Onboard system meta-model construction method, device, equipment and medium

Abstract

The invention relates to the technical field of airborne system design, and discloses an airborne system meta-model construction method and device, equipment and a medium. The method comprises the following steps: extracting entities, attributes and relationships from airborne system multi-source heterogeneous data by utilizing a natural language processing algorithm NLP and a machine learning algorithm, and constructing an airborne system meta-model; the knowledge graph based on the airborne system meta-model is constructed, rapid construction and efficient reuse of the airborne system meta-model are achieved, the efficiency and quality of airborne system design are effectively improved, existing airborne system knowledge can be fully utilized, the workload of repeated modeling is reduced, the design cost is reduced, the product development period is shortened, and the development period is shortened. And design requirements can be accurately matched through the semantic retrieval capability of the knowledge graph, and support is provided for design of an airborne system.

Description

Technical Field

[0001] This invention relates to the field of airborne system design technology, and discloses a method, apparatus, equipment, and medium for constructing an airborne system meta-model. Background Technology

[0002] Airborne systems refer to a collective term for a series of interconnected devices, software, and subsystems installed and operating on aircraft (such as airplanes, helicopters, and drones) to accomplish specific flight missions, ensure flight safety, and provide services to crew and passengers. Airborne systems involve multiple disciplines and are generally divided into three major areas: avionics, electromechanical systems, and flight control. With the rapid development of information technology, the complexity of airborne systems is increasing daily. Traditional airborne system modeling mainly relies on expert experience and manual modeling, which has many limitations. First, manual modeling is time-consuming, labor-intensive, and prone to errors, especially when dealing with large and complex systems. Second, due to the subjectivity of expert experience and knowledge, the consistency and accuracy of the model are difficult to guarantee. Furthermore, traditional modeling methods often lack a deep understanding and representation of the internal relationships of the system, resulting in poor model reusability and scalability.

[0003] Knowledge graphs are graph-based data structures that can intuitively represent entities and their relationships, making them ideal for modeling complex systems. By constructing a knowledge graph for an airborne system, the various components within the system, their connections, data flow, and functional interactions can be clearly displayed, enabling a comprehensive understanding and in-depth analysis of the system. However, applying knowledge graphs to airborne system design also faces several challenges. First, airborne systems involve a large number of technical terms and details, requiring the construction of a specialized ontology library to support knowledge representation and reasoning. Second, the data for airborne systems originates from multiple heterogeneous data sources, including design documents, technical manuals, and maintenance records, with varying quality and formats, necessitating effective data extraction, fusion, and cleaning. Furthermore, to support model reuse, a reusable meta-model library needs to be built, and corresponding tools and methods need to be developed to support model retrieval, combination, and customization. Summary of the Invention

[0004] The purpose of this invention is to provide a method, apparatus, equipment, and medium for constructing a meta-model of an airborne system, which can improve the design efficiency of airborne systems, reduce design costs, and accelerate product development cycles.

[0005] To achieve the above-mentioned technical effects, the technical solution adopted by the present invention is as follows: A method for constructing an airborne system meta-model includes: Based on the definition standard of the general meta-model and the airborne system business domain of the airborne system business model, the airborne system business and existing models are abstracted to construct the initial meta-model of the airborne system; the initial meta-model of the airborne system includes a requirement meta-model and a functional meta-model. The attributes and relationships of the requirement meta-model and functional meta-model of the initial meta-model of the airborne system are defined to form an airborne system meta-model that represents airborne domain knowledge. Natural language processing and machine learning algorithms are used to extract entity and relation information from the airborne system metamodel, semantic descriptions are added to the entities and relations, and a knowledge graph of the airborne system metamodel is formed by Neo4j and stored in a graph database. Based on the design requirements of the airborne system to be designed, a semantic-based model retrieval method is adopted to retrieve existing airborne system meta-models that fit the design requirements from the airborne system meta-model knowledge graph. The retrieved airborne system meta-models are matched and combined, or customized and extended, to form an airborne system meta-model suitable for the design requirements of the airborne system to be designed.

[0006] Furthermore, the method for constructing the initial meta-model of the airborne system includes: Based on the definition standard of the general meta-model, the airborne system business and existing models are abstracted to construct a hierarchical architecture of the airborne system business model; Based on the hierarchical architecture of the airborne system business model, the initial meta-model of the airborne system is constructed according to the airborne system business domain.

