Data quality evaluation methods, devices, equipment and storage media for vehicle-to-everything (V2X)

By evaluating vehicle network data from multiple dimensions, the problem of incomplete data quality assessment in vehicle network systems has been solved, enabling scientific, accurate, and comprehensive evaluation of vehicle monitoring.

CN118860832BActive Publication Date: 2026-11-17BEIJING INST OF TECH XINYUAN INFORMATION TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411129225.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-16
Publication Date
2026-11-17
Estimated Expiration
2044-08-16

AI Technical Summary

Technical Problem

In existing technologies, the lack of comprehensive, scientific, and intuitive data quality indicators in vehicle networking systems makes it impossible to accurately assess data quality and affects the effectiveness of vehicle monitoring.

Method used

The raw dataset for remote monitoring of vehicle emissions is evaluated from five dimensions: terminal activation quality, data verification quality, data transmission quality, terminal acquisition quality, and long-term offline performance. The evaluation results of the vehicle network data quality are determined by multiple quality evaluation values ​​and weight values.

Benefits of technology

It enables a scientific, comprehensive, and intuitive evaluation of the quality of vehicle network data, ensuring the effectiveness and accuracy of vehicle monitoring, with broad coverage and a scientific and accurate scoring method.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118860832B_ABST
    Figure CN118860832B_ABST
Patent Text Reader

Abstract

This invention relates to the field of vehicle networking technology and discloses a data quality evaluation method, device, equipment, and storage medium for vehicle networking. This invention evaluates the acquired raw dataset of remote monitoring of vehicle emissions from five dimensions: terminal activation quality, data verification quality, data transmission quality, terminal acquisition quality, and long-term offline performance. It has a wide coverage and can more scientifically, accurately, comprehensively, and intuitively identify data quality problems, thereby completing a reasonable and accurate evaluation of data quality and realizing effective vehicle monitoring.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of vehicle networking technology, and specifically to a data quality evaluation method, apparatus, device, and storage medium for vehicle networking. Background Technology

[0002] With the development of communication technology and automotive electronics technology, vehicle networking systems have been widely used. Due to different data sources, the data collected by vehicle terminals is bound to be abnormal. If the abnormal data cannot be accurately and effectively judged, it will affect subsequent data processing and services. Therefore, it is necessary to accurately assess the quality of vehicle networking data.

[0003] Existing technologies primarily rely on continuously acquiring information from multiple data sources, including events, statuses, and alerts from devices and systems, based on raw data collected and uploaded. This efficient real-time data collection forms analytical data sources, allowing for rapid identification of abnormal data or their causes through analysis and evaluation, facilitating the assessment of the quality of data uploaded from devices. Currently, however, because data quality information is scattered across multiple application modules of the automotive service platform, the lack of comprehensive, scientific, and intuitive data quality indicators prevents a reasonable and accurate evaluation of data quality, thus hindering effective vehicle monitoring. Summary of the Invention

[0004] In view of this, the present invention provides a data quality evaluation method, apparatus, device and storage medium for the Internet of Vehicles, in order to solve the problem that the lack of comprehensive, scientific and intuitive data quality indicators in the prior art leads to the inability to complete reasonable and accurate evaluation of data quality, and thus the inability to achieve effective vehicle monitoring.

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

[0006] Obtain the raw dataset for remote monitoring of vehicle emissions; evaluate the raw dataset for remote monitoring of vehicle emissions from five dimensions: terminal activation quality, data verification quality, data transmission quality, terminal acquisition quality, and long-term offline performance, and obtain multiple quality evaluation values; determine multiple quality evaluation weight values ​​based on the multiple quality evaluation values; and determine the vehicle network data quality evaluation result based on the multiple quality evaluation values ​​and the multiple quality evaluation weight values.

[0007] The data quality evaluation method for the Internet of Vehicles provided by this invention evaluates the acquired raw dataset of remote monitoring of vehicle emissions from five dimensions: terminal activation quality, data verification quality, data transmission quality, terminal acquisition quality, and long-term offline performance. This method has a wide coverage and can more scientifically, accurately, comprehensively, and intuitively identify data quality problems, thereby completing a reasonable and accurate evaluation of data quality and achieving effective vehicle monitoring.

[0008] In one optional implementation, multiple quality evaluation values ​​include terminal activation quality evaluation value, data verification quality evaluation value, data transmission quality evaluation value, terminal acquisition quality evaluation value, and long-term offline quality evaluation value; the raw dataset for remote vehicle emission monitoring is evaluated from five dimensions—terminal activation quality, data verification quality, data transmission quality, terminal acquisition quality, and long-term offline—to obtain multiple quality evaluation values, including:

[0009] Obtain the terminal activation problem type set, data verification problem type set, data transmission problem type set, terminal acquisition quality verification index set, and long-term offline verification dataset; based on the original vehicle emission remote monitoring dataset, terminal activation problem type set, data verification problem type set, and data transmission problem type set, determine the terminal activation quality evaluation value, data verification quality evaluation value, and data transmission quality evaluation value; based on the original vehicle emission remote monitoring dataset and the terminal acquisition quality verification index set, determine the terminal acquisition quality evaluation value; based on the original vehicle emission remote monitoring dataset and the long-term offline verification dataset, determine the long-term offline quality evaluation value.

[0010] The data quality evaluation method for the Internet of Vehicles provided by this invention, by combining the acquired terminal activation problem type set, data verification problem type set, data transmission problem type set, terminal collection quality verification index set, and long-term offline verification dataset, can achieve a comprehensive, reasonable, and accurate evaluation of data quality, and realize effective vehicle monitoring.

[0011] In one optional implementation, based on the original dataset of vehicle emission remote monitoring, the set of terminal activation problem types, the set of data verification problem types, and the set of data transmission problem types, the terminal activation quality evaluation value, the data verification quality evaluation value, and the data transmission quality evaluation value are determined, including:

[0012] Based on the original dataset of remote vehicle emission monitoring and the set of terminal activation problem types, the terminal activation quality evaluation value is obtained after processing by the terminal activation quality verification model; based on the original dataset of remote vehicle emission monitoring and the set of data verification problem types, the data verification quality evaluation value is obtained after processing by the data verification quality verification model; based on the original dataset of remote vehicle emission monitoring and the set of data transmission problem types, the data transmission quality evaluation value is obtained after processing by the data transmission quality verification model.

