Vehicle scene automatic test method, device and equipment and storage medium

Abstract

The invention discloses a vehicle scene automatic test method, device and equipment and a storage medium, and the method comprises the steps: automatically generating a test case corresponding to a test scene based on a plurality of test scenes defined by an SOA scene master, simulating the test scene, and obtaining an execution truth value signal and an expected execution effect image; controlling the vehicle to execute a corresponding action based on the test case, and obtaining an execution effect image; and comparing the executed action signal with the execution truth value signal, comparing the execution effect image with the expected execution effect image to judge whether the execution action is consistent with the execution effect or not, and outputting a test result. The test period can be shortened, the test efficiency can be improved, and the pertinence and the accuracy of the test result can be ensured.

Description

Technical Field

[0001] This invention relates to the field of vehicle scenario testing technology, and in particular to an automatic vehicle scenario testing method, apparatus, equipment, and storage medium. Background Technology

[0002] Automotive SOA Scene Master is a highly practical feature that allows users to customize their driving experience based on their needs and preferences. By setting appropriate trigger conditions and actions, users can easily achieve various convenient operations and intelligent controls. Features: Customizable Scenes: Users can set up various usage scenarios according to their needs and preferences, such as commuting to work, outdoor entertainment, and nighttime driving. Diverse Trigger Conditions: Trigger conditions can include various factors such as owner account status, time, navigation status, driving mode, window and door status, seatbelt buckle status, and driver fatigue status. Rich Actions: Actions cover multiple aspects including windows, doors, air conditioning, seats, ambient lighting, sound system, navigation, and multimedia, encompassing almost all controllable devices inside the vehicle. Application Scenario Examples: Commute to Work Scene: Set up automatic navigation to the office, music playback, seat and ambient lighting adjustments after buckling up on weekday mornings, making the start of the workday more relaxed and enjoyable for the driver. Outdoor Entertainment Scene: Play music through the vehicle's external speakers or connect to a Bluetooth-connected mobile phone to play music, enhancing the enjoyment of outdoor activities. Safe driving scenario: Set up driver fatigue monitoring. When driver fatigue is detected, automatically issue a reminder or take other safety measures.

[0003] Current testing methods require building numerous test scenarios and testing them one by one, resulting in low testing efficiency. They also require significant investment of human, material, and financial resources and pose substantial security risks.

[0004] Therefore, how to shorten the testing cycle and improve testing efficiency is a technical problem that urgently needs to be solved. Summary of the Invention

[0005] The main objective of this invention is to provide an automatic testing method, apparatus, equipment, and storage medium for vehicle scenarios, which can shorten the testing cycle, improve testing efficiency, and ensure the relevance and accuracy of the test results.

[0006] Firstly, this application provides an automatic testing method for vehicle scenarios, wherein the method includes the following steps: Based on multiple test scenarios defined by SOA Scenario Master, test cases corresponding to the test scenarios are automatically generated, and the test scenarios are simulated to obtain execution truth signals and expected execution effect images; Based on the test cases, control the vehicle to perform corresponding actions and obtain images of the execution results; The executed action signal is compared with the execution truth signal, and the execution effect image is compared with the expected execution effect image to determine whether the executed action and execution effect are consistent, and the test result is output.

[0007] In conjunction with the first aspect mentioned above, as an optional implementation, the action signal to be executed is transmitted to the SOA Scene Master using a communication device, and the difference D between the action signal and the execution truth signal is calculated using the one-dimensional convolutional Siamese network model in the SOA Scene Master. The difference D is compared with the set threshold to determine whether the actions performed by the two are consistent.

[0008] In conjunction with the first aspect mentioned above, as an optional implementation method, according to the formula: Calculate the difference between the executed action signal and the execution truth signal, wherein, , These represent the collected action signal and the scene ground truth signal, respectively. The F-dimensional feature represents the signal type, Y is the label indicating whether the two match, and th is the distance threshold.

