Vehicle data management method and device, computer equipment and storage medium

Abstract

The invention relates to a vehicle data management method and device, computer equipment and a storage medium. The method comprises the steps that the data type of vehicle part performance data and the data type of vehicle fault frequency are obtained, the vehicle part performance data are the vehicle part performance data type, and the vehicle fault frequency is the vehicle fault frequency type; determining whether the vehicle component performance data type and the vehicle fault frequency type are both quantitative; in response to both quantification, performing normality test on the vehicle component performance data and the vehicle fault frequency to obtain a normality test result; determining a first correlation analysis algorithm according to the normality test result; or in response to determining that at least one is not quantitative, determining a second correlation analysis algorithm; and obtaining the correlation between the vehicle part performance data and the vehicle fault frequency according to the first correlation analysis algorithm or the second correlation analysis algorithm. By adopting the method, the accuracy of vehicle data correlation analysis is improved.

Description

Technical Field

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

[0002] In the field of automobile manufacturing and maintenance, the correlation analysis between the performance and failure frequency of vehicle components is an important way to improve production efficiency and vehicle reliability. The system can identify potential failure hazards in advance by analyzing the correlation between the performance data of different vehicle components and historical failure data.

[0003] In related technologies, the selection of appropriate correlation analysis methods often depends on the analyst's experience and understanding of data characteristics. If the selection is inappropriate, it may lead to inaccurate or misleading analysis results. Summary of the invention

[0004] Based on this, it is necessary to provide a vehicle data management method, device, computer equipment and storage medium that can improve the accuracy of vehicle data correlation analysis in response to the above technical problems.

[0005] In one aspect, a vehicle data management method is provided, the method comprising:

[0006] Acquire data types of vehicle component performance data and vehicle failure frequency, wherein the data type of the vehicle component performance data is a vehicle component performance data type, and the data type of the vehicle failure frequency is a vehicle failure frequency type;

[0007] Determine whether the vehicle component performance data type and vehicle failure frequency type are both quantitative;

[0008] In response to determining that the vehicle component performance data type and the vehicle failure frequency type are both quantitative, performing a normality test on the vehicle component performance data and the vehicle failure frequency to obtain a normality test result;

[0009] Determining, based on the normality test result, a first correlation analysis algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; or

[0010] In response to determining that at least one of the vehicle component performance data type and the vehicle failure frequency type is not quantitative, determining a second correlation analysis algorithm for performing a correlation analysis on the vehicle component performance data and the vehicle failure frequency;

[0011] The correlation between the vehicle component performance data and the vehicle failure frequency is obtained according to the first correlation analysis algorithm or the second correlation analysis algorithm.

[0012] In some embodiments, the step of performing a normality test on vehicle component performance data and vehicle failure frequency to obtain a normality test result includes:

[0013] Determining a first fit between a data distribution of vehicle component performance data and a first theoretical normal distribution, and determining a second fit between a data distribution of vehicle failure frequencies and a second theoretical normal distribution;

[0014] Determining a first normality test method according to the first fitting situation, and determining a second normality test method according to the second fitting situation; and

[0015] A normality test is performed on the vehicle component performance data according to the first normality test method, and a normality test is performed on the vehicle failure frequency according to the second normality test method to obtain a normality test result.

[0016] In some embodiments, according to the normality test result, determining a first correlation analysis algorithm step for performing correlation analysis on vehicle component performance data and vehicle failure frequency includes:

[0017] Determine whether the normality test results are vehicle component performance data and vehicle failure frequency that conform to normal distribution;

[0018] In response to determining that the normality test result is that both the vehicle component performance data and the vehicle failure frequency conform to a normal distribution, determining a first preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; or

[0019] In response to determining that the normality test result is that the vehicle component performance data and the vehicle failure frequency do not conform to the normal distribution, a second preset correlation analysis algorithm is determined as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency.

[0020] In some embodiments, in response to determining that at least one of the vehicle component performance data type and the vehicle failure frequency type is not quantitative, determining a second correlation analysis algorithm step for performing a correlation analysis on the vehicle component performance data and the vehicle failure frequency includes:

[0021] In response to determining that the vehicle component performance data type and the vehicle failure frequency type are both classified, determining a third preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency;

[0022] In response to determining that the vehicle component performance data type is categorical and the vehicle failure frequency type is quantitative, determining a second preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; or

[0023] In response to the vehicle component performance data type being quantitative and the vehicle failure frequency type being categorical, a second preset correlation analysis algorithm is determined as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency.

[0024] In some embodiments, the step of obtaining data types of vehicle component performance data and vehicle failure frequency includes:

[0025] The vehicle component performance data and the vehicle failure frequency are sequentially used as the data to be analyzed, and the diversity of the data to be analyzed is analyzed to obtain a diversity index;

[0026] Determining whether the diversity index is greater than a preset index threshold;

[0027] In response to determining that the diversity index is not greater than a preset index threshold, setting the data type of the data to be analyzed to categorical; or

[0028] In response to determining that the diversity index is greater than a preset index threshold, the data type of the data to be analyzed is set to quantitative.

[0029] In some embodiments, after the step of determining whether the diversity index is greater than a preset index threshold, the method further includes:

[0030] In response to determining that the diversity index is greater than a preset index threshold, performing discretization detection on the data to be analyzed to determine the number of categories of the data to be analyzed;

[0031] Determine whether the number of categories is greater than a preset number threshold;

[0032] In response to determining that the number of categories is greater than a preset number threshold, setting the data type of the data to be analyzed to quantitative; or

[0033] In response to determining that the number of categories is not greater than a preset number threshold, the data type of the data to be analyzed is set to categorical.

[0034] In some embodiments, the step of performing discretization detection on the data to be analyzed and determining the number of categories of the data to be analyzed includes:

[0035] De-duplication processing is performed on the data to be analyzed to obtain de-duplication data;

[0036] According to the amount of deduplicated data, the number of categories of data to be analyzed is determined.

