Multi-scale scene generation method of intelligent automobile information physical system based on domain ontology

Abstract

The invention relates to an intelligent automobile information physical system multi-scale scene generation method based on domain ontology. The method is characterized by comprising the following steps: S1, carrying out multi-scale division on an intelligent automobile information physical system IVCPS; s2, constructing an IVCPS scene domain ontology based on the ontology and a Steinfu seven-step method; and S3, constructing a signalized intersection IVCPS scene ontology instance by using the constructed scene domain ontology, and designing a corresponding test case. According to the method, the test complexity is reduced, the test efficiency is improved, a unified scene description framework is provided, the logic consistency is ensured, and the intersection performance is improved.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent transportation technology and relates to a multi-scale scene generation method for an intelligent automobile cyber-physical system based on domain ontology. Background Art

[0002] IVCPS is a closed-loop enabling system for state perception, real-time analysis, scientific decision-making, and precise execution based on the automatic flow of data between the transportation cyberspace and physical space. It features multi-entity, heterogeneous, open, closed-loop, emergent, and evolutionary characteristics. IVCPS enables secure and reliable collaboration and interoperability between heterogeneous information systems (broadly defined) and physical systems, supporting reliable, efficient, and real-time perception and decision-making control for intelligent vehicles, and promoting safe, efficient, and environmentally friendly transportation. However, its complex system architecture and diverse functional requirements present unprecedented challenges for system testing and verification.

[0003] From the perspective of system composition, IVCPS involves many different types of components and technologies. In terms of hardware, it includes various types of vehicle-mounted sensors, roadside equipment, computing platforms, and communication modules; the software level covers complex algorithms, protocols, and operating systems. These components and technologies are intertwined, making IVCPS a highly heterogeneous system. This heterogeneity increases the difficulty of system integration and testing. The compatibility and interoperability between different components require extensive testing and verification to be guaranteed. In terms of diverse needs, IVCPS must not only meet basic transportation needs, but also take into account requirements in traffic safety, environmental protection, and user experience. These diverse needs make the test scenarios of IVCPS extremely complex, making it difficult to fully cover and effectively verify them through traditional testing methods.

[0004] Existing testing technologies have numerous shortcomings when it comes to addressing the complexity of IVCPS. Firstly, due to the high complexity of IVCPS scenarios, traditional testing methods are often limited to testing certain functions or specific scenarios, failing to comprehensively and accurately assess the system's overall performance and reliability. Secondly, the lack of a unified and effective scenario description and modeling approach makes it difficult to compare and verify test results between different testing teams, hindering the standardization and formalization of testing technology. Summary of the Invention

[0005] In view of this, the object of the present invention is to construct a multi-scale division system, a scene domain ontology and a signalized intersection scene model for system testing and verification, scene standardization description and complex scene performance testing. Then, through each scale test, ontology construction and instantiation and test case design, the focus of different scale tests is clarified, a unified structured scene framework is established and intersection-related performance is improved. Finally, an overall scheme of multi-scale scene modeling of an intelligent vehicle cyber-physical system (IVCPS) based on domain ontology is proposed, which provides theoretical and practical support for IVCPS test case design and verification, ensures system reliability and safety, and promotes the widespread application and optimization upgrade of IVCPS in actual traffic scenes.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] A method for generating multi-scale scenarios for an intelligent vehicle cyber-physical system based on domain ontology includes the following steps:

[0008] S1: Multi-scale division of intelligent vehicle cyber-physical system IVCPS;

[0009] S2: Construct IVCPS scenario domain ontology based on ontology and Stanford seven-step method;

[0010] S3: Use the constructed scenario domain ontology to construct the signalized intersection IVCPS scenario ontology instance and design corresponding test cases.

[0011] Furthermore, in step S1, the IVCPS is divided into node level, unit level, subsystem level, system level and regional level;

[0012] The node level takes a single smart car as the perspective, only considering the internal components and system operation process of the vehicle, focusing on the intelligent reliability of the single vehicle, and testing the various functions equipped on the single vehicle based on the micro-vehicle model;

[0013] The unit-level IVCPS consists of multiple node-level IVCPSs, focusing on the reliability of vehicle-to-vehicle interaction and collaborative decision-making, and testing emerging collaborative functions between vehicles based on a vehicle-to-vehicle collaborative model.

[0014] The subsystem-level IVCPS consists of multiple unit-level IVCPSs and edge clouds, sensors, and actuators deployed at both ends of the road. It focuses on the effectiveness of edge computing in collaborative decision-making and tests roadside facilities and vehicle-road collaborative functions based on the vehicle-road collaborative model.

[0015] The system-level IVCPS includes multiple vehicle swarm systems, a certain amount of roadside infrastructure, multiple edge clouds, and regional clouds, which share local traffic status and decision-making. The system-level focuses on the interaction and effectiveness of collaborative decision-making between the vehicle, road, and cloud. Based on the vehicle-road-cloud collaborative model, the collaborative perception and decision-making functions under the vehicle-road-cloud integration are tested.

[0016] The regional-level IVCPS consists of multiple system-level IVCPSs and a central cloud and its Cyber. It focuses on the rationality of the global strategy on the cloud and deduces and verifies the macro traffic control strategy based on the regional traffic model.

[0017] Furthermore, the scenario domain ontology model in step S2 is described by a tuple:

[0018] Scenario=(C,P,R,A,I)

[0019] Among them, C is the concept set, which represents the set of related concepts in the intelligent vehicle cyber-physical system scenario; P is the attribute set, which is the data item used to describe the characteristics of the concept; R is the relationship set, and the relationship defines how different concepts interact with each other; A represents the axiom set, which is the constraints imposed on concepts, attributes and relationships, and is used to express the logical structure of the domain; I represents the instance set, and the instance is the specific implementation of the concept.

[0020] Furthermore, step S2 specifically includes the following steps:

[0021] S21: Determine the professional field and scope, covering multi-scale test scenarios and related content, from macro road networks to local single intersections;

[0022] S22: Construct an ontology concept terminology system, referencing existing standards and combining new elements of IVCPS to define concepts and attributes;

[0023] S23: Build a conceptual classification system and divide the scenarios into seven levels: static traffic roads, road landscapes, temporary road modifications, dynamic objects, environmental conditions, digital information, and cloud control services;

[0024] S24: Define concept relationships, including basic relationships between ontology concepts and specialized relationships extended for IVCPS scenarios;

[0025] S25: Define axioms and rules to ensure the consistency and correctness of the scenario ontology;

[0026] S26: Perform ontology instantiation and knowledge injection, and build scenario instances according to test requirements;

[0027] S27: Ensure ontology quality through verification and iteration.

