CN114461936A

CN114461936A - Map verification method, map verification device, computer equipment and storage medium

Info

Publication number: CN114461936A
Application number: CN202210043920.6A
Authority: CN
Inventors: 冯洁; 江波
Original assignee: Guangzhou Xiaopeng Autopilot Technology Co Ltd
Current assignee: Guangzhou Xiaopeng Autopilot Technology Co Ltd
Priority date: 2022-01-14
Filing date: 2022-01-14
Publication date: 2022-05-10

Abstract

The application discloses a map verification method, a map verification device, computer equipment and a storage medium, wherein the method comprises the steps of sequentially matching each crowdsourcing track in a crowdsourcing data set with a map road network, the crowdsourcing track is driving track data uploaded by a vehicle, and the crowdsourcing data set comprises at least two crowdsourcing tracks; determining a first success rate corresponding to the crowdsourcing data set and a second success rate corresponding to the map road network based on the matching result, wherein the first success rate is used for representing the probability that crowdsourcing tracks in the crowdsourcing data set are successfully matched with the map road network, and the second success rate is used for representing the probability that track segments in the crowdsourcing tracks are successfully matched with road network segments in the map road network; and confirming whether the map network passes the verification or not according to the first power composition and the second power composition. The method can verify the quality of the map network to confirm whether the map network can correctly instruct the vehicle to travel.

Description

Map verification method, map verification device, computer equipment and storage medium

Technical Field

The present application relates to the field of maps, and in particular, to a map verification method, apparatus, computer device, and storage medium.

Background

In the development trend of vehicle intellectualization, more and more automobiles can acquire a driving track of a vehicle based on a vehicle-mounted sensor, and further draw a map network of an environment where the vehicle is located, so that operations such as navigation and Positioning of the vehicle are realized without passing through a Global Positioning System (GPS) signal. However, the map network obtained based on the vehicle travel track may have errors, and the quality of the map network is not stable.

Disclosure of Invention

In view of the above problems, the present application proposes a map verification method, apparatus, computer device and storage medium to solve the problem of unstable quality of a map acquired by a vehicle.

In a first aspect, an embodiment of the present application provides a map verification method, where the method includes: sequentially matching each crowdsourcing track in a crowdsourcing data set with a map road network, wherein the crowdsourcing track is driving track data uploaded by a vehicle, and the crowdsourcing data set comprises at least two crowdsourcing tracks; determining a first power component corresponding to the crowdsourcing data set and a second power component corresponding to the map road network based on the matching result, wherein the first power component is used for representing the probability that crowdsourcing tracks in the crowdsourcing data set are successfully matched with the map road network, and the second power component is used for representing the probability that track segments in the crowdsourcing tracks are successfully matched with road network segments in the map road network; and confirming whether the map road network passes the verification or not according to the first power consumption and the second power consumption.

In a second aspect, an embodiment of the present application provides a map verification apparatus, including: the device comprises a track matching module, a success rate determining module and a map judging module. The track matching module is used for sequentially matching each crowdsourcing track in a crowdsourcing data set with a map road network, the crowdsourcing track is driving track data uploaded by a vehicle, and the crowdsourcing data set comprises at least two crowdsourcing tracks; the success rate determination module is used for determining a first success rate corresponding to the crowdsourcing data set and a second success rate corresponding to the map road network based on the matching result, wherein the first success rate is used for representing the probability that crowdsourcing tracks in the crowdsourcing data set are successfully matched with the map road network, and the second success rate is used for representing the probability that track segments in the crowdsourcing tracks are successfully matched with road network segments in the map road network; the map judging module is used for confirming whether the map road network passes the verification or not according to the first power forming rate and the second power forming rate.

In a third aspect, an embodiment of the present application provides a computer device, including: one or more processors; a memory; one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the map validation method provided by the first aspect above.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where a program code is stored in the computer-readable storage medium, and the program code may be invoked by a processor to execute the map verification method provided in the first aspect.

According to the scheme provided by the application, each crowdsourcing track in a crowdsourcing data set is sequentially matched with a map road network, the crowdsourcing tracks are driving track data uploaded by vehicles, and the crowdsourcing data set comprises at least two crowdsourcing tracks; determining a first success rate corresponding to the crowdsourcing data set and a second success rate corresponding to the map road network based on the matching result, wherein the first success rate is used for representing the probability that crowdsourcing tracks in the crowdsourcing data set are successfully matched with the map road network, and the second success rate is used for representing the probability that track segments in the crowdsourcing tracks are successfully matched with road network segments in the map road network; and confirming whether the map network passes the verification or not according to the first power cost and the second power cost. Therefore, the quality of the map road network can be verified according to the probability of successful matching between the crowdsourcing track and the map road network and the probability of successful matching between the track segment in the crowdsourcing track and the road network segment in the map road network, so that the accurate verification of the quality of the map road network is realized, and a basis is provided for the application of the map road network.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 illustrates a verification system related to a map verification method provided by an embodiment of the present application.

Fig. 2 is a flowchart illustrating a map verification method according to an embodiment of the present application.

Fig. 3 is a flowchart illustrating a map verification method according to another embodiment of the present application.

Fig. 4 shows a detailed flowchart of step S270 in another embodiment of the present application.

Fig. 5 is a flowchart illustrating a map verification method according to still another embodiment of the present application.

Fig. 6 is a flowchart illustrating a map verification method according to another embodiment of the present application.