[0037] In some embodiments, the method further comprises:

[0038] Using a determined correlation analysis algorithm to perform correlation analysis on vehicle component performance data and vehicle failure frequency, obtaining a correlation analysis result, and determining a correlation analysis chart according to the vehicle component performance data type and the vehicle failure frequency type;

[0039] The correlation analysis results are presented through correlation analysis charts.

[0040] In another aspect, a vehicle data management device is provided, the device comprising:

[0041] A data type acquisition module, used to acquire data types of vehicle component performance data and vehicle failure frequency, wherein the data type of the vehicle component performance data is a vehicle component performance data type, and the data type of the vehicle failure frequency is a vehicle failure frequency type;

[0042] A quantitative determination module, used to determine whether the vehicle component performance data type and the vehicle fault frequency type are both quantitative;

[0043] A normality test module, configured to perform a normality test on the vehicle component performance data and the vehicle failure frequency in response to determining that the vehicle component performance data type and the vehicle failure frequency type are both quantitative, and obtain a normality test result;

[0044] A first correlation analysis module, used to determine a first correlation analysis algorithm for performing correlation analysis on vehicle component performance data and vehicle failure frequency according to a normality test result; or

[0045] a second correlation analysis module for determining a second correlation analysis algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency in response to determining that at least one of the vehicle component performance data type and the vehicle failure frequency type is not quantitative;

[0046] A data correlation analysis module is used to obtain the correlation between the vehicle component performance data and the vehicle failure frequency according to the first correlation analysis algorithm or the second correlation analysis algorithm.

[0047] In some embodiments, the normality test module includes:

[0048] A fitting determination submodule, used to determine a first fitting situation between the data distribution of vehicle component performance data and a first theoretical normal distribution, and to determine a second fitting situation between the data distribution of vehicle failure frequency and a second theoretical normal distribution;

[0049] a normality test submodule, configured to determine a first normality test method according to the first fitting condition, and to determine a second normality test method according to the second fitting condition; and

[0050] The result acquisition submodule is used to perform a normality test on the vehicle component performance data according to the first normality test method, and to perform a normality test on the vehicle failure frequency according to the second normality test method, so as to obtain a normality test result.

[0051] In some embodiments, the first correlation analysis module includes:

[0052] A normal distribution determination submodule is used to determine whether the normality test results are vehicle component performance data and vehicle failure frequency that conform to normal distribution;

[0053] a first correlation analysis algorithm determination submodule, configured to determine a first preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency in response to determining that the normality test result is that both the vehicle component performance data and the vehicle failure frequency conform to a normal distribution; or

[0054] The second correlation analysis algorithm determination submodule determines a second preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency in response to determining that the normality test result is that the vehicle component performance data and the vehicle failure frequency do not conform to the normal distribution.

[0055] In some embodiments, the second correlation analysis module includes:

[0056] A first determination submodule, configured to, in response to determining that the vehicle component performance data type and the vehicle failure frequency type are both classified, determine a third preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency;

[0057] A second determination submodule is used to determine a second preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency in response to determining that the vehicle component performance data type is categorical and the vehicle failure frequency type is quantitative; or

[0058] The second determination submodule is used to determine a second preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency in response to the vehicle component performance data type being quantitative and the vehicle failure frequency type being categorical.

[0059] In some embodiments, the data type acquisition module includes:

[0060] A diversity index acquisition submodule is used to sequentially use vehicle component performance data and vehicle failure frequency as data to be analyzed, and analyze the diversity of the data to be analyzed to obtain a diversity index;

[0061] An index comparison submodule, used to determine whether the diversity index is greater than a preset index threshold;

[0062] A first classification submodule is configured to, in response to determining that the diversity index is not greater than a preset index threshold, set the data type of the data to be analyzed to be classified; or

[0063] The first quantitative submodule is configured to set the data type of the to-be-analyzed data to quantitative in response to determining that the diversity index is greater than a preset index threshold.

[0064] In some embodiments, the data type acquisition module further includes:

[0065] A discretization detection submodule, for performing discretization detection on the data to be analyzed in response to determining that the diversity index is greater than a preset index threshold, and determining the number of categories of the data to be analyzed;

[0066] A threshold comparison submodule is used to determine whether the number of categories is greater than a preset number threshold;

[0067] A second quantitative submodule is configured to set the data type of the data to be analyzed to quantitative in response to determining that the number of categories is greater than a preset number threshold; or

[0068] The second classification submodule is configured to set the data type of the to-be-analyzed data to be classified in response to determining that the number of categories is not greater than a preset number threshold.

[0069] In some embodiments, the discretization detection submodule is used to:

[0070] De-duplication processing is performed on the data to be analyzed to obtain de-duplication data;

[0071] According to the amount of deduplicated data, the number of categories of data to be analyzed is determined.

[0072] In some embodiments, the apparatus further comprises:

[0073] A correlation analysis module, used to perform correlation analysis on vehicle component performance data and vehicle failure frequency using a determined correlation analysis algorithm to obtain a correlation analysis result, and determine a correlation analysis chart according to the vehicle component performance data type and the vehicle failure frequency type;

[0074] The analysis result acquisition module is used to display the correlation analysis results through correlation analysis charts.

[0075] In another aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented:

[0076] Acquire data types of vehicle component performance data and vehicle failure frequency, wherein the data type of the vehicle component performance data is a vehicle component performance data type, and the data type of the vehicle failure frequency is a vehicle failure frequency type;

[0077] Determine whether the vehicle component performance data type and vehicle failure frequency type are both quantitative;

[0078] In response to determining that the vehicle component performance data type and the vehicle failure frequency type are both quantitative, performing a normality test on the vehicle component performance data and the vehicle failure frequency to obtain a normality test result;

[0079] Determining, based on the normality test result, a first correlation analysis algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; or

[0080] In response to determining that at least one of the vehicle component performance data type and the vehicle failure frequency type is not quantitative, a second correlation analysis algorithm for performing a correlation analysis on the vehicle component performance data and the vehicle failure frequency is determined.

