Internet of vehicles dynamic data quality evaluation method and device

Abstract

The invention relates to the technical field of Internet of Vehicles, and discloses an Internet of Vehicles dynamic data quality evaluation method and device, which are beneficial to improving the comprehensiveness of index information evaluation of vehicle dynamic data in various application scenes due to the fact that various index information in various application scenes is taken into consideration, thereby improving the evaluation accuracy of the dynamic data of the Internet of Vehicles and improving the evaluation accuracy of the dynamic data of the Internet of Vehicles. Corresponding weight parameters are automatically given to the normal index score values under the index information of at least one application scene in the multiple application scenes, manual subjective weighting is not needed, and therefore the scientificity, rationality and accuracy of weight distribution are ensured; and the data quality score of the normal index score value under each piece of index information in the target application scene is further evaluated, so that the objectivity, the fairness and the comprehensiveness of data quality evaluation of multiple pieces of index information in various different application scenes are finally improved.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Vehicles, and particularly to a method and device for evaluating the quality of dynamic data in Internet of Vehicles. Background Art

[0002] Under the background of the global energy structure transformation, new energy vehicles, as an important part of the national strategy, are becoming increasingly popular and widely used. These vehicles generate tens of billions of in-vehicle data every day. These data include various data such as vehicle operation status, geographical location, and energy consumption information. However, due to the uncertainty and complexity of the data reporting environment, the quality of the reported data is uneven, and there are a large number of invalid and abnormal data. Therefore, identifying and evaluating the quality of these data is of extremely important significance for further enhancing the value and application effect of the data.

[0003] In the related art, generally, by monitoring the anomalies of single-index data, it is impossible to comprehensively evaluate the overall data quality after combining multiple indicators. Such a single-index monitoring method limits the comprehensive evaluation of data quality and is difficult to accurately reflect the overall situation of the data. In addition, the assignment of weights for single indicators mostly relies on subjective experience and lacks scientificity. Since the importance of different indicators varies in different application scenarios, subjective weight assignment may lead to deviations in the evaluation results and is difficult to comprehensively and objectively reflect the actual quality of the data. Moreover, by only focusing on the data quality problems in a specific aspect, it is impossible to comprehensively evaluate the data quality from multiple perspectives. Summary of the Invention

[0004] In view of this, the present invention provides a method and device for evaluating the quality of dynamic data in Internet of Vehicles to solve the problems that the importance of different indicators varies in different application scenarios, subjective weight assignment may lead to deviations in the evaluation results, and it is difficult to comprehensively and objectively reflect the actual quality of the data. Moreover, by only focusing on the data quality problems in a specific aspect, it is impossible to comprehensively evaluate the data quality from multiple perspectives.

[0005] In a first aspect, the present invention provides a method for evaluating the quality of dynamic data in Internet of Vehicles, the method comprising:

[0006] Defining a variety of application scenarios and a variety of indicator information according to vehicle information, wherein the variety of application scenarios include: vehicle type application scenario, data type application scenario, and service type application scenario;

[0007] Collecting the vehicle dynamic data uploaded by a batch of vehicles within a preset time;

[0008] Counting the normal index score values of the vehicle dynamic data uploaded within the preset time under each indicator information in the target application scenario, where the target application scenario is at least one of the variety of application scenarios;

[0009] Calculate the weight parameters for each piece of index information in the target application scenario based on the normal index score values for each piece of index information in the target application scenario, so that the normal index score values for each piece of index information in the target application scenario tend to the standard values;

[0010] Evaluate the data quality score of the normal index score values for each piece of index information in the target application scenario based on the normal index score values for each piece of index information in the target application scenario and the weight parameters for each piece of index information in the target application scenario.

[0011] Since the embodiments of the present disclosure consider various pieces of index information in multiple application scenarios, it is beneficial to improve the comprehensiveness of evaluating the index information of vehicle dynamic data in multiple application scenarios, and automatically assign corresponding weight parameters to the normal index score values for each piece of index information in at least one of the multiple application scenarios, without subjective human weighting, thereby ensuring the scientificity, rationality, and accuracy of weight allocation, and further evaluating the data quality score of the normal index score values for each piece of index information in the target application scenario, ultimately enhancing the objectivity, fairness, and comprehensiveness of the data quality evaluation of multiple pieces of index information in various different application scenarios.

[0012] In some alternative embodiments, obtaining the weight parameters for each piece of index information in the target application scenario based on the normal index score values for each piece of index information in the target application scenario includes:

[0013] Construct a target data matrix based on the normal index score values for each piece of index information in the target application scenario;

[0014] Select the minimum data and the maximum data from the target data matrix;

[0015] Perform standardization processing on each piece of index information in the target data matrix according to the minimum data and the maximum data;

[0016] Calculate the proportion parameters of the normal index score values for each piece of index information in the target application scenario according to the standardization processing results;

[0017] Calculate the information entropy of the normal index score values for each piece of index information in the target application scenario according to the proportion parameters of the normal index score values for each piece of index information in the target application scenario;

[0018] Calculate the weight parameters of the normal index score values for each piece of index information in the target application scenario according to the information entropy of the normal index score values for each piece of index information in the target application scenario.