[0007] Furthermore, the demand meta-model is used to represent the set of requirements for the functions and attributes of a system, component, or device, and the functional meta-model is used to represent the model components of system functions.

[0008] Furthermore, the requirement meta-model includes a requirement specification meta-model, a requirement item meta-model, and a verification method meta-model.

[0009] Furthermore, methods for forming a knowledge graph of the airborne system meta-model include: The entities extracted from the airborne system meta-model are analyzed to clarify the attributes of each entity and the relationships between entities, and to determine the basic structure of the airborne system knowledge graph. Based on the control tasks and functional interaction logic of the airborne system, an initial airborne system knowledge graph is constructed using the entities. The initial airborne system knowledge graph is simulated under given design requirements. The accuracy, completeness and usability of the initial airborne system knowledge graph are evaluated based on the simulation results. The initial airborne system knowledge graph is then improved based on the evaluation results. Given design requirements, the airborne system design test is conducted using the improved initial airborne system knowledge graph to verify the accuracy and usability of the airborne system knowledge graph. Based on the verification results, the airborne system knowledge graph is iteratively optimized to obtain the optimized airborne system knowledge graph.

[0010] Furthermore, the newly obtained customized and expanded airborne system meta-models are added to the existing airborne system meta-model knowledge graph.

[0011] Furthermore, the data in the airborne system meta-model includes structured data, semi-structured data, and unstructured data. The structured data includes standard databases, spreadsheets, and SysML models; the semi-structured data includes JSON files, XML files, and HTML web pages; and the unstructured data includes image files and video files.

[0012] An airborne system meta-model construction device, comprising: The airborne system initial meta-model construction module is used to abstract airborne system services and existing models based on the definition standards of general meta-models and the airborne system business domain of airborne system business models, and to construct the airborne system initial meta-model; the airborne system initial meta-model includes a functional meta-model and a requirement meta-model. The airborne system metamodel construction module is used to define the attributes and relationships of the requirement metamodel and functional metamodel of the initial metamodel of the airborne system, forming an airborne system metamodel that represents airborne domain knowledge. The knowledge graph construction module is used to extract entity and relation information from the airborne system metamodel using natural language processing and machine learning algorithms, add semantic descriptions to entities and relations, and form an airborne system metamodel knowledge graph using Neo4j tools and store it in a graph database. The reuse module is used to retrieve existing airborne system meta-models that fit the design requirements of the airborne system to be designed from the airborne system meta-model knowledge graph using a semantic model retrieval method. The retrieved airborne system meta-models are matched and combined, or customized and extended, to form an airborne system meta-model suitable for the design requirements of the airborne system to be designed.

[0013] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the aforementioned airborne system meta-model construction methods.

[0014] A computer-readable storage medium storing a computer program that performs any of the aforementioned methods for constructing an airborne system metamodel.

[0015] Compared with the prior art, the beneficial effects of this invention are: This invention utilizes Natural Language Processing (NLP) and Machine Learning (MLM) algorithms to extract entities, attributes, and relationships from multi-source heterogeneous data of airborne systems, constructing a meta-model of the airborne system. By building a knowledge graph based on the airborne system meta-model, it achieves rapid construction and efficient reuse of the airborne system meta-model, effectively improving the efficiency and quality of airborne system design. Moreover, it can fully utilize existing airborne system knowledge, reduce the workload of repetitive modeling, lower design costs, accelerate product development cycles, and accurately match design requirements through the semantic retrieval capabilities of the knowledge graph, providing support for the design of airborne systems. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the knowledge graph-based method for constructing an airborne system meta-model in this embodiment. Figure 2 This is a schematic diagram of the airborne system model architecture in the embodiment; Figure 3 This is a schematic diagram illustrating the airborne system knowledge graph construction process in the embodiment. Figure 4 This is a schematic diagram illustrating how matching and combining airborne system meta-models in this embodiment forms an airborne system model suitable for design requirements. Figure 5 This is a structural block diagram of the airborne system meta-model construction device based on knowledge graphs in the embodiment; Figure 6 This is a structural block diagram of the computer device in the embodiment; Wherein, 1-memory, 2-processor. Detailed Implementation

[0017] The present invention will now be described in further detail with reference to the embodiments and accompanying drawings. However, this should not be construed as limiting the scope of the above-described subject matter of the present invention to the following embodiments; all technologies implemented based on the content of the present invention fall within the scope of the present invention.

