Map data acquisition method, electronic equipment, storage medium and program product

Abstract

The invention discloses a map data acquisition method, electronic equipment, a storage medium and a program product, and the method comprises the steps: determining a plurality of abnormal position points for carrying out map data acquisition on a target geographic region; determining at least one path planning point set based on the plurality of abnormal position points, each path planning point set including K target planning points, K being an integer greater than 1, the target planning points being abnormal position points and / or mapping points corresponding to the abnormal position points, the mapping point is a corresponding point on an existing path matched with the corresponding abnormal position point in the target geographic area; and for each path planning point set, carrying out the following processing: carrying out path planning on a sub-geographic area corresponding to the path planning point set according to K target planning points included in the path planning point set to obtain an acquisition path, so that a preset vehicle carries out map data acquisition on the sub-geographic area according to the acquisition path, and the target geographic area comprises the sub-geographic area. Through the process, the data volume of data acquisition can be reduced.

Description

Technical Field

[0001] The present application belongs to the field of map technology, and in particular relates to a map data collection method, electronic equipment, storage medium and program product. Background Art

[0002] With the rapid development of autonomous driving technology, maps are an important part of the autonomous driving system, and their accuracy and real-time performance are crucial to the safety and efficiency of autonomous driving. Due to the complexity and dynamic changes of the road environment, changes in certain sections of the road cannot be discovered in time. For example, a section of the road is currently inaccessible due to construction, or a section of the road has safety hazards due to damage caused by natural disasters and is not allowed to be passed.

[0003] To ensure the accuracy of the map, the map needs to update the data of the changed roads. At present, the data collection vehicle usually collects data while traveling, and collects data from multiple location points on the travel path, resulting in a large amount of data collection. Summary of the invention

[0004] The embodiments of the present application provide a map data collection method, electronic device, storage medium and program product, which can reduce the amount of data collection.

[0005] In a first aspect, an embodiment of the present application provides a map data collection method, the method comprising:

[0006] Determining a plurality of outlier locations for collecting map data for a target geographic area;

[0007] Determine at least one path planning point set based on the multiple abnormal location points, each of the path planning point sets includes K target planning points, where K is an integer greater than 1, and the target planning points are the abnormal location points and / or mapping points corresponding to the abnormal location points, and the mapping points are corresponding points on the existing paths matched by the corresponding abnormal location points in the target geographic area;

[0008] The following processing is performed on each path planning point set: path planning is performed on the sub-geographical area corresponding to the path planning point set according to the K target planning points included in the path planning point set to obtain a collection path, so that a preset vehicle collects map data for the sub-geographical area according to the collection path, and the target geographical area includes the sub-geographical area.

[0009] In a second aspect, an embodiment of the present application provides a map data collection device, the device comprising:

[0010] A first determination module is used to determine a plurality of abnormal location points for collecting map data of a target geographic area;

[0011] A second determination module is used to determine at least one path planning point set based on the multiple abnormal location points, each of the path planning point sets includes K target planning points, where K is an integer greater than 1, and the target planning point is the abnormal location point and / or a mapping point corresponding to the abnormal location point, and the mapping point is a corresponding point on an existing path matched by the corresponding abnormal location point in a target geographic area;

[0012] The planning module is used to perform the following processing on each path planning point set: according to the K target planning points included in the path planning point set, path planning is performed on the sub-geographical area corresponding to the path planning point set to obtain a collection path, so that a preset vehicle collects map data for the sub-geographical area according to the collection path, and the target geographical area includes the sub-geographical area.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory storing computer program instructions;

[0014] When the processor executes the computer program instructions, the map data collection method as described in the first aspect is implemented.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the map data collection method as described in the first aspect is implemented.

[0016] In a fifth aspect, an embodiment of the present application provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the map data collection method as described in the first aspect.

[0017] In an embodiment of the present application, multiple abnormal location points for map data collection of a target geographical area are determined; at least one path planning point set is determined based on the multiple abnormal location points, each of the path planning point sets includes K target planning points, K is an integer greater than 1, the target planning point is the abnormal location point and / or the mapping point corresponding to the abnormal location point, and the mapping point is the corresponding point on the existing path matched by the corresponding abnormal location point in the target geographical area; the following processing is performed for each path planning point set: according to the K target planning points included in the path planning point set, a path is planned for the sub-geographic area corresponding to the path planning point set to obtain a collection path, so that a preset vehicle collects map data for the sub-geographic area according to the collection path, and the target geographical area includes the sub-geographic area. In the above process, the collection path is determined by processing multiple abnormal location points. In this way, when the vehicle is predicted to collect data on the collection path, it can only collect map data at the abnormal location point and / or the mapping point corresponding to the abnormal location point. On the one hand, data collection is more targeted, and on the other hand, the amount of data collected on the collection path can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 It is a flowchart of a map data collection method provided by an embodiment of the present application;

[0020] Figure 2a is a schematic diagram of the distribution of points in a point cluster in a map provided in an embodiment of the present application;

[0021] Figure 2b is a schematic diagram of the distribution of point clusters in a map provided by an embodiment of the present application;

[0022] Figure 3 is a structural schematic diagram of a map data acquisition device provided in an embodiment of the present application;

[0023] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0025] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0026] In each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the disclosed embodiment will be obtained.

[0027] In order to solve the problems in the prior art, the embodiments of the present application provide a map data collection method, an electronic device, a storage medium and a program product. The map data collection method provided by the embodiments of the present application is first introduced below.

[0028] Figure 1 FIG. 1 is a flow chart of a map data collection method provided by an embodiment of the present application. Figure 1 As shown, the map data collection method provided in the embodiment of the present application is applied to an electronic device, such as a server, and includes the following steps 101 to 103, wherein:

[0029] Step 101, determining a plurality of abnormal location points for collecting map data in a target geographic area.

[0030] The target geographical area may be a preset geographical area, for example, a town, a village, etc., and may be set according to actual conditions and is not limited here.

[0031] The abnormal location point may be a geographical location point that needs to be collected for map data as reported by an intelligence source. For example, the abnormal location point includes at least one of the following:

[0032] (1) Geographical location points where the actual data is inconsistent with the map data in the target map. For example, the map records that the road is under construction, but the actual situation is that it is not under construction, or the map records that the road ahead is blocked, but the actual situation is that the road ahead is unobstructed, etc.