[0028] Furthermore, the concept classification system constructed in step S23 specifically includes:

[0029] The static traffic road layer describes the static roads and fixed facilities that constitute the basic road network of the IVCPS physical space;

[0030] The road landscape layer describes the static entities on both sides of the road that have relatively little impact on road traffic;

[0031] The road temporary modification layer describes the temporary adjustment of the original traffic roads and road landscape layout;

[0032] The dynamic object layer describes the traffic physical entities in the scene that have at least one parameter that changes over time;

[0033] The environmental condition layer describes the natural and man-made environmental factors that affect road traffic;

[0034] The digital information layer describes the digital information collected and generated during the operation of IVCPS and the transmission and communication process;

[0035] The cloud control service layer describes the collection, processing and distribution of traffic network information in large cities.

[0036] Furthermore, the conceptual relationships described in step S24 include relationships between concepts and relationships within concepts. Relationships are the specific applications of attributes and are expressed in the form of triples of "subject-predicate-object". On the basis of retaining the basic relationships of ontological concepts, the IVCPS scenario relationships are expanded through IVCPS scenario-domain-specific relationships and spatiotemporal refinement semantics.

[0037] Furthermore, the conceptual relationships described in step S24 include: the relationship between the part and the whole, the relationship between the parent class and the child class, the relationship between the concept and the instance, the attributes of the concept or instance, the spatial rear relationship, the set contains members, the entity contains a part, the road section is associated with the construction area and obstacles, the vehicle is associated with a specific communication mode, a specific vehicle has the right of way, the connection between road elements, the spatial front relationship, the scene is associated with weather conditions, the road is associated with a specific type, the traffic light is associated with the current state, the traffic participant performs a specific driving action, the vehicle follows other vehicles, the scene is associated with the obstacle type, the condition or behavior triggers a specific event, the traffic participant or facility has the priority of way, the environment is associated with the visible range, and the entity belongs to a specific area.

[0038] Furthermore, when constructing the signalized intersection IVCPS scenario ontology instance in step S3, a model including static traffic roads, road landscapes, temporary road modifications, dynamic objects, environmental conditions, digital information, and cloud control service layers is constructed according to the characteristics of the signalized intersection;

[0039] The ontological concept attributes involved in static traffic roads include road type, shape parameters, number of lanes, pavement material, road marking type, location, type, speed limit range and scope of fixed traffic signs, as well as the location and status information of traffic lights, type and area of ​​special areas, and location and type of other additional structures;

[0040] The ontological conceptual attributes of road landscape include building parameters, tree height and its covered area; location information, height and material type of safety protection facilities; location, road occupation and covered area of ​​public facilities; and type, height and location of other building structures.

[0041] The ontological conceptual attributes of temporary road modifications include the type, location, and effective time of temporary construction signs; the color, type, and clarity of temporary construction road markings; the type, location, and lane occupation ratio of temporary obstacles; the location information, arrangement, color, and mobility of temporary traffic guidance facilities; and changes in the number of lanes, road shape, road surface condition, and slope caused by temporary modifications.

[0042] The ontological conceptual attributes of dynamic objects include the lateral and longitudinal position, velocity, acceleration, size of the vehicle, its lane and behavior mode; the type, position, speed and steering angle of non-motor vehicles; the age, position and movement mode of pedestrians; the type and motion parameters of other movable objects; and the dynamic parameters within the duration of the scene.

[0043] The ontological conceptual attributes of environmental conditions include weather type, duration event, climate intensity, definition of different time periods, visibility under atmospheric conditions, temperature, precipitation, as well as light type, light intensity, artificial light source position and the impact of weather on road conditions;

[0044] The ontological conceptual attributes of digital information include V2X communication objects, communication protocols, message types, signal coverage, signal strength, priority, transmission rate, data size, and packet loss rate; information about traffic facilities controlled by the traffic management platform; the source, data type, and timestamp of perception information; and decision-making information provided by the computing unit.

[0045] The ontological conceptual attributes of cloud services include the level, service scope, computing time, cache time, data interface protocol, service type and recommendation information of the edge cloud control system; the level, coverage, computing resources, optimization cycle, guidance suggestions and interface standards of the regional cloud control system; the level, data storage scale, preset model, response time and macro-control type of the central cloud control system.

[0046] Furthermore, in step S3, the test cases are designed in accordance with the “input-processing-output” closed-loop verification principle. By deconstructing the real traffic scenario, elements are extracted from the scenario model to generate test cases, and the test case number, name, type, scenario description, preset conditions, test steps, evaluation criteria and expected results are clearly defined.

[0047] The beneficial effects of the present invention are:

[0048] 1. Reduce test complexity and improve test efficiency: The multi-scale partitioning method of the present invention decomposes complex IVCPS tests into independently verifiable modules, and performs layered and progressive verification from a single vehicle to the entire system. This reduces test complexity, improves test case coverage, shortens the full system verification cycle, and makes faults traceable.

[0049] 2. Provide a unified scenario description framework: The IVCPS scenario domain ontology and structured scenario model built based on the domain ontology provide a unified, structured and extensible scenario description framework, ensuring the unified definition of entities, attributes and relationships in the test scenario, facilitating the generation of automated test scenarios, and can be flexibly updated as technology develops, ensuring logical consistency.

[0050] 3. Improve intersection performance: Scenario models and test cases constructed for signalized intersections help improve the traffic efficiency and safety of IVCPS at intersections. They can more comprehensively and accurately test the performance of the system in complex traffic scenarios, providing strong support for the practical application of IVCPS.

