Data processing method, device and electronic equipment for generating lane-level map

Abstract

The present disclosure provides a data processing method and device, electronic equipment and storage medium for generating a lane-level map, relating to the technical field of artificial intelligence. The specific implementation scheme is: obtaining road data of an original map, a target road level and a target kilometer number; performing road segmentation on the road data based on the target road level to generate a work unit; clustering the work unit based on the target kilometer number to obtain a work material package; and outputting the work material package. The present disclosure does not require manual segmentation of the road data of the original map, thereby solving the technical problem of low lane-level map generation efficiency in related technologies, and further achieving the technical effect of improving the lane-level map generation efficiency.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of artificial intelligence, and in particular, to a data processing method and device for generating a lane-level map, an electronic device, and a storage medium. BACKGROUND

[0002] With increasingly complex roads and increasingly mature autonomous driving technology, traditional map data has long been unable to meet user needs, and the market demand for lane-level navigation maps is growing. However, the generation of existing lane-level navigation maps requires manual extraction and distribution of work materials, which has the technical problem of low efficiency. SUMMARY

[0003] The present disclosure provides a data processing method and device for generating a lane-level map, an electronic device, and a storage medium.

[0004] According to an aspect of the present disclosure, a data processing method for generating a lane-level map is provided, comprising: obtaining road data of an original map, a target road level, and a target kilometer number; performing road segmentation on the road data based on the target road level to generate a work unit, wherein the work unit contains part of the roads in the original map; clustering the work unit based on the target kilometer number to obtain a work material package, wherein the first kilometer number of all roads in the work material package matches the target kilometer number; and outputting the work material package.

[0005] According to another aspect of the present disclosure, a data processing device for generating a lane-level map is provided, comprising: an acquisition module configured to obtain road data of an original map, a target road level, and a target kilometer number; a segmentation module configured to perform road segmentation on the road data based on the target road level to generate a work unit, wherein the work unit contains part of the roads in the original map; a clustering module configured to cluster the work unit based on the target kilometer number to obtain a work material package, wherein the first kilometer number of all roads in the work material package matches the target kilometer number; and an output module configured to output the work material package.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform any one of the above-described data processing methods for generating a lane-level map.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to perform any one of the above-described data processing methods for generating a lane-level map.

[0008] According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements any of the above-described methods for generating a lane-level map.

[0009] The above-described embodiments of the present disclosure can improve the efficiency of lane-level map generation.

[0010] It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0011] The accompanying drawings are used to better understand the present scheme and do not limit the present disclosure. Among them:

[0012] Figure 1 is a flowchart of a data processing method for generating a lane-level map according to an embodiment of the present disclosure;

[0013] Figure 2A is a first schematic diagram of the spatial relationship between a lane and a road in an embodiment of the present disclosure;

[0014] Figure 2B is a second schematic diagram of the spatial relationship between a lane and a road according to an embodiment of the present disclosure;

[0015] Figure 3A is a schematic diagram of selecting a road section as a splitting position;

[0016] Figure 3B is a schematic diagram of selecting an intersection as a splitting position;

[0017] Figure 4A is a first schematic diagram of a splitting position in an embodiment of the present disclosure;

[0018] Figure 4B is a first schematic diagram of a splitting position in an embodiment of the present disclosure;

[0019] Figure 4C is a first schematic diagram of a splitting position in an embodiment of the present disclosure;

[0020] Figure 5 is a schematic diagram of a plurality of grids in an embodiment of the present disclosure;

[0021] Figure 6 is a first schematic diagram of a map corresponding to a work package of the present disclosure;

[0022] Figure 7 is a second schematic diagram of a map corresponding to a work package of the present disclosure;

[0023] Figure 8 This is a flowchart of a data processing method for generating lane-level maps according to a preferred embodiment of the present disclosure;

[0024] Figure 9 This is a schematic diagram of the structure of a data processing apparatus for generating lane-level maps according to an embodiment of the present disclosure;

[0025] Figure 10 A schematic block diagram of an example electronic device 1000 that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0026] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0027] First, some nouns or terms that appear in the description of the embodiments of this disclosure shall be interpreted as follows:

[0028] Lane-level maps, also known as lane-level navigation maps, are high-precision maps that depict lane groups, lane center lines, lane dividers, and lane boundary lines on roads. Furthermore, they offer significantly higher accuracy than traditional maps, with an absolute error margin of less than 0.2 meters.

[0029] A lane group is defined as one or more lanes at one entrance of an intersection that serve one or more traffic flows.

[0030] The Fraser distance can be used to describe the similarity of path spaces.

[0031] A road with separate lanes for left and right traffic, also known as a split road, is a highway where the left and right lanes are built separately and a median strip is set between the left and right lanes.

[0032] An intersection with separate upper and lower lanes indicates an intersection composed of roads with separate upper and lower lanes.

[0033] In the existing generation process of lane-level navigation map, all the work materials need to be manually extracted by the work group leader relying on personal experience, and the work materials are manually divided into work units according to a certain kilometer number and given to the work personnel for subsequent map drawing. However, this manual division of work units will increase the workload of edge connection, and it is difficult to grasp the work progress of the work personnel. In addition, if the work group leader or the work personnel makes a mistake in the distribution process, it is very difficult to find out, and a lot of manpower may be needed to make up for it later. Therefore, the prior art has the technical problems of low generation efficiency and high cost.

[0034] To solve the above technical problems, the present disclosure provides a data processing method, device, electronic equipment and storage medium which can improve the efficiency of lane-level map generation.

[0035] Figure 1 is a flowchart of a data processing method for generating a lane-level map according to an embodiment of the present disclosure, as shown in Figure 1 The method comprises the following steps:

[0036] Step S102, acquiring road data of an original map, a target road level and a target kilometer number.

[0037] Specifically, the above-mentioned original map can be a traditional electronic navigation map, which has lower precision compared with the lane-level navigation map. The road data can be the road data contained in the original map, including but not limited to road level, lane group, association relationship between lane group and road, road length, road name and road capacity level data, etc.