[0019] In the embodiments of the present disclosure, the weight parameters of the normal index score values under various index information in the target application scenario are determined in the above manner, and the corresponding weight parameters are automatically assigned to the normal index score values under various index information in at least one of multiple application scenarios, without subjective human weighting, thereby ensuring the scientificity, rationality, and accuracy of weight distribution.

[0020] In some alternative embodiments, according to the normal index score values under various index information in the target application scenario and the weight parameters under various index information in the target application scenario, evaluating the normal index score values under various index information in the target application scenario includes:

[0021] Calculating the product weighting result between the standardized processing result of the normal index score values under various index information in the target application scenario and the weight parameters under various index information in the target application scenario;

[0022] Calculating the weight weighting result of the weight parameters under various index information in the target application scenario;

[0023] Calculating the quotient of the product weighting result divided by the weight weighting result to obtain the normal index score values under various index information in the target application scenario.

[0024] By evaluating the data quality score of the normal index score values under various index information in the target application scenario in the embodiments of the present disclosure, it is beneficial to improve the objectivity, fairness, and comprehensiveness of the data quality evaluation of multiple index information in various different application scenarios.

[0025] In some alternative embodiments, counting the vehicle dynamic data uploaded within a preset time and the normal index score values under various index information in the target application scenario includes:

[0026] Counting the total number of vehicle dynamic data uploaded within a preset time;

[0027] Counting the number of vehicle dynamic data uploaded within a preset time that is in a normal state;

[0028] According to the total number of vehicle dynamic data uploaded within a preset time and the number of vehicle dynamic data uploaded within a preset time that is in a normal state, calculating the normal index score values under various index information in the target application scenario.

[0029] By counting the total number of vehicle dynamic data uploaded within a preset time and the number in the normal state in the embodiments of the present disclosure, it is beneficial to determine the normal index score values under various index information in at least one of multiple application scenarios for the vehicle dynamic data uploaded within a preset time.

[0030] In some alternative embodiments, according to vehicle information, multiple application scenarios and multiple metric information are defined. The vehicle information includes vehicle static attribute information and vehicle dynamic attribute information, including:

[0031] According to the vehicle static attribute information, a vehicle type application scenario is defined;

[0032] According to the vehicle dynamic attribute information, a data type application scenario, a service type application scenario, and multiple metric information are defined.

[0033] By defining multiple application scenarios in the embodiments of the present disclosure, it is beneficial to improve the comprehensiveness of the analysis of multiple metric information.

[0034] In some alternative embodiments, vehicle dynamic data uploaded by a batch of vehicles within a preset time is collected, including:

[0035] Vehicle message data uploaded by a batch of vehicles within a preset time is collected;

[0036] Vehicle dynamic data is parsed from the vehicle message data uploaded within a preset time.

[0037] Through the above method, the embodiments of the present disclosure are beneficial to quickly obtain the vehicle dynamic data uploaded within a preset time.

[0038] In a second aspect, the present invention provides an apparatus for evaluating the quality of vehicle networking dynamic data. The apparatus includes:

[0039] An information definition module, configured to define multiple application scenarios and multiple metric information according to vehicle information, where the multiple application scenarios include: a vehicle type application scenario, a data type application scenario, and a service type application scenario;

[0040] A data collection module, configured to collect vehicle dynamic data uploaded by a batch of vehicles within a preset time;

[0041] A data statistics module, configured to count the normal metric score values of the vehicle dynamic data uploaded within a preset time under each metric information in a target application scenario, where the target application scenario is at least one of the multiple application scenarios;

[0042] A data calculation module, configured to calculate the weight parameters of each metric information in the target application scenario according to the normal metric score values of each metric information in the target application scenario, so that the normal metric score values of each metric information in the target application scenario tend to a standard value;

[0043] A data evaluation module, configured to evaluate the data quality score of the normal metric score values of each metric information in the target application scenario according to the normal metric score values of each metric information in the target application scenario and the weight parameters of each metric information in the target application scenario.

[0044] In a third aspect, the present invention provides a computer device, including:

[0045] a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the vehicle networking dynamic data quality evaluation method in the first aspect or any implementation manner of the first aspect.

[0046] In a fourth aspect, the present invention provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to cause a computer to execute the vehicle networking dynamic data quality evaluation method in the first aspect or any implementation manner of the first aspect.

[0047] In a fifth aspect, the present invention provides a computer program product, including computer instructions, and the computer instructions are used to cause a computer to execute the vehicle networking dynamic data quality evaluation method in the first aspect or any implementation manner of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the specific implementation manners of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required to be used in the specific implementation manners or the description of the prior art. Obviously, the drawings in the following description are some implementation manners of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0049] Figure 1 is a flowchart of the vehicle networking dynamic data quality evaluation method according to an embodiment of the present invention;

[0050] Figure 2 is a schematic diagram of defining vehicle type application scenarios according to an embodiment of the present invention;

[0051] Figure 3 is a schematic diagram of accessing vehicle data according to an embodiment of the present invention;

[0052] Figure 4 is a schematic diagram of parsing vehicle message data according to an embodiment of the present invention;

[0053] Figure 5 is a schematic diagram of data type application scenarios and service type application scenarios according to an embodiment of the present invention;

[0054] Figure 6 is a flowchart of another vehicle networking dynamic data quality evaluation method according to an embodiment of the present invention;

