Connected vehicle data quality assessment method, system, device and medium

Abstract

The present invention discloses a method, system, computer equipment and medium for evaluating the quality of data of a connected vehicle, including the steps of: obtaining status data reported by a connected vehicle and perception data of the connected vehicle perceived by a roadside device; obtaining a first score according to the status data and the perception data; obtaining a second score and a third score according to the status data; and determining a final score of the connected vehicle according to the first score, the second score and the third score. The scheme proposed in the present invention can score the accuracy, authenticity and real-time performance of the status data reported by the connected vehicle by matching and comparing the data reported by the connected vehicle itself and the perception data collected by the road test equipment, and scoring from multiple dimensions, which can not only prevent the falsification of connected vehicle data, but also more comprehensively, objectively and reasonably measure the comprehensive quality and overall performance of the connected vehicle in multiple key dimensions.

Description

Technical Field

[0001] The present invention relates to the field of vehicle-road collaboration, and in particular to a method, system, device and medium for evaluating the data quality of a connected vehicle. Background Art

[0002] In recent years, autonomous driving technology and vehicle-to-everything (V2X) technology have made significant progress, which has led to the increasing application of connected vehicles in intelligent transportation systems. Autonomous driving technology aims to enable vehicles to complete driving tasks without excessive intervention from human drivers, covering multiple levels from assisted driving to fully autonomous driving. It relies on various sensors (such as cameras, radars, etc.) and complex algorithms equipped on the vehicle itself to perceive the environment, make decisions and control vehicle driving. Vehicle-to-everything (V2X) technology focuses on the information exchange between vehicles and surrounding infrastructure (such as roadside units, traffic lights, etc.) and other vehicles, and realizes data sharing through wireless communication and other means, thereby improving the efficiency, safety and comfort of the entire transportation system. For example, vehicles can obtain the status of traffic lights at the intersection ahead in advance, reasonably adjust the speed to avoid unnecessary parking and waiting, or receive danger warning information sent by other vehicles, and make avoidance actions in time.

[0003] In order to promote the rapid development of autonomous driving technology and accelerate its application and promotion in actual traffic scenarios, subsidies will be provided for the autonomous driving mileage of corporate vehicles. Then, due to differences in the level of autonomous driving technology among different companies, some companies with strong technical strength can accurately record and report relevant data such as autonomous driving mileage in accordance with regulatory requirements, but some companies with relatively weak technical levels or lack of integrity have adopted improper behavior of falsifying data in order to obtain more subsidy funds, which has led to uneven quality of connected vehicle data. At the same time, in terms of verifying the authenticity of uploaded data, there is a lack of reliable means to verify whether the data reported by the company truthfully reflects the actual operation of the vehicle.

[0004] Currently, the market generally relies on self-reported data from companies, but lacks effective comprehensive quality assessment methods, which further exacerbates the impact of the above-mentioned data quality issues. Summary of the invention

[0005] In view of this, in order to overcome at least one aspect of the above problems, an embodiment of the present invention proposes a method for evaluating the quality of connected vehicle data, comprising the following steps: Acquire status data reported by the connected vehicle and perception data of the connected vehicle using roadside equipment; Obtaining a first score for evaluating accuracy based on the state data and the perception data; Obtaining a second score for evaluating authenticity and a third score for evaluating real-time performance according to the status data; A final score of the connected vehicle is determined based on the first score, the second score, and the third score.

[0006] In some embodiments, obtaining a first score according to the state data and the perception data further includes: Dividing the state data into a plurality of sub-state data and dividing the perception data into a plurality of sub-perception data according to a time window of a preset size; Matching each of the sub-state data with the corresponding sub-perception data; Comparing the matched sub-state data with the corresponding sub-perception data in multiple dimensions to obtain a comparison result; A first score of the status data is determined according to the matching ratio and the comparison result.