Fig. 7 is a flowchart illustrating a map verification method according to another embodiment of the present application.

Fig. 8 shows a detailed flowchart of step S540 in another embodiment of the present application.

Fig. 9 is a block diagram illustrating a structure of a map verification apparatus according to an embodiment of the present application.

Fig. 10 shows a block diagram of a computer device provided in an embodiment of the present application.

Fig. 11 shows a block diagram of a computer-readable storage medium provided in an embodiment of the present application.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

Currently, the automobile is rapidly developed in an intelligent manner, and the use scenes and functions of the automobile are various, but most of the automobile is related to the extended application of the automobile in the road driving process, and some problems still exist in relation to the realization of intelligent driving of the automobile in a parking lot which is a low-speed scene with a complex environment. If the parking lot is mostly in underground environment, GPS signals are weak, vehicle positioning capacity is poor, and navigation in the parking lot is not easy to achieve. And it is difficult to obtain a navigation map of the parking lot, so that the automatic driving of the vehicle in the parking lot lacks the positioning and map support.

In some technical schemes, the vehicles obtain different driving track data of a plurality of vehicles in the same parking lot, and the track data are spliced and fused to form a complete parking lot map road network, so that the vehicles can not be guided by navigation signals, and a more accurate parking lot map road network can be obtained. However, the quality of the map network generated at this time is not stable, and depends greatly on the traveling trajectory of the vehicle, and there may be some wrong positions. When the map network is directly put into use, operations such as navigation of the vehicle based on the map network pose a certain threat to the safety of the vehicle and the user.

In view of the above problems, the inventor proposes a map verification method, a map verification apparatus, a computer device, and a storage medium provided in the embodiments of the present application, so as to implement verification of map quality. The specific map verification method is described in detail in the following embodiments.

The following describes a hardware environment of the map verification method provided in the embodiment of the present application.

Referring to fig. 1, it is shown that a hardware environment related to a map verification method provided by the embodiment of the present application includes a verification system 10, where the verification system 10 includes a plurality of vehicles 300 (only 1 is shown in fig. 1), a user terminal 400, and a computer device 100, and the vehicles 300 and the computer device 100 may be wirelessly connected. The vehicle 300 may include a sensor for acquiring the driving trace data of the vehicle, and the vehicle 300 may upload the driving trace data to the computer device 100, so that the computer device 100 updates the map network according to the driving trace data uploaded by the vehicle 300. Of course, the user terminal 400 and the display terminal in the vehicle 300 may receive the map network transmitted by the computer device 100 to display the map network. The computer device 100 may further output a prompt message to the user terminal 400 or a display terminal in the vehicle 300 to prompt the user to perform a manual verification when the computer device 100 cannot determine whether the map network is verified.

The map verification method provided by the embodiment of the present application will be described in detail below with reference to the accompanying drawings.

Referring to fig. 2, fig. 2 is a schematic flowchart illustrating a map verification method according to an embodiment of the present application. As will be explained in detail with respect to the flow shown in fig. 2, the map verification method may specifically include the following steps:

step S110: each crowdsourcing track in the crowdsourcing data set is matched with a map road network in sequence, the crowdsourcing track is running track data uploaded by vehicles, and the crowdsourcing data set comprises at least two crowdsourcing tracks.

In the embodiment of the application, the map network may be a map which is acquired by a computer device and used for displaying the traffic road communication condition in a specific environment. Before the map network is really put into use, the computer equipment needs to verify the reliability of the map network. Therefore, the computer device can match a plurality of crowdsourcing tracks of the vehicle in the environment where the map network is located with the map network to be verified so as to determine whether the map network can be verified according to the matching result. The crowd-sourced trajectory is running trajectory data of a vehicle in an environment where a map network is located, and comprises attitude data information such as speed, direction and angle of the vehicle at any moment, and information such as located coordinates. In order to ensure the accuracy of map network verification, the crowdsourcing data set comprises at least two crowdsourcing tracks.

In some embodiments, the crowdsourcing trajectories in the crowdsourcing data set may be different trajectories generated by the computer device based on the vehicle in the environment where the map road network is located at different times, or different trajectories generated by the computer device in the same environment through different vehicles.

In some embodiments, the computer device matches the crowd-sourced trajectory with the map network, may match road sign elements in the crowd-sourced trajectory with the map network in sequence from a starting position of the crowd-sourced trajectory, i.e., an entrance, and may also label a matching result.

Step S120: determining a first power consumption corresponding to the crowdsourcing data set and a second power consumption corresponding to the map road network based on the matching result, wherein the first power consumption is used for representing the probability that crowdsourcing tracks in the crowdsourcing data set are successfully matched with the map road network, and the second power consumption is used for representing the probability that track segments in the crowdsourcing tracks are successfully matched with road network segments in the map road network.