[0038] The road level is used to represent the classification of the road, for example: a number can be used to represent the classification of the road, “0” represents that the road is under construction, “1” represents that the road is a “highway”, “2” represents that the road is a “city expressway”, “3” represents that the road is a national road or a city main trunk road, “4” represents that the road is a provincial road or a city trunk road, “5” represents that the road is a reserved road, “6” represents that the road is a county road or a city secondary road, “7” represents that the road is a township and village road or a city branch road, “8” represents that the road is other road, “9” represents that the road is a special service road, “10” represents that the road is a pedestrian road, and “11” represents that the road is a human crossing road. The target road level can be the road level of the main road required to be displayed in the lane-level map generated this time, and the target road level can be manually specified according to actual needs, for example, the user requires that the lane-level map can display roads with road levels of highway, city trunk road, national road, county road and reserved road. The target kilometer number can be the total kilometer number of the road in the material package allocated to each work personnel this time.

[0039] In an alternative embodiment, the job group leader can select the electronic navigation map required for the job task from the map database, manually set the target road level and target mileage, and then upload the data to the server, so that the server automatically generates the job material package.

[0040] In step S104, the road data is segmented based on the target road level to generate a job unit, wherein the job unit contains part of the road in the original map.

[0041] Specifically, the job unit can essentially represent the smallest unit of information that cannot be divided.

[0042] Before performing road segmentation, in order to avoid repeated work, the target road data is obtained by removing the road data that already has lane data, and then extracting the target job material from the target road data based on the pre-set target road level. Then, the target job material is segmented based on the pre-set segmentation rule to obtain the job unit.

[0043] In an alternative embodiment, as shown in Figure 2A and Figure 2B , the rectangle represents the road, and the line segment with an arrow represents the lane group, wherein the arrow represents the direction of the vehicle on the lane group, and the spatial relationship between the lane group and the road is generally divided into two types, as shown in Figure 2A , the lane group is located in the road, and as shown in Figure 2B , the lane group is separated from the road, therefore, in the present disclosure, whether the lane data is the lane data already existing in the road data of the original map is determined by the following method: obtaining the association relationship between the road and the lane group in the road data, determining the coverage ratio of the lane group on the road where the lane group is located, if the coverage ratio meets the pre-set threshold, the road is considered as an existing road, if the coverage ratio is lower than the pre-set threshold, the road still needs to be drawn and the specific lane group information is added, therefore, the road data of the road belongs to the target material. In addition, the coverage ratio of the lane group on the road where the lane group is located can be obtained by the following method: first, projecting the starting position and the ending position of the lane group onto the road where the lane group is located, then obtaining the length between the projection position of the starting position and the projection position of the terminal position, i.e. the projection length of the lane group, and then dividing the projection length of the lane group by the length of the road to obtain the above-mentioned coverage ratio.

[0044] In an optional embodiment, the extracting the target work data from the target road level comprises: extracting a target main road from the target road data according to the target road level, and extracting the target road data according to a preset range of the target main road to obtain an initial auxiliary road. It should be noted that the preset range of the target main road can be the target auxiliary road level data corresponding to the target main road. Then, it is determined whether the initial auxiliary road has an auxiliary road name. If the initial auxiliary road has an auxiliary road name, the initial auxiliary road name and the main road name of the target main road are filtered. If the auxiliary road name of the initial auxiliary road is consistent with the main road name of the target main road, the initial auxiliary road is determined as a first auxiliary road. If the initial auxiliary road does not have an auxiliary road name, the Frechet distance of the initial auxiliary road and the target main road is obtained, the similarity between the initial auxiliary road and the target main road is calculated based on the Frechet distance, and a pre-established similarity threshold is obtained. The initial auxiliary road that meets the similarity threshold is regarded as a second auxiliary road. Then, the first auxiliary road and the second auxiliary road are combined to obtain the target auxiliary road.

[0045] In an optional embodiment, before the splitting, a splitting position needs to be selected, Figure 3A is a schematic diagram of selecting a road middle section as a splitting position, and the small dots represent the splitting position. However, in the present disclosure, the road middle section is not usually selected as the splitting position, because doing so will increase the workload of edge connection, Figure 3B is a schematic diagram of selecting an intersection as a splitting position, and the small dots in the figure represent the splitting position. In the present disclosure, the intersection where the upper and lower lines are separated is usually selected as the splitting position, because the intersection and the lane group in the road where the upper and lower lines are separated need to be disconnected, so that the repeated workload of edge connection can be avoided, and the amount of edge connection data caused by splitting can be conveniently calculated. However, it should be noted that although the splitting position selected in the present disclosure can avoid repeated work, due to the existence of special roads such as left and right extraction, the present disclosure still needs to output edge connection data to facilitate manual checking and avoid splitting errors. The left extraction refers to a left-turn exclusive lane, and the right extraction refers to a right-turn exclusive lane.

[0046] In step S106, the work units are clustered based on the target kilometer number to obtain a work data package. In the work data package, the first kilometer number of all roads matches the target kilometer number.

[0047] Specifically, the target kilometer number includes the kilometer number of each road in the road data. Since the work units are obtained by splitting the road data, the kilometer number of the road in the work unit matches the target kilometer number. The first kilometer number can be the total kilometer number of the roads in the work data package.

[0048] Before clustering, the original map needs to be divided into multiple grids. First, the target number of the multiple grids needs to be determined. The target number of the multiple grids can be determined by the following method: obtaining the target kilometer number and the total kilometer number of the roads in the work unit, and then determining the target number of the multiple grids according to the target kilometer number and the total kilometer number of the roads in the work unit. Then, the original map is equally divided according to the target number of the multiple grids to obtain the multiple grids. Then, the work unit is matched with the multiple grids according to the spatial position of the roads contained in the work unit to determine the first work unit corresponding to each grid. It should be noted that if a single work unit belongs to multiple grids, the grid with a larger second kilometer number is selected. The second kilometer number corresponding to each grid is obtained based on the kilometer number of the roads contained in the first work unit. Then, the multiple grids are merged in a predetermined merging order to obtain a merged grid. After obtaining the merged grid, the total kilometer number of the merged grid, i.e., the third kilometer number, is determined according to the second kilometer number. If the total kilometer number of the merged grid is within the predetermined range of the first kilometer number, the second work unit corresponding to the merged grid is determined as the work material package. If the total kilometer number of the merged grid is less than the minimum value within the predetermined range of the first kilometer number, the merged grid is added to the target work material, and the merged grid is continued to be merged. If the total kilometer number of the merged grid is greater than the maximum value of the predetermined range, the merged grid is reduced. The reduction of the second work unit corresponding to the merged grid includes: determining the missing number in the second work unit, which represents the number of other work units missing at the cutting position corresponding to the second work unit, and then preferentially selecting the second work unit with a large missing number for reduction. If the missing number is the same, the second work units are sorted and reduced in descending order of the total kilometer number of the roads in the second work unit. After the reduction is completed, the third kilometer number of the reduced work unit is confirmed again for subsequent steps.