[0033] (2) Actual observation of geographical locations where road anomalies exist. For example, abnormal location points are locations where abnormalities (such as those under construction) are determined through on-site observation by a vehicle camera.

[0034] (3) The user provides the geographical location where data collection is required.

[0035] The abnormal location point can be described by longitude and latitude, or by a custom coordinate system, which is not limited here.

[0036] The abnormal location point can be obtained from at least one information source, and the information source includes a vehicle, a vehicle-mounted device deployed on the vehicle, a computer terminal, and a map server; the map server is, for example, a provider of commonly used navigation software, or a high-definition map provider, a precision map provider, etc. The information source can also refer to a vehicle involved in map data collection, for example, a vehicle providing intelligent driving, a crowdsourcing vehicle, a surveying vehicle, an ordinary private car, etc., which is not limited here.

[0037] In this embodiment, the abnormal location point can be a geographical location point where map data collection is required, and the intelligence source for obtaining the abnormal location point supports the vehicle, the on-board equipment deployed on the vehicle, the computer terminal, and the map server, making the method of obtaining the abnormal location point more flexible and convenient, which is conducive to the timely updating of map data.

[0038] Step 102: determine at least one path planning point set based on the multiple abnormal location points, each of the path planning point sets includes K target planning points, where K is an integer greater than 1, and the target planning points are the abnormal location points and / or mapping points corresponding to the abnormal location points, and the mapping points are corresponding points on the existing paths matched by the corresponding abnormal location points in the target geographic area.

[0039] Exemplarily, the mapping point may be a vertical point on an existing path that matches the abnormal position point, and the vertical point is a point on the existing path that is closest to the abnormal position point.

[0040] Step 103, performing the following processing for each path planning point set: performing path planning for the sub-geographical area corresponding to the path planning point set according to the K target planning points included in the path planning point set, and obtaining a collection path, so that a preset vehicle collects map data for the sub-geographical area according to the collection path, and the target geographical area includes the sub-geographical area.

[0041] Each path planning point set corresponds to a sub-geographical area in the target geographical area, and different path planning point sets correspond to different sub-geographical areas. Path planning is performed for each path planning point set to obtain a collection path corresponding to each path planning point set, and map data can be collected later based on the obtained collection path.

[0042] The preset vehicle may refer to a vehicle that participates in map data collection, such as a vehicle that provides intelligent driving, a crowdsourcing vehicle, a surveying vehicle, an ordinary private car, etc. After receiving the collection path, the vehicle terminal of the preset vehicle may collect data according to the collection path, and upload the collected data to the server, and the server updates the map, for example, updating the data of the location points passed by the collection path recorded in the map.

[0043] Exemplarily, the preset vehicle may be a vehicle currently within a preset range of the location point passed by the collection path. The preset range may be 30 meters or 50 meters, etc., which is not limited here.

[0044] In this embodiment, multiple abnormal location points for collecting map data for a target geographical area are determined; at least one path planning point set is determined based on the multiple abnormal location points; and the following processing is performed for each path planning point set: a path is planned for the sub-geographical area corresponding to the path planning point set according to the K target planning points included in the path planning point set, and a collection path is obtained, so that a preset vehicle collects map data for the sub-geographical area according to the collection path. Through the above process, a collection path is determined based on multiple abnormal location points. When predicting that a vehicle collects data on the collection path, only map data at the abnormal location points and / or the mapping points corresponding to the abnormal location points can be collected. On the one hand, data collection is more targeted. On the other hand, the amount of data collected on the collection path can be reduced, and the efficiency of data collection on the collection path can be improved. This can further shorten the map update cycle and make map updates more timely.

[0045] In an embodiment of the present application, determining at least one path planning point set based on the multiple abnormal location points includes one of the following:

[0046] (1) Each of the multiple abnormal position points is determined as the target planning point to obtain a path planning point set.

[0047] In this case, only one path planning point set is determined based on multiple abnormal location points, and the path planning point set includes all abnormal location points, and each abnormal location point in the path planning point set is a target planning point. Accordingly, the sub-geographical area corresponding to the path planning point set is the target geographical area.

[0048] (2) Determine the mapping points corresponding to each first abnormal location point among the multiple abnormal location points as the target planning point to obtain a path planning point set, wherein the first abnormal location point is an abnormal location point that matches an existing path in the target geographical area.

[0049] In this case, only one path planning point set is determined based on multiple abnormal location points. It should be noted that not every abnormal location point matches the existing path of the target geographical area. The abnormal location point that matches the existing path of the target geographical area is regarded as the first abnormal location point. The path planning point set includes all mapping points corresponding to the first abnormal location points, and each first abnormal location point in the path planning point set is a target planning point. Accordingly, the sub-geographical area corresponding to the path planning point set is the target geographical area.

[0050] (3) Clustering the multiple abnormal position points to obtain at least one point cluster, and executing for each point cluster: determining each abnormal position point in the point cluster as the target planning point, to obtain a path planning point set corresponding to the point cluster.

[0051] A clustering analysis may be performed on multiple abnormal location points by using a clustering algorithm, such as a density-based clustering method with noise (Density—Based Spatial Clustering of Application with Noise, DBSCAN), a Gaussian mixture model (Gaussian Mixture Model, GMM), etc., which are not limited here.

[0052] After clustering and classification, at least one point cluster is obtained, each point cluster includes at least one abnormal position point, each point cluster corresponds to a path planning point set, the path planning point set includes each abnormal position point in the corresponding point cluster, and each abnormal position point in the path planning point set is a target planning point. Each path planning point set corresponds to a sub-geographical area, and the sub-geographical area can be determined based on the abnormal position points in the path planning point set. For example, point cluster U includes two abnormal position points, and the circular area with the center position of the path between the two abnormal position points as the center and a radius slightly larger than the distance from the center position to an abnormal position point is the sub-geographical area corresponding to point cluster U (the sub-geographical area corresponding to point cluster U is also the sub-geographical area corresponding to the path planning point set corresponding to point cluster U). Of course, the sub-geographical area corresponding to point cluster U can also be determined in other ways, which are not limited here. It should be noted that the shape of the sub-geographical area corresponding to the point cluster can be set according to actual conditions, such as rectangle, circle or ellipse, etc.

