is no different from that of the support device 10, so a description thereof will be omitted.

[0174] The support device 10, which is an information processing device, is equipped with a computer, and the functions of the support device 10 can be realized by causing the computer to execute a program. Furthermore, the support device 10 executes a control method for the support device 10 (information processing device) by the program.

[0175] [Variations] The configuration, operation, etc. of the information processing system described in the above embodiment are merely examples, and are not intended to limit the configuration, etc. of the system.

[0176] In the above embodiment, the assistance device 10 extracts multiple elements from a system requirement and then generates new elements by interpreting the extracted elements from various perspectives. However, the assistance device 10 may directly obtain the new elements from the system requirement by inputting the system requirement and an appropriate prompt into a language model.

[0177] The support device 10 may generate requirement information candidates using knowledge information generated from system design information. That is, the support device 10 may incorporate components and constraints essential to system design into requirement information candidates in advance by referring to the knowledge information.

[0178] The support device 10 may use a language model to specify requirement information candidates instead of or in addition to an algorithm for solving a multi-objective optimization problem or an automatic design algorithm. For example, the support device 10 may generate a prompt including requirement information candidates and instructions for generating a specific configuration plan for the requirement information candidates, and input the prompt into the language model to obtain the specific configuration plan.

[0179] In the above embodiment, the support device 10 has been described for structuring requirement information candidates and knowledge information using the JSON format as an example. However, it goes without saying that the support device 10 may convert requirement information candidates, etc., into other formats. For example, the support device 10 may convert requirement information candidates into the RDF (Resource Description Framework) format or the XML (Extensible Markup Language) format. The support device 10 may convert requirement information candidates into any machine-processable format and structure the requirement information candidates.

[0180] The assistance device 10 may acquire an input system request (request information) from a user using a voice recognition technology. Specifically, the structuring control unit 202 acquires voice data via a microphone provided in the terminal 20. The structuring control unit 202 acquires the system request converted into text by applying the voice recognition technology to the voice data.

[0181] The support device 10 can accept system requests in any format. For example, the support device 10 acquires system requirements written in spoken language such as minutes of a meeting, system requirements such as a draft of a requirements definition, etc. In other words, there is no restriction on the format (form) of the system request acquired by the support device 10.

[0182] The support device 10 may acquire system requirements using a technology related to generating minutes. For example, the structuring control unit 202 generates minutes from text data or audio data related to a meeting between a vendor company and a client company. The structuring control unit 202 may treat the generated minutes as system requirements. Alternatively, the support device 10 may generate (acquire) system requirements by utilizing a learning model that generates a summary from the minutes, as needed.

[0183] In the above embodiment, an example has been described in which a language model is implemented in the assistance device 10. However, the language model may be implemented in a server or the like different from the assistance device 10. In this case, the assistance device 10 generates a prompt to be input to the language model and transmits the generated prompt to an external server (a server in which the language model is implemented). The assistance device 10 may obtain an output of the language model (for example, structured requirement information candidates, etc.) from the external server.

[0184] The support device 10 may hold general technical information and knowledge information for each technical field (each type of system). For example, the support device 10 may store technical information and knowledge information for each system, such as an information distribution system, an online conference system, and a face authentication system. In this case, before providing a service to a user, the support device 10 may acquire the type of system that the user is designing, and generate design information corresponding to the acquired system.

[0185] In the above embodiment, the support device 10 is described as a server in a server-client system. However, the support device 10 may be implemented as a user terminal 20 on which a predetermined application is installed.

[0186] In the flow charts (flowcharts, sequence diagrams) used in the above explanation, multiple steps (processes) are described in order, but the execution order of the steps executed in the embodiments is not limited to the order described. In the embodiments, the order of the illustrated steps can be changed to the extent that the content is not affected, such as by executing each process in parallel.