[0051] Other advantages, objects, and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art upon examination of the following description or may be learned from practice of the present invention. The objects and other advantages of the present invention may be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below with reference to the accompanying drawings, in which:

[0053] Figure 1 Multi-scale partitioning of cyber-physical systems for intelligent vehicles;

[0054] Figure 2 Build a framework for IVCPS scenario domain ontology;

[0055] Figure 3 Structuring scenario ontology for IVCPS;

[0056] Figure 4 This is a schematic diagram of a signalized intersection scene;

[0057] Figure 5 It is the UML-based IVCPS cloud-controlled signalized intersection scene ontology;

[0058] Figure 6 This is the CCFtap condition in Euro-NCAP;

[0059] Figure 7 It is an instance of IVCPS scenario ontology;

[0060] Figure 8 Schematic diagram for scene layout. DETAILED DESCRIPTION

[0061] The following describes the embodiments of the present invention by means of specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and the features in the following embodiments and embodiments can be combined with each other without conflict.

[0062] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0063] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the embodiments of the present invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring the embodiments of the present invention.

[0064] Example 1:

[0065] The present invention provides an IVCPS multi-scale scene generation method based on domain ontology, comprising the following steps:

[0066] Step 1: Divide IVCPS into multiple scales, including node level, unit level, subsystem level, system level and regional level, such as Figure 1 and as shown in Table 1.

[0067] Table 1

[0068]

[0069] The node-level IVCPS is the smallest entity of the entire system. It takes a single smart car as the perspective and only considers the internal components of the vehicle and the system operation process. The single vehicle completes the functions of perception, calculation, interaction and decision-making. The vehicle virtual body needs to load a high-precision vehicle mapping model, the environmental model perceived by the vehicle entity, and the relevant decision-making and control algorithms of the vehicle's own operation, and share the vehicle's parameter information, perception and received traffic information with other traffic elements in the system. The node level focuses on the intelligent reliability of the single vehicle, tests the various functions equipped on the single vehicle based on the micro-vehicle model, and realizes low-latency and high-precision perception and control of the single vehicle;

[0070] The unit-level IVCPS is composed of multiple vehicle IVCPS (node ​​level), and each vehicle system has independent vehicle entities, vehicle virtual entities, and sensing and execution components. The unit level focuses on the reliability of vehicle-to-vehicle interaction and collaborative decision-making, and tests the emerging collaborative functions between vehicles based on the vehicle-to-vehicle collaborative model. The unit-level IVCPS breaks through the intelligence of a single vehicle and establishes a communication link with surrounding vehicles in a V2V manner. Vehicles interact and share information, and make decisions and controls in a collaborative manner. It can achieve beyond-visual-range perception, collision warning, formation collaboration and other functions that cannot be completed by a single vehicle;

[0071] The subsystem-level IVCPS consists of multiple multi-vehicle IVCPS (unit level) and edge clouds, sensors, and actuators deployed at both ends of the road. The subsystem level focuses on the effectiveness of edge computing in collaborative decision-making, and tests roadside facilities and vehicle-road collaborative functions based on the vehicle-road collaborative model. The edge cloud can be combined with traditional transportation infrastructure to become an intelligent transportation facility. In addition to the basic transportation facility functions, it also has a certain computing power to support task offloading and provide smart cars with cloud-controlled basic services such as real-time and weak real-time distributed computing that enhance safety and reduce energy consumption. It can realize short-term traffic flow prediction, small-scale collaborative control, and other low-latency functions to improve driving safety and optimize fleet collaboration.

[0072] System-level IVCPS includes a large number of vehicles forming a swarm system, a certain number of roadside infrastructures, multiple edge clouds and regional clouds, which are linked by wired or wireless communications and can share a large amount of information to share local traffic status and decision-making. The system level focuses on the effectiveness of the interaction and collaborative decision-making between the vehicle, road and cloud, and tests the collaborative perception, decision-making and other functions under the vehicle-road-cloud integration based on the vehicle-road-cloud collaborative model. The regional cloud can provide basic services such as weak real-time or non-real-time computing for transportation and management, and is the convergence point of multiple edge clouds. Within a certain road section, more information can be shared between traffic elements, and weak real-time traffic tasks such as large-scale data analysis and processing can be realized;

[0073] The regional-level IVCPS consists of multiple vehicle-road IVCPS (system level) and a central cloud and its Cyber. The regional level focuses on the rationality of the global strategy on the cloud, and deduces and verifies the macro-traffic control strategy based on the regional traffic model. The central cloud usually has more powerful computing resources, including high-performance servers, storage devices and computing clusters. The regional-level IVCPS can achieve cross-system and cross-platform interconnection, intercommunication and interoperability through the big data platform, and realize on-demand response, rapid iteration and dynamic optimization of road resource configuration and operation. The regional-level IVCPS is capable of centralized data processing, backup, recovery and long-term storage of data, and integration of third-party services to solve more complex non-real-time traffic tasks.

[0074] Step 2: Construct an IVCPS scenario domain ontology model based on ontology and Stanford seven-step method;

[0075] The scenario domain ontology model can be described by a tuple:

[0076] Scenario=(C,P,R,A,I)

[0077] Among them, C is the concept set, which represents the collection of related concepts in the intelligent vehicle cyber-physical system scenario. It is an abstract classification of all objects in the domain and an accurate and standardized description of each type of scene objects with the same characteristics. Common attribute types include numerical classes, enumeration classes, and date classes. P is the attribute set, which is a data item used to describe the characteristics of a concept and can provide a more detailed description of a single concept. R is the relationship set. Relationships define how different concepts interact with each other. These relationships link different concepts. Common relationship types include inheritance relationships (subclasses and parent classes) and composition relationships. A represents the axiom set, which is the constraints imposed on concepts, attributes, and relationships. It is an objective criterion used to express the logical structure of the domain. I represents the instance set. An instance is a specific implementation of a concept.

[0078] Constructing IVCPS scenario domain ontology framework Figure 2 The specific steps are as follows:

[0079] (1) Determine the professional field and scope;

[0080] The domain ontology defined in this paper represents typical scenarios for intelligent vehicle cyber-physical systems. It covers multi-scale test scenarios, from macroscopic road networks to localized single intersections, and encompasses environmental factors, traffic infrastructure, vehicle behavior, communication information, decision-making and control, and real-time data acquisition and processing. The goal is to provide unified and accurate semantic support for test scenario description, modeling, verification, and test case generation.

