Design support system, design support method, and program

Abstract

To provide a system that can reduce the user's burden in system model creation and generate an appropriate system model that meets a user's intent.SOLUTION: A design support system includes: an input information analysis unit configured to analyze user input information related to a system model; a model candidate identification unit configured to identify, based on analysis results of the input information, a system model to be generated from system model information containing multiple types of system model templates registered therein; an information extraction unit configured to extract, based on the analysis results of the input information, necessary information to be used in generating the system model from a database storing design-related information; and a system model generation unit configured to use the extracted necessary information and a template of the system model to be generated to generate the system model based on the input information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a design support system, a design support method, and a program, and more particularly to a technology for supporting the creation of a system model related to product design. [Background technology]

[0002] In recent years, as products have become more complex, product design has also become more complex, requiring the consideration of multiple areas, such as electrical circuits and strength against vibration. Furthermore, product design often requires the simultaneous satisfaction of multiple KPIs (Key Performance Indexes), such as environmental friendliness, reliability, and safety, in addition to product performance. The use of system models has been proposed as one method for designing such increasingly complex products.

[0003] A system model is a cross-sectional model of various product-related areas, and describes them structurally. Expressing product design in a system model eliminates the ambiguity inherent in natural language expressions and the ambiguity of relationships between elements, leading to more efficient product design. Furthermore, using a system model makes it easier to identify the impact of design changes on existing functions, for example.

[0004] Additionally, MBSE (Model-Based Systems Engineering) is an advanced form of system modeling. MBSE correlates the configurations of different areas, such as the product's component structure, required functions, use cases, design parameters, and internal processing flow, and can express them in a visually easy-to-understand image by describing them in a modeling language such as SysML (Systems Modeling Language).

[0005] However, creating system models, including MBSE models, requires highly specialized knowledge of system modeling and requires a significant amount of man-hours, which is a problem. Therefore, there is a demand for technology to support the creation of system models.

[0006] Patent Document 1 discloses a technology related to the creation of a system model. Specifically, Patent Document 1 states that "a storage device is provided that stores parameters used to create a model, tools used to create a model, and model templates for multiple components that make up a system, and the model templates and parameters for the multiple components are read out in accordance with instructions input by a user, models of the multiple components are created by assigning parameters to the model templates for the multiple components, and the multiple component models are combined to create a single system model by reading out and executing the tool." [Prior art documents] [Patent documents]

[0007] [Patent Document 1] Japanese Patent Application Laid-Open No. 2006-343858 Summary of the Invention [Problem to be solved by the invention]

[0008] The technology of Patent Document 1 creates a system model of components by using template models of multiple components and assigning parameters to each template model of the component. However, the technology of this document does not take into consideration the creation of system models other than component models. Therefore, it is considered difficult for the technology of this document to solve the above-mentioned problems when creating a system model related to a domain (category) other than components or when creating an MBSE model that associates submodels across multiple domains.

[0009] The present invention has been made in view of the above-mentioned problems, and aims to reduce the burden on the user involved in creating a system model and to generate an appropriate system model that meets the user's intentions. [Means for solving the problem]

[0010] The present application includes a plurality of means for solving at least part of the above-described problems, examples of which are as follows: A design support system according to one aspect of the present invention for solving the above-described problems includes an input information analysis unit that analyzes input information related to a system model from a user, a model candidate identification unit that identifies a system model to be generated from system model information in which templates of multiple types of system models are registered based on a result of the analysis of the input information, an information extraction unit that extracts necessary information to be used in generating the system model from a database in which information related to design is stored based on a result of the analysis of the input information, and a system model generation unit that generates a system model according to the input information using the extracted necessary information and the template of the system model to be generated. [Effects of the Invention]

[0011] According to the present invention, it is possible to reduce the burden on the user involved in creating a system model and to generate an appropriate system model that meets the user's intentions.

