Vehicle voice test method and device and new energy vehicle

Abstract

The invention provides a vehicle voice test method and device, a new energy vehicle and electronic equipment, and the method comprises the steps: obtaining the real-time data of the vehicle; in a test environment, performing function verification on a pre-constructed test case according to the real-time data to obtain an execution instruction; if the execution instruction is execution starting, triggering the test case to perform a cyclic pressure test to obtain a test result; and performing consistency judgment on the test result, and generating a test report. According to the invention, the method can improve the testing efficiency of the vehicle-mounted voice, shortens the testing period, does not depend on manual testing, is more sensitive to the voice wake-up time, can completely cover the voice instruction and the voice environment of a user, and achieves the comprehensive and reasonable voice testing.

Description

Technical Field

[0001] This application relates to the field of voice testing technology, and more specifically, to a vehicle voice testing method, device, new energy vehicle, and electronic device. Background Technology

[0002] With the rapid development of the automotive industry and intelligent connected vehicle technology, the intelligence and connectivity of automobiles are constantly improving. Cars are gradually being equipped with more intelligent, convenient, and user-friendly functions, among which intelligent voice systems are one of the most common features. Intelligent voice can activate a voice assistant through a specific wake word or a user-defined wake word. Voice commands can then enable the vehicle system to automatically execute corresponding functions, allowing users to control the vehicle automatically.

[0003] However, most existing in-vehicle voice functions rely on real-vehicle testing. Testers need to get into the vehicle, verbally issue voice commands based on the voice function test sheet, and then conduct manual testing based on the actual vehicle performance and collected vehicle data. This testing method is not sensitive enough to the wake-up time of the voice function and the time of execution of the test. It also relies on the testing experience of the testers, has a long testing cycle, and the testers may not be able to cover the language environment carried by the in-vehicle voice, resulting in a small coverage of test indicators and low testing efficiency. Summary of the Invention

[0004] The purpose of this application is to provide a vehicle voice testing method, device, new energy vehicle and electronic device, which can improve the testing efficiency of vehicle voice, shorten the testing cycle, eliminate the need for manual testing, be more sensitive to voice wake-up time, and fully cover the user's voice commands and language environment to achieve comprehensive and reasonable voice testing.

[0005] In a first aspect, embodiments of this application provide a vehicle voice testing method, the method comprising: Obtain real-time vehicle data; In the testing environment, the pre-built test cases are functionally verified based on the real-time data to obtain execution instructions; If the execution instruction is to start execution, the test case is triggered to perform a cyclic stress test, and the test results are obtained; The consistency of the test results is determined, and a test report is generated.

[0006] In the above implementation process, constructing test cases to perform functional verification and cyclic stress testing of the voice system can improve the testing efficiency of in-vehicle voice systems, shorten the testing cycle, eliminate reliance on manual testing, be more sensitive to voice wake-up time, and fully cover the user's voice commands and language environment, thereby achieving comprehensive and reasonable voice testing.

[0007] Furthermore, the step of performing functional verification on the pre-built test cases based on the real-time data to obtain execution instructions further includes: constructing test cases, wherein the step of constructing test cases includes: Construct use cases for voice command conversion, audio parameter adjustment, and microphone recognition in sequence; The test cases are generated based on the voice command conversion test case, the audio parameter adjustment test case, and the microphone recognition test case.

[0008] In the above implementation process, voice conversion, audio parameter adjustment and microphone recognition are added to the voice test cases in sequence. This allows for voice testing from multiple perspectives, improving the vehicle system's ability to recognize voice.

[0009] Furthermore, the step of performing functional verification on the pre-built test cases based on the real-time data to obtain execution instructions includes: Obtain the voice commands from the real-time data; The voice command was functionally verified according to the test cases, and the verification results were obtained. If the verification result is correct, the execution instruction is determined to begin execution; If the verification result is incorrect, rebuild the test case.

[0010] In the above implementation process, the voice commands are functionally verified according to the test cases, and the corresponding verification results are obtained. This ensures the accuracy of the test cases and guarantees that each test is complete and effective, without affecting the voice function.

