Intelligent connected vehicle full-scene cooperative test system and method

Abstract

The application relates to the technical field of automobile testing, in particular to an intelligent networked vehicle full-scene cooperative testing system and method, wherein the system comprises: a multi-source testing module for synchronously collecting three types of heterogeneous testing original data from simulation virtual dimensions, real vehicle running dimensions and bench controlled dimensions; a cloud cooperative hub for uniformly timing alignment and format standardization processing of the three types of heterogeneous testing original data, and based on the normalized data set, reverse supplement testing and two-dimensional verification of the function safety and information safety of a testing object; and an intelligent analysis module for automatically analyzing the normalized data set to generate a structured evaluation report of the corresponding testing object, and training a pre-constructed prediction model by using the normalized data set to provide risk prediction basis for the scene generation link. Therefore, the problems of process fragmentation, incomplete scene coverage, low automation degree and single safety verification in the existing automobile function testing are solved.

Description

Technical Field

[0001] This application relates to the field of automotive testing technology, and in particular to a collaborative testing system and method for intelligent connected vehicles that integrates simulation testing, real vehicle verification and cloud collaboration, applicable to the full lifecycle verification of core functions such as the three-electric system, intelligent driving, vehicle network and high voltage safety of new energy vehicles. Background Technology

[0002] With the automotive industry's deep transformation towards intelligence, connectivity, and electrification, and the widespread application of technologies such as 800V high-voltage platforms, central computing architectures, and advanced autonomous driving, the complexity of automotive functions is increasing exponentially, posing numerous bottlenecks to traditional testing methods. First, the testing process is fragmented, with data from various stages of MIL (Model-in-the-Loop), SIL (Software-in-the-Loop), HIL (Hardware-in-the-Loop), and real-vehicle testing being disconnected, lacking a closed-loop collaborative mechanism, resulting in lengthy testing cycles and high R&D costs. Second, test scenario coverage is incomplete, with extreme environments (-40℃ to 85℃ temperature cycles, high-altitude low-pressure environments) and edge cases (multi-instruction conflicts, network attacks) difficult to cover, leading to low fault detection rates. Third, testing automation is low, relying on manual configuration of the testing environment, data analysis, and report generation, with single testing cycles lasting several weeks and easily influenced by subjective factors, resulting in insufficient standardization. Fourth, for intelligent connected vehicles, issues such as long supply chains, incomplete libraries, and black-box testing make it difficult for existing testing methods to achieve accurate vulnerability localization without relying on prior knowledge bases.

[0003] While some existing technologies attempt to optimize testing processes through virtual simulation or automation tools, they still suffer from shortcomings such as insufficient collaboration, poor scenario adaptability, and limited safety verification. For example, some solutions focus only on a single testing stage, such as standalone HIL testing or real-vehicle road testing, failing to achieve end-to-end data integration; others lack integrated verification of functional safety (ISO 26262) and information security (UN R155 / R156), thus failing to meet the comprehensive safety requirements of intelligent connected vehicles.

[0004] Therefore, there is an urgent need to build a testing system and method that is collaborative across all scenarios, automated and closed-loop, and secure, to solve the above-mentioned technical problems. Summary of the Invention

[0005] This application provides a collaborative testing system and method for intelligent connected vehicles across all scenarios, in order to solve the technical problems of fragmented processes, incomplete scenario coverage, low automation, and single safety verification in existing vehicle functional testing, thereby improving testing efficiency, expanding scenario coverage, improving verification accuracy, and ensuring quality throughout the entire lifecycle.

[0006] The first aspect of this application provides a collaborative testing system for intelligent connected vehicles across all scenarios, including: The multi-source testing module is used to simultaneously collect three types of heterogeneous test raw data from simulation virtual dimension, actual vehicle operation dimension, and bench controlled dimension. The cloud-based collaborative hub communicates with the multi-source testing module to perform unified timing alignment and format standardization processing on the three types of heterogeneous test raw data to form a normalized dataset. Based on the normalized dataset, it dynamically generates extended test scenarios adapted to the current test requirements and sends them back to the multi-source testing module for supplementary testing. At the same time, it relies on the normalized dataset to perform dual-dimensional verification of the functional safety and information security of the test object. The intelligent analysis module interacts with the cloud-based collaborative hub to automatically parse the normalized dataset, generate a structured evaluation report for the corresponding test object, and train a pre-built prediction model using the normalized dataset to provide risk prediction basis for the scenario generation process of the cloud-based collaborative hub.

