CN116929781A

CN116929781A - Vehicle evaluation method, cloud platform, vehicle and storage medium

Info

Publication number: CN116929781A
Application number: CN202310695350.3A
Authority: CN
Inventors: 张俊超; 靳铃花; 梁佳; 梁文艳; 李玉梅
Original assignee: Guangzhou Automobile Group Co Ltd
Current assignee: Guangzhou Automobile Group Co Ltd
Priority date: 2023-06-12
Filing date: 2023-06-12
Publication date: 2023-10-24

Abstract

The application discloses a vehicle evaluation method, a cloud platform, a vehicle and a storage medium, wherein the method comprises the following steps: transmitting the test instruction and the configuration file to the vehicle so that the vehicle executes the test case set according to the test instruction, and collecting the characteristic signals and the test data corresponding to the buried point information according to the data collection rule; the configuration file comprises a test case set, a data acquisition rule, characteristic signals required to be acquired and buried point information; and receiving test data sent by the vehicle, and evaluating the effect of the vehicle based on the software and hardware of the vehicle according to the test data to obtain an evaluation result of the vehicle. According to the application, the test data which can reflect the actual effect and the compatibility of the vehicle software when running on the hardware of the vehicle can be obtained by executing the test case set, so that the obtained evaluation result according to the test data can be used for referring to the evaluation results of the vehicle software and the hardware, and the accuracy of the vehicle evaluation result is improved.

Description

Vehicle evaluation method, cloud platform, vehicle and storage medium

Technical Field

The application relates to the technical field of vehicle management, in particular to a vehicle evaluation method, a cloud platform, a vehicle and a storage medium.

Background

With the vigorous development of the automobile industry, a plurality of software and hardware suppliers exist in the industry, even on the same model of automobile, the situation that different software and hardware versions are used is common, and how to evaluate the effect of the automobile based on the software and hardware versions is a great difficulty.

The existing vehicle evaluation method generally obtains an evaluation result after hardware and software are tested independently and specified software and hardware are tested integrally, and the accuracy of the obtained evaluation result is low.

Therefore, there is a need for a vehicle evaluation method that improves the accuracy of evaluating the effect of a vehicle based on a software and hardware version.

Disclosure of Invention

The application provides a vehicle evaluation method, a cloud platform, a vehicle and a storage medium, so as to improve the defects.

In a first aspect, an embodiment of the present application provides a vehicle evaluation method, applied to a cloud platform, where the method includes: transmitting the test instruction and the configuration file to the vehicle so that the vehicle executes the test case set according to the test instruction, and collecting the characteristic signals and the test data corresponding to the buried point information according to the data collection rule; the configuration file comprises a test case set, a data acquisition rule, characteristic signals required to be acquired and buried point information; and receiving test data sent by the vehicle, and evaluating the effect of the vehicle based on the software and hardware of the vehicle according to the test data to obtain an evaluation result of the vehicle.

In a second aspect, an embodiment of the present application provides a vehicle evaluation method, applied to a vehicle, including: receiving a test instruction and a configuration file sent by a cloud platform, wherein the configuration file comprises a test case set, characteristic signals to be acquired and buried point information; executing a test case set according to the test instruction, and collecting test data corresponding to the characteristic signals and the buried point information according to the data collection rule; and sending the test data to the cloud platform so that the cloud platform can evaluate the effect of the vehicle based on the software and hardware of the vehicle according to the test data to obtain the evaluation result of the vehicle. .

In a third aspect, an embodiment of the present application further provides a vehicle evaluation device, applied to a vehicle, where the device includes:

the first acquisition module is used for responding to the received test instruction and configuration file sent by the cloud platform, and controlling the software development kit to load the configuration file according to the test instruction to obtain a test case set corresponding to the test instruction; the software development kit is obtained from a cloud platform;

the data acquisition module is used for acquiring test data corresponding to the test case set in the process of executing the test case set;

the first sending module is used for sending the test data to the cloud platform so that the cloud platform can evaluate the vehicle according to the test data to obtain an evaluation result of the vehicle.

In a fourth aspect, an embodiment of the present application further provides a vehicle evaluation device, applied to a cloud platform, where the device includes:

the second sending module is used for sending the test instruction and the configuration file to the vehicle so that the vehicle can control the software development kit to load the configuration file according to the test instruction to obtain a test case set corresponding to the test instruction, and collecting test data corresponding to the test case set in the process of executing the test case set; the software development kit is obtained from a cloud platform;

and the evaluation module is used for responding to the test data sent by the vehicle, evaluating the vehicle according to the test data and obtaining an evaluation result of the vehicle.

In a fifth aspect, an embodiment of the present application further provides a vehicle, where the cloud platform includes:

one or more first processors;

a first memory;

one or more first applications, wherein the one or more first applications are stored in the first memory and configured to be executed by the one or more first processors, the one or more first applications configured to perform the above-described method.

In a sixth aspect, an embodiment of the present application further provides a cloud platform, where the vehicle includes:

one or more second processors;

A second memory;

one or more second applications, wherein the one or more second applications are stored in the second memory and configured to be executed by the one or more second processors, the one or more second applications configured to perform the above-described method.

In a seventh aspect, embodiments of the present application also provide a computer readable storage medium storing program code executable by a processor, the program code when executed by the processor causing the processor to perform the above method.

According to the vehicle evaluation method, the cloud platform, the vehicle and the storage medium, the cloud platform sends the test instruction and the configuration file to the vehicle, so that the vehicle executes the test case set according to the test instruction, acquires the characteristic signals and the test data corresponding to the embedded point information according to the data acquisition rule, receives the test data sent by the vehicle, determines the evaluation result according to the test data, and can acquire the test data capable of reflecting the actual effect and the compatibility of the vehicle software when the vehicle runs on the vehicle hardware by executing the test case set, so that the actual running condition of the vehicle software and the hardware can be accurately indicated according to the test data, the evaluation result of the vehicle software and the hardware can be referred according to the obtained evaluation result of the test data, and the accuracy of the vehicle evaluation result is improved.

Additional features and advantages of embodiments of the application will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of embodiments of the application. The objectives and other advantages of embodiments of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 shows a schematic diagram of a cloud platform suitable for use in an embodiment of the present application.

FIG. 2 illustrates a schematic diagram of a vehicle hardware environment suitable for use with embodiments of the present application.

Fig. 3 shows a flow chart of a vehicle evaluation method according to an embodiment of the application.

Fig. 4 shows a flow chart of a vehicle evaluation method according to a further embodiment of the application.

Fig. 5 shows a schematic diagram of evaluation result acquisition of a vehicle in an embodiment of the present application.

