Vehicle-mounted voice interaction test method, device and equipment, storage medium and vehicle

Abstract

The embodiment of the invention provides a vehicle-mounted voice interaction test method and device, equipment, a storage medium and a vehicle, and the method comprises the steps: replying a reply language corresponding to a received first test voice through a preset vehicle-mounted voice large model under the condition that a current test is detected to be a question and answer reply function test; and when it is detected that the current test is a multi-intention execution type function test, analyzing semantics corresponding to received second test voice through a preset vehicle-mounted voice large model, determining whether the semantics is multi-intention semantics, and if yes, monitoring an execution result of a multi-intention instruction contained in the second test voice. According to the embodiment of the invention, question and answer reply type and multi-intention execution type function tests can be efficiently and accurately processed, semantics are automatically analyzed, the execution result of a multi-intention instruction is monitored, the test efficiency, accuracy and automation level are remarkably improved, and powerful support is provided for development and optimization of a vehicle-mounted voice interaction system.

Description

Technical Field

[0001] The present invention relates to the field of vehicle testing technology, and in particular to an in-vehicle voice interaction testing method, device, equipment, storage medium and vehicle. Background Art

[0002] As smart cars have more and more functions, the vehicle cockpit is becoming more and more simple, so in-vehicle voice will take on more and more important responsibilities for human-computer interaction. In recent years, many automobile manufacturers have applied AI big models to in-vehicle voice to make it more intelligent, improve the efficiency of human-computer interaction, reduce user learning costs, and improve user experience. This type of in-vehicle voice big model has significant changes in functional test points and test methods compared to conventional in-vehicle voice and ordinary text big models.

[0003] The testing methods for in-vehicle voice in related technologies basically do not cover voice systems with large model capabilities, resulting in the inability to test voice interactions in vehicle intelligence. Summary of the invention

[0004] The object of the present invention is to provide a vehicle-mounted voice interaction test method. In order to achieve the above object, the present invention discloses a vehicle-mounted voice interaction test method, the method comprising:

[0005] When it is detected that the current test is a question-answer reply function test, replying a reply corresponding to the received first test voice through a preset in-vehicle voice model;

[0006] When it is detected that the current test is a multi-intent execution function test, the semantics corresponding to the received second test voice is analyzed by a pre-set in-vehicle voice model to determine whether the semantics are multi-intent semantics. If so, the execution results of the multi-intent instructions contained in the second test voice are monitored.

[0007] Optionally, the reply language corresponding to the first test voice received by replying through the preset in-vehicle voice large model includes:

[0008] Receive the preset corpus text to be tested;

[0009] Broadcasting a first test speech corresponding to the corpus text to be tested through an artificial mouth;

[0010] The first test voice is recognized by a preset in-vehicle voice model, and a reply language corresponding to the first test voice is broadcast.

[0011] Optionally, after the step of replying a reply word corresponding to the received first test voice through a preset in-vehicle voice large model, the method includes:

[0012] Output the corpus text corresponding to the first test voice and a first test table composed of the reply language, and export the test log generated during the question-answer reply function test.

[0013] Optionally, the first test table includes time information corresponding to the corpus text and the reply language. After the steps of outputting the first test table consisting of the corpus text corresponding to the first test voice and the reply language, and exporting the test log generated during the question-answer reply function test, the method includes:

[0014] Locating target log information in the test log according to the time information in the first test table;

[0015] Perform test analysis based on the log information.

[0016] Optionally, monitoring the execution result of the multi-intention instruction included in the second test voice includes:

[0017] In case of detecting that the multi-intention instructions include a vehicle control instruction, monitoring a communication signal of the test vehicle;

[0018] The execution result of the vehicle control instruction is determined according to the communication signal.

[0019] Optionally, monitoring the execution result of the multi-intention instruction included in the second test voice includes:

[0020] When it is detected that the multi-intention instructions include an application control instruction, it is determined whether the iconic UI picture and text of the EDC match to determine the execution result of the application control instruction.