[0007] Optionally, the three types of heterogeneous test raw data include simulation operation raw data, actual vehicle operation data, and bench controlled test raw data.

[0008] Optionally, the multi-source testing module includes a simulation testing unit, a real vehicle testing unit, and a bench testing unit, wherein, The simulation test unit has a built-in extreme scenario library and supports MIL / SIL / HIL three-level simulation operation output corresponding simulation operation raw data; The actual vehicle test unit is equipped with a multi-sensor data acquisition terminal with a sampling frequency of ≥100Hz to collect actual vehicle operation data in real time; The bench test unit covers the three-electric system integrated debugging and high-voltage safety special test scenarios to support the acquisition of controlled test data for battery thermal runaway, motor overspeed, and electronic control fault injection, and obtain the raw data of the bench controlled test.

[0009] Optionally, the cloud-based collaborative hub includes a data synchronization unit, a scene generation unit, and a security verification unit, wherein... The data synchronization unit is used to perform global time synchronization correction and format normalization on the three types of heterogeneous raw data to obtain the normalized dataset. The scenario generation unit is used to identify the current test coverage blind spot based on the normalized dataset, and generate a supplementary test scenario with millions of concurrent connections based on the current test coverage blind spot, and send it to the multi-source test module. The security verification unit is used to invoke the mimicry threat injection technology based on the normalized dataset to perform vulnerability location and security verification under the dual standard framework of ISO26262 and UN R155 / R156.

[0010] Optionally, the intelligent analysis module is used to extract fault features from the normalized dataset and use the large language model to transform the extracted fault features into a structured evaluation report containing performance analysis items and optimization suggestions. At the same time, the fault diagnosis algorithm is iteratively trained using the full historical normalized dataset to predict potential fault prediction results and synchronously transmit them back to the scene generation unit of the cloud collaborative hub to provide input basis for the generation of high-risk targeted scenarios.

[0011] A second aspect of this application provides a method for full-scenario collaborative testing of intelligent connected vehicles, including the following steps: Match the corresponding test plan to the type of function to be tested, so as to determine the units to participate in the test and bind the corresponding quantitative acceptance indicators; Based on the test plan, an adaptation test scenario is generated, and the adaptation test scenario is decomposed into exclusive test instructions that can be directly identified and executed; The test is started synchronously with the exclusive test command as the unified trigger condition, the raw data of each dimension is collected, and the millisecond-level time alignment and format standardization of the full data are completed by relying on the global unified time signal to obtain a normalized dataset. Based on the normalized dataset, functional safety and information security are verified in two dimensions to calculate the measured indicators of the quantitative acceptance indicators and locate the fault points. A structured evaluation report is generated based on the measured indicators and the location of the fault points. The measured indicators are compared with the quantitative acceptance indicators. If there are any unmet items, the test parameters are automatically adjusted and the updated test requirements are sent back to the scenario deployment stage until all indicators meet the preset requirements.

[0012] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent connected vehicle full-scenario collaborative testing method as described in the above embodiments.

[0013] A fourth aspect of the present invention provides a computer program product, which, when executed by a processor, implements the above-described intelligent connected vehicle full-scenario collaborative testing method.

[0014] A fifth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described intelligent connected vehicle full-scenario collaborative testing method.

[0015] The intelligent connected vehicle full-scenario collaborative testing system and method proposed in this invention achieves million-level concurrent testing through multi-source testing collaboration and automated closed-loop mechanisms, compressing the single evaluation cycle from weeks to hours, significantly improving testing efficiency and reducing labor costs. It integrates the advantages of simulation, bench, and real-vehicle testing, covering various scenarios such as extreme environments, edge cases, and network attacks, significantly improving fault detection rates. It spans the entire process from design, R&D, mass production, to OTA, supporting continuous iteration of test data and model optimization, providing dynamic assurance for vehicle quality throughout its entire lifecycle. It is the first to achieve collaborative verification of functional safety and information security, meeting both ISO 26262 and UN R155 / R156 standards, adapting to the comprehensive safety requirements of intelligent connected vehicles. It automatically generates standardized reports through large language models, avoiding human subjective errors and significantly improving report consistency. Simultaneously, AI prediction models can predict potential risks in advance, reducing mass production failure rates.