[0009] In conjunction with the first aspect mentioned above, as an optional implementation method, an execution effect image is acquired through an acquisition device, and features are extracted from the execution effect image using the Gray-Level Co-occurrence Matrix (GLCM) and Local Binary Pattern (LBP). The extracted features are compared with the expected execution effect image to determine the similarity between the execution effect image and the expected execution effect image; Based on the similarity, determine whether the execution results are consistent.

[0010] In conjunction with the first aspect mentioned above, as an optional implementation method, the output test results are analyzed to evaluate the performance of SOA Scenario Master in different scenarios; This includes: calculating the time interval between receiving the trigger condition and executing the corresponding action in the SOA Scenario Master, and evaluating the response speed of the SOA Scenario Master; Compare the actual execution time with the expected execution time to evaluate the execution efficiency of SOA Scenario Master; Compare the output of SOA Scenario Master with the expected results to evaluate the accuracy of SOA Scenario Master.

[0011] In conjunction with the first aspect mentioned above, as an optional implementation method, multiple test scenarios are written using SOA Scenario Master, including: daily commuting, long-distance travel, night driving, severe weather, and emergency avoidance. The SOA Scenario Master automatically matches the test cases corresponding to the input test scenario.

[0012] In conjunction with the first aspect mentioned above, as an optional implementation method, SOA Scene Master is used to simulate test scene trigger signals, and corresponding actions are executed through the trigger signals to obtain the execution action truth signal and execution effect image. The trigger signals include: seat belt, navigation, environment, driving, doors and windows, camera, time, and account. The execution truth signals include: interior lights, vehicle body, exterior lights, navigation, multimedia, air conditioning, Bluetooth, doors and windows, screen display, camera, sound, network, fragrance, and seats.

[0013] Secondly, this application provides an automatic vehicle scenario testing device, which includes: The processing module is used to automatically generate test cases corresponding to multiple test scenarios defined by SOA Scenario Master, and simulate the test scenarios to obtain execution truth signals and expected execution effect images. An execution module is used to control the vehicle to perform corresponding actions based on the test cases and to obtain images of the execution results. The output module is used to compare the executed action signal with the execution truth signal, and to compare the execution effect image with the expected execution effect image, so as to determine whether the executed action and execution effect are consistent, and output the test result.

[0014] Thirdly, this application also provides an electronic device, the electronic device comprising: a processor; and a memory storing computer-readable instructions, which, when executed by the processor, implement the method described in any one of the first aspects.

[0015] Fourthly, this application also provides a computer-readable storage medium storing computer program instructions that, when executed by a computer, cause the computer to perform the method described in any of the first aspects.

[0016] This application provides an automatic testing method, apparatus, device, and storage medium for vehicle scenarios. The method includes the following steps: automatically generating test cases corresponding to multiple test scenarios defined by an SOA scenario master, simulating the test scenarios to obtain execution truth signals and expected execution effect images; controlling the vehicle to perform corresponding actions based on the test cases, and acquiring the execution effect images; comparing the executed action signals with the execution truth signals, and comparing the execution effect images with the expected execution effect images to determine whether the executed actions and execution effects are consistent, and outputting the test results. This application can shorten the testing cycle, improve testing efficiency, and ensure the relevance and accuracy of the test results.

[0017] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit the invention. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0019] Figure 1 This is a flowchart of an automatic vehicle scenario testing method provided in the embodiments of this application; Figure 2 This is a schematic diagram of an automatic vehicle scenario testing device provided in the embodiments of this application; Figure 3 This is a schematic diagram of the automatic testing provided in the embodiments of this application; Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of this application; Figure 5 This is a schematic diagram of a computer-readable program medium provided in an embodiment of this application. Detailed Implementation

[0020] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0021] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. Some of the block diagrams shown in the drawings represent functional entities and do not necessarily correspond to physically or logically independent entities.