[0013] In one optional implementation, the terminal data collection quality verification index set includes OBD data out-of-bounds rate index, OBD data inefficiency index, engine data out-of-bounds rate index, engine data inefficiency index, SCR downstream NOx data out-of-bounds rate index, SCR downstream NOx data inefficiency index, terminal time synchronization accuracy index, packet loss rate index, data collection cycle index, and data forwarding latency index.

[0014] Based on the original dataset of vehicle emission remote monitoring and the set of terminal data acquisition quality verification indicators, the terminal data acquisition quality evaluation value is determined, including:

[0015] The accuracy of the raw dataset for remote vehicle emission monitoring is evaluated based on the following indicators: OBD data out-of-bounds rate, engine data out-of-bounds rate, and SCR downstream NOx data out-of-bounds rate, resulting in an accuracy score. The effectiveness of the raw dataset is evaluated based on the following indicators: OBD data inefficiency, engine data inefficiency, and SCR downstream NOx data inefficiency, resulting in an effectiveness score. The timeliness of the raw dataset is evaluated based on the following indicators: terminal time synchronization accuracy and data forwarding latency, resulting in a timeliness score. The compliance of the raw dataset is evaluated based on the following indicators: data acquisition cycle, resulting in a compliance score. The integrity of the raw dataset is evaluated based on the following indicators: packet loss rate, resulting in an integrity score. Finally, the terminal acquisition quality evaluation value is determined based on the accuracy score, effectiveness score, timeliness score, compliance score, and integrity score.

[0016] The data quality evaluation method for the Internet of Vehicles provided by this invention evaluates the terminal collection quality based on 10 indicators, including OBD data out-of-bounds rate, OBD data inefficiency, engine data out-of-bounds rate, engine data inefficiency, SCR downstream NOx data out-of-bounds rate, SCR downstream NOx data inefficiency, terminal time synchronization accuracy, packet loss rate, data collection cycle, and data forwarding latency. The method has broad data coverage, high utilization rate, and a scientific and accurate scoring method.

[0017] In one optional implementation, after determining multiple quality evaluation weight values ​​based on multiple quality evaluation values, the method further includes:

[0018] Obtain a real-time dataset of vehicle emissions remote monitoring, and optimize multiple quality evaluation weight values ​​based on the real-time dataset of vehicle emissions remote monitoring.

[0019] The data quality evaluation method for the Internet of Vehicles provided by this invention continuously optimizes multiple quality evaluation weight values ​​as the data of the Internet of Vehicles increases, making the quality evaluation weight values ​​more and more accurate, and thus making the final score more and more objective and reasonable.

[0020] In one optional implementation, the quality evaluation result of the vehicle-to-everything (V2X) data is determined based on multiple quality evaluation values ​​and multiple quality evaluation weight values, including:

[0021] Based on multiple quality evaluation values ​​and multiple quality evaluation weight values, a data quality score is calculated; based on the data quality score, the quality of the original dataset of vehicle emission remote monitoring is divided to obtain the data quality evaluation result of the Internet of Vehicles.

[0022] Secondly, the present invention provides a data quality evaluation device for the Internet of Vehicles, the device comprising:

[0023] The system comprises the following modules: an acquisition module for acquiring the raw dataset of remote vehicle emission monitoring; an evaluation module for evaluating the raw dataset from five dimensions: terminal activation quality, data verification quality, data transmission quality, terminal acquisition quality, and long-term offline performance, resulting in multiple quality evaluation values; a first determination module for determining multiple quality evaluation weight values ​​based on these values; and a second determination module for determining the vehicle network data quality evaluation result based on the multiple quality evaluation values ​​and their weight values.

[0024] Thirdly, the present invention provides a computer device, comprising: 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 computer instructions to perform the data quality evaluation method for the Internet of Vehicles described in the first aspect or any corresponding embodiment thereof.

[0025] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the data quality evaluation method for the Internet of Vehicles described in the first aspect or any corresponding embodiment thereof.

[0026] Fifthly, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute the data quality evaluation method for the Internet of Vehicles described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0027] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0028] Figure 1 This is a flowchart illustrating a data quality evaluation method for the Internet of Vehicles according to an embodiment of the present invention.

[0029] Figure 2 This is a schematic diagram of the underlying communication bearer protocol according to an embodiment of the present invention;

[0030] Figure 3 This is a schematic diagram of the real-time information reporting process according to an embodiment of the present invention;

[0031] Figure 4 This is a flowchart illustrating another data quality evaluation method for the Internet of Vehicles according to an embodiment of the present invention;

[0032] Figure 5 This is a flowchart illustrating another data quality evaluation method for the Internet of Vehicles according to an embodiment of the present invention;

[0033] Figure 6 This is a flowchart illustrating another data quality evaluation method for the Internet of Vehicles according to an embodiment of the present invention.

[0034] Figure 7 This is a structural block diagram of a data quality evaluation device for the Internet of Vehicles according to an embodiment of the present invention;

[0035] Figure 8 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0037] This invention provides a data quality evaluation method for the Internet of Vehicles (IoV). The method evaluates the acquired raw dataset of remote monitoring of vehicle emissions from five dimensions: terminal activation quality, data verification quality, data transmission quality, terminal acquisition quality, and long-term offline performance. This results in a more scientific, accurate, comprehensive, and intuitive evaluation of data quality.

[0038] According to an embodiment of the present invention, a data quality evaluation method for vehicle networking is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0039] This embodiment provides a data quality evaluation method for the Internet of Vehicles (IoV), which can be used in electronic devices such as computers, mobile phones, and tablets. Figure 1 This is a flowchart of a data quality evaluation method for the Internet of Vehicles according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0040] Step S101: Obtain the raw dataset for remote monitoring of vehicle emissions.