[0012] Problems, configurations, and effects other than those described above will become clear from the following description of the embodiments. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a diagram illustrating an example of a schematic configuration of a design support system according to a first embodiment. [Figure 2A] FIG. 10 is a diagram illustrating an example of system model information. [Figure 2B] FIG. 10 is a diagram showing an example of information registered in a model image. [Figure 3] FIG. 10 is a flow chart illustrating an example of a design support process. [Figure 4A] FIG. 10 is a diagram for explaining generation of a system model. [Figure 4B] FIG. 10 is a diagram illustrating an example of a generated system model. [Figure 5]FIG. 1 is a diagram illustrating the generation of a system model composed of multiple submodels. [Figure 6] FIG. 10 is a diagram illustrating an example of a schematic configuration of a design support system according to a modified example. [Figure 7] FIG. 1 illustrates an example of a hardware configuration of a design support system. DETAILED DESCRIPTION OF THE INVENTION

[0014] The following embodiments are examples for explaining the present invention, and some omissions and simplifications have been made as appropriate for clarity of explanation. The present invention can be implemented in various other forms. Furthermore, unless otherwise specified, each component may be singular or plural.

[0015] Furthermore, in order to facilitate understanding of the invention, the position, size, shape, range, etc. of each component shown in the drawings may not represent the actual position, size, shape, range, etc. Therefore, the present invention is not necessarily limited to the position, size, shape, range, etc. disclosed in the drawings.

[0016] Furthermore, various types of information may be described using expressions such as "table," "list," and "queue," but the various types of information may be expressed using data structures other than these. For example, various types of information such as "XX table," "XX list," and "XX queue" may be expressed as "XX information." When describing identification information, expressions such as "identification information," "identifier," "name," "ID," and "number" are used, but these are interchangeable.

[0017] In addition, when there are multiple components having the same or similar functions, they may be described by using the same reference numeral with different subscripts, or when there is no need to distinguish between these multiple components, the subscripts may be omitted.

[0018] In addition, in the embodiments, there may be cases where processing performed by executing a program is described. Here, a computer executes the program using a processor (e.g., a CPU or a GPU), and performs processing defined by the program while using storage resources (e.g., memory) and interface devices (e.g., communication ports). Therefore, the processor may be the entity that executes the program and performs the processing.

[0019] Similarly, the entity that executes the program and performs the processing may be a controller, device, system, computer, or node having a processor. The entity that executes the program and performs the processing may be any computing unit, and may include a dedicated circuit that performs specific processing. Here, the dedicated circuit is, for example, an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), or a CPLD (Complex Programmable Logic Device).

[0020] A program may be installed on a computer from a program source. The program source may be, for example, a program distribution server or a computer-readable storage medium. When the program source is a program distribution server, the program distribution server may include a processor and a storage resource for storing the program to be distributed, and the processor of the program distribution server may distribute the program to be distributed to other computers. In addition, in an embodiment, two or more programs may be realized as one program, or one program may be realized as two or more programs.

[0021] Hereinafter, each embodiment of the present invention will be described with reference to the drawings.

[0022] First Embodiment <Outline of the design support system> 1 is a diagram showing an example of a schematic configuration of a design support system 1000 according to this embodiment. The design support system 1000 is realized by a computer 100 that performs calculation processing, and is a system that supports a user's product design by generating a system model according to instructions or requests from the user (for example, a designer who designs a product).

[0023] Specifically, when the design support system 1000 receives input information from a user regarding a system model (for example, user instructions or requests regarding the system model, hereinafter sometimes referred to as user input information), it analyzes the content of the user input information and, based on the analysis results, identifies (selects) an appropriate system model template from a database.

[0024] Furthermore, when the identified system model template includes multiple submodels, the design support system 1000 identifies and associates the interrelationships between the submodels based on the analysis results of the user input information.

[0025] Furthermore, the design support system 1000 identifies a predetermined prompt based on the analysis result of the user input information, and extracts information required for generating a system model from a database of design information using an information extraction model (for example, a generation AI).

[0026] Furthermore, the design support system 1000 uses the system model template and the extracted information to generate and present a system model that meets the user's request or the like.

[0027] Such a design support system 1000 can reduce the burden on the user involved in creating a system model, and can generate an appropriate system model that meets the user's intentions.

[0028] <Functional configuration of design support system 1000> As shown in FIG. 1, the design support system 1000 is realized by a computer 100, such as a server device or a personal computer, and has an input receiving unit 110, an output information generating unit 120, a communication unit 130, a memory unit 140, and a processing unit 150.

