A new energy vehicle voice function testing method, system and device
By obtaining vehicle-computer interactive interface information to generate virtual voice control instructions and recording operation logs, combining image recognition and reinforcement learning, the problem of low efficiency of voice function testing in new energy vehicles is solved, and efficient and accurate testing and optimization are achieved to adapt to complex vehicle-mounted vehicles. Changes in the environment.
Patent Information
- Application Number
- CN202411089210.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-08-09
AI Technical Summary
The existing voice function testing methods for new energy vehicles are complex and time-consuming, resulting in low efficiency and difficult to adapt to the frequent updates of on-board software and changes in user habits.
By obtaining vehicle-computer interactive interface information, generating virtual voice control instructions and playing, recording operation logs and interface change information, determining the effectiveness of voice command results, and automatically identifying user interface elements using image recognition and layer layout algorithms to realize automated testing, combined with Reinforcement learning optimizes speech recognition and response.
It improves the degree of test automation and accuracy, improves the testing efficiency, and can continuously learn and optimize in complex vehicle-mounted environments, adapt to user behavior and system updates, and significantly improves the recognition and response capabilities of voice commands.
Smart Images

Figure CN118629396B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of vehicle computer testing, and specifically relates to a new energy vehicle voice function testing method, system and equipment. Background Art
[0002] With the rapid development of new energy vehicle technology, in-vehicle voice control systems have gradually become a key component to enhance the driving experience. Users control more than 95% of the functions in the car through voice commands. Managing these functions through voice commands not only improves driving safety, but also significantly enhances the driving experience and ease of operation. However, with the increase in vehicle functions and technological advancement, the software of the in-vehicle system often needs to be updated or iterated to introduce new functions or improve existing functions. As user usage habits change and new functions are added, the system should be able to continuously learn and optimize its performance. The changes in these functions lead to technical challenges in the accurate recognition and execution of voice commands, especially in complex in-vehicle environments. Therefore, in order to ensure the accuracy of the voice function, it is necessary to test the function after each update iteration. The existing testing methods are often complex and time-consuming, resulting in low efficiency. Therefore, there is an urgent need for a method or device that can adapt to the frequent updates of existing in-vehicle software and improve testing efficiency. Summary of the invention
[0003] In view of the above shortcomings of the prior art, the purpose of the present invention is to provide a new energy vehicle voice function testing method, system and equipment to improve the problem that the existing testing methods are often complicated, time-consuming and inefficient.
[0004] To achieve the above purpose and other related purposes, the present invention provides a new energy vehicle voice function testing method, comprising:
[0005] Get the interactive interface information of the vehicle computer;
[0006] Generate a virtual voice control instruction according to the interactive interface information and play it;
[0007] Acquire an operation log corresponding to the operation performed by the vehicle system in response to the virtual voice control command, and interface change information after the operation performed by the vehicle system in response to the virtual voice control command;
[0008] Whether the result of the vehicle system responding to the virtual voice control instruction is valid is determined according to the operation log and the interface change information to obtain a test result.
[0009] In one embodiment of the present invention, the step of generating a virtual voice control instruction according to the interactive interface information and playing the instruction comprises:
[0010] Obtaining the playback text according to the interactive interface information decision;
[0011] Convert the played text into an audio file to obtain the virtual voice control instruction;
[0012] The virtual voice control instruction is sent to the speaker for playing.
[0013] In one embodiment of the present invention, the step of converting the played text into an audio file to obtain the virtual voice control instruction includes:
[0014] Processing the played text to obtain text content of the voice command;
[0015] An audio file is generated according to the text content of the voice instruction to obtain a virtual voice control instruction.
[0016] In one embodiment of the present invention, the testing method further includes: recording and saving the result of the vehicle system responding to the virtual voice control instruction as valid voice instruction text content.
[0017] In one embodiment of the present invention, the testing method further comprises: recording the played virtual voice control instructions, and verifying the accuracy of the played virtual voice control instructions according to the text content of the voice instructions.
[0018] In one embodiment of the present invention, the step of recording the played virtual voice control instruction and verifying the accuracy of the played virtual voice control instruction according to the text content of the voice instruction includes:
[0019] Record the virtual voice control instructions after playback;
[0020] Transcribing the virtual voice control instruction into text information;
[0021] The text information is compared with the expected text content of the voice command to verify the accuracy of the virtual voice control command.