[0055] Figure 7It is a simple schematic diagram of the method for evaluating the quality of vehicle networking dynamic data according to an embodiment of the present disclosure;

[0056] Figure 8 It is a structural block diagram of the device for evaluating the quality of vehicle networking dynamic data according to an embodiment of the present invention;

[0057] Figure 9 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Specific embodiments

[0058] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0059] In this embodiment, a method for evaluating the quality of vehicle networking dynamic data is provided, which can be used in computer devices such as mobile phones, tablet computers, desktop computers, portable notebooks, servers, etc. Figure 1 It is a flowchart of the method for evaluating the quality of vehicle networking dynamic data according to an embodiment of the present invention, as Figure 1 shown, and the process includes the following steps:

[0060] According to an embodiment of the present invention, an embodiment of a method for evaluating the quality of vehicle networking dynamic data is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0061] In this embodiment, a method for evaluating the quality of vehicle networking dynamic data is provided, which can be used in devices such as mobile phones, tablet computers, desktop computers, portable notebooks, servers, etc. Figure 1 It is a flowchart of the method for evaluating the quality of vehicle networking dynamic data according to an embodiment of the present invention, as Figure 1 shown, and the process includes the following steps:

[0062] Step S101, according to vehicle information, define multiple application scenarios and multiple index information, where the multiple application scenarios include: vehicle type application scenario, data type application scenario, and service type application scenario.

[0063] Specifically, the vehicle information includes, but is not limited to, vehicle static attribute information and vehicle dynamic attribute information. The vehicle type application scenarios include single vehicle type, vehicle model type, brand vehicle model, etc. For example, according to the vehicle model data in the vehicle static attribute information, application scenarios of multiple vehicle model types are defined; for example, according to the single vehicle data in the vehicle static attribute information, application scenarios of multiple single vehicle types are defined; for example, according to the brand data in the vehicle static attribute information, application scenarios of multiple brand types are defined.

[0064] The data type application scenarios include, but are not limited to, vehicle data, location data, single entity data, extreme value data, fuel cell data, alarm data, drive motor data. As shown in Table 1 below, it is the index description information of various types of data under the data type application scenarios.

[0065] Table 1

[0066]

[0067]

[0068] The business type application scenarios include splitting business metric data and safety warning metric data. As Figure 5 shown, it is a schematic diagram of the data type application scenarios and the business type application scenarios. The multiple metric information is combined with GBT32960 data (technical specification data of the electric vehicle remote service and management system), and then 99 metric information items are determined. The splitting business metric data can be the key metrics concerned among the 99 metrics. For example, the splitting business metric data can be the splitting business divided in the driving or charging segments; for example, the safety warning metric data can be the data that triggers an alarm when the warning condition is reached.

[0069] Since the traditional method generally monitors the abnormal conditions of a single metric data and cannot comprehensively evaluate the overall data quality after combining multiple metrics, therefore, in the embodiments of the present disclosure, according to the vehicle information, multiple metric information items are defined, specifically combined with GBT32960 data (technical specification data of the electric vehicle remote service and management system), and then according to the vehicle information related to the vehicle, 99 metric information items are defined, and a comprehensive evaluation is performed on these 99 metric information items. For example, based on the GBT32960 protocol, index messages such as vehicle operation terminal time, vehicle status, charging status, vehicle speed, mileage, total voltage, total current, remaining battery charge soc, etc. are determined. The 99 metric information items in the embodiments of the present disclosure can be determined by rules such as outliers and null values. The embodiments of the present disclosure can build a comprehensive data quality evaluation system by formulating index definition rules.

[0070] In some alternative embodiments, in step S101, according to vehicle information, a variety of application scenarios and a variety of metric information are defined, where the vehicle information includes vehicle static attribute information and vehicle dynamic attribute information;

[0071] Step a1, according to the vehicle static attribute information, define vehicle type application scenarios.

[0072] Specifically, the vehicle static attribute information includes the vehicle model, single vehicle, brand, etc., and the vehicle type application scenarios include single vehicle type, vehicle model type, brand vehicle model, etc. For example, according to the vehicle model data in the vehicle static attribute information, define application scenarios of multiple vehicle model types; for example, according to the single vehicle data in the vehicle static attribute information, define application scenarios of multiple single vehicle types; for example, according to the brand data in the vehicle static attribute information, define application scenarios of multiple brand types.

[0073] As Figure 2 shown, it is a schematic diagram for defining vehicle type application scenarios. In Figure 2 , according to the vehicle static attribute information, vehicle model portrait data, single vehicle portrait data, and brand portrait data can be defined.

[0074] Step a2, according to the vehicle dynamic attribute information, define data type application scenarios, business type application scenarios, and a variety of metric information.

[0075] Specifically, the vehicle dynamic attribute information includes vehicle operation data, including but not limited to the charging state, vehicle speed, mileage, total voltage, total current, remaining battery capacity SOC, etc. of the vehicle. Through the vehicle dynamic attribute information, define the above-mentioned data type application scenarios, business type application scenarios, and a variety of metric information.

[0076] Since the traditional method often ignores the importance of vehicle metric data in different application scenarios when analyzing vehicle dynamic data, resulting in inaccurate evaluation of vehicle metric data, therefore, the embodiments of the present disclosure comprehensively analyze the data quality of multiple metric information in data type application scenarios, business type application scenarios, and vehicle type application scenarios.