[0081] (2) Constructing the ontology concept terminology system;

[0082] Refer to existing standards, such as autonomous driving and vehicle-road collaboration specifications, and combine new elements of IVCPS, such as new on-board equipment and cloud control functions, to accurately define concepts and attributes.

[0083] The cyber-physical system for intelligent vehicles involves technical fields such as intelligent vehicles, autonomous driving, and V2X communication technology. Many of these technologies have been updated and iterated for many years. Following the principles of sharing and formalization, the ontology concepts, their attributes, and relationships constructed in this paper refer to the definitions of existing scenario-based autonomous driving, vehicle-road collaborative testing processes, and related standards, such as the 6-layer scenario model proposed by PEGASUS, ISO 23150 (Autonomous Driving System Architecture), and ETSI TS103 900 (C-V2X Communication Protocol). Concept attributes describe the personalized characteristics of a concept. Different concepts, and even different instances, require different attributes.

[0084] Based on the existing ontology concepts, in response to the new elements added to the intelligent vehicle cyber-physical system and the emerging new functions, some concepts and attributes of the IVCPS scenario ontology are shown in Table 2.

[0085] Table 2

[0086]

[0087] (3) Construct a conceptual classification system;

[0088] In order to reduce complexity and provide a structured method, the present invention establishes a hierarchical concept classification system to support the hierarchical description of IVCPS scenarios. A top-down approach is adopted to intuitively display the classification structure of the scenario ontology concepts through a tree diagram. Starting from the root node "IVCPS scenario ontology", the scene is divided into the following seven levels: static traffic roads, road landscapes, temporary road modifications, dynamic objects, environmental conditions, digital information and cloud control services. Through this structured model, the concepts and attributes are refined layer by layer to construct leaf-level concepts and attributes. The tree structure intuitively shows the category relationship and hierarchical division between the concepts in the IVCPS scenario, where each subtree represents an independent and modular knowledge unit in the domain, reflecting the semantic associations and constraints between different concepts or entities. The specific structure will be described in detail in the next step.

[0089] (4) define conceptual relationships;

[0090] In the IVCPS scenario domain ontology, concepts do not exist in isolation. Instead, they are coupled and linked between ontology concepts, interweaving scenario information to form a complex, multidimensional intelligent vehicle cyber-physical system scenario. Conceptual relationships include those between concepts and those within concepts. Relationships are the specific application of attributes and can be expressed using triples (subject-predicate-object). Common basic relationships in ontology, such as inheritance and composition, can be expressed using triples, as shown in Table 3.

[0091] Table 3

[0092]

[0093]

[0094] However, the basic relationships in traditional ontology are clearly insufficient to describe complex systems like intelligent vehicle cyber-physical systems. While retaining the basic relationships within the ontology concepts, we can expand the IVCPS scenario relationships through IVCPS scenario-specific relationships and spatiotemporal semantic refinement, thereby constructing a refined IVCPS scenario knowledge model. The constructed relationships are shown in Table 4.

[0095]

[0096] (5) Define axioms and rules;

[0097] Axioms and rules are used to ensure the consistency and correctness of the scenario ontology. Defining axioms and rules mainly includes describing the basic logical relationships between concepts and attributes, realizing complex business logic reasoning, and defining data integrity rules. The scenario ontology comes from the real world, so all definitions of the scenario ontology are subject to the constraints of physical rules. For example, there is an upper limit on vehicle speed under vehicle dynamics, the braking distance at different speeds is different, and the detection range of radar has limits. Attribute restrictions are the key to constructing logical scenarios. In logical scenarios, they can be understood as the parameter space of different scenario elements. Therefore, attribute restrictions are subject to the constraints of real traffic data and can be obtained through natural driving data analysis. Finally, there are restrictions on relevant traffic laws and regulations, such as speed limit regulations in different areas, the setting of emergency lanes, etc. These restrictions together constitute the axioms and rules of the IVCPS scenario book.

[0098] (6) Ontology instantiation and knowledge injection;

[0099] A scenario instance describes a specific scenario or actual application case by concretizing the concepts, attributes, and relationships in the ontology for application and reasoning. The construction of the scenario instance in this patent first defines the research object as an urban signalized intersection based on the test requirements. Starting with a seven-layer structured scenario model, the concepts at each layer are gradually expanded downward. Concept attributes and their value ranges are further determined through simulation data, expert experience, and real-world scenario data to construct a logical scenario. Finally, the actual attribute data is filled in to obtain a specific scenario, or scenario instance.

[0100] (7) Verification and iteration;

[0101] In modern ontology methodology, in order to focus on the construction of dynamic knowledge systems, a verification and iteration process is introduced to ensure the quality of the ontology through multi-dimensional verification and iteration. Verification uses formal methods to test the logical consistency, conceptual completeness, and rule validity of the ontology. Iteration is based on verification results and business feedback to continuously optimize the ontology structure, expand the knowledge coverage, and form a closed loop. IVCPS scenarios mainly use expert inspections and software reasoning execution to check the logical consistency of the scenario ontology, determine whether the definition of the relationship meets actual needs, and whether the data conforms to the domain specifications. The project is iterated and versioned through the Git version management tool, and logs are established to ensure version traceability.

[0102] This paper proposes a hierarchical IVCPS scenario ontology structured model, which divides the scenario into seven levels: static traffic road, road landscape, temporary road modification, dynamic objects, environmental conditions, digital information and cloud control services. The specific definitions are as follows:

[0103] (1) Static traffic roads;

[0104] The first layer, "static traffic roads," mainly describes the static roads that constitute the basic road network of the IVCPS physical space and the fixed facilities that have a significant impact on traffic. This layer reflects the basic attributes of the road, such as its geometry, topology, and elevation. It also includes a description of the road surface features and guiding facilities associated with traffic rules, such as permanent traffic signs, traffic lights, road direction indicators, and speed limit signs. It should be noted that although permanent traffic signs and traffic lights are classified as static facilities, their state changes will be described in subsequent layers. Including these facilities in the static layer reflects the comprehensive layout of road structure and basic traffic facilities in modern road construction, which helps to simulate and construct the modern road environment more realistically.