[0053] (4) Clustering the multiple abnormal location points to obtain at least one point cluster, and executing for each of the point clusters: determining the abnormal location point that matches the existing path in the sub-geographical area corresponding to the point cluster as a second abnormal location point, and determining the mapping points corresponding to each of the second abnormal location points as the target planning points, to obtain a path planning point set corresponding to the point cluster.

[0054] The method of clustering the multiple abnormal location points can be found in the above records and will not be elaborated here. In this case, the abnormal location points in the point cluster that match the existing paths of the sub-geographical area corresponding to the point cluster are regarded as second abnormal location points, and the path planning point set corresponding to the point cluster includes the mapping points corresponding to the second abnormal location points in all point clusters, and each second abnormal location point in the path planning point set is a target planning point. Correspondingly, the sub-geographical area corresponding to the point cluster is also the sub-geographical area corresponding to the path planning point set.

[0055] In the above, multiple abnormal position points are clustered to obtain at least one point cluster, and then path planning is performed for the path planning point set corresponding to each point cluster, which can reduce the computational complexity of path planning, and the path planning process of each point cluster can be executed in parallel on different processors of the electronic device (the electronic device includes multiple processors, each processor executes the path planning process of a point cluster, and the execution processes between the processors are not affected by each other), which also improves the efficiency of obtaining the collection path corresponding to each point cluster. In addition, since the target planning points in the same point cluster are obtained through cluster analysis, the positions of these target planning points are relatively concentrated. When performing path planning, the purpose of using a shorter path to pass through more target planning points can be achieved, so that the collection cost of the planned collection path is low.

[0056] When path planning is subsequently performed according to the path planning point set corresponding to the point cluster, the computational complexity of path planning can be reduced.

[0057] In this embodiment, at least one path planning point set is obtained based on multiple abnormal location points. The path planning point set includes a target planning point. The target planning point can be an abnormal location point or a mapping point of an abnormal location point. It can be selected whether the target planning point is an abnormal location point or a mapping point of an abnormal location point according to actual needs. When the target planning point is an abnormal location point, the acquisition path passes through the abnormal location point. When data collection is performed, data can be collected from the abnormal location point. In this way, when the map data is updated, the data collected at the abnormal location point can be used to update the map data, thereby improving the update accuracy of the map data. When the target planning point is a mapping point of an abnormal location point, the acquisition path passes through the mapping point of the abnormal location point. Since the mapping point is a point on an existing path, the acquisition path obtained by planning is composed of the existing path. There will be no situation where the path is unreachable and needs to be detoured, and a more optimized acquisition path can be obtained.

[0058] In another embodiment of the present application, performing path planning on the sub-geographical area corresponding to the path planning point set according to the K target planning points included in the path planning point set to obtain a collection path includes:

[0059] According to the K target planning points included in the path planning point set, a weighted directed graph corresponding to the path planning point set is constructed, wherein any two target planning points in the path planning point set are used to determine two directed edges of the weighted directed graph and the vertices of the two directed edges, and the weights of the directed edges are determined according to the data collection costs of the navigation paths corresponding to the two target planning points;

[0060] According to the weighted directed graph, path planning is performed on the sub-geographical area corresponding to the path planning point set to obtain the collection path.

[0061] Specifically, according to any two target planning points in the path planning point set, two directed edges of a weighted directed graph can be constructed, the vertices of the directed edges are the two target planning points respectively, and the weights of the directed edges are determined according to the data collection costs of the navigation paths corresponding to the two target planning points.

[0062] It should be noted that in order to reduce the computational overhead, multiple target planning points can be deduplicated. For example, if the distance between two target planning points is less than or equal to the preset distance, any one of the target planning points is retained and the other target planning point is deleted. If the distance between two target planning points is greater than the preset distance, the two target planning points are retained. The preset distance can be set according to the actual situation, for example, 10 meters or 20 meters, which is not limited here.

[0063] The data collection cost can be composed of multiple dimensions, such as at least one of the collection cost, collection efficiency, collection mileage, road congestion, etc. It should be noted that if there is no navigation path from the target planning point a to the target planning point b, the weight of the directed edge from a to b can be set to infinity. The larger the weight, the greater the data collection cost.

[0064] The following uses the data collection cost, collection efficiency and collection mileage as an example to illustrate how to calculate the weight of a directed edge.

[0065] For example, there are target planning points A and B on the highway, and there are many vehicles in this area for data collection. The collection costs of the two directed edges formed by target planning points A and B are both 600, and the data collection time is 7 hours. The corresponding collection efficiency is 0.8. Exemplarily, the collection efficiency can be determined according to a preset comparison relationship, and the comparison relationship includes multiple data collection time and the collection efficiency corresponding to each data collection time, wherein the shorter the data collection time, the higher the collection efficiency; the collection mileage of the directed edge formed by target planning point A to target planning point B (that is, the length of the navigation path from target planning point A to target planning point B) is 50 meters, and the collection mileage of the directed edge formed by target planning point B to target planning point A (that is, the length of the navigation path from target planning point B to target planning point A) is 2000 meters;

[0066] There is a target planning point C in a remote area. There are fewer vehicles used for data collection in this area. The collection costs of the two directed edges formed by the target planning point C and the target planning point A are both 1000. The data collection time is 48 hours, and the corresponding collection efficiency is 0.2; the collection mileage of the directed edge formed by the target planning point A to the target planning point C (that is, the length of the navigation path from the target planning point A to the target planning point C) is 100 meters, and the collection mileage of the directed edge formed by the target planning point C to the target planning point A (that is, the length of the navigation path from the target planning point C to the target planning point A) is 6000 meters.

[0067] The collection costs of the two directed edges formed by the target planning point C and the target planning point B are both 5000, the data collection time is 24 hours, and the corresponding collection efficiency is 0.5; the collection mileage of the directed edge formed by the target planning point B to the target planning point C (that is, the length of the navigation path from the target planning point B to the target planning point C) is 200 meters, and the collection mileage of the directed edge formed by the target planning point C to the target planning point B (that is, the length of the navigation path from the target planning point C to the target planning point B) is 4000 meters.