[0187] The above-described embodiments have been described in detail to facilitate understanding of the present disclosure, and it is not intended that all of the above-described configurations are required. Furthermore, when multiple embodiments are described, each embodiment may be used alone or in combination. For example, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace part of the configuration of one embodiment with another configuration.

[0188] From the above explanation, it is clear that the present invention has industrial applicability, and the present invention can be suitably applied to information processing systems that support system design by users.

[0189] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes.

[0190] [Appendix 1] a structuring control means for acquiring requirement information written in a natural language, generating at least one requirement information candidate based on the acquired requirement information, and structuring the generated at least one requirement information candidate; a concretization control means for concretizing the at least one structured requirement information candidate; An information processing device comprising: [Appendix 2] 2. The information processing device according to claim 1, further comprising an information provision control means for providing a user with information obtained by concretizing the at least one structured requirement information candidate. [Appendix 3] the concretization control means generates design information of the at least one or more structured requirement information candidates by concretizing the at least one or more structured requirement information candidates; 3. The information processing device according to claim 2, wherein the information provision control means provides the generated design information to the user. [Appendix 4] the concretization control means determines the feasibility of each of the at least one or more structured requirement information candidates by attempting to concretize each of the at least one or more structured requirement information candidates; The information processing device described in Appendix 3, wherein the information provision control means provides the user with the requirement information candidate that is determined to be feasible among the at least one or more structured requirement information candidates and the corresponding design information, or if there are no requirement information candidates that are determined to be feasible, notifies the user of the absence of feasible design information. [Appendix 5] The system further comprises a knowledge management means for acquiring information relating to system design as system design information, extracting know-how in the system design from the acquired system design information as knowledge information, and structuring the extracted knowledge information; 5. The information processing device according to claim 1, wherein the concretization control means uses the structured knowledge information to concretize the at least one structured requirement information candidate. [Appendix 6] The information processing device described in Appendix 5, wherein the concretization control means adds constraints or components obtained from the knowledge information to the at least one or more structured requirement information candidates, and concretizes the at least one or more structured requirement information candidates to which the constraints or components have been added. [Appendix 7] The information processing device according to any one of appendices 2 to 4, wherein the information provision control means provides the user with the results of performing at least one of a process of summarizing, extracting, and highlighting all or part of the design information. [Appendix 8] the concretization control means calculates a score from a predetermined viewpoint for each of the at least one structured requirement information candidate; The information processing device according to any one of appendices 2 to 4, wherein the information provision control means determines information to be provided to the user based on a score of each of the at least one or more structured requirement information candidates. [Appendix 9] The information processing device described in any one of Appendices 2 to 4, wherein the structuring control means generates multiple new elements corresponding to each of the elements by interpreting each element included in the acquired requirement information from different perspectives, and generates the at least one or more requirement information candidates by combining the multiple generated new elements. [Appendix 10] a structuring control step of acquiring requirement information written in a natural language, generating at least one requirement information candidate based on the acquired requirement information, and structuring the generated at least one requirement information candidate; a concretization control step of concretizing the at least one structured requirement information candidate; A control method for an information processing device comprising: [Appendix 11] The control method for an information processing device according to claim 10, further comprising an information provision control step of providing a user with information obtained by concretizing the at least one structured requirement information candidate. [Appendix 12] the concretization control step generates design information of the at least one or more structured requirement information candidates by concretizing the at least one or more structured requirement information candidates; 12. The control method for an information processing device according to claim 11, wherein the information provision control step provides the generated design information to the user. [Appendix 13] the concretization control step determines the feasibility of each of the at least one or more structured requirement information candidates by attempting to concretize each of the at least one or more structured requirement information candidates; The control method of an information processing device described in Appendix 12, wherein the information provision control step provides the user with requirement information candidates that are determined to be feasible