Design support device and design support method

Abstract

The system automatically generates a system model that aligns with the user's intent from the design documents. [Solution] The design support device of the present invention is characterized by supporting the user by comprising: an input processing unit that accepts design documents relating to product design, creation instructions relating to the creation of a system model of a product, an ontology model and an instance; a prompt creation unit that creates a prompt for a generation AI to which the design documents, creation instructions, ontology model and instance have been added; a model information extraction unit that inputs the created prompt to the generation AI and receives model information relating to the creation of the system model extracted by the generation AI from the design documents; and a system model creation unit that creates the system model from the extracted model information.

Description

Technical Field

[0001] The present invention relates to a design support device and a design support method, and particularly relates to a technique for assisting in creating a system model related to product design.

Background Art

[0002] Due to the complexity of products, systems, etc. (hereinafter referred to as products), in product design, it is often necessary to consider multiple areas such as electricity, vibration, and strength. Also, not only the performance of the product but also multiple KPIs (Key Performance Indicators) such as environmental friendliness, reliability, and safety often need to be satisfied simultaneously. Thus, as one of the techniques for complex product design, the utilization of system models has been proposed.

[0003] A system model captures various areas related to a product as a cross-sectional system, models information related to the system, and describes it structurally. By expressing product design in a system model, it is possible to eliminate the ambiguity of expression due to natural language and the ambiguity of the relationship between elements, and more efficient product design can be expected. By using a system model, for example, when a design change is made, it is possible to quickly identify the impact of the design change on existing functions.

[0004] Model-Based Systems Engineering (MBSE) has been proposed as an advanced form of system modeling. MBSE models the relationships between components such as product component structure, required functions, use cases, design parameters, and internal processing flows, and represents them in easily understandable graphs using a modeling language, thereby improving design efficiency and preventing design errors. One example of a modeling language is SysML (OMG (Object Management Group) Systems Modeling Language). However, creating a system model or MBSE model from design documents requires advanced expertise in system modeling and often involves a huge amount of effort, so there is a desire for efficient system model creation.

[0005] As a technology to solve these problems, Patent Document 1 describes a specification determination support device comprising: a design parameter input receiving unit configured to receive input of product design parameters; a feasibility determination unit configured to determine whether the design parameters are feasible; a system specification model generation unit configured to generate a system specification model by reflecting the design parameters in the acquired system metamodel of the product if the design parameters are feasible; and a document generation unit configured to generate a product specification based on the system specification model (see Claim 1 of Patent Document 1).

[0006] Furthermore, in order to create a system model or MBSE model from design documents, it is necessary to extract the information (knowledge) required for model creation from the design documents. As a technique for extracting information from a vast database, the use of knowledge graphs or ontology models has been proposed. An ontology model describes the concepts (classes) and their relationships (relationships) that appear in knowledge in a tree structure, and defines the inclusion relationships and constituent elements of concepts as a hierarchical structure.

[0007] For example, Patent Document 2 describes a knowledge metadata generation device that generates knowledge metadata related to content provided to a user, characterized in that it comprises a knowledge metadata generation means for generating the knowledge metadata based on an information resource related to the content and an ontology of a field related to the information resource that has been stored in advance, and a storage means for storing the knowledge metadata obtained by the knowledge metadata generation means (see Claim 1 of Patent Document 2). [Prior art documents] [Patent Documents]

[0008] [Patent Document 1] Japanese Patent Publication No. 2023-83915 [Patent Document 2] Japanese Patent Publication No. 2007-249907 [Overview of the project] [Problems that the invention aims to solve]

[0009] Patent Document 1 discloses a technique for generating a system specification model from product design parameters, but it does not mention the creation of system models other than the specification model. Furthermore, while Patent Document 2 discloses a technique for extracting information based on ontologs, it does not mention any means of utilizing ontologs in generative AI. Also, Patent Document 2 does not mention a method for creating a system model from the extracted information. This invention has been made in view of these problems, and the object of this invention is to automatically create a system model that conforms to the user's intentions from design documents. [Means for solving the problem]