In this embodiment, after matching the crowdsourcing trajectory with the map road network, the computer device may determine, according to the matching result, a probability that a crowdsourcing trajectory in the crowdsourcing data set is successfully matched with the map road network, that is, a first success rate, and a probability that a trajectory segment in the crowdsourcing trajectory is successfully matched with a road network segment in the map road network, that is, a second success rate. Specifically, the first success rate corresponding to the crowdsourcing data set may represent the probability of successful matching of the crowdsourcing trajectory in the crowdsourcing data set and the map road network, and the computer device may determine the quality of the crowdsourcing trajectory in the crowdsourcing data set based on the first success rate, and further have basic judgment on the quality of the map road network matched with the crowdsourcing trajectory; the second power component corresponding to the map network can represent the probability of successful matching of each segment of the map network with the track segment, and the computer device can judge the quality of the local segment of the map network based on the second power component. Therefore, the computer device may determine the quality of the crowdsourcing trajectory in the crowdsourcing data set based on the first contribution power, and further determine the quality of the map network matched therewith based on the quality of the crowdsourcing trajectory; the computer device can also judge the quality of each road network segment in the map road network based on the second component power, and further confirm the quality of the whole map road network.

Step S130: and confirming whether the map road network passes the verification or not according to the first power consumption and the second power consumption.

In this embodiment of the application, the computer device may determine, according to a preset standard, whether the map road network may pass the verification based on the magnitudes of the first power consumption corresponding to the crowdsourcing data set and the second power consumption corresponding to the map road network, that is, if both the first power consumption and the second power consumption satisfy the preset standard, the computer device may confirm that the map road network passes the verification. The preset criteria for confirming whether the map road network passes the verification may be different for different map road networks or different systems, but it can be understood that the higher the preset criteria is, the higher the quality of the verified map road network is, and the less error is caused in the actions of navigation, positioning and the like of the vehicle based on the map road network.

According to the map verification method provided by the embodiment of the application, each crowdsourcing track in the crowdsourcing data set is sequentially matched with a map road network, first success rate corresponding to the crowdsourcing data set and second success rate corresponding to the map road network are determined based on a matching result, and whether the map road network passes verification or not is determined according to the first success rate and the second success rate. The quality of the map network is verified, and whether the map network can correctly instruct the vehicle to travel is confirmed.

Referring to fig. 3, fig. 3 is a schematic flow chart illustrating a map verification method according to another embodiment of the present application. As will be described in detail with respect to the flow shown in fig. 3, the map verification method may specifically include the following steps:

step S210: each crowdsourcing track in the crowdsourcing data set is matched with a map road network in sequence, the crowdsourcing track is running track data uploaded by vehicles, and the crowdsourcing data set comprises at least two crowdsourcing tracks.

In the embodiment of the present application, step S210 may refer to the contents of other embodiments, which are not described herein again.

Step S220: and acquiring the quantity of the crowdsourcing tracks successfully matched with the map network as a first quantity.

In the embodiment of the application, after the crowdsourcing trajectory is matched with the map road network, the computer device can obtain the number of crowdsourcing trajectories matched with the map road network in the crowdsourcing data set, and the number is used as the first number. Because the crowdsourcing data set includes a plurality of crowdsourcing tracks, the computer device can determine, based on the first quantity, a probability that a track matching corresponding to the crowdsourcing data set is successful. It can be understood that the computer device confirms the crowdsourcing trajectory and the map road network as matching, which may be that the crowdsourcing trajectory and the map road network are completely matched, that is, information such as each road sign element included in the crowdsourcing trajectory is completely overlapped with a road sign element in the map road network; or the matching number of the road sign elements between the crowdsourcing track and the map road network is more than the preset number. The first number of confirmations may have different criteria for different map networks or different applications, wherein the roadmap elements used to confirm a match may also have different selection criteria.

Step S230: obtaining a number of crowdsourcing tracks in the crowdsourcing data set as a second number.

In an embodiment of the present application, the computer device may use the number of crowdsourcing traces in the crowdsourcing data set as the second number. One crowdsourcing trajectory can be a driving trajectory of a vehicle from an entrance to any preset point, namely a driving trajectory of the vehicle from the entrance of a parking lot to any parking space therebetween, and can also be a driving trajectory of the vehicle from the entrance to the exit. The crowd-sourced data set may include different driving trajectory data of a plurality of vehicles in an environment where the same map network is located. It can be understood that the greater the number of crowdsourcing tracks included in the crowdsourcing data set, the more accurate the verification result of the map road network is verified based on the crowdsourcing tracks.

Step S240: taking the ratio of the first quantity to the second quantity as the first power generation rate.

In this embodiment, the computer device may use a ratio of the number of crowdsourcing tracks in the crowdsourcing data set that match the map network to the number of crowdsourcing tracks included in the crowdsourcing data set as the first success rate corresponding to the crowdsourcing data set. The first success rate may characterize a probability that the crowd-sourced trajectory in the crowd-sourced data set is successfully matched with the map network. The computer device can have a comprehensive judgment on the quality of the crowdsourcing track in the crowdsourcing data set based on the first success rate, and further confirm the quality of the map road network. It can be understood that if the first success rate corresponding to the crowdsourcing data set is higher, most crowdsourcing tracks can be matched with the map road network, which indicates that the quality of the map road network is better, otherwise, the quality is poorer.

Step S250: dividing each crowdsourcing track in the crowdsourcing data set into a plurality of track segments according to a preset standard, dividing the map road network into a plurality of road network segments according to the same preset standard, wherein one or more track segments are corresponding to the road network segments.

In this embodiment of the application, in order to facilitate matching of the crowdsourcing trajectory with the map road network and more accurately judge the local map road network, the computer device may segment each crowdsourcing trajectory in the crowdsourcing data set according to a preset standard, and segment the map road network according to the same preset standard, so as to judge the local quality of the map road network based on each segment. The preset standard can be the same fixed length, namely the crowdsourcing track and the map road network are divided according to the fixed length; or the segmentation can be performed based on adjacent road sign elements, that is, the crowd-sourced tracks and the map network are segmented at the same road sign element, at this time, the obtained segments can be different in length, but road sign elements which can be used for positioning are arranged at two ends of each segment.