among the at least one or more structured requirement information candidates and the corresponding design information, or, if there are no requirement information candidates that are determined to be feasible, notifies the user of the absence of feasible design information. [Appendix 14] The method further comprises a knowledge management step of acquiring information related to system design as system design information, extracting know-how in the system design from the acquired system design information as knowledge information, and structuring the extracted knowledge information; The control method for an information processing device according to any one of appendices 10 to 13, wherein the concretization control step uses the structured knowledge information to concretize at least one structured requirement information candidate. [Appendix 15] The control method for an information processing device described in Appendix 14, wherein the concretization control step adds constraints or components obtained from the knowledge information to the at least one or more structured requirement information candidates, and concretizes the at least one or more structured requirement information candidates to which the constraints or components have been added. [Appendix 16] The control method of an information processing device according to any one of appendices 11 to 13, wherein the information provision control step provides the user with the results of performing at least one of a process of summarizing, extracting, and highlighting all or part of the design information. [Appendix 17] the concretization control step calculates a score from a predetermined viewpoint for each of the at least one structured requirement information candidate; A control method for an information processing device described in any one of Appendices 11 to 13, wherein the information provision control process determines information to be provided to the user based on the score of each of the at least one or more structured requirement information candidates. [Appendix 18] The control method of an information processing device described in any one of Appendices 11 to 13, wherein the structuring control process generates multiple new elements corresponding to each of the elements by interpreting each element contained in the acquired requirement information from different perspectives, and generates the at least one or more requirement information candidates by combining the multiple generated new elements. [Appendix 19] The computer installed in the information processing device a structuring control process for acquiring requirement information written in a natural language, generating at least one requirement information candidate based on the acquired requirement information, and structuring the generated at least one requirement information candidate; a concretization control process for concretizing the at least one structured requirement information candidate; A program to execute. [Appendix 20] The program according to claim 19, further comprising an information provision control process for providing a user with information obtained by concretizing the at least one structured requirement information candidate. [Appendix 21] the concretization control process generates design information of the at least one or more structured requirement information candidates by concretizing the at least one or more structured requirement information candidates; 21. The program according to claim 20, wherein the information provision control process provides the generated design information to the user. [Appendix 22] the concretization control process determines the feasibility of each of the at least one or more structured requirement information candidates by attempting to concretize each of the at least one or more structured requirement information candidates; The program described in Appendix 21, wherein the information provision control process provides the user with requirement information candidates that are determined to be feasible among the at least one or more structured requirement information candidates and the corresponding design information, or, if there are no requirement information candidates that are determined to be feasible, notifies the user of the absence of feasible design information. [Appendix 23] acquiring information related to system design as system design information, extracting know-how in the system design from the acquired system design information as knowledge information, and structuring the extracted knowledge information; 23. The program according to any one of appendices 19 to 22, wherein the concretization control process uses the structured knowledge information to concretize the at least one structured requirement information candidate. [Appendix 24] The program described in Appendix 23, wherein the concretization control process adds constraints or components obtained from the knowledge information to the at least one or more structured requirement information candidates, and concretizes the at least one or more structured requirement information candidates to which the constraints or components have been added. [Appendix 25] The program described in any one of Appendices 20 to 22, wherein the information provision control process provides the user with the results of executing at least one of a process of summarizing, extracting, and highlighting all or part of the design information. [Appendix 26] the concretization control process calculates a score from a predetermined viewpoint for each of the at least one or more structured requirement information candidates; The program according to any one of appendices 20 to 22, wherein the information provision control process determines information to be provided to the user based on the score of each of the at least one or more structured requirement information candidates. [Appendix 27] The program described in any one of Appendices 20 to 22, wherein the structuring control process generates multiple new elements corresponding to each of the elements by interpreting each element included in the acquired requirement information from different perspectives, and generates the at least one or more requirement information candidates by combining the multiple generated new elements.

