Map data matching methods, devices, equipment, media and products

Abstract

This application provides a map data matching method, apparatus, device, medium, and product. The method includes: reconstructing the road network between intersections in a fusion area of ​​high-precision map data and low-precision map data; dividing the data into several data processing scenarios based on the road attributes of each road in the road network; for each data processing scenario, matching the roads in the high-precision map data and the roads in the low-precision map data within the data processing scenario, and generating high- and low-precision map fusion data based on the matching results. On the one hand, by reconstructing the road network between intersections, the differences between the two data specifications on roads are weakened, effectively improving the matching efficiency of high- and low-precision data; on the other hand, by adopting a data layering processing method, the impact of different road attributes on matching is effectively reduced, improving the matching accuracy of high- and low-precision data, and the entire matching process does not require manual intervention, effectively reducing labor costs.

Description

Technical Field

[0001] This application relates to the field of high-precision map technology, and in particular to a map data matching method, apparatus, device, medium and product. Background Technology

[0002] With the development of intelligent driving technology, intelligent driving vehicles are increasingly inclined to use high-precision maps for positioning and planning.

[0003] However, since high-precision map data is not as widely available as ordinary low-precision map data, there are still many gaps in high-precision map data. Intelligent driving vehicles need to use a combination of high-precision and low-precision data to complete vehicle positioning and planning.

[0004] Currently, low-precision map data covers the entire country, and high-precision map data is also continuously increasing. However, the two data specifications differ in granularity and spatial location. For example, low-precision map data is based on road representation, while high-precision map data is based on lane representation. If simple road matching or manual matching is used to match the two types of map data, it will lead to problems such as high matching error rate, low matching efficiency, and high cost. Summary of the Invention

[0005] This application provides a map data matching method, apparatus, device, medium, and product to at least solve one of the above-mentioned technical problems.

[0006] According to a first aspect of this application, a map data matching method is provided, comprising:

[0007] The initial fusion area is determined based on the location areas of high-precision map data and low-precision map data.

[0008] Obtain the bounding rectangle corresponding to the location area of ​​the high-precision map data, and determine the final fusion area in the initial fusion area based on the bounding rectangle, so as to reconstruct the road network between intersections in the final fusion area;

[0009] Based on the road attributes of each road in the road network, several data processing scenarios are defined;

[0010] For each data processing scenario, the roads in the high-precision map data and the roads in the low-precision map data in the data processing scenario are matched, and high- and low-precision map fusion data is generated based on the matching results.

[0011] In one implementation, the reconstruction of the road network between intersections includes:

[0012] The intersections in the high-precision map data and the intersections in the low-precision map data are initialized as intersection points with the same representation, and the intersections and the road network between them are reconstructed based on the intersection points; and / or

[0013] Wherein, the road attributes include road type or road grade, and the step of dividing the data processing scenarios according to the road attributes of each road in the road network includes:

[0014] The number of data processing scenarios is determined based on the number of road types or road grades, and roads of the same type or grade in the road network are grouped into the same data processing scenario; and / or

[0015] The matching of roads in the high-precision map data and roads in the low-precision map data in the data processing scenario includes:

[0016] Identify the high-precision road strings to be matched in the high-precision map data in the data processing scenario;

[0017] Based on the start and end points of the high-precision road string to be matched, determine the low-precision road string in the low-precision map data that matches the high-precision road string to be matched; and match the roads in the high-precision road string to be matched with the roads in the low-precision road string.

[0018] In one implementation, after determining the high-precision road string to be matched in the high-precision map data, and before determining the low-precision road string in the low-precision map data that matches the high-precision road string to be matched based on the start and end points of the high-precision road string to be matched, the method further includes:

[0019] Select several candidate low-precision road strings from the preset buffer of the high-precision road string to be matched;

[0020] The step of determining the low-precision road string in the low-precision map data that matches the high-precision road string based on the start and end points of the high-precision road string to be matched includes:

[0021] Draw a starting point perpendicular line and an ending point perpendicular line along the crossing direction of the high-precision road string to be matched, respectively.

[0022] The intersection of the starting point vertical line and each candidate matching low-precision road string is determined as the starting point of each candidate matching low-precision road string.

[0023] The intersection of the endpoint vertical line and each candidate matching low-precision road string is determined as the endpoint of each candidate matching low-precision road string.

[0024] The starting point and the ending point of the stringing are strung together along the stringing direction of the high-precision road string to be matched, resulting in several matching low-precision road strings. Based on the several matching low-precision road strings, a low-precision road string that matches the high-precision road string to be matched is determined.

[0025] In one implementation, determining the low-precision road string that matches the high-precision road string to be matched based on the plurality of matching low-precision road strings includes:

[0026] When the plurality of matching low-precision road strings are equal to one, the matching low-precision road string is determined to be a low-precision road string that matches the high-precision road string to be matched.

[0027] When there is more than one matching low-precision road string, the matching low-precision road string with the shortest average distance between each discrete point in the matching low-precision road string and the high-precision road string to be matched is determined as the low-precision road string that matches the high-precision road string to be matched.

[0028] In one implementation, after matching roads in the high-precision map data and roads in the low-precision map data in the data processing scenario, and before generating high- and low-precision map fusion data based on the matching results, the method further includes:

[0029] Determine the mapping relationship between the roads in the high-precision road string to be matched and the roads in the corresponding low-precision road string;

[0030] Based on the mapping relationship, the percentage relationship between high-precision roads and low-precision roads in the fusion area is obtained. The percentage relationship is used to indicate the proportion of high-precision map data and low-precision map data on the corresponding roads.

