A road network data generation method and device

Abstract

The present invention discloses a method and device for generating road network data, and relates to the field of computer technology. A specific implementation of the method includes: obtaining historical trajectory information, screening out trajectory points within a set area from the historical trajectory information; rasterizing the area, counting the number of trajectory points belonging to the same grid, dividing multiple grids into empty grids and non-empty grids, and determining the coordinate points of non-empty grids; selecting an initial starting grid from the non-empty grids, and repeatedly performing the following steps until all the grids that are not connected around the starting grid are empty grids, connecting multiple starting grids to obtain road network data of the area: connecting the coordinate points of the starting grid with the coordinate points of the adjacent non-empty grids to perform line clustering to obtain a line group, and updating the starting grid according to the adjacent non-empty grids at the end of the line in the line group. The method solves the problem that road network data cannot be obtained through road sampling in some areas, and establishes the road network data of the area.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for generating road network data. Background Art

[0002] Road network is indispensable information for public transportation. Complete road network data plays a vital role in map services such as travel navigation and route optimization. The traditional way to obtain and update road network data is road collection, that is, for unknown and newly added road sections, data collection vehicles are used to collect data on site and complete the existing road network data.

[0003] In the process of implementing the present invention, there are at least the following problems in the prior art:

[0004] Data collection vehicles can only travel on roads and cannot enter certain specific areas, such as residential areas, industrial parks, hospitals, schools, scenic spots, etc. As a result, the existing road data collection method can only collect road network data on roads, but cannot collect road network data in the above-mentioned specific areas. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a road network data generation method and device, which screens out trajectory points within a set area from historical trajectory information, and rasterizes the area to divide the grid into empty grids and non-empty grids, then selects an initial starting grid, connects the starting grid and the surrounding adjacent non-empty grids, performs line clustering, and updates the starting grid, and repeats this process to establish road network data for the area.

[0006] To achieve the above objective, according to one aspect of an embodiment of the present invention, a method for generating road network data is provided.

[0007] A road network data generation method according to an embodiment of the present invention comprises: obtaining historical trajectory information, screening out trajectory points within a set area from the historical trajectory information; rasterizing the area, counting the number of trajectory points belonging to the same grid, dividing a plurality of the grids into empty grids and non-empty grids according to the number of trajectory points, and determining the coordinate points of the non-empty grids; selecting an initial starting grid from the non-empty grids, and repeatedly performing the following steps until all the grids not connected around the starting grid are the empty grids, connecting a plurality of the starting grids to obtain road network data within the area; determining adjacent non-empty grids of the starting grid, connecting the coordinate points of the starting grid with the coordinate points of the adjacent non-empty grids to perform line clustering to obtain a line group, and updating the starting grid according to the adjacent non-empty grids at the ends of the lines in the line group.

[0008] Optionally, the performing line clustering to obtain a line group includes: calculating angles between the lines, and classifying the lines whose angles are smaller than a set angle threshold as lines of the same type to form a line group.

[0009] Optionally, updating the starting grid includes: determining an adjacent non-empty grid in the line group that is closest to the starting grid in the line direction, and updating the nearest adjacent non-empty grid as the starting grid.

[0010] Optionally, determining the coordinate point of the non-empty grid includes: clustering the trajectory points belonging to the same non-empty grid as a trajectory point group to obtain the center point of the non-empty grid, and using the center point as the coordinate point of the non-empty grid.

[0011] Optionally, the method further includes: mapping the points of interest within the area to the empty grid, calculating the first distances from the points of interest on both sides of the road in the road network data to the road; based on the first distances, screening out the points of interest closest to one side of the road and the points of interest closest to the other side of the road; calculating the second distance between the two screened points of interest, and determining whether the first distances and the second distances from the two screened points of interest to the road meet the set driving conditions; if the driving conditions are met, determining that the road is a vehicle road; if the driving conditions are not met, determining that the road is a pedestrian road.

[0012] Optionally, the driving condition is any one or more of the following: the first distance from the two selected points of interest to the road, and the second distance are both greater than a set first distance threshold; and the first distance from the two selected points of interest to the road is less than a set second distance threshold, and the second distance is greater than a set third distance threshold.

[0013] Optionally, the calculating the second distance between the two filtered interest points includes: counting the number of non-empty grids in the direction of the line connecting the two filtered interest points; and calculating the second distance between the two filtered interest points based on the number of non-empty grids and the grid side length.

[0014] Optionally, the method further includes: acquiring delivery address information, segmenting the delivery address information to obtain target address elements; and acquiring a corresponding area range from map data according to the target address elements.

[0015] To achieve the above objective, according to another aspect of an embodiment of the present invention, a road network data generating device is provided.