[0018] See Figure 1 This embodiment provides a method for constructing an airborne system meta-model, including: Based on the definition standard of the general meta-model and the airborne system business domain of the airborne system business model, the airborne system business and existing models are abstracted to construct the initial meta-model of the airborne system; the initial meta-model of the airborne system includes a functional meta-model and a requirement meta-model. The attributes and relationships of the requirement meta-model and functional meta-model of the initial meta-model of the airborne system are defined to form an airborne system meta-model that represents airborne domain knowledge. Natural language processing and machine learning algorithms are used to extract entity and relation information from the airborne system metamodel, semantic descriptions are added to the entities and relations, and a knowledge graph of the airborne system metamodel is formed by Neo4j and stored in a graph database. Based on the design requirements of the airborne system to be designed, a semantic-based model retrieval method is adopted to retrieve existing airborne system meta-models that fit the design requirements from the airborne system meta-model knowledge graph. The retrieved airborne system meta-models are matched and combined, or customized and extended, to form an airborne system meta-model suitable for the design requirements of the airborne system to be designed.

[0019] This invention achieves rapid construction and efficient reuse of airborne system meta-models by constructing a knowledge graph-based meta-model, effectively improving the efficiency and quality of airborne system design. It can also make full use of existing airborne system knowledge, reduce the workload of repetitive modeling, improve airborne system design efficiency, reduce design costs, accelerate product development cycles, and accurately match design requirements through the semantic retrieval capabilities of the knowledge graph, providing support for the design of airborne systems.

[0020] This invention starts from the top-level business domains of the airborne system (such as avionics, electromechanical systems, and flight control), and decomposes the airborne system layer by layer into business units, business components, and ultimately indivisible business atoms based on the inherent logic and business boundaries of these domains. This process ensures that the airborne system meta-model architecture is strictly aligned with the real-world business topology. Simultaneously, existing specific airborne system business models (such as flight control law models and navigation system models) are analyzed, and reusable patterns, common constraints, and interaction interfaces are abstracted in reverse, elevating them to candidate elements of the meta-model. Through continuous interaction and calibration of these two processes, a clear and hierarchical initial meta-model of the airborne system is ultimately formed, conforming to the theoretical framework and validated in practice.

[0021] See Figures 1 to 4 This embodiment details a method for constructing an airborne system meta-model, specifically including: Step 1: Referring to the general metamodel definition standards for modeling languages ​​such as DoDAF, SysML, and Modelica, abstract the airborne system business and existing models to construct the airborne system model architecture. Then, construct the airborne system business domain of the airborne system business model to build the initial metamodel of the airborne system. The airborne system business includes existing airborne system business knowledge, and the existing airborne system models include existing, already designed airborne systems. The airborne system model architecture includes a general metamodel layer, an airborne system metamodel layer, and an airborne system instance layer, such as... Figure 2As shown, the general meta-model layer includes activity meta-models, timing meta-models, block meta-models, package meta-models, parameter meta-models, etc.; the airborne system meta-model layer includes task meta-models, requirement meta-models, functional meta-models, component meta-models, etc.; and the airborne system instance layer includes a requirement model for a specific type of airborne system, etc. The airborne system business domain includes avionics business domain, electromechanical business domain, and flight control business domain.

[0022] Step 2: Define the attributes and relationships of the requirement meta-model and functional meta-model of the initial meta-model of the airborne system to form an airborne system meta-model that represents airborne domain knowledge.

[0023] Specifically, the requirement meta-model includes a requirement specification meta-model, a requirement item meta-model, and a verification method meta-model. The requirement meta-model represents the set of requirements for the functions and attributes of a system, component, or equipment. The requirement item meta-model represents the functional, performance requirements, and constraints that a product must meet. The attribute definitions of the requirement item meta-model are shown in Table 1. The functional meta-model represents the model components of system functions and is the basic unit constituting the system's functional architecture. The attribute definitions of the functional meta-model are shown in Table 2. The relationship between the airborne system requirement meta-model, the functional meta-model, and the airborne system is defined in Table 3.

[0024] Table 1. Attribute Definitions of the Meta-model for Airborne System Requirements

[0025] Table 2 Attribute Definitions of the Functional Meta-Model of Airborne Systems

[0026] Table 3. Definitions of the Relationship between the Demand Meta-model, Functional Meta-model, and Airborne Systems

[0027] Step 3: Extract entity and relation information from the airborne system metamodel using natural language processing and machine learning algorithms, add semantic descriptions to the entities and relations, and form an airborne system metamodel knowledge graph using Neo4j and store it in a graph database.