[0022] The embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0023] Reference Figure 1 , Figure 1 The diagram shown is a flowchart of an automatic vehicle scenario testing method provided by the present invention. Figure 1 As shown, the method includes the following steps: Step S101: Based on multiple test scenarios defined by SOA Scenario Master, automatically generate test cases corresponding to the test scenarios, simulate the test scenarios, and obtain execution truth signals and expected execution effect images.

[0024] Specifically, multiple test scenarios were written using SOA Scenario Master, including: daily commute, long-distance travel, night driving, severe weather, and emergency avoidance; The SOA Scenario Master automatically matches the test cases corresponding to the input test scenario.

[0025] SOA Scene Master is used to simulate and test scene trigger signals, and corresponding actions are executed through the trigger signals to obtain the execution action truth signal and execution effect image. The trigger signals include: seat belt, navigation, environment, driving, doors and windows, camera, time, and account. The execution truth signals include: interior lights, body, exterior lights, navigation, multimedia, air conditioning, Bluetooth, doors and windows, screen display, camera, sound, network, fragrance, and seats.

[0026] To make it easier to understand, let's define test scenarios: Based on product characteristics and user needs, define a series of test scenarios, including daily commuting, long-distance travel, night driving, severe weather, emergency avoidance, etc. Generate a scenario library based on SOA trigger conditions and execution actions. The scenario library should cover all scenarios of users' daily car use.

[0027] Based on the test scenarios and functions, generate detailed test cases, including test steps, expected results, and evaluation criteria. Ensure that the test cases cover all key functions and scenarios to comprehensively evaluate the performance and stability of the scenario master. Test content includes ensuring that the scenario master can automatically and accurately adjust vehicle settings according to preset conditions, such as seat heating, air conditioning temperature, and music playback; evaluating the scenario master's response speed, execution efficiency, and other performance indicators under different scenarios; and verifying the stability and reliability of the scenario master under long-term, high-load operation. Generate a scenario test case library based on scenario functions, which can be called upon promptly according to subsequent test scenarios.

[0028] Test script writing: Automated test scripts are written using high-level programming languages ​​such as Python. These scripts utilize Python's standard libraries (os, sys, re) to handle file paths, invoke external commands, and perform text processing. Scripts are written to automatically set various parameters of the scenario master based on test cases and capture vehicle responses. Select appropriate automated testing tools, such as Selenium, Appium, or a customized testing framework, to execute test scripts and manage test results. Combine driving simulators and real vehicles to build a closed-loop testing environment to ensure the comprehensiveness and accuracy of the tests.

[0029] It should be noted that the SOA Scenario Master's real-vehicle functionality is divided into 8 categories and 47 trigger conditions, and 17 categories and 74 execution actions. A maximum of 10 triggers and actions can be selected. The main development work involves connecting the interface services involved in the DIY logic function library of the vehicle infotainment system with the interface services of the driving simulator. The development of host computer software allows for editing, distributing, and saving execution results of test cases, and can also distribute test cases to the vehicle infotainment system. The vehicle infotainment system creates library files, and finally, the execution of the library files is verified on the driving simulator, with the execution results fed back to both the vehicle infotainment system and the host computer.

[0030] SOA Scenario Master Function Verification Interface Development Requirements: The SOA Scenario Master's real-vehicle functionality is divided into 8 categories and 47 trigger conditions, and 17 categories and 74 execution actions. A maximum of 10 triggers and 10 actions can be selected. Specific selections include Table 1: Cockpit Logic Interaction Function - Trigger Condition Selection and Table 2: Cockpit Logic Interaction Function - Execution Action Selection. Table 1

[0031] Table 2

[0032] Based on product characteristics and user needs, a series of test scenarios were designed, including daily commuting, long-distance travel, nighttime driving, severe weather, and emergency avoidance. The automated testing software generates test cases based on the input test scenarios, including test steps, expected results, and evaluation criteria. The test cases must cover all key functions and scenarios to comprehensively evaluate the performance and stability of the scenario master. Test content includes ensuring that the scenario master can automatically and accurately adjust vehicle settings according to preset conditions, such as seat heating, air conditioning temperature, and music playback; evaluating the scenario master's response speed, execution efficiency, and other performance indicators under different scenarios; and verifying the stability and reliability of the scenario master under long-term, high-load operation.