[0105] Based on the above description, the ontological conceptual attributes involved in this layer include road type, shape parameters, number of lanes, pavement material, and road marking type. It also covers the location, type, speed limit range, and scope of fixed traffic signs, as well as the location and status information of traffic lights. Furthermore, the type and area of ​​special areas (such as parking spaces and fire areas) must be defined, and the location and type of other additional structures (such as manhole covers and speed bumps) are also included in the description. After completing the construction of this layer, traffic participants can perform basic driving tasks based on this foundation, forming a partially orderly traffic state. At the same time, based on information about road geometry, topology, terrain, and related infrastructure, a preliminary assessment of the scene complexity can be made.

[0106] (2) Traffic road landscape;

[0107] The second layer, "traffic road landscape," mainly describes all static entities located on both sides of the traffic road that have relatively little impact on road traffic. These entities are usually fixed to the edge of the road rather than on the road surface. Although existing modeling and simulation studies often ignore these landscape elements, as an indispensable component of the cyber-physical system, their description is equally important. Compared with highways, rural roads and urban roads, especially in large cities, have a larger number of roadside buildings, green facilities, and public supporting facilities. Under specific environmental conditions, these landscapes may have a certain impact on traffic lighting, vision, etc., and are also an important factor in the multi-source information noise detected by vehicle-mounted and road sensors. In order to balance realism and computational cost, this layer can be simplified or simulated in detail according to specific needs during the simulation process.

[0108] In general, the ontological conceptual attributes defined at this layer include building parameters, tree heights, and their covered areas; the location, height, and material type of safety features (such as guardrails and steps); the location, road occupation, and covered area of ​​public facilities (such as streetlights, fire hydrants, and bus shelters); and the type, height, and location of other structures (such as tunnels and bridges). This description provides essential background information for overall IVCPS scenario modeling. While its direct impact on traffic operations is minimal, it impacts the granularity and fidelity of the scenario during testing and simulation.

[0109] (3) Temporary modifications of the first and second layers;

[0110] The third layer, "Temporary Adjustments to Traffic and Landscape Facilities," describes temporary adjustments to the original traffic and landscape layout. These modifications arise from situations such as road construction, emergencies, or traffic control, and may alter road signs, route planning, and safety features, impacting road structure, traversable areas, and some traffic regulations. Although these modifications are inherently short-term, they must remain consistent throughout the scenario duration for stable simulation and evaluation.

[0111] Specifically, the third layer includes measures such as setting up temporary traffic signals, adjusting road markings, demarcating temporary no-parking zones, and deploying temporary roadblocks and fences. While some facilities normally belong to the first or second layer, they appear in different states in temporary modification scenarios and therefore require separate descriptions. The duration of a temporary modification depends on the test requirements and the spatiotemporal scale of the scenario and may range from a few minutes to several days. The conceptual attribute definitions for this layer in the ontology cover the type, location, and effective time of temporary construction signs; the color, type, and clarity of temporary construction road markings; the type, location, and lane occupation ratio of temporary obstacles (such as cardboard boxes, fallen trees, fallen rocks, or spilled liquids); the location information, arrangement, color, and mobility of temporary traffic guidance facilities (such as traffic cones and warning lines); and changes in the number of lanes, road shape, road surface condition, and slope caused by temporary modifications.

[0112] Through the systematic description of these temporary adjustments, the third layer provides support for IVCPS scenario modeling to cope with dynamic changing factors in reality, enabling the test platform to more accurately simulate the impact of emergencies on the traffic system, thereby improving the comprehensiveness and effectiveness of simulation tests.

[0113] (4) Dynamic objects;

[0114] The fourth layer, "dynamic objects," describes physical traffic entities in the scene whose at least one parameter changes over time. These entities primarily convey the characteristics and state of traffic participants during their motion. Unlike the static entities in the first three layers, whose attributes remain unchanged, the fourth layer introduces a temporal dimension, encompassing dynamic changes in displacement, velocity, acceleration, and other aspects of vehicles, non-motorized vehicles, pedestrians, and other movable objects. It is worth noting that traffic participants that remain completely stationary on the road and whose state remains unchanged or shows no trend of change should be classified as first-layer static entities. However, instances such as a stopped vehicle with its hazard lights activated, a vehicle preparing to start with varying acceleration even at zero speed, and the periodic switching of traffic lights in operation are considered dynamic objects. Furthermore, objects whose state changes due to external factors, such as a sphere intruding on the road or a traffic sign gradually buried by snow, are also considered dynamic objects. Attributes such as lighting and weather conditions will be defined separately in subsequent layers.

[0115] The fourth layer's ontological attributes include the vehicle's lateral and longitudinal position, velocity, acceleration, size, lane, and behavior pattern; the type, position, velocity, and steering angle of non-motor vehicles; the age, position, and movement pattern of pedestrians (e.g., scattered and random or queued and gathered); and the type and motion parameters of other movable objects (e.g., animals or a soccer ball kicked into the road). This layer also describes dynamic parameters over the duration of the scene, such as the pattern of traffic light changes. The construction of this layer provides the necessary support for capturing dynamic interactions in traffic systems in real time, thereby helping to improve the simulation accuracy and system response evaluation of IVCPS testing.

[0116] (5) Environmental conditions;

[0117] The fifth layer, "Environmental Conditions," describes the natural and man-made environmental factors that affect road traffic. These objective conditions play a key role in the safety and comfort of road users. This layer covers not only weather types, persistent climate events, and climate intensity, but also environmental changes during different time periods such as daytime, dawn / dusk, and nighttime, as well as visibility, temperature, and precipitation under atmospheric conditions. In addition, this layer provides a detailed description of lighting conditions, including both natural light sources (such as the sun) and artificial light sources (such as streetlights), clearly recording their lighting type and intensity, as well as the spatial distribution of light sources. It should be noted that environmental conditions only refer to these objective natural and man-made factors; if these conditions cause dynamic changes, such as wind causing a garbage bin to collapse or snow covering a traffic sign, they should be classified as the fourth layer, "Dynamic Objects." In the ontology construction, the fifth layer of conceptual attributes includes weather type, duration, climate intensity, definitions of different time periods (daytime, dawn / dusk, nighttime), visibility under atmospheric conditions, temperature, precipitation, as well as lighting type, lighting intensity, location of artificial light sources, and the impact of weather on road conditions (such as residual precipitation and friction). This layer provides an objective description of the overall scenario, helping to accurately evaluate the impact of external conditions on traffic system performance during testing.

