CN114842573B

CN114842573B - Vehicle test data processing method, system and cloud platform

Info

Publication number: CN114842573B
Application number: CN202210343713.2A
Authority: CN
Inventors: 李茂生; 蓝超浩; 邓晓仪; 郭杰军; 李芷筠; 黄润鑫
Original assignee: Zongshen Piaggio Foshan Motorcycle Co Ltd
Current assignee: Zongshen Piaggio Foshan Motorcycle Co Ltd
Priority date: 2022-04-02
Filing date: 2022-04-02
Publication date: 2023-05-23
Anticipated expiration: 2042-04-02
Also published as: CN114842573A

Abstract

According to the vehicle test data processing method, system and cloud platform, the first association condition of the first maintenance description of the previously set sample in the data and the first maintenance description of the derivative sample in the derivative vehicle working state test set is obtained firstly, and the collected vehicle working state test set and/or the residual maintenance description in the derivative vehicle working state test set are identified after the first association condition is determined, so that the collected vehicle working state test set is optimized, namely the residual maintenance description which is irrelevant to the first association condition in the vehicle working state test set can be identified after the first association condition is obtained is executed, the problem that the residual maintenance description is inaccurate is solved, and therefore the accuracy of the vehicle working state test set can be effectively improved, and the possibility of vehicle faults can be reduced.

Description

Vehicle test data processing method, system and cloud platform

Technical Field

The application relates to the technical field of data processing, in particular to a vehicle test data processing method, a vehicle test data processing system and a cloud platform.

Background

Data processing is a fundamental link of system engineering and automatic control. Data processing extends throughout various areas of social production and social life. The development of data processing technology and the breadth and depth of application thereof greatly influence the progress of human society development.

At present, the technology applied to data processing is more and more widely applied, so that the efficiency can be effectively improved, and the labor cost can be reduced. For example, taking a vehicle test as an example, the types of data of the vehicle test are relatively large (such as vehicle brake data and vehicle engine operation data) and a lot of time is consumed by manually analyzing, and inaccuracy of data analysis or omission of data may occur to cause no analysis. Therefore, it is difficult to ensure the accuracy of the vehicle operating state test set.

Disclosure of Invention

In view of the above, the application provides a vehicle test data processing method, a vehicle test data processing system and a cloud platform.

In a first aspect, a vehicle test data processing method is provided, including: identifying a first maintenance description of a previously set sample in the collected vehicle working state test set and a first maintenance description of a derivative sample in the derivative vehicle working state test set; obtaining a first association situation between a first maintenance description of a previously set sample and a first maintenance description of a derived sample; optimizing the collected vehicle working state test set through a first maintenance description of the derivative sample in combination with the first association condition; wherein one or more of the remaining maintenance descriptions of the pre-set samples in the already-collected vehicle operating condition test set, the remaining maintenance descriptions of the derived samples in the derived vehicle operating condition test set are identified after determining the first correlation condition for optimizing the already-collected vehicle operating condition test set.

It can be understood that by first obtaining the first association condition of the first maintenance description of the previous set sample in the data and the first maintenance description of the derivative sample in the test set of the derived vehicle working condition, the collected vehicle working condition test set and/or the residual maintenance description in the test set of the derived vehicle working condition are identified after the first association condition is determined, so as to optimize the collected vehicle working condition test set, that is, the residual maintenance description in the test set of the vehicle working condition and not related to the first association condition can be identified after the first association condition is obtained is executed, the problem of inaccurate residual maintenance description is improved, thus effectively improving the accuracy of the test set of the vehicle working condition, and thus, reducing the possibility of vehicle faults.

In an independently implemented embodiment, before obtaining the first association between the first dimension description of the previously set sample and the first dimension description of the derived sample, the method further comprises: obtaining a second association situation between the initial maintenance description in the initial vehicle working state test set and the first maintenance description of the previously set sample in the collected vehicle working state test set; the first maintenance description of the derived sample is determined by carrying out feature selection on initial maintenance descriptions in an initial vehicle working state test set and combining the initial maintenance descriptions in the corresponding feature selection set; detecting an initial maintenance description and a prior setting sample of the second association condition meeting the first prior setting requirement; optimizing the first maintenance description of the corresponding pre-set sample in the collected vehicle working state test set through the detected initial maintenance description, and eliminating the first maintenance description of the derivative sample corresponding to the detected initial maintenance description in the derivative vehicle working state test set.

It can be appreciated that by optimizing the collected vehicle operating condition test set for the first time through the initial vehicle operating condition test set before the first association condition is processed, and by optimizing the derived vehicle operating condition test set and the collected vehicle operating condition test set after the optimization, the likelihood that the initial maintenance description in the initial vehicle operating condition test set can be added to the collected vehicle operating condition test set is improved.

In an independently implemented embodiment, after rejecting a first service description of a derived sample in a test set of derived vehicle operating conditions corresponding to the detected initial service description, the method further comprises: marking the derived sample from which the first maintenance description is removed as the sample to be removed so as to remove the second maintenance description of the sample to be removed after the second maintenance description of the derived sample is identified later.

It can be understood that, instead of removing the second maintenance description of the derived sample at the same time when removing the content of the first maintenance description, the derived sample from which the first maintenance description has been removed is marked, and when the second maintenance description needs to be used, the second maintenance description is identified and the removing step of the second maintenance description of the derived sample is performed, so that the difficulty in identifying the second maintenance description is reduced.

In an independently implemented embodiment, before obtaining the first association between the first dimension description of the previously set sample and the first dimension description of the derived sample, the method further comprises: identifying a first maintenance description of a candidate sample in the candidate vehicle working state test set, and obtaining a third association condition between the first maintenance description of the derivative sample and the first maintenance description of the candidate sample; and optimizing the working state test set of the derivative vehicle by combining the third association condition.

It can be understood that by optimizing the derived vehicle operating state test set by the candidate vehicle operating state test set, the sample data volume of the derived vehicle operating state test set is improved, so that more and more vehicle abnormal data can be loaded into the collected vehicle operating state test set, and the optimization possibility of the collected vehicle operating state test set is improved.

In an independently implemented embodiment, optimizing the derived vehicle operating condition test set in combination with the third association case includes: identifying a second maintenance description of the derived sample in the derived vehicle operating state test set and a second maintenance description of the candidate sample in the candidate vehicle operating state test set; optimizing a working state test set of the derivative vehicle by combining the third association condition, the second maintenance description of the derivative sample and the second maintenance description of the candidate sample; and/or optimizing a derived vehicle operating state test set comprising: splicing the maintenance description content of the candidate sample to the maintenance description content of the derivative sample, or taking the maintenance description content of the candidate sample as the maintenance description content of the updated derivative sample.