Fig. 6 shows a flowchart of a vehicle evaluation method according to still another embodiment of the present application.

Fig. 7 is a schematic diagram illustrating an implementation of a vehicle evaluation method in a vehicle according to an embodiment of the present application.

Fig. 8 shows a schematic diagram of a vehicle evaluation system in an embodiment of the application.

Fig. 9 is a block diagram showing a configuration of a vehicle evaluating apparatus according to an embodiment of the present application.

Fig. 10 is a block diagram showing a construction of still another vehicle evaluating apparatus according to an embodiment of the present application.

Detailed Description

In order to make the present application better understood by those skilled in the art, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present application.

It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.

With the rapid development of the automobile industry, a plurality of software and hardware suppliers exist in the industry, even on the same automobile model, the situation that different software and hardware versions are used is common, and the different software and hardware versions have influence on the automobile effect, so that the automobile effect needs to be evaluated based on the software and hardware versions in the application of new energy automobile development, automobile production quality control, automobile fault diagnosis, automobile performance improvement and the like, and therefore, how to evaluate the automobile effect based on the software and hardware versions becomes a great difficulty.

In the existing vehicle evaluation method, generally, a task of testing hardware is operated on a vehicle hardware resource to obtain a hardware test result, software is operated on a test sample and a simulator to test to obtain a software test result, and an appointed hardware and software version is integrated to test to obtain an appointed software and hardware version test result, and finally three test results are combined to obtain a vehicle evaluation result.

However, the inventor finds that the software and the hardware are tested independently, the actual effect and the compatibility of the software running on the hardware cannot be known in time, the software and hardware integration test cannot flexibly test the compatibility of multiple versions of software and hardware according to service requirements, and the accuracy of the vehicle evaluation result obtained by comprehensively analyzing the test result is low.

Therefore, in order to overcome the above-mentioned drawbacks, the inventor proposes a vehicle evaluation method, a cloud platform, a vehicle and a storage medium, where the cloud platform sends a test instruction and a configuration file to the vehicle, so that the vehicle executes a test case set according to the test instruction, collects test data corresponding to feature signals and embedded point information according to a data collection rule, receives the test data sent by the vehicle, determines an evaluation result according to the test data, and can obtain the test data capable of reflecting an actual effect and a compatible condition of software of the vehicle when the software runs on hardware of the vehicle by executing the test case set, so that the actual running condition of the software and the hardware of the vehicle can be accurately indicated according to the test data, further the obtained evaluation result according to the test data can refer to the evaluation result of the software and the hardware of the vehicle, and the accuracy of the vehicle evaluation result is improved.

Referring to fig. 1, fig. 1 shows a schematic diagram of a cloud platform suitable for use in an embodiment of the present application, where the cloud platform 100 includes a configuration management module 110, a score calculation module 111, a comprehensive evaluation module 112, one or more (only one is shown in the figure) first processors 113, and a first memory 114.

The configuration management module 110 is configured to manage the data collection configuration file, and can create, edit, delete, and update the configuration file content.

The scoring module 111 is used for scoring the test data of the vehicle.

The comprehensive evaluation module 112 is configured to perform comprehensive evaluation on the vehicle according to the score obtained by the score calculation module 111.

The first processor 113 may include one or more processing cores. The first processor 113 connects various parts within the entire cloud platform 100 using various interfaces and lines, and performs various functions of the cloud platform 100 and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the first memory 114, and invoking data stored in the first memory 114. Alternatively, the first processor 113 may be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic Array, PLA). The first processor 113 may integrate one or a combination of several of a central first processor (Central Processing Unit, CPU), an image first processor (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for being responsible for rendering and drawing of display content; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the first processor 113 and may be implemented by a single communication chip.

The first Memory 114 may include a random first Memory (Random Access Memory, RAM) or a Read-Only second Memory (Read-Only Memory). The first memory 114 may be used to store instructions, programs, code sets, or instruction sets. The first memory 114 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the method embodiments described below, etc. The storage data area may also store data created by the cloud platform 100 in use (e.g., phonebook, audio-video data, chat log data), and so forth.

Referring to fig. 2, fig. 2 shows a schematic diagram of a vehicle hardware environment suitable for use in an embodiment of the present application, and a vehicle 200 includes an on-board electronic system 210, a test execution module 211, a data acquisition module 212, one or more (only one is shown in the figure) second processors 213, and a second memory 214.

The in-vehicle electronic system 210 includes an automobile information system (in-vehicle computer), a navigation system, an automobile audio-visual entertainment system, an in-vehicle communication system, and the like, which includes a plurality of software and hardware.

The test execution module 211 is divided into a case execution unit and a test case set unit, the case execution unit receives a test signal sent by the cloud platform, finds a corresponding test case in the test case set unit according to the content of the signal, and then tests a plurality of software and hardware of the vehicle-mounted electronic system 210.

The data acquisition module 212 is configured to acquire test data obtained by the test performed by the test execution module 211.

The second processor 213 may be a Micro Control Unit (MCU) having a second memory 214 built in, and the second memory 214 stores therein a program that can execute the contents of the embodiments described below, and the second processor 213 may execute the program stored in the second memory 214.

Wherein the second processor 213 may comprise one or more processors. The second processor 213 connects various parts within the entire vehicle 200 using various interfaces and lines, performs various functions of the vehicle 200 and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the second memory 214, and calling data stored in the second memory 214.

The second memory 214 may include a random access memory (RandomAccessMemory, RAM) or a Read-only memory (Read-only memory). The second memory 214 may be used to store instructions, programs, code sets, or instruction sets. The second memory 214 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described below, etc.

Referring to fig. 3, fig. 3 shows a flowchart of a vehicle evaluation method according to an embodiment of the present application, for a cloud platform, the method includes:

s101, sending a test instruction and a configuration file to a vehicle so that the vehicle executes a test case set according to the test instruction, and collecting test data corresponding to characteristic signals and buried point information according to a data collection rule; the configuration file comprises a test case set, a data acquisition rule, characteristic signals required to be acquired and buried point information.

In some embodiments, the cloud platform is communicatively connected to the vehicle, and the cloud platform may issue a control command to a remote communication Terminal (TBOX) of the vehicle based on a communication protocol with the vehicle, and the TBOX notifies the intelligent interconnection system (AVNT or AVT) to download the configuration file. The communication protocol may be a message queue telemetry transport protocol (Message Queuing Telemetry Transport, MQTT), which is a "lightweight" communication protocol based on publish/subscribe (TCP/IP) mode, and is constructed on a TCP/IP protocol, which can provide real-time reliable message service with very little code and limited bandwidth for connecting remote devices.