[0011] Further, the step of performing functional verification of the voice command based on the test cases and obtaining the verification result includes: Execute the voice command conversion test case in the test case, and convert the voice command into the corresponding voice audio using a pre-built large model; The parameters of the speech audio are adjusted according to the audio parameter adjustment example to obtain synthesized audio; Microphone identification is performed on the synthesized audio according to the microphone identification use case; If the microphone correctly recognizes the synthesized audio, the verification result is determined to be correct; If the microphone cannot correctly recognize the synthesized audio, the verification result is determined to be incorrect.

[0012] In the above implementation process, converting voice commands and then adjusting the parameters of the voice audio can reduce noise in the voice audio, reduce recognition errors in the voice audio, and improve the accuracy of verification results.

[0013] Further, the step of triggering the test case to perform cyclic stress testing and obtain test results if the execution instruction is to start execution includes: After the test case is triggered, the audio segment of the voice response corresponding to the voice command is obtained; Semantic recognition is performed on the audio segments to obtain a recognition file; The test results are obtained based on the identified file.

[0014] In the above implementation process, semantic recognition of the voice segments corresponding to the voice response can clarify the specific meaning of the voice command, and the test results can be confirmed based on the recognition file, thus ensuring the accuracy of the test results.

[0015] Further, the step of obtaining the test result based on the identified file includes: Extract the vehicle bus signal from the identification file; The vehicle bus signals are analyzed to obtain the corresponding signal characteristics; The test results are obtained by determining whether the vehicle is performing voice functions based on the signal characteristics.

[0016] In the above implementation process, the vehicle's voice function is determined by analyzing the signal characteristics obtained from the vehicle bus signal. This enables automated testing, effectively shortens the testing cycle, and eliminates the need for manual testing.

[0017] Furthermore, the step of determining the consistency of the test results and generating a test report includes: Obtain the expected test results; The test results are compared with the expected test results to generate the test report.

[0018] In the above implementation process, consistency judgment of test results is performed to improve the accuracy of testing, which can achieve complete coverage of the voice environment and realize comprehensive and reasonable voice testing.

[0019] Secondly, embodiments of this application also provide a vehicle voice testing device, the device comprising: The acquisition module is used to acquire real-time vehicle data; The functional verification module is used to perform functional verification on pre-built test cases in a test environment based on the real-time data, and obtain execution instructions. The testing module is used to trigger the test cases to perform cyclic stress testing and obtain test results if the execution instruction is to start execution; The generation module is used to determine the consistency of the test results and generate a test report.

[0020] In the above implementation process, constructing test cases to perform functional verification and cyclic stress testing of the voice system can improve the testing efficiency of in-vehicle voice systems, shorten the testing cycle, eliminate reliance on manual testing, be more sensitive to voice wake-up time, and fully cover the user's voice commands and language environment, thereby achieving comprehensive and reasonable voice testing.

[0021] Thirdly, the embodiments of this application provide a new energy vehicle, including the vehicle voice testing device of the second aspect.

[0022] Fourthly, an electronic device provided in this application includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method as described in any of the first aspects.

[0023] Fifthly, embodiments of this application provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method described in any of the first aspects.

[0024] Other features and advantages of this disclosure will be set forth in the following description, or some features and advantages may be inferred from the description or determined without doubt, or may be learned by practicing the techniques described above.

[0025] It can be implemented in accordance with the contents of the specification. The preferred embodiments of this application are described in detail below with reference to the accompanying drawings. Attached Figure Description

[0026] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation on the range. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 A flowchart illustrating a vehicle voice testing method is provided for embodiments of this application. Figure 2 A schematic diagram of the structural composition of a vehicle voice testing device is provided for embodiments of this application; Figure 3 This is a schematic diagram of the structural composition of the electronic device provided in the embodiments of this application. Detailed Implementation

[0028] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0029] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0030] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The following examples are used to illustrate this application, but are not intended to limit the scope of this application.

[0031] Most existing in-vehicle voice functions rely on real-vehicle testing and manual testing. This testing method is not sensitive enough to the wake-up time of the voice function and the execution time of the test. It also depends on the testing experience of the testers, has a long testing cycle, and the testers may not be able to cover the language environment carried by the in-vehicle voice, resulting in a small coverage of test indicators and low testing efficiency.

[0032] This application utilizes an automated voice function testing method, which can significantly improve testing accuracy and shorten testing time. It not only reduces the manpower and time costs of testing but also increases the volume of voice testing, lowers the experience threshold for testing work, and makes testing tasks simple and easy to implement.