[0031] The step of generating high- and low-precision map fusion data based on the matching results includes: generating high- and low-precision map fusion data based on the matching results and the percentage relationship.

[0032] In one implementation, determining the mapping relationship between roads in the high-precision road string to be matched and roads in the corresponding low-precision road string includes:

[0033] The first proportion data of each road node in the high-precision road string to be matched in the corresponding low-precision road string, and the second proportion data of each road node in the low-precision road string in the high-precision road string to be matched are determined respectively.

[0034] Based on the first ratio data and the second ratio data, the mapping relationship between the roads in the high-precision road string to be matched and the roads in the corresponding low-precision road string is determined.

[0035] According to a second aspect of this application, a map data matching apparatus is provided, comprising:

[0036] The road network reconstruction module is configured to determine an initial fusion region based on the location regions of high-precision map data and low-precision map data, obtain the bounding rectangle corresponding to the location region of the high-precision map data, and determine the final fusion region based on the bounding rectangle in the initial fusion region, so as to reconstruct the road network between intersections in the final fusion region.

[0037] The scene segmentation module is configured to divide several data processing scenes based on the road attributes of each road in the road network.

[0038] The matching module is configured to match roads in the high-precision map data and roads in the low-precision map data for each data processing scenario, and generate high- and low-precision map fusion data based on the matching results.

[0039] In one implementation, the road network reconstruction module is specifically configured to initialize intersections in the high-precision map data and intersections in the low-precision map data as intersection points with the same representation, and reconstruct the road network between intersections based on the intersection points; and / or

[0040] The road attributes include road type or road grade. Specifically, the scene module is configured to determine the number of data processing scenes based on the number of road types or road grades, and to group roads of the same type or grade in the road network into the same data processing scene; and / or

[0041] The matching module includes:

[0042] The first determining unit is configured to determine the high-precision road string to be matched in the high-precision map data in the data processing scenario.

[0043] The second determining unit is configured to determine, based on the start and end points of the high-precision road string to be matched, a low-precision road string in the low-precision map data that matches the high-precision road string to be matched; and,

[0044] The matching unit is configured to match the roads in the high-precision road string to be matched with the roads in the low-precision road string.

[0045] In one embodiment, the device further includes:

[0046] The selection module is configured to select several candidate low-precision road strings from a preset buffer of the high-precision road strings to be matched;

[0047] The second determining unit is specifically configured to: draw a starting point perpendicular line and an ending point perpendicular line along the threading direction of the high-precision road string to be matched, respectively; determine the intersection of the starting point perpendicular line with each candidate matching low-precision road string as the threading starting point of each candidate matching low-precision road string; determine the intersection of the ending point perpendicular line with each candidate matching low-precision road string as the threading ending point of each candidate matching low-precision road string; thread the threading starting point and the threading ending point along the threading direction of the high-precision road string to be matched to obtain several matching low-precision road strings, and determine the low-precision road string that matches the high-precision road string to be matched based on the several matching low-precision road strings.

[0048] In one implementation, determining the low-precision road string that matches the high-precision road string to be matched based on the plurality of matching low-precision road strings specifically involves: when there is only one matching low-precision road string, determining the matching low-precision road string as the low-precision road string that matches the high-precision road string to be matched; when there is more than one matching low-precision road string, determining the matching low-precision road string with the shortest average distance between each discrete point in the plurality of matching low-precision road strings and the high-precision road string to be matched as the low-precision road string that matches the high-precision road string to be matched.

[0049] In one embodiment, the device further includes:

[0050] The mapping relationship determination module is configured to determine the mapping relationship between roads in the high-precision road string to be matched and roads in the corresponding low-precision road string;

[0051] The percentage acquisition module is configured to acquire the percentage relationship between high-precision roads and low-precision roads in the fusion area based on the mapping relationship. The percentage relationship is used to indicate the proportion of high-precision map data and low-precision map data on the corresponding roads.

[0052] The matching module includes a fusion unit, which is configured to generate high- and low-precision map fusion data based on the matching result and the percentage relationship.

[0053] In one implementation, the mapping relationship determination module includes:

[0054] The ratio determination unit is configured to determine the first ratio data of each road node in the high-precision road string to be matched in the corresponding low-precision road string, and the second ratio data of each road node in the low-precision road string in the high-precision road string to be matched.

[0055] The mapping determination unit is configured to determine the mapping relationship between roads in the high-precision road string to be matched and roads in the corresponding low-precision road string based on the first proportional data and the second proportional data.

[0056] According to a third aspect of this application, an electronic device is provided, comprising: a processor, and a memory communicatively connected to the processor;

[0057] The memory stores computer-executed instructions;

[0058] The processor executes computer execution instructions stored in the memory to implement the map data matching method.

[0059] According to a fourth aspect of this application, a computer-readable storage medium is provided, wherein computer-executable instructions are stored therein, which, when executed by a processor, are used to implement the map data matching method described above.

[0060] According to a fifth aspect of this application, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the map data matching method.