[0016] A road network data generating device according to an embodiment of the present invention comprises: a trajectory point screening module, which is used to obtain historical trajectory information, and screen out trajectory points within a set area from the historical trajectory information; a grid division module, which is used to grid the area, count the number of trajectory points belonging to the same grid, divide a plurality of the grids into empty grids and non-empty grids according to the number of trajectory points, and determine the coordinate points of the non-empty grids; a road network determination module, which is used to select an initial starting grid from the non-empty grids, and repeatedly perform the following steps until all the grids that are not connected around the starting grid are the empty grids, connect a plurality of the starting grids, and obtain road network data of the area: determine the adjacent non-empty grids of the starting grid, connect the coordinate points of the starting grid with the coordinate points of the adjacent non-empty grids to perform line clustering to obtain a line group, and update the starting grid according to the adjacent non-empty grids at the ends of the lines in the line group.

[0017] Optionally, the road network determination module is further used to calculate the angles between the links, and classify the links whose angles are less than a set angle threshold into the same type of links to form a link group.

[0018] Optionally, the road network determination module is further used to determine the adjacent non-empty grid closest to the starting grid in the link direction in the link group, and update the nearest adjacent non-empty grid as the starting grid.

[0019] Optionally, the grid division module is further used to cluster the trajectory points belonging to the same non-empty grid as a trajectory point group to obtain the center point of the non-empty grid, and use the center point as the coordinate point of the non-empty grid.

[0020] Optionally, the device also includes: a type judgment module, used to map the points of interest within the area to the empty grid, calculate the first distance from the points of interest on both sides of the road in the road network data to the road; based on the first distance, filter out the points of interest closest to one side of the road and the points of interest closest to the other side of the road; calculate the second distance between the two filtered points of interest, and judge whether the first distance and the second distance of the two filtered points of interest to the road meet the set driving conditions; if the driving conditions are met, determine that the road is a vehicle road; if the driving conditions are not met, determine that the road is a pedestrian road.

[0021] Optionally, the driving condition is any one or more of the following: the first distance from the two selected points of interest to the road, and the second distance are both greater than a set first distance threshold; and the first distance from the two selected points of interest to the road is less than a set second distance threshold, and the second distance is greater than a set third distance threshold.

[0022] Optionally, the type determination module is further used to count the number of non-empty grids in the direction of the line connecting the two screened interest points; and calculate the second distance between the two screened interest points based on the number of non-empty grids and the grid side length.

[0023] Optionally, the method further includes: acquiring delivery address information, segmenting the delivery address information to obtain target address elements; and acquiring a corresponding area range from map data according to the target address elements.

[0024] To achieve the above objective, according to another aspect of an embodiment of the present invention, an electronic device is provided.

[0025] An electronic device according to an embodiment of the present invention comprises: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement a road network data generation method according to an embodiment of the present invention.

[0026] To achieve the above objective, according to another aspect of the embodiments of the present invention, a computer readable medium is provided.

[0027] A computer-readable medium according to an embodiment of the present invention stores a computer program, and when the program is executed by a processor, a road network data generation method according to an embodiment of the present invention is implemented.

[0028] An embodiment of the above invention has the following advantages or beneficial effects: by screening out trajectory points within a set area from historical trajectory information, and rasterizing the area to divide the grid into empty grids and non-empty grids, then selecting an initial starting grid, connecting the starting grid and the surrounding adjacent non-empty grids, performing line clustering, and updating the starting grid, and repeating this process to form a connection relationship between trajectory points, thereby establishing road network data for the area, and solving the problem of missing road network data in a specific area.

[0029] By calculating the angle between the lines, the lines are clustered, so that the starting grid can be updated in groups later, improving the efficiency of establishing road network data. The nearest adjacent non-empty grid in the line direction of the line group is used as the new starting grid to ensure the integrity and accuracy of the road network data. Through point clustering, the density of trajectory points can be reduced, and abnormal trajectory points can be filtered out.

[0030] Based on the first distance from the point of interest to the road, the second distance between the points of interest and the set driving conditions, it is determined whether the road is drivable to achieve the refinement of the road type. The driving conditions are set based on actual experience to ensure the accuracy of the refined road type. The second distance between the points of interest is calculated by counting the number of non-empty grids in the direction of the line connecting the points of interest, which reduces the calculation complexity while ensuring accuracy. The delivery address information is a by-product of logistics distribution. Extracting the target address elements from the delivery address information and then obtaining the corresponding area range can save economic costs.

[0031] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0033] Figure 1 is a schematic diagram of the main steps of the method for generating road network data according to an embodiment of the present invention;

[0034] Figure 2 is a schematic diagram of the main process of the method for generating road network data according to an embodiment of the present invention;

[0035] Figure 3 is a schematic diagram of a starting grid, adjacent non-empty grids, and a non-empty grid in an embodiment of the present invention;

[0036] Figure 4 is a schematic diagram of a road type determination process according to an embodiment of the present invention;

[0037] Figure 5 is a schematic diagram of the road type judgment principle of an embodiment of the present invention;

[0038] Figure 6 is a schematic diagram of main modules of a road network data generating device according to an embodiment of the present invention;

[0039] Figure 7 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0040] Figure 8 It is a schematic diagram of the structure of a computer device suitable for implementing the electronic device of the embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0042] The terms involved in the embodiments of the present invention are explained below.

