Vehicle test method and device, test equipment and storage medium

Abstract

The invention is suitable for the technical field of automobiles, and provides a vehicle test method and device, test equipment and a storage medium, and the method comprises the steps: obtaining a test scene and an expected test result corresponding to a to-be-tested function when a test request for the to-be-tested function of a vehicle is detected; determining a test verification strategy according to the expected test result; testing the to-be-tested function in the test scene to obtain actual test data; verifying the actual test data according to the test verification strategy and the expected test result to obtain a verification result; and if the verification result is that the verification is passed, determining that the to-be-tested function test is passed. Compared with the prior art, the method not only can flexibly determine test scenes of different to-be-tested functions, but also can flexibly determine the verification strategy of the data obtained by the actual test according to the expected test result of the to-be-tested functions, and verifies the data according to the verification strategy to determine whether the to-be-tested functions pass the test or not. And the test accuracy of the vehicle function is improved.

Description

Technical Field

[0001] The present application belongs to the field of automobile technology, and in particular, relates to a vehicle testing method, device, testing equipment and storage medium. Background Art

[0002] Currently, when developing intelligent driving functions for cars, major companies not only conduct simulation tests, but also carry out a large number of real-vehicle tests to verify whether the functional logic meets development requirements and ensure that the performance meets customer satisfaction requirements.

[0003] However, existing real vehicle testing methods usually conduct real vehicle testing on various functions of the vehicle under fixed test conditions (such as visual sensor pollution conditions and rainy conditions). This is not comprehensive enough and cannot accurately test various functions of the vehicle, thereby reducing the accuracy of testing vehicle functions. Summary of the invention

[0004] The embodiments of the present application provide a vehicle testing method, apparatus, testing equipment and storage medium, which improve the testing accuracy of vehicle functions.

[0005] In a first aspect, an embodiment of the present application provides a vehicle testing method, comprising:

[0006] When a test request for a function to be tested of the vehicle is detected, obtaining a test scenario and an expected test result corresponding to the function to be tested;

[0007] Determine a test verification strategy based on the expected test results;

[0008] Testing the function to be tested under the test scenario to obtain actual test data;

[0009] Verifying the actual test data according to the test verification strategy and the expected test result to obtain a verification result;

[0010] If the verification result is that the verification is passed, it is determined that the function to be tested has passed the test.

[0011] Optionally, testing the function to be tested in the test scenario to obtain actual test data includes:

[0012] When it is detected that the vehicle is traveling in the test scenario, obtaining motion information generated by the vehicle during the traveling process;

[0013] Detecting the validity of the motion information to obtain a detection result;

[0014] If the detection result is that the motion information is valid, the motion information is determined as the actual test data.

[0015] Optionally, the detecting the validity of the motion information to obtain a detection result includes:

[0016] When the type of the motion information is a type that changes with time, traversing and calculating the change amplitude between data of any two adjacent time points in the motion information;

[0017] If the variation is a specified value, determining that the detection result is that the motion information is invalid;

[0018] If the change amplitude is not the specified value, the detection result is determined to be that the motion information is valid.

[0019] Optionally, determining a test verification strategy according to the expected test result includes:

[0020] Detecting the data type of the test indicator included in the expected test result;

[0021] If the data type is a numerical type, determining that the test verification strategy is a numerical comparison strategy;

[0022] Correspondingly, the actual test data is verified according to the test verification strategy and the expected test result to obtain the verification result, including:

[0023] Based on the numerical comparison strategy, the test index included in the actual test data is compared with the test index included in the expected test result to obtain the verification result.

[0024] Optionally, determining a test verification strategy according to the expected test result includes:

[0025] Detecting the data type of the test indicator included in the expected test result;

[0026] If the data type is a non-numeric type, determining that the test verification strategy is a model verification strategy;

[0027] Correspondingly, the actual test data is verified according to the test verification strategy and the expected test result to obtain the verification result, including:

[0028] Based on the model verification strategy, the actual test data is input into the trained test indicator evaluation model for processing to obtain the test indicator corresponding to the actual test data; wherein the test indicator evaluation model is used to complete the evaluation of non-numerical test indicators according to the input test data;

[0029] The test indicator corresponding to the actual test data is compared with the test indicator included in the expected test result to obtain the verification result.

[0030] Optionally, the test indicator evaluation model is trained in the following manner:

[0031] Acquire training sample data; wherein the training sample data includes historical driving data corresponding to the historical driving process of the sample vehicle under different scenario parameters, and non-numerical historical test indicators corresponding to the historical driving data, wherein the historical test indicators are determined according to driving experience information entered by the user of the sample vehicle for the historical driving process;

[0032] The training of the neural network model is completed based on the training sample data to obtain the test index evaluation model.

[0033] Optionally, the different scene parameters are determined in the following manner:

[0034] Acquire historical scene information of the sample vehicle during the historical driving process;

[0035] The historical environment information is clustered, and the different scene parameters are determined according to the result of the clustering process.