[0061] The map data matching method, apparatus, device, medium, and product provided in this application reconstruct the road network between intersections in the fusion area of ​​high-precision map data and low-precision map data. Based on the road attributes of each road in the road network, several data processing scenarios are divided. Then, for each data processing scenario, roads in the high-precision map data and roads in the low-precision map data within that scenario are matched, and high- and low-precision map fusion data is generated based on the matching results. In this process, on the one hand, by reconstructing the road network between intersections, the differences between the two data specifications on roads are weakened, effectively improving the matching efficiency of high- and low-precision data; on the other hand, the use of a data layering processing method effectively reduces the impact of different road attributes on matching, improving the matching accuracy of high- and low-precision data. Furthermore, the entire matching process requires no manual intervention, effectively reducing labor costs. Attached Figure Description

[0062] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0063] Figure 1 This is a schematic diagram of a possible scenario provided for an embodiment of this application;

[0064] Figure 2 A flowchart illustrating a map data matching method provided in an embodiment of this application;

[0065] Figure 3a This is an example diagram of the initial fusion region in an embodiment of this application;

[0066] Figure 3b This is an example diagram of the final fusion region in the embodiments of this application;

[0067] Figure 4a This is an example diagram of the original road network in the existing technology;

[0068] Figure 4b This is an example diagram of the reconstructed road network in the embodiments of this application;

[0069] Figure 5a This is one of the example diagrams of a data processing scenario in the embodiments of this application;

[0070] Figure 5b This is the second example diagram of a data processing scenario in the embodiments of this application;

[0071] Figure 6 For this Figure 2 A flowchart illustrating step S203;

[0072] Figure 7 A flowchart illustrating another map data matching method provided in an embodiment of this application;

[0073] Figure 8 This is a schematic diagram of the structure of a map data matching device provided in an embodiment of this application;

[0074] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application;

[0075] Figure 10 This is a block diagram of a terminal device provided in an exemplary embodiment of this application.

[0076] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0077] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0078] The embodiments of this application will be explained below in conjunction with application scenarios. The map data matching method provided in the embodiments of this application can be applied to the application scenario of intelligent driving, and more specifically, it can be applied to the application scenario of autonomous driving based on vehicle cloud computing. For example, the execution subject of the method provided in the embodiments of this application can be a server, and more specifically, for example, the server of the map data provider. The following will introduce the method provided in the embodiments of this application as the execution subject of the server. Figure 1 This is a schematic diagram of a map data matching method provided in an embodiment of this application, such as... Figure 1 As shown, server 110 is connected to intelligent vehicle 120, first terminal 130 and second terminal 140 via network. Optionally, the first terminal provides high-precision map data to server 110, and the second terminal provides low-precision data to server 110. Server 110 matches the high-precision map data provided by first terminal 130 and the low-precision map data provided by second terminal 140 to generate high- and low-precision map fusion data. After generating the high-precision map fusion data, the high- and low-precision map fusion data can be transmitted to intelligent vehicle 120. Intelligent vehicle 120 uses the high- and low-precision map fusion data to assist in autonomous driving. Optionally, during driving, intelligent vehicle 120 can flexibly use the high-precision map data and low-precision map data in the fusion data to facilitate rapid switching between high-precision and low-precision in lane guidance and decision-making.

[0079] Server 110 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, and cloud computing. The first terminal 130 and the second terminal 140 can be computers, smartphones, tablets, e-book readers, Moving Picture Experts Group Audio Layer III (MP3) players, Moving Picture Experts Group Audio Layer IV (MP4) players, portable computers, in-vehicle computers, wearable devices, desktop computers, set-top boxes, smart TVs, etc.

[0080] In related technologies, the matching between high-precision map data and low-precision map data in the above process usually adopts simple road matching or manual matching methods. This method matches whether high-precision map data or low-precision map data is available for each road segment. However, since the two data specifications have differences in granularity and spatial location, such as low-precision map data being based on road representation and high-precision map data being based on lane representation, if simple road matching or manual matching is used to match the two types of map data, the matching time cost is too high. In addition, there are too many data scenarios and human subjective matching errors are uncontrollable. This will lead to problems such as high matching error rate, low matching efficiency, and high cost.

[0081] In view of this, embodiments of this application provide a map data matching method, apparatus, device, medium, and product. On the one hand, by reconstructing the road network between intersections in the fusion area of ​​high-precision map data and low-precision map data, the differences between the two data specifications on roads are weakened, effectively avoiding road matching within complex intersections and improving the matching efficiency of the skeleton road network. On the other hand, by utilizing the road attributes of each road in the road network to divide several data processing scenarios, and matching the roads in the high-precision map data and the roads in the low-precision map data for each data processing scenario, high- and low-precision map fusion data is generated. Through data layering processing, the impact of different road attributes on matching is effectively reduced, and the matching efficiency and accuracy of roads are effectively improved. In addition, the matching process of high- and low-precision map data does not require manual intervention, effectively reducing labor costs.

[0082] The technical solution of this application and how it solves the above-mentioned technical problems will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that these specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0083] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0084] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating a map data matching method provided in an embodiment of this application. Taking server 110 as an example, the method includes steps S201-S205.

[0085] Step S201: Determine the initial fusion area based on the location area of ​​the high-precision map data and the location area of ​​the low-precision map data.

[0086] Step S202: Obtain the bounding rectangle corresponding to the location area of ​​the high-precision map data, and determine the final fusion area in the initial fusion area based on the bounding rectangle, so as to reconstruct the road network between intersections in the final fusion area.

[0087] In this embodiment, the fusion area refers to the matching area between high-precision map data (hereinafter referred to as high-precision data) and low-precision map data (hereinafter referred to as low-precision data). Optionally, this matching area can be determined based on actual needs. For example, if researchers find that a certain location area contains high-precision data for a portion of the area and low-precision data for the entire area, this location area can be determined as the matching area. In other embodiments, it can also be determined directly based on the actual coverage area of ​​the high-precision map data. It is understood that currently, low-precision map data covers the entire country, while high-precision map data covers a portion of the country. The matching area can be divided based on this portion of the area. In the actual matching process of high-precision and low-precision data, high-precision map data can generally be matched with low-precision map data by province or part of the map sheet.