[0081] In another aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0082] Acquire data types of vehicle component performance data and vehicle failure frequency, wherein the data type of the vehicle component performance data is a vehicle component performance data type, and the data type of the vehicle failure frequency is a vehicle failure frequency type;

[0083] Determine whether the vehicle component performance data type and vehicle failure frequency type are both quantitative;

[0084] In response to determining that the vehicle component performance data type and the vehicle failure frequency type are both quantitative, performing a normality test on the vehicle component performance data and the vehicle failure frequency to obtain a normality test result;

[0085] Determining, based on the normality test result, a first correlation analysis algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; or

[0086] In response to determining that at least one of the vehicle component performance data type and the vehicle failure frequency type is not quantitative, a second correlation analysis algorithm for performing a correlation analysis on the vehicle component performance data and the vehicle failure frequency is determined.

[0087] The above-mentioned vehicle data management method, device, computer equipment and storage medium can determine the correlation analysis algorithm according to the type and normality test results of vehicle component performance data and vehicle failure frequency, and then analyze the correlation between vehicle component performance data and vehicle failure frequency according to the determined correlation analysis algorithm, thereby improving the accuracy of vehicle data correlation analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0088] Figure 1 An application environment diagram of the vehicle data management method provided by an embodiment of the present invention;

[0089] Figure 2A schematic diagram of a process flow of a vehicle data management method provided by an embodiment of the present invention;

[0090] Figure 3 A structural block diagram of a vehicle data management device provided by an embodiment of the present invention;

[0091] Figure 4 An internal structure diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0092] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0093] The vehicle data management method provided in this application can be applied to Figure 1 In the application environment shown. Among them, the vehicle 102 communicates with the server 104 through the network. The vehicle 102 forwards the vehicle component performance data and the vehicle failure frequency to the server 104. The server 104 first obtains the data types of the vehicle component performance data and the vehicle failure frequency, wherein the data type of the vehicle component performance data is the vehicle component performance data type, and the data type of the vehicle failure frequency is the vehicle failure frequency type. Then it is determined whether the vehicle component performance data type and the vehicle failure frequency type are both quantitative. In response to determining that the vehicle component performance data type and the vehicle failure frequency type are both quantitative, the server 104 performs a normality test on the vehicle component performance data and the vehicle failure frequency to obtain a normality test result. According to the normality test result, a first correlation analysis algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency is determined. Or in response to determining that at least one of the vehicle component performance data type and the vehicle failure frequency type is not quantitative, the server 104 determines a second correlation analysis algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency. The correlation between the vehicle component performance data and the vehicle failure frequency is obtained according to the first correlation analysis algorithm or the second correlation analysis algorithm. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0094] In one embodiment, Figure 2 As shown, a vehicle data management method is provided, which is applied to Figure 1 The server in the example is used to illustrate the following steps:

[0095] Step S101, obtaining vehicle component performance data and vehicle failure frequency data types, wherein the vehicle component performance data data type is a vehicle component performance data type, and the vehicle failure frequency data type is a vehicle failure frequency type.

[0096] Vehicle component performance data and vehicle failure frequency can be obtained from multiple sources such as sensor data, test reports and user feedback, and then pre-stored in the database. The database contains performance indicators of components such as the engine and brake system, as well as historical failure frequencies, such as engine oil temperature and fuel consumption.

[0097] In some embodiments, the step of obtaining data types of vehicle component performance data and vehicle failure frequency includes:

[0098] (A1) taking vehicle component performance data and vehicle failure frequency as data to be analyzed in turn, and analyzing the diversity of the data to be analyzed to obtain a diversity index;

[0099] (A2) determining whether the diversity index is greater than a preset index threshold;

[0100] (A3) in response to determining that the diversity index is not greater than a preset index threshold, setting the data type of the data to be analyzed to a nominal category;

[0101] (A4) In response to determining that the diversity index is greater than a preset index threshold, the data type of the data to be analyzed is set to quantitative.

[0102] Assuming that the preset index threshold is 0.7, firstly, the vehicle component performance data is used as the data to be analyzed. If the Shannom diversity index of the vehicle component performance data is calculated to be 0.6, in response to the Shannom diversity index of the vehicle component performance data being not greater than the preset index threshold, the data type of the vehicle component performance data is set to categorical. Then, the vehicle fault frequency is used as the data to be analyzed. If the Shannom diversity index of the vehicle fault frequency is calculated to be 0.8, in response to the Shannom diversity index of the vehicle fault frequency being greater than the preset index threshold, the data type of the vehicle fault frequency is set to quantitative.

[0103] In some embodiments, after the step of determining whether the diversity index is greater than a preset index threshold, the method further includes:

[0104] (B1) in response to determining that the diversity index is greater than a preset index threshold, performing discretization detection on the data to be analyzed to determine the number of categories of the data to be analyzed;

[0105] (B2) determining whether the number of categories is greater than a preset number threshold;

[0106] (B3) in response to determining that the number of categories is greater than a preset number threshold, setting the data type of the data to be analyzed to quantitative; or

[0107] (B4) In response to determining that the number of categories is not greater than a preset number threshold, the data type of the data to be analyzed is set to categorical.

[0108] Further, in response to determining that the diversity index is greater than a preset index threshold, the data to be analyzed may be further analyzed to more accurately determine its data type. Discretization detection is performed on the data to be analyzed to determine whether the data to be analyzed has significant discrete characteristics, such as the data to be analyzed only contains a small number of different values.