[0016] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0017] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a block diagram of a collaborative testing system for intelligent connected vehicles in all scenarios according to an embodiment of this application; Figure 2 This is a flowchart of a collaborative testing method for intelligent connected vehicles across all scenarios, provided according to an embodiment of this application. Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application.

[0018] Explanation of reference numerals in the attached figures: 10-Intelligent Connected Vehicle Full-Scenario Collaborative Testing System, 101-Multi-Source Testing Module, 102-Cloud Collaborative Hub, 103-Intelligent Analysis Module, 301-Memory, 302-Processor, 303-Communication Interface. Detailed Implementation

[0019] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0020] The following description, with reference to the accompanying drawings, describes an intelligent connected vehicle full-scenario collaborative testing system and method according to embodiments of this application.

[0021] Figure 1 This is a block diagram of a collaborative testing system for intelligent connected vehicles in all scenarios provided according to an embodiment of this application.

[0022] like Figure 1 As shown, the intelligent connected vehicle full-scenario collaborative testing system 10 includes: a multi-source testing module 101, a cloud collaborative hub 102, and an intelligent analysis module 103.

[0023] The multi-source testing module 101 is used to simultaneously collect three types of heterogeneous test raw data from simulation virtual dimensions, actual vehicle operation dimensions, and bench controlled dimensions. The cloud-based collaborative hub 102 communicates with the multi-source testing module and performs unified timing alignment and format standardization processing on the three types of heterogeneous test raw data to form a normalized dataset. Based on the normalized dataset, it dynamically generates extended test scenarios adapted to current test requirements and sends them back to the multi-source testing module for supplementary testing. Simultaneously, it uses the normalized dataset to perform dual-dimensional verification of the functional safety and information security of the test objects. The intelligent analysis module 103 interacts with the cloud-based collaborative hub to automatically parse the normalized dataset to generate structured evaluation reports for the corresponding test objects. It also uses the normalized dataset to train a pre-built prediction model, providing risk prediction basis for the scenario generation stage of the cloud-based collaborative hub. The multi-source testing module 101, the cloud-based collaborative hub 102, and the intelligent analysis module 103 establish a closed-loop mechanism of "test-analysis-optimization-retest". The optimization suggestions output by the intelligent analysis module 103 are automatically converted into test parameter adjustment instructions and fed back to the multi-source testing module 101 to achieve adaptive iteration of the testing process.

[0024] In some embodiments, the three types of heterogeneous test raw data include simulation run raw data, actual vehicle run data, and bench controlled test raw data.

[0025] In some embodiments, the multi-source testing module includes a simulation testing unit, a real vehicle testing unit, and a bench testing unit, wherein... The simulation test unit has a built-in extreme scenario library and supports MIL / SIL / HIL level three simulation runs, outputting corresponding original simulation run data; The real vehicle test unit is equipped with a multi-sensor data acquisition terminal with a sampling frequency of ≥100Hz to collect real vehicle operation data in real time; The bench test unit covers the three-electric system integration and high-voltage safety special test scenarios to support the acquisition of controlled test data for battery thermal runaway, motor overspeed, and electronic control fault injection, and obtain the raw test data of the bench.

[0026] In actual implementation, the multi-source testing module includes a simulation testing unit, a real vehicle testing unit, and a bench testing unit. The simulation testing unit has a built-in library of 300+ extreme scenarios (including weak network, high concurrency, network attack, temperature cycling, etc.) and supports MIL / SIL / HIL level three simulation. The real vehicle testing unit is equipped with a multi-sensor data acquisition terminal (sampling frequency ≥100Hz) to collect real-time measured data on vehicle power performance, economy, ADAS functions, etc. The bench testing unit includes a three-electric system integrated debugging bench and a high-voltage safety testing bench, supporting specialized tests such as battery thermal runaway, motor overspeed, and electronic control fault injection to collect raw data from controlled bench tests.