[0007] In some embodiments, matching each of the sub-state data with the corresponding sub-perception data further includes: Aligning each frame of data in the sub-state data with each frame of data in the corresponding sub-perception data using a data frame number; Determine the matching ratio based on the number of alignments.

[0008] In some embodiments, using the matched sub-state data and the corresponding sub-perception data to compare multiple dimensions to obtain a comparison result further includes: Determining a first speed, a first acceleration, and a first driving direction of the connected vehicle according to the sub-state data; Determining a second speed, a second acceleration, and a second driving direction of the connected vehicle according to the sub-sensing data; A comparison result is obtained by comparing the first speed and the second speed, the first acceleration and the second acceleration, and the first driving direction and the second driving direction of the networked vehicle.

[0009] In some embodiments, obtaining a second score for evaluating authenticity according to the status data further includes: Determining a driving trajectory of the connected vehicle according to the status data; Determining whether the connected vehicle is traveling on a designated road by combining a map and the driving trajectory; In response to the connected vehicle not traveling on the designated road, marking it as abnormal; A second score of the connected vehicle is determined based on whether it is abnormal.

[0010] In some embodiments, obtaining a third score for evaluating real-time performance according to the status data further includes: Obtaining the reporting time, receiving time and receiving interval of the status data; Determining the delay according to the difference between the reporting time and the receiving time; A third score of the connected vehicle is determined based on the delay and the receiving interval.

[0011] In some embodiments, determining a final score of the connected vehicle according to the first score, the second score, and the third score further includes: The first score, the second score and the third score are multiplied by corresponding weights to obtain a final score of the connected vehicle.

[0012] Based on the same inventive concept, according to another aspect of the present invention, an embodiment of the present invention further provides a connected vehicle data quality assessment system, comprising: An acquisition module configured to acquire status data reported by a connected vehicle and perception data of the connected vehicle perceived by a roadside device; A first calculation module, configured to obtain a first score for evaluating accuracy according to the state data and the perception data; a second calculation module, configured to obtain a second score for evaluating authenticity and a third score for evaluating real-time performance according to the status data; The scoring module is configured to determine a final score of the connected vehicle based on the first score, the second score, and the third score.

[0013] Based on the same inventive concept, according to another aspect of the present invention, an embodiment of the present invention further provides a computer device, including: at least one processor; and A memory, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the program, the steps of any one of the methods for evaluating the quality of connected vehicle data as described above are performed.

[0014] Based on the same inventive concept, according to another aspect of the present invention, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any one of the connected vehicle data quality assessment methods described above are performed.

[0015] The present invention has one of the following beneficial technical effects: the scheme proposed in the present invention matches and compares the data reported by the connected vehicle itself and the perception data collected by the road test equipment, and scores them from multiple dimensions. It can score the accuracy, authenticity and real-time of the status data reported by the connected vehicle, which can not only prevent the falsification of connected vehicle data, but also more comprehensively, objectively and reasonably measure the comprehensive quality and overall performance of the connected vehicle in multiple key dimensions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A schematic diagram of a flow chart of a method for evaluating the quality of connected vehicle data provided by an embodiment of the present invention; Figure 2 A flowchart of a method for evaluating the quality of connected vehicle data provided by an embodiment of the present invention; Figure 3 A schematic diagram of the structure of a connected vehicle data quality assessment system provided by an embodiment of the present invention; Figure 4 A schematic diagram of the structure of a computer device provided by an embodiment of the present invention; Figure 5 A schematic diagram of the structure of a computer-readable storage medium provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the embodiments of the present invention are further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0019] It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are for distinguishing two non-identical entities with the same name or non-identical parameters. It can be seen that "first" and "second" are only for the convenience of expression and should not be understood as limitations on the embodiments of the present invention. The subsequent embodiments will not explain this one by one.