[0036] In a second aspect, an embodiment of the present application provides a vehicle testing device, comprising:

[0037] A first acquisition unit, configured to, when a test request for a function to be tested of a vehicle is detected, acquire a test scenario and an expected test result corresponding to the function to be tested;

[0038] A first determining unit, configured to determine a test verification strategy according to the expected test result;

[0039] A testing unit, used to test the function to be tested under the test scenario to obtain actual test data;

[0040] A first verification unit, configured to verify the actual test data according to the test verification strategy and the expected test result to obtain a verification result;

[0041] The second determining unit is used to determine that the function to be tested has passed the test if the verification result is verification passed.

[0042] In a third aspect, an embodiment of the present application provides a testing 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 computer program, a vehicle testing method as described in any one of the first aspects above is implemented.

[0043] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the vehicle testing method as described in any one of the above-mentioned first aspects is implemented.

[0044] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on a test device, enables the test device to execute the vehicle test method described in any one of the first aspects above.

[0045] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0046] A vehicle testing method provided by an embodiment of the present application can, when a test request for a function to be tested of a vehicle is detected, determine a test verification strategy based on the expected test result corresponding to the function to be tested; and test the function to be tested in the test scenario corresponding to the function to be tested to obtain actual test data; then verify the actual test data based on the test verification strategy and the expected test result to obtain a verification result; finally, when it is detected that the verification result is a passed verification, it can be determined that the function to be tested has passed the test. Compared with the prior art that only tests a certain function of the vehicle in a fixed test scenario, the present method can not only flexibly determine the test scenarios for different functions to be tested, but also flexibly determine the verification strategy for the data obtained from the actual test based on the expected test result of the function to be tested, and verify the data with the verification strategy to determine whether the function to be tested has passed the test, thereby improving the accuracy of the vehicle function test. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 is a flow chart of an implementation of a vehicle testing method provided in an embodiment of the present application;

[0049] Figure 2 is a flow chart of an implementation of a vehicle testing method provided by another embodiment of the present application;

[0050] Figure 3 is a flow chart of an implementation of a vehicle testing method provided in yet another embodiment of the present application;

[0051] Figure 4 is a flow chart of an implementation of a vehicle testing method provided by another embodiment of the present application;

[0052] Figure 5 is a flow chart of an implementation of a vehicle testing method provided by another embodiment of the present application;

[0053] Figure 6 is a structural schematic diagram of a vehicle testing device provided in one embodiment of the present application;

[0054] Figure 7 It is a structural schematic diagram of a testing device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0055] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0056] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0057] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0058] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0059] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0060] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0061] See also Figure 1 , Figure 1 This is a flow chart of a vehicle testing method provided in an embodiment of the present application. In the embodiment of the present application, the vehicle testing method is performed by a testing device, which may be a vector device, an industrial computer, a display, or other devices.

[0062] like Figure 1 As shown, the vehicle testing method provided in one embodiment of the present application may include S101 to S105, which are described in detail as follows:

[0063] In S101, when a test request for a function to be tested of a vehicle is detected, a test scenario and an expected test result corresponding to the function to be tested are obtained.

[0064] In actual applications, developers need to conduct a large number of real-vehicle tests during the development of the vehicle's intelligent driving / autonomous driving functions to verify whether the above-mentioned functional logic meets the development requirements and ensure that the performance meets customer satisfaction requirements. Based on this, in order to clarify whether the vehicle's functions to be tested meet the requirements, developers can wirelessly connect the vehicle's on-board terminal to the test equipment (i.e., realize the communication connection between the vehicle and the test equipment) before conducting real-vehicle tests on the vehicle, so as to enable the test equipment to detect any function to be tested of the vehicle.

[0065] In an embodiment of the present application, when a developer needs to perform a real vehicle test on a certain function of a vehicle, a test request for a certain function to be tested in the vehicle can be sent to a test device.

[0066] In one embodiment of the present application, when the vehicle includes multiple functions to be tested, in order to clarify the function to be tested this time and improve the test accuracy, each function to be tested may be provided with an identification corresponding to the function to be tested, wherein the identification may be a digital serial number.

[0067] Therefore, in this embodiment, the test request for the function to be tested of the vehicle obtained by the test device may carry the identifier of the function to be tested.

[0068] In an embodiment of the present application, the test device pre-stores the test scenarios and expected test results corresponding to different functions to be tested. Based on this, when the test device detects the above-mentioned test request for a certain function to be tested, it can obtain the test scenario and expected test result corresponding to the function to be tested.

[0069] It should be noted that the test scenario is used to characterize the environment information of the vehicle and the vehicle information of the vehicle when the function to be tested is tested.