It can be understood that by identifying the second maintenance descriptions of the derived vehicle operating state test set and the candidate vehicle operating state test set, respectively, and then giving the third association condition, the second maintenance description of the derived sample, and the second maintenance description of the candidate sample to determine whether to splice the maintenance description content of the candidate sample to the maintenance description content of the derived sample or to take the maintenance description content of the candidate sample as the updated maintenance description content of the derived sample, the data in the derived vehicle operating state test set can be continuously updated when the number of sample data in the derived vehicle operating state test set is increased, so that the normal operation of the vehicle can be ensured as much as possible.

In an independently implemented embodiment, optimizing the derived vehicle operating condition test set in combination with the third association, the second maintenance description of the derived sample, and the second maintenance description of the candidate sample, comprises: selecting candidate samples and derived samples with the third association condition meeting the second preset requirement as a first pre-configured sample and a first pre-derived sample; determining a first maintenance description and a second maintenance description of the first pre-configured sample and the second pre-derived sample after splicing, and obtaining a fourth association condition between the first maintenance description and the second maintenance description after splicing; selecting a first pre-configured sample and a first pre-derived sample, the fourth association condition of which meets the third pre-set requirement, as a first reference sample and a first derived sample; splicing the maintenance description content of the first reference sample to the maintenance description content of the first derivative sample; and taking the rest candidate samples except the first reference sample as the maintenance description content of the updated derivative samples.

It can be understood that by configuring the third previous setting requirement, the association condition between the mutually spliced data meets the requirement, so that the possibility that the candidate samples spliced to the derived samples belong to the same data is higher, and the data with differences in a plurality of covers in the spliced derived samples are weakened, so that the normal operation of the vehicle cannot be accurately ensured.

In an independently implemented embodiment, optimizing a test set of vehicle operating conditions that have been collected by a first maintenance description of a derived sample in combination with a first correlation, comprises at least one of the following steps: selecting a prior setting sample and a derivative sample of which the first association condition meets the fourth prior setting requirement to obtain a first prior setting sample and a second derivative sample, and splicing the maintenance description content of the second derivative sample to the maintenance description content of the first prior setting sample; and selecting the derivative sample with the first association condition meeting the fifth prior setting requirement as a third derivative sample, and taking the maintenance description content of the third derivative sample as the maintenance description content of the updated prior setting sample on the basis that the feature selection set of the third derivative sample meets the prior setting template.

It can be understood that by configuring the fourth prior setting requirement and the fifth prior setting requirement, the derivative samples can be sorted by the already-collected vehicle working state test set when the association condition meets the requirement, or can be changed into updated prior setting samples in the already-collected vehicle working state test set, so that the continuously updated prior setting samples in the already-collected vehicle working state test set are ensured to a certain extent, and the normal operation of the vehicle can be ensured.

In an independent embodiment, selecting the first set of samples and the derived samples for which the first association meets the fourth set of prior requirements to obtain the first set of prior samples and the second derived samples comprises: selecting a first preset sample and a derivative sample of which the first association condition meets a sixth preset requirement, and determining a first preset sample and a second derivative sample; or selecting the first set sample and the derivative sample with the first association condition meeting the seventh set requirement as the first reference set sample and the second derivative sample, identifying the third maintenance description of the first reference set sample, and taking the first reference set sample and the second derivative sample as the first set sample and the second derivative sample based on the fifth association condition between the first maintenance description of the second derivative sample and the third maintenance description of the first reference set sample meeting the eighth set requirement.

It will be appreciated that by configuring the sixth and seventh prior set of requirements, more derivative data can be used to optimize the already acquired vehicle operating condition test set.

In an independently implemented embodiment, splicing the maintenance description of the candidate sample to the maintenance description of the derivative sample, or splicing the maintenance description of the second derivative sample to the maintenance description of the first prior set sample, comprises: the candidate sample and the derivative sample are correspondingly used as a first sample to be spliced and a second sample to be spliced, or the second derivative sample and the first preset sample are correspondingly used as the first sample to be spliced and the second sample to be spliced; weighting the first maintenance description of the first sample to be spliced and the first maintenance description of the second sample to be spliced so as to obtain the first maintenance description of the second sample to be spliced again; and comparing the range of the characteristic selection set of the first sample to be spliced with the range of the characteristic selection set of the second sample to be spliced, and selecting the second maintenance description bound by the characteristic selection set with the larger range as the second maintenance description of the second sample to be spliced.

It can be understood that the maintenance description content of the derivative sample is spliced with the maintenance description content of the previous setting sample, so that the first maintenance description of the spliced previous setting sample changes, and the second maintenance description becomes the optimal second maintenance description, so that the spliced previous setting sample can cover the maintenance description content of the original derivative data, the first maintenance description can represent the maintenance description of the global data in the previous setting sample, and the reliability of the maintenance data is improved.

In an independently implemented embodiment, the method further comprises, prior to optimizing the derived vehicle operating condition test set, or optimizing the already acquired vehicle operating condition test set: identifying a second maintenance description of the derived samples in the derived vehicle operating state test set; and on the basis of verifying that the derivative samples are marked as the samples to be rejected, rejecting the second maintenance description of the samples to be rejected.

It can be understood that the frequency of identifying the content of the second maintenance description can be reduced by removing the data of the second maintenance description abnormality once before optimizing the vehicle working state test set or optimizing the collected vehicle working state test set, thereby reducing the workload.

In an independently implemented embodiment, no less than one of the first association, the second association, the third association, the fourth association, and the fifth association is a matching relationship between the corresponding two maintenance descriptions.

It can be understood that whether the derived data can be spliced by the previously set samples in the collected vehicle working state test set or the data is continuously optimized in the manner of the updated previously set samples in the collected vehicle working state test set is judged by the matching relationship, so that the data can be continuously updated, and the normal operation of the vehicle is ensured to the greatest extent.

In an independent embodiment, the first maintenance description is a focusing maintenance description of a feature selection set where a sample bound with the first maintenance description is located, wherein the feature selection set is obtained by selecting a plurality of overhaul data according to the features of the covered sample; the remaining maintenance descriptions comprise at least one of a second maintenance description and a third maintenance description of the sample bound with the remaining maintenance descriptions, the second maintenance description is used for limiting the spliced feature selection set according to a specific instruction when the feature selection set where the sample bound with the second maintenance description exists is spliced, and the third maintenance description is recorded as the first maintenance description when the sample bound with the third maintenance description is recorded as the previously set sample.

It can be understood that by dividing the maintenance description into a first maintenance description, a second maintenance description and a third maintenance description, the splicing of the feature selection sets can be limited by a plurality of maintenance descriptions, so that the accuracy of the two maintenance descriptions of the splicing is improved.

In a second aspect, a vehicle test data processing system is provided comprising a processor and a memory in communication with each other, the processor being adapted to retrieve a computer program from the memory and to implement the above-mentioned method by running the computer program.