[0021] The embodiment of the present invention further discloses a vehicle-mounted voice interaction test device, the device comprising:

[0022] The first test module is used to reply a reply corresponding to the received first test voice through a preset in-vehicle voice model when detecting that the current test is a question-answer reply type function test;

[0023] The second test module is used to analyze the semantics corresponding to the received second test voice through a pre-set vehicle-mounted voice model when it is detected that the current test is a multi-intention execution function test, to determine whether the semantics are multi-intention semantics, and if so, to monitor the execution results of the multi-intention instructions contained in the second test voice.

[0024] An embodiment of the present invention further discloses an electronic device, comprising at least one processor and a memory communicatively connected to the at least one processor;

[0025] The memory is used to store computer programs;

[0026] The processor is used to implement the method described in the embodiment of the present invention when executing the program stored in the memory.

[0027] The embodiment of the present invention further discloses a computer-readable storage medium on which a computer program is stored. When executed by one or more processors, the processors are enabled to execute the method described in the embodiment of the present invention.

[0028] Beneficial effects of the present invention:

[0029] The present application provides a vehicle-mounted voice interaction test method, device, equipment and storage medium. When it is detected that the current test is a question-answer reply type functional test, the reply corresponding to the received first test voice is replied through a pre-set vehicle-mounted voice large model; when it is detected that the current test is a multi-intention execution type functional test, the semantics corresponding to the received second test voice is analyzed through a pre-set vehicle-mounted voice large model to determine whether the semantics are multi-intention semantics. If so, the execution results of the multi-intention instructions contained in the second test voice are monitored. The vehicle-mounted voice interaction test method, device, equipment and storage medium provided by the embodiments of the present invention can efficiently and accurately process question-answer reply type and multi-intention execution type functional tests through a pre-set vehicle-mounted voice large model, automatically analyze semantics and monitor the execution results of multi-intention instructions, significantly improve the test efficiency, accuracy and automation level, and provide strong support for the development and optimization of vehicle-mounted voice interaction systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A flowchart of a vehicle voice interaction testing method provided in an embodiment of the present invention;

[0031] Figure 2 A device block diagram of a vehicle-mounted voice interaction test device provided in an embodiment of the present invention;

[0032] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present invention;

[0033] Figure 4 A schematic diagram of a test system in a vehicle-mounted voice interaction test provided in an embodiment of the present invention;

[0034] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0036] In order to more clearly describe the content of the present invention, the present invention will be further explained below in conjunction with the drawings in the present application.

[0037] Reference Figure 1 , Figure 1 This is a flow chart of the steps of a vehicle voice interaction test method provided in an embodiment of the present invention. The method may include:

[0038] Step 101, when it is detected that the current test is a question-answer reply type function test, replying to a reply corresponding to the received first test voice through a preset in-vehicle voice large model;

[0039] It should be noted that in the embodiment of the present application, the test difficulty of the large model is that the reply language is not fixed, the interactivity is strong, and the support corpus is large. Therefore, the present application can be applied to a test system. Specifically, the test system can refer to Figure 4 As shown, module 301: corpus input module, this module has the ability to recognize text corpus input, and can broadcast the corpus to the vehicle EDC through an artificial mouth, module 304: reply recording and recognition module, this module can save the TTS broadcast reply recording of EDC, and recognize and convert it into text records. Module 306: data monitoring and acquisition module, this module mainly relies on the collected CAN signals and Ethernet services, analyzes and monitors the communication signals of the vehicle, determines whether the voice command is executed successfully, and saves the data for subsequent analysis. Module 303: table sorting and output module, this module is the system input information from the previous modules, collects and organizes the information, converts it into table text and outputs it to the test engineer for subsequent analysis and troubleshooting. Using these results is also of certain significance to the development and training of large vehicle models.

[0040] Therefore, in the embodiment of the present application, the test process is divided into three parts: corpus input, TTS broadcast reply, and function execution for control and corresponding arrangement, so as to improve the test efficiency and facilitate automated operation.

[0041] For the corpus input in the first part, in order to simulate the real car user environment and be closer to the problems that users will encounter when actually using voice, an artificial mouth is used to broadcast the corpus input, which can test software recognition problems.

[0042] Furthermore, the reply language corresponding to the first test voice received by replying to the preset in-vehicle voice model includes:

[0043] Receive the preset corpus text to be tested;

[0044] Broadcasting a first test speech corresponding to the corpus text to be tested through an artificial mouth;

[0045] The first test voice is recognized by a preset in-vehicle voice model, and a reply language corresponding to the first test voice is broadcast.