Step S260: and matching each track segment with the road network segment in sequence.

In this embodiment, after segmenting the crowd-sourced trajectory and the map road network, the computer device may sequentially match all trajectory segments included in each crowd-sourced trajectory in the crowd-sourced data set with each road network segment in the map road network, so as to determine a second power generation rate corresponding to the road network segment according to the number of trajectory segments matched with the road network segment.

Specifically, since the crowd-sourced trajectory and the map network are divided according to the same preset criteria, if the crowd-sourced trajectory matches the map network, each trajectory segment included in the crowd-sourced trajectory should also coincide with each road network segment in the map network, that is, the matching result of the trajectory segment should be successful. In some cases, even if the crowd-sourced trajectory does not completely match the map network, then the crowd-sourced trajectory should coincide with the road network segments included in the matching portion of the map network, and the matching results are failed for the track segments included in the non-matching portion.

Step S270: and obtaining second power according to the matching result of the track segment and the road network segment.

In the embodiment of the present application, the computer device may not only determine whether each track segment matches a road network segment, but also obtain the number of track segments corresponding to the road network segment and matching therewith. Since the crowdsourcing data set includes not less than two crowdsourcing tracks, there may be more track segments corresponding to any road network segment. The computer device can match the plurality of track segments with the road network segment, and obtain a successful matching rate corresponding to the road network segment according to a matching result, namely the number of track segments successfully matched with the track segments in each track segment corresponding to the road network segment, so as to confirm the successful matching rate of the whole map network through each road network segment, namely the second power generation rate corresponding to the map network.

In some embodiments, the process of obtaining the first power cost corresponding to the crowdsourcing data set and the process of obtaining the second power cost corresponding to the map road network by the computer device may be performed simultaneously or sequentially, which is not limited herein.

In some embodiments, as shown in fig. 4, the process of determining the second power based on the matching result in step S270 may include the following steps:

step S271: and acquiring the number of the track segments matched with the road network segments as a third number.

In this embodiment, after matching each track segment with the road network segment, the computer device may obtain the number of track segments matched with the road network segment, and use the number as a third number, where the third number may be at least zero and at most the total number of track segments, so as to determine the quality of the road network segment based on the third number.

In some embodiments, the method for the computer device to confirm the matching of the trajectory segment and the road network segment may be based on the same road sign elements between the trajectory segment and the road network segment. The computer equipment can also output the matching relation to a display terminal after confirming that the track segment is matched with the road network segment, and the matching relation is used for prompting a user to manually check the matching relation.

Step S272: and acquiring the number of track segments corresponding to the road network segments as a fourth number, wherein the fourth number is greater than or equal to the third number.

In this embodiment of the present application, as can be seen from the analysis of the foregoing embodiment, a plurality of track segments may correspond to a road network segment, where a matching result of matching the track segments with the road network segment may be successful or failed, and the computer device may use the number of successful track segments as a third number and use the total number of track segments corresponding to the road network segment as a fourth number.

It is understood that, since the matching result of any track segment and road network segment may be success or failure, the value of the track segment with successful matching should be less than or equal to the total amount of the track segments corresponding to the road network segment, i.e. the third amount should be less than or equal to the fourth amount. Generally, if each crowdsourcing trajectory passes through the road network segment only once, the number of crowdsourcing trajectories included in the crowdsourcing data set is the number of trajectory segments corresponding to the road network segment, i.e. the fourth number.

Step S273: and taking the ratio of the third number to the fourth number as the third power corresponding to the map segment.

In this embodiment, after dividing the map road network into a plurality of road network segments according to a preset standard, for any one of the road network segments, a ratio between a third number, which is the number of track segments matched with the road network segment, and a fourth number, which is the number of track segments corresponding to the road network segment, may be used as a matching success rate, which is a third success rate, corresponding to the road network segment. The third success rate is used to represent the probability of successful matching of the track segment corresponding to a certain road network segment, and may reflect the quality of the road network segment to a certain extent, that is, if the third success rate corresponding to a certain road network segment is higher, the quality of the road network segment is higher.

Step S274: and determining a second power forming rate corresponding to the map road network based on the third power forming rate corresponding to each map segment.

In this embodiment, after obtaining the third success rates corresponding to the road network segments, that is, the probability of successful matching between each trajectory segment and the road network segment, the computer device may determine the success rate of matching of the whole map network, that is, the second success rate, based on the third success rates corresponding to the road network segments. It can be understood that the magnitude of the second power component corresponding to the map road network can reflect the overall quality of the map road network to a certain extent, that is, the higher the matching success rate of the map road network is, the larger the second power component is, the better the quality of the map road network is, and the more accurate the vehicle is in navigation or positioning and other operations based on the map road network.

In some embodiments, the computer device may obtain the second power rating in a different manner for different map networks. If the average of the third power generation corresponding to each road network segment is used as the second power generation of the whole map road network; for another example, the median of the third power generation rates corresponding to the respective road network segments is used as the second power generation rate of the entire map road network.

Step S280: and confirming whether the map road network passes the verification or not according to the first power consumption and the second power consumption.