[0043] AOI: The full name is Area of ​​Interest, which refers to the regional geographic entity in the map data. An AOI contains at least four basic information: name, address, category, longitude and latitude coordinates. It can be a residential area, a university, an office building, an industrial park, a comprehensive shopping mall, etc.

[0044] POI: The full name is Point of Interest. A POI contains at least four basic information: name, address, category, and longitude and latitude coordinates. It can be a house, a shop, a mailbox, a bus stop, etc.

[0045] GPS: The full name is Global Positioning System.

[0046] Figure 1 FIG. 1 is a schematic diagram of the main steps of the method for generating road network data according to an embodiment of the present invention. Figure 1 As shown, the road network data generation method of the embodiment of the present invention mainly includes the following steps:

[0047] Step S101: Obtain historical trajectory information, and filter out trajectory points within a set area from the historical trajectory information. The historical trajectory information refers to the trajectory information formed by activities in a historical time period, such as the delivery trajectory information of the deliveryman, the movement trajectory information of the user, etc. The set area refers to the geographical range corresponding to the area where the road network data needs to be obtained, which can be a closed area or an open area, such as a residential area, school, industrial park, etc.

[0048] Taking the historical trajectory information as the delivery trajectory information as an example, the delivery personnel will send back the delivery trajectory information during the delivery process. The delivery trajectory information is formed by collecting the location coordinates of the delivery personnel in a certain period of time (i.e., the trajectory point coordinates, which are longitude and latitude coordinates), and then smoothly connecting the location coordinates in chronological order, which can characterize the movement behavior and movement direction of the delivery personnel in the time period. In the embodiment, the delivery trajectory information sent back by the delivery personnel can be obtained, and the existing map data, especially the AOI data, can be used to filter out the trajectory points within the set area.

[0049] In an optional embodiment, the trajectory points can be filtered in the following manner: rasterize the AOI data to obtain the lower left corner coordinates and upper right corner coordinates of each grid (the coordinates are longitude and latitude coordinates); filter out the trajectory points whose coordinates are between the lower left corner coordinates and the upper right corner coordinates, which are the trajectory points within the set area.

[0050] Among them, the judgment basis for whether the trajectory point coordinates are located between the lower left corner coordinates and the upper right corner coordinates is: if the horizontal coordinate of the trajectory point coordinates is greater than the horizontal coordinate of the lower left corner coordinates, and less than the horizontal coordinate of the upper right corner coordinates, and at the same time the vertical coordinate of the trajectory point coordinates is greater than the vertical coordinate of the lower left corner coordinates, and less than the vertical coordinate of the upper right corner coordinates, then the trajectory point coordinates are located between the lower left corner coordinates and the upper right corner coordinates.

[0051] Step S102: Grid the area, count the number of track points belonging to the same grid, and divide the grids into empty grids and non-empty grids according to the number of track points. The delivery track information contains long-term track point coordinates. There is no time relationship between these track point coordinates, which makes the connection relationship between track points uncontrollable and makes it impossible to form road network data. Therefore, the entire area needs to be gridded.

[0052] In the embodiment, a grid is established on the entire area with a set side length to achieve rasterization of the area. Then, the number of track points contained in each grid (hereinafter referred to as the number of track points) is counted. If the number of track points in a grid is greater than the set number threshold, the grid is divided into a non-empty grid; if the number of track points in a grid is less than or equal to the set number threshold, the grid is divided into an empty grid.

[0053] This step sets the grids with the number of trajectory points less than or equal to the set number threshold as empty grids, reducing the errors caused by abnormal points (i.e., abnormal trajectory points) and GPS positioning drift, and improving the accuracy of road network data.

[0054] Step S103: Determine the coordinate points of the non-empty grid, and select an initial starting grid from the non-empty grid. The coordinate points are used to represent the coordinates of the non-empty grid. In an embodiment, a trajectory point coordinate can be selected from the coordinates of the trajectory points contained in the non-empty grid (hereinafter referred to as trajectory point coordinates) as the coordinate point of the non-empty grid. In order to improve accuracy, the trajectory points belonging to the same non-empty grid can also be clustered as a trajectory point group to obtain the center point of the non-empty grid, and the center point is used as the coordinate point of the non-empty grid.