[0046] It should be noted that in the embodiment of the present application, the designed corpus text is first input into the test system. After receiving the input corpus, the test system broadcasts it to the microphone of the EDC through the artificial mouth. This process can verify whether the speech recognition ability of the EDC is qualified. After the EDC recognizes the corpus, the reply TTS is broadcast through the large in-vehicle voice model. The test system saves the recording of the reply broadcast by TTS, recognizes the semantics of the reply, and converts it into text.

[0047] Further, after the step of replying a reply word corresponding to the received first test voice through the preset in-vehicle voice model, the method includes:

[0048] Output the corpus text corresponding to the first test voice and a first test table composed of the reply language, and export the test log generated during the question-answer reply function test.

[0049] Further, the first test table includes time information corresponding to the corpus text and the reply language. After the steps of outputting the first test table composed of the corpus text corresponding to the first test voice and the reply language, and exporting the test log generated during the question-answer reply function test, the method includes:

[0050] Locating target log information in the test log according to the time information in the first test table;

[0051] Perform test analysis based on the log information.

[0052] It should be noted that the test system organizes the input corpus and the corresponding broadcast response words in the test into a table output, and exports the logs during the test process for subsequent test engineers to analyze problems. For the output table, in addition to recording the corpus and the corresponding response words, the specific time of the corpus and the response words should also be recorded, so as to find the corresponding log data for further analysis after discovering the problem.

[0053] Specifically, for question-and-answer reply functions, since the reply language of the large model does not have a strict correspondence with the corpus, it is impossible to simply judge right or wrong. Therefore, after the test system is completed, the corpus and reply language of each execution will be organized into a one-to-one corresponding text table and output to the test engineer for judgment. The standard for judging the rationality can be measured from three dimensions: whether it is the pre-set shielding content and whether the reply language is correct.

[0054] Step 102, when it is detected that the current test is a multi-intent execution type functional test, the semantics corresponding to the received second test voice is analyzed by a pre-set vehicle-mounted voice large model to determine whether the semantics are multi-intent semantics. If so, the execution results of the multi-intent instructions contained in the second test voice are monitored.

[0055] Further, the monitoring of the execution result of the multi-intention instruction included in the second test voice includes:

[0056] In case of detecting that the multi-intention instructions include a vehicle control instruction, monitoring a communication signal of the test vehicle;

[0057] The execution result of the vehicle control instruction is determined according to the communication signal.

[0058] Further, the monitoring of the execution result of the multi-intention instruction included in the second test voice includes:

[0059] When it is detected that the multi-intention instructions include an application control instruction, it is determined whether the iconic UI picture and text of the EDC match to determine the execution result of the application control instruction.

[0060] It should be noted that in the embodiment of the present application, for the multi-intent execution type function test, the overall test process is similar to the question-and-answer response type function test method. The main difference is that the multi-intent function has a function execution end, and its execution result needs to be monitored, that is, the execution result of the multi-intent instructions contained in the second test voice needs to be monitored.

[0061] Specifically, if you want to monitor whether the execution result of an instruction is successful, you must first determine whether the instruction is a vehicle control instruction with an executable component or an application control instruction that only acts on EDC. Vehicle control instructions need to monitor the vehicle's communication signals, namely CAN signals and Ethernet service signals, to determine the execution result. Application control instructions only need to determine whether the EDC's iconic UI picture and text match.

[0062] For example, for monitoring the results of function execution, if it is a function that involves the participation of physical parts, it is necessary to use the communication method between EDC (vehicle computer) and VIU (vehicle intelligent unit) to monitor whether the semantic execution information matches the execution signal sent and collected by the vehicle computer. For Ethernet communication, monitor whether the GET, RR, SET method signals sent by EDC match the NTF method signals replied by VIU, and whether the signal values ​​are correct; if it is a function without physical parts, such as navigation and music modules, it can be compared based on the iconic information of the UI interface on the screen to determine whether the execution is successful, such as the text and color at a certain coordinate position on the screen. Usually, instructions that need to control physical controls will also cause changes in the corresponding switches on the UI interface, so both signal changes and UI changes need to be monitored.