The test instruction refers to an instruction for informing the vehicle of starting the test and which software and hardware are tested, and the test instruction may be a test signal. The test instruction may be an instruction for testing all software and hardware in the vehicle, or may be an instruction for testing part of the software and hardware.

The configuration file is generated by the cloud platform, the generated configuration file can be stored in the cloud platform or a third-party system, the third-party system can be a data embedded point configuration system, and the configuration file downloading pressure can be reduced when the configuration file is stored in the third-party system. The configuration file refers to a collection of data collection rules and data reporting rules in the test process, such as software test execution results, application starting time consumption, high-speed operation, brake stopping, acceleration, power down, CPU occupancy rate, microphone, loudspeaker, GPS, HUD and other software and hardware data, collection frequency, reporting period and the like. The configuration file can be newly built, edited, deleted and updated according to the requirements.

The Test Case set is an unordered set of Test cases (Test cases), the Test cases are a group of Test inputs, execution conditions and expected results designed for specific purposes so as to Test whether a specific requirement is met or not, and the operation effect of software and hardware is checked through a large number of Test cases, namely the basis for carrying out Test work. The test case elements comprise case numbers, case titles, test items, case levels, preset conditions, test inputs, execution steps and expected results.

The data acquisition rule refers to a rule for acquiring test data, and comprises data acquisition frequency and the like, and the data acquisition rule can be set according to requirements.

The test data comprises corresponding test data and test data corresponding to embedded point information, wherein the characteristic signals refer to national standard and enterprise standard signals of a vehicle end, and the embedded point information refers to customized contents of various vehicle factories on vehicle software and is used for recording user behavior data, abnormal information of a vehicle machine, system application and the like.

In some embodiments, the cloud platform also sends test software information to the vehicle to cause the vehicle to download a software development kit based on the test software information, where the test software information may be a test software version, and the software development kit (Software Development Kit, or SDK) is typically a collection of development tools that are used by software engineers to build application software for a particular software package, software framework, hardware platform, operating system, etc.

S102, receiving test data sent by the vehicle, and performing effect evaluation on the vehicle based on the software and hardware of the vehicle according to the test data to obtain an evaluation result of the vehicle.

In some embodiments, before classifying the test data according to the multiple evaluation indexes to obtain the respective data to be evaluated of each evaluation index, the test data may be preprocessed, where the preprocessing may be data cleaning, data conversion, and the like. The data cleaning is a process of rechecking and checking the data, and aims to delete repeated information, correct existing errors and provide data consistency, which is usually completed by a computer, and can be completed manually when the data volume is small.

After the preprocessed test data are obtained, the cloud platform evaluates the vehicle according to the test data.

In some embodiments, performing effect evaluation based on hardware and software of the vehicle on the vehicle according to the test data to obtain an evaluation result of the vehicle may include: classifying the test data according to a plurality of evaluation indexes corresponding to the test case set to obtain respective data to be evaluated of each evaluation index, wherein each evaluation index comprises a plurality of evaluation characteristics; classifying the respective data to be evaluated of each evaluation index according to a plurality of evaluation features included in each evaluation index to obtain feature evaluation data corresponding to the plurality of evaluation features under each evaluation index; inputting the characteristic evaluation data corresponding to each of the plurality of evaluation characteristics under each evaluation index into an evaluation model to obtain an evaluation result corresponding to each evaluation index; and determining the evaluation result of the vehicle according to the evaluation results corresponding to the plurality of evaluation indexes.

The test case set can be arbitrarily selected according to requirements, and the test case set can be a test case set for testing the whole vehicle, wherein a plurality of evaluation indexes corresponding to the test case set comprise all evaluation indexes for evaluating the whole vehicle, or the test case set for testing part of software and hardware, and a plurality of evaluation indexes corresponding to the test case set only comprise the evaluation indexes corresponding to the part of software and hardware.

The plurality of first evaluation indexes may include a vehicle control system software evaluation index, other vehicle-mounted software evaluation indexes, a software security evaluation index, a control system evaluation index, a wireless network evaluation index, a sensor evaluation index, and other device evaluation indexes, and the plurality of second evaluation indexes may include a plurality of evaluation indexes respectively included in the vehicle control system software evaluation index, other vehicle-mounted software evaluation indexes, software security evaluation indexes, control system evaluation indexes, wireless network evaluation indexes, sensor evaluation indexes, and other device evaluation indexes.

The vehicle control system software evaluation index comprises a plurality of evaluation characteristics such as software response speed, stability, reliability, compatibility, functional completeness, software performance and the like; other vehicle-mounted software evaluation indexes comprise a plurality of evaluation characteristics such as response speed, precision, stability, loading time length, resource occupation, task completion degree and the like of a vehicle-mounted entertainment system, a navigation system and a third party application; the software security evaluation index comprises a plurality of evaluation characteristics such as security vulnerability discovery, privacy protection, malicious attack protection and the like; the control system evaluation index comprises a plurality of evaluation characteristics such as performance, stability and compatibility of the core control chip; the wireless network evaluation index comprises a plurality of evaluation characteristics such as whether wireless communication standards such as Wi-Fi, bluetooth and LTE are compatible, stability and network speed; the sensor evaluation index comprises a plurality of evaluation characteristics such as a sensor method, precision, resolution and the like; other equipment evaluation indexes comprise a plurality of evaluation characteristics such as sound quality, frequency response, distortion condition, display effect, display stability, operation efficiency, power consumption and the like.

The evaluation model is a model for evaluating each evaluation index according to the characteristic evaluation data corresponding to each of a plurality of evaluation characteristics under each evaluation index, and the evaluation result corresponding to the evaluation index is a scoring result of the evaluation index by the evaluation model.

In some embodiments, the evaluation model may be a support vector machine model or a neural network model. And inputting the data to be evaluated corresponding to each evaluation index into a trained support vector machine or extending into a network model to obtain an evaluation result corresponding to each evaluation index, and synthesizing the evaluation result corresponding to each evaluation index to obtain the evaluation result of the vehicle.

Wherein the support vector machine (support vector machines, SVM) is a two-class model, the basic model of which is a linear classifier defined with the largest interval in the feature space, and the largest interval makes it different from the perceptron; the SVM also includes a kernel technique, which makes it a substantially nonlinear classifier.