[0109] In some embodiments, the step of performing discretization detection on the data to be analyzed and determining the number of categories of the data to be analyzed includes:

[0110] (C1) performing deduplication processing on the data to be analyzed to obtain deduplication data;

[0111] (C2) Determine the number of categories of data to be analyzed based on the amount of deduplicated data.

[0112] First, the data to be analyzed is deduplicated, that is, repeated values ​​are removed to obtain deduplicated data containing unique values. Then, according to the amount of deduplicated data, the number of categories of the data to be analyzed is determined. In one embodiment, the deduplicated data can be sorted, for example, the unique values ​​in the deduplicated data are sorted in order from small to large, or in order from large to small. Then, the number of unique values ​​is counted, and the number of unique values ​​is set as the number of categories of the data to be analyzed.

[0113] For example, assuming that the preset quantity threshold is 10. If the number of categories of the data to be analyzed is 8, in response to the number of categories of the data to be analyzed being not greater than the preset quantity threshold, it is determined that the data to be analyzed has a strong discretization feature, and thus the data type of the data to be analyzed is set to categorical. If the number of categories of the data to be analyzed is 12, in response to the number of categories of the data to be analyzed being greater than the preset quantity threshold, it is determined that the data to be analyzed does not have a strong discretization feature, and thus the data type of the data to be analyzed is set to quantitative.

[0114] The embodiment of the present application can automatically and accurately identify the data type of the data by analyzing the diversity of vehicle component performance data and vehicle failure frequency and performing discretization detection. For example, when the vehicle component performance data is engine temperature data, diversity analysis and discretization detection are used to determine whether the engine temperature data is continuous quantitative data or data with discrete characteristics. If the engine temperature data is highly discrete data, such as only a limited number of high temperature alarms, the engine temperature data is regarded as categorical data.

[0115] Step S102, determining whether the vehicle component performance data type and the vehicle failure frequency type are both quantitative.

[0116] Determine whether the vehicle component performance data type and the vehicle fault frequency type are both quantitative. In response to determining that the vehicle component performance data type and the vehicle fault frequency type are both quantitative, proceed to step S103. In response to determining that at least one of the vehicle component performance data type and the vehicle fault frequency type is not quantitative, proceed to step S105.

[0117] Step S103, performing a normality test on the vehicle component performance data and the vehicle failure frequency to obtain a normality test result.

[0118] The distribution characteristics of each performance indicator are detected by generating a QQ (Quantile-Quantile) graph to determine whether standard statistical methods are suitable. For example, if the engine temperature data is roughly distributed along a straight line and conforms to a normal distribution, the Pearson correlation analysis algorithm is preferred. Otherwise, other appropriate algorithms are used.

[0119] In one embodiment, the step of performing a normality test on vehicle component performance data and vehicle failure frequency to obtain a normality test result includes:

[0120] (D1) determining a first fit between a data distribution of vehicle component performance data and a first theoretical normal distribution, and determining a second fit between a data distribution of vehicle failure frequencies and a second theoretical normal distribution;

[0121] (D2) determining a first normality test method according to the first fitting situation, and determining a second normality test method according to the second fitting situation; and

[0122] (D3) performing a normality test on the vehicle component performance data according to the first normality test method, and performing a normality test on the vehicle failure frequency according to the second normality test method to obtain a normality test result.

[0123] The vehicle component performance data can be used to generate a QQ graph to determine the first fit between the data distribution of the vehicle component performance data and the first theoretical normal distribution. If the points in the QQ graph are roughly distributed along a straight line, the first fit is that the values ​​of the vehicle component performance data are roughly normal and close to the normal distribution; otherwise, the first fit is that there are abnormal values ​​in the vehicle component performance data.

[0124] Similarly, the vehicle failure frequency can be used to generate a QQ (Quantile-Quantile) graph to determine the second fit between the data distribution of the vehicle failure frequency and the second theoretical normal distribution. If the points in the QQ graph are roughly distributed along a straight line, the second fit is: the value of the vehicle failure frequency is roughly normal and close to the normal distribution; otherwise, the second fit is: there are abnormal values ​​in the vehicle failure frequency.

[0125] Then, a first normality test method for performing a normality test on the vehicle component performance data is determined according to the first fitting situation, and a second normality test method for performing a normality test on the vehicle failure frequency is determined according to the second fitting situation.

[0126] If the first fitting situation is that the vehicle component performance data has abnormal values, the first normality test method is determined to be the Shapiro-Wilk test method. If the first fitting situation is that the values ​​of the vehicle component performance data are roughly normal and close to normal distribution, the first normality test method is determined to be the Kolmogorov-Smirnov test method. Compared with the Kolmogorov-Smirnov test method, the Shapiro-Wilk test method performs better in the presence of small samples or abnormal data.

[0127] Similarly, if the second fitting situation is that there are abnormal values ​​in the vehicle failure frequency, the second normality test method is determined to be the Shapiro-Wilk test method. If the second fitting situation is that the value of the vehicle failure frequency is roughly normal and close to the normal distribution, the second normality test method is determined to be the Kolmogorov-Smirnov test method.

[0128] The appropriate algorithm can be automatically recommended based on the data type and normality test results. For example, when analyzing the relationship between engine temperature data and fault frequency data, if the data is quantitative and conforms to the normal distribution, it is recommended to use the Pearson correlation coefficient. When fuel consumption is quantitative data and brake status is categorical data, it is recommended to use the Spearman rank correlation coefficient. This method ensures the applicability of the algorithm and the reliability of the analysis results. The following is a detailed introduction:

[0129] Step S104: determining a first correlation analysis algorithm for performing correlation analysis on vehicle component performance data and vehicle failure frequency according to the normality test result.