[0033] The development of SOA-based automated testing software involves testing scenarios. This software can simulate scenario trigger signals (such as seatbelts, navigation, environment, driving, doors and windows, cameras, time, accounts, etc.) and automatically obtain execution information truth signals (such as interior lights, body lights, exterior lights, navigation, multimedia, air conditioning, Bluetooth, doors and windows, screen display, cameras, sound, network, fragrance, seats, etc.) and execution effect images. The trigger signals are then sent to the actual vehicle / test bench platform. Upon receiving the signals, the SOA scenario master is automatically executed, performing vehicle-mounted actions according to the scenario. Image acquisition devices such as cameras are used to capture and collect various settings within the cabin in real time. The collected execution action signals are compared with the truth signals to determine correctness. Using image recognition technology, the testing system analyzes and processes the collected images, comparing the identified content with preset execution effect images to determine the correctness of the automated testing software strategy.

[0034] Step S102: Control the vehicle to perform corresponding actions based on the test cases, and obtain the execution effect image.

[0035] Specifically, test cases are automatically generated by automated testing software. The status and condition signals related to the test cases are transmitted to the real vehicle testing platform via communication equipment. The real vehicle performs corresponding actions based on the status and condition signals, and the execution images of the vehicle are captured by image recognition equipment such as cameras. The action signals are then transmitted back to the automated testing software via communication equipment. The software platform determines whether the action signals are correct, performs image recognition and comparison between the captured images and the preset execution effect images, and outputs the test results, further improving the reliability of the testing process and development efficiency.

[0036] Step S103: Compare the executed action signal with the execution truth signal, and compare the execution effect image with the expected execution effect image to determine whether the executed action and execution effect are consistent, and output the test result.

[0037] Specifically, the action signal to be executed is transmitted to the SOA Scene Master using a communication device, and the difference D between the action signal and the execution truth signal is calculated using the one-dimensional convolutional Siamese network model in the SOA Scene Master. The difference D is compared with the set threshold to determine whether the actions performed by the two are consistent.

[0038] According to the formula: Calculate the difference between the executed action signal and the execution truth signal, wherein, , These represent the collected action signal and the scene ground truth signal, respectively. The F-dimensional feature represents the signal type, Y is the label indicating whether the two match, and th is the distance threshold.

[0039] For ease of understanding, let's illustrate with an example. Trigger information N, N1-N8 represent seat belt, navigation, environment, driving, doors and windows, camera, time, and account, respectively.

[0040] Execute truth signal ; Execute action signal For SOA scenario signals, the main focus is on the model matching consistency between the acquired execution action signals and the ground truth signals. The algorithm uses a Siamese network model based on one-dimensional convolution to analyze the consistency between the two and calculate their difference:

[0041] The execution effect image is acquired by the acquisition device, and features are extracted from the execution effect image using the Gray-Level Co-occurrence Matrix (GLCM) and Local Binary Pattern (LBP). The extracted features are compared with the expected execution effect image to determine the similarity between the execution effect image and the expected execution effect image; Based on the similarity, determine whether the execution results are consistent.

[0042] Specifically, various settings within the cockpit are captured and collected in real time using image acquisition devices such as cameras. First, features are extracted from the images using methods such as Gray-Level Co-occurrence Matrix (GLCM) and Local Binary Pattern (LBP). Then, the extracted features are compared with known execution effect images. Deep learning algorithms such as Convolutional Neural Networks (CNN) and Residual Networks (ResNet) are used to extract hierarchical feature representations from the original images, which are then used for image classification and recognition. The similarity between the acquired images and preset images is determined, thereby assessing the correctness of the automated testing software strategy.