[0070] Environmental information includes, but is not limited to: static environmental elements, dynamic environmental elements, traffic participant elements, meteorological elements, etc. Among them, static environmental elements refer to objects in the vehicle's environment that are in a stationary state, such as roads, traffic facilities, surrounding landscapes, and obstacles. Dynamic environmental elements refer to elements in the vehicle's environment that are in dynamic change, such as dynamic indicator facilities and communication environment information. Traffic participant elements refer to object information that affects vehicle decision-making and planning in the test scene corresponding to the function to be tested, such as other vehicles, pedestrians, and animals. Meteorological elements refer to information such as ambient temperature, lighting conditions, and weather conditions in the test scene corresponding to the function to be tested.

[0071] Vehicle information refers to the basic attributes, location information, motion status information and driving task information of the vehicle when testing the function to be tested.

[0072] In S102, a test verification strategy is determined according to the expected test result.

[0073] In actual applications, the types of test indicators corresponding to different functions to be tested are not the same. For example, the test indicators may be: when conducting a real vehicle test on a certain function to be tested, the vehicle's lateral control requires that the straight road deviation does not exceed 0.1cm, the curve deviation does not exceed 0.2cm, and other test requirements with specific values; the test indicators may also be: when conducting a real vehicle test on a certain function to be tested, the requirement for the vehicle during braking is that the braking is smooth, without any abruptness, etc., which do not have specific values, but are test requirements for evaluating the driving experience.

[0074] Based on this, in the embodiment of the present application, according to the specific content included in the expected test result, it can be determined that the data type of the test indicator included in the expected test result includes but is not limited to: numerical type and non-numerical type. Among them, the numerical type refers to the type in which the specific content of the test indicator contains a specific numerical value, and the non-numerical type refers to the type in which the specific content of the test indicator does not contain a specific numerical value.

[0075] After determining the data type of the test indicators included in the expected test results, the test equipment can determine the test verification strategy based on the data type. The test verification strategy refers to a strategy for verifying the expected test results and the actual test data obtained after the actual vehicle test of the function to be tested.

[0076] In the embodiment of the present application, the test verification strategy includes but is not limited to: a numerical comparison strategy and a model verification strategy. Among them, the numerical comparison strategy refers to comparing the numerical values ​​of the test indicators contained in the expected test results with the numerical values ​​of the test indicators contained in the actual test data, and the model verification strategy refers to comparing the actual test data with the expected test results in combination with the test indicator evaluation model.

[0077] When the data type of the test indicator included in the expected test result is a numeric type, it means that the specific content of the test indicator contains a numeric value. Therefore, the test equipment can set the test verification strategy corresponding to the numeric type to a numeric comparison strategy; when the data type of the test indicator included in the expected test result is a non-numeric type, it means that the specific content of the test indicator does not contain a numeric value. Therefore, the test equipment can set the test verification strategy corresponding to the non-numeric type to a model verification strategy.

[0078] Based on this, in the embodiment of the present application, after determining the expected test result corresponding to the function to be tested, the test device can determine the test verification strategy corresponding to the expected test result according to the above-mentioned corresponding relationship.

[0079] In S103, the function to be tested is tested in the test scenario to obtain actual test data.

[0080] In the embodiment of the present application, after obtaining the test scenario corresponding to the function to be tested, the test equipment can test the function to be tested of the vehicle under the test scenario to obtain actual test data.

[0081] Specifically, after obtaining the test scenario corresponding to the function to be tested, the test equipment can generate a test instruction based on the function to be tested and the test scenario, and send the test instruction to the vehicle connected to it wirelessly. After receiving the test instruction, the vehicle's on-board terminal can determine the function to be tested and the test scenario that need to be tested at this time from the test instruction. After that, the on-board terminal can control the vehicle to start the function to be tested in the test scenario to collect actual test data, and send the actual test data to the test equipment.

[0082] It should be noted that, in combination with S101, since the test scenario includes environmental information, the test equipment can output the environmental information to prompt relevant personnel to build a test environment according to the environmental information, so that the vehicle can perform actual vehicle testing on the function to be tested under the test environment.

[0083] In one embodiment of the present application, when the test device acquires data from the vehicle being tested in real time, in order to avoid invalid data due to hardware device connection, thereby reducing the test pass rate and test accuracy of the vehicle's function under test, the test device can specifically perform the following steps: Figure 2 The steps S201 to S203 shown in the figure obtain actual test data, which are described in detail as follows:

[0084] In S201, when it is detected that the vehicle is traveling in the test scenario, motion information generated by the vehicle during the traveling is obtained.

[0085] In this embodiment, the motion information includes, but is not limited to: vehicle speed, acceleration, deviation of the vehicle's driving trajectory when the vehicle is driving on a straight road, deviation of the vehicle when turning, and the like.

[0086] In S202, the validity of the motion information is detected to obtain a detection result.

[0087] In this embodiment, the detection results include but are not limited to: invalid motion information and valid motion information.

[0088] In one embodiment of the present application, when the type of motion information is a type that changes over time, the test device can specifically determine the detection result of the motion information according to the following steps, which are described in detail as follows:

[0089] When the type of the motion information is a type that changes with time, traversing and calculating the change amplitude between data of any two adjacent time points in the motion information;

[0090] If the variation is a specified value, determining that the detection result is that the motion information is invalid;

[0091] If the change amplitude is not the specified value, the detection result is determined to be that the motion information is valid.