[0028] Specifically, such as Figure 3 As shown, the method for constructing the knowledge graph of the airborne system metamodel includes: Data Input and Processing Stage: Entities, attributes, and relationships are extracted from the data of the airborne system metamodel using Natural Language Processing (NLP) and machine learning algorithms. The data of the airborne system metamodel includes structured data, semi-structured data, and unstructured data. The structured data includes standard databases, spreadsheets, and SysML models; the semi-structured data includes JSON files, XML files, and HTML web pages; and the unstructured data includes image files and video files. Analysis phase: Analyze the extracted entities, clarify the attributes of each entity and the relationships between entities, and determine the basic structure of the airborne system knowledge graph; Design phase: Based on the control tasks and functional interaction logic of the airborne system, the entities are used to construct an initial airborne system knowledge graph; Simulation phase: Under given design requirements, the behavior and performance of the knowledge graph are simulated and verified using RDFLib. The accuracy, completeness and usability of the initial airborne system knowledge graph are evaluated based on the simulation and verification results, and the initial airborne system knowledge graph is improved based on the evaluation results. Verification Phase: Under the given design requirements, the airborne system design is tested using the improved initial airborne system knowledge graph to verify the accuracy and usability of the airborne system knowledge graph. Based on the verification results, the airborne system knowledge graph is iteratively optimized to obtain the optimized airborne system knowledge graph.

[0029] Step 4: Based on the design requirements of the airborne system to be designed, a semantic-based model retrieval method is used to retrieve existing airborne system meta-models that fit the design requirements from the airborne system meta-model knowledge graph. The retrieved airborne system meta-models are then matched and combined, or customized and extended, to form an airborne system meta-model suitable for the design requirements of the airborne system to be designed, such as... Figure 4 As shown.

[0030] It should be noted that the newly obtained customized and extended airborne system meta-models can be added to the existing airborne system meta-model knowledge graph, which can enrich the airborne system meta-model library in the airborne field, provide a more comprehensive reference for subsequent airborne system design, and ensure the accuracy and reusability of the model.

[0031] This invention first establishes a hierarchical architecture for airborne business models, defining the attributes and relationships of airborne system requirement meta-models and functional meta-models. Then, it uses natural language processing and machine learning techniques to extract entity and relationship information from the airborne requirement meta-models and functional meta-models, adding semantic descriptions to the entities and relationships to form an airborne system meta-model library. In the model reuse stage, relevant meta-models are retrieved from the meta-model library for reuse, or customized and extended, according to the airborne system design requirements of new projects, to form airborne system models suitable for new projects.

[0032] In this embodiment, a computer device is provided, such as... Figure 6 As shown, the system includes a memory 1, a processor 2, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the aforementioned method for constructing an airborne system meta-model based on a knowledge graph. Specifically, the computer device can be a computer terminal, a server, or a similar computing device.

[0033] In this embodiment, a computer-readable storage medium is provided, which stores a computer program that executes the above-described method for constructing an airborne system meta-model based on a knowledge graph.

[0034] Specifically, computer-readable storage media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer-readable storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable storage media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0035] Based on the same inventive concept, such as Figure 5 This embodiment also provides an airborne system meta-model construction device, including: The airborne system initial meta-model construction module is used to abstract airborne system services and existing models based on the definition standards of general meta-models and the airborne system business domain of airborne system business models, and to construct the airborne system initial meta-model; the airborne system initial meta-model includes a functional meta-model and a requirement meta-model. The airborne system metamodel construction module is used to define the attributes and relationships of the requirement metamodel and functional metamodel of the initial metamodel of the airborne system, forming an airborne system metamodel that represents airborne domain knowledge. The knowledge graph construction module is used to extract entity and relation information from the airborne system metamodel using natural language processing and machine learning algorithms, add semantic descriptions to entities and relations, and form an airborne system metamodel knowledge graph using Neo4j tools and store it in a graph database. The reuse module is used to retrieve existing airborne system meta-models that fit the design requirements of the airborne system to be designed from the airborne system meta-model knowledge graph using a semantic model retrieval method. The retrieved airborne system meta-models are matched and combined, or customized and extended, to form an airborne system meta-model suitable for the design requirements of the airborne system to be designed.