[0118] (6) Digital information;

[0119] The sixth layer, "digital information," describes all digital information collected and generated during the operation of the IVCPS, as well as the related transmission and communication processes, forming the foundation of the system's cyberspace. This layer brings together diverse data from on-board sensors, roadside sensors, high-precision map platforms, and other data sources. It aims to support intelligent vehicles' perception of their surroundings, decision-making, and path planning, while also providing a data basis for traffic status monitoring and cloud-based management. Compared to traditional autonomous driving systems, the digital information in the IVCPS is richer in source, type, and structure, and the proportion of information collected from non-vehicle sources is increasing. Although current V2X communications, cloud-based control technologies, and intelligent transportation infrastructure are still under development, the amount and importance of information carried by this layer will continue to grow with technological advancements.

[0120] The conceptual attributes of the sixth layer include: V2X communication objects, communication protocols, message types, signal coverage, signal strength, priority, transmission rate, data size, and packet loss rate; information from the traffic management platform regarding traffic facility control, such as phase switching logic, variable traffic sign status, dynamic speed limits, and fault codes; the source, data type (such as video, audio, text), and timestamp of perception information; and decision-making information provided by the computing unit, such as recommended speed and recommended route. The information integration and communication mechanisms at this layer provide solid data support for IVCPS, helping the system achieve efficient decision-making and precise traffic management.

[0121] (7) Cloud services;

[0122] The seventh layer, "cloud services," describes the collection, processing, and distribution of information on larger urban traffic networks, transportation hubs, public transportation systems, and cross-regional management. This layer can integrate traffic data from multiple roads, multiple intersections, and even the entire city, and perform operations on physical processes and biological characteristic information, such as control, collaboration, cloudification, calculation, and deduction. Through in-depth processing of the sixth layer of digital information, this layer constructs a digital twin to achieve real-time simulation of the physical system in a virtual environment, thereby providing virtual-reality interactive feedback, data fusion analysis, and iterative decision optimization, and ultimately establishing a virtual mapping model that fully corresponds to the real physical system. This model not only strengthens the connection between physical space and cyberspace, but also supports the system tasks that the IVCPS is currently executing or will soon execute, ensuring that the overall system achieves safe and reliable operation while meeting functional and performance requirements.

[0123] It should be noted that the seventh layer only involves the processing of digital information, while physical entities such as roadside infrastructure and cloud-based control facilities that collect this information belong to the previous layers. In the ontology construction, the conceptual attributes of the seventh layer include: the level, service scope, computing time, caching time, data interface protocol, service type, and recommended information of the edge cloud and cloud-based control system; the level, coverage, computing resources, optimization cycle, guidance recommendations, and interface standards of the regional cloud and cloud-based control system; and the level, data storage scale, pre-configured model, response time, and macro-control type of the central cloud and cloud-based control system. Together, these attributes provide a comprehensive description and technical support for the cloud-based service capabilities of the IVCPS.

[0124] The above content describes in detail each layer of the IVCPS structured scenario, including its naming, definition, and content, thereby enabling accurate classification of various concepts within the intelligent vehicle cyber-physical system operational scenario. To further reduce ambiguity in the ontological concept classification process, the following points should be noted: First, within the ontological framework, concepts in the IVCPS scenario encompass not only physical entities but also virtual entities such as data and digital twins. Broadly speaking, entities encompass both objective material entities and abstract concepts, processes, and events. Therefore, in the IVCPS structured scenario, layers 1 through 5 correspond to the physical space, while layers 6 through 7 correspond to the cyber space. The deep integration of physical and cyber spaces is a key characteristic of CPS. Separating these concepts during the construction process helps reduce overall complexity and facilitates system development and testing. Second, layers 1 through 3 employ static, spatially based descriptions that do not account for temporal changes. Although temporary modifications in layer 3 may vary internally, their impact on traffic remains constant throughout the scenario. Finally, identical attributes of the same entity should be assigned to the same layer to ensure consistent attribute descriptions.

[0125] like Figure 3 As shown in the figure, the IVCPS structured scenario ontology deconstructs the entire scenario at a finer granularity. The hierarchical order is only for the convenience of structural division and does not represent the importance of each layer. In actual traffic scenarios, the number of traffic elements is infinite, but they can be classified according to type. When testing IVCPS, the use of structured scenario elements can select relevant content, thereby constructing test scenarios more accurately and realistically, which is convenient for simulation modeling. The structured IVCPS scenario helps to establish a standardized test scenario library. By dividing all scenario parameters into seven levels, the parameter indicators of each scenario can be clearly described, providing a solid foundation for subsequent standardized testing and realizing the reproduction of scenarios on different test platforms.

[0126] Step 3: Use the constructed scenario domain ontology to construct the signalized intersection IVCPS scenario ontology instance and design corresponding test cases.

[0127] (1) In this embodiment, a signalized intersection scene ontology instance is constructed:

[0128] After the IVCPS scenario domain ontology is defined, the framework can be used to analyze and model different scenarios. The signal intersection scenario diagram is as follows: Figure 4 First, a seven-layer structured model of the signalized intersection scene is constructed:

[0129] Layer 1: The road type is an intersection, with four lanes in both north-south and east-west directions, a hard shoulder, solid lines on the road boundary, dashed lines between lanes, a traffic sign with a speed limit of 40, and a road camera in the RSU.

[0130] Layer 2: Buildings and houses along the road

[0131] Tier 3: None

[0132] Level 4: Multiple cars, trucks, pedestrians, and normal traffic lights

[0133] Layer 5: Clear weather, normal lighting conditions, visibility, and temperature conditions (not visible in the sketch)

[0134] Layer 6: V2V, V2I, V2C, I2C communications, traffic data information perceived by vehicles and RSUs

[0135] Layer 7: The regional cloud and the edge cloud in the RSU receive various types of information, build a digital twin model of the intersection, and provide services such as vehicle-road-cloud collaborative perception and cloud-based path planning.

[0136] Use the Unified Modeling Language (UML) to describe the signalized intersection scene ontology and analyze the detailed concepts, attributes and relationships within the signalized intersection. In addition, annotations can be added using annotation symbols, such as Figure 5 shown.