[0092] In this embodiment, when the test device detects that the type of motion information is a type that changes over time, it can traverse and calculate the change amplitude between the data of any two adjacent time points in the motion information, and compare the change amplitude with the specified value. The specified value can be determined according to actual needs and is not limited here. For example, the specified value can be 0.

[0093] In this embodiment, when the test device detects that the change amplitude between the data of any two adjacent time points mentioned above is a specified value, it means that the data of any two adjacent time points are the same, that is, the data of the two adjacent time points have not changed. In other words, at this time, the test device has not successfully obtained accurate data. Therefore, the test device can determine that the detection result is that the motion information is invalid.

[0094] When the test device detects that the change amplitude between the data of any two adjacent time points is not the specified value, it means that the data of any two adjacent time points are different, that is, there is a change in the data of the two adjacent time points. In other words, at this time, the test device has successfully acquired accurate data. Therefore, the test device can detect that the motion information is valid.

[0095] In another embodiment of the present application, when the type of motion information is a fixed value type, the testing device can detect in real time whether the motion information has a normal value, and when it is detected that the motion information at any time is empty or an abnormal value, it can be determined that the detection result is that the motion information is invalid; when it is detected that the motion information at any time is a normal value, it can be determined that the detection result is that the motion information is valid.

[0096] In this embodiment, when the test device detects that the detection result is that the motion information is valid, step S203 may be executed.

[0097] In one embodiment of the present application, when the test device detects that the detection result is invalid motion information, it indicates that there is a problem with the connection between the test device and the vehicle. Therefore, the test device can output a first prompt message for prompting to detect the connection between the test device and the vehicle.

[0098] In S203, if the detection result is that the motion information is valid, the motion information is determined as the actual test data.

[0099] In this embodiment, when the test device detects that the detection result is that the motion information is valid, it means that the test device has successfully acquired the data of the vehicle during the actual vehicle test. Therefore, the test device can determine the motion information as actual test data.

[0100] Through the process of detecting the validity of the motion information in steps S201 to S203, the test pass rate and test accuracy of the vehicle's function to be tested are improved.

[0101] In S104, the actual test data is verified according to the test verification strategy and the expected test result to obtain a verification result.

[0102] In the embodiment of the present application, after obtaining the actual test data, the test device can compare the expected test result and the actual test data based on the test verification strategy to obtain a verification result.

[0103] The verification results include but are not limited to: verification passed and verification failed. Verification passed is used to describe that the actual test data is consistent with the expected test results, and verification failed is used to describe that the actual test data is inconsistent with the expected test results.

[0104] In one embodiment of the present application, when the test device detects that the verification result is passed, step S105 may be executed.

[0105] In another embodiment of the present application, when the test equipment detects that the verification result is a verification failure, it indicates that the actual test data does not match the expected test result. Therefore, the test equipment can determine that the test of the vehicle's function to be tested has failed, that is, the performance of the vehicle's actual vehicle test of the function to be tested does not meet the requirements. Based on this, the test equipment can output a second prompt message for prompting that the test of the function to be tested has failed.

[0106] In S105, if the verification result is verification passed, it is determined that the function to be tested has passed the test.

[0107] In the embodiment of the present application, when the test equipment detects that the verification result is passed, it means that the actual test data is consistent with the expected test result. Therefore, the test equipment can determine that the test of the vehicle's function to be tested has passed, that is, the performance of the vehicle's actual vehicle test of the function to be tested meets the requirements. Based on this, the test equipment can output a third prompt information for prompting that the test of the function to be tested has passed.

[0108] From the above, it can be seen that a vehicle testing method provided by an embodiment of the present application can determine a test verification strategy based on the expected test result corresponding to the function to be tested when a test request for the function to be tested of the vehicle is detected; and test the function to be tested in the test scenario corresponding to the function to be tested to obtain actual test data; then verify the actual test data according to the test verification strategy and the expected test result to obtain the verification result; finally, when it is detected that the verification result is passed, it can be determined that the function to be tested has passed the test. Compared with the prior art that only tests a certain function of the vehicle in a fixed test scenario, the present method can not only flexibly determine the test scenarios for different functions to be tested, but also flexibly determine the verification strategy for the data obtained from the actual test according to the expected test result of the function to be tested, and verify the data with the verification strategy to determine whether the function to be tested has passed the test, thereby improving the accuracy of the test of the vehicle function.

[0109] See also Figure 3 , Figure 3 This is a vehicle testing method provided by another embodiment of the present application. Figure 1 Corresponding embodiment, in this embodiment, S102 may specifically include S301 to S302, and correspondingly, S104 may specifically include S303, which is described in detail as follows:

[0110] In S301, the data type of the test indicator included in the expected test result is detected.