[0022] The present invention also proposes a new energy vehicle voice function test system, comprising:
[0023] A data acquisition module is used to obtain the interactive interface information of the vehicle computer;
[0024] A virtual voice command generation module, used to generate a virtual voice control command according to the interactive interface information, and send the virtual voice control command to the speaker for playback;
[0025] A response information acquisition module, used to acquire an operation log corresponding to the operation performed by the vehicle system in response to the virtual voice control command, and interface change information after the operation performed by the vehicle system in response to the virtual voice control command;
[0026] The test result generating module is used to determine whether the result of the vehicle system responding to the virtual voice control instruction is valid according to the operation log and the interface change information to obtain the test result.
[0027] In one embodiment of the present invention, the virtual voice instruction generation module includes:
[0028] A playback text acquisition module, used to acquire the playback text according to the interactive interface information;
[0029] A voice command generation module, used for converting the play text into an audio file to obtain the virtual voice control command;
[0030] The output module is used to send the virtual voice control instruction to the speaker for playback.
[0031] In one embodiment of the present invention, the test result generation module is further used to record and save the result of the vehicle system responding to the virtual voice command as valid voice command text content, and feed it back to the playback text acquisition module.
[0032] The present invention also proposes a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the new energy vehicle voice function testing method as described in any one of the above embodiments are implemented.
[0033] The present invention proposes a new energy vehicle voice function testing method, system and equipment, which use image recognition and layer layout algorithms to automatically identify interactive elements of the user interface, which not only improves the degree of test automation, but also improves the accuracy and efficiency of the test process, and can also accurately simulate and test specific voice commands without human intervention, thereby improving test efficiency; and through logs and interface changes, it can more accurately judge the effectiveness of voice commands, while recording and saving valid voice commands during the test, and performing reinforcement learning based on these voice commands, so that it can continue to learn and optimize in a complex vehicle environment, thereby adapting to changing user behaviors and system updates, thereby ensuring that the system can more effectively process and optimize the recognition and response of voice commands, especially showing higher robustness when facing unknown commands or new interaction scenarios.
[0034] The present invention proposes a new energy vehicle voice function testing method, system and equipment. The high integration and automation capabilities of the system enable it to be seamlessly integrated into the on-board system of any new energy vehicle. This versatility and flexibility make it not only suitable for current vehicle models, but also easily adaptable to future technological upgrades and new vehicle models, thereby making the testing and optimization of the new energy vehicle menu more efficient, accurate and adaptable, thereby significantly improving the user experience and the overall performance of the system. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.
[0036] Figure 1 The figure is a flow chart of a method for testing the voice function of a new energy vehicle in one embodiment of the present invention.
[0037] Figure 2 The figure is a flow chart of generating a virtual voice control instruction in one embodiment of the present invention.
[0038] Figure 3 The figure is a flow chart of voice instruction accuracy verification in one embodiment of the present invention.
[0039] Figure 4 The figure is a structural block diagram of a new energy vehicle voice function test system in one embodiment of the present invention. DETAILED DESCRIPTION
[0040] The following describes the embodiments of the present invention through specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention.
[0041] It should be noted that the illustrations provided in this embodiment are only used to illustrate the basic concept of the present invention in a schematic manner. Therefore, the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.
[0042] See also Figure 1As shown, the present invention proposes a new energy vehicle voice function testing method, system and equipment, which, combined with an adaptive learning model, can effectively respond to rapid software iterations and diverse user operation scenarios, ensuring that no matter how the environment changes, the system can maintain efficient response and excellent performance, thereby improving the problem that existing testing methods are often complex, time-consuming and inefficient. Figure 1 The flowchart of the voice function test method of a new energy vehicle in the embodiment of the present application is shown. Specifically, the voice function test method of a new energy vehicle includes the following steps:
[0043] S1. Obtain the interactive interface information of the vehicle computer. In the present embodiment, the interactive interface information includes the layer information and display picture information of the vehicle computer system. For example, the test system is connected to the vehicle computer system through a test interface, so that the test system obtains the layer information and display picture information of the vehicle computer system through the test interface.