[0130] In some embodiments, according to the normality test result, determining a first correlation analysis algorithm step for performing correlation analysis on vehicle component performance data and vehicle failure frequency includes:

[0131] (E1) Determine whether the normality test results are vehicle component performance data and vehicle failure frequency that conform to normal distribution;

[0132] (E2) in response to determining that the normality test result is that both the vehicle component performance data and the vehicle failure frequency conform to a normal distribution, determining a first preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; or

[0133] (E3) In response to determining that the normality test result is that the vehicle component performance data and the vehicle failure frequency do not conform to the normal distribution, determining a second preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency.

[0134] For example, when it is determined that the normality test result is that the vehicle component performance data and the vehicle failure frequency conform to the normal distribution, it is determined that the Person correlation analysis algorithm is used as the first preset correlation analysis algorithm for correlation analysis. When it is determined that the normality test result is that the vehicle component performance data and the vehicle failure frequency do not conform to the normal distribution, it is determined that the Spearman correlation analysis algorithm is used as the second preset correlation analysis algorithm for correlation analysis.

[0135] Step S105 , determining a second correlation analysis algorithm for performing correlation analysis on vehicle component performance data and vehicle failure frequency.

[0136] In some embodiments, in response to determining that at least one of the vehicle component performance data type and the vehicle failure frequency type is not quantitative, determining a second correlation analysis algorithm step for performing a correlation analysis on the vehicle component performance data and the vehicle failure frequency includes:

[0137] (F1) in response to determining that the vehicle component performance data type and the vehicle failure frequency type are both classified, determining a third preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency;

[0138] (F2) in response to determining that the vehicle component performance data type is categorical and the vehicle failure frequency type is quantitative, determining a second preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; or

[0139] (F3) In response to the vehicle component performance data type being quantitative and the vehicle failure frequency type being categorical, determining a second preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency.

[0140] For example, in response to determining that both the vehicle component performance data type and the vehicle fault frequency type are categorical, the Kendall's tau correlation analysis algorithm is determined as the third preset correlation analysis algorithm to perform correlation analysis. In response to determining that one of the vehicle component performance data type and the vehicle fault frequency type is categorical and the other is quantitative, the Spearman correlation analysis algorithm is used as the second preset correlation analysis algorithm to perform correlation analysis.

[0141] Step S106: Obtain the correlation between the vehicle component performance data and the vehicle failure frequency according to the first correlation analysis algorithm or the second correlation analysis algorithm.

[0142] The above data processing flow and efficient algorithm can quickly identify significant correlations between different performance indicators and fault frequencies. For example, if the correlation between engine temperature and brake failure is high, the vehicle will be marked as high risk, indicating that further inspection is required. For abnormal data, such as abnormal points with excessively high temperatures, alarms or optimization suggestions will be automatically generated to help optimize the design of the vehicle before it is put on the market.

[0143] In some embodiments, the correlation analysis results may also be obtained, and a correlation analysis chart may be determined based on the vehicle component performance data type and the vehicle failure frequency type; and the correlation analysis results may then be displayed via the correlation analysis chart.

[0144] After analyzing the vehicle component performance data and the vehicle failure frequency using the correlation analysis algorithm, a correlation analysis chart can be determined based on the vehicle component performance data type and the vehicle failure frequency type to display the correlation analysis results. The correlation analysis chart includes at least one of a scatter plot, a box plot, a bar plot, and / or a correlation matrix.

[0145] For example, when the vehicle component performance data type and the vehicle failure frequency type are both quantitative data, the correlation analysis chart can be determined to be a scatter plot to intuitively display the relationship between the two columns of data. When displaying the correlation analysis results through a scatter plot, the correlation coefficient and P value can also be marked. For another example, when the vehicle component performance data type and the vehicle failure frequency type are both categorical data, the correlation analysis chart can be determined to be a box plot or a bar plot. When displaying the correlation analysis results through a box plot, the median, quartiles, and possible outliers of the data can be displayed. When displaying the correlation analysis results through a bar chart, the average or median of each category can be displayed.

[0146] The above visualization helps engineers to intuitively view the data correlation. Combined with the regression line and significance mark, the impact of different data on system performance can be judged, providing a scientific basis for subsequent improvements.

[0147] The correlation analysis algorithm can also be combined to further determine the correlation analysis chart to be displayed. When the vehicle component performance data type and the vehicle failure frequency type are both quantitative data, if the correlation analysis algorithm used is the Pearson correlation analysis algorithm, a regression line can be added to the scatter plot to display the linear fit of the data.

[0148] The vehicle data management method provided in the embodiment of the present application can determine a correlation analysis algorithm based on the types and normality test results of vehicle component performance data and vehicle failure frequency, and then analyze the correlation between vehicle component performance data and vehicle failure frequency based on the determined correlation analysis algorithm, thereby improving the accuracy of vehicle data correlation analysis.

[0149] It should be understood that although Figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0150] In one embodiment, Figure 3 As shown, a vehicle data management device is provided, including: a data type acquisition module 301, a quantitative determination module 302, a normality test module 303, a first correlation analysis module 304, a second correlation analysis module 305 and a data correlation analysis module 306, wherein:

[0151] The data type acquisition module 301 is used to acquire the data types of vehicle component performance data and vehicle failure frequency, wherein the data type of the vehicle component performance data is the vehicle component performance data type, and the data type of the vehicle failure frequency is the vehicle failure frequency type; the quantitative determination module 302 is used to determine whether the vehicle component performance data type and the vehicle failure frequency type are both quantitative; the normality test module 303 is used to respond to the determination that the vehicle component performance data type and the vehicle failure frequency type are both quantitative, perform a normality test on the vehicle component performance data and the vehicle failure frequency, and obtain a normality test result; the first correlation analysis module 304 is used to determine, based on the normality test result, a first correlation analysis algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; or the second correlation analysis module 305 is used to respond to the determination that at least one of the vehicle component performance data type and the vehicle failure frequency type is not quantitative, determine a second correlation analysis algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; the data correlation analysis module 306 is used to obtain the correlation between the vehicle component performance data and the vehicle failure frequency according to the first correlation analysis algorithm or the second correlation analysis algorithm.