[0043] In one embodiment, the output test results are analyzed to evaluate the performance of SOA Scenario Master in different scenarios; This includes: calculating the time interval between receiving the trigger condition and executing the corresponding action in the SOA Scenario Master, and evaluating the response speed of the SOA Scenario Master; Compare the actual execution time with the expected execution time to evaluate the execution efficiency of SOA Scenario Master; Compare the output of SOA Scenario Master with the expected results to evaluate the accuracy of SOA Scenario Master.

[0044] Specifically, performance evaluation: Response Time Assessment: Calculate the time interval between receiving the trigger condition and executing the corresponding action to assess its response speed. The time assessment formula is as follows: [Response time = Trigger time - Execution time] Execution efficiency evaluation: The execution efficiency of Scenario Master is evaluated by comparing the actual execution time with the expected execution time. The execution efficiency evaluation formula is as follows: [Execution efficiency = Expected execution time = Actual execution time = 100%] Accuracy Assessment: Compare the output of Scene Master with the expected results to calculate the accuracy rate and assess the accuracy of its functionality. The accuracy assessment formula is as follows: [\text{accuracy} = \frac{\text{number of correct executions}}{\text{total number of executions}} \times 100%].

[0045] In summary, by automatically generating test cases using automated testing software, the relevant status and condition signals of the test cases are transmitted to the real vehicle testing platform via communication equipment. The real vehicle executes corresponding actions based on the status and condition signals, and the execution images are captured by image recognition devices such as cameras. The action signals are then transmitted back to the automated testing software via communication equipment. The software platform determines whether the action signals are correct, performs image recognition and comparison between the captured images and preset execution effect images, outputs the test results, and automatically executes the next test case, further improving the reliability of the testing process and development efficiency.

[0046] Reference Figure 2 , Figure 2 The diagram shown is a schematic of an automatic vehicle scenario testing device provided by the present invention. Figure 2 As shown, the device includes: Processing module 201: It is used to automatically generate test cases corresponding to multiple test scenarios defined by SOA Scenario Master, and simulate the test scenarios to obtain execution truth signals and expected execution effect images.

[0047] Execution module 202: It is used to control the vehicle to perform corresponding actions based on the test cases and obtain the execution effect image.

[0048] Output module 203: It is used to compare the executed action signal with the execution truth signal, and compare the execution effect image with the expected execution effect image to determine whether the executed action and execution effect are consistent, and output the test result.

[0049] Furthermore, in one possible implementation, the output module is also used to transmit the executed action signal to the SOA Scene Master using a communication device, and to calculate the difference D between the executed action signal and the executed truth signal using a one-dimensional convolutional Siamese network model in the SOA Scene Master. The difference D is compared with the set threshold to determine whether the actions performed by the two are consistent.

[0050] Furthermore, in one possible implementation, the output module is also used to calculate according to the formula: Calculate the difference between the executed action signal and the execution truth signal, wherein, , These represent the collected action signal and the scene ground truth signal, respectively. The F-dimensional feature represents the signal type, Y is the label indicating whether the two match, and th is the distance threshold.

[0051] Furthermore, in one possible implementation, the output module is also used to acquire the execution effect image through the acquisition device, and to extract features from the execution effect image using the gray-level co-occurrence matrix (GLCM) and local binary mode (LBP). The extracted features are compared with the expected execution effect image to determine the similarity between the execution effect image and the expected execution effect image; Based on the similarity, determine whether the execution results are consistent.

[0052] Furthermore, in one possible implementation, the processing module is also used to analyze the output test results to evaluate the performance of SOA Scenario Master in different scenarios. This includes: calculating the time interval between receiving the trigger condition and executing the corresponding action in the SOA Scenario Master, and evaluating the response speed of the SOA Scenario Master; Compare the actual execution time with the expected execution time to evaluate the execution efficiency of SOA Scenario Master; Compare the output of SOA Scenario Master with the expected results to evaluate the accuracy of SOA Scenario Master.