[0044] S2. Generate a virtual voice control command based on the interactive interface information and play it. Figure 2 As shown, Figure 2 The flowchart of generating a virtual voice control instruction in the embodiment of the present application is shown. The steps are as follows:
[0045] S21. Obtain the playback text based on the interactive interface information decision; for example, obtain the playback text through image recognition and layer layout analysis. Specifically, image recognition technology can be used to identify elements and text on the vehicle system interface, and a layer layout algorithm can be used to analyze the interface structure, automatically identifying the content-desc and text attributes of the interactive elements, thereby improving the degree of test automation and improving the accuracy and efficiency of the test process. By automatically analyzing the content-desc and text attributes of the interface elements, the system can accurately obtain the playback text corresponding to the voice command to be tested, thereby simulating and testing specific voice commands without human intervention.
[0046] Specifically, the step of determining and obtaining the playback text according to the interactive interface information includes:
[0047] The interactive interface information is processed to obtain text information; for example, the layer information and the display picture information may be processed by the above-mentioned image recognition and layer layout analysis technology to obtain text information.
[0048] Filter according to the text information, and make a decision based on the filtered text information to obtain the corresponding playback text; for example, filter the text information obtained through the layer information and the display image information, such as text preprocessing, keyword extraction, etc. to obtain the required text, and then make a decision based on the filtered text to obtain the corresponding playback text.
[0049] S22, converting the played text into an audio file to obtain the virtual voice control instruction; specifically comprising the following steps:
[0050] The playback text is processed to obtain the voice command text content; for example, the playback text can be processed by the language macro model to be expanded into a complete voice command text content. For example, the playback text determined in step S21 is "air conditioning". At this time, in this step, the playback text "air conditioning" is expanded into voice command text content such as "turn on the air conditioner" through the language macro model.
[0051] An audio file is generated according to the text content of the voice command to obtain a virtual voice control command; for example, the "turn on the air conditioner" expanded by the language model can be converted into a playable audio file through text-to-speech technology to obtain a virtual voice control command.
[0052] S23, sending the virtual voice control instruction to the speaker for playing; for example, the corresponding virtual voice control instruction can be played through an external player or a vehicle computer, the obtained playback text is expanded into a complete text instruction content, and then converted into an audio file and played to simulate the user's voice input.
[0053] S3. Obtain the operation log corresponding to the operation performed by the vehicle system in response to the virtual voice control instruction, and the interface change information after the vehicle system responds to the virtual voice control instruction; for example, when the vehicle system receives the virtual voice control instruction after the corresponding system plays, the vehicle system responds to the virtual voice control instruction and performs the operation to generate a corresponding operation log. At the same time, after the vehicle system responds to the virtual voice control instruction, its interface will also undergo corresponding changes, such as interface adjustments or pop-up windows. At this time, the test system can obtain the corresponding operation log and the interface change information of the vehicle system.
[0054] It can be understood that in this embodiment, the operation log includes a voice collection log and an input log. The voice collection log is a system that records all user voice commands and system voice feedback in real time to generate detailed voice logs. These logs contain voice recognition semantics and corresponding response voice output feedback. The input log is a system that records all device input events related to voice commands through the getevent tool, such as touch screen operations or other physical button operations. These logs help analyze the user's direct interaction after specific voice feedback to evaluate the user's acceptance of the system response and the convenience of operation.
[0055] S4. Determine whether the playback result of the virtual voice control instruction is valid according to the log and the interface change information to obtain a test result;
[0056] It is understandable that after the test system obtains the corresponding operation log and interface change information, it analyzes the log and interface change information to determine whether the virtual voice control instruction is a valid instruction and whether the interface is changed to the target interface corresponding to the virtual voice control instruction. For example, when the input virtual voice control instruction is "turn on the air conditioner", by analyzing the log and interface change information, for example, it can be found in the system log that is related to the voice playback instruction, which usually includes information such as the success or failure of voice recognition, the start of the playback task, the execution status (success / failure), and confirmation that the voice recognition module correctly understands the user's instructions. It is understandable that there should be a text record in the log indicating that the voice command was correctly transcribed.