[0063] Furthermore, similarly, multi-intent execution function tests will also record data output results. Compared with question-and-answer response functions, the test system needs to add function execution results to the output table of multi-intent functions and record the vehicle's communication message data for subsequent problem analysis and troubleshooting.

[0064] The present application provides a vehicle-mounted voice interaction test method. When it is detected that the current test is a question-answer reply type functional test, a reply corresponding to the received first test voice is replied through a pre-set vehicle-mounted voice large model; when it is detected that the current test is a multi-intention execution type functional test, the semantics corresponding to the received second test voice is analyzed through a pre-set vehicle-mounted voice large model to determine whether the semantics are multi-intention semantics, and if so, the execution results of the multi-intention instructions contained in the second test voice are monitored. The vehicle-mounted voice interaction test method, device, equipment and storage medium provided by the embodiments of the present invention can efficiently and accurately process question-answer reply type and multi-intention execution type functional tests through a pre-set vehicle-mounted voice large model, automatically analyze semantics and monitor the execution results of multi-intention instructions, significantly improving the test efficiency, accuracy and automation level, and providing strong support for the development and optimization of vehicle-mounted voice interaction systems.

[0065] In addition, refer to Figure 5 ,like Figure 5The figure shows the structure diagram of the test points for the vehicle-mounted speech model function. Module 405: The vehicle-mounted speech model can be divided into two major functional categories. One function is module 401: question-answer response category, and its main test point is module 402: response output; the other function is module 404: multi-intention instruction category, and its main test point is module 403: function execution. Module 402 response output, the main test points are concentrated on the three sections of the bottom-line response to politically sensitive content, the bottom-line response to pornographic and violent content, and the naturalness and accuracy of the response. Therefore, the design of the test corpus should also be carried out around these three sections. Test corpora are designed for politically sensitive content, pornographic and violent content, and continuous daily conversation content, and the output response is used to judge whether the response is natural and accurate. Module 403 function execution, the main test points are the number of speech control intentions, such as three-intention speech control, five-intention speech control; cross-module intent speech control, such as navigation control, music control, and body control, mainly for different intention numbers and cross-module intent speech control Whether can be successfully executed, test whether its success rate meets the indicators.

[0066] Reference Figure 2 , Figure 2 This is a device block diagram of a vehicle-mounted voice interaction test device provided in an embodiment of the present invention. The method may include:

[0067] The first test module 201 is used to reply to the reply language corresponding to the received first test voice through a preset in-vehicle voice model when detecting that the current test is a question-answer reply type function test;

[0068] The second test module 202 is used to analyze the semantics corresponding to the received second test voice through a preset vehicle-mounted voice model when it is detected that the current test is a multi-intention execution type functional test, to determine whether the semantics are multi-intention semantics, and if so, to monitor the execution results of the multi-intention instructions contained in the second test voice.

[0069] The present application provides an in-vehicle voice interaction test device. When it is detected that the current test is a question-answer reply type functional test, the reply corresponding to the received first test voice is replied through a pre-set in-vehicle voice large model; when it is detected that the current test is a multi-intention execution type functional test, the semantics corresponding to the received second test voice is analyzed through a pre-set in-vehicle voice large model to determine whether the semantics are multi-intention semantics, and if so, the execution results of the multi-intention instructions contained in the second test voice are monitored. The in-vehicle voice interaction test method, device, equipment and storage medium provided by the embodiments of the present invention can efficiently and accurately process question-answer reply and multi-intention execution type functional tests through a pre-set in-vehicle voice large model, automatically analyze semantics and monitor the execution results of multi-intention instructions, significantly improving the test efficiency, accuracy and automation level, and providing strong support for the development and optimization of in-vehicle voice interaction systems.

[0070] The embodiment of the present invention further provides an electronic device, such as Figure 3 As shown, it includes a processor 501, a device interface 502, a memory 503 and a bus 504;

[0071] Memory 503, used for storing computer programs;

[0072] The processor 501 is used to execute the program stored in the memory 503, and implements the following steps:

[0073] When it is detected that the current test is a question-answer reply function test, replying a reply corresponding to the received first test voice through a preset in-vehicle voice model;

[0074] When it is detected that the current test is a multi-intent execution function test, the semantics corresponding to the received second test voice is analyzed by a pre-set in-vehicle voice model to determine whether the semantics are multi-intent semantics. If so, the execution results of the multi-intent instructions contained in the second test voice are monitored.