[0041] Specifically, GB 17691-2018 "Emission Limits and Measurement Methods for Pollutants from Heavy-Duty Diesel Vehicles (China VI)" and HJ 1239-2021 "Technical Specifications for Remote Monitoring of Emissions from Heavy-Duty Vehicles" stipulate that newly manufactured heavy-duty vehicles must be equipped with onboard terminals to transmit specified parameters to the ecological and environmental authorities. The standards also specify the basic requirements for data upload, stipulating that the TCP / IP network control protocol should be used as the underlying communication protocol. Figure 2 As shown.

[0042] Among them, such as Figure 3 As shown, the vehicle terminal initiates a communication connection request to the management platform. Once the communication link is established, the vehicle terminal should automatically send login information to the management platform for identity verification. The remote service and management platform should verify the received data. If the verification is correct, the management platform receives the data; if the verification is incorrect, the platform should ignore the received data.

[0043] In this embodiment, the evaluation of raw data from remote monitoring of emissions from heavy-duty diesel vehicles is taken as an example. The data acquisition frequency is 1 Hz, and the raw dataset for remote monitoring of vehicle emissions may include:

[0044] (1) OBD data stream: OBD diagnostic protocol, MIL status, diagnostic support status, diagnostic ready status, vehicle identification number, software calibration identification number, calibration verification code, IUPR value, total number of fault codes.

[0045] (2) Engine data stream: vehicle speed, atmospheric pressure, net engine output torque, friction torque, engine speed, engine fuel flow, output value of NOx sensor upstream of SCR, output value of NOx sensor downstream of SCR, reactant balance, intake air volume, SCR inlet temperature, SCR outlet temperature, DPF differential pressure, engine coolant temperature, fuel tank level, positioning status, longitude, latitude, and cumulative mileage.

[0046] (3) Terminal message sending time and server receiving time.

[0047] Step S102: The raw dataset for remote monitoring of vehicle emissions is evaluated from five dimensions: terminal activation quality, data verification quality, data transmission quality, terminal acquisition quality, and long-term offline performance, resulting in multiple quality evaluation values.

[0048] Specifically, the obtained raw dataset for remote monitoring of vehicle emissions is divided into five dimensions: terminal activation quality, data verification quality, data transmission quality, terminal acquisition quality, and long-term offline quality. The quality of vehicle-uploaded data is evaluated from these five dimensions, and multiple corresponding quality evaluation values ​​are obtained.

[0049] Step S103: Determine multiple quality evaluation weight values ​​based on multiple quality evaluation values.

[0050] Specifically, by combining the obtained multiple quality evaluation values, the quality evaluation weight value corresponding to each quality evaluation value can be calculated.

[0051] Step S104: Determine the quality evaluation result of the vehicle network data based on multiple quality evaluation values ​​and multiple quality evaluation weight values.

[0052] Specifically, the final vehicle network data quality evaluation result can be calculated and determined by combining each quality evaluation value and the corresponding quality evaluation weight value.

[0053] The data quality evaluation method for the Internet of Vehicles provided in this embodiment evaluates the acquired raw dataset of remote monitoring of vehicle emissions from five dimensions: terminal activation quality, data verification quality, data transmission quality, terminal acquisition quality, and long-term offline performance. This method has a wide coverage and can more scientifically, accurately, comprehensively, and intuitively identify data quality problems, thereby completing a reasonable and accurate evaluation of data quality and achieving effective vehicle monitoring.

[0054] This embodiment provides a data quality evaluation method for the Internet of Vehicles (IoV), which can be used in electronic devices such as computers, mobile phones, and tablets. Figure 4 This is a flowchart of a data quality evaluation method for the Internet of Vehicles according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps:

[0055] Step S401: Obtain the raw dataset for remote vehicle emissions monitoring. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0056] Step S402: The raw dataset for remote monitoring of vehicle emissions is evaluated from five dimensions: terminal activation quality, data verification quality, data transmission quality, terminal acquisition quality, and long-term offline performance, resulting in multiple quality evaluation values.

[0057] Among them, multiple quality evaluation values ​​include terminal activation quality evaluation value, data verification quality evaluation value, data transmission quality evaluation value, terminal acquisition quality evaluation value, and long-term offline quality evaluation value.

[0058] Specifically, step S402 includes:

[0059] Step S4021: Obtain the terminal activation problem type set, data verification problem type set, data transmission problem type set, terminal collection quality verification index set, and long-term offline verification dataset.

[0060] Specifically, the set of terminal activation problem types can include:

[0061] 1) Terminal activation VIN format error;

[0062] 2) Incorrect key;

[0063] 3) The vehicle was not registered;

[0064] 4) Message structure error;

[0065] 5) Vehicle reactivation;

[0066] 6) Signature decryption failed;

[0067] 7) Data packet structure error: Only vehicles directly connected to the terminal are allowed to have inconsistent VINs.

[0068] Furthermore, the set of data verification question types can include:

[0069] 1) Real-time identification error: Real-time data transmission is of data older than 10 minutes;

[0070] 2) Signature decryption failed: Data signature verification failed;

[0071] 3) Incorrect fuel type: The data transmission format identifier is inconsistent with the fuel type registered statically;

[0072] 4) Data packet structure error: The data packet structure is incorrect;

[0073] 5) Error after current time: Transmitting data for future time.

[0074] Furthermore, the data transmission problem types and their corresponding causes are shown in Table 1 below:

[0075] Table 1. Specific Problem Types and Causes of Data Transmission

[0076]

[0077]

[0078] Furthermore, the terminal data acquisition quality verification index set may include: OBD data out-of-bounds rate index B1, OBD data inefficiency index B4, engine data out-of-bounds rate index B2, engine data inefficiency index B5, SCR downstream NOx data out-of-bounds rate index B3, SCR downstream NOx data inefficiency index B6, terminal time synchronization accuracy index B7, and packet loss rate index B8.10 Data collection cycle index B9, data forwarding latency index B8.