In a third aspect, a cloud platform is provided, including: a memory for storing a computer program; and the processor is connected with the memory and is used for executing the computer program stored in the memory so as to realize the method.

According to the vehicle test data processing method, system and cloud platform, the first association condition of the first maintenance description of the previously set sample in the data and the first maintenance description of the derivative sample in the derivative vehicle working state test set is obtained firstly, and the collected vehicle working state test set and/or the residual maintenance description in the derivative vehicle working state test set are identified after the first association condition is determined, so that the collected vehicle working state test set is optimized, namely, the residual maintenance description which is irrelevant to the first association condition in the vehicle working state test set can be identified after the first association condition is obtained is executed, the problem that the residual maintenance description is inaccurate is solved, and therefore the accuracy of the vehicle working state test set can be effectively improved, and the possibility of vehicle faults can be reduced.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered limiting the scope, and that other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flowchart of a vehicle test data processing method according to an embodiment of the present application.

Fig. 2 is a block diagram of a vehicle test data processing device according to an embodiment of the present application.

FIG. 3 is a block diagram of a vehicle test data processing system according to an embodiment of the present application.

Detailed Description

In order to better understand the technical solutions described above, the following detailed description of the technical solutions of the present application is provided through the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and embodiments of the present application are detailed descriptions of the technical solutions of the present application, and not limit the technical solutions of the present application, and the technical features of the embodiments and embodiments of the present application may be combined with each other without conflict.

Referring to fig. 1, a vehicle test data processing method is shown, which may include the following technical solutions described in S11-S13.

Step S11: a first maintenance description of a previously set sample of the collected vehicle operating condition test set and a first maintenance description of a derived sample of the derived vehicle operating condition test set are identified.

In the present embodiment, it is necessary to obtain the derivative vehicle operating condition test set before identifying the first maintenance description of the previously set sample in the already collected vehicle operating condition test set and the first maintenance description of the derivative sample in the derivative vehicle operating condition test set.

Further, the already collected vehicle operating state test set may be built in a cloud platform or in a residual manner for storing maintenance descriptions about some prior set-up samples.

In one possible embodiment, the maintenance description content of each previous set sample in the collected vehicle working state test set may be obtained by performing feature selection on the maintenance description related to the previous set sample, that is, the maintenance description content of each previous set sample is the maintenance description content of the feature selection set bound by the previous set sample. For example, different overhaul data covering the previous setting sample can be extracted according to the initial maintenance description of the covered previous setting sample, and then the extracted initial maintenance description is subjected to feature selection to obtain the maintenance description content of the feature selection set bound with the previous setting sample (also understood as the feature selection set where the previous setting sample is located). In a specific implementation process, the preset sample is a local sample, initial maintenance description about the local sample can be extracted from overhaul data of different local samples, and then feature selection is performed on the initial maintenance description of the local sample to obtain a feature selection set bound by each local sample, and further maintenance description of the feature selection set bound by each local sample is obtained to serve as maintenance description content of the local sample. Further, the maintenance descriptions of the previous setting samples may include a first maintenance description, a second maintenance description, and a third maintenance description. The first maintenance description of the previous setting sample may represent a focus maintenance description of a feature selection set where the previous setting sample is located, where the first maintenance description is bound. The characteristic selection set is obtained by selecting characteristics according to the covered samples in the plurality of overhaul data. The second maintenance description of the previous set sample is used for limiting the spliced feature selection set according to a specific instruction when the feature selection set of the previous set sample bound with the second maintenance description is spliced, so that the second maintenance description can be called as a focusing maintenance description. And limiting the spliced feature selection sets according to specific instructions, namely judging whether the two feature selection sets can be spliced or not. The third maintenance description of the prior setting sample is the first maintenance description when the sample record of the binding of the third maintenance description is the prior setting sample, namely the first maintenance description when the feature selection set of the prior setting sample bound by the third maintenance description exists in the collected vehicle working state test set for the first time with the prior setting sample, namely the first maintenance description of the prior setting sample when the latest generated prior setting sample file is in the collected vehicle working state test set, and the third maintenance description can be called as the original focusing maintenance description.

Further, the candidate vehicle working state test set related to the derivative vehicle working state test set has higher similarity with the vehicle working state test set collected above. The derived vehicle operating condition test set and the samples in the candidate vehicle operating condition test set, such as derived samples and candidate samples, may be local samples, residual samples, and the like, with reference to the above related maintenance descriptions of the previously set samples. The maintenance description contents of the derived sample and the candidate sample in the derived vehicle working state test set or the candidate vehicle working state test set can also be: the maintenance descriptions of the feature selection set where the sample is bound by the maintenance description content, for example, the maintenance description content of the derivative sample and the candidate sample includes a first maintenance description and a second maintenance description, and the definition of the first maintenance description and the second maintenance description can refer to the related maintenance descriptions, for example, the first maintenance description of the derivative sample is a focusing maintenance description of the feature selection set where the derivative sample is, and the second maintenance description of the derivative sample is a second maintenance description of the feature selection set where the derivative sample is. In the derivative vehicle operating condition test set and the candidate vehicle operating condition test set, the first maintenance description of the sample may or may not be consistent with the second maintenance description. For example, when the test set of the working states of the derivative vehicles is first formed, the first maintenance description of the derivative samples is the same as the second maintenance description, and if the derivative samples in the test set of the working states of the derivative vehicles are optimized, the first maintenance description may be different from the second maintenance description (the range of the second maintenance description exceeds the first maintenance description). The derived vehicle working state test set may cover a plurality of derived samples, and of course, may cover an independent derived sample. The candidate vehicle operating condition test set may also cover only one independent candidate sample. When the derived vehicle working state test set only covers one derived sample, and the range of a plurality of feature selection sets exceeds a, the derived sample has no bound feature selection set, and the derived sample at this time only includes the initial maintenance description in the initial vehicle working state test set described in the following embodiment, and does not include the first maintenance description and the second maintenance description, but can still participate in the optimization process of the collected vehicle working state test set. And if the range of the specified feature selection set is not lower than a, the result is consistent with the result that a plurality of derived samples are included in the derived vehicle working state test set.