[0027] In some embodiments, the cloud-based collaborative hub includes a data synchronization unit, a scene generation unit, and a security verification unit, wherein... The data synchronization unit is used to perform global time synchronization correction and format normalization on three types of heterogeneous raw data to obtain a normalized dataset; The scenario generation unit is used to identify the current test coverage blind spot based on the normalized dataset, and generate supplementary test scenarios with millions of concurrent requests based on the current test coverage blind spot, and distribute them to the multi-source test module. The security verification unit is used to invoke mimicry threat injection technology based on a normalized dataset to perform vulnerability location and security verification under the dual standard framework of ISO 26262 and UN R155 / R156.

[0028] In actual execution, the cloud-based collaborative hub includes a data synchronization unit, a scenario generation unit, and a security verification unit. The data synchronization unit uses global time synchronization correction and information caching pool technology to perform time alignment (error ≤ 1ms) and format standardization on three types of heterogeneous raw data, constructing a unified data platform, and synchronously pushing the normalized dataset to the scenario generation unit and the security verification unit. The scenario generation unit, based on a pre-built reinforcement learning algorithm, identifies the current test coverage blind spots according to the normalized dataset and dynamically generates adaptive test scenarios (i.e., supplementary test scenarios) to support the concurrent output of millions of instructions. The security verification unit integrates functional safety (ISO 26262) and information security (UN R155 / R156) dual verification frameworks, and uses the normalized dataset to call the mimicry threat injection technology to achieve vulnerability perception and location.

[0029] In some embodiments, the intelligent analysis module is equipped with a large language model and a fault diagnosis algorithm.

[0030] In some embodiments, the intelligent analysis module is used to extract fault features from the normalized dataset and use a large language model to transform the extracted fault features into a structured evaluation report containing performance analysis items and optimization suggestions. At the same time, the fault diagnosis algorithm is iteratively trained using the full historical normalized dataset to predict potential fault prediction results and synchronously transmit them back to the scene generation unit of the cloud collaborative hub to provide input basis for the generation of high-risk targeted scenarios.

[0031] In actual execution, the intelligent analysis module is equipped with a large language model and a fault diagnosis algorithm. It extracts fault features from the normalized dataset and uses the large language model to transform the extracted fault features into a structured evaluation report containing performance analysis and optimization suggestions. At the same time, it trains the fault diagnosis algorithm based on historical data to predict protocol compatibility and potential fault risks, obtains potential fault prediction results, and synchronously sends them back to the scenario generation unit in the cloud collaboration center to provide input basis for the generation of high-risk targeted scenarios.

[0032] The following is a detailed description of the intelligent connected vehicle full-scenario collaborative testing system proposed in this application through a specific embodiment.

[0033] I. System Hardware Configuration The simulation test unit in the multi-source test module uses a multi-core processor and is equipped with Prescan / Simulink simulation software, supporting full-scale virtual user concurrent simulation and full-scene rendering frame rate; the real vehicle test unit is equipped with LiDAR, millimeter-wave radar, high-definition camera and high-voltage data acquisition instrument, with a sampling frequency of 100Hz and extremely low data transmission latency; the bench test unit includes an 800V high-voltage integrated bench, a three-electric system debugging bench and an environmental chamber, supporting temperature adjustment from -40℃ to 85℃, motor speed simulation from 0 to 20000rpm and battery thermal runaway trigger testing.

[0034] Cloud-based collaborative hub: It adopts a distributed server cluster, supports PB-level data storage and millisecond-level data processing, global time synchronization accuracy ≤1ms, and information cache pool capacity ≥2TB.

[0035] Intelligent Analysis Module: Equipped with a customized large language model, optimized based on the Transformer architecture, with an inference speed of ≥100 tokens / s, and the fault diagnosis algorithm adopts a fusion solution of deep learning and rule engine.