[0033] Example 1 Figure 1 This is a flowchart illustrating the vehicle voice testing method provided in this application embodiment, as shown below. Figure 1 As shown, the method includes: S1, acquire real-time vehicle data; S2, in the test environment, performs functional verification on pre-built test cases based on real-time data to obtain execution instructions; S3, if the execution command is to start execution, trigger the test cases to perform cyclic stress testing and obtain the test results; S4 performs consistency checks on the test results and generates a test report.

[0034] In the above implementation process, constructing test cases to perform functional verification and cyclic stress testing of the voice system can improve the testing efficiency of in-vehicle voice systems, shorten the testing cycle, eliminate reliance on manual testing, be more sensitive to voice wake-up time, and fully cover the user's voice commands and language environment, thereby achieving comprehensive and reasonable voice testing.

[0035] This application uses an automated program to perform voice output, test result data collection, and test result aggregation, thereby conducting high-intensity stress tests on the in-vehicle voice system, extending the test time, and uncovering test problems.

[0036] Furthermore, before constructing test cases, this application also requires the setup of a test environment in Huanjiang.

[0037] The setup of the testing environment mainly consists of three parts: test computers, hardware equipment, and vehicles.

[0038] To test the computer-based system, a testing software platform must first be built. This platform is used to automatically execute written voice test cases, collect real-time vehicle data, and perform functional verification.

[0039] On the hardware side, a sound card and related drivers need to be installed on the computer, and speakers and microphones need to be connected to enable sound output and reception.

[0040] On the vehicle side, the controller corresponding to the test function needs to be prepared to ensure that the function can be executed correctly. A wired or wireless ADB is used to connect the vehicle's computer and the test computer, and Canoe is used to collect real-time data of the current vehicle.

[0041] Furthermore, S2 includes: Construct use cases for voice command conversion, audio parameter adjustment, and microphone recognition in sequence; Test cases are generated based on voice command conversion test cases, audio parameter adjustment test cases, and microphone recognition test cases.

[0042] In the above implementation process, voice conversion, audio parameter adjustment and microphone recognition are added to the voice test cases in sequence. This allows for voice testing from multiple perspectives, improving the vehicle system's ability to recognize voice.

[0043] After setting up the environment, test cases need to be compiled. This application allows for the pre-integration of code for some common operations, such as returning to the vehicle's home screen, using the default voice wake-up word, recognizing Canoe signal data, performing DBC parsing, and outputting test results and compiling test reports.

[0044] In addition, the corresponding code function of image recognition can be used to detect whether the vehicle system function is executed successfully; the microphone recording time can be collected to accurately obtain the start and end time of the voice function; and dialect voice packs or dialect voice synthesized through a large voice model can be used for output testing.

[0045] After the environment is set up and test cases are constructed, the program can be tested. On the test software platform, debugging can be performed step by step, one voice command at a time, to observe for errors or unexpected operations and make corrections. Examples include adjusting the accuracy threshold for image recognition, the frequency of Canoe signal acquisition, and the output of test results.

[0046] This application aims to achieve comprehensive coverage of test metrics while improving testing efficiency within a limited functional testing period. Therefore, test metrics need to be quantified, and multiple metrics can be selected for evaluation, including voice wake-up time, voice wake-up success rate, voice command misrecognition rate, function execution success rate, and voice feedback time. Test metrics include: Voice wake-up time: The average time to wake up a voice using a specific wake word (default wake word or user-defined wake word).

[0047] Voice wake-up success rate: The percentage of successful voice wake-up attempts out of the total number of wake-up attempts.

[0048] Voice command misrecognition rate: The percentage of times a voice command is incorrectly recognized and executed after a successful wake-up voice command.

[0049] Function execution success rate: The percentage of times a function is successfully executed after a voice command is issued out of the total number of tests.

[0050] Voice feedback time: The average time to recognize and process user commands during user-voice interaction.

[0051] Furthermore, S3 includes: Retrieve voice commands from real-time data; The voice commands were functionally verified based on the test cases, and the verification results were obtained. If the verification result is correct, then the execution command will begin. If the verification result is incorrect, rebuild the test case.

[0052] In the above implementation process, the voice commands are functionally verified according to the test cases, and the corresponding verification results are obtained. This ensures the accuracy of the test cases and guarantees that each test is complete and effective, without affecting the voice function.