[0152] In some embodiments, the normality test module 303 includes: a fitting determination submodule, a normality test submodule and a result acquisition submodule.

[0153] The fitting determination submodule is used to determine a first fitting situation between the data distribution of the vehicle component performance data and the first theoretical normal distribution, and to determine a second fitting situation between the data distribution of the vehicle failure frequency and the second theoretical normal distribution; the normality test submodule is used to determine a first normality test method according to the first fitting situation, and to determine a second normality test method according to the second fitting situation; and the result acquisition submodule is used to perform a normality test on the vehicle component performance data according to the first normality test method, and to perform a normality test on the vehicle failure frequency according to the second normality test method, so as to obtain a normality test result.

[0154] In some embodiments, the first correlation analysis module 304 includes: a normal distribution determination submodule, a first correlation analysis algorithm determination submodule, and a second correlation analysis algorithm determination submodule.

[0155] A normal distribution determination submodule is used to determine whether the normality test results are that the vehicle component performance data and the vehicle failure frequency both conform to the normal distribution; a first correlation analysis algorithm determination submodule is used to determine the first preset correlation analysis algorithm as the algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency in response to determining that the normality test results are that the vehicle component performance data and the vehicle failure frequency both conform to the normal distribution; or a second correlation analysis algorithm determination submodule is used to determine the second preset correlation analysis algorithm as the algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency in response to determining that the normality test results are that the vehicle component performance data and the vehicle failure frequency do not conform to the normal distribution.

[0156] In some embodiments, the second correlation analysis module 305 includes: a first determination submodule, a second determination submodule, and a second determination submodule.

[0157] A first determination submodule is used to determine a third preset correlation analysis algorithm as an algorithm for performing correlation analysis on vehicle component performance data and vehicle failure frequency in response to determining that both the vehicle component performance data type and the vehicle failure frequency type are classified; a second determination submodule is used to determine a second preset correlation analysis algorithm as an algorithm for performing correlation analysis on vehicle component performance data and vehicle failure frequency in response to determining that the vehicle component performance data type is classified and the vehicle failure frequency type is quantitative; or a second determination submodule is used to determine a second preset correlation analysis algorithm as an algorithm for performing correlation analysis on vehicle component performance data and vehicle failure frequency in response to determining that the vehicle component performance data type is quantitative and the vehicle failure frequency type is classified.

[0158] In some embodiments, the data type acquisition module 301 includes: a diversity index acquisition submodule, an index comparison submodule, a first classification submodule and a first quantification submodule.

[0159] A diversity index acquisition submodule is used to sequentially use vehicle component performance data and vehicle failure frequency as data to be analyzed, and analyze the diversity of the data to be analyzed to obtain a diversity index; an index comparison submodule is used to determine whether the diversity index is greater than a preset index threshold; a first classification submodule is used to set the data type of the data to be analyzed to a classification in response to determining that the diversity index is not greater than the preset index threshold; or a first quantitative submodule is used to set the data type of the data to be analyzed to a quantitative in response to determining that the diversity index is greater than the preset index threshold.

[0160] In some embodiments, the data type acquisition module 301 further includes: a discretization detection submodule, a threshold comparison submodule, a second quantification submodule, and a second classification submodule.

[0161] A discretization detection submodule is used to perform discretization detection on the data to be analyzed in response to determining that the diversity index is greater than a preset index threshold, and determine the number of categories of the data to be analyzed; a threshold comparison submodule is used to determine whether the number of categories is greater than a preset number threshold; a second quantitative submodule is used to set the data type of the data to be analyzed to quantitative in response to determining that the number of categories is greater than the preset number threshold; or a second categorized submodule is used to set the data type of the data to be analyzed to categorized in response to determining that the number of categories is not greater than the preset number threshold.

[0162] In some embodiments, the discretization detection submodule is used to: perform deduplication processing on the data to be analyzed to obtain deduplication data; and determine the number of categories of the data to be analyzed based on the amount of the deduplication data.

[0163] In some embodiments, the device further includes: a correlation analysis module and an analysis result acquisition module.

[0164] The correlation analysis module is used to perform correlation analysis on vehicle component performance data and vehicle failure frequency using a determined correlation analysis algorithm to obtain correlation analysis results, and determine a correlation analysis chart based on the vehicle component performance data type and the vehicle failure frequency type; the analysis result acquisition module is used to display the correlation analysis results through a correlation analysis chart.

[0165] The specific definition of the vehicle data management device can be found in the definition of the vehicle data management method above, which will not be repeated here. Each module in the above-mentioned vehicle data management device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0166] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store vehicle component performance data and vehicle failure frequency. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a vehicle data management method is implemented.

[0167] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0168] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0169] Obtain data types of vehicle component performance data and vehicle failure frequency, wherein the data type of the vehicle component performance data is the vehicle component performance data type, and the data type of the vehicle failure frequency is the vehicle failure frequency type; determine whether the vehicle component performance data type and the vehicle failure frequency type are both quantitative; in response to determining that the vehicle component performance data type and the vehicle failure frequency type are both quantitative, perform a normality test on the vehicle component performance data and the vehicle failure frequency to obtain a normality test result; based on the normality test result, determine a first correlation analysis algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; or in response to determining that at least one of the vehicle component performance data type and the vehicle failure frequency type is not quantitative, determine a second correlation analysis algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency.

[0170] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0171] Determine a first fitting situation between the data distribution of vehicle component performance data and a first theoretical normal distribution, and determine a second fitting situation between the data distribution of vehicle failure frequency and a second theoretical normal distribution; determine a first normality test method based on the first fitting situation, and determine a second normality test method based on the second fitting situation; and perform a normality test on the vehicle component performance data according to the first normality test method, and perform a normality test on the vehicle failure frequency according to the second normality test method, so as to obtain a normality test result.