[0029] The input accepting unit 110 is a functional unit that accepts user input information related to the system model via a predetermined input device (for example, an input device included in the design support system 1000, such as a keyboard or a microphone). Specifically, the input accepting unit 110 accepts user input information of various contents in natural language, such as, for example, "I would like to check the functions defined in the digital camera," "When designing the digital camera, I would like to see the relationship between the safety requirement specifications and related parts," or "I would like to review the requirements while ensuring the safety of the digital camera. I would also like to check changes in the part structure that affect the requirements." The input format of the user input information may be either text input or voice input.

[0030] The output information generating unit 120 is a functional unit that generates various types of output information, such as screen information that accepts user input information and screen information that shows the calculation results of the generated system model, etc. The output information generating unit 120 also outputs the generated output information to an output device (e.g., a display) included in the design support system 1000.

[0031] The communication unit 130 is a functional unit that communicates information with an external device (for example, an external device such as a cloud server or a terminal device used by a user). Specifically, the communication unit 130 acquires various types of information used in the arithmetic processing of the design support system 1000 from the external device via a network. The communication unit 130 also transmits information generated by the design support system 1000 to the external device via the network.

[0032] The storage unit 140 is a functional unit for storing various information. Specifically, the storage unit 140 has a design information database 141, a system model database 142, an information extraction model database 143, and a prompt database 144.

[0033] The design information database 141 stores various pieces of design-related information. Specifically, the design information database 141 stores various types of design information (for example, requirement specifications, function definition documents, parts information, design review documents, standard information, product information, CAD (Computer-Aided Design), BOM (Bill of Materials), product defect information, etc.).

[0034] The system model database 142 stores system model information in which templates of a plurality of types of system models are registered. The system model information has templates that define each system model.

[0035] 2A is a diagram showing an example of system model information. As shown in the figure, in system model information 200, for each model ID that identifies the type of each system model, a system model / sub-model, a model description, a model description language, necessary information, and a model image are registered as templates for each system model.

[0036] In addition, information indicating the type of system model is registered in the system model / sub-model. Here, if one system model corresponding to a model ID is composed of multiple system models (for example, a requirement model and a component model), each system model is treated as a sub-model and information indicating the type of each sub-model is registered. For example, in the example of Figure 2A, the type of system model M001 is indicated as a "requirement model," and the type of system model M003 is indicated as being composed of two sub-models, a "requirement model" and a "component model."

[0037] The model description contains information that indicates the characteristics of each system model. Specifically, the model description contains a variety of information, such as the usage scenarios, constraints, roles, usage precautions, relationships between other system models or subsystems (e.g., dependencies and aggregation relationships), and how to combine them.

[0038] The model description language stores information describing each system model in a modeling language, such as UML (Unified Modeling Language) or SysML (Systems Modeling Language).

[0039] The required information is registered with the information necessary to generate a system model. Specifically, the required information includes the type and content of design information required to generate a system model. For example, in the case of the M001 system model (requirements model), "structured data describing the product requirements specifications" is registered as the information necessary to generate the system model.

[0040] 2B is a diagram showing an example of information registered in a model image. As shown in the figure, an image of a visualized system model (e.g., a diagram showing a block diagram of the system model) is registered in the model image. Note that in the system model block diagram, information such as the blocks in which information extracted from the design information is embedded and displayed, and their positions, is predefined in the model description language.

[0041] The information extraction model database 143 stores information extraction models for extracting information required for generating a system model from the design information database 141. Specifically, the information extraction model database 143 stores information models using machine learning algorithms typified by generative AI (Artificial Intelligence) and neural networks as information extraction models. Types of information models include, for example, LLMs (Large Language Models). The following describes an example in which generative AI is used as an information extraction model.

[0042] The information extraction model extracts information required for generating a system model from the design information database 141 using a predetermined prompt identified based on the analysis result of the user input information.

[0043] The prompt database 144 stores prompts for instructions and requests to be input to the information extraction model. These prompts have been prepared in advance with various contents so that the information extraction model can accurately extract appropriate information corresponding to the user input information from the design information database 141.

[0044] Next, a description will be given of the processing unit 150. The processing unit 150 is a functional unit that performs various processes executed in the design support system 1000. Specifically, the processing unit 150 has an input information analysis unit 151, a model candidate identification unit 152, an information extraction unit 153, and a system model generation unit 154 as individual functional units that perform each process.