In this embodiment, a test instruction and a configuration file are sent to a vehicle, so that the vehicle executes a test case set according to the test instruction, test data corresponding to feature signals and buried point information are collected according to a data collection rule, the test data sent by the vehicle is received, an evaluation result is determined according to the test data, the test data which can embody the actual effect and compatibility of the software of the vehicle when running on the hardware of the vehicle can be obtained by executing the test case set, the actual running condition of the software and the hardware of the vehicle can be accurately indicated according to the test data, the obtained evaluation result according to the test data can be used for referencing the evaluation result of the software and the hardware of the vehicle, and the accuracy of the vehicle evaluation result is improved.

Referring to fig. 4, fig. 4 shows a flowchart of a vehicle evaluation method according to another embodiment of the present application, for a cloud platform, the method includes:

s201, sending a test instruction and a configuration file to a vehicle so that the vehicle executes a test case set according to the test instruction, and collecting test data corresponding to characteristic signals and buried point information according to a data collection rule; the configuration file comprises a test case set, a data acquisition rule, characteristic signals required to be acquired and buried point information.

The description of S201 refers to the description of S101 above, and is not repeated here.

S202, receiving test data sent by a vehicle, and classifying the test data according to a plurality of evaluation indexes corresponding to a test case set to obtain respective data to be evaluated of each evaluation index, wherein each evaluation index comprises a plurality of evaluation characteristics.

After receiving test data sent by a vehicle, the test data can be preprocessed, and the preprocessed test data is classified according to a plurality of evaluation indexes corresponding to the test case set, so that respective data to be evaluated of each evaluation index is obtained.

S203, classifying the respective data to be evaluated of each evaluation index according to the plurality of evaluation features included in each evaluation index to obtain the feature evaluation data corresponding to the plurality of evaluation features under each evaluation index.

After the respective data to be evaluated of each evaluation index is obtained, the respective data to be evaluated of each evaluation index can be classified according to the plurality of evaluation characteristics under each evaluation index, so that the characteristic evaluation data corresponding to the plurality of evaluation characteristics under each evaluation index can be obtained.

The plurality of evaluation features under each evaluation index may be all evaluation features under each evaluation index, or may be part of evaluation features selected according to requirements.

S204, inputting the characteristic evaluation data corresponding to the plurality of evaluation characteristics under each evaluation index into an evaluation model to obtain an evaluation result corresponding to each evaluation index.

After the feature evaluation data corresponding to the multiple evaluation features under each evaluation index are obtained, the feature evaluation data corresponding to the multiple evaluation features under each evaluation index are input into an evaluation model, and the evaluation model can be a trained support vector machine.

In some embodiments, the training method of the evaluation model comprises the steps of obtaining a plurality of sample test data of a sample vehicle, wherein each sample test data comprises sample evaluation data of a plurality of evaluation indexes and sample evaluation results of each sample test data, and the sample test data of each evaluation index comprises sample feature test data of a plurality of evaluation features under each evaluation index; for each sample test data, constructing a feature vector corresponding to the sample test data according to the sample feature test data of each of a plurality of evaluation features under each evaluation index; constructing label vectors corresponding to the plurality of sample test data according to respective sample evaluation results of the plurality of sample test data; and training a support vector machine in an initial state according to the feature vectors corresponding to the sample test data and the label vectors corresponding to the sample test data to obtain an evaluation model.

The plurality of sample test data of the sample vehicle may be a plurality of sample test data obtained for each sample vehicle, or a plurality of sample test data obtained for a plurality of sample vehicles.

After the plurality of sample test data are obtained, for each sample test data, constructing a feature vector corresponding to the sample test data according to the sample feature test data of each of the plurality of evaluation features under each evaluation index, wherein the length of the feature vector can be determined according to the total number of the evaluation features corresponding to the plurality of evaluation indexes included in the sample test data, and the lengths of the feature vectors corresponding to the plurality of sample test data are the same.

The sample test data is represented by the evaluation features corresponding to the evaluation indexes, and if M sample data are provided, the length of the feature vector is N, the corresponding feature vector can be represented as:

X1＝[x11，x12，...，x1N]，X2＝[x21，x22，...，x2N]，...，Xi＝[xi1，xi2，...，xij，...，xiN]，...，XM＝[xM1，xM2，...，xMN]，

wherein xij represents the j-th evaluation feature in the i-th sample data, and a plurality of sample evaluation data construct a plurality of feature vectors.

Taking the example that the sample test data comprises the evaluation index of the software of the vehicle control system and the evaluation index of the control system, if the evaluation index of the software of the vehicle control system comprises the evaluation characteristics of the response speed, the stability and the reliability of the software, the evaluation index of the control system comprises the performance of the core control chip and the real-time evaluation characteristics of the control strategy, the sample test data is represented by the evaluation characteristics corresponding to a plurality of evaluation indexes, namely the sample test data comprises the evaluation characteristics of the response speed, the stability, the reliability of the software, the performance of the core control chip and the real-time evaluation characteristics of the control strategy, and a characteristic vector with the length of 5 can be constructed according to the 5 evaluation characteristics.

In some embodiments, the sample evaluation result is an evaluation result manually made on the sample test data, and the sample evaluation result corresponding to each sample test data is put into one label vector y, and if M sample data are provided, the corresponding label vector can be expressed as:

Y＝[y1，y2，...，ys，...，yM]，

where ys denotes the label of the s-th sample profile.

In some embodiments, the sample evaluation results corresponding to the sample test data can be classified into three grades of good, medium and bad, and three numbers of-1, 0 and 1 can be used as labels, wherein the label of-1 indicates that the software and hardware corresponding to the sample test data are represented as bad; a label of 0 indicates that the software and hardware corresponding to the sample test data are represented as medium; a label of 1 indicates that the software and hardware corresponding to the sample test data is "good".

After the feature vectors corresponding to the sample test data and the label vectors corresponding to the sample test data are obtained, training a support vector machine in an initial state according to the feature vectors corresponding to the sample test data and the label vectors corresponding to the sample test data to obtain an evaluation model.

The calculation formula of the support vector machine in the initial state is as follows: w (w) ^T X+b=y, where w= (w 1, …, wp) is a normal vector of the hyperplane, b is an offset, X is input data, i.e., a feature vector, and Y is a label vector.

In some embodiments, the support vector machine for the initial state may be trained by using a software package, which may be scikit-learn.

In some embodiments, after the evaluation model is obtained, a classification model may be further constructed, which is used to classify the evaluation result output by the evaluation model into three grades, namely, good, medium and bad.