[0055] In one embodiment, point clustering can be achieved by a clustering algorithm, such as a K-Means clustering algorithm, a mean shift clustering algorithm, etc. Taking the K-Means algorithm as an example, the algorithm randomly initializes the center point of each trajectory point group, calculates the distance from each trajectory point in the trajectory point group to the center point, divides the trajectory points into the nearest center point, and then calculates the center point of each class as the new center point, repeating the above steps until each center point does not change much after each iteration. The final center point is the coordinate point of the non-empty grid.

[0056] Before selecting the initial starting grid, it is necessary to first determine the region entrance. The trajectory points contained in the region entrance belong to the region entrance points. The grid containing the largest number of region entrance points is used as the starting grid. In the embodiment, the region entrance is taken as the location where the trajectory points and the AOI data intersect most densely. If there are multiple region entrances, one can be randomly selected.

[0057] Step S104: Determine whether all the unconnected grids around the starting grid are empty grids. If the unconnected grids around the starting grid are non-empty grids, execute step S105; if all the unconnected grids around the starting grid are empty grids, execute step S106. In the embodiment, a two-dimensional rectangular coordinate system can be established with the region entrance as the origin, and the coordinate value can be used as the unique identifier of each grid to express the relative position relationship within the region. For example, the coordinate value of the third grid to the right of the origin is (3, 0), and the coordinate value can be used to uniquely represent the grid.

[0058] In step S102, it has been determined whether each grid is an empty grid or a non-empty grid, and the coordinate values ​​of the grids can express their positional relationship. Therefore, the grids located in N circles around the starting grid can be determined in combination with the coordinate values. If all of these grids are empty grids except the grids that have been connected, it means that the road network collection is completed; if there are non-empty grids except the grids that have been connected, it means that the road network collection is not yet completed. Where N is an integer, such as 1 or 2.

[0059] Step S105: Determine the adjacent non-empty grids of the starting grid, connect the coordinate points of the starting grid with the coordinate points of the adjacent non-empty grids to perform line clustering to obtain a line group, update the starting grid according to the adjacent non-empty grids at the ends of the lines in the line group, and execute step S104. The adjacent grids refer to the grids in a circle around the starting grid, and the adjacent non-empty grids are the non-empty grids in the adjacent grids.

[0060] Connect the coordinate point of the starting grid with the coordinate point of the adjacent non-empty grid to obtain a line between the two, that is, one end of the line is the starting grid and the other end is the non-empty grid. Then, the lines are clustered according to the angle difference between the lines to obtain a line group. Specifically, the angle between the lines can be calculated, and the lines with an angle less than a set angle threshold can be classified as the same type of lines to form a line group. A line group includes several lines. In an embodiment, the line angle can be obtained by calculating the cosine value of the angle between two lines. The angle threshold can be set according to the specific scenario, such as setting it to 90°.

[0061] After the line clustering is completed, the starting grid needs to be updated. Specifically, the grid at the end of any line in the line group (i.e., the other end of the line) can be used as the starting grid for the next time. In a preferred embodiment, in order to ensure the integrity and accuracy of the road network data, when updating the starting grid, the nearest adjacent non-empty grid in the line direction of the line group and the starting grid can be first determined, and the nearest adjacent non-empty grid is updated as the starting grid for the next time.

[0062] There may be multiple updated starting grids, and then step S104 to step S105 are repeatedly performed until all the unconnected grids around the starting grid are empty grids.

[0063] Step S106: Connect multiple starting grids to obtain road network data of the area. Road network data is used to characterize the characteristics of roads within the set area, such as the shape of the road, the connectivity between the roads, etc. In the embodiment, all starting grids are connected to form a connection relationship between the trajectory points, thereby obtaining the road network data of the area.

[0064] Figure 2 FIG. 1 is a schematic diagram of the main flow of the method for generating road network data according to an embodiment of the present invention. Figure 2 As shown, the road network data generation method of the embodiment of the present invention mainly includes the following steps:

[0065] Step S201: Obtain the delivery address information, segment the delivery address information, and obtain the target address element. Obtain the delivery address information of the delivery person on a daily basis, segment it according to the administrative area division (such as the four-level administrative division), road, road number, POI, POI gate address, postscript, etc., and obtain the target address element. In the embodiment, the target address element corresponds to the area where the road network data is to be collected, which can be the name of the community, the name of the school, the name of the industrial park, etc.

[0066] Step S202: According to the target address element, the corresponding area range is obtained from the map data. The map data includes AOI data, including the target address element and the corresponding area range. In the embodiment, the area range corresponding to the target address element is found from the AOI data. This operation enables the unnecessary delivery tracks to be filtered out from the delivery track information later, and only the tracks within the area are retained.

[0067] Step S203: Obtain the delivery track information, and filter out the track points within the area from the delivery track information. This step is used to filter out the track points within each area from the delivery track information returned by the delivery person.

[0068] Step S204: Grid the area and count the number of track points belonging to the same grid. Grid the entire area with a set side length to achieve regional gridding. The side length can be customized and can be greater than the width of a car, such as 5 meters (about the width of 2 cars). The grid shape is not limited in the embodiment. For ease of calculation, a square can be selected.