[0057] It can also be understood that in this embodiment, the interface change information is also analyzed at the same time. For example, the system uses advanced image recognition technology to monitor the changes on the vehicle interface to ensure that the execution of each voice command can be correctly reflected on the interface. Dynamic elements on the interface, such as pop-up menus and warning messages, can be detected to verify the actual effect of the virtual voice control command. For example, the interface screenshots before and after the voice playback can be compared to confirm whether there are expected UI element changes. For example, if the virtual voice control command is "turn on the air conditioner", the air conditioner interface is detected to see if it appears as expected. If the virtual voice control command is "turn on the navigation", the navigation interface should be checked to see if it appears as expected. It is confirmed that any interactive elements related to the voice command (such as button activation status, progress bar changes) conform to the expected behavior, and it can also be checked whether the status message corresponding to the success or failure of the voice operation is displayed on the interface, such as "playing", "playing completed" or error prompts to confirm whether the playback result of the virtual voice control command is valid.
[0058] See also Figure 1As shown, in this embodiment, the test method also includes: recording and saving the result of the vehicle system responding to the virtual voice control command as valid voice command text content. In this embodiment, the system can perform self-learning based on the text information corresponding to the saved valid virtual voice control command. For example, the system can use a variety of reinforcement learning algorithms including Q-learning for reinforcement learning. Through the adaptive learning model, the system should be able to automatically collect usage data, analyze user behavior, and optimize the voice recognition algorithm and response mechanism accordingly, so that it can continue to learn and optimize in a complex vehicle environment, so as to adapt to the ever-changing user behavior and system updates, thereby ensuring that the system can more effectively process and optimize the recognition and response of voice commands, especially when facing unknown commands or new interaction scenarios, it shows higher robustness, and improves the overall performance of the system and user satisfaction.
[0059] See also Figure 3 As shown, Figure 3 The following is a flow chart of verifying the accuracy of voice commands in an embodiment of the present application. In order to ensure that the played audio is consistent with the expected virtual voice control command, it is necessary to compare the played audio with the text content of the voice command to verify their consistency, thereby ensuring the accuracy of the output audio. Therefore, in this embodiment, the test method includes: recording the played virtual voice control command, and verifying the accuracy of the played virtual voice control command based on the text content of the voice command. Specifically, it includes:
[0060] S101, recording the virtual voice control instruction after playing;
[0061] S102, transcribing the virtual voice control instruction into text information;
[0062] S103: Compare the text information with the expected text content of the voice command to verify the accuracy of the virtual voice control command.
[0063] It is understandable that the voice played by the system is recorded, transcribed by voice recognition technology, and compared with the expected playback text to verify the accuracy of the playback content. The played audio file can also be analyzed to check the volume, clarity, noise or distortion to ensure that the quality of the voice output meets the standard. In this embodiment, the system not only records the voice output, but also uses advanced voice analysis models to evaluate the rationality and accuracy of the voice output. Through machine learning algorithms, the system analyzes the consistency of the voice output with the expected instructions and determines its actual help to the user's operation, thereby optimizing the voice model.
[0064] See also Figure 4 As shown, Figure 4It is shown as a structural block diagram of the new energy vehicle voice function test system in the embodiment of the present application. In this embodiment, a new energy vehicle voice function test system is provided, and the new energy vehicle voice function test system corresponds to the new energy vehicle voice function test method in the above embodiment. Specifically, the new energy vehicle voice function test system 100 includes a data acquisition module 10, a virtual voice command generation module, a response information acquisition module 30, and a test result generation module 40. The functional modules are described in detail as follows:
[0065] The data acquisition module 10 is used to obtain the interactive interface information of the vehicle computer; the data acquisition module 10 is used to obtain the layer information and display image information of the vehicle computer system 200. For example, the data acquisition module 10 is used to obtain the test data source used for testing from the vehicle computer system 200 through the test interface, such as the layer information and display image information described in the above embodiments.