In the embodiment of the present application, step S280 may refer to the contents of other embodiments, which are not described herein again.

According to the map verification method provided by the embodiment of the application, the ratio of the number of crowdsourcing tracks matched with the map road network to the number of crowdsourcing tracks in a crowdsourcing data set is used as first success power, the ratio of the number of track segments matched with the road network segments to the number of track segments corresponding to the road network segments is used as third success power, and then second success power corresponding to the map road network is obtained.

Referring to fig. 5, fig. 5 is a schematic flowchart illustrating a map verification method according to still another embodiment of the present application. As will be described in detail with respect to the flow shown in fig. 5, the map verification method may specifically include the following steps:

step S310: and traversing a path from an entrance of the map road network to any road sign element in the map road network to determine whether the map road network has connectivity.

In the embodiment of the application, the computer device verifies the quality of the map road network, and is used for verifying whether the vehicle can smoothly navigate to a preset position through the map road network, whether a reasonable departure route can be planned based on the map road network, whether the position of the vehicle can be located based on the map road network, and the like. Therefore, a qualified map road network not only needs to have a certain threshold matching success rate with the crowdsourcing trajectory, but also needs to confirm that the road sign elements used for operations such as positioning in the map road network are complete enough, so that the vehicle can complete operations such as navigation and positioning based on the map road network, and whether the position relationship between the road sign elements of the map road network is correct, and whether the traveling route of the vehicle can be planned smoothly. Therefore, in the embodiment of the present application, the computer device may confirm whether each road in the map road network has connectivity by traversing the road between the entrance and any position in the map road network, wherein the computer device may confirm whether the map road network has connectivity by each road sign element in the map road network, that is, confirm the road where the road sign element is located by any road sign element, and further plan the road between the entrance and the road.

Step S320: and acquiring a shortest path from an entrance of the map road network to any road sign element in the map road network, and determining whether the map road network has continuity.

In the embodiment of the application, the computer device may further verify whether the travel route of the vehicle can be navigated based on the map road network by obtaining a shortest path between the map road network and any road from the entrance. The computer device can determine the road where any road sign element in the map road network is located as a target road, and determine the shortest path from the entrance to the target road in the map road network.

In some embodiments, after acquiring any shortest path in the map network, the computer device may output the shortest path to the user terminal for display, so that the user verifies whether the path is the shortest path, and at the same time, the computer device may also acquire path information fed back by the user through the display terminal, so as to correct the shortest path.

Step S330: each crowdsourcing track in the crowdsourcing data set is matched with a map road network in sequence, the crowdsourcing track is running track data uploaded by vehicles, and the crowdsourcing data set comprises at least two crowdsourcing tracks.

Step S340: determining a first power consumption corresponding to the crowdsourcing data set and a second power consumption corresponding to the map road network based on the matching result, wherein the first power consumption is used for representing the probability that crowdsourcing tracks in the crowdsourcing data set are successfully matched with the map road network, and the second power consumption is used for representing the probability that track segments in the crowdsourcing tracks are successfully matched with road network segments in the map road network.

Step S350: and confirming whether the map road network passes the verification or not according to the first power forming rate and the second power forming rate.

In the embodiment of the present application, reference may be made to the contents of the other embodiments in steps S330 to S350, which are not described herein again.

According to the map verification method provided by the embodiment of the application, the quality of the map road network is verified from the other side by traversing each passage in the map road network and the shortest path to each passage, so that the quality of the map road network is verified, the verified map road network is ensured to have enough abundant road sign elements, and the road sign elements have correct logical relations, so that the map road network can support the planning of the driving route of a vehicle and the positioning and displaying of the vehicle.

Referring to fig. 6, fig. 6 is a flowchart illustrating a map verification method according to another embodiment of the present application. As will be described in detail with respect to the flow shown in fig. 6, the map verification method may specifically include the following steps:

step S410: each crowdsourcing track in the crowdsourcing data set is matched with a map road network in sequence, the crowdsourcing track is running track data uploaded by vehicles, and the crowdsourcing data set comprises at least two crowdsourcing tracks.

Step S420: determining a first power consumption corresponding to the crowdsourcing data set and a second power consumption corresponding to the map road network based on the matching result, wherein the first power consumption is used for representing the probability that crowdsourcing tracks in the crowdsourcing data set are successfully matched with the map road network, and the second power consumption is used for representing the probability that track segments in the crowdsourcing tracks are successfully matched with road network segments in the map road network.

Step S430: and marking the road network segment of the map road network according to the first power forming rate and the second power forming rate, wherein the mark is used for representing the matching degree of the crowdsourcing track and the map road network.

In this embodiment of the application, after the computer device obtains the first power contribution and the second power contribution, the computer device may mark the road network segment based on a crowdsourcing trajectory successfully matched in the first power contribution and a matching success probability corresponding to each trajectory segment in the second power contribution, so as to characterize a matching degree between the crowdsourcing trajectory and the map road network. Specifically, after obtaining the number of the track segments corresponding to each road network segment and capable of being matched with the road network segment, the computer device may mark the road network segment differently according to the ratio of the number to a fixed value, where the ratio data corresponding to each road network segment may reflect the probability that the track segment corresponding to the road network segment is successfully matched, and after performing the above operation on each road network segment, the matching degree between the crowdsourced track and the whole map road network may be obtained. It can be understood that when the map road network is segmented, there may be different dividing criteria for the road network segments, for example, the map road network may be segmented based on adjacent road sign elements, or the map road network may be segmented according to the same distance, and the specific dividing criteria for the road network segments are not limited herein.