[0045] The input information analysis unit 151 is a functional unit that analyzes user input information related to the system model. Specifically, the input information analysis unit 151 acquires the user input information via the input receiving unit 110 and performs natural language analysis processing (hereinafter, may be referred to as natural language processing) to identify (extract) information related to the type of system model and information related to the target of the system model from the user input information. Note that when the user input information is input by voice, the input information analysis unit 151 converts the voice information into text information and performs natural language processing using the text information.

[0046] Natural language processing can be achieved, for example, by using a Bidirectional Encoder Representations from Transformers (BERT) model to fine-tune Name Entity Recognition (NER) for system models and design information.

[0047] The model candidate identification unit 152 is a functional unit that identifies (selects) system model candidates. The model candidate identification unit 152 identifies appropriate system model candidates from the system model database 142 based on information related to the type of the identified system model.

[0048] The information extraction unit 153 is a functional unit that extracts information required for generating a system model from the design information database 141 using an information extraction model.

[0049] The system model generation unit 154 is a functional unit that generates a system model using a system model template. Specifically, the system model generation unit 154 generates the system model by embedding the necessary information extracted by the information extraction unit 153 in a predetermined position defined in the selected system model template.

[0050] An example of the functional configuration of the design support system 1000 has been described above.

[0051] <Processing Description> Next, the design support process executed by the design support system 1000 will be described.

[0052] 3 is a flow diagram showing an example of the design support process. The design support process starts, for example, when the input receiving unit 110 receives an instruction to execute the process from the user.

[0053] When the process starts, the input receiving unit 110 receives user input information related to the system model (step S10).

[0054] Next, the input information analysis unit 151 analyzes the user input information (step S20). Specifically, the input information analysis unit 151 analyzes the user input information by natural language processing, and identifies information about the type of system model and information about the target of the system model.

[0055] The information on the type of system model is information indicating the type of system model estimated from the analysis result of the user input information. For example, if the user input information is "I would like to check the functions defined in the digital camera," the input information analysis unit 151 identifies "functional model (functional block diagram)" as information on the type of system model based on natural language processing. Also, for example, if the user input information is "I would like to see the relationship between the safety requirement specifications and related components when designing a digital camera," the input information analysis unit 151 identifies "requirement model (requirement block diagram) and component model (component block diagram)" as information on the type of system model based on natural language processing.

[0056] Furthermore, information about the target of the system model refers to information required when generating a system model. For example, if the user input information is "I would like to check the functions defined in the digital camera," the input information analysis unit 151 identifies a "function definition document" as information about the target of the system model based on natural language processing. Also, for example, if the user input information is "When designing a digital camera, I would like to see the relationship between the safety requirement specifications and related components together," the input information analysis unit 151 identifies, based on natural language processing, information such as "safety requirement specifications for the requirement model (requirement block diagram), and information associated with the requirement model (requirement block diagram) for the component model (component block diagram)" as information about the target of the system model.

[0057] Next, the model candidate identification unit 152 determines whether or not a system model can be generated (step S30). Specifically, based on the information on the type of system model, if a template of the system model registered in the system model information 200 can be identified, the model candidate identification unit 152 determines that the system model can be generated, and if a template of the system model cannot be identified, the model candidate identification unit 152 determines that the system model cannot be generated (is not possible).

[0058] More specifically, the model candidate identification unit 152 calculates the similarity between information on the type of system model and information registered in the model description of the system model information 200, and if there is a system model with a similarity equal to or greater than a predetermined value, it determines that the system model can be identified from the system model information 200 and that it is possible to generate the system model. Note that the similarity is calculated using, for example, cosine similarity.

[0059] If it is determined that generation of a system model is not possible (impossible) (No in step S30), the model candidate identification unit 152 returns the process to step S10. At this time, the model candidate identification unit 152 displays, for example, via the output information generation unit 120, a message on the output device requesting the user to re-input the user input information (for example, "The type of system model cannot be identified from the input information. Please input additional information").

[0060] Furthermore, if it is determined that a system model can be generated (Yes in step S30), the model information identification unit determines a system model to be generated (step S40), and proceeds to step S50. Specifically, if there is one system model for which it is determined in step S30 that a system model can be generated, the model candidate identification unit 152 determines that system model as the system model to be generated.