[0053] Furthermore, in one possible implementation, the processing module is also used to write multiple test scenarios using SOA Scenario Master, including: daily commute, long-distance travel, night driving, severe weather, and emergency avoidance; The SOA Scenario Master automatically matches the test cases corresponding to the input test scenario.

[0054] Furthermore, in one possible implementation, the processing module is also used to simulate test scenario trigger signals using SOA Scene Master, and execute corresponding actions through the trigger signals to obtain execution action truth signals and execution effect images. The trigger signals include: seat belt, navigation, environment, driving, doors and windows, camera, time, and account. The execution truth signals include: interior lights, vehicle body, exterior lights, navigation, multimedia, air conditioning, Bluetooth, doors and windows, screen display, camera, sound, network, fragrance, and seats.

[0055] Reference Figure 3 , Figure 3 The diagram shown is an automatic testing schematic provided by the present invention. Figure 3 As shown: The SOA Scenario Master is used to define test scenarios and take these scenarios as input to simulate the test scenarios, thereby obtaining execution truth signals and expected execution effect images. Simultaneously, the simulated signals are sent to the actual vehicle / bench platform. Upon receiving the simulated signals, the corresponding actions are executed to obtain execution action signals. The execution images are then captured by acquisition devices, such as cameras, for image recognition to obtain execution effect images. The execution truth signals and expected execution effect images are compared with the execution action signals and execution effect images to determine whether the actions and scenario requirements are consistent, and the test results are output.

[0056] Understandably, SOA-based automated testing software requires testing scenarios. This software can simulate scenario trigger signals (such as seatbelts, navigation, environment, driving, doors and windows, cameras, time, accounts, etc.) and automatically obtain execution information truth signals (such as interior lights, vehicle body, exterior lights, navigation, multimedia, air conditioning, Bluetooth, doors and windows, screen display, cameras, sound, network, fragrance, seats, etc.) and execution effect images. The trigger signals are sent to the actual vehicle / bench platform. Upon receiving the signals, the SOA scenario master is automatically executed, performing vehicle-mounted actions according to the scenario. Image acquisition devices such as cameras are used to capture and collect various settings within the cabin in real time. The collected execution action signals are compared with the truth signals to determine correctness. Using image recognition technology, the testing system analyzes and processes the collected images, comparing the identified content with preset execution effect images to determine the correctness of the automated testing software strategy.

[0057] The following reference Figure 4 To describe an electronic device 400 according to this embodiment of the present invention. Figure 4 The electronic device 400 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0058] like Figure 4As shown, the electronic device 400 is manifested in the form of a general-purpose computing device. The components of the electronic device 400 may include, but are not limited to: at least one processing unit 410, at least one storage unit 420, and a bus 430 connecting different system components (including storage unit 420 and processing unit 410).

[0059] The storage unit stores program code that can be executed by the processing unit 410, causing the processing unit 410 to perform the steps described in the "Embodiment Methods" section of this specification according to various exemplary embodiments of the present invention.

[0060] Storage unit 420 may include readable media in the form of volatile storage units, such as random access memory (RAM) 421 and / or cache memory 422, and may further include read-only memory (ROM) 423.

[0061] Storage unit 420 may also include a program / utility 424 having a set (at least one) of program modules 425, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0062] Bus 430 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0063] Electronic device 400 can also communicate with one or more external devices (e.g., keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with electronic device 400, and / or any device that enables electronic device 400 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 450. Furthermore, electronic device 400 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 460. As shown, network adapter 460 communicates with other modules of electronic device 400 via bus 430. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0064] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0065] According to the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible embodiments, various aspects of the present invention can also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of the present invention described in the "Exemplary Methods" section above.