[0049] Step S108: output the work material package.

[0050] The work material package is output to the staff, who will map based on the work material package.

[0051] In the above embodiments of the present disclosure, the road data of the original map, the target road level and the target kilometer are obtained, the road data is segmented based on the target road level, then the work units are clustered based on the target kilometer, the work data package is obtained, and finally the work data package is output. It is easy to note that the present disclosure can automatically extract work units from the road data based on the road data of the original map and the obtained target road level and target kilometer, aggregate the work units, generate the data package, and output the data package without manually segmenting the road data of the original map, thereby solving the technical problem of low lane-level map generation efficiency in the related art, and further achieving the technical effect of improving the lane-level map generation efficiency.

[0052] Optionally, the road segmentation of the road data based on the target road level to generate the work unit comprises: extracting the road data based on the target road level to obtain target work data; and segmenting the target work data based on a preset segmentation rule to obtain the work unit, wherein the preset segmentation rule is used to represent the segmentation of the road located at the intersection and separated by the upper and lower lines.

[0053] Specifically, the target work data includes road data of the target main road and the target auxiliary road. Before extracting the target work data, to avoid duplication of work, the road data of the existing lane group in the original map needs to be removed first. After the removal is completed, the target work data is obtained, and then the road data of the target main road that meets the target road level is extracted from the target work data according to the target road level. Then, the road data of the target auxiliary road is obtained according to the road data of the target main road and the preset range of the auxiliary road. Finally, the road data of the target main road and the road data of the target auxiliary road are merged to obtain the target work data. After obtaining the target work data, the segmentation position, i.e., the position of the intersection of the road separated by the upper and lower lines, is determined according to the preset segmentation rule, and the target work data is segmented according to the segmentation position to obtain a plurality of work units. It should be noted that since the intersection position of the road separated by the upper and lower lines, the lane group itself is disconnected, and the above segmentation position adopted by the present disclosure can avoid the repeated work of edge connection, and thus the generation efficiency of the lane-level map can be improved.

[0054] In the above optional embodiments, the road is segmented at the intersection position of the road separated by the upper and lower lines, which can avoid the repeated work of edge connection, and thus the generation efficiency of the lane-level map can be improved.

[0055] Optionally, the extraction of the road data based on the target road level to obtain the target work data comprises: removing the target road in the road data that meets a preset condition to obtain target road data, wherein the preset condition is used to represent that the target road already exists lane data; and extracting the target road data based on the target road level to obtain the target work data.

[0056] Specifically, to generate the lane-level map, lane information needs to be added on the basis of the original map. To avoid repeated work, the road data of the target road satisfying the preset condition is first removed, i.e., the road data of the target road, before extraction. After removing the road data of the target road from the road data of the original map, the target work data is obtained. Then, the road data of the target main road satisfying the target road level is extracted from the target work data according to the target road level. Then, the road data of the target auxiliary road is obtained according to the road data of the target main road and the preset range of the auxiliary road. Finally, the road data of the target main road and the road data of the target auxiliary road are merged to obtain the target work data.

[0057] In the optional embodiment, the target road with existing lane data avoids repeated work, thereby achieving the technical effect of improving the efficiency of generating the lane-level map.

[0058] Optionally, removing the target road satisfying the preset condition from the road data to obtain the target road data comprises: determining a lane group contained in the road data based on an association relationship between the road and the lane group; determining a coverage ratio of the lane group on a road where the lane group is located; obtaining a target lane group with a coverage ratio greater than a preset ratio, wherein the road where the target lane group is located is a target road; and removing the road where the target lane group is located to obtain the target road data.

[0059] Specifically, the association relationship between the road and the lane group in the road data is obtained, and the coverage ratio of the lane group on the road where the lane group is located is determined. If the coverage ratio meets a preset threshold, the road is regarded as an existing road. If the coverage ratio is lower than the preset threshold, the road still needs to be drawn and the specific lane group information is added. Therefore, the road data of the road belongs to the target data. In an optional embodiment, the preset threshold can be set to 60%.

[0060] In the optional embodiment, the target road is determined by the coverage ratio, and the road data of the target road is removed based on the coverage ratio to avoid repeated work, thereby achieving the technical effect of improving the efficiency of generating the lane-level map.

[0061] Optionally, determining the coverage ratio of the lane group on the road where the lane group is located comprises: projecting a starting position and an ending position of the lane group onto the road respectively to obtain a first projection position corresponding to the starting position and a second projection position corresponding to the ending position; obtaining a length between the first projection position and the second projection position to obtain a projection length of the lane group; and obtaining a ratio of the projection length to a road length of the road to obtain the coverage ratio.

[0062] Specifically, the start position and the end position of the lane group are projected onto the road where the lane group is located respectively to obtain a first projection position corresponding to the start position and a second projection position corresponding to the end position, and then the length between the start position and the end position, i.e., the projection length of the lane group, is obtained, and then the projection length of the lane group is divided by the length of the road to obtain the coverage ratio.

[0063] In the optional embodiment, the target road is determined by the coverage ratio, and the road data of the target road is removed based on the coverage ratio, so as to avoid repeated work, and thus the technical effect of improving the efficiency of lane-level map generation is achieved.

[0064] Optionally, the target road data is extracted based on the target road level to obtain the target work material, including: extracting the target main road from the target road data based on the target road level; extracting the auxiliary road in the preset range of the target main road in the target road data to obtain the target auxiliary road; and generating the target work material based on the target main road and the target auxiliary road.