[0069] Step S205: Determine whether the number of track points in the grid is greater than the set number threshold. If the number of track points in the grid is greater than the number threshold, the grid is set as a non-empty grid; if the number of track points in the grid is less than or equal to the number threshold, the grid is set as an empty grid. The number threshold can be determined based on the density of the track points. It is usually expected that there should not be too many or too few track points in a grid. In an embodiment, the number threshold can be set to 10 track points.

[0070] Step S206: Cluster the trajectory points belonging to the same non-empty grid to obtain the coordinate points of the non-empty grid. Use the K-Means algorithm to cluster the trajectory points belonging to the same non-empty grid. After clustering, the center point of each category will be obtained, which is the coordinate point of the non-empty grid.

[0071] Step S207: Select an initial starting grid from the non-empty grids. In the embodiment, the grid containing the largest number of area entry points is used as the starting grid.

[0072] Step S208: Determine whether all the unconnected grids around the starting grid are empty grids. If there are non-empty grids around the starting grid, execute step S209; if all the unconnected grids around the starting grid are empty grids, execute step S211. The initial value of the starting grid is the initial starting grid. After each update, the starting grid is the currently updated starting grid.

[0073] Step S209: Determine the adjacent non-empty grid of the starting grid, connect the coordinate point of the starting grid with the coordinate point of the adjacent non-empty grid. Select two circles of adjacent non-empty grids around the starting grid, and connect the coordinate point of the starting grid with the coordinate point of the adjacent non-empty grid. Figure 3 Schematic diagram of the starting grid, adjacent non-empty grids, and non-empty grids in an embodiment of the present invention. Figure 3 As shown, the non-empty grids in a circle outside the starting grid are adjacent non-empty grids.

[0074] Step S210: Cluster the lines, update the starting grid, and execute step S208. Calculate the angle between the lines, determine whether the angle is less than the set angle threshold, and classify the lines with angles less than the angle threshold into the same type of lines to form a line group. After clustering, the adjacent non-empty grid closest to the starting grid in the line direction of the line group is used as the new starting grid.

[0075] Step S211: Connect all the starting grids to obtain the road network data of the area. If the grids around the starting grid that are not connected are all empty grids, it means that the road network data collection is completed, and all the starting grids are connected to obtain the road network data of the area.

[0076] In one embodiment, since the period for the delivery personnel to send back the delivery trajectory information is relatively long, the GPS positioning error in the area is relatively large, and the delivery address information of a single day is usually not sufficient to cover the entire area, long-term delivery address information and delivery trajectory information can be introduced to compensate for the problems of discontinuous trajectory point coordinates and GPS point drift, while achieving full area coverage of the delivery address information.

[0077] This embodiment uses the delivery address information and delivery track information of the delivery personnel in the area to obtain the roads in the area, without any other financial or material support, and does not involve user privacy. At the same time, since the delivery personnel deliver packages frequently, the road network data of the area can be updated in time when there are few orders in the area or the construction of the area is adjusted, ensuring the accuracy of the road network data.

[0078] After collecting the road network data in the area, the road types contained therein can be further determined to determine whether the road is drivable. The road types include pedestrian roads and vehicle roads. The specific implementation is as follows.

[0079] Figure 4 FIG. 1 is a schematic diagram of the road type determination process according to an embodiment of the present invention. Figure 4 As shown, the road type determination process of the embodiment of the present invention includes the following steps:

[0080] Step S401: Map the points of interest within the area to empty grids, and calculate the first distance from the points of interest on both sides of the road in the road network data to the road. Obtain the POIs located in the area from the POI database, and map the POIs to different empty grids according to the POI coordinates. Then calculate the straight-line distance from the POIs on both sides of the road to the road, and use the straight-line distance as the first distance.

[0081] Figure 5 Schematic diagram of the road type judgment principle of an embodiment of the present invention. Figure 5 As shown in FIG. 1 , the straight-line distance from each of the two POIs located on both sides of the road to the road is the first distance. The distance can approximately represent the length and width of the POI.

[0082] Step S402: According to the first distance, the point of interest closest to one side of the road and the point of interest closest to the other side of the road are screened out. The two sides of a road in an area usually contain multiple POIs. From the POIs on each side, a POI closest to the road on that side is screened out to obtain two POIs located on both sides of the road, which can be called a first POI and a second POI.

[0083] Step S403: Calculate the second distance between the two selected points of interest. Calculate the distance between the first POI and the second POI. This distance can be used to approximate the distance between the POIs and is referred to as the second distance for easy distinction. Figure 5 , the length of the line connecting the two POIs is the second distance. In one embodiment, the second distance can be calculated from the POI coordinates.