[0111] In S302, if the data type is a numerical type, the test verification strategy is determined to be a numerical comparison strategy.

[0112] In S303, based on the numerical comparison strategy, the test index included in the actual test data is compared with the test index included in the expected test result to obtain the verification result.

[0113] In this embodiment, after obtaining the expected test result corresponding to the function to be tested, in order to improve the verification accuracy of the actual test data subsequently acquired, the test device can detect the data type of the test indicator contained in the expected test result and determine the test verification strategy based on the data type.

[0114] In combination with S102, after determining the data type of the test indicator included in the expected test result, the test device can determine that the test verification strategy for the test indicator with a numerical data type is a numerical comparison strategy based on the pre-set correspondence between different data types and test verification strategies.

[0115] Based on this, the test equipment can directly compare the specific numerical values ​​corresponding to the test indicators contained in the actual test data with the specific numerical values ​​corresponding to the test indicators contained in the expected test results to obtain the verification results.

[0116] For example, assume that the test indicator is: the distance between the vehicle and the stationary vehicle when the vehicle is traveling at different speeds towards the stationary vehicle in front and finally stops; the effective range of the specific numerical value corresponding to the test indicator contained in the expected test result is [2cm, 4cm], and the specific numerical value corresponding to the test indicator contained in the actual test data is 3cm, then the test equipment can determine that 3cm is within the range of [2cm, 4cm], therefore, the test equipment can determine that the verification result is passed.

[0117] It should be noted that the test indicator can be one or more.

[0118] When there are multiple test indicators, for any test indicator contained in the actual test data, the testing device can compare the specific numerical value corresponding to the test indicator contained in the actual test data with the specific numerical value corresponding to the test indicator contained in the expected test result, which is the same as the test indicator, to obtain a first comparison result corresponding to the test indicator.

[0119] The first comparison result includes but is not limited to: numerical mismatch and numerical match.

[0120] Based on this, when the testing device detects that there is a test indicator whose first comparison result is a value mismatch among multiple test indicators, it can determine that the verification result is verification failure.

[0121] From the above, it can be seen that the vehicle testing method provided by the present embodiment detects the data type of the test indicator contained in the expected test result; if the data type is a numerical type, the test verification strategy is determined to be a numerical comparison strategy; based on the numerical comparison strategy, the test indicator contained in the actual test data is compared with the test indicator contained in the expected test result to obtain a verification result. The vehicle testing method provided by the present embodiment, when detecting that the data type of the test indicator contained in the expected test result is a numerical type, can directly compare the test indicator contained in the actual test data with the test indicator contained in the expected test result to obtain a verification result, thereby further improving the test accuracy of the vehicle's function to be tested.

[0122] See also Figure 4 , Figure 4 This is a vehicle testing method provided by another embodiment of the present application. Figure 1 Corresponding embodiment, in this embodiment, S102 may specifically include S401-S402, and correspondingly, S104 may specifically include S403-S404, which are described in detail as follows:

[0123] In S401, the data type of the test indicator included in the expected test result is detected.

[0124] In S402, if the data type is a non-numeric type, it is determined that the test verification strategy is a model verification strategy.

[0125] In this embodiment, after obtaining the expected test result corresponding to the function to be tested, in order to improve the verification accuracy of the actual test data subsequently acquired, the test device can detect the data type of the test indicator contained in the expected test result and determine the test verification strategy based on the data type.

[0126] In combination with S102, after determining the data type of the test indicator included in the expected test result, the test device can determine that the test verification strategy for the test indicator with a non-numeric data type is a model verification strategy based on the pre-set correspondence between different data types and test verification strategies.

[0127] In S403, based on the model verification strategy, the actual test data is input into the trained test indicator evaluation model for processing to obtain the test indicator corresponding to the actual test data; wherein, the test indicator evaluation model is used to complete the evaluation of non-numerical test indicators based on the input test data.

[0128] In this embodiment, after the test equipment determines that the test verification strategy is the model verification strategy, since the actual test data obtained by the test equipment from the vehicle during the actual vehicle testing are specific values ​​corresponding to various vehicle information (such as vehicle speed, acceleration, etc.), they cannot be directly compared with the expected test results. Therefore, in order to improve the verification accuracy of the actual test data, the test equipment can input the actual test data into the trained test indicator evaluation model for processing to obtain the test indicators corresponding to the actual test data.

[0129] It should be noted that the test indicator evaluation model is used to complete the evaluation of non-numerical test indicators based on the input test data.

[0130] In one embodiment of the present application, the testing device can be specifically Figure 5 The steps S501 to S502 shown in the figure obtain a test index evaluation model, which is described in detail as follows:

[0131] In S501, training sample data is obtained; wherein the training sample data includes historical driving data corresponding to the historical driving process of the sample vehicle under different scenario parameters, and non-numerical historical test indicators corresponding to the historical driving data, and the historical test indicators are determined based on driving experience information entered by the user of the sample vehicle for the historical driving process.