[0066] The virtual voice command generation module is used to generate a virtual voice control command according to the interactive interface information, and send the virtual voice control command to the speaker for playback; specifically, the virtual voice command generation module includes a playback text acquisition module 21, a voice command generation module 22 and an output module 23. The functional modules are described in detail as follows:
[0067] The playback text acquisition module 21 is used to make decisions on acquiring playback text based on the interactive interface information, and specifically includes a text acquisition module 211 and an enhanced learning module 212. The text acquisition module 211 is used to process the layer information and the display image information to acquire text information, and to filter the text information. For example, the corresponding text information can be acquired by using the image recognition technology described in the above embodiment to identify elements and text on the vehicle-mounted system interface, and using the layer layout algorithm to analyze the interface structure; the enhanced learning module 212 is used to make decisions based on the filtered text information to acquire the corresponding playback text.
[0068] The voice instruction generation module 22 is used to convert the playback text into an audio file to obtain the virtual voice control instruction. The voice instruction generation module 22 includes a language model module 221 and an audio generation module 222. The language model module 221 is used to process the playback text to obtain the voice instruction text content. For example, in the language model module 221, the playback text can be processed by the language model to expand it into a complete voice instruction text content; the audio generation module 222 is used to generate a corresponding audio file according to the voice instruction text content. For example, in the audio generation module 222, the voice instruction text content expanded by the language model is converted into a playable audio file through text-to-speech technology.
[0069] The output module 23 is used to send the virtual voice control command to the speaker for playing. For example, an external player or a speaker of the vehicle system 200 can be used as the output module 23 to play the audio file.
[0070] The response information acquisition module 30 is used to acquire the operation log corresponding to the operation performed by the vehicle system in response to the voice command, and the interface change information after the operation performed by the vehicle system in response to the voice command;
[0071] The test result generating module 40 is used to determine whether the result of the vehicle system responding to the virtual voice control instruction is valid according to the operation log and the interface change information to obtain the test result.
[0072] See also Figure 1 As shown, in this embodiment, the test result generation module 50 is also used to record and save the result of the vehicle system responding to the virtual voice control instruction as valid voice instruction text content, and feed it back to the playback text acquisition module 21, specifically to the reinforcement learning module 212 used to make decisions based on the filtered text information to obtain the corresponding playback text. The reinforcement learning module 212 can perform self-learning based on the text information corresponding to the saved valid voice instructions. For example, the reinforcement learning module 212 can use a variety of reinforcement learning algorithms including Q-learning for reinforcement learning. Through the adaptive learning model, the system should be able to automatically collect usage data, analyze user behavior, and optimize the voice recognition algorithm and response mechanism accordingly, so that it can continue to learn and optimize in a complex vehicle environment, thereby adapting to changing user behavior and system updates, thereby ensuring that the system can more effectively process and optimize the recognition and response of voice commands.
[0073] It can be understood that the test system 100 in the present application can be an independent test device, which is connected to the vehicle system through the test results. Of course, the test system can also be deployed in the cloud or inside the vehicle system, and connected to the vehicle system through hard wires, wireless or other means.
[0074] For the specific limitations of the new energy vehicle voice function test system, please refer to the limitations of the new energy vehicle voice function test method mentioned above, which will not be repeated here. Each module in the above-mentioned new energy vehicle voice function test system can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
[0075] See also Figure 1As shown, the present invention also proposes a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that when the processor executes the program, the steps of the new energy vehicle voice function test method described in the above embodiment are implemented, specifically implementing the following steps:
[0076] Get the interactive interface information of the vehicle computer;
[0077] Generate a virtual voice control instruction according to the interactive interface information, and send the virtual voice control instruction to the speaker for playback;
[0078] Acquire an operation log corresponding to the operation performed by the vehicle system in response to the virtual voice control command, and interface change information after the operation performed by the vehicle system in response to the virtual voice control command;
[0079] Whether the result of the vehicle system responding to the voice command is valid is determined according to the operation log and the interface change information to obtain a test result.
[0080] The memory may be, for example, a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory, or other suitable devices, or may be a solid-state memory, such as a read-only memory, a random access memory, or the like.
[0081] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.