[0020] According to one aspect of the present invention, an embodiment of the present invention provides a method for evaluating the quality of connected vehicle data, such as Figure 1 As shown, it may include the steps of: S1, obtaining status data reported by a connected vehicle and perception data of the connected vehicle using a roadside device; S2, obtaining a first score for evaluating accuracy according to the state data and the perception data; S3, obtaining a second score for evaluating authenticity and a third score for evaluating real-time performance according to the status data; S4: Determine a final score of the connected vehicle according to the first score, the second score, and the third score.

[0021] The solution proposed in the present invention matches and compares the data reported by the connected vehicle itself and the perception data collected by the road test equipment, and scores them from multiple dimensions. It can score the accuracy, authenticity and real-time of the status data reported by the connected vehicle. This can not only prevent the falsification of connected vehicle data, but also measure the comprehensive quality and overall performance of the connected vehicle in multiple key dimensions in a more comprehensive, objective and reasonable manner.

[0022] In some embodiments, in step S1, the status data reported by the connected vehicle and the perception data of the connected vehicle perceived by the roadside equipment are obtained. Specifically, the connected vehicle itself is equipped with various types of sensors, such as speed sensors, position sensors, acceleration sensors, steering wheel angle sensors, etc. These sensors are responsible for collecting status information of different aspects of the vehicle, and these status data include key status indicators during the vehicle's driving process. The roadside equipment may include perception equipment such as cameras, laser radars, millimeter wave radars, blind spot radars, etc., which collect and fuse perception data of the connected vehicle through the perception equipment to achieve tracking of the connected vehicle.

[0023] For example, Figure 2 As shown, the connected vehicle can be configured to broadcast status data at preset time intervals, and the data is received and saved in Kafka through a designated receiving end such as a roadside unit or a cloud server, and then the connected vehicle data is obtained from the Kafka data source in real time through a Flink task. In some embodiments, the roadside device can be selectively deployed on a designated road, so the vehicle status data belonging to the area covered by the roadside device can be filtered out. When there are status data of multiple connected vehicles, the status data can be grouped by vehicle ID.

[0024] In some embodiments, obtaining a first score according to the state data and the perception data further includes: Dividing the state data into a plurality of sub-state data and dividing the perception data into a plurality of sub-perception data according to a time window of a preset size; Matching each of the sub-state data with the corresponding sub-perception data; Comparing the matched sub-state data with the corresponding sub-perception data in multiple dimensions to obtain a comparison result; A first score of the status data is determined according to the matching ratio and the comparison result.

[0025] Specifically, continuous perception data and state data can be segmented according to a set time window. For example, the state data and perception data of a connected vehicle can be segmented into multiple sub-state data and sub-perception data according to a 1-minute window. When segmenting according to a time window, the time point of the first perception data can be used as the starting time, so that the time span of each state data and the corresponding perception data is consistent, and then each sub-state data is matched with the corresponding sub-perception data. In this way, the characteristics and correlation of the data are observed from a local time period, which can better capture the state changes of the vehicle in different time periods and the corresponding relationship with the perception of the roadside equipment, so as to better verify the authenticity and accuracy of the vehicle state data.

[0026] For example, the connected vehicle broadcasts once every preset time period. The status data collected by each sensor during this time period includes but is not limited to information such as location (latitude and longitude), speed, and driving direction. For example, the location information of the vehicle can record the coordinate changes from the starting position to the end position during this time period, and then the status data is segmented according to the 1-minute time window. The roadside equipment continuously senses and collects data from the vehicle. Taking the same 1-minute time window as an example, the perception data collected and fused from different roadside equipment together constitute a sub-perception data set. In this way, the sub-state data and sub-perception data divided by the 1-minute time window can conveniently and orderly perform correlation analysis on the data between the connected vehicle and the roadside equipment. In addition, if the timestamp of the first recorded perception data is displayed as X, then starting from X, a sub-perception data is segmented every 1 minute, and the same status data is also segmented every 1 minute starting from X. In this way, the time span corresponding to each set of sub-state data and the corresponding sub-perception data is 1 minute starting from X, so that they are strictly aligned in time, which is conducive to subsequent accurate matching.