In one possible implementation, the derived vehicle operating condition test set is used as derived maintenance description content outside of the already-collected vehicle operating condition test set for optimizing the already-collected vehicle operating condition test set. In this embodiment, the derived vehicle working state test set is obtained by selecting features from an initial maintenance description in a recently collected initial vehicle working state test set, and steps S11-S13 may be directly executed through the derived vehicle working state test set so as to implement optimization of the collected vehicle working state test set. In an alternative embodiment, in order to achieve more accurate optimization of the already-collected vehicle operating state test set, the already-collected vehicle operating state test set is optimized by generating an initial vehicle operating state test set of the derived vehicle operating state test set before executing step S11, which may be specifically as follows; in addition, on the basis that there is a candidate vehicle working condition test set that has not yet been spliced to an already-acquired vehicle working condition test set, before step S11 is performed, the derivative vehicle working condition test set is optimized by the candidate vehicle working condition test set to splice the candidate vehicle working condition test set to the derivative vehicle working condition test set, and when the already-acquired vehicle working condition test set is optimized by the optimized derivative vehicle working condition test set, the following may be referred to specifically. It should be appreciated that at least one of the above is performed by first optimizing the collected vehicle operating condition test set by generating an initial vehicle operating condition test set of the derived vehicle operating condition test set and first optimizing the derived vehicle operating condition test set by the candidate vehicle operating condition test set.

In one possible implementation, a second association between the initial maintenance description in the initial vehicle operating condition test set and the first maintenance description in the previously set sample of vehicle operating condition tests that have been collected may be obtained before the first association between the first maintenance description of the previously set sample and the first maintenance description of the derived sample is obtained. Wherein, the second association condition between the initial maintenance description in the initial vehicle working state test set and the first maintenance description of the previous set sample is obtained, which can also be understood as comparing the initial maintenance description with the first maintenance description. The following association between the first maintenance description of the processing candidate sample and the first maintenance description of the derived sample and the association between the first maintenance description of the processing derived sample and the first maintenance description of the previously set sample can also be understood as comparing the corresponding two maintenance descriptions.

In one possible implementation, the initial data in the initial vehicle operating condition test set and the maintenance description of the previously set samples in the collected vehicle operating condition test set may be combined with the service data maintenance description obtained from the service data. The initial maintenance description in the initial vehicle working state test set may represent a maintenance description of each initial data in the initial vehicle working state test set, and compared with a feature selection set covering a plurality of initial data, one of the initial data in the initial vehicle working state test set corresponds to an individual unit, the maintenance description of the initial data corresponds to a maintenance description of the unit, and the first maintenance description of the derived sample in the derived vehicle working state test set may be obtained according to the initial vehicle working state test set. Preferably, initial maintenance descriptions of corresponding samples in the initial vehicle working state test set are obtained, a plurality of feature selection sets are formed by selecting features of the initial maintenance descriptions according to a matching relationship, and then a first maintenance description of the derivative samples is determined by combining the initial maintenance descriptions in the corresponding feature selection sets. For example, when the matching relation between the initial maintenance descriptions exceeds a preset feature selection judgment value, initial data of a plurality of initial maintenance descriptions with matching relation meeting requirements are formed into a feature selection set, wherein the formed feature selection set comprises a first maintenance description and a second maintenance description, and the first maintenance description of the derivative sample is the first maintenance description of the feature selection set of the derivative sample. The first maintenance description may represent a maintenance description that can represent one feature selection set by processing an initial maintenance description of each local data in the feature selection set. Wherein the second association may be a matching relationship. When the feature selection set of the derived sample is obtained by feature selection through the initial vehicle working state test set, the first maintenance description and the second maintenance description of the derived sample are consistent.

Further, feature selection is performed by the initial vehicle operating condition test set, wherein a portion of the data may constitute the feature selection set as derived samples, but a portion of the data in the initial vehicle operating condition test set does not form derived samples. Preferably, the requirement for feature selection to be a derived sample is that the size of the initial data with the matching relationship exceeding the previously set feature selection determination value, and if the number of initial overhaul data with the matching relationship meeting the requirement is too small and the lowest range of the previously set generated feature selection set is not met, the part of initial overhaul data is not feature-selected to form the derived sample.

After obtaining a second association condition between the initial maintenance description in the initial vehicle working state test set and the first maintenance description of the collected vehicle working state test set on the previous setting sample, detecting that the second association condition meets the initial maintenance description and the previous setting sample of the first previous setting requirement. And then optimizing the first maintenance description of the corresponding prior set sample in the collected vehicle working state test set through the detected initial maintenance description. And then eliminating the first maintenance description of the derivative sample bound with the detected initial maintenance description in the derivative vehicle working state test set. Wherein the second association case includes a matching relationship between the corresponding two first dimension descriptions. The first preset requirement may be that the second association condition is not lower than the first preset determination value, for example, the first preset determination value is 1.6, and when the second association condition is not lower than 1.6, the second association condition is determined to meet the second preset requirement.

Further, the form of optimizing the first maintenance description of the corresponding pre-set sample in the already-collected vehicle working state test set by the detected initial maintenance description may be that the detected initial maintenance description is found in the derivative vehicle working state test set to the first maintenance description of the corresponding derivative sample, and then the first maintenance description of the pre-set sample is optimized by the first maintenance description of the corresponding derivative sample. Preferably, when the initial maintenance description corresponding to the derivative sample and the first maintenance description corresponding to the first setting sample are weighted, the first setting sample with the updated first maintenance description is obtained. Because the first maintenance description corresponding to the derived sample has been weighted with the first maintenance description corresponding to the previously set sample, the repetition of the data is improved, and the bound first maintenance description in the derived vehicle operating state test set can be given to the culling. After the first maintenance description of the derivative sample corresponding to the detected initial maintenance description in the working state test set of the derivative vehicle is removed, marking the derivative sample of the first maintenance description to be removed as the sample to be removed, and removing the second maintenance description of the sample to be removed after the second maintenance description of the derivative sample is subsequently identified.

Therefore, by optimizing the collected vehicle operating condition test set for the first time through the initial vehicle operating condition test set and optimizing the collected vehicle operating condition test set after optimization through the derivative vehicle operating condition test set before processing the first association condition, the possibility that the initial maintenance description in the initial vehicle operating condition test set can be added into the collected vehicle operating condition test set is improved.

In the design, when the content of the first maintenance description is removed, the derived sample from which the first maintenance description is removed is marked, and when the second maintenance description is required to be used, the second maintenance description is identified and the removing step of the second maintenance description of the derived sample is executed, so that the identification difficulty of the second maintenance description is reduced.

In an alternative embodiment, the first maintenance description of the candidate sample in the candidate vehicle operating condition test set may be identified and a third association between the first maintenance description of the derivative sample and the first maintenance description of the candidate sample may be obtained before the first association between the first maintenance description of the previously set sample and the first maintenance description of the derivative sample is obtained. And combining the third association condition to optimize the working state test set of the derivative vehicle. The candidate vehicle working state test set can be formed by remaining derivative samples in the previous sample data optimization process, wherein the remaining derivative samples in the derivative vehicle working state test set are not successfully optimized to the collected vehicle working state test set. The test set of candidate vehicle operating states can then be understood in this process, wherein the candidate samples in the test set of candidate vehicle operating states also include the first maintenance description and the second maintenance description.