[0036] II. Implementation of the Testing Process Taking the testing of autonomous driving functions in intelligent connected vehicles as an example, the specific implementation steps are as follows: Step 1, Test Initialization: Determine that the function to be tested is Level 3 autonomous driving (including adaptive cruise control, lane keeping, and emergency braking), configure the test indicators: perception accuracy ≥ 95%, decision delay ≤ 100ms, emergency braking response time ≤ 500ms, and enable the simulation test unit, the real vehicle test unit, and the bench test unit. Step 2, Scene Generation and Deployment: The scene generation unit calls the city scene library (including basic scenes such as intersection congestion, pedestrian crossing, and traffic light failure) to dynamically generate a composite scene of "weak network environment + multiple vehicle intersections + sudden obstacles", and issues test instructions to each test unit through a multi-threaded concurrency mechanism. Step 3, Multi-source data acquisition: The simulation test unit outputs virtual sensor data and vehicle trajectory; the real vehicle test unit reproduces the above composite scenario in a closed environment, and collects radar, camera measured data and vehicle control signals; the bench test unit simulates ECU faults through HIL simulation and collects electronic control system response data; after all data is time-aligned by the data synchronization unit, it is stored in the cloud data platform. Step 4, Security and Performance Verification: The security verification unit injects network attack commands (such as DDoS simulation) to verify the anti-interference capability of the autonomous driving system; the intelligent analysis module compares simulation and real vehicle data and calculates that the perception accuracy rate is 96.3%, the decision delay is 85ms, and the emergency braking response time is 420ms, all of which meet the test indicators. At the same time, it locates the minor fault of "traffic light recognition delay in weak network environment". Step 5, Report Generation and Closed-Loop Optimization: The large language model generates an evaluation report containing performance analysis, fault details, and optimization suggestions within 3 minutes; the closed-loop control module automatically adjusts the network signal strength parameters of the simulation test unit, returns to Step 2 for retesting, and after optimization, the fault is eliminated, and the test process ends.

[0037] In summary, the intelligent connected vehicle full-scenario collaborative testing system proposed according to the embodiments of this application has the following beneficial effects: (1) Significantly improved testing efficiency: Through multi-source testing collaboration and automated closed-loop mechanism, millions of instructions are tested concurrently, reducing the single evaluation cycle from several weeks to hours, greatly improving testing efficiency and significantly reducing labor costs.

[0038] (2) Comprehensive and accurate scenario coverage: It integrates the advantages of simulation, bench and real vehicle testing, covering a variety of scenarios such as extreme environment, edge cases, network attacks, etc., and significantly improves the fault detection rate.

[0039] (3) Full life cycle guarantee: It runs through the entire process of design, R&D, mass production and OTA, supports continuous iteration of test data and model optimization, and provides dynamic guarantee for the quality of vehicles throughout the entire life cycle.

[0040] (4) Integrated verification system: For the first time, functional safety and information security are verified in a coordinated manner, meeting both ISO 26262 and UN R155 / R156 standards, and adapting to the comprehensive safety requirements of intelligent connected vehicles.

[0041] (5) Integration of standardization and intelligence: Standardized reports are automatically generated through large language models to avoid human subjective errors and significantly improve report consistency. At the same time, AI prediction models can predict potential risks in advance and reduce mass production failure rate.

[0042] Next, referring to the accompanying drawings, the method for collaborative testing of intelligent connected vehicles in all scenarios proposed in this application is described.

[0043] Figure 2 This is a flowchart of a collaborative testing method for intelligent connected vehicles across all scenarios, provided according to an embodiment of this application.

[0044] like Figure 2 As shown, the intelligent connected vehicle full-scenario collaborative testing method includes the following steps: In step S201, a corresponding test plan is matched for the type of function to be tested, so as to determine the unit participating in the test and bind the corresponding quantitative acceptance indicators.

[0045] In actual implementation, test plans are configured according to the type of function to be tested (electric system / intelligent driving / vehicle network, etc.) to determine the participating units and test indicators of multi-source test modules (such as battery SOC estimation error ≤2%, motor high-efficiency zone coverage ≥85%, ADAS perception accuracy ≥95%).

[0046] In step S202, an adaptation test scenario is generated according to the test plan, and the adaptation test scenario is decomposed into exclusive test instructions that can be directly identified and executed.

[0047] In actual execution, based on the test plan, basic scenarios are called from the scenario library or custom scenarios are dynamically generated. The adaptability test scenarios are decomposed into exclusive test instructions that can be directly identified and executed. The exclusive test instructions are deployed to the corresponding test units through a multi-threaded concurrency mechanism.

[0048] In step S203, the test is started synchronously with the exclusive test command as the unified trigger condition, the original data of each dimension is collected, and the millisecond-level time alignment and format standardization of the full data are completed by relying on the global unified timing signal to obtain the normalized dataset.

[0049] In actual execution, test tasks are executed synchronously with dedicated test instructions as the unified trigger condition, collecting simulation data, real vehicle operation data and bench test data, and relying on the globally unified timing signal to complete the millisecond-level time alignment and format standardization of all data to obtain a normalized dataset, which is then stored in the data platform.