[0036] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for constructing a meta-model of an airborne system, characterized in that, include: Based on the definition standard of the general meta-model and the airborne system business domain of the airborne system business model, the airborne system business and existing models are abstracted to construct the initial meta-model of the airborne system. The initial meta-model of the airborne system includes a requirement meta-model and a functional meta-model; The attributes and relationships of the requirement meta-model and functional meta-model of the initial meta-model of the airborne system are defined to form an airborne system meta-model that represents airborne domain knowledge. Natural language processing and machine learning algorithms are used to extract entity and relation information from the airborne system metamodel, semantic descriptions are added to the entities and relations, and a knowledge graph of the airborne system metamodel is formed by Neo4j and stored in a graph database. Based on the design requirements of the airborne system to be designed, a semantic-based model retrieval method is adopted to retrieve existing airborne system meta-models that fit the design requirements from the airborne system meta-model knowledge graph. The retrieved airborne system meta-models are matched and combined, or customized and extended, to form an airborne system meta-model suitable for the design requirements of the airborne system to be designed.

2. The method for constructing an airborne system meta-model according to claim 1, characterized in that, The method for constructing the initial meta-model of the airborne system includes: Based on the definition standard of the general meta-model, the airborne system business and existing models are abstracted to construct a hierarchical architecture of the airborne system business model; Based on the hierarchical architecture of the airborne system business model, the initial meta-model of the airborne system is constructed according to the airborne system business domain.

3. The method for constructing an airborne system meta-model according to claim 1, characterized in that, The demand meta-model is used to represent the set of requirements for the functions and attributes of a system, component, or device, and the functional meta-model is used to represent the model components of system functions.

4. The method for constructing an airborne system meta-model according to claim 3, characterized in that, The requirement metamodel includes a requirement specification metamodel, a requirement item metamodel, and a verification method metamodel.

5. The method for constructing an airborne system meta-model according to claim 4, characterized in that, Methods for forming knowledge graphs of airborne system meta-models include: The entities extracted from the airborne system meta-model are analyzed to clarify the attributes of each entity and the relationships between entities, and to determine the basic structure of the airborne system knowledge graph. Based on the control tasks and functional interaction logic of the airborne system, an initial airborne system knowledge graph is constructed using the entities. The initial airborne system knowledge graph is simulated under given design requirements. The accuracy, completeness and usability of the initial airborne system knowledge graph are evaluated based on the simulation results. The initial airborne system knowledge graph is then improved based on the evaluation results. Given design requirements, the airborne system design test is conducted using the improved initial airborne system knowledge graph to verify the accuracy and usability of the airborne system knowledge graph. Based on the verification results, the airborne system knowledge graph is iteratively optimized to obtain the optimized airborne system knowledge graph.

6. The method for constructing an airborne system meta-model according to claim 5, characterized in that, The newly obtained airborne system meta-models, obtained through customization and expansion, are added to the existing airborne system meta-model knowledge graph.

7. The method for constructing an airborne system meta-model according to claim 6, characterized in that, The data in the airborne system meta-model includes structured data, semi-structured data, and unstructured data. The structured data includes standard databases, spreadsheets, and SysML models; the semi-structured data includes JSON files, XML files, and HTML web pages; and the unstructured data includes image files and video files.

8. A device for constructing a meta-model of an airborne system, characterized in that, include: The airborne system initial meta-model construction module is used to abstract airborne system services and existing models based on the definition standards of general meta-models and the airborne system business domain of airborne system business models, and to construct the airborne system initial meta-model; the airborne system initial meta-model includes a requirement meta-model and a functional meta-model. The airborne system metamodel construction module is used to define the attributes and relationships of the requirement metamodel and functional metamodel of the initial metamodel of the airborne system, forming an airborne system metamodel that represents airborne domain knowledge. The knowledge graph construction module is used to extract entity and relation information from the airborne system metamodel using natural language processing and machine learning algorithms, add semantic descriptions to entities and relations, and form an airborne system metamodel knowledge graph using Neo4j tools and store it in a graph database. The reuse module is used to retrieve existing airborne system meta-models that fit the design requirements of the airborne system to be designed from the airborne system meta-model knowledge graph using a semantic-based model retrieval method. The retrieved airborne system meta-models are then matched and combined, or customized and extended, to form an airborne system meta-model suitable for the design requirements of the airborne system to be designed.

9. A computer device comprising a memory (1), a processor (2), and a computer program stored in the memory (1) and executable on the processor (2), characterized in that, When the processor (2) executes the computer program, it implements the airborne system meta-model construction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that performs the airborne system metamodel construction method according to any one of claims 1 to 7.

Images