[0132] In this embodiment, the testing equipment can obtain the historical driving data corresponding to the historical driving process of the sample vehicle under different scenario parameters, as well as the driving experience information entered by the user of the sample vehicle for the above historical driving process. Thereafter, the testing equipment can determine the non-numerical historical test indicators corresponding to the above historical driving data based on the above driving experience information.

[0133] The sample vehicle may be a vehicle of the same model as the vehicle undergoing the function test to be tested.

[0134] The historical driving process may be the driving process of the sample vehicle under different scenario parameters in a historical time period, wherein the historical time period may be determined according to actual needs and is not limited here.

[0135] It should be noted that the scene parameters are used to characterize the historical environment information of the vehicle and the historical vehicle information of the vehicle during each historical driving process of the sample vehicle.

[0136] Historical environmental information includes, but is not limited to: historical static environmental elements, historical dynamic environmental elements, historical traffic participant elements, historical meteorological elements, etc. Among them, historical static environmental elements refer to objects in the environment where the sample vehicle is located that are in a stationary state, such as roads, traffic facilities, surrounding landscapes, and obstacles. Historical dynamic environmental elements refer to elements in the environment where the sample vehicle is located that are in dynamic change, such as dynamic indicator facilities and communication environment information. Historical traffic participant elements refer to information on objects that affect the decision-making and planning of the sample vehicle during the historical driving process, such as other vehicles, pedestrians, and animals. Historical meteorological elements refer to information such as ambient temperature, lighting conditions, and weather conditions during the historical driving process.

[0137] Historical vehicle information refers to the basic attributes, location information, motion state information and driving task information of the sample vehicle during its historical driving process.

[0138] In one embodiment of the present application, in order to improve the processing efficiency of the subsequent test index evaluation model training process of the test device, the test device can specifically determine different scenario parameters according to the following steps, which are detailed as follows:

[0139] Acquire historical scene information of the sample vehicle during the historical driving process;

[0140] The historical environment information is clustered, and the different scene parameters are determined according to the result of the clustering process.

[0141] In this embodiment, the test device can obtain all historical scene information of the sample vehicle during its historical driving process through a server to which it is wirelessly connected. The server can be a cloud server.

[0142] Since the data volume of all the above historical scene information is too large, and there are similar or identical scene information in all the historical scene information, the test device can perform clustering processing on all the above historical scene information to obtain the result of clustering processing, that is, multiple clusters, and determine different scene parameters based on the multiple clusters, that is, one cluster corresponds to one scene parameter. Exemplarily, each cluster includes a cluster center, and the test device can determine multiple scene parameters based on the cluster centers corresponding to the multiple clusters.

[0143] In this embodiment, the test device may determine the above historical driving data and historical test indicators as training sample data for training a pre-built neural network model, wherein the pre-built neural network model may be an existing neural network model.

[0144] In S502, the training of the neural network model is completed based on the training sample data to obtain the test index evaluation model.

[0145] In this embodiment, after obtaining the training sample data, the testing device can train the pre-built neural network model according to the training sample data to obtain a test index evaluation model.

[0146] In S404, the test indicator corresponding to the actual test data is compared with the test indicator included in the expected test result to obtain the verification result.

[0147] In this embodiment, the testing device may compare the specific content corresponding to the test indicator corresponding to the actual test data with the specific content corresponding to the test indicator included in the expected test result to obtain a verification result.

[0148] Exemplarily, assuming that the test indicator is: the specific requirements of the vehicle during the braking process; the specific content corresponding to the test indicator contained in the expected test result is smooth braking without any abruptness, and the specific content corresponding to the test indicator contained in the actual test data is aggressive braking with abruptness, then the test equipment can determine that the specific content corresponding to the test indicator contained in the actual test data is inconsistent with the specific content corresponding to the test indicator contained in the expected test result, and therefore, the test equipment can determine that the verification result is a verification failure.

[0149] It should be noted that the test indicator can be one or more.

[0150] When there are multiple test indicators, for any test indicator contained in the actual test data, the testing device can compare the specific content corresponding to the test indicator contained in the actual test data with the specific content corresponding to the test indicator contained in the expected test result, which is the same as the test indicator, to obtain a second comparison result corresponding to the test indicator.

[0151] The second comparison result includes but is not limited to: content mismatch and content match.

[0152] Based on this, when the test device detects that there is a test indicator whose second comparison result is inconsistent with the content among multiple test indicators, it can determine that the verification result is verification failure.

[0153] From the above, it can be seen that the vehicle testing method provided by the present embodiment detects the data type of the test indicator contained in the expected test result; if the data type is a non-numeric type, the test verification strategy is determined to be a model verification strategy; based on the model verification strategy, the actual test data is input into the trained test indicator evaluation model for processing to obtain the test indicator corresponding to the actual test data; wherein the test indicator evaluation model is used to complete the evaluation of the non-numeric test indicator according to the input test data; the test indicator corresponding to the actual test data is compared with the test indicator contained in the expected test result to obtain the verification result. The vehicle testing method provided by the present embodiment, when detecting that the data type of the test indicator contained in the expected test result is a non-numeric type, can be combined with the test indicator evaluation model to obtain the test indicator corresponding to the actual test data, and the test indicator can be compared with the test indicator contained in the expected test result to obtain the verification result, thereby further improving the test accuracy of the vehicle's function to be tested.