[0010] The design support device of the present invention is characterized by supporting the user by comprising: an input processing unit that accepts design documents relating to product design, creation instructions relating to the creation of a system model of a product, an ontology model, and an instance; a prompt creation unit that creates a prompt for a generating AI to which the design documents, creation instructions, ontology model, and instance have been added; a model information extraction unit that inputs the created prompt to the generating AI and receives model information relating to the creation of the system model extracted by the generating AI from the design documents; and a system model creation unit that creates the system model from the extracted model information. Other means will be described within the descriptions of embodiments for carrying out the invention. [Effects of the Invention]

[0011] According to the present invention, a system model that aligns with the user's intentions can be automatically created from design documents. As a result, the man-hours required to create the system model can be significantly reduced, and various effects such as improved design efficiency and a shorter design process can be expected. [Brief explanation of the drawing]

[0012] [Figure 1] This is a diagram illustrating the configuration of a design support system. [Figure 2] This figure shows an example of a prompt template. [Figure 3] This figure shows an example of a database of creation know-how. [Figure 4] This figure shows an example of an ontology model. [Figure 5] This figure shows an example of a textual description of an ontology model. [Figure 6] This figure shows an example of an instance. [Figure 7] This is an example of a flowchart for the prompt generation section. [Figure 8] This figure shows an example of model information. [Figure 9] This is an example of a flowchart for the system model creation section. [Figure 10] This is a diagram showing an example of a system model created by a generative AI. [Figure 11] This is a diagram showing an example of visualizing the script of the system model in FIG. 10. [Figure 12] This is an example of the flowchart of Example 2.

Mode for Carrying Out the Invention

[0013] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Although the drawings show specific embodiments in accordance with the principles of the present invention, these are for the purpose of understanding the present invention and are not used to limit the present invention in any way.

[0014] 〈Example 1〉 FIG. 1 is a diagram for explaining the configuration of the design support device 1. The design support device 1 is a general computer and includes a central control device 11, input devices 12 such as a camera, microphone, mouse, and keyboard, output devices 13 such as a speaker and display, a main memory device 14, and an auxiliary storage device 15.

[0015] The input processing unit 21, prompt creation unit 22, model information extraction unit 23, and system model creation unit 24 in the main memory device 14 are programs. In the following description, when stating "○○ unit is", it means that the central control device 11 reads the program from the auxiliary storage device 15 into the main memory device 14 and realizes the functions of the program. The auxiliary storage device 15 stores a generative AI DB 31, a design document DB 32, a prompt template DB 33, and a creation know-how DB 34 (details will be described later). These have formats such as electronic files and relational databases. Note that "AI" means "Artificial Intelligence", and "DB" means "database, Data Base".

[0016] The auxiliary storage device 15 may be configured independently as a separate enclosure. That is, the design support device 1 performs information processing using the generated AIDB 31, etc., but this information may be stored on a cloud server or the like located outside the design support device 1. In this case, the design support device 1 and the separate enclosure constitute a design support system.

[0017] Generative AIDB31 is a collection of generative AIs that use machine learning algorithms, such as neural networks. Each generative AI outputs a prediction result by performing a given task based on input information. Generative AIs are particularly large language models (LLMs) used in the field of natural language processing, and are capable of automatically generating text or other answers to user questions. By using such generative AIs, it is possible to extract specific information from text or input files. The generative AIDB as a collection is assigned the code 31, and each individual generative AI is assigned the codes 31a, 31b, ...

[0018] The design document DB32 is a collection of design documents related to product design, such as requirements specifications, functional definitions, component information, design study documents, product defect information, CAD (Computer-Aided Design), and BOM (Bill of Materials). These design documents are used as training data or input data for the generating AI. As is clear from the specific examples of design documents, design documents are "documents" in a broad sense, and include images. More generally, the generating AI can generate specific information from the design documents, which include images or text.

[0019] The prompt template DB33 is a collection of prompt templates pre-written with various instructions for generating AI to create a system model from design documents. A prompt generally refers to "an instruction or question that a user inputs to an interactive system." The prompts in Example 1 are also instructions or questions input to the generating AI.