[0077] Step S102, collect the vehicle dynamic data uploaded by a batch of vehicles within a preset time.

[0078] Specifically, the preset time can be 1 day or 2 days or within several hours, and the vehicle dynamic data can be vehicle operation data.

[0079] In some alternative embodiments, collecting the vehicle dynamic data uploaded by a batch of vehicles within a preset time includes:

[0080] Step b1, collect the vehicle message data of a batch of vehicles within a preset time.

[0081] Specifically, as Figure 3 shown, it is a schematic diagram for accessing vehicle data. In Figure 3 , the terminal can bus message data uploaded by a batch of vehicles every day is used as the basic data for statistics. The real-time message processing framework is adopted to consume the vehicle message data in the message queue in real time, and the vehicle message data is parsed in combination with the GBT32960 protocol. The normally parsed vehicle message data is output to the detailed data stream, and the abnormal data is output to the abnormal data stream. Finally, the data is persisted to the distributed storage system.

[0082] For example, the embodiments of the present disclosure can load the vehicle message data collected yesterday every day at midnight, and group the vehicle message data according to the unique vehicle identifier. Each vehicle uploads vehicle message data according to the preset time every day. Suppose there are tens of millions of vehicles in the country that upload vehicle message data according to the preset time every day, and all the data will be aggregated into a database. The embodiments of the present disclosure will uniformly process all the data every day, and need to process the data of the same vehicle as a data set when processing the data. On this basis, the grouped data is sorted according to the collection time, and then the number of items is counted based on the defined index rules. Finally, the normal index score value of the data uploaded by a certain vehicle under various index information can be counted. For example, if vehicle B uploads 10,000 pieces of data about index a, and among them, 100 pieces of data are empty or invalid, then the normal index score value of vehicle B about index a is (10000 - 100) / 10000.

[0083] Step b2: Parse the vehicle dynamic data from the vehicle message data uploaded within the preset time.

[0084] Specifically, for the vehicle message data uploaded by a batch of vehicles every day, it is converted into structured data according to the GBT32960 protocol, as Figure 4 shown, it is a schematic diagram for parsing the vehicle message data.

[0085] As shown in Table 2 below, it is the parsed structured original data table.

[0086] Table 2

[0087] Field Type Remark Vin String Vehicle Identification Number Vid String Vehicle Unique ID Vtype String Message Type … … …

[0088] As shown in Table 3 below, it is the parsed structured abnormal data table.

[0089] Table 3

[0090]

[0091] Step S103: Count the normal index score values of the vehicle dynamic data uploaded within a preset time under each index information in the target application scenario, where the target application scenario is at least one application scenario among multiple application scenarios.

[0092] Specifically, since the target application scenario includes at least one of the vehicle type application scenario, data type application scenario, and business type application scenario, the embodiments of the present disclosure can count the normal index score values of the vehicle dynamic data uploaded within a preset time under each index information in the vehicle type application scenario or data type application scenario or business type application scenario or at least multiple scenarios.

[0093] In some alternative embodiments, the above step S103, counting the normal index score values of the vehicle dynamic data uploaded within a preset time under each index information in the target application scenario, includes:

[0094] Step c1: Count the total number of vehicle dynamic data uploaded within a preset time.

[0095] Step c2: Count the number of vehicle dynamic data uploaded within a preset time that are in a normal state.

[0096] Step c3: Calculate the normal index score values of the vehicle dynamic data uploaded within a preset time under each index information in the target application scenario according to the total number of vehicle dynamic data uploaded within a preset time and the number of vehicle dynamic data uploaded within a preset time that are in a normal state.

[0097] Taking the vehicle type application scenario as an example, in this application scenario, it includes but is not limited to scenarios such as single vehicles, vehicle models, and brands. For example, the number of vehicle dynamic data belonging to the single vehicle type is 10,000, among which 100 data are empty or invalid. Then the normal index score value belonging to the single vehicle type is (10000 - 100) / 10000;

[0098] Similarly, for the vehicle dynamic data belonging to the vehicle model type or the vehicle brand type, the statistical method of the normal index score value is the same as that of the vehicle dynamic data belonging to the single vehicle type.

[0099] Taking the data type application scenario as an example, in this application scenario, it includes but is not limited to vehicle body data, location data, single - entity data, extreme value data, fuel cell data, alarm data, and drive motor data. For example, the number of vehicle dynamic data belonging to the vehicle body data is 10,000, among which 100 data are empty or invalid. Then the normal index score value belonging to the vehicle body data is (10000 - 100) / 10000.

[0100] Similarly, for vehicle dynamic data belonging to location data, or vehicle dynamic data belonging to single - entity data, or vehicle dynamic data belonging to extreme - value data, or vehicle dynamic data belonging to fuel - cell data, or vehicle dynamic data belonging to alarm data, or vehicle dynamic data belonging to drive - motor data, the statistical method for the normal index score values is the same as that for vehicle dynamic data belonging to vehicle - whole data.

[0101] Step S104: Calculate the weight parameters for each item of index information in the target application scenario according to the normal index score values for each item of index information in the target application scenario, so that the normal index score values for each item of index information in the target application scenario tend to the standard value.