[0084] In another embodiment, the second distance can also be obtained by counting the number of non-empty grids in the direction of the line connecting the first POI and the second POI to reduce the calculation complexity. Specifically, the number of non-empty grids in the direction of the line connecting the first POI and the second POI is counted, and then the second distance between the first POI and the second POI is calculated according to the number of non-empty grids and the grid side length.

[0085] Step S404: Determine whether the first distance and the second distance from the two selected points of interest to the road meet the set driving conditions, if the driving conditions are met, execute step S405; otherwise, execute step S406. The driving conditions are used to determine whether a road is drivable.

[0086] In an embodiment, the driving condition may be any one or two of the following: (1) the first distance from the first POI to the road, the first distance from the second POI to the road, and the second distance between the first POI and the second POI are all greater than a set first distance threshold; (2) the first distance from the first POI to the road, and the first distance from the second POI to the road are all less than a set second distance threshold, and the second distance between the first POI and the second POI is greater than a set third distance threshold.

[0087] In the first condition, the first distance threshold can be set to the actual distance between POIs. For example, when the area is a residential area, the first distance threshold can be the distance between buildings in the residential area. If both the first distance and the second distance are greater than the first distance threshold, the driving condition is considered to be met. In the second condition, if the first distance is less than the second distance threshold and the second distance is greater than the third distance threshold, it means that the POI occupies a small area but the distance between POIs is large, and the driving condition is considered to be met.

[0088] Step S405: Determine whether the road is a driving road. If the driving condition is met, it means that the road is driving, and the road type of the road is determined to be a driving road.

[0089] Step S406: Determine whether the road is a pedestrian road. If the driving condition is met, it means that the road is not suitable for driving, and the road type of the road is determined to be a pedestrian road.

[0090] The road network data generation method of the embodiment of the present invention, based on the collected road network data, combines POI data and set driving conditions to determine whether a road is drivable, and then determines its road type, so that users entering the area can know in advance whether the road is drivable without the need for on-site inspection.

[0091] Figure 6 Schematic diagram of the main modules of the road network data generating device according to an embodiment of the present invention. Figure 6 As shown, the road network data generating device 600 of the embodiment of the present invention mainly includes:

[0092] The track point screening module 601 is used to obtain historical track information and screen out track points within a set area from the historical track information. The historical track information refers to the track information formed by activities in a historical time period, such as the delivery track information of the delivery person, the movement track information of the user, etc. The set area range refers to the geographical range corresponding to the area where the road network needs to be obtained. The area can be a closed area or an open area, such as a residential area, a school, an industrial park, etc.

[0093] Taking the historical trajectory information as the delivery trajectory information as an example, the delivery personnel will send back the delivery trajectory information during the delivery process. The delivery trajectory information is formed by collecting the location coordinates of the delivery personnel in a certain period of time (i.e., the trajectory point coordinates, which are longitude and latitude coordinates), and then smoothly connecting the location coordinates in chronological order, which can characterize the movement behavior and movement direction of the delivery personnel in the time period. In the embodiment, the delivery trajectory information sent back by the delivery personnel can be obtained, and the existing map data, especially the AOI data, can be used to filter out the trajectory points within the set area.

[0094] The grid division module 602 is used to grid the area, count the number of track points belonging to the same grid, divide the multiple grids into empty grids and non-empty grids according to the number of track points, and determine the coordinate points of the non-empty grids. The delivery track information contains long-term track point coordinates. There is no time relationship between these track point coordinates, which makes the connection relationship between track points uncontrollable and makes it impossible to form road network data. Therefore, the entire area needs to be gridded.

[0095] In the embodiment, a grid is established on the entire area with a set side length to achieve rasterization of the area. Then, the number of track points contained in each grid (hereinafter referred to as the number of track points) is counted. If the number of track points in a grid is greater than the set number threshold, the grid is divided into a non-empty grid; if the number of track points in a grid is less than or equal to the set number threshold, the grid is divided into an empty grid.

[0096] The coordinate point is used to represent the coordinate of the non-empty grid. In the embodiment, a trajectory point coordinate can be selected from the coordinates of the trajectory points contained in the non-empty grid (hereinafter referred to as the trajectory point coordinate) as the coordinate point of the non-empty grid. In order to improve the accuracy, the trajectory points belonging to the same non-empty grid can also be clustered as a trajectory point group to obtain the center point of the non-empty grid, and the center point is used as the coordinate point of the non-empty grid.

[0097] The road network determination module 603 is used to select an initial starting grid from the non-empty grids, repeatedly perform the following steps until all the unconnected grids around the starting grid are empty grids, and connect multiple starting grids to obtain the road network data of the area:

[0098] Determine the adjacent non-empty grid of the starting grid, connect the coordinate points of the starting grid with the coordinate points of the adjacent non-empty grid to perform line clustering to obtain a line group, and update the starting grid according to the adjacent non-empty grids at the ends of the lines in the line group.