[0079] Furthermore, the situation where a vehicle has not been online for more than 30 consecutive days is defined as long-term offline, and a corresponding long-term offline verification dataset is generated.

[0080] Step S4022: Based on the original dataset of vehicle emission remote monitoring, the set of terminal activation problem types, the set of data verification problem types, and the set of data transmission problem types, determine the terminal activation quality evaluation value, the data verification quality evaluation value, and the data transmission quality evaluation value.

[0081] Specifically, by combining the original dataset of remote vehicle emission monitoring with different sets of terminal activation problem types, data verification problem types, and data transmission problem types, different terminal activation quality evaluation values, data verification quality evaluation values, and data transmission quality evaluation values ​​can be obtained respectively.

[0082] In some optional implementations, step S4022 above includes:

[0083] Step a1: Based on the original dataset of vehicle emission remote monitoring and the set of terminal activation problem types, the terminal activation quality evaluation value is obtained after processing by the terminal activation quality verification model.

[0084] Specifically, if a vehicle has one or more terminal activation problem types in the terminal activation problem set, the vehicle is defined as a terminal activation problem vehicle, and a terminal activation quality verification model is established.

[0085] Furthermore, by inputting the number of problematic vehicles into the terminal activation quality verification model, the proportion A1 of the corresponding problematic vehicles in the total number of connected vehicles can be obtained:

[0086] A1 = Vehicles with terminal activation issues / Vehicles connected to the internet

[0087] Furthermore, this proportion A1 is used as the evaluation value for terminal activation quality.

[0088] Step a2: Based on the original dataset of vehicle emission remote monitoring and the data verification issue type set, the data verification quality evaluation value is obtained after processing by the data verification quality verification model.

[0089] Specifically, the vehicle-mounted terminal operates normally and obtains the data signed by the vehicle-mounted emission terminal, and verifies the signature of at least 100 pieces of information using the cryptographic algorithm declared by the manufacturer.

[0090] Furthermore, if a vehicle has one or more data verification issues in the data verification issue type set, the vehicle is defined as a data verification issue vehicle, and a data verification quality verification model is established.

[0091] Furthermore, by inputting the number of vehicles with verification issues into the data verification quality verification model, the proportion (A2) of the number of vehicles with verification issues to the total number of online vehicles can be obtained.

[0092] A2 = Vehicles with data verification issues / Vehicles connected to the network

[0093] Furthermore, this proportion A2 is used as the data verification quality evaluation value.

[0094] Step a3: Based on the original dataset of vehicle emission remote monitoring and the data transmission problem type set, the data transmission quality evaluation value is obtained after processing by the data transmission quality verification model.

[0095] Specifically, after the vehicle is successfully activated, the on-board terminal adds a digital signature to the collected data and transmits it according to the prescribed communication protocol.

[0096] Furthermore, if a vehicle has one or more data transmission problem types in the data transmission problem set, the vehicle is defined as a data transmission problem vehicle, and a data transmission quality verification model is established.

[0097] Furthermore, by inputting the number of vehicles with data transmission problems into the data transmission quality verification model, the proportion (A3) of the corresponding number of vehicles with data transmission problems to the total number of connected vehicles can be obtained.

[0098] A3 = Vehicle with data transmission issues / Vehicle connected to the internet

[0099] Furthermore, this proportion A3 is used as the evaluation value for data transmission quality.

[0100] Step S4023: Based on the original dataset of vehicle emission remote monitoring and the set of terminal acquisition quality verification indicators, determine the terminal acquisition quality evaluation value.

[0101] Specifically, the HJ 1239.2-2021 standard, "Technical Specification for Remote Monitoring of Emissions of Heavy-Duty Vehicles Part 2: Enterprise Platform", stipulates that: the data forwarding delay should not exceed 10s, the data transmission cycle should not exceed 10s, the data transmission packet loss rate should not exceed 1%, and the time error between the vehicle terminal and the standard time should be within ±5s within 24 hours.

[0102] Furthermore, the logic for judging out-of-bounds and invalid OBD data streams in the terminal acquisition quality verification index set is shown in Table 2 below:

[0103] Table 2. Logic for Handling Out-of-Bounds and Invalid Data Streams in OBD

[0104]

[0105]

[0106] Furthermore, the logic for determining out-of-bounds and invalid data streams is shown in Table 3 below:

[0107] Table 3. Logic for Handling Out-of-Bounds and Invalid Data Streams

[0108] Sub-item type Invalid judgment Valid range Speed 65535 [0,250.996] Atmospheric pressure 255 [0,125] Engine net output torque 255 [-125,125] Friction torque 255 [-125,125] Engine speed 65535 [0,8031.875] Engine fuel flow 65535 [0,3212.75] SCR upstream NOx sensor output 65535 [-200,3012.75] SCR downstream NOx sensor output 65535 [-200,3012.75] Reagent balance 255 [0,100] intake volume 65535 [0,3212.75] SCR inlet temperature 65535 [-273,1734.96875] SCR outlet temperature 65535 [-273,1734.96875] DPF pressure difference 65535 [0,6425.5] Engine coolant temperature 255 [-40,210] fuel tank level 255 [0,100] Location status 255 [0,1] longitude 4294967295 [0,180] latitude 4294967295 [0,90] Cumulative Mileage 4294967295 [0,1000000]

[0109] Furthermore, the data transmitted by connected vehicles is analyzed and calculated from five aspects: accuracy, effectiveness, timeliness, compliance, and completeness. The terminal collection quality is comprehensively evaluated and a corresponding terminal collection quality evaluation value is obtained.

[0110] In some optional implementations, step S4023 above includes:

[0111] Step b1: Based on the OBD data out-of-bounds rate index, engine data out-of-bounds rate index, and SCR downstream NOx data out-of-bounds rate index, evaluate the accuracy of the original dataset of vehicle emission remote monitoring and obtain an accuracy score.