[0172] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0173] Determine whether the normality test result is that the vehicle component performance data and the vehicle failure frequency both conform to the normal distribution; in response to determining that the normality test result is that the vehicle component performance data and the vehicle failure frequency both conform to the normal distribution, determine a first preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; or in response to determining that the normality test result is that the vehicle component performance data and the vehicle failure frequency do not both conform to the normal distribution, determine a second preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency.

[0174] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0175] In response to determining that the vehicle component performance data type and the vehicle failure frequency type are both classified, a third preset correlation analysis algorithm is determined as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; in response to determining that the vehicle component performance data type is classified and the vehicle failure frequency type is quantitative, a second preset correlation analysis algorithm is determined as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; or in response to the vehicle component performance data type being quantitative and the vehicle failure frequency type being classified, a second preset correlation analysis algorithm is determined as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency.

[0176] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0177] The vehicle component performance data and the vehicle failure frequency are sequentially used as the data to be analyzed, and the diversity of the data to be analyzed is analyzed to obtain a diversity index; it is determined whether the diversity index is greater than a preset index threshold; in response to determining that the diversity index is not greater than the preset index threshold, the data type of the data to be analyzed is set to categorical; or in response to determining that the diversity index is greater than the preset index threshold, the data type of the data to be analyzed is set to quantitative.

[0178] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0179] In response to determining that the diversity index is greater than a preset index threshold, discretization detection is performed on the data to be analyzed to determine the number of categories of the data to be analyzed; determine whether the number of categories is greater than a preset number threshold; in response to determining that the number of categories is greater than the preset number threshold, the data type of the data to be analyzed is set to quantitative; or in response to determining that the number of categories is not greater than the preset number threshold, the data type of the data to be analyzed is set to categorical.

[0180] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0181] The data to be analyzed is deduplicated to obtain deduplicated data; and the number of categories of the data to be analyzed is determined according to the amount of the deduplicated data.

[0182] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0183] A correlation analysis is performed on the vehicle component performance data and the vehicle failure frequency using a determined correlation analysis algorithm to obtain a correlation analysis result, and a correlation analysis chart is determined based on the vehicle component performance data type and the vehicle failure frequency type; the correlation analysis result is displayed through the correlation analysis chart.

[0184] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0185] Obtain data types of vehicle component performance data and vehicle failure frequency, wherein the data type of the vehicle component performance data is the vehicle component performance data type, and the data type of the vehicle failure frequency is the vehicle failure frequency type; determine whether the vehicle component performance data type and the vehicle failure frequency type are both quantitative; in response to determining that the vehicle component performance data type and the vehicle failure frequency type are both quantitative, perform a normality test on the vehicle component performance data and the vehicle failure frequency to obtain a normality test result; based on the normality test result, determine a first correlation analysis algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; or in response to determining that at least one of the vehicle component performance data type and the vehicle failure frequency type is not quantitative, determine a second correlation analysis algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency.

[0186] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0187] Determine a first fitting situation between the data distribution of vehicle component performance data and a first theoretical normal distribution, and determine a second fitting situation between the data distribution of vehicle failure frequency and a second theoretical normal distribution; determine a first normality test method based on the first fitting situation, and determine a second normality test method based on the second fitting situation; and perform a normality test on the vehicle component performance data according to the first normality test method, and perform a normality test on the vehicle failure frequency according to the second normality test method, so as to obtain a normality test result.

[0188] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0189] Determine whether the normality test result is that the vehicle component performance data and the vehicle failure frequency both conform to the normal distribution; in response to determining that the normality test result is that the vehicle component performance data and the vehicle failure frequency both conform to the normal distribution, determine a first preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; or in response to determining that the normality test result is that the vehicle component performance data and the vehicle failure frequency do not both conform to the normal distribution, determine a second preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency.

[0190] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0191] In response to determining that the vehicle component performance data type and the vehicle failure frequency type are both classified, a third preset correlation analysis algorithm is determined as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; in response to determining that the vehicle component performance data type is classified and the vehicle failure frequency type is quantitative, a second preset correlation analysis algorithm is determined as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; or in response to the vehicle component performance data type being quantitative and the vehicle failure frequency type being classified, a second preset correlation analysis algorithm is determined as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency.

[0192] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0193] The vehicle component performance data and the vehicle failure frequency are sequentially used as the data to be analyzed, and the diversity of the data to be analyzed is analyzed to obtain a diversity index; it is determined whether the diversity index is greater than a preset index threshold; in response to determining that the diversity index is not greater than the preset index threshold, the data type of the data to be analyzed is set to categorical; or in response to determining that the diversity index is greater than the preset index threshold, the data type of the data to be analyzed is set to quantitative.

[0194] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0195] In response to determining that the diversity index is greater than a preset index threshold, discretization detection is performed on the data to be analyzed to determine the number of categories of the data to be analyzed; determine whether the number of categories is greater than a preset number threshold; in response to determining that the number of categories is greater than the preset number threshold, the data type of the data to be analyzed is set to quantitative; or in response to determining that the number of categories is not greater than the preset number threshold, the data type of the data to be analyzed is set to categorical.

[0196] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0197] The data to be analyzed is deduplicated to obtain deduplicated data; and the number of categories of the data to be analyzed is determined according to the amount of the deduplicated data.

[0198] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0199] A correlation analysis is performed on the vehicle component performance data and the vehicle failure frequency using a determined correlation analysis algorithm to obtain a correlation analysis result, and a correlation analysis chart is determined based on the vehicle component performance data type and the vehicle failure frequency type; the correlation analysis result is displayed through the correlation analysis chart.