In some embodiments, step S430 may further include:

and according to the matching degree, determining road network segments needing to be repaired, and repairing the road network segments.

In the embodiment of the present application, after confirming the matching degree between the crowdsourcing trajectory and the map network, the computer device may repair the road network segment whose matching degree does not reach the preset range based on the matching degree corresponding to each road network segment, so as to improve the matching success rate of the whole map network, that is, improve the quality of the map network.

In some embodiments, the patching of the road network segments by the computer device may be based on crowd-sourced trajectories through the road network segments. That is, after the computer device confirms the road network segments needing to be patched, all crowdsourced tracks passing through the road network segments are acquired in the crowdsourced data set, and the road network segments are patched based on the corresponding track segments in the crowdsourced tracks, and the road network segments can be updated into the map road network after patching by the computer device.

In some embodiments, the road network segment needs to be repaired may be due to a low number of crowdsourced tracks passing through the road network segment, which results in a low successful matching rate for the road network segment. The computer device can guide a user to drive the vehicle to pass through the road network segment based on the vehicle front-end interactive interface, and the road network segment can be repaired by acquiring the crowdsourcing track passing through the road network segment.

Step S440: and confirming whether the map road network passes the verification or not according to the first power consumption and the second power consumption.

In the embodiment of the present application, step S410, step S420, and step S440 may refer to the contents of other embodiments, and are not described herein again.

According to the map verification method provided by the embodiment of the application, after the computer equipment obtains the first success rate corresponding to the crowdsourcing track and the second success rate corresponding to the map road network, each road network segment in the map road network can be marked based on the matching degree of the crowdsourcing track and the map road network, and the road network segment can be repaired based on the matching degree, so that the quality of the map road network can be verified, the construction difficulty of the map road network can be reduced, and the crowdsourcing track data and the map road network data are fully utilized.

Referring to fig. 7, fig. 7 is a flowchart illustrating a map verification method according to another embodiment of the present application. As will be described in detail with respect to the flow shown in fig. 7, the map verification method may specifically include the following steps:

step S510: each crowdsourcing track in the crowdsourcing data set is matched with a map road network in sequence, the crowdsourcing track is running track data uploaded by vehicles, and the crowdsourcing data set comprises at least two crowdsourcing tracks.

Step S520: determining a first power consumption corresponding to the crowdsourcing data set and a second power consumption corresponding to the map road network based on the matching result, wherein the first power consumption is used for representing the probability that crowdsourcing tracks in the crowdsourcing data set are successfully matched with the map road network, and the second power consumption is used for representing the probability that track segments in the crowdsourcing tracks are successfully matched with road network segments in the map road network.

In the embodiment of the present application, both step S510 and step S520 may refer to the contents of other embodiments, and are not described herein again.

Step S530: and if the first power consumption is larger than a first threshold value and the second power consumption is larger than a second threshold value, confirming that the map road network passes the verification.

In this embodiment of the application, after obtaining the first power consumption corresponding to the crowdsourcing data set and the second power consumption corresponding to the map road network, the computer device may verify the quality of the map road network according to the magnitudes of the first power consumption and the second power consumption. It can be understood that the first success rate is used for representing the probability of successful matching of the crowdsourcing trajectory and the map network, so that the higher the first success rate is, the better the quality of the crowdsourcing trajectory in the crowdsourcing data set is, and the better the quality of the map network with the crowdsourcing data set matching success rate greater than the first threshold is; the second power generation is used for representing the probability of successful matching between the track segment in the crowd-sourced track and the road network segment in the map road network, and if the second power generation is higher, the probability of matching between the map road network and the crowd-sourced track is higher, and the quality of the map road network is also higher. Accordingly, the computer device may confirm that the map network is verified when the first power cost is greater than the first threshold and the second power cost is greater than the second threshold.

Step S540: and if the first power consumption is not greater than a first threshold value or the second power consumption is not greater than a second threshold value, confirming that the map road network is not verified.

In this embodiment of the application, based on the above analysis, if the first power obtained by the computer device is not greater than the first threshold, or the second power is not greater than the second threshold, it may be determined that the probability that the crowd-sourced trajectory in the crowd-sourced data set is successfully matched with the map network is low, or the matching probability that the map network has the road network segment and the trajectory segment is low, and at this time, in order to ensure the overall quality of the map network, the map network may be determined as failed in verification.

In some embodiments, as shown in fig. 8, step S540 may further include the following steps:

step S541: and if the first power consumption is less than or equal to the first threshold value, deleting the map road network.

In the embodiment of the present application, when it is determined that the map network is not verified, if the first success rate is less than or equal to the first threshold, it may be determined that the degree of matching between the crowdsourcing trajectory in the crowdsourcing data set and the map network is low, which also means that the map network cannot be repaired by the crowdsourcing trajectory in the crowdsourcing data set, and at this time, the map network does not have more reference values, so the computer device may delete the map network.

Step S542: and if the first power generation rate is greater than the first threshold value and the second power generation rate is less than or equal to a second threshold value, repairing the map road network.