[0154] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0155] Corresponding to a vehicle testing method described in the above embodiment, Figure 6 The structure diagram of a vehicle testing device provided by an embodiment of the present application is shown. For the convenience of explanation, only the part related to the embodiment of the present application is shown. Figure 6 The vehicle testing device 600 includes: a first acquisition unit 61, a first determination unit 62, a testing unit 63, a first verification unit 64 and a second determination unit 65. Wherein:

[0156] The first acquisition unit 61 is used for acquiring a test scenario and an expected test result corresponding to the function to be tested when a test request for the function to be tested of the vehicle is detected.

[0157] The first determining unit 62 is used to determine a test verification strategy according to the expected test result.

[0158] The testing unit 63 is used to test the function to be tested in the test scenario to obtain actual test data.

[0159] The first verification unit 64 is used to verify the actual test data according to the test verification strategy and the expected test result to obtain a verification result.

[0160] The second determination unit 65 is used for determining whether the function to be tested has passed the test if the verification result is verification passed.

[0161] In one embodiment of the present application, the testing unit 63 specifically includes: a second acquisition unit, a first detection unit and a third determination unit. Among them:

[0162] The second acquisition unit is used to acquire motion information generated by the vehicle during the driving process when it is detected that the vehicle is driving in the test scenario.

[0163] The first detection unit is used to detect the validity of the motion information to obtain a detection result.

[0164] The third determining unit is configured to determine the motion information as the actual test data if the detection result indicates that the motion information is valid.

[0165] In one embodiment of the present application, the first detection unit specifically includes: a calculation unit, a fourth determination unit and a fifth determination unit.

[0166] The calculation unit is used for traversing and calculating the variation range between data of any two adjacent time points in the motion information when the type of the motion information is a type that varies with time.

[0167] The fourth determining unit is configured to determine, if the variation range is a specified value, that the detection result is that the motion information is invalid.

[0168] The fifth determination unit is configured to determine, if the variation range is not the specified value, that the detection result is that the motion information is valid.

[0169] In one embodiment of the present application, the first determination unit 62 specifically includes: a second detection unit and a sixth determination; correspondingly, the first verification unit 64 specifically includes: a second verification unit. Among them:

[0170] The second detection unit is used to detect the data type of the test indicator included in the expected test result.

[0171] The sixth determination unit is used to determine that the test verification strategy is a numerical comparison strategy if the data type is a numerical type.

[0172] The second verification unit is used to compare the test index included in the actual test data with the test index included in the expected test result based on the numerical comparison strategy to obtain the verification result.

[0173] In one embodiment of the present application, the first determination unit 62 specifically includes: a third detection unit and a seventh determination unit; correspondingly, the first verification unit 64 specifically includes: an input unit and a third verification unit.

[0174] in:

[0175] The third detection unit is used to detect the data type of the test indicator included in the expected test result.

[0176] The seventh determination unit is used to determine that the test verification strategy is a model verification strategy if the data type is a non-numeric type.

[0177] The input unit is used to input the actual test data into the trained test indicator evaluation model for processing based on the model verification strategy, so as to obtain the test indicator corresponding to the actual test data; wherein, the test indicator evaluation model is used to complete the evaluation of non-numerical test indicators according to the input test data.

[0178] The third verification unit is used to compare the test indicator corresponding to the actual test data with the test indicator included in the expected test result to obtain the verification result.

[0179] In one embodiment of the present application, the vehicle testing device 600 further includes: a third acquisition unit and a training unit.

[0180] The third acquisition unit is used to acquire training sample data; wherein the training sample data includes historical driving data corresponding to the historical driving process of the sample vehicle under different scenario parameters, and non-numerical historical test indicators corresponding to the historical driving data, and the historical test indicators are determined based on the driving experience information entered by the user of the sample vehicle for the historical driving process.

[0181] The training unit is used to complete the training of the neural network model based on the training sample data to obtain the test index evaluation model.

[0182] In one embodiment of the present application, the vehicle testing device 600 further includes: a fourth acquisition unit and a processing unit.

[0183] The fourth acquisition unit is used to acquire the historical scene information of the sample vehicle during the historical driving process.

[0184] The processing unit is used to perform clustering processing on the historical environment information and determine the different scene parameters according to the result of the clustering processing.

[0185] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0186] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0187] Figure 7 This is a schematic diagram of the structure of a test device provided in one embodiment of the present application. Figure 7 As shown, the test device 7 of this embodiment includes: at least one processor 70 ( Figure 7 (only one is shown in the figure) a processor, a memory 71, and a computer program 72 stored in the memory 71 and executable on the at least one processor 70, wherein the processor 70 implements the steps of any of the above-mentioned vehicle testing method embodiments when executing the computer program 72.