Further, the optimizing the derived vehicle operating state test set in connection with the third association may be identifying a second maintenance description of the derived sample in the derived vehicle operating state test set and a second maintenance description of the candidate sample in the candidate vehicle operating state test set, and then optimizing the derived vehicle operating state test set in connection with the third association between the first maintenance description of the candidate sample and the first maintenance description of the derived sample and the second maintenance description of both. The third association case may be a matching relationship between the corresponding two first dimension descriptions. The second preset request may indicate that the third association condition is not lower than the second preset determination value, for example, when the second preset determination value is 1.6, the third association condition is determined to be in accordance with the second preset request when the third association condition is not lower than 1.6.

For example, candidate samples and derived samples that meet the second pre-set requirement for the third association case may be selected as the first pre-configured samples and the first pre-derived samples. Determining a first maintenance description and a second maintenance description of the first pre-configured sample and the second pre-derived sample after splicing, and obtaining a fourth association condition between the first maintenance description and the second maintenance description after splicing the first pre-configured sample and the second pre-derived sample. Wherein the fourth association case here may be a matching relationship. The first pre-configured samples and the first pre-derived samples, the fourth association condition of which meets the third pre-set requirement, are selected as the first reference samples and the first derived samples. The third previous setting requirement may indicate that the fourth association condition is not lower than the third previous setting determination value, for example, when the third previous setting determination value is 1.4, the fourth association condition is determined to be in accordance with the third previous setting requirement when the fourth association condition is not lower than 1.4.

The method for optimizing the derived vehicle working state test set can be to splice the maintenance description content of the candidate sample into the maintenance description content of the derived sample, or can be to take the maintenance description content of the candidate sample as the maintenance description content of the updated derived sample. The manner of splicing the maintenance description content of the candidate sample to the maintenance description content of the derivative sample may be to correspondingly use the candidate sample and the derivative sample as the first sample to be spliced and the second sample to be spliced, and then perform weighting processing on the first maintenance description of the first sample to be spliced and the second sample to be spliced so as to obtain the first maintenance description of the first sample to be spliced again. And comparing the range of the characteristic selection set of the first sample to be spliced with the range of the characteristic selection set of the second sample to be spliced, and selecting the second maintenance description bound by the characteristic selection set of the large sample to be spliced as the second maintenance description of the second sample to be spliced. Preferably, if the fourth association meets the third prior set requirement, the maintenance description of the first reference sample is spliced to the maintenance description of the first derived sample. The first maintenance description of the updated derived sample obtained after the two are spliced is obtained by reprocessing the first maintenance descriptions of the corresponding candidate sample and the derived sample, and the second maintenance description of the updated derived sample is one of the second maintenance description of the selected candidate sample and the second maintenance description of the derived sample. Specifically, the selecting step is to judge the range of the feature selection set where the candidate sample and the derivative sample are located, and select the second maintenance description as the second maintenance description of the derivative sample updated after the splicing.

And if the fourth association condition does not meet the third preset requirement, taking the remaining candidate samples except the first reference sample as the maintenance description contents of the updated derivative samples. The maintenance description may be only the first maintenance description, or may include both the first maintenance description and the second maintenance description. Therefore, by configuring the fourth prior setting requirement and the fifth prior setting requirement, the derivative samples can be sorted by the collected vehicle working state test set when the association condition meets the requirement, or can be changed into updated prior setting samples in the collected vehicle working state test set, so that the continuously updated prior setting samples in the collected vehicle working state test set are ensured to a certain extent, and the normal operation of the vehicle can be ensured.

In one possible implementation embodiment, after the second maintenance description of the derivative sample in the derivative vehicle working state test set and the second maintenance description of the candidate sample in the candidate vehicle working state test set are identified, whether the derivative sample can be spliced with the candidate sample is directly judged according to the method, if so, the first maintenance description of the derivative sample and the second maintenance description of the derivative sample are spliced, and the splicing operation of the candidate sample and the second maintenance description of the derivative sample is marked. In some possible embodiments, after identifying the second maintenance description of the derived sample in the derived vehicle working state test set, the above-mentioned labeled rejection operation of rejecting the derived sample of the first maintenance description as the second maintenance description of the sample to be rejected may be performed before optimizing the derived vehicle working state test set. And then judging candidate samples in the candidate vehicle working state test set through the second maintenance description of the remaining derivative samples, and splicing. Of course, in other possible embodiments, after the second maintenance description of the derived sample in the derived vehicle working state test set and the second maintenance description of the candidate sample in the candidate vehicle working state test set are identified, the rejection operation of the second maintenance description of the sample to be rejected, which is marked before, is not performed, whether the maintenance description content of the derived sample and the maintenance description content between the candidate samples can be spliced is directly judged, if so, the first maintenance description and the second maintenance description of the candidate sample are weighted to the corresponding derived sample, and the rejection operation of the second maintenance description of the sample to be rejected, which is marked before, is performed.

Step S12: a first association is obtained between the first maintenance description of the previously set sample and the first maintenance description of the derived sample.

The first association here may be, for example, a matching relationship between two first maintenance descriptions. The method specifically comprises the following description, the matching relation between the first maintenance description of all derived samples in the derived vehicle working state test set and the first maintenance description of all the previously set samples in the collected vehicle working state test set is processed, and the matching relation between each derived sample and the previously set sample with the best matching relation in the collected vehicle working state test set is obtained, wherein the matching relation is the first association condition. That is, the first correlation is the one with the best matching relationship between the derived sample and the previously set sample.

Step S13: optimizing the collected vehicle working state test set through a first maintenance description of the derivative sample in combination with the first association condition; wherein one or more of the remaining maintenance descriptions of the pre-set samples in the already-collected vehicle operating condition test set, the remaining maintenance descriptions of the derived samples in the derived vehicle operating condition test set are identified after determining the first correlation condition for optimizing the already-collected vehicle operating condition test set.

In one possible implementation, the optimization of the already collected vehicle operating condition test set may include stitching the maintenance descriptions of the derived samples into the maintenance descriptions of the bound prior set samples and/or adding the derived samples as updated prior set samples, i.e., the maintenance descriptions of the derived samples, to the stored data as the maintenance descriptions of the updated prior set samples.

The above is a specific optimization of the collected vehicle working state test set, and can be determined in combination with the first association situation, for example, if the first association situation is large, the maintenance description content of the derived sample is spliced into the maintenance description content of the bound previous set sample, and if the first association situation is small, the maintenance description content of the derived sample is added into the stored data to serve as the maintenance description content of the updated previous set sample. For example, a first set of samples and derived samples having a first association meeting a fourth prior set of requirements may be selected to obtain a first prior set of samples and a second derived sample, and the maintenance description of the second derived sample is spliced to the maintenance description of the first prior set of samples. The second derivative sample and the first preset sample can be correspondingly used as a first sample to be spliced and a second sample to be spliced. And carrying out weighting treatment on the first maintenance description of the first sample to be spliced and the second sample to be spliced so as to obtain the first maintenance description of the second sample to be spliced again. And then comparing the range of the characteristic selection set of the first sample to be spliced with the range of the characteristic selection set of the second sample to be spliced, and selecting the second maintenance description bound by the characteristic selection set of the large sample to be spliced as the second maintenance description of the second sample to be spliced.