[0027] In some embodiments, matching each of the sub-state data with the corresponding sub-perception data further includes: Aligning each frame of data in the sub-state data with each frame of data in the corresponding sub-perception data using a data frame number; Determine the matching ratio based on the number of alignments.

[0028] Specifically, the connected vehicle broadcasts status data at a certain frequency and forms a sub-status data in each set time window, and this sub-status data often contains multiple frames of data. For example, the vehicle's sensors continuously collect information in the time window, and each collection will obtain a real-time speed of the vehicle. These speed values ​​collected at different times and the corresponding timestamps and other information are encapsulated into a frame of data, which will accumulate to form multiple frames of speed data in a time window. Similarly, when the roadside equipment perceives the connected vehicle, it will also collect multiple frames of data in the corresponding time window to form sub-perception data.

[0029] Since the time span of each sub-state data and the corresponding sub-perception data is consistent, the position of the vehicle at the same time should theoretically be the same, so it can be aligned through the data frame number. The data frame number is usually a number assigned by the corresponding device in a certain order when the data is generated, which is used to identify the order of the data frames. In the same time window, although the sub-state data and sub-perception data come from different devices (vehicle side and roadside device side), because the time span is the same, the data frames generated at the same time or similar time should theoretically correspond to each other. For example, a frame of state data broadcast by a connected vehicle at a certain moment (which records the speed, position and other information of the vehicle at that time) should also be able to find a corresponding frame of vehicle perception data detected at the same time or in a very short time interval in the perception data collected by the roadside device. These data frames with the same or similar time significance can be aligned and matched by their respective frame numbers, and the matching ratio can be obtained.

[0030] For example, within a specific time window, the sub-state data contains a total of 50 frames of data. After matching and aligning operations according to the data frame number, it is found that 40 frames of data can find corresponding frames in the sub-perception data (that is, frames that correspond in time and position, and reflect the vehicle-related conditions at the same time and position). Then the matching ratio is calculated by dividing the number of successfully aligned frames by the total number of frames, which is 80%.

[0031] The matching ratio can intuitively reflect the closeness of the association between the sub-state data and the sub-perception data. The higher the matching ratio, the more consistent the state data reported by the vehicle itself is with the perception data collected by the roadside equipment, and the higher the accuracy and reliability of the data reported by the vehicle itself; conversely, the accuracy and reliability of the data reported by the vehicle itself are relatively lower. In this way, by using the data frame number to align and determine the matching ratio, the data between the connected vehicle and the roadside equipment can be effectively compared quantitatively and the accuracy can be evaluated.

[0032] In some embodiments, using the matched state data and the perception data to compare multiple dimensions to obtain a comparison result further includes: Determining a first speed, a first acceleration, and a first driving direction of the connected vehicle according to the sub-state data; Determining a second speed, a second acceleration, and a second driving direction of the connected vehicle according to the sub-sensing data; A comparison result is obtained by comparing the first speed and the second speed, the first acceleration and the second acceleration, and the first driving direction and the second driving direction of the networked vehicle.

[0033] Specifically, according to the above steps, a matching status data frame and perception data frame can be obtained by comparing the information such as the first speed, the first acceleration and the first driving direction of the connected vehicle included in the status data frame with the information such as the second speed, the second acceleration and the second driving direction of the connected vehicle included in the perception data frame, for example, calculating the difference, and then scoring according to the difference. The lower the difference, the higher the score, thereby obtaining a first score determined according to the comparison result.

[0034] For example, the first speed of the connected vehicle is extracted from the state data frame, the second speed is extracted from the perception data frame, and then the speed difference is calculated. In this way, a corresponding speed difference can be calculated for each set of matching data frames. Since a sub-state data and a sub-perception data contain multiple data frames, multiple speed differences will be obtained. These speed differences constitute a data set that reflects the speed difference. Finally, the standard deviation of the speed difference data set is calculated. The standard deviation is used as the basis for scoring. Different scoring intervals can be set according to the size of the standard deviation. The larger the standard deviation, the lower the score. In this way, the matching quality of the speed of the connected vehicle and the roadside perception data can be analyzed from a statistical perspective, which can provide a reference for the subsequent evaluation of data accuracy.