[0053] Before testing, this application requires confirmation that the testing environment is ready and to conduct the test within the testing environment. This application embodiment is based on Python and LabVIEW automated testing software. The testing software can manage the test and its output, and realize automated cyclic testing.

[0054] This application allows the entire code to be run. If problems persist, modifications can be made until the expected accuracy meets the test metrics. After functional verification, if the program meets the test requirements for voice functionality (i.e., the verification result is error-free), test cases can be executed in a loop.

[0055] Furthermore, the steps for functionally verifying voice commands based on test cases and obtaining verification results include: Execute the voice command conversion test case in the test cases, and convert the voice commands into corresponding audio using a pre-built large model; The parameters of the speech audio are adjusted according to the audio parameter adjustment case to obtain the synthesized audio; Microphone identification is performed on the synthesized audio based on microphone identification use cases; If the microphone correctly identifies the synthesized audio, the verification result is confirmed to be correct. If the microphone cannot correctly recognize the synthesized audio, the verification result is determined to be incorrect.

[0056] In the above implementation process, converting voice commands and then adjusting the parameters of the voice audio can reduce noise in the voice audio, reduce recognition errors in the voice audio, and improve the accuracy of verification results.

[0057] This application addresses the conversion of voice commands across various language environments and application scenarios. Manual testing methods are insufficient for testing common dialects (such as Sichuanese, Cantonese, and Shandongese), while the program's large-scale voice model can simulate dialect outputs for comprehensive testing.

[0058] For example, the following is a partial test procedure for a test case: Voice command: Hello, XX, turn on the driver's side air conditioning, set the temperature to 24°C, and the fan speed to level 3; Using the Wenxin Yiyan and DeepSeek large model, the prepared voice commands are converted into corresponding Cantonese, and then the text-to-speech software tool is used to synthesize male or female voice audio using Cantonese language packs. Adjust parameters such as pitch and frequency of the synthesized audio; Position the speaker so that the vehicle microphone can accurately recognize the synthesized audio. Repeat the above steps until the microphone can accurately recognize it.

[0059] Furthermore, S4 includes: After the test case is triggered, obtain the audio segment of the voice response corresponding to the voice command; Perform semantic recognition on the speech segments to obtain the recognized file; The test results are obtained based on the identified file.

[0060] In the above implementation process, semantic recognition of the voice segments corresponding to the voice response can clarify the specific meaning of the voice command, and the test results can be confirmed based on the recognition file, thus ensuring the accuracy of the test results.

[0061] Furthermore, the steps for obtaining test results based on the identified file include: Extract the vehicle bus signals from the identification file; The vehicle bus signals are analyzed to obtain the corresponding signal characteristics; The test results are obtained by determining whether the vehicle is performing voice functions based on signal characteristics.

[0062] In the above implementation process, the vehicle's voice function is determined by analyzing the signal characteristics obtained from the vehicle bus signal. This enables automated testing, effectively shortens the testing cycle, and eliminates the need for manual testing.

[0063] Optionally, in this application, a waiting time can be set before it is determined that the test can be executed, and the test will start automatically when the waiting time is reached.

[0064] Recording TTS voice responses allows you to obtain the voice feedback time and perform semantic recognition on the recorded voice segments to obtain a recognition file.

[0065] The vehicle bus signals in the recognition file are captured and parsed using DBC. The signal features corresponding to the test functions are extracted, and the vehicle is judged to perform voice functions based on the signal features. The test results are then output.

[0066] Furthermore, S5 includes: Obtain the expected test results; The test results are compared with the expected test results to generate a test report.

[0067] In the above implementation process, consistency judgment of test results is performed to improve the accuracy of testing, which can achieve complete coverage of the voice environment and realize comprehensive and reasonable voice testing.

[0068] The test results are compared with the expected test results, and the test results are output. The current round of testing ends and the software is reset. After the software is reset, the test loop begins until the number of loops is completed, and a test report is generated.

[0069] The testing in this application involves multiple iterations. After each test case is executed, the system is reset to prepare for the next test cycle. After executing the test cases for the expected number of cycles, a problem log and a test report are output as deliverables. After the test is completed, all connected devices are disconnected, the system is powered off in an orderly manner, and the test hardware is reset.