In the embodiment of the application, after the computer device confirms that the map network does not pass the verification, part of the map network which does not pass the verification can be repaired to pass the verification. If the second power generation rate corresponding to the map road network is less than or equal to the second threshold value, and the first power generation rate is greater than the first threshold value, it indicates that although the matching probability of the road network segment and the track segment of the map road network is low, the probability that the crowdsourcing track in the crowdsourcing data set is successfully matched with the map road network meets the first threshold value, and at this time, the computer device may patch part of the road network segment in the map road network based on the crowdsourcing track in the crowdsourcing data set.

According to the map verification method provided by the embodiment of the application, the computer equipment confirms the standard of the map road network passing the verification and repairs part of the map road network not passing the verification based on the first power consumption corresponding to the crowdsourcing data set and the second power consumption corresponding to the map road network. The quality of the map network is verified, the cost for constructing the map network is reduced, crowdsourcing tracks can be fully utilized, and parts of the map network can be repaired.

Referring to fig. 9, which shows a block diagram of a map verification apparatus 200 according to an embodiment of the present application, the map verification apparatus 200 includes: a trajectory matching module 210, a success rate determination module 220, and a map determination module 230. The track matching module 210 is configured to match each crowdsourcing track in a crowdsourcing data set with a map road network in sequence, where the crowdsourcing track is driving track data uploaded by a vehicle, and the crowdsourcing data set includes at least two crowdsourcing tracks; the success rate determining module 220 is configured to determine, based on the matching result, a first success rate corresponding to the crowdsourcing data set and a second success rate corresponding to the map road network, where the first success rate is used to represent a probability that a crowdsourcing trajectory in the crowdsourcing data set is successfully matched with the map road network, and the second success rate is used to represent a probability that a trajectory segment in the crowdsourcing trajectory is successfully matched with a road network segment in the map road network; the map determination module 230 is configured to determine whether the map network passes the verification according to the first power consumption and the second power consumption.

As a possible implementation manner, the success rate determining module 220 may be configured to obtain the number of crowdsourcing tracks successfully matched with the map network as a first number; acquiring the number of crowdsourcing tracks in the crowdsourcing data set as a second number; and taking the ratio of the first quantity to the second quantity as the first power forming rate.

As one possible implementation, the success rate determination module 220 may include a trajectory segmentation unit, a trajectory matching unit, and a result determination unit. The track segmentation unit is used for segmenting each crowdsourcing track in the crowdsourcing data set into a plurality of track segments according to a preset standard, segmenting a map road network into a plurality of road network segments according to the same preset standard, wherein the road network segments correspond to one or more track segments; the track matching unit is used for matching each track segment with the road network segment in sequence; and the result determining unit is used for obtaining second power generation according to the matching result of the track segment and the road network segment.

As a possible implementation, the result determining unit may be configured to obtain the number of trajectory segments matching the road network segment as the third number; acquiring the number of track segments corresponding to the road network segments as a fourth number, wherein the fourth number is greater than or equal to the third number; taking the ratio of the third quantity to the fourth quantity as a third power generating rate corresponding to the map segment; and determining a second power forming rate corresponding to the map road network based on the third power forming rate corresponding to each map segment.

As a possible implementation, the map verification apparatus 200 may further include a connection confirmation module and a conduction confirmation module. The communication confirmation module is used for traversing a path from an entrance of the map network to any road sign element in the map network and determining whether the map network has connectivity; the conduction confirming module is used for obtaining the shortest path from the entrance of the map road network to any road sign element in the map road network and determining whether the map road network has conductivity.

As a possible implementation, the map verification apparatus 200 may further include: and a marking module. The marking module is used for marking the road network segments of the map road network according to the first component power and the second component power, and the marks are used for representing the matching degree of the crowdsourcing track and the map road network.

As a possible implementation, the map verification apparatus 200 may further include a patch module. The repairing module can be used for confirming the road network section to be repaired according to the matching degree and repairing the road network section.

As a possible implementation, the map determination module 230 may include a first determination unit and a second determination unit. The first determining unit is used for confirming that the map road network passes the verification if the first power consumption is larger than a first threshold value and the second power consumption is larger than a second threshold value; the second determining unit is used for confirming that the map network is not verified if the first power consumption is not larger than the first threshold value or the second power consumption is not larger than the second threshold value.

As a possible implementation manner, the second determining unit may specifically be configured to: if the first power is less than or equal to the first threshold value, deleting the map network; and if the first power generation rate is greater than the first threshold value and the second power generation rate is less than or equal to the second threshold value, repairing the map road network.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and modules may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, the coupling between the modules may be electrical, mechanical or other type of coupling.

In addition, functional modules in the embodiments of the present application may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.

In summary, in the map verification method provided by the application, each crowdsourcing track in a crowdsourcing data set is sequentially matched with a map road network, the crowdsourcing track is driving track data uploaded by a vehicle, and the crowdsourcing data set comprises at least two crowdsourcing tracks; determining a first success rate corresponding to the crowdsourcing data set and a second success rate corresponding to the map road network based on the matching result, wherein the first success rate is used for representing the probability that crowdsourcing tracks in the crowdsourcing data set are successfully matched with the map road network, and the second success rate is used for representing the probability that track segments in the crowdsourcing tracks are successfully matched with road network segments in the map road network; and confirming whether the map network passes the verification or not according to the first power cost and the second power cost. According to the method, the quality of the map road network can be verified according to the probability that the crowdsourcing track is successfully matched with the map road network and the probability that track segments in the crowdsourcing track are successfully matched with road network segments in the map road network, so that the accurate verification of the quality of the map road network is realized, and a basis is provided for the application of the map road network.