[0075] The bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0076] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0077] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0078] The present invention also provides a storage medium, which, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute the in-vehicle voice interaction test method of the aforementioned embodiment.

[0079] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0080] The algorithm and display provided herein are not inherently related to any particular computer, virtual device or other equipment. According to the above description, it is obvious that the structure required for constructing this type of device is. In addition, the present invention is not directed to any specific programming language. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific language is to disclose the best mode of the present invention.

[0081] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0082] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: that the claimed invention requires more features than those expressly recited in each claim. Rather, as reflected in the claims below, inventive aspects lie in less than all of the features of the individual embodiments disclosed above. Therefore, the claims that follow the detailed description are hereby expressly incorporated into the detailed description, with each claim itself serving as a separate embodiment of the present invention.

[0083] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0084] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the sorting device according to the present invention. The present invention may also be implemented as a device or apparatus program for executing part or all of the methods described herein. Such a program for implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0085] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

[0086] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices, apparatuses and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0087] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0088] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0089] It should be noted that the various data-related processes in the embodiments of the present application are all carried out in compliance with the corresponding data protection laws and policies of the country where the device is located, and with the authorization given by the owner of the corresponding device.

Claims

1. A vehicle-mounted voice interaction testing method, characterized in that: The method comprises: When it is detected that the current test is a question-answer reply function test, replying a reply corresponding to the received first test voice through a preset in-vehicle voice model; When it is detected that the current test is a multi-intent execution function test, the semantics corresponding to the received second test voice is analyzed by a pre-set in-vehicle voice model to determine whether the semantics are multi-intent semantics. If so, the execution results of the multi-intent instructions contained in the second test voice are monitored.

2. The method according to claim 1, characterized in that The reply language corresponding to the first test voice received by replying to the preset vehicle-mounted voice model includes: Receive the preset corpus text to be tested; Broadcasting a first test speech corresponding to the corpus text to be tested through an artificial mouth; The first test voice is recognized by a preset in-vehicle voice model, and a reply language corresponding to the first test voice is broadcast.

3. The method according to claim 1, characterized in that After the step of replying the reply language corresponding to the received first test voice through the preset in-vehicle voice model, the method includes: Output the corpus text corresponding to the first test voice and a first test table composed of the reply language, and export the test log generated during the question-answer reply function test.

4. The method according to claim 3, characterized in that The first test table includes the time information corresponding to the corpus text and the reply language. After the steps of outputting the first test table composed of the corpus text corresponding to the first test voice and the reply language, and exporting the test log generated during the question-answer reply function test, the method includes: Locating target log information in the test log according to the time information in the first test table; Perform test analysis based on the log information.

5. The method according to claim 1, characterized in that The monitoring of the execution result of the multi-intention instruction included in the second test voice includes: In case of detecting that the multi-intention instructions include a vehicle control instruction, monitoring a communication signal of the test vehicle; The execution result of the vehicle control instruction is determined according to the communication signal.

6. The method according to claim 1, characterized in that The monitoring of the execution result of the multi-intention instruction included in the second test voice includes: When it is detected that the multi-intention instructions include an application control instruction, it is determined whether the iconic UI picture and text of the EDC match to determine the execution result of the application control instruction.

7. A vehicle-mounted voice interaction test device, characterized in that: The device comprises: The first test module is used to reply a reply corresponding to the received first test voice through a preset in-vehicle voice model when detecting that the current test is a question-answer reply type function test; The second test module is used to analyze the semantics corresponding to the received second test voice through a pre-set vehicle-mounted voice model when it is detected that the current test is a multi-intention execution function test, to determine whether the semantics are multi-intention semantics, and if so, to monitor the execution results of the multi-intention instructions contained in the second test voice.

8. An electronic device, characterized in that: include: at least one processor; a memory communicatively coupled to the at least one processor; The memory has a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the in-vehicle voice interaction testing method described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the in-vehicle voice interaction testing method described in any one of claims 1 to 6 is implemented.

10. A vehicle, characterized in that: The vehicle includes the in-vehicle voice interaction testing device according to claim 6.

Images