[0035] It should be noted that if the status data reported by the vehicle does not include information such as speed, the vehicle's speed can be calculated based on the front and rear position points.

[0036] In some embodiments, obtaining the second score and the third score according to the status data further includes: Determining a driving trajectory of the connected vehicle according to the status data; Determining whether the connected vehicle is traveling on a designated road by combining a map and the driving trajectory; In response to the connected vehicle not traveling on the designated road, marking it as abnormal; A second score of the connected vehicle is determined based on whether it is abnormal.

[0037] Specifically, Figure 2As shown in the figure, the status data of the connected vehicle may include key information such as location (latitude and longitude), speed, and driving direction, which can determine the vehicle's driving trajectory. For example, the vehicle broadcasts status data once every preset time period, and each status data contains multiple latitude and longitude coordinates at different times. As time goes by, the location coordinate points at different times are connected in sequence, and the vehicle's driving trajectory can be preliminarily outlined. Then the outlined driving trajectory is superimposed on the tile map, and technical means such as coordinate matching and area judgment are used to determine whether the vehicle is driving on a road area where roadside equipment is deployed or on a real road surface. If it is not driving on a road area where road test equipment is deployed or driving on a real road surface, it is marked as abnormal. At this time, it is considered that the authenticity of the status data reported by the vehicle is low, and the second score is determined based on whether there is an abnormality. For example, the full score (assuming the full score is 100 points) can be set as the situation where the vehicle is always in a road area where roadside equipment is deployed and accurately driving on a real road surface, that is, the entire driving process is not marked as abnormal. Once an abnormal mark appears, points can be deducted based on factors such as the frequency of abnormality. In this way, by determining the second score according to whether an abnormality is marked, the matching situation between the vehicle driving position and the road area can be quantified into an intuitive evaluation score.

[0038] In some embodiments, it also includes: Obtaining the reporting time, receiving time and receiving interval of the status data; Determining the delay according to the difference between the reporting time and the receiving time; A third score of the connected vehicle is determined based on the delay and the receiving interval.

[0039] Specifically, the connected vehicle will send out the status data it has collected at a certain time interval, and this sending time is the reporting time. It is usually recorded by the vehicle-mounted communication system on the vehicle side, and will be transmitted together with the status data or marked with a corresponding timestamp field in the data format. The receiving time refers to the time when the relevant receiving end (such as the roadside unit, cloud server, etc., which is responsible for receiving the status data of the connected vehicle) obtains the vehicle's reporting data. The receiving end will also accurately record the time when the data is received, and this time also carries a corresponding timestamp. The receiving interval refers to the time interval between the receiving end receiving two adjacent sets of connected vehicle status data. Since the vehicle reports data according to a preset time period or specific trigger conditions, the receiving end will receive this data in sequence, and the length of time between two adjacent receptions is the receiving interval. The receiving delay and receiving interval reflect the time it takes for the data to be generated from the vehicle side and sent to the receiving end. Ideally, the delay should be as small as possible to ensure that the receiving end obtains the latest status information of the vehicle. Therefore, the real-time performance of the data reported by the connected vehicle can be scored based on the receiving delay and receiving interval. For example, different scoring intervals can be set according to different delays and intervals, and the third score can be determined according to the scoring interval corresponding to the receiving delay and receiving interval. In this way, the receiving delay and receiving interval can quantitatively reflect the performance of the connected vehicle status data in terms of transmission real-time performance.

[0040] In some embodiments, determining a final score of the connected vehicle according to the first score, the second score, and the third score further includes: The first score, the second score and the third score are multiplied by corresponding weights to obtain a final score of the connected vehicle.