[0102] Since the traditional method usually relies more on subjective experience when assigning index data, lacking scientific nature, the embodiments of the present disclosure determine the weight parameters for each item of index information in the target application scenario through some calculation methods, thereby ensuring that the normal index scores of multiple items of index information in the target application scenario are more standardized, and improving the accuracy of the normal index score values for each item of index information in the target application scenario.

[0103] For example, when the normal index score values for each item of index information in the target application scenario are for a data - type application scenario (vehicle - whole data, location data, single - entity data, extreme - value data, fuel - cell data, alarm data, drive - motor data), and the multiple items of index information are 99 items of index information determined based on the GBT32960 protocol. For example, the entropy - weight method can be used to assign weights based on the actual data change situation in the data - type application scenario to ensure the scientific nature, rationality, and accuracy of weight distribution, reduce human interference, and improve the objectivity and fairness of the data - quality evaluation of multiple items of index information in the data - type application scenario.

[0104] For example, when the normal index score values for each item of index information in the target application scenario are for a vehicle - type application scenario (vehicle model, single vehicle, brand), and the multiple items of index information are 99 items of index information determined based on the GBT32960 protocol, the entropy - weight method can also be used to assign weights based on the actual data change situation in the vehicle - type application scenario to ensure the scientific nature, rationality, and accuracy of weight distribution, reduce human interference, and improve the objectivity and fairness of the data - quality evaluation of multiple items of index information in the vehicle - type application scenario.

[0105] For example, when the target application scenario is the normal index score value under each index information in the business type application scenario (segmenting business index data and security warning index data), the multiple index information is 99 index information determined based on the GBT32960 protocol. The entropy weight method can also be used to assign weights based on the actual data change situation in the business type application scenario to ensure the scientificity, rationality, and accuracy of weight allocation, reduce human interference, and improve the objectivity and fairness of the data quality evaluation of multiple index information in the business type application scenario.

[0106] Step S105: According to the normal index score value under each index information in the target application scenario and the weight parameter under each index information in the target application scenario, evaluate the data quality score of the normal index score value under each index information in the target application scenario.

[0107] Specifically, for example, combining the normal index score value under each index information in the target application scenario (data type application scenario or vehicle type application scenario or business type application scenario or at least one application scenario) and the weight parameter under each index information in the target application scenario, further determine the data quality score of the normal index score value under each index information in the target application scenario finally through some calculation methods similar to weighted average.

[0108] Therefore, since the embodiments of the present disclosure consider multiple index information in multiple application scenarios, it is beneficial to improve the comprehensiveness of index information evaluation for vehicle dynamic data in multiple application scenarios, automatically assign corresponding weight parameters to the normal index score values under each index information in at least one of the multiple application scenarios, without subjective human weight assignment, thereby ensuring the scientificity, rationality, and accuracy of weight allocation, and further evaluating the data quality score of the normal index score value under each index information in the target application scenario, ultimately improving the objectivity, fairness, and comprehensiveness of the data quality evaluation of multiple index information in various different application scenarios.

[0109] In this embodiment, a method for evaluating the quality of vehicle networking dynamic data is provided, which can be used in devices such as mobile phones, tablet computers, desktop computers, portable notebooks, servers, etc. Figure 6 It is a flowchart of the method for evaluating the quality of vehicle networking dynamic data according to the embodiments of the present invention, as Figure 6 shown. The above step S104: According to the normal index score value under each index information in the target application scenario, obtain the weight parameter under each index information in the target application scenario, including:

[0110] Step S1041: According to the normal index score value under each index information in the target application scenario, construct a target data matrix.

[0111] In a specific example, according to the target application scenario (data type application scenario or vehicle type application scenario or business type application scenario or at least one of multiple application scenarios), the target data matrix is constructed as shown in the following formula (1).

[0112]

[0113] In the above formula (1), n represents the number of samples of multiple index information under the target application scenario, m represents the m-th index information, the maximum value of m is 99, and x ij represents the normal index score value of the j-th index information.

[0114] In the embodiment of the present disclosure, the normal index score values of the vehicle dynamic data uploaded within the preset time under the target application scenario are arranged in matrix form to construct the target data matrix, which is convenient for improving the data processing efficiency.

[0115] Step S1042: Select the minimum data and the maximum data from the target data matrix.

[0116] Step S1043: Perform standardization processing on each index information in the target data matrix according to the minimum data and the maximum data.

[0117] In a specific example, the standardization processing of any item in the target data matrix is performed as shown in the following formula (2).

[0118]

[0119] Among them, x ij represents the normal index score value of the j-th index information in the i-th row, min(X j ) represents the minimum data, and max(X j ) represents the maximum data.

[0120] In another specific example, the standardization processing of each index information in the target data matrix is performed as shown in the following formula (3).

[0121]

[0122] In the embodiment of the present disclosure, the standardization processing of each index information in the target data matrix is convenient for unifying the original data values into the interval [0, 1], improving the stability and accuracy of the data, and further facilitating the subsequent analysis of the data quality of the normal index score values under the target application scenario.

[0123] Step S1044: Calculate the proportion parameter of the normal index score value under each index information in the target application scenario according to the standardization processing result.

[0124] In a specific example, the proportion parameter of the normal index score value under each index information in the target application scenario is shown by the following formula (4).