[0050] In step S204, functional safety and information security are verified in two dimensions based on the normalized dataset to calculate the measured indicators of the quantitative acceptance indicators and locate the fault points.

[0051] In actual implementation, functional safety and information security integrated verification is carried out by injecting faults into the normalized dataset and simulating threats, so as to calculate the degree of achievement of the test indicators of the quantitative acceptance indicators (i.e., the measured indicators) and locate the fault points.

[0052] In step S205, a structured evaluation report is generated based on the measured indicators and the location of the fault. The measured indicators are compared with the quantitative acceptance indicators. If there are any unmet items, the test parameters are automatically adjusted and the updated test requirements are sent back to the scenario deployment stage until all indicators meet the preset requirements.

[0053] In actual execution, based on the large language model, a standardized evaluation report is automatically generated according to the measured indicators and the location of the fault (generation time ≤ 5 minutes); if the test indicators do not meet the standards, the closed-loop control module automatically adjusts the test parameters and returns to step S202 to re-execute the test until the preset requirements are met.

[0054] It should be noted that the foregoing explanation of the embodiment of the intelligent connected vehicle full-scenario collaborative testing system also applies to the intelligent connected vehicle full-scenario collaborative testing method of this embodiment, and will not be repeated here.

[0055] The intelligent connected vehicle full-scenario collaborative testing method proposed in the embodiments of this application has the following beneficial effects: (1) Significantly improved testing efficiency: Through multi-source testing collaboration and automated closed-loop mechanism, millions of instructions are tested concurrently, reducing the single evaluation cycle from several weeks to hours, greatly improving testing efficiency and significantly reducing labor costs.

[0056] (2) Comprehensive and accurate scenario coverage: It integrates the advantages of simulation, bench and real vehicle testing, covering a variety of scenarios such as extreme environment, edge cases, network attacks, etc., and significantly improves the fault detection rate.

[0057] (3) Full life cycle guarantee: It runs through the entire process of design, R&D, mass production and OTA, supports continuous iteration of test data and model optimization, and provides dynamic guarantee for the quality of vehicles throughout the entire life cycle.

[0058] (4) Integrated verification system: For the first time, functional safety and information security are verified in a coordinated manner, meeting both ISO 26262 and UN R155 / R156 standards, and adapting to the comprehensive safety requirements of intelligent connected vehicles.

[0059] (5) Integration of standardization and intelligence: Standardized reports are automatically generated through large language models to avoid human subjective errors and significantly improve report consistency. At the same time, AI prediction models can predict potential risks in advance and reduce mass production failure rate.

[0060] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application.

[0061] The electronic device may include: a memory 301, a processor 302, and a computer program stored in the memory 301 and executable on the processor 302. When the processor 302 executes the program, it implements the intelligent connected vehicle full-scenario collaborative testing method provided in the above embodiments.

[0062] Furthermore, electronic devices also include: Communication interface 303 is used for communication between memory 301 and processor 302.

[0063] The memory 301 is used to store computer programs that can run on the processor 302.

[0064] The memory 301 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0065] If the memory 301, processor 302, and communication interface 303 are implemented independently, then the communication interface 303, memory 301, and processor 302 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0066] Optionally, in a specific implementation, if the memory 301, processor 302, and communication interface 303 are integrated on a single chip, then the memory 301, processor 302, and communication interface 303 can communicate with each other through an internal interface.

[0067] Processor 302 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0068] This application also provides a computer program product, which, when executed by a processor, implements the above-described intelligent connected vehicle full-scenario collaborative testing method.

[0069] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described intelligent connected vehicle full-scenario collaborative testing method.

[0070] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0071] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0072] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0073] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0074] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0075] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0076] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0077] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A collaborative testing system for intelligent connected vehicles across all scenarios, characterized in that, include: The multi-source testing module is used to simultaneously collect three types of heterogeneous test raw data from simulation virtual dimension, actual vehicle operation dimension, and bench controlled dimension. The cloud-based collaborative hub communicates with the multi-source testing module to perform unified timing alignment and format standardization processing on the three types of heterogeneous test raw data to form a normalized dataset. Based on the normalized dataset, it dynamically generates extended test scenarios adapted to the current test requirements and sends them back to the multi-source testing module for supplementary testing. At the same time, it relies on the normalized dataset to perform dual-dimensional verification of the functional safety and information security of the test object. The intelligent analysis module interacts with the cloud-based collaborative hub to automatically parse the normalized dataset, generate a structured evaluation report for the corresponding test object, and train a pre-built prediction model using the normalized dataset to provide risk prediction basis for the scenario generation process of the cloud-based collaborative hub.