[0099] Before selecting the initial starting grid, it is necessary to first determine the area entrance. The trajectory points contained in the area entrance belong to the area entry points, and the grid containing the largest number of area entry points is used as the starting grid. In the embodiment, the location where the trajectory points and the AOI data intersect most densely is found as the area entrance. If there are multiple area entrances, one can be selected randomly. Then, it is determined whether the unconnected grids around the starting grid are all empty grids. If there are non-empty grids around the unconnected grids around the starting grid, it means that the road network collection is not completed; otherwise, it means that the road network collection is completed, and multiple starting grids are connected to obtain the road network data of the area.

[0100] If the road network collection is not completed, the coordinate point of the starting grid is connected with the coordinate point of the adjacent non-empty grid to obtain the connection between the two, and then the line clustering is performed to obtain the connection group. The grid at the end of any connection in the connection group (i.e. the other end of the connection) is used as the starting grid for the next time. This is repeated to form a connection relationship between the trajectory points, thereby establishing the road network data of the area.

[0101] In addition, the road network data generating device 600 of the embodiment of the present invention may further include: a type judgment module ( Figure 6 ), the module is used to map the points of interest within the area to the empty grid, calculate the first distance from the points of interest on both sides of the road in the road network data to the road; based on the first distance, filter out the points of interest closest to one side of the road and the points of interest closest to the other side of the road; calculate the second distance between the two filtered points of interest, and determine whether the first distance from the two filtered points of interest to the road and the second distance meet the set driving conditions; if the driving conditions are met, determine that the road is a vehicle road; if the driving conditions are not met, determine that the road is a pedestrian road.

[0102] From the above description, it can be seen that the device selects trajectory points within the set area from the delivery trajectory information, and rasterizes the area to divide the grid into empty grids and non-empty grids, then selects the initial starting grid, connects the starting grid and the surrounding adjacent non-empty grids, performs line clustering, and updates the starting grid. This is repeated to form a connection relationship between the trajectory points, thereby establishing the road network data of the area, solving the problem of missing road network data in a specific area.

[0103] Figure 7 An exemplary system architecture 700 is shown to which the road network data generating method or road network data generating device according to the embodiment of the present invention can be applied.

[0104] like Figure 7As shown, system architecture 700 may include terminal devices 701, 702, 703, network 704 and server 705. Network 704 is used to provide a medium for communication links between terminal devices 701, 702, 703 and server 705. Network 704 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0105] The user can use the terminal devices 701, 702, 703 to interact with the server 705 through the network 704 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 701, 702, 703. The terminal devices 701, 702, 703 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, etc.

[0106] The server 705 may be a server that provides various services, such as a background management server that processes the historical trajectory information sent by the administrator using the terminal devices 701, 702, and 703. The background management server may filter trajectory points, rasterize, divide empty grids and non-empty grids, determine road network data, and other processes from the historical trajectory information, and feed back the processing results (such as the generated road network data) to the terminal device.

[0107] It should be noted that the road network data generation method provided in the embodiment of the present application is generally executed by the server 705, and accordingly, the road network data generation device is generally set in the server 705.

[0108] It should be understood that Figure 7 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0109] According to an embodiment of the present invention, the present invention also provides an electronic device and a computer-readable medium.

[0110] The electronic device of the present invention comprises: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement a road network data generation method of an embodiment of the present invention.

[0111] The computer-readable medium of the present invention stores a computer program thereon, and when the program is executed by a processor, a method for generating road network data according to an embodiment of the present invention is implemented.

[0112] Reference below Figure 8 , which shows a schematic diagram of the structure of a computer system 800 suitable for implementing an electronic device of an embodiment of the present invention. Figure 8The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0113] like Figure 8 As shown, the computer system 800 includes a central processing unit (CPU) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage part 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the computer system 800 are also stored. The CPU 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0114] The following components are connected to the I / O interface 805: an input section 806 including a keyboard, a mouse, etc.; an output section 807 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN card, a modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 810 as needed, so that a computer program read therefrom is installed into the storage section 808 as needed.

[0115] In particular, according to the embodiments disclosed in the present invention, the process described in the main step diagram above can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the main step diagram. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 809, and / or installed from the removable medium 811. When the computer program is executed by the central processing unit (CPU) 801, the above-mentioned functions defined in the system of the present invention are executed.

[0116] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0117] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0118] The modules involved in the embodiments of the present invention may be implemented in software or hardware. The modules described may also be set in a processor. For example, they may be described as follows: a processor includes a trajectory point screening module, a grid division module, and a road network determination module. The names of these modules do not, in some cases, constitute limitations on the modules themselves. For example, the trajectory point screening module may also be described as a "module for obtaining historical trajectory information and screening out trajectory points within a set area from the historical trajectory information."