[0137] This embodiment is based on the CCFtap (Car-to-Car Front turn-across-path) test example in Euro-NCAP (European New Car Assessment Program) (scenario such as Figure 6 ), build an intersection scenario conflict warning test instance.

[0138] Scenario description: At an IVCPS cloud-controlled intersection, roadside facilities are able to sense and receive vehicle information. A test vehicle drives forward through the intersection and turns left. A vehicle traveling at a constant speed oncoming from the opposite direction hits the front structure of another background vehicle at 50% of its front height.

[0139] Test content: A vehicle is traveling forward at a speed of 10-20 km / h (5 km / h step length) and there is a vehicle in front of it traveling at a speed of 30-60 km / h (15 km / h step length). Under normal driving conditions, after a period of time, the two vehicles will collide in the intersection. The test tasks include 1) whether the AEB of the tested vehicle can brake in time and whether the tested vehicle intrudes into the path of the target vehicle; 2) whether the edge cloud can provide timely collision warning and give a recommended speed to avoid collision. The constructed scene entity example is Figure 7 shown.

[0140] (2) Test case description of IVCPS scenario:

[0141] The IVCPS scenario domain ontology, through refined semantic design and scenario-driven modeling, covers the entire chain of requirements, from static road networks to dynamic behaviors, from environmental constraints to rule verification. This formalizes and simplifies the test scenario construction process. Different values ​​are assigned to the constructed scenario models, and independent elements and coupled parameters are combined to generate corresponding test cases. The test case construction framework is shown in Table 5.

[0142] Table 5

[0143]

[0144]

[0145] Specific scenarios and test cases are two closely related but different concepts. A test case is a detailed test step designed for a specific test purpose based on a specific scenario. In other words, a test case is a concretization and refinement of a specific scenario. A complete description of a test case includes a description of the scenario and relevant scenario attribute parameters. The scenario description provides an abstract description of the test environment, test process, and test method, while the test case is a concrete description of the entire test process, including the use case number, name, scenario description, test steps, expected results, etc. Taking the IVCPS intersection scenario body test of the cloud collision warning (CCW) function in Table 5 as an example, the description of the test case is shown in Table 6.

[0146] Table 6

[0147]

[0148]

[0149] Example 2:

[0150] An electronic device comprising a memory and a processor;

[0151] The memory is used to store computer programs;

[0152] The processor is configured to implement the method described in Example 1 when executing the computer program.

[0153] Example 3:

[0154] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in Example 1 is implemented.

[0155] Example 4:

[0156] A computer program product includes a computer program, which implements the method described in embodiment 1 when executed by a processor.

[0157] In the above embodiments, references to "this embodiment" in the specification indicate that a particular feature, structure, or characteristic described in conjunction with the embodiment is included in at least some embodiments, but not necessarily all embodiments. Multiple occurrences of "this embodiment" do not necessarily refer to the same embodiment.

[0158] In the above embodiments, although the invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those skilled in the art based on the foregoing description. For example, other memory structures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed. The embodiments of the present invention are intended to encompass all such alternatives, modifications, and variations that fall within the broad scope of the appended claims.

[0159] Regarding the computer-readable storage medium in this embodiment, those skilled in the art will appreciate that all or part of the steps in the aforementioned method embodiments can be implemented using hardware associated with the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When executed, the program performs the steps in the aforementioned method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0160] The electronic terminal provided in this embodiment includes a processor, a memory, a transceiver and a communication interface. The memory and the communication interface are connected to the processor and the transceiver and complete communication with each other. The memory is used to store computer programs, the communication interface is used for communication, and the processor and the transceiver are used to run computer programs so that the electronic terminal executes the various steps of the above method.

[0161] In this embodiment, the memory may include a random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage.

[0162] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0163] The present invention can be used in a wide variety of general-purpose or special-purpose computing system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments that include any of the above.

[0164] The present invention may be described in the general context of computer-executable instructions, such as program modules, executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including storage devices.

[0165] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solutions, which should all be included in the scope of the claims of the present invention.

Claims

1. A multi-scale scene generation method for intelligent vehicle cyber-physical systems based on domain ontology, characterized by: The following steps are involved: S1: Multi-scale division of intelligent vehicle cyber-physical system IVCPS; S2: Construct IVCPS scenario domain ontology based on ontology and Stanford seven-step method; S3: Use the constructed scenario domain ontology to construct a signalized intersection IVCPS scenario ontology instance and design corresponding test cases.

2. The method for generating multi-scale scenarios for intelligent vehicle cyber-physical systems based on domain ontology according to claim 1 is characterized by: In step S1, the IVCPS is divided into node level, unit level, subsystem level, system level and regional level; The node level takes a single smart car as the perspective, only considering the internal components and system operation process of the vehicle, focusing on the intelligent reliability of the single vehicle, and testing the various functions equipped on the single vehicle based on the micro-vehicle model; The unit-level IVCPS consists of multiple node-level IVCPSs, focusing on the reliability of vehicle-to-vehicle interaction and collaborative decision-making, and testing emerging collaborative functions between vehicles based on a vehicle-to-vehicle collaborative model. The subsystem-level IVCPS consists of multiple unit-level IVCPSs and edge clouds, sensors, and actuators deployed at both ends of the road. It focuses on the effectiveness of edge computing in collaborative decision-making and tests roadside facilities and vehicle-road collaborative functions based on the vehicle-road collaborative model. The system-level IVCPS includes multiple vehicle swarm systems, a certain amount of roadside infrastructure, multiple edge clouds, and regional clouds, which share local traffic status and decision-making. The system-level focuses on the interaction and effectiveness of collaborative decision-making between the vehicle, road, and cloud. Based on the vehicle-road-cloud collaborative model, the collaborative perception and decision-making functions under the vehicle-road-cloud integration are tested. The regional-level IVCPS consists of multiple system-level IVCPSs and a central cloud and its Cyber. It focuses on the rationality of the global strategy on the cloud and deduces and verifies the macro traffic control strategy based on the regional traffic model.