[0065] Specifically, the target main road is extracted from the target road data according to the target road level, and the auxiliary road in the preset range of the target main road is extracted from the target road data to obtain the initial auxiliary road. It should be noted that the preset range of the target main road can be the target auxiliary road level data corresponding to the target main road. Then, it is determined whether the initial auxiliary road has an auxiliary road name, if the initial auxiliary road has an auxiliary road name, the initial auxiliary road name and the main road name of the target main road are screened, if the auxiliary road name of the initial auxiliary road is consistent with the main road name of the target main road, the initial auxiliary road is determined as the first auxiliary road; if the initial auxiliary road does not have an auxiliary road name, the Fréchet distance between the initial auxiliary road and the target main road is obtained, the similarity between the initial auxiliary road and the target main road is calculated based on the Fréchet distance, and a similarity threshold is set, the initial auxiliary road meeting the similarity threshold is regarded as the second auxiliary road, and then the first auxiliary road and the second auxiliary road are combined to obtain the target auxiliary road. Finally, the road data of the target main road and the target auxiliary road are combined to generate the target work material. It should be noted that in the process of generating the material package, the main road and the auxiliary road corresponding to the main road must be located in the same material package.

[0066] In the optional embodiment, the target work material is generated based on the target auxiliary road and the target main road, which guarantees the integrity of the data in the target work material, facilitates the subsequent work personnel to draw a map, and thus the technical effect of improving the efficiency of lane-level map generation is achieved.

[0067] Optionally, the extracting the auxiliary road in the preset range of the target main road in the target road data to obtain the target auxiliary road comprises: extracting the auxiliary road in the preset range of the target main road in the target road data to obtain an initial auxiliary road; in response to the initial auxiliary road having an auxiliary road name, screening the initial auxiliary road to obtain a first auxiliary road, the auxiliary road name of which is consistent with the main road name of the target main road; in response to the initial auxiliary road not having an auxiliary road name, screening the initial auxiliary road based on the similarity between the initial auxiliary road and the target main road to obtain a second auxiliary road; and merging the first auxiliary road and the second auxiliary road to obtain the target auxiliary road.

[0068] Specifically, the target road data is extracted according to the auxiliary road in the preset range of the target main road to obtain an initial auxiliary road, and then it is determined whether the initial auxiliary road has an auxiliary road name. If the initial auxiliary road has an auxiliary road name, the initial auxiliary road name and the main road name of the target main road are screened. If the auxiliary road name of the initial auxiliary road is consistent with the main road name of the target main road, the initial auxiliary road is determined as a first auxiliary road. If the initial auxiliary road does not have an auxiliary road name, the Fréchet distance between the initial auxiliary road and the target main road is obtained, the similarity between the initial auxiliary road and the target main road is calculated based on the Fréchet distance, a pre-established similarity threshold is obtained, and the initial auxiliary road that meets the similarity threshold is regarded as a second auxiliary road. Then, the first auxiliary road and the second auxiliary road are merged to obtain the target auxiliary road. Finally, the road data of the target main road and the target auxiliary road is merged to generate target operation materials.

[0069] In the optional embodiment described above, the target auxiliary road is confirmed by confirming whether the main road name and the auxiliary road name are consistent and confirming the Fréchet distance between the initial auxiliary road and the target main road, which can adapt to various forms of auxiliary roads existing in the target road data, thereby effectively confirming the target auxiliary road, facilitating the subsequent generation of target operation materials, and further achieving the technical effect of improving the efficiency of lane-level map generation.

[0070] Optionally, the screening the initial auxiliary road based on the similarity between the initial auxiliary road and the target main road to obtain the second auxiliary road comprises: obtaining the Fréchet distance between the initial auxiliary road and the target main road to obtain the similarity; and screening the initial auxiliary road to obtain the second auxiliary road, the similarity of which is greater than a preset similarity.

[0071] Specifically, if the initial auxiliary road does not have an auxiliary road name, the Fréchet distance between the initial auxiliary road and the target main road is obtained, the similarity between the initial auxiliary road and the target main road is calculated based on the Fréchet distance, a pre-established similarity threshold is obtained, and the initial auxiliary road that meets the similarity threshold is regarded as a second auxiliary road.

[0072] In the optional embodiment, the similarity obtained by the Fréchet distance is more accurate than the Euclidean distance, and thus the coverage ratio can be effectively confirmed, thereby achieving the technical effect of improving the efficiency of lane-level map generation.

[0073] Optionally, the target work material is segmented based on a preset segmentation rule to obtain a work unit, including: determining a target intersection in the target work material that meets the preset segmentation rule; obtaining an intersection type corresponding to the target intersection; in response to the intersection type being a preset type, segmenting the target work material based on the target intersection to obtain a work unit; and in response to the intersection type not being the preset type, generating a work unit based on a road having an association relationship with the target intersection.

[0074] Specifically, the target intersection can be an intersection in the up-and-down line road. The intersection type includes: a cross-shaped planar intersection, a ring-shaped planar intersection, an X-shaped planar intersection, a T-shaped planar intersection, a Y-shaped planar intersection, a staggered planar intersection, and a multi-way planar intersection, etc. The preset type includes: a cross-shaped planar intersection, an X-shaped planar intersection, a T-shaped planar intersection, a Y-shaped planar intersection, and a staggered planar intersection. If the road type corresponding to the target intersection is the preset type, the target intersection is taken as a segmentation position, and the target work material is segmented to obtain a work unit. When segmentation is performed, it must be ensured that the two roads parallel to the up-and-down line are in one material package, otherwise, the quality of the finally generated map will be poor, and the generation efficiency of the map will also be affected. Therefore, in the present application, the split road intersection is used to segment the road as shown in FIGS. 1 to 3, and the road selected by the rectangle in the figure can be one indivisible work unit, and the line segment between the dots in the middle of the road not selected is a segmentation line. If the intersection type is a ring-shaped intersection or an overpass, a work unit is directly generated from the road connected to the target intersection without splitting, and the work unit also includes the auxiliary road of the road connected to the target intersection. Figure 4A 、 Figure 4B 、 Figure 4C

[0075] In addition, if the total mileage of the road in the work unit generated based on the road having an association relationship with the target intersection is greater than the maximum value of the required mileage of a single material package, the work unit can be directly output as a work material package.