[0188] The test device may include, but is not limited to, a processor 70 and a memory 71. Those skilled in the art will appreciate that Figure 7 It is only an example of the test device 7 and does not constitute a limitation on the test device 7. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0189] The processor 70 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0190] In some embodiments, the memory 71 may be an internal storage unit of the test device 7, such as the memory of the test device 7. In other embodiments, the memory 71 may also be an external storage device of the test device 7, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the test device 7. Further, the memory 71 may also include both an internal storage unit and an external storage device of the test device 7. The memory 71 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 71 may also be used to temporarily store data that has been output or is to be output.

[0191] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0192] An embodiment of the present application provides a computer program product. When the computer program product is run on a test device, the test device can implement the steps in the above-mentioned method embodiments when the computer program product is executed.

[0193] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes a computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying the computer program code to the test equipment, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electric carrier signal, a telecommunication signal and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0194] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0195] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person 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 application, and should all be included in the protection scope of the present application.

Claims

1. A vehicle testing method, characterized in that: include: When a test request for a function to be tested of the vehicle is detected, obtaining a test scenario and an expected test result corresponding to the function to be tested; Determine a test verification strategy based on the expected test results; Testing the function to be tested under the test scenario to obtain actual test data; Verifying the actual test data according to the test verification strategy and the expected test result to obtain a verification result; If the verification result is that the verification is passed, it is determined that the function to be tested has passed the test.

2. The vehicle testing method according to claim 1, characterized in that: The step of testing the function to be tested under the test scenario to obtain actual test data includes: When it is detected that the vehicle is traveling in the test scenario, obtaining motion information generated by the vehicle during the traveling process; Detecting the validity of the motion information to obtain a detection result; If the detection result is that the motion information is valid, the motion information is determined as the actual test data.

3. The vehicle testing method according to claim 2, characterized in that: The detecting the validity of the motion information to obtain the detection result includes: When the type of the motion information is a type that changes with time, traversing and calculating the change amplitude between data of any two adjacent time points in the motion information; If the variation is a specified value, determining that the detection result is that the motion information is invalid; If the change amplitude is not the specified value, the detection result is determined to be that the motion information is valid.

4. The vehicle testing method according to any one of claims 1 to 3, characterized in that: Determining a test verification strategy according to the expected test result includes: Detecting the data type of the test indicator included in the expected test result; If the data type is a numerical type, determining that the test verification strategy is a numerical comparison strategy; Correspondingly, the actual test data is verified according to the test verification strategy and the expected test result to obtain the verification result, including: Based on the numerical comparison strategy, the test index included in the actual test data is compared with the test index included in the expected test result to obtain the verification result.

5. The vehicle testing method according to any one of claims 1 to 3, characterized in that: Determining a test verification strategy according to the expected test result includes: Detecting the data type of the test indicator included in the expected test result; If the data type is a non-numeric type, determining that the test verification strategy is a model verification strategy; Correspondingly, the actual test data is verified according to the test verification strategy and the expected test result to obtain the verification result, including: Based on the model verification strategy, the actual test data is input into the trained test indicator evaluation model for processing to obtain the test indicator corresponding to the actual test data; wherein the test indicator evaluation model is used to complete the evaluation of non-numerical test indicators according to the input test data; The test indicator corresponding to the actual test data is compared with the test indicator included in the expected test result to obtain the verification result.

6. The vehicle testing method according to claim 5, characterized in that: The test indicator evaluation model is trained in the following way: Acquire training sample data; wherein the training sample data includes historical driving data corresponding to the historical driving process of the sample vehicle under different scenario parameters, and non-numerical historical test indicators corresponding to the historical driving data, wherein the historical test indicators are determined according to driving experience information entered by the user of the sample vehicle for the historical driving process; The training of the neural network model is completed based on the training sample data to obtain the test index evaluation model.

7. The vehicle testing method according to claim 6, characterized in that: The different scene parameters are determined in the following way: Acquire historical scene information of the sample vehicle during the historical driving process; The historical environment information is clustered, and the different scene parameters are determined according to the result of the clustering process.

8. A vehicle testing device, characterized in that: include: A first acquisition unit, configured to, when a test request for a function to be tested of a vehicle is detected, acquire a test scenario and an expected test result corresponding to the function to be tested; A first determining unit, configured to determine a test verification strategy according to the expected test result; A testing unit, used to test the function to be tested under the test scenario to obtain actual test data; A first verification unit, configured to verify the actual test data according to the test verification strategy and the expected test result to obtain a verification result; The second determining unit is used to determine that the function to be tested has passed the test if the verification result is verification passed.

9. A test device comprising 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 computer program, the vehicle testing method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the vehicle testing method according to any one of claims 1 to 7 is implemented.

Images