[0070] Example 2 To execute the method corresponding to Embodiment 1 above and achieve the corresponding functional and technical effects, a vehicle voice testing device is provided below, such as... Figure 2 As shown, the device includes: Acquisition module 1 is used to acquire real-time vehicle data; Functional verification module 2 is used to perform functional verification on pre-built test cases in a test environment based on real-time data, and obtain execution instructions; Test module 3 is used to trigger test cases to perform cyclic stress testing if the execution command is "start execution" and obtain the test results. Module 4 is used to determine the consistency of test results and generate a test report.

[0071] In the above implementation process, constructing test cases to perform functional verification and cyclic stress testing of the voice system can improve the testing efficiency of in-vehicle voice systems, shorten the testing cycle, eliminate reliance on manual testing, be more sensitive to voice wake-up time, and fully cover the user's voice commands and language environment, thereby achieving comprehensive and reasonable voice testing.

[0072] Furthermore, the device also includes a building module for: Construct use cases for voice command conversion, audio parameter adjustment, and microphone recognition in sequence; Test cases are generated based on voice command conversion test cases, audio parameter adjustment test cases, and microphone recognition test cases.

[0073] In the above implementation process, voice conversion, audio parameter adjustment and microphone recognition are added to the voice test cases in sequence. This allows for voice testing from multiple perspectives, improving the vehicle system's ability to recognize voice.

[0074] Furthermore, the functional verification module 2 is also used for: Retrieve voice commands from real-time data; The voice commands were functionally verified based on the test cases, and the verification results were obtained. If the verification result is correct, then the execution command will begin. If the verification result is incorrect, rebuild the test case.

[0075] In the above implementation process, the voice commands are functionally verified according to the test cases, and the corresponding verification results are obtained. This ensures the accuracy of the test cases and guarantees that each test is complete and effective, without affecting the voice function.

[0076] Furthermore, the functional verification module 2 is also used for: Execute the voice command conversion test case in the test cases, and convert the voice commands into corresponding audio using a pre-built large model; The parameters of the speech audio are adjusted according to the audio parameter adjustment case to obtain the synthesized audio; Microphone identification is performed on the synthesized audio based on microphone identification use cases; If the microphone correctly identifies the synthesized audio, the verification result is confirmed to be correct. If the microphone cannot correctly recognize the synthesized audio, the verification result is determined to be incorrect.

[0077] In the above implementation process, converting voice commands and then adjusting the parameters of the voice audio can reduce noise in the voice audio, reduce recognition errors in the voice audio, and improve the accuracy of verification results.

[0078] Furthermore, test module 3 is also used for: After the test case is triggered, obtain the audio segment of the voice response corresponding to the voice command; Perform semantic recognition on the speech segments to obtain the recognized file; The test results are obtained based on the identified file.

[0079] In the above implementation process, semantic recognition of the voice segments corresponding to the voice response can clarify the specific meaning of the voice command, and the test results can be confirmed based on the recognition file, thus ensuring the accuracy of the test results.

[0080] Furthermore, test module 3 is also used for: Extract the vehicle bus signals from the identification file; The vehicle bus signals are analyzed to obtain the corresponding signal characteristics; The test results are obtained by determining whether the vehicle is performing voice functions based on signal characteristics.

[0081] In the above implementation process, the vehicle's voice function is determined by analyzing the signal characteristics obtained from the vehicle bus signal. This enables automated testing, effectively shortens the testing cycle, and eliminates the need for manual testing.

[0082] Furthermore, generation module 4 is also used for: Obtain the expected test results; The test results are compared with the expected test results to generate a test report.

[0083] In the above implementation process, consistency judgment of test results is performed to improve the accuracy of testing, which can achieve complete coverage of the voice environment and realize comprehensive and reasonable voice testing.

[0084] The vehicle voice testing device described above can implement the method of Embodiment 1. The options in Embodiment 1 also apply to this embodiment, and will not be described in detail here.

[0085] The remaining contents of this embodiment can be referred to the contents of Embodiment 1 above, and will not be repeated in this embodiment.

[0086] Example 3 This application provides a new energy vehicle, including the vehicle voice testing device of embodiment two.

[0087] Example 4 This application provides an electronic device, including a memory and a processor. The memory stores a computer program, and the processor runs the computer program to enable the electronic device to perform the vehicle voice testing method of Embodiment 1.

[0088] Alternatively, the aforementioned electronic device may be a server.