[0112] Specifically, the OBD data out-of-bounds rate index B1, the engine data out-of-bounds rate index B2, and the SCR downstream NOx data out-of-bounds rate index B3 are used as indicators to judge data accuracy, as follows:

[0113] (1) OBD data out-of-bounds rate B1

[0114] The OBD data out-of-bounds rate is calculated by dividing the number of data entries in the OBD data stream where any one of the three fields (OBD diagnostic protocol, MIL status, and total number of fault codes) is out of bounds by the total number of OBD transmissions.

[0115] (2) Engine data out-of-bounds rate B2

[0116] The number of data entries in the engine data stream that have an out-of-bounds value in any of the 18 fields (vehicle speed, atmospheric pressure, net engine output torque, friction torque, engine speed, engine fuel flow, SCR upstream NOx sensor output value, reactant balance, intake air volume, SCR inlet temperature, SCR outlet temperature, DPF differential pressure, engine coolant temperature, fuel tank level, positioning status, longitude, latitude, and cumulative mileage) is divided by the total number of engine data entries transmitted (real-time + retransmission) to obtain the engine data out-of-bounds rate.

[0117] (3) NOx data out-of-bounds rate in downstream SCR B3

[0118] In the statistical analysis of engine data stream, the proportion of data frames with atmospheric pressure > 76 kPa and engine coolant temperature > 75°C, where the output value of the NOx sensor downstream of the SCR is out of bounds, is taken as the NOx data out-of-bounds rate downstream of the SCR.

[0119] Furthermore, the weights can be solved using data normalization processing. The weights for OBD data out-of-bounds rate, engine data out-of-bounds rate, and SCR downstream NOx data out-of-bounds rate are B1 / (B1+B2+B3), B2 / (B1+B2+B3), and B3 / (B1+B2+B3), respectively.

[0120] Further, calculate the accuracy score C1:

[0121]

[0122] Step b2: Based on the OBD data inefficiency index, engine data inefficiency index, and SCR downstream NOx data inefficiency index, evaluate the effectiveness of the original dataset for remote vehicle emissions monitoring and obtain an effectiveness score.

[0123] Specifically, the OBD data inefficiency index B4, engine data inefficiency index B5, and SCR downstream NOx data inefficiency index B6 are used as indicators for judging data validity, as follows:

[0124] (1) OBD data inefficiency B4

[0125] The OBD data inefficiency is calculated by dividing the number of data entries in the OBD data stream where any one of the eight fields (OBD diagnostic protocol, MIL status, diagnostic support status, diagnostic ready status, software calibration identification number, calibration verification code, IUPR value, and total number of fault codes) has an invalid value by the total number of OBD transmissions.

[0126] (2) Engine data inefficiency B5

[0127] The number of data entries in the engine data stream where any one of the 18 fields (vehicle speed, atmospheric pressure, net engine output torque, friction torque, engine speed, engine fuel flow, SCR upstream NOx sensor output value, reactant balance, intake air volume, SCR inlet temperature, SCR outlet temperature, DPF differential pressure, engine coolant temperature, fuel tank level, positioning status, longitude, latitude, and cumulative mileage) is invalid is divided by the total number of engine data entries transmitted (real-time + retransmission) as the engine data inefficiency.

[0128] (3) SCR downstream NOx data inefficiency B6

[0129] In the statistical analysis of engine data streams, the proportion of data frames with invalid output values ​​from the downstream NOx sensor of the SCR is selected from those with atmospheric pressure > 76 kPa and engine coolant temperature > 75°C. This proportion is taken as the NOx data inefficiency of the downstream SCR.

[0130] Furthermore, the weights can be solved using data normalization processing. The weights for OBD data inefficiency, engine data inefficiency, and SCR downstream NOx data inefficiency are B4 / (B4+B5+B6), B5 / (B4+B5+B6), and B6 / (B4+B5+B6), respectively.

[0131] Further, calculate the effectiveness score C2:

[0132]

[0133] Step b3: Based on the terminal time synchronization accuracy index and data forwarding latency index, evaluate the timeliness of the original dataset of vehicle emission remote monitoring to obtain a timeliness score.

[0134] Specifically, the terminal time synchronization accuracy index B7 and the data forwarding latency index B8 are used as indicators to judge data timeliness, as follows:

[0135] (1) Terminal time synchronization accuracy B7

[0136] In real-time data, packets whose time difference between terminal packet acquisition and server reception is within 15 seconds are considered to meet protocol requirements for forwarding. The terminal time synchronization accuracy is calculated as the ratio of the accurate number of terminal packets to the number of packets forwarded in real time.

[0137] (2) Data forwarding delay B8

[0138] In real-time data, the average value of the engine data stream server receiving time minus the data sending time is calculated, in seconds. If the vehicle protocol is GB17691, then the server receiving time minus the data acquisition time is used; for other protocols, the server receiving time minus the data sending time is used.

[0139] Furthermore, the data forwarding latency score C3 is calculated:

[0140]

[0141] Furthermore, the weights can be calculated using data normalization, with the terminal time synchronization accuracy weight denoted as X and the data forwarding latency weight denoted as Y:

[0142]

[0143] Y = 1 - X

[0144] Further, calculate the timeliness score C4:

[0145] C4 = (B7*X + C3*Y) / 2 * 100

[0146] Step b4: Based on the data collection cycle index, evaluate the compliance of the original dataset of vehicle emission remote monitoring to obtain a compliance score.

[0147] Specifically, the data collection cycle indicator B9 will be used as an indicator for judging data compliance, as follows:

[0148] First, the logic for determining the data collection cycle is as follows:

[0149] a) Statistical data transmission of vehicle online and offline times, where the logic for determining offline time is: if a vehicle has no data transmission for 300 consecutive frames and the data speed of the last frame is less than 5km / h, then the vehicle is considered offline.

[0150] b) Based on the online / offline time interval and at a data collection frequency of 1 second per frame, calculate the total number of message frames that the vehicle should send during each online / offline time interval;

[0151] c) Calculate the total number of message frames actually accessed by the vehicle;

[0152] d) Data acquisition cycle = total number of message frames to be sent / actual number of message frames received.