[0125]

[0126] Among them, p ij is the proportion of a certain index data after standardized processing in the sum of multiple indexes after standard processing, and y ij represents the standardized processing result of the normal index score value of the j-th index information in the i-th row.

[0127] In the above formula (4), if the p ij value of a certain sample in a certain index is relatively different from other samples, it indicates that the characteristics of this sample in this index are obvious, this index plays an important role in distinguishing samples, and provides a lot of information. By calculating the proportion parameter, the information contribution of different samples under each index can be initially measured, providing a basis for determining the index weight later.

[0128] Step S1045, calculate the information entropy of the normal index score value under each index information in the target application scenario according to the proportion parameter of the normal index score value under each index information in the target application scenario.

[0129] In a specific example, the information entropy of the normal index score value under each index information in the target application scenario is shown by the following formula (5).

[0130]

[0131] Among them, n is the number of samples. Generally speaking, 0 ≤ E j ≤ 1, and E j is the information entropy of the normal index score value under the j-th index information. p ij is the proportion of a certain index data after standardized processing in the sum of multiple indexes after standard processing. The information entropy can reflect the dispersion degree of the index data. The smaller the dispersion degree, the larger the information entropy, and the less information is provided; the larger the dispersion degree, the smaller the information entropy, and the more information is provided. The information entropy reflects a degree of chaos or disorder of the data. The larger the entropy, the more chaotic the information, the greater the uncertainty, the smaller the amount of information, the smaller the information variation, and the smaller the weight.

[0132] Step S1046, calculate the weight parameter of the normal index score value under each index information in the target application scenario according to the information entropy of the normal index score value under each index information in the target application scenario.

[0133] In a specific example, the weight parameter of the normal index score value under each index information in the target application scenario is shown by the following formula (6).

[0134]

[0135] In the above formula (6), calculate the information entropy of the normal index score value of the index information in the above formula (1), D j is the information redundancy of the normal index score value under the j-th index information, W j is the weight parameter of the normal index score value under each index information in the target application scenario, E j is the information entropy of the normal index score value under the j-th index information.

[0136] In the embodiments of the present disclosure, the weight parameters of the normal index score values under each index information in the target application scenario are determined in the above manner, and the normal index score values under each index information in at least one of multiple application scenarios are automatically assigned corresponding weight parameters, and further, the data quality score of the normal index score values under each index information in the target application scenario is evaluated. There is no need for subjective human weighting, thereby ensuring the scientificity, rationality, and accuracy of weight allocation, and finally improving the objectivity, fairness, and comprehensiveness of the data quality evaluation of multiple index information under various different application scenarios.

[0137] In some optional embodiments, in step S105, according to the normal index score values under each index information in the target application scenario and the weight parameters under each index information in the target application scenario, evaluate the normal index score values under each index information in the target application scenario, including:

[0138] Step d1, calculate the product weighted result between the standardized processing result of the normal index score values under each index information in the target application scenario and the weight parameters under each index information in the target application scenario.

[0139] Step d2, calculate the weight weighted result of the weight parameters under each index information in the target application scenario.

[0140] Step d3, calculate the quotient of the product weighted result divided by the weight weighted result to obtain the normal index score values under each index information in the target application scenario.

[0141] In a specific example, the normal index score values under each index information in the target application scenario are shown by the following formula (7).

[0142]

[0143] where Score ij is the normal index score value under each index information in the target application scenario, W j is the weight parameter of the normal index score value under each index information in the target application scenario, y ijIt represents the normalization result of the normal index score value of the index information of the i-th row and j-th item, W j .y ij It represents the product weighting result between the normalization result of the normal index score value under each index information in the target application scenario and the weight parameter under each index information in the target application scenario.

[0144] As Figure 7 shown, it is a simple schematic diagram of the vehicle networking dynamic data quality evaluation method in the embodiments of the present disclosure. In Figure 7 , it shows the static data related to vehicles, index definitions, index classifications (multiple application scenario classifications). In addition, it also shows vehicle operation data, data parsing, statistical ratio of the normal index rate according to the index definition rules at a preset time (days), calculation of the weight of each index using the entropy weight method based on the scores of each vehicle index every day. Finally, it also shows the associated static data, and calculates the data quality scores of each category under each dimension based on the index scores and index weights, combined with the index classification (multiple application scenarios).

[0145] The embodiments of the present disclosure define multi-dimensional index data including multiple index information (99 key indexes), covering multiple data categories such as vehicle-wide data, single-entity data, and alarm data, to ensure a comprehensive evaluation of the in-vehicle data quality of new energy vehicles. The entropy weight method is used to recalculate the index weights within a preset time (every day), ensuring that the vehicle dynamic data can timely reflect the latest data changes in various application scenarios, and improving the scientificity and real-time nature of the evaluation results. Flexible index combinations are designed for multiple application scenarios to provide accurate data quality evaluation services for enterprises. The automated data governance process greatly improves the evaluation efficiency and cost-effectiveness, while reducing human intervention and enhancing the business response ability. Through a scientific automatic evaluation method, it effectively reduces the subjective deviation of the data quality scoring evaluation of the normal index score value under each index information in the target application scenario, and improves the scientificity of data application and decision-making support ability. In summary, the embodiments of the present disclosure bring a comprehensive, accurate and efficient solution for the data quality evaluation of new energy vehicles, and promote the improvement of the enterprise's data-driven decision-making ability and efficiency.