[0020] As is well known, whether a generating AI can output text that aligns with the user's intent depends on the quality of the prompt. Therefore, the design support device 1 prepares multiple prompt templates according to their intended use. A template is a "model," and the user inputs specific text into the "blanks" of the prompt template. A prompt template with information added to the blanks becomes a prompt. The prompt template DB as a whole is assigned code 33, and individual prompt templates are assigned codes 33a, 33b, ... The explanation will now move on to Figure 2, although we are still in the middle of Figure 1.

[0021] Figure 2 shows an example of a prompt template. Prompt template 33a is a prompt template for the generative AI 31a that generates model information, and consists of four parts: "#creation instruction", "#design document", "#ontology model", and "#instance". "#Creation Instructions" describes the task that the generation AI31a will perform. "#Design Document" describes the contents of the design document as input data. The section marked "~~Insert design document information here" is the aforementioned blank space in the prompt template. Specific information will be added to this section later (and so on). The hashtag "#OntologyModel" describes the definition of an ontology model as a set of conceptual connections within the information being extracted. "#instance" describes an instance entered by the user as a concrete example of the ontology model.

[0022] Prompt template 33b is a prompt template for generation AI 31b, which generates a system model, and consists of three parts: "#creation instructions", "#model information", and "#creation know-how". "#Creation Instructions" describes the task that the generating AI31b will perform. "#Model Information" is used to describe "Model Information," which is any information necessary to create a system model. The "creation know-how" describes the grammar related to the system model. The explanation returns to Figure 1.

[0023] As mentioned above, the creation know-how DB34 is a collection of creation know-how that describes the grammar related to system models. Each piece of creation know-how is information at the record (row) level in the creation know-how DB. By including these grammars in the prompts for the generation AI, the generation AI can generate a system model that conforms to the grammar. In some cases, the system model generated by generation AI31b may not be what the user desires, due to the generation AI31b not having sufficiently learned the grammar related to system models. The creation know-how grammatically describes the cause of the problem and how to fix it in such cases.

[0024] Figure 3 shows an example of the creation know-how DB34. The creation know-how DB34 is a collection of creation know-how, which is a grammar for describing each model element, based on the language specification of SysML, a modeling language.

[0025] The input processing unit 21 accepts user input as "creation instructions" in natural language, such as instructions, requests, and notes regarding the creation of a system model. For example, the user might input, "I want to extract safety requirements from the design document of a digital camera." The input creation instructions are reflected when selecting a prompt template for the generation AI. The user inputs an ontology model and instances as auxiliary data in order to accurately execute the instructed task. An ontology model is a tree-like description of concepts (classes) and their relationships (relationships) that appear in knowledge, defining the relationships between concepts (inclusion relationships, hierarchical relationships, causal relationships, etc.) and constituent elements as a hierarchical structure.

[0026] Figure 4 shows an example of an ontology model. This ontology model relates to the requirements diagram of the system to be designed, and graphs the connections between concepts such as "system requirements," "use cases," "blocks," "activities," "test cases," and "rationales" included in the requirements diagram. Each concept (ellipse) is associated with an instance that represents the specific content of that concept. The letters "has," etc., attached to the links between two concepts indicate the relationship between those concepts.

[0027] Figure 5 shows an example of a text description of an ontology model. When the ontology model in Figure 4 is converted into text using RDFS (RDF Schema), the schema language of the Resource Description Framework (RDF), it becomes as shown in Figure 5. RDFS provides a basic structure for defining vocabulary and its meanings for RDF data, and represents the relationships between resources and the hierarchy of class properties. Using such a framework, ontology models can be saved as text files, and users can input these text files into the system.

[0028] Figure 6 shows an example of an instance. In the context of an ontology model, an instance represents a concrete example and entity of a class (concept) in the ontology model. Instances play a role in linking abstract concepts and categories within the ontology model to concrete data and events. In a broader sense, the instances in Example 1 also include interpretations of classes (concepts), descriptions of concrete examples of classes (concepts) and their locations in design documents. In Example 1, instances are described for each of the system model concepts, such as "system requirements," "use cases," "blocks," "activities," and "test cases." Instances can be entered in natural language or described as text files. One or more instances are described for a single concept.

[0029] The prompt generation unit 22 creates prompts for the generative AI to extract information related to the creation of a system model from the data received by the input processing unit 21.