In some embodiments, training the support vector machine in the initial state according to the feature vectors corresponding to the sample test data and the label vectors corresponding to the sample test data to obtain an evaluation model may include training the support vector machine in the initial state according to the feature vectors corresponding to the sample test data and the label vectors corresponding to the sample test data to obtain the initial evaluation model; inputting the test data corresponding to the at least one evaluation index into an initial evaluation model to obtain an initial evaluation result corresponding to the at least one evaluation index; constructing a confusion matrix corresponding to the initial evaluation model according to the initial evaluation result corresponding to the at least one evaluation index and the test data evaluation result corresponding to the test data of the at least one evaluation index; and if the confusion matrix does not meet the preset condition, correcting the initial evaluation model according to the confusion matrix to obtain the evaluation model.

In some embodiments, after the initial evaluation model is obtained, the evaluation effect of the model needs to be verified, test data corresponding to the evaluation index is input into the initial evaluation model to obtain an initial evaluation result corresponding to the evaluation index, a test value p is obtained according to the initial evaluation result, and if p >0, the evaluation index belongs to good; if p=0, the evaluation index belongs to "middle"; if p <0, the evaluation index belongs to "bad".

Wherein, the calculation formula of the test value p is: p=sign (w ^T X+b), sign is a sign function representing the conversion of a numerical value into one of three levels { -1,0,1 }.

According to the test value corresponding to the test data and the test data grading result corresponding to the test data, a confusion matrix (confusing matrix), also called error matrix, is constructed, and is a standard format for representing precision evaluation, and is represented by a matrix form of n rows and n columns.

In some embodiments, the preset condition may be that the accuracy rate of the confusion matrix is greater than the first percentage or the accuracy rate is greater than the second percentage or the recall rate is greater than the third percentage, or that two of the three are greater than their corresponding percentages, or that all three are greater than their preset percentages.

If the confusion matrix does not meet the preset condition, the initial evaluation model can be corrected by means of cross verification and grid search according to the confusion matrix, different parameter settings are tried until the best-performing parameter combination is found to finish model correction.

The calculation formula of the evaluation result output by the corrected model isF represents the initial evaluation result, a represents the model score of the initial evaluation model on the test data, and B represents the model score of the reference model or the external data on the test data.

S205, determining an evaluation result of the vehicle according to the evaluation results corresponding to the evaluation indexes.

After the evaluation results corresponding to the plurality of evaluation indexes are obtained, the evaluation results corresponding to the plurality of evaluation indexes can be synthesized, and the evaluation results of the vehicle can be obtained.

In some embodiments, determining the evaluation result of the vehicle according to the evaluation results corresponding to the plurality of evaluation indexes may include: constructing a hierarchical structure according to a plurality of evaluation indexes, wherein the hierarchical structure comprises a plurality of evaluation criteria, and each evaluation criterion comprises a plurality of evaluation indexes; constructing a criterion judgment matrix among a plurality of evaluation criteria according to the plurality of evaluation criteria, wherein the criterion judgment matrix comprises a relative value between any two evaluation criteria, and the relative value between any two evaluation criteria indicates the importance of one evaluation criterion in the any two evaluation criteria to the other evaluation criterion; normalizing the criterion judgment matrix corresponding to the plurality of evaluation criteria to obtain a criterion weight matrix corresponding to the plurality of evaluation criteria; determining the consistency ratio of the criterion weight matrix according to the order of the criterion weight matrix and the maximum value in the criterion weight matrix; if the consistency ratio of the criterion weight matrix is smaller than a preset threshold, determining an evaluation result of the vehicle according to respective evaluation results of a plurality of evaluation indexes under each evaluation criterion side.

The plurality of evaluation criteria are indexes capable of directly evaluating the effect of the vehicle, and each evaluation criterion includes a plurality of evaluation indexes.

The number of layers of the hierarchical structure constructed according to the multiple evaluation indexes can be selected according to requirements, and the evaluation criteria contained in the hierarchical structure are determined according to the multiple evaluation indexes.

Wherein, the number in the judgment matrix represents the relative value of the importance degree between any two evaluation criteria, and the larger the number is, the more important the number is.

After the criterion judgment matrix is obtained, normalizing the alignment judgment matrix to obtain a criterion weight matrix, wherein the calculation formula of each weight value in the criterion weight matrix is as follows:

wherein n represents the number of evaluation criteria, a _ij Represents the relative value, W, of the ith evaluation criterion being more important than the jth evaluation criterion _ij A weight value representing the i-th evaluation criterion.

After the criterion weight matrix is acquired, the consistency ratio CR of the criterion weight matrix is calculated as follows:

wherein lambda is _max For the maximum eigenvalue of the criterion weight matrix, n is the order of the criterion weight matrix, RI is the random consistency index of the weight matrix, and the RI value is only related to the order of the matrix.

In some embodiments, the preset threshold may be 0.1, and if CR <0.1, the criterion weight matrix passes the consistency check.

After passing the consistency test, determining the evaluation result of the vehicle according to the respective evaluation results of the plurality of evaluation indexes under each evaluation criterion side.

In some embodiments, determining the evaluation result of the vehicle based on the respective evaluation results of the plurality of evaluation indexes under each evaluation criterion side includes: constructing an index judgment matrix among a plurality of evaluation indexes under each evaluation criterion according to the plurality of evaluation indexes included in each evaluation criterion; normalizing the index judgment matrix among the plurality of evaluation indexes under each evaluation criterion to obtain an index weight matrix corresponding to each evaluation criterion; determining the consistency ratio of the index weight matrix corresponding to each evaluation criterion according to the order and the maximum value of the index weight matrix corresponding to each evaluation criterion; if the consistency ratio of the index weight matrix corresponding to the evaluation criterion is smaller than a preset threshold, determining the weight value corresponding to each of a plurality of evaluation indexes under the evaluation criterion according to the index weight matrix corresponding to the evaluation criterion; for each evaluation criterion, weighting and summing the evaluation results corresponding to the plurality of evaluation indexes under the evaluation criterion according to the weight values corresponding to the plurality of evaluation indexes under the evaluation criterion to obtain the evaluation result of the evaluation criterion; determining the weight value of each of a plurality of evaluation criteria according to the criterion weight matrix; and according to the weight values of the evaluation criteria, carrying out weighted summation on the evaluation results of the evaluation criteria to obtain the evaluation results of the vehicle.