[0061] Furthermore, when there are multiple system models determined in step S30 as capable of generating a system model, the model candidate identification unit 152 determines the system model with the highest similarity as the system model to be generated. Alternatively, the model candidate identification unit 152 may present image information (images of the models in FIG. 2B ) showing images of the multiple system models determined as capable of being generated to the user, and determine the system model selected by the user as the system model to be generated.

[0062] Next, the model candidate identification unit 152 determines whether the identified system model is composed of multiple sub-models (step S50). If it is determined that the identified system model is composed of multiple sub-models (Yes in step S50), the model candidate identification unit 152 proceeds to step S60. On the other hand, if it is determined that the identified system model is not composed of multiple sub-models (No in step S50), the model candidate identification unit 152 proceeds to step S70. Whether a system model is composed of multiple sub-models can be determined by, for example, referring to the system model / sub-model item in the system model information 200.

[0063] In step S60, the model candidate identification unit 152 identifies and associates the relationships between submodels based on the information registered in the model description of the system model information 200. The relationships between submodels include, for example, dependency relationships, aggregation relationships, composition relationships, and generalization relationships.

[0064] A dependency relationship refers to a relationship in which one submodel depends on another. An aggregation relationship refers to a relationship in which multiple submodels come together to form a new submodel. A composition relationship refers to a relationship in which multiple submodels are combined to form a new submodel. In a composition relationship, the relationship between submodels is stronger. A generalization relationship refers to an inheritance relationship between submodels. A generalization relationship indicates that a higher-level model element generalizes a lower-level model element.

[0065] Such relationships between sub-models are registered in advance in the model description of the system model information 200.

[0066] In step S70, the information extraction unit 153 identifies a prompt to be input to the information extraction model based on the analysis result of the user input information. Specifically, the information extraction unit 153 identifies an appropriate prompt to be input to the information extraction model from the prompt database 144 based on the information on the target of the system model identified in step S20.

[0067] More specifically, the information extraction unit 153 calculates the similarity between the information about the target of the system model and each prompt stored in the prompt database 144, and identifies the prompt with the highest similarity as the prompt to be input to the information extraction model. Note that the similarity may be calculated using, for example, cosine similarity.

[0068] Furthermore, the information extraction unit 153 inputs the identified prompt into an information extraction model (generation AI) to extract (acquire) information necessary for generating a system model from the design information. For example, if the information related to the target of the system model identified by natural language processing of the user-input information is a "function definition document," the information extraction unit 153 identifies a prompt such as "Please read the function definition document of a digital camera and list the functions of the digital camera" from the prompt database 144. Furthermore, the information extraction unit 153 inputs this into the information extraction model to acquire information necessary for generating a system model from the design information database 141.

[0069] Furthermore, for example, if the information on the target of the system model is "requirement specifications related to safety for the requirement model (requirement block diagram), and information associated with the requirement model (requirement block diagram) for the component model (component block diagram)," the information extraction unit 153 identifies prompts such as "Please list the requirement specifications related to the safety of the product" and "Please extract information on the component model associated with the requirement model" from the prompt database 144. Furthermore, the information extraction unit 153 inputs these into the information extraction model, thereby acquiring information necessary for generating the system model from the design information database 141.

[0070] Furthermore, by processing the information extraction unit 153 using such an information extraction model, in response to a prompt such as "Please read the function definition document of the digital camera and list the functions of the digital camera," the following information is extracted, for example: "(Function 1) Screen capture: A basic function that takes a picture of a subject and saves it as a digital image," "(Function 2) Power management: Displays the battery charge status and switches to power-saving mode," and "(Function 3) Image display: Check captured photos and videos on the camera's LCD screen."

[0071] Next, the system model generation unit 154 generates a system model using the extracted information (step S80). Specifically, the system model generation unit 154 generates the system model by embedding the extracted information at a predetermined position defined by the system model template determined in step S40. The system model generation unit 154 then presents the generated system model to the user by displaying it on a predetermined output device (step S90), and ends this flow.

[0072] 4A is a diagram illustrating the generation of a system model according to an example. FIG. 4A-1 shows an example of an image of the system model determined in step S40, and FIG. 4A-2 shows an example of information extracted based on a prompt.