[0068] The data of the three dimensions of collection cost, collection efficiency and collection mileage are normalized separately, and the data of different dimensions are restricted to the same range, for example, between 0 and 1, or between -1 and 1, which is not limited here. The weight corresponding to each directed edge can be the value obtained by adding the collection cost, collection efficiency and collection mileage corresponding to the directed edge after each normalization process. The higher the collection cost, the greater the weight; the lower the collection efficiency, the greater the weight (the collection efficiency is inversely proportional to the weight); the longer the collection mileage, the greater the weight. Each directed edge corresponds to a path, and the weight of the directed edge can represent the total cost of data collection on the path. The greater the weight, the higher the total cost.

[0069] In the above example, the weight of a directed edge is a value. In another embodiment of the present application, the weight of a directed edge may be a vector, which includes multiple element values, each element value being used to characterize one of the collection cost, collection efficiency, and collection mileage. By way of example, as in the above example, after normalizing the data of the three dimensions of collection cost, collection efficiency, and collection mileage, the obtained numerical values ​​are used as element values ​​in the vector, thereby obtaining the weight of each directed edge.

[0070] A multi-point path planning algorithm, such as a genetic algorithm or an ant colony algorithm, is used to plan the path of a weighted directed graph to obtain a collection path.

[0071] In the above, path planning is performed based on the target planning point to obtain the collection path, and data is collected for the target planning point while the preset vehicle is traveling along the collection path. When the target planning point is an abnormal location point, data can be collected for the abnormal location point, so that when the map data is updated, the data collected at the abnormal location point can be used to update the map data, thereby improving the update accuracy of the map data. However, considering that there may be road congestion at the abnormal location point, for example, there is no existing path to reach the point or there is an existing path to reach the point but a detour is required, the collection path obtained by such planning may require a long detour, resulting in a higher collection cost.

[0072] When the target planning point is the mapping point of an abnormal position point, since the mapping point is a point on an existing path, the collection path planned in this way is composed of existing paths, and there will be no situation where the path is unreachable and a detour is required. A more optimized collection path can be obtained, reducing the collection cost. In addition, there may be a situation where the mapping points of multiple abnormal position points are located on the same existing path. When planning the path, the existing path will be planned into the collection path (because the data collection cost of the existing path is the lowest). In this way, the preset vehicle can collect multiple mapping points when passing through the existing path, which not only improves the collection efficiency, but also saves the collection cost.

[0073] In another embodiment of the present application, constructing a weighted directed graph corresponding to the path planning point set according to the K target planning points included in the path planning point set includes:

[0074] Performing deduplication processing on the K target planning points in the path planning point set, wherein the deduplication processing includes: retaining all target planning points located at intersections, and retaining any one of the multiple target planning points in the path planning point set that are not located at intersections and are located on the same direction section;

[0075] According to the target planning point in the path planning point set after deduplication processing, a weighted directed graph corresponding to the path planning point set is constructed.

[0076] In the above, since the target planning points at the intersection may be located on sections in different directions, in order to avoid information loss, all the target planning points at the intersection are retained. For multiple target planning points that are not located at the intersection and are located on the same direction, these target planning points are considered to be points with redundant information, that is, any target planning point plays the same role in the subsequent path planning. Retaining any one of the target planning points and deleting the other target planning points can effectively reduce the complexity of subsequent calculations while effectively ensuring that information is not lost.

[0077] In an embodiment of the present application, performing path planning on the sub-geographical area corresponding to the path planning point set according to the weighted directed graph to obtain the collection path includes:

[0078] Get the number of starting points M and the number of end points N of the path planning, where M and N are both positive integers;

[0079] Randomly select M vertices of the weighted directed graph as starting points, and randomly select N vertices other than the M vertices in the weighted directed graph as end points;

[0080] Based on the M starting points and N end points in the weighted directed graph, path planning is performed on the sub-geographical area corresponding to the path planning point set to obtain the collection path.

[0081] Specifically, M and N can use default values ​​or be specified by the user, which is not limited here. In this embodiment, only the number of starting points M and the number of end points N are determined, and it is not necessary to specify which vertices in the weighted directed graph are starting points and which vertices are end points. Instead, the starting point and the end point are determined by random selection. It should be noted that any vertex in the weighted directed graph can be a starting point, and any vertex can be an end point, but the same vertex cannot be both a starting point and an end point.

[0082] After determining the M starting points and N end points, a multi-point path planning algorithm, such as a genetic algorithm or an ant colony algorithm, can be used to perform path planning on the weighted directed graph to obtain a collection path.

[0083] In this embodiment, only the number of starting points and the number of end points are specified, and the starting points and end points in the weighted directed graph are determined by random selection. Then, based on the starting points and the end points, path planning is performed for the sub-geographical area corresponding to the path planning point set, thereby improving the randomness of path planning. In this way, a better collection path can be obtained in a finite number of iterations.

[0084] In the above, based on the M starting points and N end points in the weighted directed graph, path planning is performed on the sub-geographical area corresponding to the path planning point set to obtain the collection path, including:

[0085] Based on the M starting points and N end points in the weighted directed graph, multiple path planning is performed on the sub-geographical area corresponding to the path planning point set to obtain multiple groups of paths, wherein each path planning corresponds to a group of paths, each group of paths includes at least one path, the starting point of each path is one of the M starting points, and the end point of the path is one of the N end points;

[0086] At least one group of paths is selected from the multiple groups of paths based on a data collection target, and the paths included in the at least one group of paths are determined as the collection paths, wherein the data collection target is determined based on at least one of collection cost, collection efficiency and collection mileage.

[0087] Specifically, each path planning obtains a group of paths, the group of paths includes at least one path, the starting point of each path is one of the M starting points, and the end point of the path is one of the N end points. Each path planning can be an iteration of the multi-point path planning algorithm. It should be noted that the number of starting points in each iteration can be the same or different, and the number of end points in each iteration can be the same or different.