For example, the target level is to evaluate the quality of the software and hardware version, the criterion level includes a plurality of evaluation criteria, which are the functional, reliability, usability, safety, compatibility and performance of the software and hardware, and the sub-criterion level is the functional evaluation index including navigation function, voice recognition function, telephone function, audio entertainment function, application function and the like; the reliability comprises evaluation indexes such as operation stability, failure rate, service life, loss degree, sensitivity and the like; the usability comprises evaluation indexes such as interface friendliness, operation convenience and the like; the security comprises evaluation indexes such as background protection, hacking resistance, privacy protection and the like; compatibility includes evaluation indexes such as compatibility with hardware and software; the performance includes evaluation indexes such as running speed, response time, resource utilization rate and the like, a hierarchical structure including a target level, a criterion level and a sub-criterion level is constructed, then a criterion judgment matrix is constructed, and the following is a 6x6 judgment matrix formed by the functions, reliability, usability, safety, compatibility and performance of software and hardware, wherein the criterion judgment matrix is shown in table 1, and the table 1 is as follows:

TABLE 1

	Functionality of	Reliability of	Ease of use	Safety of	Compatibility of	Performance of
							Functionality of	1	3	2	4	2	4
Reliability of	1/3	1	1/2	2	2	3
							Ease of use	1/2	2	1	3	1	3
Safety of	1/4	1/2	1/3	1	1/2	2
							Compatibility of	1/2	1/2	1	2	1	3
Performance of	1/4	1/3	1/3	1/2	1/3	1

According to the criterion judgment matrix in table 1, calculating the criterion weight matrix corresponding to table 1, determining the weight value corresponding to each evaluation criterion according to the criterion weight matrix, acquiring the weight value corresponding to each evaluation criterion, determining the evaluation result of each evaluation criterion, obtaining the evaluation result of each evaluation index from the evaluation model, and determining the weight value of each of a plurality of evaluation indexes under each evaluation criterion by constructing the index judgment matrix of the plurality of evaluation indexes under each evaluation criterion. The weight value parts of the evaluation criteria and the evaluation indexes in the hierarchical structure in the example are shown in table 2, and table 2 is as follows:

TABLE 2

/>

And weighting and summing the evaluation results of the evaluation indexes according to the weight values of the evaluation indexes under each evaluation criterion to obtain the evaluation result of the vehicle.

As shown in fig. 5, after receiving the test data, classifying the test data to obtain to-be-evaluated data corresponding to a plurality of evaluation indexes, obtaining an evaluation result corresponding to each evaluation index according to the to-be-evaluated data, and then carrying out weighted summation on the evaluation results to obtain an evaluation result of the vehicle.

In this embodiment, the test data received from the vehicle is classified and then input into the trained evaluation model, so as to obtain the evaluation results of the evaluation indexes output by the evaluation model, and then the weighted sum of the evaluation results of the evaluation indexes is obtained by the weight value obtained by the analytic hierarchy process, so that the accuracy of the obtained vehicle evaluation results is higher, and the comprehensive evaluation of a plurality of evaluation indexes can be satisfied.

Referring to fig. 6, fig. 6 shows a flowchart of a vehicle evaluation method according to still another embodiment of the present application, for a vehicle, the method includes:

s301, receiving a test instruction and a configuration file sent by a cloud platform, wherein the configuration file comprises a test case set, characteristic signals to be collected and buried point information.

The vehicle can be an electric vehicle or a fuel oil vehicle, and can also be a car, suv, a bus, a truck and the like. The vehicle may be one vehicle or a plurality of vehicles.

In some embodiments, after the vehicle receives the test instruction and the configuration file, the development kit of the vehicle loads the configuration file to obtain the test case set corresponding to the configuration file. The software development tool package comprises a data embedded point software development tool package, and after the vehicle receives the test instruction and the configuration file, the data embedded point software development tool package can load the configuration file to obtain the test case set. The data embedding point is used for collecting corresponding data at a position where the data embedding point is needed, namely collecting test data of software and hardware to be tested in the test instruction.

In some embodiments, a method for acquiring a software development kit may include: and responding to the test software information sent by the cloud platform, and acquiring a software development kit according to the test software information. The test software information may be a test software version, and after the vehicle receives the test software version sent by the cloud platform, the corresponding software development kit is downloaded. The software development kit may be obtained before the test instruction and the configuration file sent by the cloud platform are received, or may be obtained after the test instruction and the configuration file sent by the cloud platform are received.

S302, executing a test case set according to the test instruction, and collecting test data corresponding to the characteristic signals and the buried point information according to the data collection rule.

After the test case set is obtained, the test case set is executed according to the test instruction, the test execution module 211 in fig. 2 executes the test case set, and the characteristic signals and the data corresponding to the embedded point information are collected according to the data collection rule to be used as test data.

In some embodiments, the test case set may be an automatic test, or may be tested by a tester, and the vehicle during the test may be in a manual driving state, an automatic driving state, an assisted driving state, or the like, or may be in a non-driving state.

S303, sending the test data to the cloud platform so that the cloud platform can evaluate the effect of the vehicle based on the software and hardware of the vehicle according to the test data to obtain an evaluation result of the vehicle.

After the test data are obtained, the test data are sent to the cloud platform, and the vehicle can be evaluated according to the test data by the cloud platform through the data embedded point software development kit.

The evaluation result may be a score for scoring the vehicle effect, or may be an evaluation of the vehicle effect, for example, "good", "medium", "bad", or the like.

As shown in fig. 7, a test software version sent by a cloud platform is received first, then a software development kit is downloaded according to the test software version, then a configuration file and a test instruction sent by the cloud platform are received, the configuration file is downloaded and loaded by the software development kit to obtain a test case set, and then the test case set is executed to collect test data and send the test data to the cloud platform for vehicle evaluation.

In this embodiment, a test instruction and a configuration file sent by a cloud platform are received, the configuration file includes a test case set, a feature signal to be collected and embedded point information, the test case set is executed according to the test instruction, test data corresponding to the feature signal and the embedded point information are collected, so that an evaluation result is determined according to the test data, the test data which can embody an actual effect and a compatible condition of vehicle software when the vehicle software runs on vehicle hardware can be obtained by executing the test case set, the actual running condition of the vehicle software and the hardware can be accurately indicated according to the test data, and further the obtained evaluation result according to the test data can refer to the evaluation result of the vehicle software and the hardware, and accuracy of the vehicle evaluation result is improved.

Referring to fig. 8, fig. 8 is a schematic diagram of a vehicle evaluation system according to an embodiment of the present application. The vehicle evaluation system comprises a cloud platform and a vehicle, wherein the cloud platform sends test software information to the vehicle through communication connection between the cloud platform and the vehicle, the vehicle downloads a corresponding software development kit according to the software test information, a test instruction is sent to the vehicle along with the platform, the cloud platform generates a configuration file and stores the configuration file in a data embedded point configuration system, the software development kit downloads the configuration file from the data embedded point configuration system according to the test instruction, a test execution module of the vehicle executes a test on a vehicle-mounted electronic system according to the configuration file, a data acquisition module acquires test data, the test data is then sent to the cloud platform through the software development kit, a score calculation module of the cloud platform carries out score calculation on an evaluation index according to the test data, and finally the comprehensive evaluation module carries out weighted summation on scores calculated by the score calculation module to obtain an evaluation result of the vehicle.