[0030] Figure 7 is an example of a flowchart of the prompt generation unit 22. In Figure 7, solid arrows indicate the flow of processing, and dashed lines indicate the flow of information (the same applies to Figures 9 and 12). As a prerequisite for the start of the flowchart in Figure 7, the input processing unit 21 is assumed to be receiving the following input from the user via the input device 12. Note that the user here may be one person or multiple people. • Instructions created by the user regarding the creation of a product system model or information extraction. • Design documents related to the product design created by the user. • User-created ontology models • User-created instances

[0031] The prompt generation unit 22 performs the following steps. In step S201, the prompt creation unit 22 determines an appropriate prompt template based on the creation instructions and reads the appropriate prompt template from the prompt template DB 33. For the sake of explanation, let's assume that the prompt creation unit 22 determines and reads prompt template 33a in Figure 2 as the appropriate prompt template. Then, the prompt creation unit 22 adds the creation instructions that the user had previously entered to the blank "#creation instructions" field of prompt template 33a.

[0032] In step S202, the prompt creation unit 22 adds the contents of the design document, which is the information source for creating the system model, to the prompt. Specifically, the prompt creation unit 102 extracts design information such as text from the design document previously entered by the user and adds it to the blank space in “#design document” of the prompt template 33a, or adds a link to the design document file to the said blank space.

[0033] In step S203, the prompt creation unit 22 adds the ontology model to the prompt. Specifically, the prompt creation unit 102 adds the text description of the ontology model, as shown in Figure 5, to the blank space "#OntologyModel" in the prompt template 33a.

[0034] In step S204, the prompt creation unit 22 adds the instance to the prompt. Specifically, the prompt creation unit 22 adds the instance text description, as shown in Figure 6, to the blank "#instance" field of the prompt template 33a.

[0035] Steps S201 through S204 create a prompt for the generating AI 31a. As mentioned above, the prompt is input information (search term) for the generating AI, and for example, it takes the form of a question.

[0036] The model information extraction unit 23 inputs the prompt created by the prompt creation unit 22 to the generation AI 31a and executes it, thereby extracting information related to the creation of the system model (hereinafter also called "model information") as the output of the generation AI 31a. The extracted model information is saved in the auxiliary storage device 15 in the form of a file or database. After that, the flowchart in Figure 7 ends.

[0037] Figure 8 shows an example of model information. The model information extraction unit 23 receives the results of the generation AI extracting each model element, including use cases, blocks, test cases, activities, requirements, etc., from the design document. The model information extraction unit 23 assigns an ID (identifier) ​​to each model element, extracts the name (title), text (specific content), dependents, and dependencies, organizes them in a table format (Figure 8), and outputs them as model information.

[0038] The system model creation unit 24 creates a system model from the model information extracted by the model information extraction unit 23.

[0039] Figure 9 is an example of a flowchart for the system model creation unit 24. Following the flowchart in Figure 7, the system model creation unit 104 performs the following steps.

[0040] In step S401, the system model creation unit 24 determines an appropriate prompt template based on the creation instructions and reads the appropriate prompt template from the prompt template DB 33. For the sake of explanation, let's assume that the system model creation unit 24 determines and reads prompt template 33b shown in Figure 2 as the appropriate prompt template. The system model creation unit 24 then adds the creation instructions previously entered by the user to the blank "#creation instructions" field of prompt template 33b.

[0041] In step S402, the system model creation unit 24 adds the model information extracted by the model information extraction unit 23 to the blank field "#Model Information" in the prompt template 33b.

[0042] In step S403, the system model creation unit 24 extracts the creation know-how instructed by the user from the creation know-how DB 34 and adds it to the blank "#creation know-how" field in the prompt template 33b.

[0043] In steps S401 to S403, prompts are generated for the generating AI31b to create the system model. The system model creation unit 24 inputs these prompts into the generating AI31b, and the user-instructed system model is output from the generating AI31b. Although we are still in the middle of Figure 9, the explanation will now move on to Figure 10.

[0044] Figure 10 shows an example of a system model created by Generator AI31b. Figure 10 is a requirements diagram of the target system written in a script conforming to the SysML specification. The explanation returns to Figure 9.