[0073] The system model generation unit 154 performs a process of embedding the extracted information (in this embodiment, information related to functions 1 to 3 of the digital camera) in predetermined positions defined in the template of the system model. Specifically, the system model generation unit 154 embeds "functions of the digital camera" in the corresponding position 301 of the template, and embeds the extracted information (functions 1 to 3) in the corresponding positions 302 to 304 of the template, respectively. Note that when the type of information and its embedding position are defined in the template, the process of embedding the extracted information in the corresponding position is well known, and therefore a detailed description thereof will be omitted. The system model generation unit 154 generates a system model based on the execution of this process.

[0074] 4B is a diagram showing an example of a system model generated by the processing of step S80. As shown in the figure, the system model is generated by embedding extracted information in predetermined positions defined in the template of the system model.

[0075] 5 is a diagram illustrating an example of generating a system model composed of multiple submodels. Similarly, the illustrated system model 350 is generated by embedding various pieces of information extracted from the design information database 141 based on prompts into predetermined positions of the submodels defined in the template of the system model 350. Furthermore, since this system model is composed of multiple submodels (requirement model 351 and structural model 352), the system model generation unit 154 associates the relationships between the submodels identified in step S60 ("constraint" relationships in the illustrated example). The embedding positions of information 353 indicating the relationships between the submodels are also defined in advance by the template.

[0076] The design support process has been described above.

[0077] Such a design support system reduces the burden on the user involved in creating a system model and can generate an appropriate system model that meets the user's intentions. In particular, the user can obtain an appropriate system model simply by inputting instructions and requests regarding the system model in natural language into the design support system without requiring specialized knowledge. Such a design support system can greatly contribute to the generation of system models.

[0078] Second Embodiment The design support system 1000 according to this embodiment generates an appropriate system model that meets the user's intentions, taking into account the user's attributes. Specifically, the design support system 1000 acquires user input information including the user's attributes, and generates a system model that meets the user's intentions by using an appropriate system model template according to the user's attributes based on a comparison with the model description in the system model information 200.

[0079] In this embodiment, it is assumed that information on user attributes is also registered in advance in the model description in the system model information 200. User attributes represent the identity and expertise of individuals or groups involved in product design, such as the user's field of expertise, role, scope of responsibility, skill level, etc.

[0080] The field of expertise is information that indicates the specialized knowledge and technical field of the user who is a designer, such as electrical designer, mechanical designer, or software designer. The role is information that indicates the specific role that the user plays in the design process, such as lead designer, subsystem designer, or integration designer. The scope of responsibility is information that indicates the range of responsibility and decision-making capacity of the user, such as designing some subsystems, designing specific functions, or designing the entire system. The skill level is information that indicates the level of experience and ability of the user, such as beginner designer, intermediate designer, or advanced designer.

[0081] Furthermore, the model descriptions in the system model information 200 contain information corresponding to these user attributes, such as "This system model is suitable for beginner designers" or "This system model is often used by electrical designers," which makes it easier to select a system model that matches the user attributes.

[0082] When the input receiving unit 110 of the design support system 1000 acquires user input information including such user attributes, the model candidate identifying unit 152 calculates the similarity between the analysis result of the user input information and the model description of the system model information 200, as in the above-described embodiment, and identifies an appropriate system model template (step S40).

[0083] In this case, the input information analysis unit 151 obtains an analysis result (information on the type of system model) including user attributes through natural language processing. Furthermore, the model candidate identification unit 152 uses the "information on the type of system model" including user attributes to calculate the similarity with the model description in the system model information 200, and selects a system model with high similarity. As a result, a system model that takes user attributes into consideration is determined as the system model to be generated.

[0084] Such a design support system can take user attributes into consideration and generate a template system model that is more suitable for the user. For example, if the user is an electrical designer, it is considered preferable that the design support system generate a system model that is often used by electrical designers. Also, if the user is a novice designer, it is considered preferable that the design support system generate a system model that is often used by novice designers, in accordance with the user's skill level. By taking such user attributes into consideration, the design support system according to this embodiment can generate a system model that is more in line with the user's intentions.

[0085] <Modification> It should be noted that the design support system 1000 is not limited to the form shown in Fig. 1, and various modifications are possible. An example of the configuration is shown in Fig. 6. Note that the same configurations and functions as those in Fig. 1 are denoted by the same reference numerals, and detailed explanations thereof will be omitted.