In the present embodiment, the fourth prior-setting request may be divided into a sixth prior-setting request and a seventh prior-setting request. I.e. selecting the first set of samples and the derived samples for which the first association meets the sixth set of requirements, and determining the first set of samples and the second derived sample. The maintenance description of the second derived sample is then spliced to the maintenance description of the first previously set sample. Here, only the first maintenance descriptions of the two may be spliced, and the derivative sample and the previously set sample, to which the two first maintenance descriptions are respectively bound, are marked so that a splicing operation of the second maintenance descriptions of the derivative sample and the previously set sample is performed in the future. The sixth preset request may be identical to the first preset request. If the matching relationship between the pre-set sample and the derived sample is sufficiently large, the likelihood that the pre-set sample and the derived sample belong to the same data is high, and therefore, when the matching relationship meets the first pre-set requirement or the sixth pre-set requirement, the pre-set sample and the derived sample can be directly spliced. By configuring the sixth and seventh pre-set requirements, more derived data can be used to optimize the already acquired vehicle operating state test set.

The first correlation case meets the first preset sample and the derivative sample of the first preset requirement are selected as the first reference preset sample and the second preset sample. The seventh pre-set requirement here may indicate that the matching relationship exceeds the lowest decision value of the splice of the pre-set samples, and then the second pre-derived sample may possibly result in a second splice. The third maintenance description of the first reference pre-set sample is identified, and the first reference pre-set sample and the second pre-derived sample are taken as the first pre-set sample and the second derived sample based on the fifth association between the first maintenance description of the second pre-derived sample and the third maintenance description of the first reference pre-set sample meeting the eighth pre-set requirement. For example, the possibility of re-splicing is to obtain a matching relationship between the first maintenance description of the second pre-derived sample and the third maintenance description of the first reference pre-set sample, and if the matching relationship between the first maintenance description and the third maintenance description meets the eighth pre-set requirement, the second pre-derived sample may be spliced into the first reference pre-set sample. Here, the eighth prior setting requirement may be to exceed the lowest determination value of the splice of the prior setting samples. The seventh prior setting requirement and the eighth prior setting requirement in the present application agree.

Further, in the concatenation of the derivative sample and the previously set sample, the first maintenance description of the previously set sample after concatenation is obtained by performing a weighting process on the derivative sample and the first maintenance description of the previously set sample. The specific implementation mode comprises the steps of taking a derivative sample to be spliced and a previously set sample as a first sample to be spliced and a second sample to be spliced, and carrying out weighting treatment on first maintenance descriptions of the first sample to be spliced and the second sample to be spliced so as to obtain first maintenance descriptions of the second sample to be spliced again. The derived samples may be the first samples to be spliced or the second samples to be spliced. And comparing the range of the derivative sample to be spliced with the range of the sample set in advance, namely selecting the second maintenance description bound by the larger characteristic selection set as the second maintenance description of the second sample to be spliced after splicing, wherein the range of the characteristic selection set is the range of the derivative sample and the sample set in advance.

In one possible implementation, after determining that the derived sample and the previously set sample have the splicing requirement, before optimizing the vehicle working state test set or during optimizing the collected vehicle working state test set, identifying a second maintenance description of the derived sample in the derived vehicle working state test set, and rejecting the second maintenance description of the sample to be rejected based on verifying that the derived sample is marked as the sample to be rejected. And e.g. optimizing the rejection steps of the derived vehicle operating condition test set left in the collected vehicle operating condition test set and the second maintenance description in the collected vehicle operating condition test set by the initial vehicle operating condition test set.

Optimizing the already collected vehicle operating state test set through the first maintenance description of the derived samples in combination with the first association case may further include: and selecting the derivative sample with the first association condition meeting the fifth prior setting requirement as a third derivative sample, and taking the maintenance description content of the third derivative sample as the maintenance description content of the updated prior setting sample on the basis that the feature selection set of the third derivative sample meets the prior setting template. The splicing requirement may be that the first association condition meets a fourth previous setting requirement, and at this time, the fourth previous setting requirement is configured to be that the first association condition is not lower than a fourth previous setting determination value. Preferably, the first and fourth prior setting requirements may coincide, i.e. the first and fourth prior setting decision values coincide.

In one possible implementation embodiment, the derived sample with the first association condition meeting the fifth previous setting requirement is selected as the third derived sample, and the maintenance description content of the third derived sample is used as the maintenance description content of the updated previous setting sample based on the feature selection set of the third derived sample meeting the previous setting template.

The fifth prior setting request may be that the first association condition is lower than the fifth prior setting determination value. The fifth preset determination value may be the maximum determination value of the preset samples generated by the preset, and thus the fifth preset determination value is lower than the seventh preset determination value in the seventh preset request. If the first association condition is lower than the fifth preset determination value, the matching relationship between the derived sample and all the preset samples in the collected vehicle working state test set is lower, and the collected vehicle working state test set does not have the preset samples belonging to the same sample as the derived sample. For example, when the matching relationship between a derived sample and all the previously set samples in the already collected vehicle working state test set is lower than the fifth previously set determination value, and the derived sample covers a plurality of contents, that is, covers a plurality of overhaul data, and accords with the lowest range of the generated previously set samples, the derived sample can be added into the already collected vehicle working state test set by the updated previously set samples. A portion of the final derived vehicle operating condition test set that is not added to the already collected vehicle operating condition test set will form a candidate vehicle operating condition test set.

The method comprises the steps of optimizing an acquired vehicle working state test set once through an initial vehicle working state test set, selecting features of the initial vehicle working state test set to obtain a derivative vehicle working state test set, optimizing the derivative vehicle working state test set through a candidate vehicle working state test set to obtain an updated derivative vehicle working state test set, and optimizing the acquired vehicle working state test set by using the updated derivative vehicle working state test set. It should be appreciated that some ways of optimizing the collected vehicle operating condition test set by the maintenance description of the derived sample in the derived vehicle operating condition test set are provided above, and in the embodiments of the present disclosure, the optimizing the collected vehicle operating condition test set by the maintenance description of the derived sample in the derived vehicle operating condition test set may also be implemented by similar ways of optimizing the derived vehicle operating condition test set by the candidate vehicle operating condition test set, for example, selecting the previously set sample and the derived sample, where the first association condition meets the above-mentioned second previously set requirement, as the previously set sample to be selected and the previously derived sample; determining a first maintenance description and a second maintenance description of a to-be-selected pre-set sample and a pre-derived sample after splicing, and obtaining a fourth association condition between the first maintenance description and the second maintenance description after splicing; selecting a to-be-selected prior setting sample and a pre-derived sample, the fourth association condition of which meets the third prior setting requirement, as the to-be-spliced prior setting sample and the to-be-spliced derived sample; splicing the maintenance description content of the derivative sample to be spliced to the maintenance description content of the pre-set sample to be spliced; and taking the residual derived samples except the samples to be subjected to splicing derived as the maintenance description contents of the updated previous setting samples.