[0076] In the optional embodiment, a work unit generation method that can adapt to various intersection types is provided, and the adaptability of the processing method is improved.

[0077] ​Optionally, the work units are clustered based on the target mileage to obtain the work data package, including: dividing the original map into a plurality of grids based on the target mileage; matching the work units with the plurality of grids according to the spatial positions of the roads contained in the work units to determine the first work unit corresponding to each grid; obtaining the second mileage corresponding to each grid based on the mileage of the roads contained in the first work unit; and merging the work units based on the second mileage to obtain the work data package.

[0078] Specifically, the work data package is extracted from the road data of the original map, and thus the mileage of the roads in the work data package is consistent with the mileage of each road included in the target mileage. Before the grid division, the target number of the plurality of grids can be determined through the target mileage, and then the original map can be equally divided into a plurality of rectangular sheets according to the target number of the plurality of grids, i.e., the plurality of grids as shown in Figure 5 Figure 5 which is a schematic diagram of the plurality of grids after the division, wherein the numbers in the grids represent the total mileage of the roads in the grid. The spatial position contained in the work unit can be the position of the road contained in the work unit in the original map. Then, the plurality of grids are matched with the work units according to the spatial position of the roads contained in the work units to obtain the first work unit corresponding to each grid. The second mileage is the total mileage of all the roads in each grid. Then, the work units are merged according to the second mileage and the first mileage to obtain the work data package, as shown in Figure 6 and Figure 7 which are the corresponding map schematic diagrams of the data package, Figure 6 wherein different lines represent roads, and if the formats of the lines are the same, it means that the lines belong to the same data package, Figure 7 which is the corresponding relationship between the line format and the data package number. It should be noted that if a single work unit belongs to multiple grids, the work unit belongs to the grid with a larger second mileage.

[0079] In the above optional embodiment, the original map is divided into a plurality of grids, and the grid corresponding first work unit is determined according to the spatial position of the road contained in the work unit, and then the work units are merged based on the second mileage of the first unit to obtain the work data package, which can make the data amount in the obtained data package more evenly distributed, thereby facilitating the subsequent distribution of the work data package to the workers, and thus achieving the technical effect of improving the efficiency of lane-level navigation map generation.

[0080] ​Optionally, the original map is grid-divided based on the target mileage to obtain the plurality of grids, including: obtaining total mileage of all roads contained in the work unit; determining a target number of the plurality of grids based on the total mileage and the target mileage; and grid-dividing the original map based on the target number to obtain the plurality of grids.

[0081] Specifically, the total mileage of all roads contained in the work unit is obtained, a quotient is obtained by dividing the target total mileage by the total mileage of all roads contained in the work unit, a square root of the quotient is obtained, and an integer of the square root is obtained to obtain the target number of the plurality of grids. Then, the original map is equally divided according to the target number to obtain the plurality of grids.

[0082] In the optional embodiment, the target number of the plurality of grids is obtained by the target mileage and the first mileage, and the original map is divided based on the target map to obtain the plurality of grids, so that the technical effect of improving the efficiency of lane-level map generation can be achieved.

[0083] Optionally, the work units are merged based on the second mileage to obtain the work material package, including: merging the plurality of grids in a preset merging order to obtain a merged grid; determining a third mileage of the merged grid according to the second mileage; in response to the third mileage of the merged grid being within a preset range of the target mileage, determining that a second work unit corresponding to the merged grid is the work material package; in response to the third mileage of the merged grid being less than a minimum value in the preset range, continuing to merge the merged grid; and in response to the third mileage of the merged grid being greater than a maximum value in the preset range, reducing the second work unit corresponding to the merged grid.

[0084] Specifically, the preset merging order can be to merge a row first and then merge a next row, or to merge a column first and then merge a next column. The preset range can be a closed interval from a total mileage of a single material package in the first mileage minus a tolerance to the total mileage of the single material package in the first mileage plus the tolerance, wherein the tolerance represents a fluctuation threshold that the first mileage can be accepted. For example, if the first mileage is 25 kilometers and a fluctuation of 5 kilometers can be tolerated, the preset range is 20 kilometers to 30 kilometers. The third mileage can be a total mileage of all roads in the merged grid. If the third mileage of the merged grid is less than a minimum value in the preset range, the merged grid is continued to be merged; and if the third mileage is greater than a maximum value in the preset range, the merged grid is reduced.

[0085] In the above optional embodiments, by comparing the third mileage with the preset range of the first mileage, the total mileage of the merged grid is adjusted, so that the total mileage in the subsequent data packet is relatively uniform, which facilitates the subsequent distribution of the data packet, and further achieves the technical effect of improving the generation efficiency of the operation data packet.

[0086] Optionally, reducing the second operation unit corresponding to the merged grid includes: determining the missing quantity of the second operation unit, where the missing quantity is used to represent the quantity of other operation units missing at the splitting position corresponding to the second operation unit; determining the target operation unit in the second operation unit based on the missing quantity and the fourth mileage of the second operation unit; and reducing the target operation unit.

[0087] Specifically, as Figure 4B shown, the area defined by the rectangular frame represents an indivisible operation unit, Figure 4B The splitting positions in the shown rectangular map sheet correspond to four indivisible operation units. If one splitting unit is missing currently, the missing quantity is 1, and the other operation units are the currently missing operation units. It is confirmed that the above fourth mileage is the total mileage of all roads in the second operation unit. The target operation unit can be an operation unit including other operation units. When reducing the second operation unit, preferentially select the second operation unit with a large missing quantity for reduction. If the missing quantities are the same, sort them in descending order according to the size of the fourth mileage of the second operation unit for reduction.

[0088] In the above optional embodiments, when the third mileage of the merged grid is greater than the maximum value of the preset range, reducing the merged grid can make the size of the finally generated operation data packet relatively uniform, which is convenient for subsequent distribution, and thus achieves the technical effect of improving the generation efficiency of the lane-level map.

[0089] Optionally, the method further includes: determining the missing operation units in the operation data packet, where the missing operation units are used to represent other operation units missing at the splitting position corresponding to the operation data packet; generating edge connection data based on the intersection geometry corresponding to the missing operation units; and outputting the edge connection data.