[0119] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The computer-readable medium carries one or more programs. When the one or more programs are executed by a device, the device includes: obtaining historical trajectory information, filtering out trajectory points within a set area from the historical trajectory information; rasterizing the area, counting the number of trajectory points belonging to the same grid, dividing multiple grids into empty grids and non-empty grids according to the number of trajectory points, and determining the coordinate points of the non-empty grids; selecting an initial starting grid from the non-empty grids, and repeatedly performing the following steps until all the unconnected grids around the starting grid are empty grids, connecting multiple starting grids to obtain road network data of the area: determining adjacent non-empty grids of the starting grid, connecting the coordinate points of the starting grid with the coordinate points of the adjacent non-empty grids to perform line clustering to obtain a line group, and updating the starting grid according to the adjacent non-empty grids at the ends of the lines in the line group.

[0120] According to the technical solution of the embodiment of the present invention, the trajectory points within the set area are screened out from the historical trajectory information, and the area is rasterized to divide the grid into empty grids and non-empty grids. Then, the initial starting grid is selected, the starting grid and the surrounding adjacent non-empty grids are connected, line clustering is performed, and the starting grid is updated. This is repeated to form a connection relationship between the trajectory points, thereby establishing the road network data of the area, solving the problem of missing road network data in a specific area.

[0121] The above product can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0122] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for generating road network data, characterized in that: include: Acquire historical trajectory information, and filter out trajectory points within a set area from the historical trajectory information; Rasterizing the area, counting the number of trajectory points belonging to the same grid, dividing the plurality of grids into empty grids and non-empty grids according to the number of trajectory points, and determining the coordinate points of the non-empty grids; An initial starting grid is selected from the non-empty grids, and the following steps are repeatedly performed until all the unconnected grids around the starting grid are empty grids, and a plurality of the starting grids are connected to obtain the road network data of the regional range: Determine the adjacent non-empty grid of the starting grid, connect the coordinate points of the starting grid with the coordinate points of the adjacent non-empty grid to perform line clustering to obtain a line group, and update the starting grid according to the adjacent non-empty grids at the ends of the lines in the line group.

2. The method according to claim 1, characterized in that The performing line clustering to obtain a line group includes: The angles between the lines are calculated, and the lines whose angles are less than a set angle threshold are classified into the same type of lines to form a line group.

3. The method according to claim 1, characterized in that The updating of the starting grid comprises: Determine an adjacent non-empty grid in the line group that is closest to the starting grid in the line direction, and update the nearest adjacent non-empty grid to the starting grid.

4. The method according to claim 1, characterized in that: The determining the coordinate points of the non-empty grid includes: The trajectory points belonging to the same non-empty grid are clustered as a trajectory point group to obtain the center point of the non-empty grid, and the center point is used as the coordinate point of the non-empty grid.

5. The method according to claim 1, characterized in that The method further comprises: Mapping the points of interest within the area to the empty grid, and calculating a first distance from the points of interest located on both sides of the road in the road network data to the road; According to the first distance, filter out the point of interest closest to one side of the road and the point of interest closest to the other side of the road; Calculating a second distance between the two selected points of interest, and determining whether the first distances from the two selected points of interest to the road and the second distances meet a set driving condition; If the driving condition is met, the road is determined to be a road for vehicles; if the driving condition is not met, the road is determined to be a road for pedestrians.

6. The method according to claim 5, characterized in that The driving condition is any one or more of the following: a first distance from the two selected points of interest to the road, and the second distance are both greater than a set first distance threshold; and The first distances from the two selected interest points to the road are less than a set second distance threshold, and the second distance is greater than a set third distance threshold.

7. The method according to claim 5, characterized in that The calculating the second distance between the two selected interest points includes: Count the number of non-empty grids in the direction of the line connecting the two selected interest points; The second distance between the two filtered interest points is calculated according to the number of non-empty grids and the grid side length.

8. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: Acquire delivery address information, segment the delivery address information, and obtain target address elements; According to the target address element, the corresponding area range is obtained from the map data.

9. A road network data generating device, characterized in that: include: A track point screening module is used to obtain historical track information and screen out track points within a set area from the historical track information; A grid division module, used for gridding the area range, counting the number of trajectory points belonging to the same grid, dividing the plurality of grids into empty grids and non-empty grids according to the number of trajectory points, and determining the coordinate points of the non-empty grids; A road network determination module is used to select an initial starting grid from the non-empty grids, repeatedly perform the following steps until all the unconnected grids around the starting grid are empty grids, connect multiple starting grids, and obtain road network data of the area: Determine the adjacent non-empty grid of the starting grid, connect the coordinate points of the starting grid with the coordinate points of the adjacent non-empty grid to perform line clustering to obtain a line group, and update the starting grid according to the adjacent non-empty grids at the ends of the lines in the line group.

10. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

11. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images