[0088] The weight of the directed edge in the weighted directed graph is determined according to the data collection cost of the navigation path. The data collection cost can be composed of multiple dimensions, such as at least one of the collection cost, collection efficiency, collection mileage, road congestion, etc. In the above example, the weight of the directed edge can be a vector, which includes three element values, each element value is used to represent one of the collection cost, collection efficiency and collection mileage. For example, after normalizing the data of the three dimensions of collection cost, collection efficiency and collection mileage, the obtained values ​​are used as the three element values ​​in the vector, thereby obtaining the weight of each directed edge. When the data collection target is the collection cost, at least one group of paths can be selected from multiple groups of paths based on the minimum collection cost. In this case, the weight corresponding to the collection cost of each path in each group of paths is summed, and at least one group of paths with the smallest sum of weights is selected (the smaller the collection cost, the smaller the corresponding weight); when the data collection target is the collection efficiency, at least one group of paths can be selected from multiple groups of paths based on the maximum collection efficiency. In this case, the weight corresponding to the collection efficiency of each path in each group of paths is summed, and at least one group of paths with the smallest sum of weights is selected (the greater the collection efficiency, the smaller the corresponding weight); when the data collection target is the collection mileage, at least one group of paths can be selected from multiple groups of paths based on the maximum collection mileage. In this case, the weight corresponding to the collection mileage of each path in each group of paths is summed, and at least one group of paths with the smallest sum of weights is selected (the smaller the collection mileage, the smaller the corresponding weight).

[0089] For example, the data collection target can also be determined based on the collection cost, collection efficiency and collection mileage. Specifically, assuming that there are five target planning points a, b, c, d and e in the path planning point set, a weighted directed graph G(V, E) is constructed, where the edge weights can be represented by the following matrix:

[0090]

[0091] Among them, w aa represents a directed edge from a to a, w ab represents a directed edge from a to b, w ba Represents the directed edge from b to a, and so on. The above matrix includes the weight of the directed edge from each target planning point to other target planning points, as well as the weight of the directed edge from each target planning point to itself.

[0092] Exemplarily, the weight of the directed edge from a to b (i.e., the data collection cost) is calculated according to the following expression:

[0093] w ab =w0+λ1w1+λ2w2+λ3w3+...+λ i w i

[0094] Among them, λ i : The weight coefficient of the i-th dimension, λ i ∈(0~1);

[0095] w i : The weight of the i-th dimension. For example, if the data collection cost consists of three dimensions: collection cost, collection efficiency, and collection mileage, then i is 3. If the data collection cost consists of four dimensions: collection cost, collection efficiency, collection mileage, and road congestion, then i is 4.

[0096] If there is a navigation route from a to b, w0 is 0; if there is no navigation route from a to b (a to b is unreachable), w0 is +∞.

[0097] If the data collection target is determined based on the collection cost, collection efficiency and collection mileage, then the data collection cost of each directed edge is composed of three dimensions: collection cost, collection efficiency and collection mileage. Based on the weighted directed graph constructed based on the target planning points a, b, c, d and e, the starting point and the end point are randomly found, and the following three groups of routes can be obtained:

[0098] 1. a->b->c, d->e, where the total cost is Cost1 = w ab +w bc +w de +W';

[0099] 2. a->b->d, b->e->d, where the total cost is Cost2 = w ac +w cd +w be +w ed +W';

[0100] 3. a->b->c->d->e, where the total cost is Cost3 = w ab +w bc +w cd +w ed +W';

[0101] According to the above combination, many path line plans can be made to cover these target planning points, wherein W' is an adjustment coefficient, which is a constant and can be determined according to actual conditions, and is not limited here.

[0102] For each group of routes, a total cost is calculated according to the above method, and one or more groups of paths with the minimum total cost are selected as the collection paths.

[0103] In addition, in addition to considering the collection cost, collection efficiency, and collection mileage (based on these three factors, the proportion of data collection costs can be obtained), the data collection target can also consider the point coverage and collection time proportion. In this case, the data collection target F is defined as:

[0104]

[0105] Among them, β0 is a constant, β1, β2 and β3 are preset proportional coefficients, which can be adjusted according to actual conditions.

[0106] Point coverage

[0107] P coll : The number of points covered by the route (only one point is retained among multiple paths that are repeated). For example, considering that the route does not necessarily pass through 5 points, it may only pass through 4 points, because in a certain path planning process, when passing through these 4 points, the collection efficiency is the highest and the collection cost is the lowest. In this case, the obtained set of paths will have a point that is not passed.

[0108] P total : The number of all target planning points in the path planning point set;

[0109] Data collection cost ratio

[0110] C plan_total : The sum of the data collection costs of all routes in a set of planned paths (such as Cost1, Cost2, or Cost3 mentioned above);

[0111] C sum : The data collection cost of each target planning point after projection (for example, the section where the mapping point is located) is added up;

[0112] Proportion of collection time

[0113] T sum : The driving time of each target planning point after projection is added up (for example, the section where the mapping point is located);

[0114] T plan_total : The time required to collect all routes in a planned set of paths, including the driving time of the road section and the vehicle scheduling time.

[0115] For each group of routes, an F value is calculated according to the above method. The F value is proportional to the point coverage and the proportion of collection time, and inversely proportional to the proportion of data collection cost. One or more groups of paths with the largest F value are selected as the collection path.

[0116] After the above process, path planning is performed according to the weighted directed graph corresponding to the path planning point set to obtain the collection path. Compared with manual planning, the above method can improve the planning efficiency of the collection path and make the collection path optimal, thereby improving the collection efficiency of subsequent data collection based on the collection path, effectively shortening the map update cycle, and making the map update more timely.

[0117] In another embodiment of the present application, after performing path planning for the sub-geographical area corresponding to the path planning point set according to the K target planning points included in the path planning point set to obtain the collection path, the method further includes:

[0118] Determine a data collection cost of a navigation path between a third abnormal location point and a target point, wherein the target point is a starting point or an end point of a path included in the collection path, and the third abnormal location point is an abnormal location point among the multiple abnormal location points that does not match an existing path in the target geographic area;

[0119] According to the data collection cost of the navigation path between the third abnormal position point and the target point, the target point corresponding to the third abnormal position point is selected, and the third abnormal position point is used as an auxiliary collection point of the path where the selected target point is located.

[0120] Specifically, the data collection cost of the navigation path between the third abnormal position point and the target point can refer to the method for determining the weight of the directed edge of the weighted directed graph in the aforementioned embodiment, which will not be elaborated here.