[0082] The present invention proposes a new energy vehicle voice function testing method, system and equipment, which use image recognition and layer layout algorithms to automatically identify interactive elements of the user interface, which not only improves the degree of test automation, but also improves the accuracy and efficiency of the test process, and can also accurately simulate and test specific voice commands without human intervention, thereby improving test efficiency; and through logs and interface changes, it can more accurately judge the effectiveness of voice commands, while recording and saving valid voice commands during the test, and performing reinforcement learning based on these voice commands, so that it can continue to learn and optimize in a complex vehicle environment, thereby adapting to changing user behaviors and system updates, thereby ensuring that the system can more effectively process and optimize the recognition and response of voice commands, especially showing higher robustness when facing unknown commands or new interaction scenarios.
[0083] The present invention proposes a new energy vehicle voice function testing method, system and equipment. The high integration and automation capabilities of the system enable it to be seamlessly integrated into the on-board system of any new energy vehicle. This versatility and flexibility make it not only suitable for current vehicle models, but also easily adaptable to future technological upgrades and new vehicle models, thereby making the testing and optimization of the new energy vehicle menu more efficient, accurate and adaptable, thereby significantly improving the user experience and the overall performance of the system.
[0084] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.
[0085] Except for the technical features described in the specification, the remaining technical features are known technologies to those skilled in the art. In order to highlight the innovative features of the present invention, the remaining technical features will not be described here in detail.
Claims
1. A method for testing the voice function of a new energy vehicle, characterized in that: include: Get the interactive interface information of the vehicle computer; Generate a virtual voice control command according to the interactive interface information and play it; which includes: Processing the interactive interface information through image recognition and layer layout algorithms to obtain text information; Filtering according to the text information, and making a decision based on the filtered text information to obtain the corresponding playback text; Convert the played text into an audio file to obtain the virtual voice control instruction; Sending the virtual voice control command to a speaker for playing; Acquire an operation log corresponding to the operation performed by the vehicle system in response to the virtual voice control command, and interface change information after the operation performed by the vehicle system in response to the virtual voice control command; Determine whether the result of the vehicle system responding to the virtual voice control command is valid according to the operation log and the interface change information to obtain a test result; Among them, the result of the vehicle system responding to the virtual voice control instruction is recorded and saved as valid voice instruction text content based on the test result, and provided to the adaptive learning model, and the voice instruction text content is used to obtain the corresponding virtual voice control instruction.
2. The new energy vehicle voice function testing method according to claim 1, characterized in that: The step of converting the played text into an audio file to obtain the virtual voice control instruction comprises: Processing the played text to obtain text content of the voice command; An audio file is generated according to the text content of the voice instruction to obtain a virtual voice control instruction.
3. The new energy vehicle voice function testing method according to claim 2, characterized in that: The testing method further includes: recording the played virtual voice control instructions, and verifying the accuracy of the played virtual voice control instructions according to the text content of the voice instructions.
4. The new energy vehicle voice function testing method according to claim 3 is characterized in that: The step of recording the played virtual voice control instruction and verifying the accuracy of the played virtual voice control instruction according to the text content of the voice instruction includes: Record the virtual voice control instructions after playback; Transcribing the virtual voice control instruction into text information; The text information is compared with the expected text content of the voice command to verify the accuracy of the virtual voice control command.
5. A new energy vehicle voice function test system, characterized in that: include: A data acquisition module is used to obtain the interactive interface information of the vehicle computer; A virtual voice command generation module, used to generate and play virtual voice control commands according to the interactive interface information; The virtual voice command generation module includes: A playback text acquisition module, used to process the interactive interface information through image recognition and layer layout algorithm to obtain text information, and to filter according to the text information, and to make a decision according to the filtered text information to obtain the corresponding playback text; A voice command generation module, used for converting the play text into an audio file to obtain the virtual voice control command; An output module, used for sending the virtual voice control instruction to a speaker for playing; A response information acquisition module, used to acquire an operation log corresponding to the operation performed by the vehicle system in response to the virtual voice control command, and interface change information after the operation performed by the vehicle system in response to the virtual voice control command; The test result generating module is used to determine whether the result of the vehicle system responding to the virtual voice control instruction is valid according to the operation log and the interface change information to obtain the test result.
6. The new energy vehicle voice function test system according to claim 5, characterized in that: The test result generation module is also used to record and save the result of the vehicle system responding to the virtual voice control command as valid voice command text content, and feed it back to the playback text acquisition module.
7. A computer device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the new energy vehicle voice function testing method as described in any one of claims 1 to 4 when executing the program.