2. The intelligent connected vehicle full-scenario collaborative testing system according to claim 1, characterized in that, The three types of heterogeneous test raw data include simulation operation raw data, actual vehicle operation data, and bench controlled test raw data.

3. The intelligent connected vehicle full-scenario collaborative testing system according to claim 1, characterized in that, The multi-source testing module includes a simulation testing unit, a real vehicle testing unit, and a bench testing unit, wherein... The simulation test unit has a built-in extreme scenario library and supports MIL / SIL / HIL three-level simulation operation output corresponding simulation operation raw data; The actual vehicle test unit is equipped with a multi-sensor data acquisition terminal with a sampling frequency of ≥100Hz to collect actual vehicle operation data in real time; The bench test unit covers the three-electric system integrated debugging and high-voltage safety special test scenarios to support the acquisition of controlled test data for battery thermal runaway, motor overspeed, and electronic control fault injection, and obtain the raw data of the bench controlled test.

4. The intelligent connected vehicle full-scenario collaborative testing system according to claim 1, characterized in that, The cloud-based collaborative hub includes a data synchronization unit, a scene generation unit, and a security verification unit. The data synchronization unit is used to perform global time synchronization correction and format normalization on the three types of heterogeneous raw data to obtain the normalized dataset. The scenario generation unit is used to identify the current test coverage blind spot based on the normalized dataset, and generate a supplementary test scenario with millions of concurrent connections based on the current test coverage blind spot, and send it to the multi-source test module. The security verification unit is used to invoke the mimicry threat injection technology based on the normalized dataset to perform vulnerability location and security verification under the dual standard framework of ISO26262 and UN R155 / R156.

5. The intelligent connected vehicle full-scenario collaborative testing system according to claim 1, characterized in that, The intelligent analysis module is equipped with a large language model and fault diagnosis algorithm.

6. The intelligent connected vehicle full-scenario collaborative testing system according to claim 5, characterized in that, The intelligent analysis module is used to extract fault features from the normalized dataset and use the large language model to transform the extracted fault features into a structured evaluation report containing performance analysis items and optimization suggestions. At the same time, the fault diagnosis algorithm is iteratively trained using the full historical normalized dataset to predict potential fault prediction results. The results are synchronously sent back to the scene generation unit of the cloud collaborative hub to provide input basis for the generation of high-risk targeted scenarios.

7. A method for full-scenario collaborative testing of intelligent connected vehicles, characterized in that, The intelligent connected vehicle full-scenario collaborative testing system according to any one of claims 1-6 includes the following steps: Match the corresponding test plan to the type of function to be tested, so as to determine the units to participate in the test and bind the corresponding quantitative acceptance indicators; Based on the test plan, an adaptation test scenario is generated, and the adaptation test scenario is decomposed into exclusive test instructions that can be directly identified and executed; The test is started synchronously with the exclusive test command as the unified trigger condition, the raw data of each dimension is collected, and the millisecond-level time alignment and format standardization of the full data are completed by relying on the global unified time signal to obtain a normalized dataset. Based on the normalized dataset, functional safety and information security are verified in two dimensions to calculate the measured indicators of the quantitative acceptance indicators and locate the fault points. A structured evaluation report is generated based on the measured indicators and the location of the fault points. The measured indicators are compared with the quantitative acceptance indicators. If there are any unmet items, the test parameters are automatically adjusted and the updated test requirements are sent back to the scenario deployment stage until all indicators meet the preset requirements.

8. An electronic device, characterized in that, include: The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent connected vehicle full-scenario collaborative testing method as described in claim 7.

9. A computer program product, characterized in that, When the computer program / instruction is executed by the processor, it implements the intelligent connected vehicle full-scenario collaborative testing method as described in claim 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the intelligent connected vehicle full-scenario collaborative testing method as described in claim 7.

Images