[0088] Understandably, high-precision maps refer to maps with higher requirements for detail and richness compared to ordinary maps (i.e., low-precision maps in this embodiment). Through networking, interaction, big data sharing and other methods, they have expanded into infinite possibilities. Currently, the main application environment of high-precision maps is to serve autonomous driving. In L2+ and above autonomous driving solutions, high-precision maps play an indispensable and important role.

[0089] In this embodiment, to improve the matching efficiency of high-precision and low-precision data, a certain data processing range is extracted as the final fusion region, and unnecessary data matching regions are removed to simplify the high-precision and low-precision data matching process. Combining steps S201 and S202:

[0090] Understandably, low-precision map data typically covers the entire country, while the location area of ​​high-precision map data is determined by the high-precision data acquisition or publishing platform. Therefore, in practical applications, the initial fusion area is primarily determined based on the location area of ​​the high-precision data. In some scenarios, such as certain abandoned areas that may not be covered by low-precision map data, data fusion in these areas is meaningless and therefore not included as initial fusion areas, effectively reducing the matching workload.

[0091] In this embodiment, the bounding rectangle, or minimum bounding rectangle, is obtained by acquiring the minimum bounding rectangle corresponding to the location area of ​​the high-precision map data. This ensures that the final fused area includes the location areas of all high-precision map data, as well as some low-precision map data. Excess low-precision map data is truncated, thus removing unnecessary data matching areas and extracting the smallest matching area range, effectively simplifying the high-precision / low-precision matching process. Combined with... Figure 3a and Figure 3b As shown, where Figure 3a This is an example of the initial fusion region. Figure 3b This is the final merged region after extraction in this example.

[0092] In some embodiments, in addition to the above methods, the initial fusion region can also be predetermined by the user. This initial fusion location region carries high-precision map data and low-precision map data. The server obtains the predetermined initial fusion region, then calculates the bounding rectangle of the location region of the high-precision map data in the initial fusion region, and determines the final fusion region based on the bounding rectangle.

[0093] Furthermore, the reconstruction of the road network between intersections in step S202 above may include the following steps:

[0094] The intersections in the high-precision map data and the intersections in the low-precision map data are initialized as intersection points with the same expression form, and the intersections and the road network between the intersections are reconstructed based on the intersection points.

[0095] Because high-precision and low-precision data differ in their representation of roads—low-precision data is based on roads, while high-precision data is based on lanes—the differences are particularly significant at intersections. This embodiment abstracts intersections in both high-precision and low-precision data into intersection points with the same representation and reconstructs the road network, thus mitigating the differences between the two data specifications on roads. This effectively avoids road matching at complex intersections and improves the matching efficiency of the skeleton road network.

[0096] Combination Figure 4a and Figure 4b As shown, Figure 4a This is the original road network. Lighter colored dots represent intersections with low-precision data, while darker colored dots represent intersections with high-precision data. Figure 4b The diagram shows the reconstructed road network, with road intersections represented as abstracted road junctions. As can be seen, the reconstructed road network significantly simplifies the road complexity between high-precision and low-precision data, thereby improving the matching efficiency between the two datasets.

[0097] Step S203: Divide the data processing scenarios into several categories based on the road attributes of each road in the road network.

[0098] Understandably, while high-precision and low-precision data may represent roads differently, the essential elements of a road (i.e., road attributes) are not lost. Road attributes include road grade, road type, direction of traffic, width, name, and traffic restrictions. Road grades can be categorized as expressways, arterial roads, secondary arterial roads, and local roads. Road types, based on their usage characteristics, can be classified as highways, urban roads, rural roads, industrial and mining roads, and forestry roads.

[0099] In this embodiment, several data processing scenarios are divided according to the road data in the road network to achieve hierarchical processing of data matching. This can effectively reduce the impact of different geometric elements on matching and greatly improve the accuracy and efficiency of road matching.

[0100] In one implementation, if the road attributes include road type or road grade, then step S202, which divides the data processing scenarios according to the road attributes of each road in the road network, may include the following steps:

[0101] The number of data processing scenarios is determined based on the number of road types or road grades, and roads of the same type or road grade in the road network are assigned to the same data processing scenario.

[0102] In other words, the number of road attributes existing in the integrated area can be used to stratify the area into layers, combined with... Figure 5a and Figure 5b As shown, Figure 5a and Figure 5b Examples of two layered scenarios (i.e., data scenarios) are shown. The dark lines represent high-precision data in the layered data processing scenario, while the light lines represent low-precision data. It can be seen that these two figures are data that are layered and superimposed based on the elements.

[0103] Step S204: For each data processing scenario, match the roads in the high-precision map data and the roads in the low-precision map data in the data processing scenario; and Step S205: Generate high- and low-precision map fusion data based on the matching results.

[0104] In this embodiment, high-precision data and low-precision data are matched for each data processing scenario. Specifically, the roads in the high-precision data and the roads in the low-precision data are matched. The matching result includes whether the corresponding road has high-precision data or low-precision data. High-precision data is used for roads that have both high-precision and low-precision data. Low-precision data is fused for roads that do not have high-precision data. High-precision and low-precision map fusion data is generated based on the matching result so that the driving vehicle can quickly switch between high-precision and low-precision data in lane guidance and decision-making.