[0041] Specifically, the first score reflects the accuracy of the connected vehicle data, the second score reflects the authenticity of the connected vehicle data, and the third score reflects the real-time performance of the connected vehicle data. The first score, the second score, and the third score are multiplied by the corresponding weights to obtain the final score of the connected vehicle, thereby comprehensively considering the comprehensive performance of the connected vehicle from multiple dimensions. In some embodiments, the three scores multiplied by the weights can be added together to obtain the final score, or they can be mapped to a standard range (e.g., 1-100) after being multiplied by the weights, so as to obtain the score of the connected vehicle more intuitively. When setting the weights of the first score, the second score, and the third score, they can be set according to actual needs. If the focus is on the accuracy of the connected vehicle, the weight of the first score is increased. If the focus is on the authenticity of the connected vehicle, the weight of the second score is increased. If the focus is on the real-time performance of the connected vehicle, the weight of the third score is increased. The final scoring results can be stored in a database for subsequent use, such as for supervision and subsidy issuance.

[0042] The solution proposed in the present invention matches and compares the data reported by the connected vehicle itself and the perception data collected by the road test equipment, and scores them from multiple dimensions. It can score the accuracy, authenticity and real-time of the status data reported by the connected vehicle. This can not only prevent the falsification of connected vehicle data, but also measure the comprehensive quality and overall performance of the connected vehicle in multiple key dimensions in a more comprehensive, objective and reasonable manner.

[0043] Based on the same inventive concept, according to another aspect of the present invention, an embodiment of the present invention further provides a connected vehicle data quality assessment system 400, such as Figure 3 As shown, including: An acquisition module 401 is configured to acquire status data reported by a connected vehicle and perception data of the connected vehicle perceived by a roadside device; A first calculation module 402, configured to obtain a first score for evaluating accuracy according to the state data and the perception data; A second calculation module 403, configured to obtain a second score for evaluating authenticity and a third score for evaluating real-time performance according to the state data; The scoring module 404 is configured to determine a final score of the connected vehicle according to the first score, the second score, and the third score.

[0044] Based on the same inventive concept, according to another aspect of the present invention, Figure 4 As shown, an embodiment of the present invention further provides a computer device 501, including: at least one processor 520; and The memory 510 stores a computer program 511 that can be run on a processor. When the processor 520 executes the program, the steps of any one of the above-mentioned methods for evaluating the quality of connected vehicle data are performed.

[0045] Based on the same inventive concept, according to another aspect of the present invention, Figure 5 As shown, an embodiment of the present invention further provides a computer-readable storage medium 601, which stores a computer program 610. When the computer program 610 is executed by a processor, the steps of any one of the above-mentioned connected vehicle data quality assessment methods are performed.

[0046] Finally, it should be noted that a person skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0047] Furthermore, it should be appreciated that the computer-readable storage medium (eg, memory) herein may be either volatile memory or nonvolatile memory, or may include both volatile memory and nonvolatile memory.

[0048] It will also be appreciated by those skilled in the art that various exemplary logic blocks, modules, circuits and algorithm steps described in conjunction with the disclosure herein can be implemented as electronic hardware, computer software or a combination of the two. In order to clearly illustrate this interchangeability of hardware and software, a general description has been given to the functions of various schematic components, blocks, modules, circuits and steps. Whether this function is implemented as software or hardware depends on specific applications and the design constraints imposed on the entire system. Those skilled in the art can implement the function in various ways for each specific application, but this implementation decision should not be interpreted as causing a departure from the disclosed scope of the embodiments of the present invention.

[0049] The above are exemplary embodiments disclosed in the present invention, but it should be noted that various changes and modifications may be made without departing from the scope disclosed in the embodiments of the present invention as defined in the claims. The functions, steps and / or actions of the method claims according to the disclosed embodiments described herein do not need to be performed in any particular order. In addition, although the elements disclosed in the embodiments of the present invention may be described or required in individual form, they may also be understood as multiple unless explicitly limited to the singular.