According to the above, by first obtaining the first association condition of the first maintenance description of the previously set sample in the data and the first maintenance description of the derived sample in the derived vehicle operation state test set, the remaining maintenance descriptions in the already-collected vehicle operation state test set and/or the derived vehicle operation state test set are identified after the first association condition is determined, so that the already-collected vehicle operation state test set is optimized, that is, the remaining maintenance descriptions in the vehicle operation state test set which are not related to the obtained first association condition can be identified after the first association condition is obtained is performed, the problem that the remaining maintenance descriptions are inaccurate is improved, so that the accuracy of the vehicle operation state test set can be effectively improved, and therefore, the possibility of the vehicle failure can be reduced.

On the basis of the above, please refer to fig. 2 in combination, there is provided a vehicle test data processing apparatus 200, which is applied to a vehicle test data processing system, the apparatus comprising:

a description identifying module 210 for identifying a first maintenance description of a previously set sample of the collected vehicle operation state test set and a first maintenance description of a derived sample of the derived vehicle operation state test set;

a case obtaining module 220, configured to obtain a first association case between the first maintenance description of the previously set sample and the first maintenance description of the derived sample;

a vehicle testing module 230, configured to optimize the collected vehicle working state testing set through a first maintenance description of the derived sample in combination with the first association situation; wherein one or more of the remaining maintenance descriptions of the prior set sample in the already-collected vehicle operating condition test set, and the remaining maintenance descriptions of the derivative sample in the derivative vehicle operating condition test set are identified after determining the first association condition for optimizing the already-collected vehicle operating condition test set.

On the basis of the above, referring to fig. 3 in combination, there is shown a vehicle test data processing system 300 comprising a processor 310 and a memory 320 in communication with each other, the processor 310 being adapted to read a computer program from the memory 320 and execute the computer program to implement the method described above.

On the basis of the above, there is also provided a computer readable storage medium on which a computer program stored which, when run, implements the above method.

In summary, based on the above-mentioned scheme, by first obtaining the first association condition of the first maintenance description of the previously set sample in the data and the first maintenance description of the derivative sample in the derivative vehicle operation state test set, the collected vehicle operation state test set and/or the residual maintenance description in the derivative vehicle operation state test set are identified after the first association condition is determined, so as to optimize the collected vehicle operation state test set, that is, the residual maintenance description in the vehicle operation state test set which is not related to the first association condition is identified after the first association condition is obtained is executed, the problem that the residual maintenance description is inaccurate is improved, so that the accuracy of the vehicle operation state test set can be effectively improved, and the possibility of vehicle failure can be reduced.

It should be appreciated that the systems and modules thereof shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may then be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, CD or DVD-ROM, a programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only with hardware circuitry, such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also with software, such as executed by various types of processors, and with a combination of the above hardware circuitry and software (e.g., firmware).

It should be noted that, the advantages that may be generated by different embodiments may be different, and in different embodiments, the advantages that may be generated may be any one or a combination of several of the above, or any other possible advantages that may be obtained.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations of the present application may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this application, and are therefore within the spirit and scope of the exemplary embodiments of this application.

Meanwhile, the present application uses specific words to describe embodiments of the present application. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present application may be combined as suitable.

Furthermore, those skilled in the art will appreciate that the various aspects of the invention are illustrated and described in the context of a number of patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.

The computer storage medium may contain a propagated data signal with the computer program code embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take on a variety of forms, including electro-magnetic, optical, etc., or any suitable combination thereof. A computer storage medium may be any computer readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or a combination of any of the foregoing.

The computer program code necessary for operation of portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, scala, smalltalk, eiffel, JADE, emerald, C ++, c#, vb net, python, etc., a conventional programming language such as C language, visual Basic, fortran 2003, perl, COBOL 2002, PHP, ABAP, dynamic programming languages such as Python, ruby and Groovy, or other programming languages, etc. The program code may execute entirely on the user's computer or as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any form of network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or the use of services such as software as a service (SaaS) in a cloud computing environment.

Furthermore, the order in which the elements and sequences are presented, the use of numerical letters, or other designations are used in the application and are not intended to limit the order in which the processes and methods of the application are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present application. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.

Likewise, it should be noted that in order to simplify the presentation disclosed herein and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the subject application. Indeed, less than all of the features of a single embodiment disclosed above.

In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the numbers allow for adaptive variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.

Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited in this application is hereby incorporated by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the present application, documents that are currently or later attached to this application for which the broadest scope of the claims to the present application is limited. It is noted that the descriptions, definitions, and/or terms used in the subject matter of this application are subject to such descriptions, definitions, and/or terms if they are inconsistent or conflicting with such descriptions, definitions, and/or terms.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of this application. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present application may be considered in keeping with the teachings of the present application. Accordingly, embodiments of the present application are not limited to only the embodiments explicitly described and depicted herein.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims

1. A vehicle test data processing method, characterized by being applied to a data processing system, the method comprising at least:

identifying a first maintenance description of a previous set sample in an collected vehicle working state test set and a first maintenance description of a derivative sample in a derivative vehicle working state test set, wherein the maintenance description content of each previous set sample in the collected vehicle working state test set is obtained by carrying out feature selection on the maintenance description related to the previous set sample, specifically, the first maintenance description of the derivative sample is obtained by extracting different overhaul data covering the previous set sample according to the initial maintenance description of the covered previous set sample, then carrying out feature selection on the extracted initial maintenance description, so as to obtain the maintenance description content of a feature selection set bound with the previous set sample, the first maintenance description of the previous set sample represents the focused maintenance description of the feature selection set of the previous set sample, and the feature selection set is obtained by carrying out feature selection on the plurality of overhaul data according to the covered sample;