[0191] Furthermore, some or all of the configurations described in Supplementary Notes 2 to 9, which are dependent on Supplementary Note 1, may also be dependent on Supplementary Notes 10 and 19 in the same dependent relationship as Supplementary Notes 2 to 9. Furthermore, not limited to Supplementary Notes 1, 10, and 19, some or all of the configurations described as Supplements may be made dependent on various hardware, software, various recording means for recording software, or systems, within the scope of each of the above-mentioned embodiments.

[0192] The disclosures of the above-cited prior art documents are incorporated herein by reference. Although the embodiments of the present invention have been described above, the present invention is not limited to these embodiments. Those skilled in the art will understand that these embodiments are merely illustrative and that various modifications are possible without departing from the scope and spirit of the present invention. In other words, the present invention naturally includes various modifications and alterations that may be made by those skilled in the art in accordance with the entire disclosure, including the claims, and the technical concepts thereof. [Explanation of symbols]

[0193] 10 Support equipment 20 terminals 100 Information processing device 101 Structured Control Measures 102 Concretization control means 201 Communication control unit 202 Structured control section 203 Instantiation control section 204 Information provision control section 205 Storage section 206 Knowledge Management Department 311 processor 312 memory 313 Input / Output Interface 314 Communication Interface

Claims

1. a structuring control means for acquiring requirement information written in a natural language, generating at least one requirement information candidate based on the acquired requirement information, and structuring the generated at least one requirement information candidate; a concretization control means for concretizing the at least one structured requirement information candidate; An information processing device comprising:

2. 2. The information processing apparatus according to claim 1, further comprising information provision control means for providing a user with information obtained by instantiating said at least one structured requirement information candidate.

3. the concretization control means generates design information of the at least one or more structured requirement information candidates by concretizing the at least one or more structured requirement information candidates; The information processing apparatus according to claim 2 , wherein said information provision control means provides said generated design information to said user.

4. the concretization control means determines the feasibility of each of the at least one or more structured requirement information candidates by attempting to concretize each of the at least one or more structured requirement information candidates; 4. The information processing device according to claim 3, wherein the information provision control means provides the user with requirement information candidates that are determined to be feasible among the at least one structured requirement information candidate and the corresponding design information, or, if there are no requirement information candidates that are determined to be feasible, notifies the user of the absence of feasible design information.

5. The system further comprises a knowledge management means for acquiring information relating to system design as system design information, extracting know-how in the system design from the acquired system design information as knowledge information, and structuring the extracted knowledge information; The information processing apparatus according to claim 1 , wherein the concretization control means concretizes the at least one structured requirement information candidate by using the structured knowledge information.

6. 6. The information processing device according to claim 5, wherein the concretization control means adds constraints or components obtained from the knowledge information to the at least one or more structured requirement information candidates, and concretizes the at least one or more structured requirement information candidates to which the constraints or components have been added.

7. 5. The information processing device according to claim 2, wherein the information provision control means provides the user with a result of executing at least one of a process of summarizing, extracting, and highlighting all or part of the design information.

8. the concretization control means calculates a score from a predetermined viewpoint for each of the at least one structured requirement information candidate; The information processing apparatus according to claim 2 , wherein the information provision control means determines information to be provided to the user based on a score of each of the at least one or more structured requirement information candidates.

9. The information processing device described in any one of claims 2 to 4, wherein the structuring control means generates multiple new elements corresponding to each of the elements by interpreting each element contained in the acquired requirement information from different perspectives, and generates the at least one or more requirement information candidates by combining the multiple generated new elements.

10. a structuring control step of acquiring requirement information written in a natural language, generating at least one requirement information candidate based on the acquired requirement information, and structuring the generated at least one requirement information candidate; a concretization control step of concretizing the at least one structured requirement information candidate; A control method for an information processing device comprising:

11. The computer installed in the information processing device a structuring control process for acquiring requirement information written in a natural language, generating at least one requirement information candidate based on the acquired requirement information, and structuring the generated at least one requirement information candidate; a concretization control process for concretizing the at least one structured requirement information candidate; A program to execute.

Images