[0045] In step S404, the system model creation unit 24 determines whether the system model is what the user wanted based on the user's verification of the output system model. Specifically, the user directly deciphers the script of the output system model to verify for errors. Alternatively, the system model creation unit 24 visualizes the system model, and the user verifies the visualized model. Although we are still in the middle of Figure 9, the explanation will now move on to Figure 11.

[0046] Figure 11 shows an example of visualizing the script of the system model in Figure 10. Visualization improves the visibility of the system model and makes it easier to verify. In the upper center of Figure 11, there is a model element (rectangle) with "ID=1". This model element corresponds to the record on the 5th line of the model information in Figure 8. Furthermore, the "Text=********" of this model element in Figure 11 is the same as "******" stored in the text field of the record on the 5th line of the model information in Figure 8. Moreover, this "Text=********" is described in "1.1 Overview" and "1.2 Terminology Definitions" of the design document, as shown in the record on the 1st line of the instance in Figure 6. The explanation returns to Figure 9.

[0047] If, as a result of the above judgment, there are no problems, the system model creation unit 24 terminates its operation. If there are problems, that is, if the system model generated by the generation AI 31b is not what the user wants, the system model creation unit 24 proceeds to step S405. In step S405, the system model creation unit 24 identifies the cause of the problem and modifies part of the creation know-how. Then, the system model creation unit 24 reflects the modified creation know-how in the creation know-how DB 34 and updates the creation know-how DB 34. After that, the flowchart in Figure 9 is completed.

[0048] <Example 2> In Example 2, the user directly instructs the creation of a system model when inputting creation instructions. As a result, the design support device 1 creates a system model directly from the design document without going through the step of extracting model information. In other words, in Example 2, the prompt creation unit 22 and the system model creation unit 24 generate prompts for creating a system model, and the system model creation unit 24 creates the system model by inputting these prompts into the generation AI. In Example 2, the model information extraction unit 23 is unnecessary.

[0049] Figure 12 is an example of a flowchart for Example 2. Example 2 consists of the following steps. In step S501, the prompt generation unit 22 determines an appropriate prompt template based on the user's instructions for creating a system model, and reads the appropriate prompt template from the prompt template DB 33. For the sake of explanation, it is assumed that the prompt creation unit 22 determined and read prompt template 33c (not shown) as the appropriate prompt template.

[0050] Prompt template 33c is a combination of prompt templates 33a and 33b in Figure 2, and has blank fields for "#creation instruction", "#design document", "#ontology model", "#instance", and "#creation know-how". The prompt creation unit 22 then adds the creation instruction that the user has previously entered to the blank field for "#creation instruction" in prompt template 33c.

[0051] In step S502, the prompt creation unit 22 adds the contents of the design document, which is the information source for creating the system model, to the prompt. Specifically, the prompt creation unit 22 extracts design information such as text from the design document previously entered by the user and adds it to the blank space in “#design document” of the prompt template 33c, or adds a link to the design document file to the said blank space.

[0052] In step S503, the prompt creation unit 22 adds the ontology model to the prompt. Specifically, the prompt creation unit 22 adds the text description of the ontology model, as shown in Figure 5, to the blank space "#OntologyModel" in the prompt template 33c.

[0053] In step S504, the prompt creation unit 22 adds the instance to the prompt. Specifically, the prompt creation unit 22 adds the instance text description, as shown in Figure 6, to the blank "#instance" field of the prompt template 33c.

[0054] In step S505, the system model creation unit 24 extracts the creation know-how instructed by the user from the creation know-how DB 34 and adds it to the blank space "#creation know-how" in the prompt template 33c.

[0055] Steps S501 to S505 create prompts for the generation AI 31c to create a system model. The system model creation unit 24 inputs these prompts into the generation AI 31c, which then outputs the system model specified by the user. The generation AI 31c is a combination of generation AIs 31a and 31b, and generates the system model from the information input (added) to the prompt template 33c.