[0105] In one implementation, to further improve the matching efficiency of high-precision and low-precision data, matching is performed by determining the high-precision road strings and low-precision road strings to be matched. Specifically, in step S204, the process of matching roads in the high-precision map data and the roads in the low-precision map data in the data processing scenario is as follows: Figure 6 As shown, the following steps may be included:

[0106] Step S204a: Determine the high-precision road string to be matched in the high-precision map data in the data processing scenario;

[0107] Step S204b: Determine the low-precision road string in the low-precision map data that matches the high-precision road string to be matched based on the start and end points of the high-precision road string to be matched; and Step S204c: Match the roads in the high-precision road string to be matched with the roads in the low-precision road string.

[0108] In one implementation, one or more roads from intersection to intersection (intersection point) in the high-precision map data can be identified as the high-precision road string to be matched. Then, based on the start and end points of the high-precision road string, a matching low-precision road string is determined, and the roads in the high-precision road string to be matched and the roads in the low-precision road string are matched. Optionally, the start and end points of the low-precision data can be determined by drawing perpendicular lines based on the start and end points of the high-precision road string, and then performing string crossing processing to determine the low-precision road string. This has been detailed later and will not be repeated here. It is understood that the high-precision road string to be matched can be one or more, and some roads in the high-precision road string to be matched may not have high-precision data. In this case, the corresponding low-precision data needs to be merged, and the corresponding low-precision road string can also be one or more.

[0109] In practical applications, since road data is usually numerous and complex, using a one-to-one road matching method will inevitably result in low matching efficiency between high-precision data and low-precision data. In this embodiment, by using a matching method between road strings in the matching process of high-precision data and low-precision data, the matching efficiency between high-precision data and low-precision data can be effectively improved.

[0110] In one implementation, after determining the high-precision road string to be matched in the high-precision map data, and before determining the low-precision road string in the low-precision map data that matches the high-precision road string to be matched based on the start and end points of the high-precision road string to be matched, the following step may be included: selecting a number of candidate matching low-precision road strings in a preset buffer of the high-precision road string to be matched.

[0111] It should be noted that those skilled in the art can adaptively set the preset buffer based on practical applications and existing technologies. In one implementation, the preset buffer for the high-precision road string to be matched can be a rectangular region surrounding the high-precision road string to be matched. The length of this rectangular region can be determined according to the length of the high-precision road string to be matched, and the width can be set to about 15m. Candidate low-precision road strings that coincide with the position of the high-precision road string to be matched are searched in this buffer region. In some embodiments, the preset buffer can also be a circular region or an elliptical region, or other forms of region. This embodiment does not specifically limit this.

[0112] The step of determining the low-precision road string in the low-precision map data that matches the high-precision road string based on the start and end points of the high-precision road string to be matched may specifically include the following steps:

[0113] Draw a starting point perpendicular line and an ending point perpendicular line along the crossing direction of the high-precision road string to be matched, respectively.

[0114] The intersection of the starting point vertical line and each candidate matching low-precision road string is determined as the starting point of each candidate matching low-precision road string.

[0115] The intersection of the endpoint vertical line and each candidate matching low-precision road string is determined as the endpoint of each candidate matching low-precision road string.

[0116] The starting point and the ending point of the stringing are strung together along the stringing direction of the high-precision road string to be matched, resulting in several matching low-precision road strings. Based on the several matching low-precision road strings, a low-precision road string that matches the high-precision road string to be matched is determined.

[0117] In practical applications, there are usually multiple low-precision road strings falling within the buffer area of ​​the high-precision road string to be matched, and these low-precision road strings may be relatively short. To improve matching efficiency and accuracy, this embodiment finds a low-precision road string whose length matches the high-precision road string to be matched. That is, the starting point and ending point of the high-precision road string to be matched are drawn along the crossing direction. The candidate matching low-precision road string where the starting point perpendicular line falls is taken as the crossing starting point, and the candidate matching low-precision road string where the ending point perpendicular line falls is taken as the crossing ending point. The candidate matching low-precision road strings are then crossed along the crossing direction of the high-precision road string to be matched, based on the crossing starting point and crossing ending point. This yields one or more matching low-precision road strings that match the length of the high-precision road string to be matched, and the final low-precision road string is then determined.

[0118] As can be understood, in this embodiment, the direction of the high-precision road string to be matched is the direction of the road string.

[0119] Furthermore, considering that there may be more than one matching low-precision road string, in order to further improve the matching accuracy of high-precision and low-precision data, the matching low-precision road string with the shortest average distance between each discrete point and the high-precision road string to be matched is selected as the low-precision road string that matches the high-precision road string to be matched. Specifically, the step of determining the low-precision road string that matches the high-precision road string to be matched based on the several matching low-precision road strings may include the following steps:

[0120] When the plurality of matching low-precision road strings are equal to one, the matching low-precision road string is determined to be a low-precision road string that matches the high-precision road string to be matched.

[0121] When there is more than one matching low-precision road string, the matching low-precision road string with the shortest average distance between each discrete point in the matching low-precision road string and the high-precision road string to be matched is determined as the low-precision road string that matches the high-precision road string to be matched.

[0122] As is understandable, discrete points are the discrete points of the road string. The matching low-precision road is obtained by connecting the starting point and ending point of the perpendicular line. After connecting the lines, the matching low-precision road string has discrete points, that is, the corresponding matching low-precision road string has a certain deviation. In this embodiment, by selecting the matching low-precision road string with the shortest average distance between each discrete point in the matching low-precision road string and the high-precision road string to be matched, the matching low-precision road string to be matched can be effectively improved.