[0086] 6 is a diagram showing an example of a schematic configuration of a design support system 1000 according to a modified example. As shown in the figure, the design support system 1000 includes a computer 101, a terminal device 400, and an external device 500, which are interconnected so as to be able to communicate with each other via a predetermined network N. The network N is, for example, a communication network such as the Internet, a LAN (Local Area Network), or a WAN (Wide Area Network).

[0087] The basic configuration of the computer 101 is the same as that of the above-described embodiment, but differs in that it does not have a storage unit 140 that stores various databases. In this modification, the various databases stored in the storage unit 140 in FIG. 1 are stored in an external device 500.

[0088] The terminal device 400 is used by a user who is a designer, and is, for example, a personal computer, a smartphone, a tablet terminal, etc. The user inputs user input information via the terminal device 400.

[0089] The external device 500 is, for example, a computer such as a server device placed on a cloud, and has each database in the storage unit 140 that the computer 100 in FIG.

[0090] The computer 101 of the design support system 1000 according to this modification acquires user input information via the terminal device 400. The computer 101 also acquires various types of information from the external device 500 as appropriate depending on the processing. The computer 101 also displays screen information of the generated system model on a display provided in the terminal device 400.

[0091] As with the above-described embodiment, this type of design support system can reduce the burden on the user by reducing the amount of work required to create a system model, thereby improving design efficiency and shortening the design process period.

[0092] In the above-described embodiment, a predetermined prompt is identified from the prompt database 144 based on the analysis result of the user-input information, but the present invention is not limited to this, and an appropriate prompt may be automatically generated by the generation AI. Specifically, the design support system 1000 may use the user-input information to cause the generation AI to generate a prompt that enables the information extraction model to accurately extract necessary information.

[0093] This design support system eliminates the need to prepare prompts in advance and allows the AI ​​to generate appropriate prompts based on user input information. As a result, the design support system can more accurately extract necessary information from the design information database in line with the user's intentions.

[0094] <Hardware configuration of design support system 1000> 7 is a diagram showing an example of the hardware configuration of a design support system 1000. As shown in the figure, the design support system 1000 has an input device 610, an output device 620, a processing device 630, a main memory device 640, an auxiliary memory device 650, a communication device 660, and a bus 670 that electrically interconnects these devices.

[0095] The input device 610 is, for example, a touch panel, a keyboard, a mouse, etc. The output device 620 is a display device such as a liquid crystal display or an organic display.

[0096] The processing device 630 is, for example, a processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). The main storage device 640 is a memory device (memory resource) such as a RAM (Random Access Memory) or a ROM (Read Only Memory). The design support system 1000 has at least one processor and one or more memory resources.

[0097] The auxiliary storage device 650 is a non-volatile storage device capable of storing digital information, such as a so-called hard disk drive, a solid state drive (SSD), or a flash memory.

[0098] The communication device 660 is a wired communication device that performs wired communication via a network cable, or a wireless communication device that performs wireless communication via an antenna.

[0099] An example of the hardware configuration of the design support system 1000 has been described above.

[0100] The processing unit 150 of the design support system 1000 is realized by a program that causes the processing device 630 to perform processing. This program is stored in the main storage device 640 or the auxiliary storage device 650, and is loaded onto the main storage device 640 and executed by the processing device 630 when the program is executed.

[0101] The storage unit 140 is realized by a main storage device 640, an auxiliary storage device 650, or a combination thereof. The communication unit 130 is realized by a communication device 660.

[0102] Furthermore, the above-described configurations, functions, processing unit 150, processing means, etc. of design support system 1000 may be partially or entirely implemented in hardware, for example, by designing them as integrated circuits. The above-described configurations and functions may also be implemented in software, with a processor interpreting and executing programs that implement the respective functions. Information such as programs, tables, and files that implement the respective functions can be stored in storage devices such as memory, hard disks, and SSDs, or in recording media such as IC cards, SD cards, and DVDs.

[0103] Furthermore, the present invention is not limited to the above-described embodiments and modifications, and includes various modifications within the scope of the same technical concept. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those including all of the described configurations. Furthermore, 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 each embodiment with other configurations.