Obtaining a first association condition between a first maintenance description of the pre-set sample and a first maintenance description of the derivative sample, wherein data with a size of initial data, of which the matching relationship in an initial vehicle working state test set exceeds a pre-set feature selection judgment value, is subjected to feature selection as the derivative sample, and the first association condition is a matching relationship between two first maintenance descriptions, specifically: processing the matching relation between the first maintenance descriptions of all the derivative samples in the derivative vehicle working state test set and the first maintenance descriptions of all the previously set samples in the collected vehicle working state test set to obtain the matching relation between each derivative sample and the previously set sample with the best matching relation in the collected vehicle working state test set, wherein the matching relation is the first association condition;

optimizing the collected vehicle working state test set through the first maintenance description of the derivative sample in combination with the first association condition; wherein one or more of the remaining maintenance descriptions of the prior set sample in the already-collected vehicle operating condition test set, the remaining maintenance descriptions of the derivative sample in the derivative vehicle operating condition test set are identified after determining the first association condition for optimizing the already-collected vehicle operating condition test set;

The optimizing the collected vehicle working state test set through the first maintenance description of the derivative sample according to the first association condition comprises the following steps of:

selecting a prior setting sample and a derivative sample of which the first association condition meets a fourth prior setting requirement to obtain a first prior setting sample and a second derivative sample, and splicing the maintenance description content of the second derivative sample to the maintenance description content of the first prior setting sample;

and selecting the derivative sample of which the first association condition meets the fifth prior setting requirement as a third derivative sample, and taking the maintenance description content of the third derivative sample as the updated maintenance description content of the prior setting sample on the basis that the feature selection set of the third derivative sample meets the prior setting template.

2. The method of claim 1, wherein prior to the obtaining the first association between the first maintenance description of the prior set sample and the first maintenance description of the derived sample, the method further comprises:

obtaining a second association condition between an initial maintenance description in an initial vehicle working state test set and a first maintenance description of a previously set sample in the collected vehicle working state test set; the first maintenance description of the derivative sample is determined by carrying out feature selection on initial maintenance descriptions in the initial vehicle working state test set and combining the initial maintenance descriptions in the corresponding feature selection set;

Detecting an initial maintenance description and a prior setting sample of the second association condition meeting a first prior setting requirement; optimizing the first maintenance description of the corresponding pre-set sample in the collected vehicle working state test set through the detected initial maintenance description, and eliminating the first maintenance description of the derivative sample corresponding to the detected initial maintenance description in the derivative vehicle working state test set.

3. The method of claim 2, wherein after said rejecting a first maintenance description of said derived sample corresponding to said detected initial maintenance description in said derived vehicle operating condition test set, said method further comprises: marking the derived sample from which the first maintenance description is removed as a sample to be removed, so as to remove a second maintenance description of the sample to be removed after the second maintenance description of the derived sample is identified later, wherein the second maintenance description is used for limiting the spliced feature selection set according to a specific instruction when the feature selection set of the sample bound with the second maintenance description is spliced.

4. A method according to claim 3, wherein prior to said obtaining a first association between the first maintenance description of the prior set sample and the first maintenance description of the derived sample, the method further comprises: identifying a first maintenance description of a candidate sample in a candidate vehicle working state test set, and obtaining a third association condition between the first maintenance description of the derivative sample and the first maintenance description of the candidate sample; and optimizing the working state test set of the derivative vehicle according to the third association condition.

5. The method of claim 4, wherein said optimizing said set of derived vehicle operating condition tests in combination with said third association comprises:

identifying a second maintenance description of a derivative sample in the derivative vehicle working state test set and a second maintenance description of a candidate sample in the candidate vehicle working state test set; optimizing the derived vehicle working state test set by combining the third association, the second maintenance description of the derived sample and the second maintenance description of the candidate sample;

and/or, said optimizing said derived vehicle operating condition test set comprises: splicing the maintenance description content of the candidate sample to the maintenance description content of the derivative sample, or taking the maintenance description content of the candidate sample as the updated maintenance description content of the derivative sample.

6. The method of claim 5, wherein said optimizing said derived vehicle operating condition test set in combination with said third correlation, said derived sample second maintenance description, and candidate sample second maintenance description comprises:

selecting candidate samples and derived samples, the third association condition of which meets the second preset requirement, as a first pre-configuration sample and a first pre-derived sample;

Determining a first maintenance description and a second maintenance description of the first pre-configured sample and the second pre-derived sample after splicing, and obtaining a fourth association condition between the first maintenance description and the second maintenance description after splicing;

selecting a first pre-configuration sample and a first pre-derivative sample, the fourth association condition of which meets the third pre-setting requirement, as a first reference sample and a first derivative sample;

splicing the maintenance description content of the first reference sample to the maintenance description content of the first derivative sample; and taking the rest of the candidate samples except the first reference sample as updated maintenance descriptive contents of the derivative samples.

7. The method of claim 1, wherein the selecting the first correlation instance to meet the fourth prior-set requirement prior-set samples and derived samples to obtain the first prior-set samples and second derived samples comprises:

selecting a prior setting sample and a derivative sample of which the first association condition meets a sixth prior setting requirement, and determining a first prior setting sample and a second derivative sample;

or selecting a prior setting sample and a derivative sample, the first association condition of which meets the seventh prior setting requirement, as a first reference prior setting sample and a second prior derivative sample, identifying a third maintenance description of the first reference prior setting sample, and taking the first reference prior setting sample and the second prior derivative sample as a first prior setting sample and a second derivative sample on the basis that a fifth association condition between the first maintenance description of the second prior derivative sample and the third maintenance description of the first reference prior setting sample meets the eighth prior setting requirement;

Wherein splicing the maintenance description of the candidate sample to the maintenance description of the derivative sample or the maintenance description of the second derivative sample to the maintenance description of the first previous setting sample comprises:

the candidate sample and the derivative sample are correspondingly used as a first sample to be spliced and a second sample to be spliced, or the second derivative sample and the first preset sample are correspondingly used as the first sample to be spliced and the second sample to be spliced;

weighting the first maintenance description of the first sample to be spliced and the second sample to be spliced so as to obtain the first maintenance description of the second sample to be spliced again;

comparing the range of the characteristic selection set of the first sample to be spliced with the range of the characteristic selection set of the second sample to be spliced, and selecting a second maintenance description bound by the characteristic selection set with a larger range as a second maintenance description of the second sample to be spliced;

wherein prior to said optimizing said derived vehicle operating condition test set, or said optimizing said collected vehicle operating condition test set, said method further comprises: identifying a second maintenance description of derived samples in the derived vehicle operating state test set; on the basis of verifying that the derived sample is marked as a sample to be removed, removing a second maintenance description of the sample to be removed;

The remaining maintenance description includes at least one of a second maintenance description and a third maintenance description of a sample bound to the remaining maintenance description, the third maintenance description being a first maintenance description when the sample bound to the third maintenance description is recorded as the previously set sample.

8. A vehicle test data processing system comprising a processor and a memory in communication with each other, said processor being adapted to retrieve a computer program from said memory and to implement the method of any of claims 1-7 by running said computer program.

9. A cloud platform, comprising:

a memory for storing a computer program;

a processor coupled to the memory for executing a computer program stored in the memory for implementing the method of any one of claims 1-7.