[0123] Please refer to Figure 7 , Figure 7 This application provides another map data matching method. Based on the above embodiments, this embodiment obtains the percentage relationship between high-precision map data and low-precision map data to indicate the proportion of high-precision map data and low-precision map data on the corresponding road. When using high-precision and low-precision fused data, users can quickly make switching decisions based on this percentage relationship, improving the user's map data experience. Specifically, in addition to the above steps S201-S205, after matching the roads in the high-precision map data and the roads in the low-precision map data in the data processing scenario in step S204, and before generating high-precision and low-precision fused data based on the matching results in step S205, this embodiment also includes the following steps S701 and S702, and further divides step S205 into step S205a.

[0124] Step S701: Determine the mapping relationship between the roads in the high-precision road string to be matched and the roads in the corresponding low-precision road string.

[0125] It is understandable that the mapping relationship between roads in this embodiment is the matching relationship between high-precision roads and low-precision roads, meaning that roads simultaneously contain both high-precision and low-precision data.

[0126] In one implementation, the mapping relationship between roads is determined using the proportion data of road nodes in the road string. Specifically, step S701, which determines the mapping relationship between roads in the high-precision road string to be matched and roads in the corresponding low-precision road string, may include the following steps:

[0127] The first proportion data of each road node in the high-precision road string to be matched in the corresponding low-precision road string, and the second proportion data of each road node in the low-precision road string in the high-precision road string to be matched are determined respectively.

[0128] Based on the first ratio data and the second ratio data, the mapping relationship between the roads in the high-precision road string to be matched and the roads in the corresponding low-precision road string is determined.

[0129] In this embodiment, a road node is a node in a road string that intersects with other roads. The mapping relationship between high-precision and low-precision roads is determined by determining the proportion of each road node in the high-precision road string to be matched within its corresponding low-precision road string, and the proportion of each road node in the low-precision road string within the high-precision road string. In one implementation, if the proportion of a road node is the same in both the high-precision and low-precision road strings, it indicates that the corresponding road segment is mapped in both strings; otherwise, there is no mapping relationship.

[0130] It is understood that the high-precision road string in this embodiment may include roads that do not have high-precision data, and each road node in the high-precision road string in this embodiment is a road node of a road that has high-precision data.

[0131] It should be noted that the first and second ratio data in this embodiment are only used to distinguish similar objects and have no other special meaning. The first and second ratio data can be the same ratio data or different ratio data.

[0132] Step S702: Based on the mapping relationship, obtain the percentage relationship between high-precision roads and low-precision roads in the fusion area. The percentage relationship is used to indicate the proportion of high-precision map data and low-precision map data on the corresponding roads.

[0133] Specifically, a path with a mapping relationship has both high-precision and low-precision data, while a path without a mapping relationship has only low-precision data or only high-precision data. Understandably, in practical applications, the possibility of having only high-precision data is almost zero. A high-precision path is one that has either high-precision data or both high-precision and low-precision data, while a low-precision path is one that has only low-precision data.

[0134] Step S205a: Generate high- and low-precision map fusion data based on the matching results and the percentage relationship.

[0135] In this embodiment, the generated high-precision and low-precision map fusion data carries the percentage relationship between high-precision and low-precision roads in the fusion area. When using the high-precision and low-precision map fusion data, the server can use this percentage relationship to remind the user in advance of the proportion of high-precision and low-precision data for the road ahead. In some embodiments, this percentage relationship can also be displayed in the high-precision and low-precision map fusion data, allowing the user to intuitively see the corresponding percentage relationship on the map while using the high-precision and low-precision map fusion data, thereby further realizing flexible switching between high-precision and low-precision data.

[0136] This application also provides a schematic diagram of the structure of a map data matching device, as shown in the embodiments below. Figure 8 As shown, it includes a road network reconstruction module 81, a scene segmentation module 82, and a matching module 83, wherein,

[0137] The road network reconstruction module 81 is configured to determine an initial fusion region based on the location regions of high-precision map data and low-precision map data, obtain the bounding rectangle corresponding to the location region of the high-precision map data, and determine the final fusion region based on the bounding rectangle in the initial fusion region, so as to reconstruct the road network between intersections in the final fusion region.

[0138] The scene segmentation module 82 is configured to divide several data processing scenes according to the road attributes of each road in the road network.

[0139] The matching module 83 is configured to match the roads in the high-precision map data and the roads in the low-precision map data in each data processing scenario, and generate high- and low-precision map fusion data based on the matching results.

[0140] In one embodiment, the road network reconstruction module 81 is specifically configured to initialize the intersections in the high-precision map data and the intersections in the low-precision map data as intersection points with the same expression form, and reconstruct the road network between the intersections based on the intersection points.

[0141] In one implementation, the road attributes include road type or road grade, and the scene module 82 is specifically configured to determine the number of data processing scenes based on the number of road types or road grades, and to classify roads of the same road type or road grade in the road network into the same data processing scene.

[0142] In one embodiment, the matching module 83 includes:

[0143] The first determining unit is configured to determine the high-precision road string to be matched in the high-precision map data in the data processing scenario.

[0144] The second determining unit is configured to determine, based on the start and end points of the high-precision road string to be matched, a low-precision road string in the low-precision map data that matches the high-precision road string to be matched; and,

[0145] The matching unit is configured to match the roads in the high-precision road string to be matched with the roads in the low-precision road string.