[0200] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0201] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0202] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A vehicle data management method, characterized in that: include: Acquire data types of vehicle component performance data and vehicle failure frequency, wherein the data type of the vehicle component performance data is a vehicle component performance data type, and the data type of the vehicle failure frequency is a vehicle failure frequency type; Determining whether the vehicle component performance data type and the vehicle failure frequency type are both quantitative; In response to determining that the vehicle component performance data type and the vehicle failure frequency type are both quantitative, performing a normality test on the vehicle component performance data and the vehicle failure frequency to obtain a normality test result; Determining, according to the normality test result, a first correlation analysis algorithm for performing a correlation analysis on the vehicle component performance data and the vehicle failure frequency; or In response to determining that at least one of the vehicle component performance data type and the vehicle failure frequency type is not quantitative, determining a second correlation analysis algorithm for performing a correlation analysis on the vehicle component performance data and the vehicle failure frequency; The correlation between the vehicle component performance data and the vehicle failure frequency is obtained according to the first correlation analysis algorithm or the second correlation analysis algorithm.

2. The vehicle data management method according to claim 1, characterized in that: The step of performing a normality test on the vehicle component performance data and the vehicle failure frequency to obtain a normality test result comprises: Determine a first fit between the data distribution of the vehicle component performance data and a first theoretical normal distribution, and determine a second fit between the data distribution of the vehicle failure frequency and a second theoretical normal distribution; Determining a first normality test method according to the first fitting situation, and determining a second normality test method according to the second fitting situation; and The vehicle component performance data is subjected to a normality test according to the first normality test method, and the vehicle failure frequency is subjected to a normality test according to the second normality test method, so as to obtain the normality test result.

3. The vehicle data management method according to claim 1, characterized in that: The step of determining a first correlation analysis algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency according to the normality test result comprises: Determining the normality test result as whether the vehicle component performance data and the vehicle failure frequency both conform to a normal distribution; In response to determining that the normality test result is that both the vehicle component performance data and the vehicle failure frequency conform to a normal distribution, determining a first preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; or In response to determining that the normality test result is that the vehicle component performance data and the vehicle failure frequency do not conform to a normal distribution, a second preset correlation analysis algorithm is determined as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency.

4. The vehicle data management method according to claim 1, characterized in that: In response to determining that at least one of the vehicle component performance data type and the vehicle failure frequency type is not quantitative, determining a second correlation analysis algorithm step for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency comprises: In response to determining that the vehicle component performance data type and the vehicle failure frequency type are both classified, determining a third preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; In response to determining that the vehicle component performance data type is categorical and the vehicle failure frequency type is quantitative, determining a second preset correlation analysis algorithm as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency; or In response to the vehicle component performance data type being quantitative and the vehicle failure frequency type being categorical, a second preset correlation analysis algorithm is determined as an algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency.

5. The vehicle data management method according to claim 1, characterized in that: The step of obtaining the data type of vehicle component performance data and vehicle failure frequency includes: The vehicle component performance data and the vehicle failure frequency are sequentially used as data to be analyzed, and the diversity of the data to be analyzed is analyzed to obtain a diversity index; Determining whether the diversity index is greater than a preset index threshold; In response to determining that the diversity index is not greater than a preset index threshold, setting the data type of the to-be-analyzed data to be classified; or In response to determining that the diversity index is greater than the preset index threshold, the data type of the data to be analyzed is set to quantitative.

6. The vehicle data management method according to claim 5, characterized in that: After the step of determining whether the diversity index is greater than a preset index threshold, the method further includes: In response to determining that the diversity index is greater than the preset index threshold, performing discretization detection on the data to be analyzed to determine the number of categories of the data to be analyzed; Determining whether the number of categories is greater than a preset number threshold; In response to determining that the number of categories is greater than the preset number threshold, setting the data type of the data to be analyzed to quantitative; or In response to determining that the number of categories is not greater than the preset number threshold, the data type of the data to be analyzed is set to categorical.

7. The vehicle data management method according to claim 6, characterized in that: The step of performing discretization detection on the data to be analyzed and determining the number of categories of the data to be analyzed includes: Performing deduplication processing on the data to be analyzed to obtain deduplication data; The number of categories of the data to be analyzed is determined according to the amount of the deduplicated data.

8. The vehicle data management method according to any one of claims 1 to 7, characterized in that: After the step of obtaining the correlation between the vehicle component performance data and the vehicle failure frequency according to the first correlation analysis algorithm or the second correlation analysis algorithm, the method further includes: Obtaining a correlation analysis result, and determining a correlation analysis chart according to the vehicle component performance data type and the vehicle failure frequency type; The correlation analysis result is presented through the correlation analysis chart.

9. A vehicle data management device, characterized in that: The device comprises: A data type acquisition module, used to acquire data types of vehicle component performance data and vehicle failure frequency, wherein the data type of the vehicle component performance data is a vehicle component performance data type, and the data type of the vehicle failure frequency is a vehicle failure frequency type; A quantitative determination module, used to determine whether the vehicle component performance data type and the vehicle fault frequency type are both quantitative; A normality test module, configured to perform a normality test on the vehicle component performance data and the vehicle failure frequency in response to determining that the vehicle component performance data type and the vehicle failure frequency type are both quantitative, to obtain a normality test result; A first correlation analysis module, configured to determine, according to the normality test result, a first correlation analysis algorithm for performing a correlation analysis on the vehicle component performance data and the vehicle failure frequency; or a second correlation analysis module for determining a second correlation analysis algorithm for performing correlation analysis on the vehicle component performance data and the vehicle failure frequency in response to determining that at least one of the vehicle component performance data type and the vehicle failure frequency type is not quantitative; A data correlation analysis module is used to obtain the correlation between the vehicle component performance data and the vehicle failure frequency according to the first correlation analysis algorithm or the second correlation analysis algorithm.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images