[0066] refer to Figure 5 As shown, a program product 500 for implementing the above-described method according to an embodiment of the present invention is described. It may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0067] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0068] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0069] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0070] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0071] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0072] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

[0073] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

Claims

1. A method of automatically testing a vehicle scenario, the method comprising: The method comprises the following steps: Based on the SOA scenario master defines a plurality of test scenarios, automatically generates test cases corresponding to the test scenarios, and simulates the test scenarios to obtain execution truth signals and expected execution effect images; Based on the test cases, control the vehicle to execute corresponding actions, and obtain execution effect images; Compare the executed action signals with the execution truth signals, compare the execution effect images with the expected execution effect images, to determine whether the executed actions and the execution effects are consistent, and output the test results.

2. The method of claim 1, wherein, The comparison of the executed action signals and the execution truth signals to determine whether the executed actions are consistent comprises: Use a communication device to transmit the executed action signals to the SOA scenario master, and use a one-dimensional convolution twin network model in the SOA scenario master to calculate the difference D between the executed action signals and the execution truth signals; Compare the difference D with the set threshold to determine whether the executed actions of the two are consistent.

3. The method of claim 2, wherein, The method comprises the following steps: According to the formula: , compute the gap between the executed action signal and the execution ground truth signal, wherein, , respectively represent the collected executed action signal and the scene ground truth signal, F-dimensional features represent the signal category, Y is the label of whether they match, and th is the distance threshold.

4. The method of claim 1, wherein, The comparison of the execution effect images and the expected execution effect images to determine whether the execution effects are consistent comprises: Use a collection device to obtain the execution effect images, and use a gray level co-occurrence matrix GLCM and a local binary pattern LBP to extract features of the execution effect images; Compare the extracted features with the expected execution effect images to determine the similarity between the execution effect images and the expected execution effect images; According to the similarity, determine whether the execution effects are consistent.

5. The method of claim 1, wherein, The method comprises the following steps: Analyze the output test results to evaluate the performance of the SOA scenario master in different scenarios; It comprises: calculating the time interval from when the SOA scenario master receives the trigger condition to when it executes the corresponding action, evaluating the response speed of the SOA scenario master; Compare the actual execution time with the expected execution time to evaluate the execution efficiency of the SOA scenario master; Compare the output results of the SOA scenario master with the expected results to evaluate the accuracy of the SOA scenario master.

6. The method of claim 1, wherein, The method comprises the following steps: Use the SOA scenario master to write a plurality of test scenarios, which include: daily commuting, long-distance travel, night driving, bad weather, and emergency escape; The SOA scenario master automatically generates test cases corresponding to the test scenarios according to the input test scenarios.

7. The method of claim 1, wherein, The method comprises the following steps: Use the SOA scenario master to simulate test scenario trigger signals, and execute corresponding actions through the trigger signals to obtain execution action truth signals and execution effect images, wherein the trigger signals include: seat belts, navigation, environment, driving, doors and windows, cameras, time, and accounts, and the execution truth signals include: interior lights, vehicle body, exterior lights, navigation, multimedia, air conditioning, Bluetooth, doors and windows, screen display, cameras, sound, network, fragrance, and seats.

8. A vehicle scene automatic testing device, characterized by, The method comprises the following steps: a processing module, configured to automatically generate a test case corresponding to a test scene defined by a SOA scene master based on a plurality of test scenes, and simulate the test scene to obtain an execution truth signal and an expected execution effect image; an execution module, configured to control a vehicle to perform a corresponding action based on the test case, and obtain an execution effect image; an output module, configured to compare the execution action signal with the execution truth signal, compare the execution effect image with the expected execution effect image, to determine whether the execution action and the execution effect are consistent, and output a test result.

9. An electronic device, comprising: The electronic device comprises: a processor; a memory, which stores computer readable instructions, and the computer readable instructions are executed by the processor to implement the method in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer program instructions are stored in the computer, and when the computer program instructions are executed by the computer, the computer executes the method in any one of claims 1 to 7.

Images