[0146] In this embodiment, a vehicle networking dynamic data quality evaluation device is also provided. This device is used to implement the above embodiments and preferred implementation manners, and those that have been described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0147] This embodiment provides a vehicle networking dynamic data quality evaluation device. As Figure 8 shown, it includes:

[0148] An information definition module 801, configured to define multiple application scenarios and multiple metric information according to vehicle information, where the multiple application scenarios include: vehicle type application scenarios, data type application scenarios, and service type application scenarios;

[0149] A data collection module 802, configured to collect vehicle dynamic data uploaded by a batch of vehicles within a preset time;

[0150] A data statistics module 803, configured to count the vehicle dynamic data uploaded within a preset time and the normal metric score values of each metric information under a target application scenario, where the target application scenario is at least one of the multiple application scenarios;

[0151] A data calculation module 804, configured to calculate weight parameters of each metric information under a target application scenario according to the normal metric score values of each metric information under the target application scenario, so that the normal metric score values of each metric information under the target application scenario tend to a standard value;

[0152] A data evaluation module 805, configured to evaluate the data quality score of the normal metric score values of each metric information under a target application scenario according to the normal metric score values of each metric information under the target application scenario and the weight parameters of each metric information under the target application scenario.

[0153] In some alternative embodiments, the data calculation module 804 includes:

[0154] A data construction sub-module, configured to construct a target data matrix according to the normal metric score values of each metric information under a target application scenario;

[0155] A data selection sub-module, configured to select the minimum data and the maximum data from the target data matrix;

[0156] A data processing sub-module, configured to perform standardization processing on each metric information in the target data matrix according to the minimum data and the maximum data;

[0157] A first calculation sub-module, configured to calculate the proportion parameters of the normal metric score values of each metric information under a target application scenario according to the standardization processing result;

[0158] A second calculation sub-module, configured to calculate the information entropy of the normal metric score values of each metric information under a target application scenario according to the proportion parameters of the normal metric score values of each metric information under a target application scenario;

[0159] A third calculation sub-module, configured to calculate weight parameters of normal index score values under each index information in a target application scenario according to the information entropy of the normal index score values under each index information in the target application scenario.

[0160] In some alternative embodiments, the data evaluation module 805 includes:

[0161] A first calculation sub-module, configured to calculate a product weighting result between a standardized processing result of normal index score values under each index information in a target application scenario and weight parameters of normal index score values under each index information in the target application scenario;

[0162] A second calculation sub-module, configured to calculate a weight weighting result of weight parameters of normal index score values under each index information in the target application scenario;

[0163] A third calculation sub-module, configured to calculate a quotient value obtained by dividing the product weighting result by the weight weighting result, so as to obtain normal index score values under each index information in the target application scenario.

[0164] In some alternative embodiments, the data statistics module 803 includes:

[0165] A first statistics sub-module, configured to count the total number of vehicle dynamic data uploaded within a preset time;

[0166] A second statistics sub-module, configured to count the number of vehicle dynamic data uploaded within a preset time that are in a normal state;

[0167] A data calculation sub-module, configured to calculate normal index score values under each index information in a target application scenario according to the total number of vehicle dynamic data uploaded within a preset time and the number of vehicle dynamic data uploaded within a preset time that are in a normal state.

[0168] In some alternative embodiments, the information definition module 801 includes:

[0169] A first definition sub-module, configured to define a vehicle type application scenario according to vehicle static attribute information;

[0170] A second definition sub-module, configured to define a data type application scenario, a service type application scenario, and multiple index information according to vehicle dynamic attribute information.

[0171] In some alternative embodiments, the data acquisition module 802 includes:

[0172] A data acquisition sub-module, configured to acquire vehicle message data uploaded by a batch of vehicles within a preset time;

[0173] A data parsing sub-module, configured to parse vehicle dynamic data from the vehicle message data uploaded within a preset time.

[0174] A data evaluation module, configured to evaluate the data quality score of the normal index score value of each item of index information in the target application scenario according to the normal index score value of each item of index information in the target application scenario and the weight parameter of each item of index information in the target application scenario.

[0175] The further function descriptions of the above-mentioned various modules and units are the same as those in the corresponding embodiments above, and will not be repeated here.

[0176] The vehicle networking dynamic data quality evaluation device in this embodiment is presented in the form of functional units. Here, the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0177] An embodiment of the present invention further provides a computer device having the above-mentioned vehicle networking dynamic data quality evaluation device.

[0178] Please refer to Figure 9 , Figure 9 which is a schematic structural diagram of a computer device provided by an optional embodiment of the present invention. As Figure 9 shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including a high-speed interface and a low-speed interface. Each component communicates with each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (such as a server array, a set of blade servers, or a multi-processor system). Figure 9 In

[0179] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Among them, processor 10 may further include a hardware chip. The above-mentioned hardware chip may be an application specific integrated circuit, a programmable logic device, or a combination thereof. The above-mentioned programmable logic device may be a complex programmable logic device, a field programmable gate array, a general array logic, or any combination thereof.

[0180] Among them, the memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiments.

[0181] The memory 20 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 may optionally include a memory remotely disposed relative to the processor 10, and these remote memories may be connected to the computer device through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0182] The memory 20 may include a volatile memory, for example, a random access memory; the memory may also include a non-volatile memory, for example, a flash memory, a hard disk, or a solid-state drive; the memory 20 may also include a combination of the above types of memories.