[0153] Secondly, calculate the data acquisition cycle score C5:

[0154]

[0155] Finally, calculate the compliance score C6:

[0156] C6 = (1 - C5) * 100

[0157] Step b5: Based on the packet loss rate index, evaluate the integrity of the original dataset of vehicle emission remote monitoring and obtain an integrity score.

[0158] Specifically, the packet loss rate indicator B 10 The specific indicators used to judge data integrity are as follows:

[0159] First, the logic for determining the data packet loss rate is as follows:

[0160] a) Statistical analysis of vehicle online and offline times in vehicle data transmission. The logic for determining offline time is as follows: if a vehicle has no data transmission for 300 consecutive frames and the speed of the last frame is less than 5 km / h, then the vehicle is considered offline.

[0161] b) Based on the online / offline time interval and at a data collection frequency of 1 second per frame, calculate the total number of message frames that the vehicle should send during each online / offline time interval;

[0162] c) Calculate the total number of message frames actually accessed by the vehicle;

[0163] d) Packet loss rate = 1 - (Actual number of access packet frames / Number of packet frames to be sent).

[0164] Secondly, calculate the packet loss rate score C7:

[0165]

[0166] Finally, calculate the integrity score C8:

[0167] C8 = (1 - C7) * 100

[0168] Step b6: Determine the terminal data collection quality evaluation value based on the accuracy score, effectiveness score, timeliness score, compliance score, and completeness score.

[0169] Specifically, the weights for data accuracy, validity, timeliness, compliance, and completeness can be determined based on the proportion of problematic vehicles according to different indicators:

[0170] (1) The weight D1 for data accuracy is:

[0171]

[0172] (2) The weight D2 for data validity is:

[0173]

[0174] (3) The weight D3 for data validity is:

[0175]

[0176] (4) The weight D4 for data validity is:

[0177]

[0178] (5) The weight D5 for data validity is:

[0179]

[0180] Furthermore, the terminal collects the quality evaluation value A4:

[0181] A4=C1*D1+C2*D2+C4*D3+C6*D4+C8*D5

[0182] Step S4024: Determine the long-term offline quality evaluation value based on the original dataset of vehicle emission remote monitoring and the long-term offline verification dataset.

[0183] Specifically, a situation where a vehicle has been offline for more than 30 consecutive days is defined as long-term offline, and a long-term offline vehicle verification model is constructed. Furthermore, this model is used to calculate the long-term offline quality evaluation value A5.

[0184]

[0185] Step S403: Determine multiple quality evaluation weight values ​​based on multiple quality evaluation values.

[0186] Specifically, the quality evaluation values ​​corresponding to each quality evaluation value are as follows:

[0187] (1) The weight W1 for terminal activation quality is:

[0188]

[0189] (2) The weight W2 for data verification quality is:

[0190]

[0191] (3) The weight W3 for data transmission quality is:

[0192]

[0193] (4) The weight W4 for the terminal acquisition quality is:

[0194]

[0195] (5) The weight W5 for long-term offline status is:

[0196]

[0197] Step S404: Based on multiple quality evaluation values ​​and multiple quality evaluation weight values, determine the vehicle network data quality evaluation result. For details, please refer to [link to relevant documentation]. Figure 1 Step S104 of the illustrated embodiment will not be described again here.

[0198] The data quality evaluation method for the Internet of Vehicles (IoV) provided in this embodiment combines the acquired set of terminal activation problem types, data verification problem types, data transmission problem types, terminal collection quality verification index set, and long-term offline verification dataset to achieve a comprehensive, reasonable, and accurate evaluation of data quality. Furthermore, it evaluates terminal collection quality based on 10 indicators, including OBD data out-of-bounds rate, OBD data inefficiency, engine data out-of-bounds rate, engine data inefficiency, SCR downstream NOx data out-of-bounds rate, SCR downstream NOx data inefficiency, terminal time synchronization accuracy, packet loss rate, data collection cycle, and data forwarding latency. This method boasts broad data coverage, high utilization, and a scientifically accurate scoring method. Therefore, by implementing this invention, a comprehensive, reasonable, and accurate evaluation of data quality is achieved, thereby enabling effective vehicle monitoring.

[0199] This embodiment provides a data quality evaluation method for the Internet of Vehicles (IoV), which can be used in electronic devices such as computers, mobile phones, and tablets. Figure 5 This is a flowchart of a data quality evaluation method for the Internet of Vehicles according to an embodiment of the present invention, such as... Figure 5 As shown, the process includes the following steps:

[0200] Step S501: Obtain the raw dataset for remote monitoring of vehicle emissions. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0201] Step S502 involves evaluating the raw dataset for remote vehicle emissions monitoring from five dimensions: terminal activation quality, data verification quality, data transmission quality, terminal acquisition quality, and long-term offline performance, resulting in multiple quality evaluation values. For details, please refer to [link to relevant documentation]. Figure 4 Step S402 of the illustrated embodiment will not be described again here.

[0202] Step S503: Determine multiple quality evaluation weight values ​​based on multiple quality evaluation values. For details, please refer to [link to relevant documentation]. Figure 4 Step S403 of the illustrated embodiment will not be described again here.

[0203] Step S504: Determine the quality evaluation result of the vehicle network data based on multiple quality evaluation values ​​and multiple quality evaluation weight values.

[0204] Specifically, step S504 includes:

[0205] Step S5041: Calculate the data quality score based on multiple quality evaluation values ​​and multiple quality evaluation weight values.

[0206] Specifically, the data quality score S is calculated:

[0207] S=A1*W1+A2*W2+A3*W3+A4*W4+A5*W5

[0208] Step S5042: The quality of the original dataset for remote monitoring of vehicle emissions is divided based on the data quality score to obtain the data quality evaluation result of the Internet of Vehicles.

[0209] Specifically, the quality of the acquired raw dataset for remote monitoring of vehicle emissions can be classified into four levels: unqualified, qualified, good, and excellent, based on the obtained data quality score S.