Referring to fig. 9, fig. 9 is a block diagram showing a vehicle evaluating apparatus according to still another embodiment of the present application. For a cloud platform, apparatus 400 includes:

The first sending module 401 is configured to send a test instruction and a configuration file to a vehicle, so that the vehicle executes a test case set according to the test instruction, and collects test data corresponding to a characteristic signal and buried point information according to a data collection rule; the configuration file comprises a test case set, a data acquisition rule, characteristic signals required to be acquired and buried point information;

and the evaluation module 402 is configured to receive test data sent by the vehicle, perform effect evaluation on the vehicle based on software and hardware of the vehicle according to the test data, and obtain an evaluation result of the vehicle.

Optionally, the evaluation module 402 is further configured to classify the test data according to a plurality of evaluation indexes corresponding to the test case set, to obtain respective data to be evaluated of each evaluation index, where each evaluation index includes a plurality of evaluation features; classifying the respective data to be evaluated of each evaluation index according to a plurality of evaluation features included in each evaluation index to obtain feature evaluation data corresponding to the plurality of evaluation features under each evaluation index; inputting the characteristic evaluation data corresponding to each of the plurality of evaluation characteristics under each evaluation index into an evaluation model to obtain an evaluation result corresponding to each evaluation index; and determining the evaluation result of the vehicle according to the evaluation results corresponding to the plurality of evaluation indexes.

Optionally, the evaluation module 402 is further configured to obtain a plurality of sample test data of the sample vehicle, where each sample test data includes a sample evaluation data of a plurality of evaluation indexes and a sample evaluation result of each sample test data, and the sample test data of each evaluation index includes a sample feature test data of a plurality of evaluation features under each evaluation index; for each sample test data, constructing a feature vector corresponding to the sample test data according to the sample feature test data of each of a plurality of evaluation features under each evaluation index; constructing label vectors corresponding to the plurality of sample test data according to respective sample evaluation results of the plurality of sample test data; and training a support vector machine in an initial state according to the feature vectors corresponding to the sample test data and the label vectors corresponding to the sample test data to obtain an evaluation model.

Optionally, the evaluation module 402 is further configured to train a support vector machine in an initial state according to the feature vectors corresponding to the plurality of sample test data and the tag vectors corresponding to the plurality of sample test data, to obtain an initial evaluation model; inputting the test data corresponding to the at least one evaluation index into an initial evaluation model to obtain an initial evaluation result corresponding to the at least one evaluation index; constructing a confusion matrix corresponding to the initial evaluation model according to the initial evaluation result corresponding to the at least one evaluation index and the test data evaluation result corresponding to the test data of the at least one evaluation index; and if the confusion matrix does not meet the preset condition, correcting the initial evaluation model according to the confusion matrix to obtain the evaluation model.

Optionally, the evaluation module 402 is further configured to construct a hierarchy according to a plurality of evaluation indexes, where the hierarchy includes a plurality of evaluation criteria, and each evaluation criterion includes a plurality of evaluation indexes; constructing a criterion judgment matrix among a plurality of evaluation criteria according to the plurality of evaluation criteria, wherein the criterion judgment matrix comprises a relative value between any two evaluation criteria, and the relative value between any two evaluation criteria indicates the importance of one evaluation criterion in the any two evaluation criteria to the other evaluation criterion; normalizing the criterion judgment matrix corresponding to the plurality of evaluation criteria to obtain a criterion weight matrix corresponding to the plurality of evaluation criteria; determining the consistency ratio of the criterion weight matrix according to the order of the criterion weight matrix and the maximum value in the criterion weight matrix; if the consistency ratio of the criterion weight matrix is smaller than a preset threshold, determining an evaluation result of the vehicle according to respective evaluation results of a plurality of evaluation indexes under each evaluation criterion side.

Optionally, the evaluation module 402 is further configured to construct an index judgment matrix between the multiple evaluation indexes under each evaluation criterion according to the multiple evaluation indexes included in each evaluation criterion; normalizing the index judgment matrix among the plurality of evaluation indexes under each evaluation criterion to obtain an index weight matrix corresponding to each evaluation criterion; determining the consistency ratio of the index weight matrix corresponding to each evaluation criterion according to the order and the maximum value of the index weight matrix corresponding to each evaluation criterion; if the consistency ratio of the index weight matrix corresponding to the evaluation criterion is smaller than a preset threshold, determining the weight value corresponding to each of a plurality of evaluation indexes under the evaluation criterion according to the index weight matrix corresponding to the evaluation criterion; for each evaluation criterion, weighting and summing the evaluation results corresponding to the plurality of evaluation indexes under the evaluation criterion according to the weight values corresponding to the plurality of evaluation indexes under the evaluation criterion to obtain the evaluation result of the evaluation criterion; determining the weight value of each of a plurality of evaluation criteria according to the criterion weight matrix; and according to the weight values of the evaluation criteria, carrying out weighted summation on the evaluation results of the evaluation criteria to obtain the evaluation results of the vehicle.

Referring to fig. 10, fig. 10 is a block diagram showing a vehicle evaluating apparatus according to an embodiment of the present application. For a vehicle, the apparatus 500 includes:

the second receiving module 501 is configured to receive a test instruction and a configuration file sent by the cloud platform, where the configuration file includes a test case set, a feature signal to be collected, and buried point information;

the data acquisition module 502 is configured to execute a test case set according to the test instruction, and acquire test data corresponding to the characteristic signal and the buried point information according to a data acquisition rule;

the second sending module 503 is configured to send the test data to the cloud platform, so that the cloud platform performs effect evaluation based on software and hardware of the vehicle on the vehicle according to the test data, and obtains an evaluation result of the vehicle.

It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the apparatus and modules described above may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.

In addition, each function in each embodiment of the present application may be integrated into one processing module, each module may exist alone physically, or two or more modules may be integrated into one module. The integrated modules may be implemented in hardware or in software functional modules.

In another aspect, the present application also provides a computer readable storage medium having stored therein program code that can be invoked by a processor to perform the method described in the above method embodiments.