[0089] Please see Figure 3 , Figure 3 This is a schematic diagram illustrating the structural composition of an electronic device provided in an embodiment of this application. The electronic device may include a processor 31, a communication interface 32, a memory 33, and at least one communication bus 34. The communication bus 34 is used to enable direct communication between these components.

[0090] Optionally, the electronic device may also include a storage controller and an input / output unit. The memory 33, storage controller, processor 31, peripheral interface, and input / output unit are electrically connected to each other directly or indirectly to realize data transmission or interaction.

[0091] Input / output units are used to enable users to create tasks and set optional start periods or preset execution times for those tasks, facilitating user-server interaction. Input / output units can be, but are not limited to, a mouse and keyboard.

[0092] Understandable. Figure 3 The structure shown is for illustrative purposes only; the electronic device may also include components that are more advanced than those shown. Figure 3 The more or fewer components shown, or having the same Figure 3 Different configurations are shown. Additionally, embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the vehicle voice testing method of Embodiment 1.

[0093] This application also provides a computer program product that, when run on a computer, causes the computer to perform the method described in the method embodiment.

[0094] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application. It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0095] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of protection of the claims.

Claims

1. A vehicle voice testing method, characterized in that, The method includes: Obtain real-time vehicle data; In the testing environment, the pre-built test cases are functionally verified based on the real-time data to obtain execution instructions; If the execution instruction is to start execution, the test case is triggered to perform a cyclic stress test, and the test results are obtained; The consistency of the test results is determined, and a test report is generated.

2. The vehicle voice testing method according to claim 1, characterized in that, The step of performing functional verification on pre-built test cases based on the real-time data to obtain execution instructions further includes: constructing test cases, wherein the step of constructing test cases includes: Construct use cases for voice command conversion, audio parameter adjustment, and microphone recognition in sequence; The test cases are generated based on the voice command conversion test case, the audio parameter adjustment test case, and the microphone recognition test case.

3. The vehicle voice testing method according to claim 1, characterized in that, The step of performing functional verification on pre-built test cases based on the real-time data to obtain execution instructions includes: Obtain the voice commands from the real-time data; The voice command was functionally verified according to the test cases, and the verification results were obtained. If the verification result is correct, the execution instruction is determined to begin execution; If the verification result is incorrect, rebuild the test case.

4. The vehicle voice testing method according to claim 3, characterized in that, The step of performing functional verification of the voice command according to the test cases and obtaining the verification result includes: Execute the voice command conversion test case in the test case, and convert the voice command into the corresponding voice audio using a pre-built large model; The parameters of the speech audio are adjusted according to the audio parameter adjustment example to obtain synthesized audio; Microphone identification is performed on the synthesized audio according to the microphone identification use case; If the microphone correctly recognizes the synthesized audio, the verification result is determined to be correct; If the microphone cannot correctly recognize the synthesized audio, the verification result is determined to be incorrect.

5. The vehicle voice testing method according to claim 1, characterized in that, The step of triggering the test case to perform cyclic stress testing and obtain test results if the execution instruction is to start execution includes: After the test case is triggered, the audio segment of the voice response corresponding to the voice command is obtained; Semantic recognition is performed on the audio segments to obtain a recognition file; The test results are obtained based on the identified file.

6. The vehicle voice testing method according to claim 5, characterized in that, The step of obtaining the test result based on the identified file includes: Extract the vehicle bus signal from the identification file; The vehicle bus signals are analyzed to obtain the corresponding signal characteristics; The test results are obtained by determining whether the vehicle is performing voice functions based on the signal characteristics.

7. The vehicle voice testing method according to claim 1, characterized in that, The step of determining the consistency of the test results and generating a test report includes: Obtain the expected test results; The test results are compared with the expected test results to generate the test report.

8. A vehicle voice testing device, characterized in that, The device includes: The acquisition module is used to acquire real-time vehicle data; The functional verification module is used to perform functional verification on pre-built test cases in a test environment based on the real-time data, and obtain execution instructions. The testing module is used to trigger the test cases to perform cyclic stress testing and obtain test results if the execution instruction is to start execution; The generation module is used to determine the consistency of the test results and generate a test report.

9. A new energy vehicle, characterized in that, Includes the vehicle voice testing device as described in claim 8.

10. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as claimed in claims 1-7.

11. A storage medium, characterized in that, The storage medium stores instructions that, when executed on a computer, cause the computer to perform the method as described in claims 1-7.

Images