[0210] The rules for classifying vehicle data quality levels are as follows:

[0211]

[0212] In some optional implementations, after step S503, the method further includes: acquiring a real-time dataset of remote monitoring of vehicle emissions, and optimizing multiple quality evaluation weight values ​​based on the real-time dataset of remote monitoring of vehicle emissions.

[0213] Specifically, as the number of connected vehicles increases, the amount of data they upload will also increase. By including each newly uploaded data in the weight calculation, the weights of the five major indicators of vehicle data upload terminal activation quality, data verification quality, data transmission quality, terminal collection quality, and long-term offline quality, as well as the weights of each sub-indicator of terminal collection quality, will become more and more accurate, and the final score will become more and more objective and reasonable.

[0214] The data quality evaluation method for the Internet of Vehicles (IoV) provided in this embodiment evaluates the acquired raw dataset of remote vehicle emission monitoring from five dimensions: terminal activation quality, data verification quality, data transmission quality, terminal acquisition quality, and long-term offline performance. This broad coverage allows for a more scientific, accurate, comprehensive, and intuitive identification of data quality issues, leading to a reasonable and accurate data quality evaluation and effective vehicle monitoring. Furthermore, as IoV data continues to increase, the weighting values ​​for multiple quality evaluation criteria are continuously optimized, resulting in increasingly accurate weighting values ​​and a more objective and reasonable final score.

[0215] In one example, a data quality evaluation method for the Internet of Vehicles is provided, the specific process of which is as follows: Figure 6 As shown in the diagram, implementing this process enables data quality evaluation across different time dimensions (day / month / year) and spatial dimensions (city / province / country). Furthermore, it can specifically reflect various results of remote monitoring data, helping enterprises identify data quality issues, complete data governance, and upload accurate and effective data. Simultaneously, it assists relevant authorities in understanding the true state of monitoring data, providing technical support for effective data evaluation, data mining analysis and application, and comprehensive vehicle supervision.

[0216] This embodiment also provides a data quality evaluation device for vehicle-to-everything (V2X) networks. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0217] This embodiment provides a data quality evaluation device for the Internet of Vehicles, such as Figure 7 As shown, the device also includes:

[0218] The acquisition module 701 is used to acquire the raw dataset of remote monitoring of vehicle emissions.

[0219] Evaluation module 702 is used to evaluate the raw dataset of vehicle emission remote monitoring from five dimensions: terminal activation quality, data verification quality, data transmission quality, terminal acquisition quality, and long-term offline performance, and obtain multiple quality evaluation values.

[0220] The first determining module 703 is used to determine multiple quality evaluation weight values ​​based on multiple quality evaluation values.

[0221] The second determining module 704 is used to determine the quality evaluation result of the vehicle network data based on multiple quality evaluation values ​​and multiple quality evaluation weight values.

[0222] In some optional implementations, multiple quality evaluation values ​​include terminal activation quality evaluation value, data verification quality evaluation value, data transmission quality evaluation value, terminal acquisition quality evaluation value, and long-term offline quality evaluation value; the evaluation module 702 includes:

[0223] The acquisition submodule is used to acquire the terminal activation problem type set, data verification problem type set, data transmission problem type set, terminal collection quality verification index set, and long-term offline verification dataset.

[0224] The first determination submodule is used to determine the terminal activation quality evaluation value, data verification quality evaluation value, and data transmission quality evaluation value based on the original dataset of vehicle emission remote monitoring, the terminal activation problem type set, the data verification problem type set, and the data transmission problem type set.

[0225] The second determination submodule is used to determine the terminal acquisition quality evaluation value based on the original dataset of vehicle emission remote monitoring and the terminal acquisition quality verification index set.

[0226] The third determination submodule is used to determine the long-term offline quality evaluation value based on the original dataset of vehicle emission remote monitoring and the long-term offline verification dataset.

[0227] In some alternative implementations, the first determining submodule includes:

[0228] The first processing unit is used to obtain the terminal activation quality evaluation value based on the original dataset of vehicle emission remote monitoring and the set of terminal activation problem types, through the terminal activation quality verification model.

[0229] The second processing unit is used to obtain the data verification quality evaluation value based on the original dataset of vehicle emission remote monitoring and the data verification issue type set, through the data verification quality verification model.

[0230] The third processing unit is used to obtain the data transmission quality evaluation value based on the original dataset of vehicle emission remote monitoring and the data transmission problem type set, after processing by the data transmission quality verification model.

[0231] In some optional implementations, the terminal data acquisition quality verification index set includes OBD data out-of-bounds rate index, OBD data inefficiency index, engine data out-of-bounds rate index, engine data inefficiency index, SCR downstream NOx data out-of-bounds rate index, SCR downstream NOx data inefficiency index, terminal time synchronization accuracy index, packet loss rate index, data acquisition cycle index, and data forwarding latency index; the second determination submodule includes:

[0232] The first evaluation unit is used to evaluate the accuracy of the raw dataset of remote vehicle emission monitoring based on the OBD data violation rate index, the engine data violation rate index, and the SCR downstream NOx data violation rate index, and obtain an accuracy score.

[0233] The second evaluation unit is used to evaluate the effectiveness of the raw dataset of remote vehicle emission monitoring based on the inefficiency indicators of OBD data, engine data, and SCR downstream NOx data, and obtain an effectiveness score.

[0234] The third evaluation unit is used to evaluate the timeliness of the raw dataset of remote monitoring of vehicle emissions based on the terminal time synchronization accuracy index and the data forwarding latency index, and obtain a timeliness score.

[0235] The fourth evaluation unit is used to evaluate the compliance of the raw dataset of remote monitoring of vehicle emissions based on the data collection cycle indicators, and obtain a compliance score.

[0236] The fifth evaluation unit is used to evaluate the integrity of the original dataset of remote monitoring of vehicle emissions based on the packet loss rate index, and obtain an integrity score.

[0237] The determination unit is used to determine the terminal data collection quality evaluation value based on the accuracy score, effectiveness score, timeliness score, compliance score, and completeness score.