[0121] The higher the collection cost, the greater the data collection cost of the navigation path between the third abnormal position point and the target point; the lower the collection efficiency, the greater the data collection cost of the navigation path between the third abnormal position point and the target point; the longer the collection mileage, the greater the data collection cost of the navigation path between the third abnormal position point and the target point. The data collection cost of the navigation path between the third abnormal position point and the target point can be the value obtained by adding the collection cost, collection efficiency and collection mileage corresponding to the navigation path. In this case, the target point corresponding to the navigation path with the smallest weight can be selected, and the third abnormal position point can be used as an auxiliary collection point of the path where the selected target point is located.

[0122] When the preset vehicle collects data according to the path in the collection path, if the path has auxiliary collection points, data collection is also required for the auxiliary collection points.

[0123] Alternatively, the subsidiary collection points are marked, for example, the subsidiary collection points are marked as collection points with additional rewards, so that the preset vehicle can decide whether to collect data from the subsidiary collection points. For example, when the additional rewards for the subsidiary collection points are high, the preset vehicle can also choose to collect data from the subsidiary collection points when collecting data.

[0124] Through the above method, a collection path can be matched for abnormal location points among multiple abnormal location points that do not match the existing paths in the target geographic area, and the third abnormal location point can be used as an auxiliary collection point of the matching path in the collection path, so that when the preset vehicle collects data on the path in the collection path, if the path has an auxiliary collection point, data is also collected on the auxiliary collection point to obtain data from more abnormal location points, so that the data used for map updating is more comprehensive, thereby improving the accuracy of the map.

[0125] The following is an example of the map data collection method provided in the embodiment of the present application.

[0126] Step 0: Collect the abnormal points fed back by the multi-source intelligence points (i.e., the geographical location points that need to be collected for map data), process the abnormal points collected from the multi-source intelligence points into a unified specification (e.g., normalization), and output the multi-source intelligence point set infoPointVector.

[0127] Among them, the abnormal points are geographical location points or coordinate points that are preliminarily judged to require map data collection. The abnormal points can be points where the current actual situation is inconsistent with the map data (for example, the map shows that it is under construction, but the current actual situation is not under construction, etc.), or points where vehicle on-site observations are abnormal (such as under construction), points where users directly feedback that data collection is required, etc.; the collection sources of these abnormal points can be multiple source ends, such as different map manufacturers (for example, high-definition map providers or standard map providers, etc.), different vehicles (such as smart driving vehicles, crowdsourcing vehicles, surveying and mapping vehicles, ordinary private cars, etc.).

[0128] Step 1: Remove noise points to obtain a set of current problem points: Verify whether each point in the multi-source intelligence point set infoPointVector obtained from the multi-source intelligence points in step 0 is a point that needs data collection. If so, keep it. If it is not a point that needs data collection (such as the data of the point has been collected, or the information is obtained incorrectly, etc.), delete it, and finally obtain the filtered current problem point set infoPointVectorFilter, that is, multiple abnormal location points;

[0129] Step 2: Perform cluster analysis on the current problem point set to obtain multiple point clusters. For example, the infoPointVectorFilter obtained in step 1 is classified by machine learning or deep learning clustering methods such as DBSCAN, GMM, etc. to obtain multiple point clusters infoPointClusters; each cluster corresponds to a geographical area, such as Figure 2a As shown, the red points are the points in the point cluster;

[0130] Step 3: Process each point cluster separately, including the processing of steps 31 and 32:

[0131] Step 31, match each point info_point in each point cluster with the path (also called road) (which can be a standard road or a high-precision road) in the geographical area corresponding to the point cluster, determine the matching relationship between each point info_point in the point cluster and the standard road / high-precision road, and calculate the standard road found for each point.

[0132] Among them, the matching relationship between info_point and the precise road is calculated, and the matching relationship is obtained through map matching methods such as HMM, and then the vertical point infor_point_vertical from info_point to the matched precise road is calculated. If the precise road to which the info_Point is actually mapped cannot be found within a certain range, it can be regarded as an isolated point or a suspected newly opened road that has not been covered by a single precise road. This type of point is temporarily classified as OtherInfoPoints (i.e., the third abnormal location point).

[0133] Step 32: For each point cluster after step 31, duplicate vertical points are removed, and info_points in the same direction of the same road section are removed. Then, a mapping relationship is established between info_point_vertical and the precise road (a directed graph G(V, E) is established between vertical points, where V is each info_point_vertical, and E is a navigation route between two points based on the precise road. Its weight is the comprehensive cost such as the travel time, mileage, and whether tolls are required between the two points). Then, it is determined whether these different info_point_verticals in each point cluster are on the road in the same direction of two intersections of the precise road, or between the sections in the same direction between two ramp entrances and exits. If so, one of them can be retained; at the same time, if the info_point_vertical is within the intersection surface or the entrance and exit surface, it is retained without filtering.

[0134] Through steps 0 to 3 (including steps 31 and 32), the information of multi-source current changes can be transformed into point clusters in different spaces, and each point in the point cluster has unique features in certain sections. These information points after deduplication and screening are defined as trueInfoPoints and the point cluster trueInfoPointsCluster corresponding to each point, such as Figure 2b In the map schematic diagram shown, the area enclosed by each circle is a point cluster 1, and the point cluster 1 includes multiple abnormal location points. The number 2 shows the third abnormal location point.

[0135] Step 4: Perform the following processing on each point cluster processed in step 3:

[0136] Calculate the points that need to be updated in each point cluster, use multi-point path planning algorithms, such as genetic algorithms or ant colony algorithms, to plan paths based on the marked roads, and at the same time increase the collection of comprehensive data collection targets (such as CostFunction established based on collection cost, collection efficiency, collection mileage and other dimensions). Calculate the optimal comprehensive collection target (such as the shortest collection cost and collection mileage, the highest collection efficiency) within a limited number of iterations to obtain the optimal number of collection items and collection routes; that is, for each point cluster: iteratively optimize the collection path and number of items based on the overall collection cost and collection efficiency in a comprehensive and optimal way to determine the optimal collection route and number of items.