[0146] In one embodiment, the device further includes:

[0147] The selection module is configured to select several candidate low-precision road strings from a preset buffer of the high-precision road strings to be matched;

[0148] The second determining unit is specifically configured to: draw a starting point perpendicular line and an ending point perpendicular line along the threading direction of the high-precision road string to be matched, respectively; determine the intersection of the starting point perpendicular line with each candidate matching low-precision road string as the threading starting point of each candidate matching low-precision road string; determine the intersection of the ending point perpendicular line with each candidate matching low-precision road string as the threading ending point of each candidate matching low-precision road string; thread the threading starting point and the threading ending point along the threading direction of the high-precision road string to be matched to obtain several matching low-precision road strings, and determine the low-precision road string that matches the high-precision road string to be matched based on the several matching low-precision road strings.

[0149] In one implementation, determining the low-precision road string that matches the high-precision road string to be matched based on the plurality of matching low-precision road strings specifically involves: when there is only one matching low-precision road string, determining the matching low-precision road string as the low-precision road string that matches the high-precision road string to be matched; when there is more than one matching low-precision road string, determining the matching low-precision road string with the shortest average distance between each discrete point in the plurality of matching low-precision road strings and the high-precision road string to be matched as the low-precision road string that matches the high-precision road string to be matched.

[0150] In one embodiment, the device further includes:

[0151] The mapping relationship determination module is configured to determine the mapping relationship between roads in the high-precision road string to be matched and roads in the corresponding low-precision road string;

[0152] The percentage acquisition module is configured to acquire the percentage relationship between high-precision roads and low-precision roads in the fusion area based on the mapping relationship. The percentage relationship is used to indicate the proportion of high-precision map data and low-precision map data on the corresponding roads.

[0153] The matching module 83 includes a fusion unit, which is configured to generate high- and low-precision map fusion data based on the matching result and the percentage relationship.

[0154] In one implementation, the mapping relationship determination module includes:

[0155] The ratio determination unit is configured to determine the first ratio data of each road node in the high-precision road string to be matched in the corresponding low-precision road string, and the second ratio data of each road node in the low-precision road string in the high-precision road string to be matched.

[0156] The mapping determination unit is configured to determine the mapping relationship between roads in the high-precision road string to be matched and roads in the corresponding low-precision road string based on the first proportional data and the second proportional data.

[0157] For relevant instructions, please refer to the corresponding text. Figures 2-7 The relevant descriptions and effects of the steps in the corresponding embodiments are understood, and will not be elaborated on here.

[0158] Please refer to Figure 9 , Figure 9 An electronic device provided in the embodiments of this application, such as Figure 9 As shown, it includes: a processor 91, and a memory 92 communicatively connected to the processor 91;

[0159] The memory 91 stores computer-executed instructions;

[0160] The processor 92 executes computer execution instructions stored in the memory 91 to implement the map data matching method, wherein the memory 92 and the processor 91 are connected via a bus 93.

[0161] For relevant instructions, please refer to the corresponding text. Figures 2-7 The relevant descriptions and effects of the steps in the corresponding embodiments are understood, and will not be elaborated on here.

[0162] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the map data matching method.

[0163] For relevant instructions, please refer to the corresponding text. Figures 2-7 The relevant descriptions and effects of the steps in the corresponding embodiments are understood, and will not be elaborated on here.

[0164] This application also provides a computer program product, including a computer program that implements the map data matching method when executed by a processor.

[0165] For relevant instructions, please refer to the corresponding text. Figures 2-7 The relevant descriptions and effects of the steps in the corresponding embodiments are understood, and will not be elaborated on here.

[0166] This application also provides a chip, including a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory to execute the map data matching method.

[0167] For relevant instructions, please refer to the corresponding text. Figures 2-7 The relevant descriptions and effects of the steps in the corresponding embodiments are understood, and will not be elaborated on here.

[0168] The computer-readable storage medium can be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0169] Figure 10 This is a block diagram illustrating an exemplary embodiment of the present application of a terminal device 800, which may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness device, personal digital assistant, etc.

[0170] The terminal device 800 may include one or more of the following components: processing component 802, memory 804, power supply component 806, multimedia component 808, audio component 810, input / output (I / O) interface 812, sensor component 814, and communication component 816.

[0171] Processing component 802 typically controls the overall operation of terminal device 800, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the methods described above. Furthermore, processing component 802 may include one or more modules to facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.

[0172] Memory 804 is configured to store various types of data to support operation on terminal device 800. Examples of this data include instructions for any application or method operating on terminal device 800, contact data, phonebook data, messages, pictures, videos, etc. Memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0173] Power supply component 806 provides power to various components of terminal device 800. Power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to terminal device 800.

[0174] Multimedia component 808 includes a screen that provides an output interface between terminal device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 808 includes a front-facing camera and / or a rear-facing camera. When terminal device 800 is in an operating mode, such as a shooting mode or video mode, the front-facing camera and / or rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0175] Audio component 810 is configured to output and / or input audio signals. For example, audio component 810 includes a microphone (MIC) configured to receive external audio signals when terminal device 800 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 804 or transmitted via communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

[0176] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0177] Sensor assembly 814 includes one or more sensors for providing status assessments of various aspects of terminal device 800. For example, sensor assembly 814 can detect the on / off state of terminal device 800, the relative positioning of components such as the display and keypad of terminal device 800, changes in the position of terminal device 800 or a component of terminal device 800, the presence or absence of user contact with terminal device 800, the orientation or acceleration / deceleration of terminal device 800, and temperature changes of terminal device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 814 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0178] Communication component 816 is configured to facilitate wired or wireless communication between terminal device 800 and other devices. Terminal device 800 can access wireless networks based on communication standards, such as WiFi, 3G, 4G, 5G, or other standard communication networks, or combinations thereof. In one exemplary embodiment, communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 816 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0179] In an exemplary embodiment, the terminal device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the functions described in this application. Figures 2-7 The method provided in any of the corresponding embodiments.