The computer readable storage medium may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a cluster of ROMs. Optionally, the computer readable storage medium comprises a non-volatile computer readable storage medium (non-transitoroompter-readabblestonemagemedium). The computer readable storage medium has storage space for program code to perform any of the method steps described above. The program code can be read from or written to one or more computer program products. The program code may be compressed, for example, in a suitable form.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be appreciated by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not drive the essence of the corresponding technical solutions to depart from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A vehicle evaluation method, applied to a cloud platform, the method comprising:

transmitting a test instruction and a configuration file to a vehicle so that the vehicle executes a test case set according to the test instruction, and collecting test data corresponding to characteristic signals and buried point information according to a data collection rule; the configuration file comprises a test case set, a data acquisition rule, characteristic signals to be acquired and buried point information;

and receiving test data sent by the vehicle, and performing effect evaluation on the vehicle based on software and hardware of the vehicle according to the test data to obtain an evaluation result of the vehicle.

2. The method according to claim 1, wherein the evaluating the vehicle according to the test data to obtain the evaluation result of the vehicle comprises:

classifying the test data according to a plurality of evaluation indexes corresponding to the test case set to obtain respective data to be evaluated of each evaluation index, wherein each evaluation index comprises a plurality of evaluation characteristics;

classifying the data to be evaluated of each evaluation index according to a plurality of evaluation features included in each evaluation index to obtain feature evaluation data corresponding to the plurality of evaluation features under each evaluation index;

Inputting the characteristic evaluation data corresponding to each of the plurality of evaluation characteristics under each evaluation index into an evaluation model to obtain an evaluation result corresponding to each evaluation index;

and determining the evaluation result of the vehicle according to the evaluation results corresponding to the plurality of evaluation indexes.

3. The method of claim 2, wherein the training method of the evaluation model comprises:

acquiring a plurality of sample test data of a sample vehicle, wherein each sample test data comprises sample evaluation data of a plurality of evaluation indexes and sample evaluation results of each sample test data, and each sample test data of each evaluation index comprises sample characteristic test data of a plurality of evaluation characteristics under each evaluation index;

constructing feature vectors corresponding to the sample test data according to the sample feature test data of each of a plurality of evaluation features under each evaluation index aiming at each sample test data;

constructing label vectors corresponding to the plurality of sample test data according to respective sample evaluation results of the plurality of sample test data;

and training a support vector machine in an initial state according to the feature vectors corresponding to the sample test data and the label vectors corresponding to the sample test data to obtain the evaluation model.

4. The method of claim 3, wherein training the support vector machine in the initial state according to the feature vectors corresponding to the sample test data and the label vectors corresponding to the sample test data to obtain the evaluation model includes:

training a support vector machine in an initial state according to the feature vectors corresponding to the sample test data and the label vectors corresponding to the sample test data to obtain an initial evaluation model;

inputting test data corresponding to at least one evaluation index into the initial evaluation model to obtain an initial evaluation result corresponding to the at least one evaluation index;

constructing a confusion matrix corresponding to the initial evaluation model according to the initial evaluation result corresponding to the at least one evaluation index and the test data evaluation result corresponding to the test data of the at least one evaluation index;

and if the confusion matrix does not meet the preset condition, correcting the initial evaluation model according to the confusion matrix to obtain the evaluation model.

5. The method according to claim 2, wherein the determining the evaluation result of the vehicle according to the evaluation results corresponding to the plurality of evaluation indexes includes:

Constructing a hierarchical structure according to the plurality of evaluation indexes, wherein the hierarchical structure comprises a plurality of evaluation criteria, and each evaluation criterion comprises a plurality of evaluation indexes;

constructing a criterion judgment matrix among a plurality of evaluation criteria according to the plurality of evaluation criteria, wherein the criterion judgment matrix comprises a relative value between any two evaluation criteria, and the relative value between any two evaluation criteria indicates the importance of one evaluation criterion in the any two evaluation criteria to the other evaluation criteria;

normalizing the criterion judgment matrix corresponding to the plurality of evaluation criteria to obtain a criterion weight matrix corresponding to the plurality of evaluation criteria;

determining the consistency ratio of the criterion weight matrix according to the order of the criterion weight matrix and the maximum value in the criterion weight matrix;

and if the consistency ratio of the criterion weight matrix is smaller than a preset threshold, determining the evaluation result of the vehicle according to the respective evaluation results of the plurality of evaluation indexes under each evaluation criterion side.

6. The method according to claim 5, wherein the determining the evaluation result of the vehicle based on the respective evaluation results of the plurality of evaluation indexes under each of the evaluation quasi sides includes:

Constructing an index judgment matrix among a plurality of evaluation indexes under each evaluation criterion according to the plurality of evaluation indexes included in each evaluation criterion;

normalizing the index judgment matrix among the plurality of evaluation indexes under each evaluation criterion to obtain an index weight matrix corresponding to each evaluation criterion;

determining the consistency ratio of the index weight matrix corresponding to each evaluation criterion according to the order and the maximum value of the index weight matrix corresponding to each evaluation criterion;

if the consistency ratio of the index weight matrix corresponding to the evaluation criterion is smaller than a preset threshold, determining the weight value corresponding to each of a plurality of evaluation indexes under the evaluation criterion according to the index weight matrix corresponding to the evaluation criterion;

for each evaluation criterion, according to the weight values corresponding to the evaluation indexes under the evaluation criterion, carrying out weighted summation on the evaluation results corresponding to the evaluation indexes under the evaluation criterion to obtain the evaluation results of the evaluation criterion;

determining the weight value of each of a plurality of evaluation criteria according to the criterion weight matrix;

and according to the weight values of the evaluation criteria, carrying out weighted summation on the evaluation results of the evaluation criteria to obtain the evaluation results of the vehicle.

7. A vehicle evaluation method, characterized by being applied to a vehicle, comprising:

receiving a test instruction and a configuration file sent by a cloud platform, wherein the configuration file comprises a test case set, characteristic signals to be acquired and buried point information;

executing the test case set according to the test instruction, and collecting test data corresponding to the characteristic signals and the buried point information according to the data collection rule;

and sending the test data to the cloud platform, so that the cloud platform carries out effect evaluation on the vehicle based on vehicle software and hardware according to the test data, and an evaluation result of the vehicle is obtained.

8. A cloud platform, characterized in that the cloud platform comprises:

one or more first processors;

a first memory;

one or more first applications, wherein the one or more first applications are stored in the first memory and configured to be executed by the one or more first processors, the one or more first applications configured to perform the method of any of claims 1-6.

9. A vehicle, characterized in that the vehicle comprises:

One or more second processors;

a second memory;

one or more second applications, wherein the one or more second applications are stored in the second memory and configured to be executed by the one or more second processors, the one or more second applications configured to perform the method of claim 7.

10. A computer readable storage medium, characterized in that the computer readable storage medium stores a program code executable by a processor, which program code, when executed by the processor, causes the processor to perform the method of any of claims 1-7.