[0137] Step 5: For the otherInfoPoints obtained in the step, find the starting point or end point of the collection route calculated in step 5, and calculate the collection route with the smallest edge weight as the subsidiary collection point of the route. When the collection task is issued later, the collector can be temporarily rewarded or encouraged to cover its point in other ways.

[0138] The map data collection method provided in the embodiment of the present application can ensure the comprehensiveness and real-time nature of map update data by analyzing user feedback data and dynamically adjusting the collection path, while improving the efficiency of map collection, reducing collection costs, and achieving targeted and accurate collection.

[0139] Figure 3 FIG. 1 shows a structural diagram of a map data collection device provided in an embodiment of the present application. Figure 3 As shown, the map data collection device 300 includes:

[0140] The first determination module 301 is used to determine a plurality of abnormal location points for collecting map data of a target geographical area;

[0141] A second determination module 302 is used to determine at least one path planning point set based on the multiple abnormal location points, each of the path planning point sets includes K target planning points, where K is an integer greater than 1, and the target planning point is the abnormal location point and / or a mapping point corresponding to the abnormal location point, and the mapping point is a corresponding point on an existing path matched by the corresponding abnormal location point in a target geographic area;

[0142] The planning module 303 is used to perform the following processing on each path planning point set: perform path planning for the sub-geographical area corresponding to the path planning point set according to the K target planning points included in the path planning point set, and obtain a collection path, so that a preset vehicle collects map data for the sub-geographical area according to the collection path, and the target geographical area includes the sub-geographical area.

[0143] In an embodiment of the present application, the second determining module 302 includes:

[0144] A first determination submodule is used to determine each of the multiple abnormal position points as the target planning point to obtain a path planning point set;

[0145] or,

[0146] A second determination submodule is used to determine the mapping points corresponding to each first abnormal position point among the multiple abnormal position points as the target planning point to obtain a path planning point set, wherein the first abnormal position point is an abnormal position point that matches an existing path in the target geographical area;

[0147] or,

[0148] A third determination submodule is configured to cluster the plurality of abnormal position points to obtain at least one point cluster, and execute, for each point cluster: determining each abnormal position point in the point cluster as the target planning point to obtain a path planning point set corresponding to the point cluster;

[0149] or,

[0150] The fourth determination submodule is used to cluster the multiple abnormal location points to obtain at least one point cluster, and execute for each point cluster: determine the abnormal location point that matches the existing path in the sub-geographical area corresponding to the point cluster as the second abnormal location point, and determine the mapping points corresponding to each of the second abnormal location points as the target planning points, so as to obtain a path planning point set corresponding to the point cluster.

[0151] In one embodiment of the present application, the planning module 303 includes:

[0152] A construction submodule, configured to construct a weighted directed graph corresponding to the path planning point set according to the K target planning points included in the path planning point set, wherein any two target planning points in the path planning point set are used to determine two directed edges of the weighted directed graph and the vertices of the two directed edges, and the weights of the directed edges are determined according to the data collection costs of the navigation paths corresponding to the two target planning points;

[0153] The planning submodule is used to perform path planning on the sub-geographical area corresponding to the path planning point set according to the weighted directed graph to obtain the collection path.

[0154] In one embodiment of the present application, the construction submodule includes:

[0155] A deduplication unit, configured to perform deduplication processing on the K target planning points in the path planning point set, wherein the deduplication processing includes: retaining all target planning points located at intersections, and retaining any one of the multiple target planning points in the path planning point set that are not located at intersections and are located on the same direction section;

[0156] The construction unit is used to construct a weighted directed graph corresponding to the path planning point set according to the target planning point in the path planning point set after deduplication processing.

[0157] In an embodiment of the present application, the planning submodule includes:

[0158] An acquisition unit, used to acquire the number M of starting points and the number N of end points of the path planning, where both M and N are positive integers;

[0159] A determination unit, configured to randomly select M vertices of the weighted directed graph as starting points, and randomly select N vertices other than the M vertices in the weighted directed graph as end points;

[0160] A planning unit is used to perform path planning on the sub-geographical area corresponding to the path planning point set based on the M starting points and N end points in the weighted directed graph to obtain the collection path.

[0161] In one embodiment of the present application, the planning unit includes:

[0162] A planning subunit, configured to perform multiple path planning on the sub-geographical area corresponding to the path planning point set based on the M starting points and the N end points in the weighted directed graph, to obtain multiple groups of paths, wherein each path planning corresponds to obtaining a group of paths, each group of paths includes at least one path, the starting point of each path is one of the M starting points, and the end point of the path is one of the N end points;

[0163] A determination subunit is used to select at least one group of paths from the multiple groups of paths based on a data collection target, and determine the paths included in the at least one group of paths as the collection paths, wherein the data collection target is determined based on at least one of collection cost, collection efficiency and collection mileage.

[0164] In one embodiment of the present application, the plurality of abnormal location points are obtained from at least one information source, the information source including a vehicle, an on-board device deployed on the vehicle, a computer terminal, and a map server;

[0165] and / or,

[0166] The abnormal location point includes at least one of the following:

[0167] Geographical location points where actual data is inconsistent with map data in the target map;

[0168] The geographical locations where road anomalies are actually observed;

[0169] The user provides the geographical location where data collection is required.

[0170] In one embodiment of the present application, the map data collection device 300 further includes:

[0171] A third determination module is used to determine the data collection cost of the navigation path between a third abnormal location point and a target point, wherein the target point is a starting point or an end point of a path included in the collection path, and the third abnormal location point is an abnormal location point among the multiple abnormal location points that does not match an existing path in the target geographic area;

[0172] The fourth determination module is used to select the target point corresponding to the third abnormal position point according to the data collection cost of the navigation path between the third abnormal position point and the target point, and use the third abnormal position point as an auxiliary collection point of the path where the selected target point is located.

[0173] The map data collection device 300 provided in the embodiment of the present application can implement each process implemented in the aforementioned map data collection method embodiment and achieve the same technical effect. To avoid repetition, it will not be described here.

[0174] Figure 4 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0175] The electronic device may include a processor 401 and a memory 402 storing computer program instructions.

[0176] Specifically, the processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0177] Memory 402 may include a large capacity memory for data or instructions. By way of example and not limitation, memory 402 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, memory 402 may include a removable or non-removable (or fixed) medium. In appropriate cases, memory 402 may be inside or outside of an integrated gateway disaster recovery device. In a specific embodiment, memory 402 is a non-volatile solid-state memory.