[0180] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, which can be executed by a processor 820 of a terminal device 800 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0181] This application also provides a non-transitory computer-readable storage medium, which, when the instructions in the storage medium are executed by the processor of a terminal device, enables the terminal device 800 to perform the above-described embodiments of this application. Figures 2-7 The method provided in any of the corresponding embodiments.

[0182] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0183] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0184] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A map data matching method characterized by, The method comprises the following steps: determining an initial fusion area based on a location area of high-definition map data and a location area of low-definition map data; obtaining an external rectangular frame corresponding to the location area of the high-definition map data, and determining a final fusion area in the initial fusion area based on the external rectangular frame, so as to reconstruct a road network between intersections in the final fusion area; dividing a plurality of data processing scenes according to road attributes of roads in the road network; for each data processing scene, matching roads in the high-definition map data and roads in the low-definition map data in the data processing scene, and generating high-low-definition map fusion data according to the matching result.

2. The method of claim 1, wherein, The method of reconstructing the road network between intersections comprises the following steps: initializing intersections in the high-definition map data and intersections in the low-definition map data into intersection points with the same expression form respectively, and reconstructing the road network between intersections according to the intersection points; wherein the road attributes include road types or road levels, and the method of dividing a plurality of data processing scenes according to road attributes of roads in the road network comprises the following steps: determining the number of data processing scenes according to the number of road types or road levels, and dividing roads with the same road type or the same road level in the road network into the same data processing scene; the method of matching roads in the high-definition map data and roads in the low-definition map data in the data processing scene comprises the following steps: determining a to-be-matched high-definition road string in the high-definition map data in the data processing scene; determining a low-definition road string matched with the to-be-matched high-definition road string in the low-definition map data based on the start point and the end point of the to-be-matched high-definition road string, and matching roads in the to-be-matched high-definition road string with roads in the low-definition road string.

3. The method of claim 2, wherein, After determining the to-be-matched high-definition road string in the high-definition map data, and before determining the low-definition road string matched with the to-be-matched high-definition road string in the low-definition map data based on the start point and the end point of the to-be-matched high-definition road string, the method further comprises the following steps: selecting a plurality of candidate matching low-definition road strings in a preset buffer area of the to-be-matched high-definition road string; the method of determining the low-definition road string matched with the to-be-matched high-definition road string in the low-definition map data based on the start point and the end point of the to-be-matched high-definition road string comprises the following steps: drawing a start point vertical line and an end point vertical line along the string-through direction of the to-be-matched high-definition road string respectively from the start point and the end point of the to-be-matched high-definition road string; determining the intersection of the start point vertical line and each candidate matching low-definition road string as the string-through start point of each candidate matching low-definition road string; determining the intersection of the end point vertical line and each candidate matching low-definition road string as the string-through end point of each candidate matching low-definition road string; stringing through the string-through start point and the string-through end point along the string-through direction of the to-be-matched high-definition road string to obtain a plurality of matching low-definition road strings, and determining the low-definition road string matched with the to-be-matched high-definition road string based on the plurality of matching low-definition road strings.

4. The method of claim 3, wherein, The determining the low-precision road string matched with the high-precision road string to be matched based on the plurality of matched low-precision road strings comprises: When the plurality of matched low-precision road strings is one, the matched low-precision road string is determined as the low-precision road string matched with the high-precision road string to be matched; When the plurality of matched low-precision road strings is more than one, the matched low-precision road string with the shortest average distance between each discrete point in the plurality of matched low-precision road strings and the high-precision road string to be matched is determined as the low-precision road string matched with the high-precision road string to be matched.

5. The method according to any one of claims 2 to 4, characterized in that, After matching the roads in the high-precision map data and the low-precision map data in the data processing scene, and before generating the high-low precision map fusion data according to the matching result, the method further comprises: determining the mapping relationship between the road in the high-precision road string to be matched and the road in the corresponding low-precision road string; obtaining the percentage relationship between the high-precision road and the low-precision road in the fusion area based on the mapping relationship, the percentage relationship being used to prompt the proportion of the high-precision map data and the low-precision map data on the corresponding road; and the generating the high-low precision map fusion data according to the matching result comprises: generating the high-low precision map fusion data according to the matching result and the percentage relationship.

6. The method of claim 5, wherein, The determining the mapping relationship between the road in the high-precision road string to be matched and the road in the corresponding low-precision road string comprises: respectively determining the first proportion data of each road node in the high-precision road string to be matched in the corresponding low-precision road string, and the second proportion data of each road node in the low-precision road string in the high-precision road string to be matched; determining the mapping relationship between the road in the high-precision road string to be matched and the road in the corresponding low-precision road string based on the first proportion data and the second proportion data.

7. A map data matching apparatus characterized by comprising: comprises: a road network reconstruction module configured to reconstruct a road network between intersections in a fusion area of high-precision map data and low-precision map data; a scene division module configured to divide a plurality of data processing scenes according to road attributes of roads in the road network; a matching module configured to match roads in high-precision map data and roads in low-precision map data in each data processing scene, and generate high-low precision map fusion data according to a matching result.

8. An electronic device comprising: a processor, and a memory in communication connection with the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the map data matching method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to implement the map data matching method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program, when executed by the processor, implements the map data matching method according to any one of claims 1 to 6.

Images