[0090] Specifically, the missing operation units can be other operation units lacking in the quantity of the operation units corresponding to the splitting position. The intersection set can be the central position of the intersections of the roads in the missing operation units. For example, if the road is in a "well" shape, the intersection is a "square", and the intersection set is the center point of the "square". Generate edge connection data based on the intersection set corresponding to the missing unit, and output the edge connection data together with the operation data packet.

[0091] In the optional embodiment, the corresponding edge connecting data is generated, so that after the drawing is completed according to the operation data package, the edge connecting operation is performed, thereby achieving the technical effect of improving the efficiency of lane-level map generation.

[0092] In one preferred embodiment of the present disclosure, as shown in Figure 8 the road data of the original map and the target road level are obtained, and then the target road level is used to extract the target road data from the road data of the original map, including: obtaining the target main road from the road data of the original map according to the target road level, obtaining the road data of the target auxiliary road according to the road data of the target main road, and merging the road data of the target main road and the road data of the target auxiliary road to obtain the target operation data. Then, the target operation data is divided according to the preset division data to obtain the operation unit. The total kilometer number and the target kilometer number of the operation unit are obtained, and the target number of the plurality of grids is obtained. The original map is equally divided according to the target number of the plurality of grids to obtain the plurality of grids. The operation unit is matched with the plurality of grids according to the spatial position of the road contained in the operation unit, to determine the first operation unit corresponding to each grid. Meanwhile, the plurality of grids are merged in sequence according to the preset merging order to obtain the merged grid. Then, the total kilometer number of the merged grid, i.e., the third kilometer number, is determined according to the second kilometer number. If the total kilometer number in the merged grid is within the preset range of the first kilometer number, it is determined that the second operation unit corresponding to the merged grid is the operation data package. If the total kilometer number in the merged grid is less than the minimum value within the preset range of the first kilometer number, the merged grid is added to the target operation data, and the merged grid is continuously merged. If the total kilometer number of the merged grid is greater than the maximum value of the preset range, the merged grid is reduced. Wherein, the reduction of the second operation unit corresponding to the merged grid includes: determining the missing number in the second operation unit, the missing number representing the number of other operation units missing in the second operation unit corresponding to the division position, then preferentially selecting the second operation unit with a large missing number for reduction, if the missing numbers are the same, then the second operation units are sequentially sorted and reduced from large to small according to the total kilometer number of the road in the second operation unit, and after the reduction is completed, the third kilometer number of the reduced operation unit is confirmed again for subsequent steps.

[0093] According to the embodiments of the present disclosure, an embodiment of a data processing device for generating a lane-level map is also provided. The specific implementation manner and the optional embodiment in the embodiment are similar or identical to those in the above-mentioned embodiments, and will not be described herein.

[0094] Figure 9 is a structural schematic diagram of a data processing device for generating a lane-level map according to an embodiment of the present disclosure, as shown in Figure 9 the device comprises:

[0095] The acquisition module 90 is configured to acquire road data of an original map, a target road level, and a target kilometer number.

[0096] The segmentation module 92 is configured to perform road segmentation on the road data based on the target road level to generate a work unit, where the work unit contains part of a road in the original map.

[0097] The clustering module 94 is configured to cluster the work unit based on the target kilometer number to obtain a work package, where a first kilometer number of all roads in the work package matches the target kilometer number.

[0098] The output module 96 is configured to output the work package.

[0099] In the above embodiment, the road data of the original map, the target road level, and the target kilometer number are acquired, the road data is segmented based on the target road level, then the work unit is clustered based on the target kilometer number to obtain the work package, and finally the work package is output. It is easy to note that, based on the road data of the original map and the acquired target road level and target kilometer number, the work unit can be automatically extracted from the road data, the work unit can be clustered to generate the package, and the package can be output without manually segmenting the road data of the original map, thereby solving the technical problem of low lane-level map generation efficiency in the related art, and further achieving the technical effect of improving the lane-level map generation efficiency.

[0100] Optionally, the segmentation module includes an extraction submodule configured to extract the road data based on the target road level to obtain target work data, and a segmentation submodule configured to segment the target work data based on a preset segmentation rule to obtain the work unit, where the preset segmentation rule is used to represent segmentation of a road located at an intersection and separated by upper and lower lines.

[0101] Optionally, the extraction submodule includes an elimination unit configured to eliminate a target road in the road data that meets a preset condition to obtain target road data, where the preset condition is used to represent that the target road already has lane data, and an extraction unit configured to extract the target road data based on the target road level to obtain the target work data.

[0102] Optionally, the elimination unit includes a first determination submodule configured to determine a lane group contained in the road data based on an association relationship between a road and a lane group, a second determination submodule configured to determine a coverage ratio of the lane group to a road on which the lane group is located, an acquisition submodule configured to acquire a target lane group with a coverage ratio greater than a preset ratio, where the road on which the target lane group is located is a target road, and an elimination submodule configured to eliminate the road on which the target lane group is located to obtain the target road data.

[0103] Optionally, the second determining subunit is further configured to project the start position and the end position of the lane group onto the road respectively to obtain a first projection position corresponding to the start position and a second projection position corresponding to the end position; obtain a length between the first projection position and the second projection position to obtain a projection length of the lane group; and obtain a ratio of the projection length to a road length of the road to obtain a coverage ratio.

[0104] Optionally, the extraction unit comprises: a first extraction subunit configured to extract the target road data based on a target road level to obtain a target main road; a second extraction subunit configured to extract a secondary road in a preset range of the target main road in the target road data to obtain a target secondary road; and a first generation subunit configured to generate the target work material based on the target main road and the target secondary road.

[0105] Optionally, the second extraction subunit is further configured to extract the secondary road in the preset range of the target main road in the target road data to obtain an initial secondary road; in response to the initial secondary road having a secondary road name, filter the initial secondary road to obtain a first secondary road, the first secondary road having a secondary road name consistent with a main road name of the target main road; in response to the initial secondary road not having a secondary road name, filter the initial secondary road based on a similarity between the initial secondary road and the target main road to obtain a second secondary road; and merge the first secondary road and the second secondary road to obtain the target secondary road.