[0178] The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to the first aspect or the second aspect of the present disclosure.

[0179] The processor 401 implements any one of the information auditing methods in the above embodiments by reading and executing computer program instructions stored in the memory 402 .

[0180] In one example, the electronic device may further include a communication interface 403 and a bus 410. Figure 4 As shown, the processor 401, the memory 402, and the communication interface 403 are connected via a bus 410 and communicate with each other.

[0181] The communication interface 403 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0182] Bus 410 includes hardware, software or both, and the parts of information audit method or verification equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 410 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0183] In addition, in combination with the map data collection method in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the map data collection methods in the above embodiment is implemented.

[0184] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiment, several specific steps are described as examples. However, the method process of the present application is not limited to the specific steps described, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0185] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0186] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0187] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0188] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A map data collection method, characterized in that: include: Determining a plurality of outlier locations for collecting map data for a target geographic area; Determine at least one path planning point set based on the multiple abnormal location points, each of the path planning point sets includes K target planning points, K is an integer greater than 1, the target planning point is the abnormal location point and / or a mapping point corresponding to the abnormal location point, and the mapping point is a corresponding point on an existing path matched by the corresponding abnormal location point in a target geographic area; The following processing is performed on each path planning point set: path planning is performed on the sub-geographical area corresponding to the path planning point set according to the K target planning points included in the path planning point set to obtain a collection path, so that a preset vehicle collects map data for the sub-geographical area according to the collection path, and the target geographical area includes the sub-geographical area.

2. The map data collection method according to claim 1, characterized in that: The determining at least one path planning point set based on the multiple abnormal location points comprises: Determine each of the plurality of abnormal position points as the target planning point to obtain a path planning point set; or, Determine the mapping points corresponding to each first abnormal position point among the multiple abnormal position points as the target planning point to obtain a path planning point set, wherein the first abnormal position point is an abnormal position point that matches an existing path in the target geographical area; or, Clustering the multiple abnormal position points to obtain at least one point cluster, and executing for each point cluster: determining each abnormal position point in the point cluster as the target planning point to obtain a path planning point set corresponding to the point cluster; or, The multiple abnormal location points are clustered to obtain at least one point cluster, and for each point cluster, the following steps are performed: an abnormal location point that matches an existing path in a sub-geographical area corresponding to the point cluster is determined as a second abnormal location point, and mapping points corresponding to each of the second abnormal location points are determined as the target planning points, to obtain a path planning point set corresponding to the point cluster.

3. The map data collection method according to claim 1, characterized in that: The step of performing path planning on a sub-geographical area corresponding to the path planning point set according to the K target planning points included in the path planning point set to obtain a collection path includes: According to the K target planning points included in the path planning point set, a weighted directed graph corresponding to the path planning point set is constructed, wherein any two target planning points in the path planning point set are used to determine two directed edges of the weighted directed graph and the vertices of the two directed edges, and the weights of the directed edges are determined according to the data collection costs of the navigation paths corresponding to the two target planning points; According to the weighted directed graph, path planning is performed on the sub-geographical area corresponding to the path planning point set to obtain the collection path.

4. The map data collection method according to claim 3, characterized in that: The step of constructing a weighted directed graph corresponding to the path planning point set according to the K target planning points included in the path planning point set includes: Performing deduplication processing on the K target planning points in the path planning point set, wherein the deduplication processing includes: retaining all target planning points located at intersections, and retaining any one of the multiple target planning points in the path planning point set that are not located at intersections and are located on the same direction section; According to the target planning point in the path planning point set after deduplication processing, a weighted directed graph corresponding to the path planning point set is constructed.

5. The map data collection method according to claim 3, characterized in that: The step of performing path planning on the sub-geographical area corresponding to the path planning point set according to the weighted directed graph to obtain the collection path includes: Get the number of starting points M and the number of end points N of the path planning, where M and N are both positive integers; Randomly select M vertices of the weighted directed graph as starting points, and randomly select N vertices other than the M vertices in the weighted directed graph as end points; Based on the M starting points and N end points in the weighted directed graph, path planning is performed on the sub-geographical area corresponding to the path planning point set to obtain the collection path.

6. The map data collection method according to claim 5, characterized in that: Based on the M starting points and the N end points in the weighted directed graph, path planning is performed on the sub-geographical area corresponding to the path planning point set to obtain the collection path, including: Based on the M starting points and N end points in the weighted directed graph, multiple path planning is performed on the sub-geographical area corresponding to the path planning point set to obtain multiple groups of paths, wherein each path planning corresponds to a group of paths, each group of paths includes at least one path, the starting point of each path is one of the M starting points, and the end point of the path is one of the N end points; At least one group of paths is selected from the multiple groups of paths based on a data collection target, and the paths included in the at least one group of paths are determined as the collection paths, wherein the data collection target is determined based on at least one of collection cost, collection efficiency and collection mileage.

7. The map data collection method according to claim 1, characterized in that: The multiple abnormal location points are obtained from at least one information source, and the information source includes a vehicle, an on-board device deployed on the vehicle, a computer terminal, and a map server; and / or, The abnormal location point includes at least one of the following: Geographical location points where actual data is inconsistent with map data in the target map; The geographical locations where road anomalies are actually observed; The user provides the geographical location where data collection is required.

8. The map data collection method according to claim 1, characterized in that: After performing path planning for the sub-geographical area corresponding to the path planning point set according to the K target planning points included in the path planning point set to obtain a collection path, the method further includes: Determine a data collection cost of a navigation path between a third abnormal location point and a target point, wherein the target point is a starting point or an end point of a path included in the collection path, and the third abnormal location point is an abnormal location point among the multiple abnormal location points that does not match an existing path in the target geographic area; According to the data collection cost of the navigation path between the third abnormal position point and the target point, the target point corresponding to the third abnormal position point is selected, and the third abnormal position point is used as an auxiliary collection point of the path where the selected target point is located.

9. An electronic device, characterized in that: include: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the map data collection method according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the map data collection method according to any one of claims 1 to 8 is implemented.

11. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the map data collection method as described in any one of claims 1 to 8.

Images