Referring to fig. 10, a block diagram of a computer device 100 according to an embodiment of the present disclosure is shown. The computer device 100 in the present application may include one or more of the following components: a processor 110, a memory 120, and one or more applications, wherein the one or more applications may be stored in the memory 120 and configured to be executed by the one or more processors 110, the one or more programs configured to perform a method as described in the aforementioned method embodiments.

Processor 110 may include one or more processing cores. The processor 110 connects various parts within the overall computer device using various interfaces and lines, performs various functions of the computer device and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 120, and calling data stored in the memory 120. Alternatively, the processor 110 may be implemented in hardware using at least one of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 110 may integrate one or more of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a modem, and the like. Wherein, the CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing display content; the modem is used to handle wireless communications. It is understood that the modem may not be integrated into the processor 110, but may be implemented by a communication chip.

The Memory 120 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). The memory 120 may be used to store instructions, programs, code sets, or instruction sets. The memory 120 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing various method embodiments described below, and the like. The data storage area may also store data created by the computer device during use (e.g., phone book, audio-video data, chat log data), etc.

Referring to fig. 11, a block diagram of a computer-readable storage medium according to an embodiment of the present application is shown. The computer-readable storage medium 800 has stored therein program code that can be called by a processor to execute the methods described in the above-described method embodiments.

The computer-readable storage medium 800 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. Alternatively, the computer-readable storage medium 800 includes a non-volatile computer-readable storage medium. The computer readable storage medium 800 has storage space for program code 810 to perform any of the method steps of the method described above. The program code can be read from or written to one or more computer program products. The program code 810 may be compressed, for example, in a suitable form.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not necessarily depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims

1. A map validation method, the method comprising:

sequentially matching each crowdsourcing track in a crowdsourcing data set with a map road network, wherein the crowdsourcing track is driving track data uploaded by a vehicle, and the crowdsourcing data set comprises at least two crowdsourcing tracks;

determining a first power component corresponding to the crowdsourcing data set and a second power component corresponding to the map road network based on the matching result, wherein the first power component is used for representing the probability that crowdsourcing tracks in the crowdsourcing data set are successfully matched with the map road network, and the second power component is used for representing the probability that track segments in the crowdsourcing tracks are successfully matched with road network segments in the map road network;

and confirming whether the map road network passes the verification or not according to the first power consumption and the second power consumption.

2. The method of claim 1, wherein before matching each crowdsourcing trajectory in the crowdsourcing data set to a map road network in turn, the method further comprises:

traversing a path from an entrance of the map road network to any road sign element in the map road network to determine whether the map road network has connectivity;

and acquiring a shortest path from an entrance of the map road network to any road sign element in the map road network, and determining whether the map road network has continuity.

3. The method of claim 1, wherein after determining a first power cost corresponding to the crowdsourcing data set and a second power cost corresponding to the mapping network based on the matching results, the method further comprises:

and marking the road network segment of the map road network according to the first power forming rate and the second power forming rate, wherein the mark is used for representing the matching degree of the crowdsourcing track and the map road network.

4. The method of claim 3, further comprising:

5. The method according to claim 1, wherein said confirming whether said map road network is verified according to said first power cost and said second power cost comprises:

if the first power generation rate is greater than a first threshold value and the second power generation rate is greater than a second threshold value, confirming that the map road network passes verification;

and if the first power consumption is not greater than a first threshold value or the second power consumption is not greater than a second threshold value, confirming that the map road network is not verified.

6. The method according to claim 5, wherein the confirming that the map network is not verified if the first power consumption is not greater than a first threshold or the second power consumption is not greater than a second threshold comprises:

if the first power is less than or equal to the first threshold value, deleting the map road network;

and if the first power generation rate is greater than the first threshold value and the second power generation rate is less than or equal to a second threshold value, repairing the map road network.

7. The method of any of claims 1-6, wherein the determining a first power contribution for the crowdsourcing data set based on the matching result comprises:

acquiring the number of the crowdsourcing tracks successfully matched with the map road network as a first number;

obtaining a number of crowdsourcing tracks in the crowdsourcing data set as a second number;

taking the ratio of the first quantity to the second quantity as the first power generation rate.

8. A map validation apparatus, the apparatus comprising: a track matching module, a success rate determining module and a map judging module, wherein

The track matching module is used for sequentially matching each crowdsourcing track in a crowdsourcing data set with a map road network, wherein the crowdsourcing track is driving track data uploaded by a vehicle, and the crowdsourcing data set comprises at least two crowdsourcing tracks;

the success rate determination module is used for determining a first success rate corresponding to the crowdsourcing data set and a second success rate corresponding to the map road network based on the matching result, wherein the first success rate is used for representing the probability that crowdsourcing tracks in the crowdsourcing data set are successfully matched with the map road network, and the second success rate is used for representing the probability that track segments in the crowdsourcing tracks are successfully matched with road network segments in the map road network;

the map judging module is used for confirming whether the map road network passes the verification or not according to the first power forming rate and the second power forming rate.

9. A computer device, comprising:

one or more processors;

a memory;

one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the method of any of claims 1-7.

10. A computer-readable storage medium, having stored thereon program code that can be invoked by a processor to perform the method according to any one of claims 1 to 7.