[0106] Optionally, the second extraction subunit is further configured to filter the initial secondary road based on a similarity between the initial secondary road and the target main road to obtain the second secondary road, the filtering comprising: obtaining a Fréchet distance between the initial secondary road and the target main road to obtain the similarity; and filtering the initial secondary road to obtain the second secondary road, the second secondary road having a similarity greater than a preset similarity.

[0107] Optionally, the segmentation sub-module comprises: a first determining unit configured to determine a target intersection in the target work material that satisfies a preset segmentation rule; a first obtaining unit configured to obtain an intersection type corresponding to the target intersection; a first responding unit configured to, in response to the intersection type being a preset type, segment the target work material based on the target intersection to obtain a work unit; and a second responding unit configured to, in response to the intersection type not being the preset type, generate the work unit based on a road having an association relationship with the target intersection.

[0108] Optionally, the clustering module comprises: a division sub-module configured to divide the original map into a plurality of grids based on a target kilometer number; a matching sub-module configured to match the work unit with the plurality of grids according to a spatial position of a road included in the work unit to determine a first work unit corresponding to each grid; a second kilometer number sub-module configured to obtain a second kilometer number corresponding to each grid based on a kilometer number of a road included in the first work unit; and a material package sub-module configured to merge the work units based on the second kilometer number to obtain a work material package.

[0109] Optionally, the dividing sub-module comprises: a total kilometer acquisition unit, configured to acquire a total kilometer number of all roads contained in the work unit; a target number determination unit, configured to determine a target number of the plurality of grids based on the total kilometer number and the target kilometer number; and a grid unit, configured to perform grid division on the original map based on the target number to obtain the plurality of grids.

[0110] Optionally, the data package sub-module comprises: a merging unit, configured to sequentially merge the plurality of grids according to a preset merging order to obtain a merged grid; a third road determination unit, configured to determine a third kilometer number of the merged grid according to the second kilometer number; a third response unit, configured to, in response to the third kilometer number of the merged grid being within a preset range of the first kilometer number, determine that the second work unit corresponding to the merged grid is the work data package; a fourth response unit, configured to, in response to the third kilometer number of the merged grid being less than a minimum value in the preset range, continue to merge the merged grid; and a fifth response unit, configured to, in response to the third kilometer number of the merged grid being greater than a maximum value in the preset range, reduce the second work unit corresponding to the merged grid.

[0111] Optionally, the fifth response unit comprises: a missing number sub-unit, configured to determine a missing number of the second work unit, wherein the missing number is used to represent a number of other work units missing at a split position corresponding to the second work unit; a target work unit sub-unit, configured to determine a target work unit in the second work unit based on the missing number and the fourth kilometer number of the second work unit; and a reducing sub-unit, configured to reduce the target work unit.

[0112] Optionally, the apparatus further comprises: a missing module, configured to determine a missing work unit in the work data package, wherein the missing work unit is used to represent other work units missing at a split position corresponding to the work data package; an edge connecting data module, configured to generate edge connecting data based on intersection geometry corresponding to the missing work unit; and an edge connecting data output module, configured to output the edge connecting data.

[0113] According to embodiments of the present disclosure, the present disclosure further provides an electronic device, a non-transitory computer-readable storage medium storing computer instructions, and a computer program product.

[0114] Figure 10A schematic block diagram of an example electronic device 1000 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present disclosure described and / or claimed in this document.

[0115] As shown in Figure 10 The device 1000 includes a computing unit 1001 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 1002 or a computer program loaded into a random access memory (RAM) 1003 from a storage unit 1008. Various programs and data required for the operation of the device 1000 can also be stored in the RAM 1003. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other through a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0116] Various components in the device 1000 are connected to the I / O interface 1005, including an input unit 1006, such as a keyboard, a mouse, etc.; an output unit 1007, such as various types of displays, speakers, etc.; the storage unit 1008, such as magnetic disks, optical disks, etc.; and a communication unit 1009, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1009 allows the device 1000 to exchange information / data with other devices through computer networks, such as the Internet, and / or various telecommunication networks.

[0117] The computing unit 1001 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1001 performs various methods and processes described above, such as the data processing method for generating a lane-level map. For example, in some embodiments, the data processing method for generating a lane-level map can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 1008. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 1000 via the ROM 1002 and / or the communication unit 1009. When the computer program is loaded onto the RAM 1003 and executed by the computing unit 1001, one or more steps of the data processing method for generating a lane-level map described above can be performed. Alternatively, in other embodiments, the computing unit 1001 can be configured to perform the data processing method for generating a lane-level map by any other suitable means, such as by means of firmware.

[0118] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0119] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0120] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0121] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0122] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0123] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0124] It should be understood that the various forms of flow shown above can be re-ordered, added to, or have steps deleted, using the flow. For example, the steps described in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the technical solutions of the present disclosure can be achieved, which are not limited herein.

[0125] The specific implementation described above does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A data processing method for generating a lane-level map, comprising: obtaining road data of an original map, a target road level, and a target kilometer number; performing road segmentation on the road data based on the target road level to generate a work unit, wherein the work unit contains part of roads in the original map; performing clustering on the work unit based on the target kilometer number to obtain a work package, wherein a first kilometer number of all roads in the work package matches the target kilometer number; outputting the work package; the performing road segmentation on the road data based on the target road level to generate a work unit comprises: removing target roads in the road data that meet a preset condition to obtain target road data, wherein the preset condition is used to represent that the target roads already exist lane data; extracting the target road data based on the target road level to obtain target work data; determining a segmentation position based on a preset segmentation rule, and segmenting the target work data according to the segmentation position to obtain the work unit, wherein the preset segmentation rule is used to represent that the road located at an intersection and separated by an upper line and a lower line is segmented, and the segmentation position is a position where the intersection of the road separated by the upper line and the lower line is located; the performing clustering on the work unit based on the target kilometer number to obtain a work package comprises: performing grid division on the original map based on the target kilometer number to obtain a plurality of grids; matching the work unit with the plurality of grids according to the spatial position of the road contained in the work unit to determine a first work unit corresponding to each grid; obtaining a second kilometer number corresponding to each grid based on the kilometer number of the road contained in the first work unit; sequentially merging the plurality of grids according to a preset merging order to obtain a merged grid, and determining a third kilometer number of the merged grid according to the second kilometer number; in response to the third kilometer number of the merged grid being within a preset range of the target kilometer number, determining that a second work unit corresponding to the merged grid is the work package, wherein the preset range is a closed interval of a total kilometer number of a single package in the first kilometer number minus a tolerance to the total kilometer number of a single package in the first kilometer number plus the tolerance, and the tolerance is used to represent a fluctuation threshold of the first kilometer number being received.