[0056] In step S506, the system model creation unit 24 determines whether the system model is what the user wants based on the user's verification of the output system model. Specifically, the system model creation unit 24 directly deciphers the script of the output system model to verify for errors. Alternatively, the system model creation unit 24 visualizes the system model, and the user verifies the visualized model. If there are no problems as a result of the above determination, the system model creation unit 24 terminates its operation. If there are problems, that is, if the system model generated by the generating AI 31c is not what the user wants, the system model creation unit 24 proceeds to step S507.

[0057] In step S507, the system model creation unit 24 identifies the cause of the problem and modifies part of the creation know-how. The system model creation unit 24 reflects the modified creation know-how in the creation know-how DB 34 and updates the creation know-how DB 34. After that, the flowchart in Figure 12 is completed.

[0058] Example 2 is also an example in which the generated AI 31c also plays the roles of generated AIs 31a and 31b in Example 1. Thus, the generated AIDB 31 may store only a single general-purpose generated AI.

[0059] While several embodiments of the present invention have been described, these embodiments are presented as examples only and do not limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims of the invention and its equivalents. [Explanation of Symbols]

[0060] 1 Design support equipment 11 Central Control Unit 12 Input devices 13 Output device 14 Main memory 15 Auxiliary storage 21 Input Processing Unit 22 Prompt Creation Section 23 Model Information Extraction Unit 24 System Model Creation Department 31. Generating AI Database 32 Design Document Database 33 Prompt Template Database 34. Creation Know-how Database

Claims

1. An input processing unit that accepts design documents related to product design, instructions for creating a product system model, ontology models, and instances, A prompt creation unit that creates prompts for a generative AI by adding the aforementioned design document, the creation instructions, the ontology model, and the instance, A model information extraction unit inputs the created prompt to the generating AI and receives model information related to the creation of the system model extracted by the generating AI from the design document. A system model creation unit that creates the system model from the extracted model information, A design support device characterized by providing support to the user.

2. A generation AI database that stores multiple generation AIs that generate specific information from the design document containing images or text, A design document database that stores information related to product design, including requirements specifications, functional definitions, component information, design study documents, product defect information, and CAD or BOM, as design documents, A prompt template database that stores multiple prompt templates, which are templates of prompts input to the generating AI in order to create a system model using the generating AI, A creation know-how database that stores the know-how for creating the aforementioned system model, To be equipped, The design support device according to claim 1, characterized by the following:

3. The aforementioned ontology model is The user describes the elements and connections between them that they wish to extract from the design document in a graph or text format, and adds this to the prompts for the generating AI. The design support device according to claim 1, characterized by the following:

4. The aforementioned instance is A specific example of an element defined by the ontology model or its location in the design document is described and added to the prompt for the generating AI. The design support device according to claim 1, characterized by the following:

5. The prompt generation unit, Select an appropriate prompt template based on the user's creation instructions, and add the ontology model and instance entered by the user to the prompt template. A design support device according to any one of claims 2 to 4, characterized by the following:

6. The aforementioned system model creation unit, By adding the extracted model information and the creation know-how extracted from the creation know-how database to the prompt template, a prompt for creating a system model is created. By inputting the prompt into the generating AI, the system model instructed by the user is created. The design support device according to claim 2, characterized by the following:

7. The aforementioned system model creation unit, The system model created is verified to determine whether it meets the user's requirements. If the verification reveals that the system model does not meet the user's requirements, the creation know-how is modified and the creation know-how database is updated. The design support device according to claim 6, characterized by the following:

8. A means of receiving design documents related to product design, instructions for creating product system models, ontology models, and instances, Means for creating prompts for a generative AI, which include the aforementioned design document, the creation instructions, the ontology model, and the instance; A means for inputting the created prompt into the generating AI model and for the generating AI to receive the system model extracted from the design document, To support users by providing the following: A design support device characterized by the following.

9. The input processing unit of the design support device is We receive design documents related to the product design, instructions for creating the product's system model, ontology models, and instances. The prompt generation unit of the design support device is: A prompt for the generative AI is created, adding the aforementioned design document, the creation instructions, the ontology model, and the instance. The model information extraction unit of the design support device is The generated prompt is input to the generating AI, and the generating AI receives model information related to the creation of the system model extracted from the design document. The system model creation unit of the aforementioned design support device is: Creating the system model from the extracted model information, A design support method characterized by the following.

Images