[0104] In addition, in the above explanation, the control lines and information lines are those that are considered necessary for the explanation, and do not necessarily show all the control lines and information lines in the product. In reality, it can be considered that almost all components are interconnected. [Explanation of symbols]

[0105] 1000... Design support system, 100 (101)... Computer, 110... Input reception unit, 120... Output information generation unit, 130... Communication unit, 140... Memory unit, 141... Design information database, 142... System model database, 143... Information extraction model database, 144... Prompt database, 150... Processing unit, 151... Input information analysis unit, 152... Model candidate identification unit, 153... Information extraction unit, 154... System model generation unit, 400... Terminal device, 500... External device, 610... Input device, 620... Output device, 630... Processing device, 640... Main memory device, 650... Auxiliary memory device, 660... Communication device, 670... Bus, N... Network

Claims

1. an input information analysis unit that analyzes user input information related to the system model; a model candidate specifying unit that specifies a system model to be generated from system model information in which templates of multiple types of system models are registered, based on an analysis result of the input information; an information extraction unit that extracts necessary information to be used for generating the system model from a database that stores information about design, based on the analysis result of the input information; a system model generation unit that generates a system model according to the input information by using the extracted necessary information and a template of the system model to be generated. A design support system characterized by:

2. 2. The design support system according to claim 1, The system model information registers relationships between sub-models that configure the system model, The model candidate identification unit When the system model to be generated is composed of a plurality of submodels, the system model information is used to identify the relationships between the submodels and associate them with each other. A design support system characterized by:

3. 2. The design support system according to claim 1, The system model information includes information about attributes of the user. the input information analysis unit analyzes the input information including information about attributes of the user; The model candidate specifying unit specifies a template of the system model that takes into consideration the attributes of the user from the system model information based on an analysis result of the input information. A design support system characterized by:

4. 2. The design support system according to claim 1, The model candidate identification unit Identifying a system model to be generated from the system model information based on the similarity between the registered contents of the system model information and the analysis result of the input information. A design support system characterized by:

5. 2. The design support system according to claim 1, The input information analysis unit The user's input information is analyzed using natural language processing. A design support system characterized by:

6. 2. The design support system according to claim 1, The system model information includes image information indicating an image of each system model, The model candidate identification unit When there are multiple candidates for the system model to be generated, the system model information is used to present image information of the image corresponding to the candidate system model to the user, and the candidate system model selected by the user is identified as the system model to be generated. A design support system characterized by:

7. 2. The design support system according to claim 1, The information extraction unit extracts the necessary information from the database using an information extraction model, which is an information model generated based on artificial intelligence (AI) or machine learning. A design support system characterized by:

8. 8. The design support system according to claim 7, The information extraction unit Identifying a prompt to be input to the information extraction model based on the analysis result of the input information; The required information is extracted by inputting the identified prompt into the information extraction model. A design support system characterized by:

9. 2. The design support system according to claim 1, The system model is MBSE (Model-Based Systems Engineering). A design support system characterized by:

10. 3. The design support system according to claim 2, The relationships between the sub-models are dependency relationships, aggregation relationships, composition relationships, or generalization relationships. A design support system characterized by:

11. 4. The design support system according to claim 3, The information about the user's attributes is the user's specialty, role, scope of responsibility, or skill level. A design support system characterized by:

12. A design support method executed by a design support system, The design support system includes: an input information analysis step of analyzing user input information related to the system model; a model candidate specification step of specifying a system model to be generated from system model information in which templates of multiple types of system models are registered, based on the analysis result of the input information; an information extraction step of extracting necessary information to be used for generating the system model from a database storing design information based on the analysis result of the input information; a system model generation step of generating a system model according to the input information using the extracted necessary information and a template of the system model to be generated. A design support method comprising:

13. A program that causes a computer to function as a design support system, The computer an input information analysis unit that analyzes user input information related to the system model; a model candidate specifying unit that specifies a system model to be generated from system model information in which templates of multiple types of system models are registered, based on an analysis result of the input information; an information extraction unit that extracts necessary information to be used for generating the system model from a database that stores information about design, based on the analysis result of the input information; and causing the system model generating unit to function as a system model generating unit that generates a system model according to the input information using the extracted necessary information and a template of the system model to be generated. A program characterized by:

Images