[0050] It should be understood that, as used herein, the singular forms "a", "an" are intended to include the plural forms as well, unless the context clearly supports an exception. It should also be understood that, as used herein, "and / or" refers to any and all possible combinations including one or more of the associated listed items.

[0051] The serial numbers of the embodiments disclosed in the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0052] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0053] A person skilled in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the disclosure of the embodiments of the present invention (including the claims) is limited to these examples; under the concept of the embodiments of the present invention, the technical features in the above embodiments or different embodiments can also be combined, and there are many other changes in different aspects of the above embodiments of the present invention, which are not provided in detail for the sake of simplicity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the embodiments of the present invention.

Claims

1. A method for evaluating the quality of connected vehicle data, characterized in that: The following steps are involved: Acquire status data reported by the connected vehicle and perception data of the connected vehicle using roadside equipment; Obtaining a first score for evaluating accuracy based on the state data and the perception data; Obtaining a second score for evaluating authenticity and a third score for evaluating real-time performance according to the status data; A final score of the connected vehicle is determined based on the first score, the second score, and the third score.

2. The method according to claim 1, characterized in that Obtaining a first score for evaluating accuracy according to the state data and the perception data further includes: Dividing the state data into a plurality of sub-state data and dividing the perception data into a plurality of sub-perception data according to a time window of a preset size; Matching each of the sub-state data with the corresponding sub-perception data; Comparing the matched sub-state data with the corresponding sub-perception data in multiple dimensions to obtain a comparison result; A first score of the status data is determined according to the matching ratio and the comparison result.

3. The method according to claim 2, characterized in that Matching each of the sub-state data with the corresponding sub-perception data further includes: Aligning each frame of data in the sub-state data with each frame of data in the corresponding sub-perception data using a data frame number; Determine the matching ratio based on the number of alignments.

4. The method according to claim 2, characterized in that Using the matched sub-state data and the corresponding sub-perception data to compare multiple dimensions to obtain a comparison result further includes: Determining a first speed, a first acceleration, and a first driving direction of the connected vehicle according to the sub-state data; Determining a second speed, a second acceleration, and a second driving direction of the connected vehicle according to the sub-sensing data; A comparison result is obtained by comparing the first speed and the second speed, the first acceleration and the second acceleration, and the first driving direction and the second driving direction of the networked vehicle.

5. The method according to claim 1, characterized in that Obtaining a second score for evaluating authenticity according to the status data further includes: Determining a driving trajectory of the connected vehicle according to the status data; Determining whether the connected vehicle is traveling on a designated road by combining a map and the driving trajectory; In response to the connected vehicle not traveling on the designated road, marking it as abnormal; A second score of the connected vehicle is determined based on whether it is abnormal.

6. The method according to claim 5, characterized in that Obtaining a third score for evaluating real-time performance according to the status data further includes: Obtaining the reporting time, receiving time and receiving interval of the status data; Determining the delay according to the difference between the reporting time and the receiving time; A third score of the connected vehicle is determined based on the delay and the receiving interval.

7. The method according to claim 6, characterized in that Determining a final score of the connected vehicle according to the first score, the second score, and the third score further includes: The first score, the second score and the third score are multiplied by corresponding weights to obtain a final score of the connected vehicle.

8. A connected vehicle data quality assessment system, characterized in that: include: An acquisition module configured to acquire status data reported by a connected vehicle and perception data of the connected vehicle perceived by a roadside device; A first calculation module, configured to obtain a first score for evaluating accuracy according to the state data and the perception data; a second calculation module, configured to obtain a second score for evaluating authenticity and a third score for evaluating real-time performance according to the status data; The scoring module is configured to determine a final score of the connected vehicle based on the first score, the second score, and the third score.

9. A computer device comprising: at least one processor; as well as A memory storing a computer program executable on the processor, wherein the processor executes the steps of the method according to any one of claims 1 to 7 when executing the program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are performed.

Images