3. The method for generating multi-scale scenarios for intelligent vehicle cyber-physical systems based on domain ontology according to claim 1 is characterized by: In step S2, the scenario domain ontology model is described by a tuple: Scenario=(C,P,R,A,I) Where C is the concept set, which represents the set of related concepts in the intelligent vehicle cyber-physical system scenario; P is the attribute set, which is the data item used to describe the characteristics of the concept; R is a set of relations, which define how different concepts interact with each other; A represents a set of axioms, which are constraints imposed on concepts, attributes, and relations, and are used to express the logical structure of the domain; I represents a set of instances, which are the concrete implementations of concepts.

4. The method for generating multi-scale scenarios for intelligent vehicle cyber-physical systems based on domain ontology according to claim 1 is characterized by: Step S2 specifically includes the following steps: S21: Determine the professional field and scope, covering multi-scale test scenarios and related content, from macro road networks to local single intersections; S22: Construct an ontology concept terminology system, referencing existing standards and combining new elements of IVCPS to define concepts and attributes; S23: Build a conceptual classification system and divide the scenarios into seven levels: static traffic roads, road landscapes, temporary road modifications, dynamic objects, environmental conditions, digital information, and cloud control services; S24: Define concept relationships, including basic relationships between ontology concepts and specialized relationships extended for IVCPS scenarios; S25: Define axioms and rules to ensure the consistency and correctness of the scenario ontology; S26: Perform ontology instantiation and knowledge injection, and build scenario instances according to test requirements; S27: Ensure ontology quality through verification and iteration.

5. The method for generating multi-scale scenarios for intelligent vehicle cyber-physical systems based on domain ontology according to claim 4 is characterized in that: The concept classification system constructed in step S23 specifically includes: The static traffic road layer describes the static roads and fixed facilities that constitute the basic road network of the IVCPS physical space; The road landscape layer describes the static entities on both sides of the road that have relatively little impact on road traffic; The road temporary modification layer describes the temporary adjustment of the original traffic roads and road landscape layout; The dynamic object layer describes the traffic physical entities in the scene that have at least one parameter that changes over time; The environmental conditions layer describes the natural and man-made environmental factors that affect road traffic; The digital information layer describes the digital information collected and generated during the operation of IVCPS and the transmission and communication process; The cloud control service layer describes the collection, processing and distribution of traffic network information in large cities.

6. The method for generating multi-scale scenarios for intelligent vehicle cyber-physical systems based on domain ontology according to claim 4 is characterized in that: The conceptual relationships described in step S24 include relationships between concepts and relationships within concepts. Relationships are the specific applications of attributes and are expressed through the triple "subject-predicate-object" method. On the basis of retaining the basic relationships of ontological concepts, the IVCPS scenario relationships are expanded through IVCPS scenario domain-specific relationships and spatiotemporal refinement semantics.

7. The method for generating multi-scale scenes for an intelligent vehicle cyber-physical system based on domain ontology according to claim 6 is characterized in that: The conceptual relationships described in step S24 include: the relationship between the part and the whole, the relationship between the parent class and the child class, the relationship between the concept and the instance, the attributes of the concept or instance, the spatial rear relationship, the set contains members, the entity contains a part, the road section is associated with the construction area and obstacles, the vehicle is associated with a specific communication mode, a specific vehicle has the right of way, the connection between road elements, the spatial front relationship, the scene is associated with weather conditions, the road is associated with a specific type, the traffic light is associated with the current state, the traffic participant performs a specific driving action, the vehicle follows other vehicles, the scene is associated with the obstacle type, the condition or behavior triggers a specific event, the traffic participant or facility has the priority of way, the environment is associated with the visible range, and the entity belongs to a specific area.

8. The method for generating multi-scale scenarios for intelligent vehicle cyber-physical systems based on domain ontology according to claim 1 is characterized by: When constructing the signalized intersection IVCPS scenario ontology instance in step S3, a model including static traffic roads, road landscapes, temporary road modifications, dynamic objects, environmental conditions, digital information, and cloud control service layers is constructed according to the characteristics of the signalized intersection; The ontological concept attributes involved in static traffic roads include road type, shape parameters, number of lanes, pavement material, road marking type, location, type, speed limit range and scope of fixed traffic signs, as well as the location and status information of traffic lights, type and area of ​​special areas, and location and type of other additional structures; The ontological conceptual attributes of road landscape include building parameters, tree height and its covered area; location information, height and material type of safety protection facilities; location, road occupation and covered area of ​​public facilities; and type, height and location of other building structures. The ontological conceptual attributes of temporary road modifications include the type, location, and effective time of temporary construction signs; the color, type, and clarity of temporary construction road markings; the type, location, and lane occupation ratio of temporary obstacles; the location information, arrangement, color, and mobility of temporary traffic guidance facilities; and changes in the number of lanes, road shape, road surface condition, and slope caused by temporary modifications. The ontological conceptual attributes of dynamic objects include the lateral and longitudinal position, velocity, acceleration, size of the vehicle, its lane and behavior mode; the type, position, speed and steering angle of non-motor vehicles; the age, position and movement mode of pedestrians; the type and motion parameters of other movable objects; and the dynamic parameters within the duration of the scene. The ontological conceptual attributes of environmental conditions include weather type, duration event, climate intensity, definition of different time periods, visibility under atmospheric conditions, temperature, precipitation, as well as light type, light intensity, artificial light source position and the impact of weather on road conditions; The ontological conceptual attributes of digital information include V2X communication objects, communication protocols, message types, signal coverage, signal strength, priority, transmission rate, data size, and packet loss rate; information about traffic facilities controlled by the traffic management platform; the source, data type, and timestamp of perception information; and decision-making information provided by the computing unit. The ontological conceptual attributes of cloud services include the level, service scope, computing time, cache time, data interface protocol, service type and recommendation information of the edge cloud control system; the level, coverage, computing resources, optimization cycle, guidance suggestions and interface standards of the regional cloud control system; the level, data storage scale, preset model, response time and macro-control type of the central cloud control system.

9. The method for generating multi-scale scenes for an intelligent vehicle cyber-physical system based on domain ontology according to claim 8 is characterized in that: In step S3, test case design follows the "input-processing-output" closed-loop verification principle. By deconstructing the real traffic scenario, elements are extracted from the scenario model to generate test cases. The test case number, name, type, scenario description, pre-conditions, test steps, evaluation criteria and expected results are clearly defined.

Images