[0238] In some alternative embodiments, the device further includes:

[0239] The acquisition and optimization module is used to acquire real-time datasets of vehicle emission remote monitoring and optimize multiple quality evaluation weight values ​​based on these datasets.

[0240] In some alternative implementations, the second determining module 704 includes:

[0241] The calculation submodule is used to calculate the data quality score based on multiple quality evaluation values ​​and multiple quality evaluation weight values.

[0242] The sub-module is used to classify the quality of the raw dataset of remote monitoring of vehicle emissions based on the data quality score, so as to obtain the data quality evaluation result of the Internet of Vehicles.

[0243] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0244] In this embodiment, the data quality evaluation device for the Internet of Vehicles is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0245] This invention also provides a computer device having the above-described features. Figure 7 The data quality evaluation device shown is for the Internet of Vehicles.

[0246] Please see Figure 8 , Figure 8 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 8 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 8 Take a processor 10 as an example.

[0247] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0248] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0249] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0250] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0251] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0252] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0253] A portion of this 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 invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist 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 executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0254] Although embodiments of the 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 invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A data quality evaluation method for the Internet of Vehicles, characterized in that, The method includes: Obtain the raw dataset for remote monitoring of vehicle emissions; The raw dataset for remote monitoring of vehicle emissions was evaluated from five dimensions: terminal activation quality, data verification quality, data transmission quality, terminal acquisition quality, and long-term offline performance, resulting in multiple quality evaluation values. Multiple quality evaluation weight values ​​are determined based on the multiple quality evaluation values; Based on the multiple quality evaluation values ​​and the multiple quality evaluation weight values, the quality evaluation result of the vehicle network data is determined; The multiple quality evaluation values ​​include terminal activation quality evaluation value, data verification quality evaluation value, data transmission quality evaluation value, terminal acquisition quality evaluation value, and long-term offline evaluation value. The original dataset for remote vehicle emission monitoring is evaluated from five dimensions: terminal activation quality, data verification quality, data transmission quality, terminal acquisition quality, and long-term offline performance, resulting in multiple quality evaluation values, including: Obtain the terminal activation problem type set, data verification problem type set, data transmission problem type set, terminal collection quality verification index set, and long-term offline verification dataset; Based on the original dataset of vehicle emission remote monitoring, the set of terminal activation problem types, the set of data verification problem types, and the set of data transmission problem types, the terminal activation quality evaluation value, the data verification quality evaluation value, and the data transmission quality evaluation value are determined. Based on the original dataset of the vehicle emission remote monitoring and the set of terminal acquisition quality verification indicators, the terminal acquisition quality evaluation value is determined; The long-term offline evaluation value is determined based on the original dataset of the vehicle emission remote monitoring and the long-term offline verification dataset. Based on the original dataset of vehicle emission remote monitoring, the set of terminal activation problem types, the set of data verification problem types, and the set of data transmission problem types, the terminal activation quality evaluation value, the data verification quality evaluation value, and the data transmission quality evaluation value are determined, including: Based on the original dataset of the vehicle emission remote monitoring and the set of terminal activation problem types, the terminal activation quality evaluation value is obtained after processing by the terminal activation quality verification model. Based on the original dataset of remote monitoring of vehicle emissions and the set of data verification and signature issues, the data verification and signature quality evaluation value is obtained after processing by the data verification and signature quality verification model. Based on the original dataset of the vehicle emission remote monitoring and the data transmission problem type set, the data transmission quality evaluation value is obtained after processing by the data transmission quality verification model. The terminal data collection quality verification index set includes OBD data out-of-bounds rate index, OBD data inefficiency index, engine data out-of-bounds rate index, engine data inefficiency index, SCR downstream NOx data out-of-bounds rate index, SCR downstream NOx data inefficiency index, terminal time synchronization accuracy index, packet loss rate index, data collection cycle index, and data forwarding latency index.

2. The method according to claim 1, characterized in that, After determining multiple quality evaluation weight values ​​based on the multiple quality evaluation values, the method further includes: Obtain a real-time dataset of remote monitoring of vehicle emissions, and optimize the multiple quality evaluation weight values ​​based on the real-time dataset of remote monitoring of vehicle emissions.

3. The method according to claim 1, characterized in that, Based on the multiple quality evaluation values ​​and the multiple quality evaluation weight values, the quality evaluation result of the vehicle network data is determined, including: Based on the multiple quality evaluation values ​​and the multiple quality evaluation weight values, a data quality score is calculated; The quality of the original dataset for remote monitoring of vehicle emissions is classified based on the data quality score, and the data quality evaluation result of the Internet of Vehicles is obtained.

4. An apparatus for implementing the data quality evaluation method for the Internet of Vehicles as described in claim 1, characterized in that, The device includes: The acquisition module is used to acquire the raw dataset for remote monitoring of vehicle emissions. The evaluation module is used to evaluate the raw dataset of the vehicle emission remote monitoring from five dimensions: terminal activation quality, data verification quality, data transmission quality, terminal acquisition quality, and long-term offline performance, and obtain multiple quality evaluation values. The first determining module is used to determine multiple quality evaluation weight values ​​based on the multiple quality evaluation values; The second determining module is used to determine the quality evaluation result of the vehicle network data based on the plurality of quality evaluation values ​​and the plurality of quality evaluation weight values.

5. A computer device, characterized in that, include: A memory and a processor are interconnected, the memory stores computer instructions, and the processor executes the computer instructions to perform the data quality evaluation method for vehicle networking as described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the data quality evaluation method for the Internet of Vehicles as described in any one of claims 1 to 3.

7. A computer program product, characterized in that, It includes computer instructions for causing a computer to execute the data quality evaluation method for the Internet of Vehicles as described in any one of claims 1 to 3.

Citation Information

Patent Citations

  • Diesel vehicle management and control method based on Internet of Vehicles big data

    CN116911660A

  • ZigBee network environment evaluation method, device, system and equipment and storage medium

    CN117042030A