[0183] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0184] The embodiments of the present invention further provide a computer-readable storage medium. The method according to the embodiments of the present invention can be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented as computer code that is originally stored in a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be processed by such software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium may be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium may also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.

[0185] A part of the present invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the present invention through the operations of the computer. Those skilled in the art should understand that the forms of existence of computer program instructions in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Herein, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0186] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for evaluating the quality of dynamic data of an Internet of Vehicles, characterized in that: The method comprises: According to the vehicle information, multiple application scenarios and multiple indicator information are defined, wherein the multiple application scenarios include: vehicle type application scenario, data type application scenario, and business type application scenario; Collect vehicle dynamic data uploaded by batches of vehicles within a preset time; Counting the vehicle dynamic data uploaded within the preset time, and the normal index score values ​​under each index information in the target application scenario, wherein the target application scenario is at least one application scenario among the multiple application scenarios; Calculate the weight parameters of each item of indicator information under the target application scenario according to the normal indicator score values ​​under each item of indicator information under the target application scenario, so that the normal indicator score values ​​under each item of indicator information under the target application scenario tend to the standard value; According to the normal indicator score values ​​under the various indicator information under the target application scenario and the weight parameters under the various indicator information under the target application scenario, the data quality score of the normal indicator score values ​​under the various indicator information under the target application scenario is evaluated.

2. The method according to claim 1, characterized in that: According to the normal indicator score value under the various indicator information under the target application scenario, the weight parameter under the various indicator information under the target application scenario is obtained, including: Constructing a target data matrix according to the normal indicator score values ​​under the various indicator information under the target application scenario; Selecting minimum data and maximum data from the target data matrix; According to the minimum data and the maximum data, standardize the information of each indicator in the target data matrix; According to the normalization processing result, calculate the weight parameter of the normal indicator score value under the various indicator information in the target application scenario; Calculating the information entropy of the normal indicator score value under the various indicator information under the target application scenario according to the weight parameter of the normal indicator score value under the various indicator information under the target application scenario; According to the information entropy of the normal indicator score value under the various indicator information under the target application scenario, the weight parameter of the normal indicator score value under the various indicator information under the target application scenario is calculated.

3. The method according to claim 2, characterized in that According to the normal indicator score value under the various indicator information under the target application scenario and the weight parameter under the various indicator information under the target application scenario, the normal indicator score value under the various indicator information under the target application scenario is evaluated, including: Calculate the weighted product of the normalized processing result of the normal indicator score value under the various indicator information under the target application scenario and the weight parameter under the various indicator information under the target application scenario; Calculate the weighted results of the weight parameters under the various indicator information under the target application scenario; The quotient of the weighted product result divided by the weighted weight result is calculated to obtain the normal indicator score value under the various indicator information in the target application scenario.

4. The method according to claim 1, characterized in that The vehicle dynamic data uploaded within the preset time is counted, and the normal index score values ​​under the various index information in the target application scenario include: Counting the total amount of vehicle dynamic data uploaded within the preset time; Counting the number of vehicle dynamic data uploaded within the preset time that are in normal state; According to the total amount of vehicle dynamic data uploaded within the preset time and the amount of vehicle dynamic data uploaded within the preset time that is in a normal state, the normal indicator score value under the various indicator information in the target application scenario is calculated.

5. The method according to claim 1, characterized in that The vehicle information includes vehicle static attribute information and vehicle dynamic attribute information, and includes: Defining the vehicle type application scenario according to the vehicle static attribute information; According to the vehicle dynamic attribute information, the data type application scenario, the business type application scenario, and the multiple indicator information are defined.

6. The method according to claim 1, characterized in that The vehicle dynamic data uploaded by batch vehicles within a preset time is collected, including: Collect vehicle message data uploaded by batch vehicles within a preset time; The vehicle dynamic data is parsed from the vehicle message data uploaded within the preset time.

7. A vehicle network dynamic data quality evaluation device, characterized in that: The device comprises: An information definition module, used to define multiple application scenarios and multiple indicator information according to vehicle information, wherein the multiple application scenarios include: vehicle type application scenario, data type application scenario, and business type application scenario; The data collection module is used to collect vehicle dynamic data uploaded by batches of vehicles within a preset time; A data statistics module, used to count the vehicle dynamic data uploaded within the preset time, and the normal index score value under each index information in the target application scenario, wherein the target application scenario is at least one application scenario among the multiple application scenarios; A data calculation module, used to calculate the weight parameters of each indicator information under the target application scenario according to the normal indicator score value under each indicator information under the target application scenario, so that the normal indicator score value under each indicator information under the target application scenario tends to a standard value; The data evaluation module is used to evaluate the data quality score of the normal indicator score under the various indicator information under the target application scenario according to the normal indicator score under the various indicator information under the target application scenario and the weight parameters under the various indicator information under the target application scenario.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the vehicle network dynamic data quality assessment method according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the vehicle network dynamic data quality assessment method according to any one of claims 1 to 6.

10. A computer program product, characterized in that It includes computer instructions, which are used to enable a computer to execute the vehicle network dynamic data quality assessment method according to any one of claims 1 to 6.

Images