2. The method of claim 1, wherein, the removing target roads in the road data that meet a preset condition to obtain the target road data comprises: determining a lane group contained in the road data based on an association relationship between a road and a lane group; determining a coverage ratio of the lane group on the road where the lane group is located; obtaining a target lane group with a coverage ratio greater than a preset ratio, wherein the road where the target lane group is located is the target road; removing the road where the target lane group is located to obtain the target road data.

3. The method of claim 2, wherein, the determining the coverage ratio of the lane group and the road where the lane group is located comprises: Project the start position and the end position of the lane group onto the road respectively to obtain a first projection position corresponding to the start position and a second projection position corresponding to the end position; Obtain a length between the first projection position and the second projection position to obtain a projection length of the lane group; Obtain a ratio of the projection length to a road length of the road to obtain the coverage ratio.

4. The method of claim 1, wherein, The target work material is obtained by extracting the target road data based on the target road level, and includes: The target main road is obtained by extracting the target road data based on the target road level; The target auxiliary road is obtained by extracting the auxiliary road within the preset range of the target main road in the target road data; The target work material is generated based on the target main road and the target auxiliary road.

5. The method of claim 4, wherein, The target auxiliary road is obtained by extracting the auxiliary road within the preset range of the target main road in the target road data, and includes: The initial auxiliary road is obtained by extracting the auxiliary road within the preset range of the target main road in the target road data; The first auxiliary road is obtained by screening the auxiliary road in the initial auxiliary road, in which the auxiliary road name is consistent with the main road name of the target main road, in response to the initial auxiliary road existing auxiliary road name; The second auxiliary road is obtained by screening the initial auxiliary road based on the similarity between the initial auxiliary road and the target main road, in response to the initial auxiliary road not existing auxiliary road name; The target auxiliary road is obtained by merging the first auxiliary road and the second auxiliary road.

6. The method of claim 5, wherein, The second auxiliary road is obtained by screening the initial auxiliary road based on the similarity between the initial auxiliary road and the target main road, and includes: The similarity is obtained by obtaining the Frechet distance between the initial auxiliary road and the target main road; The second auxiliary road is obtained by screening the auxiliary road in the initial auxiliary road, in which the similarity is greater than a preset similarity.

7. The method of claim 1, wherein, The work unit is obtained by determining a split position based on a preset split rule, and splitting the target work material according to the split position, and includes: The target intersection that meets the preset split rule in the target work material is determined, wherein the target intersection is the intersection of the road separated by the uplink and downlink; The intersection type corresponding to the target intersection is obtained; The work unit is obtained by splitting the target work material based on the target intersection, in response to the intersection type being a preset type; The work unit is obtained by generating the work unit based on the road having an association relationship with the target intersection, in response to the intersection type not being the preset type.

8. The method of claim 1, wherein, The plurality of grids is obtained by grid dividing the original map based on the target kilometer number, and includes: The total kilometer number of all roads contained in the work unit is obtained; The target number of the plurality of grids is determined based on the total kilometer number and the target kilometer number; The plurality of grids is obtained by grid dividing the original map based on the target number.

9. The method of claim 1, wherein, The method further includes: In response to the third kilometer number of the merged grid being less than the minimum value within the preset range, the merged grid is continuously merged. In response to the third number of kilometers of the merged grid being greater than the maximum value within the preset range, the second job unit corresponding to the merged grid is reduced.

10. The method of claim 9, wherein, The second job unit corresponding to the merged grid is reduced, including: determining a missing number of the second job unit, wherein the missing number is used to represent a number of other job units missing at a split position corresponding to the second job unit; based on the missing number and a fourth number of kilometers of the second job unit, determining a target job unit in the second job unit; the target job unit is reduced.

11. The method of any one of claims 1-9, further comprising: determining a missing job unit in the job package, wherein the missing job unit is used to represent other job units missing at a split position corresponding to the job package; generating an edge connecting data based on intersection geometry corresponding to the missing job unit; outputting the edge connecting data.

12. A data processing apparatus for generating a lane-level map, comprising: an acquisition module configured to acquire road data of an original map, a target road level, and a target number of kilometers; a segmentation module configured to perform road segmentation on the road data based on the target road level to generate a job unit, wherein the job unit contains part of the roads in the original map; a clustering module configured to cluster the job unit based on the target number of kilometers to obtain a job package, wherein a first number of kilometers of all roads in the job package matches the target number of kilometers; an output module configured to output the job package; the segmentation module is further configured to perform road segmentation on the road data based on the target road level to generate a job unit by: removing target roads in the road data that meet a preset condition to obtain target road data, wherein the preset condition is used to represent that the target roads already have lane data; extracting the target road data based on the target road level to obtain target job data; determining a split position based on a preset split rule, and segmenting the target job data according to the split position to obtain the job unit, wherein the preset split rule is used to represent that the roads located at an intersection and separated by upper and lower lines are split, and the split position is a position where the intersection of the roads separated by the upper and lower lines is located. The clustering module is further configured to cluster the job units based on the target mileage to obtain a job package by: dividing the original map based on the target mileage to obtain a plurality of grids; matching the job units with the plurality of grids according to the spatial positions of the roads contained in the job units to determine first job units corresponding to each grid; obtaining second mileages corresponding to each grid based on the mileages of the roads contained in the first job units; merging the plurality of grids in a preset merging order to obtain merged grids, and determining third mileages of the merged grids according to the second mileages; and in response to the third mileage of the merged grid being within a preset range of the target mileage, determining a second job unit corresponding to the merged grid as the job package, wherein the preset range is a closed interval of a total mileage of a single package in the first mileages minus a tolerance to the total mileage of a single package in the first mileages plus the tolerance, and the tolerance is used to represent a fluctuation threshold of the first mileage being received.

13. An electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-11.

14. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method of any one of claims 1-11.

15. A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1-11.

Images